git/config.c

3568 lines
86 KiB
C
Raw Normal View History

/*
* GIT - The information manager from hell
*
* Copyright (C) Linus Torvalds, 2005
* Copyright (C) Johannes Schindelin, 2005
*
*/
#include "cache.h"
#include "branch.h"
#include "config.h"
#include "environment.h"
#include "repository.h"
#include "lockfile.h"
#include "exec-cmd.h"
#include "strbuf.h"
#include "quote.h"
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
#include "hashmap.h"
#include "string-list.h"
#include "object-store.h"
#include "utf8.h"
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
#include "dir.h"
#include "color.h"
#include "refs.h"
struct config_source {
struct config_source *prev;
union {
FILE *file;
struct config_buf {
const char *buf;
size_t len;
size_t pos;
} buf;
} u;
enum config_origin_type origin_type;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
const char *name;
const char *path;
enum config_error_action default_error_action;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
int linenr;
int eof;
config: reject parsing of files over INT_MAX While the last few commits have made it possible for the config parser to handle config files up to the limits of size_t, the rest of the code isn't really ready for this. In particular, we often feed the keys as strings into printf "%s" format specifiers. And because the printf family of functions must return an int to specify the result, they complain. Here are two concrete examples (using glibc; we're in uncharted territory here so results may vary): Generate a gigantic .gitmodules file like this: git submodule add /some/other/repo foo { printf '[submodule "' perl -e 'print "a" x 2**31' echo '"]path = foo' } >.gitmodules git commit -m 'huge gitmodule' then try this: $ git show BUG: strbuf.c:397: your vsnprintf is broken (returned -1) The problem is that we end up calling: strbuf_addf(&sb, "submodule.%s.ignore", submodule_name); which relies on vsnprintf(), and that function has no way to report back a size larger than INT_MAX. Taking that same file, try this: git config --file=.gitmodules --list --name-only On my system it produces an output with exactly 4GB of spaces. I confirmed in a debugger that we reach the config callback with the key intact: it's 2147483663 bytes and full of a's. But when we print it with this call: printf("%s%c", key_, term); we just get the spaces. So given the fact that these are insane cases which we have no need to support, the weird behavior from feeding the results to printf even if the code is careful, and the possibility of uncareful code introducing its own integer truncation issues, let's just declare INT_MAX as a limit for parsing config files. We'll enforce the limit in get_next_char(), which generalizes over all sources (blobs, files, etc) and covers any element we're parsing (whether section, key, value, etc). For simplicity, the limit is over the length of the _whole_ file, so you couldn't have two 1GB values in the same file. This should be perfectly fine, as the expected size for config files is generally kilobytes at most. With this patch both cases above will yield: fatal: bad config line 1 in file .gitmodules That's not an amazing error message, but the parser isn't set up to provide specific messages (it just breaks out of the parsing loop and gives that generic error even if see a syntactic issue). And we really wouldn't expect to see this case outside of somebody maliciously probing the limits of the config system. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-04-10 19:50:07 +00:00
size_t total_len;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
struct strbuf value;
struct strbuf var;
unsigned subsection_case_sensitive : 1;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
int (*do_fgetc)(struct config_source *c);
int (*do_ungetc)(int c, struct config_source *conf);
long (*do_ftell)(struct config_source *c);
};
/*
* These variables record the "current" config source, which
* can be accessed by parsing callbacks.
*
* The "cf" variable will be non-NULL only when we are actually parsing a real
* config source (file, blob, cmdline, etc).
*
* The "current_config_kvi" variable will be non-NULL only when we are feeding
* cached config from a configset into a callback.
*
* They should generally never be non-NULL at the same time. If they are both
* NULL, then we aren't parsing anything (and depending on the function looking
* at the variables, it's either a bug for it to be called in the first place,
* or it's a function which can be reused for non-config purposes, and should
* fall back to some sane behavior).
*/
static struct config_source *cf;
static struct key_value_info *current_config_kvi;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
/*
* Similar to the variables above, this gives access to the "scope" of the
* current value (repo, global, etc). For cached values, it can be found via
* the current_config_kvi as above. During parsing, the current value can be
* found in this variable. It's not part of "cf" because it transcends a single
* file (i.e., a file included from .git/config is still in "repo" scope).
*/
static enum config_scope current_parsing_scope;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
static int core_compression_seen;
static int pack_compression_seen;
Custom compression levels for objects and packs Add config variables pack.compression and core.loosecompression , and switch --compression=level to pack-objects. Loose objects will be compressed using core.loosecompression if set, else core.compression if set, else Z_BEST_SPEED. Packed objects will be compressed using --compression=level if seen, else pack.compression if set, else core.compression if set, else Z_DEFAULT_COMPRESSION. This is the "pack compression level". Loose objects added to a pack undeltified will be recompressed to the pack compression level if it is unequal to the current loose compression level by the preceding rules, or if the loose object was written while core.legacyheaders = true. Newly deltified loose objects are always compressed to the current pack compression level. Previously packed objects added to a pack are recompressed to the current pack compression level exactly when their deltification status changes, since the previous pack data cannot be reused. In either case, the --no-reuse-object switch from the first patch below will always force recompression to the current pack compression level, instead of assuming the pack compression level hasn't changed and pack data can be reused when possible. This applies on top of the following patches from Nicolas Pitre: [PATCH] allow for undeltified objects not to be reused [PATCH] make "repack -f" imply "pack-objects --no-reuse-object" Signed-off-by: Dana L. How <danahow@gmail.com> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-05-09 20:56:50 +00:00
static int zlib_compression_seen;
static int config_file_fgetc(struct config_source *conf)
{
return getc_unlocked(conf->u.file);
}
static int config_file_ungetc(int c, struct config_source *conf)
{
return ungetc(c, conf->u.file);
}
static long config_file_ftell(struct config_source *conf)
{
return ftell(conf->u.file);
}
static int config_buf_fgetc(struct config_source *conf)
{
if (conf->u.buf.pos < conf->u.buf.len)
return conf->u.buf.buf[conf->u.buf.pos++];
return EOF;
}
static int config_buf_ungetc(int c, struct config_source *conf)
{
if (conf->u.buf.pos > 0) {
conf->u.buf.pos--;
if (conf->u.buf.buf[conf->u.buf.pos] != c)
BUG("config_buf can only ungetc the same character");
return c;
}
return EOF;
}
static long config_buf_ftell(struct config_source *conf)
{
return conf->u.buf.pos;
}
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
#define MAX_INCLUDE_DEPTH 10
static const char include_depth_advice[] = N_(
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
"exceeded maximum include depth (%d) while including\n"
" %s\n"
"from\n"
" %s\n"
"This might be due to circular includes.");
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
static int handle_path_include(const char *path, struct config_include_data *inc)
{
int ret = 0;
struct strbuf buf = STRBUF_INIT;
char *expanded;
if (!path)
return config_error_nonbool("include.path");
expanded = expand_user_path(path, 0);
if (!expanded)
return error(_("could not expand include path '%s'"), path);
path = expanded;
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
/*
* Use an absolute path as-is, but interpret relative paths
* based on the including config file.
*/
if (!is_absolute_path(path)) {
char *slash;
if (!cf || !cf->path)
return error(_("relative config includes must come from files"));
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
slash = find_last_dir_sep(cf->path);
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
if (slash)
strbuf_add(&buf, cf->path, slash - cf->path + 1);
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
strbuf_addstr(&buf, path);
path = buf.buf;
}
config: allow inaccessible configuration under $HOME The changes v1.7.12.1~2^2~4 (config: warn on inaccessible files, 2012-08-21) and v1.8.1.1~22^2~2 (config: treat user and xdg config permission problems as errors, 2012-10-13) were intended to prevent important configuration (think "[transfer] fsckobjects") from being ignored when the configuration is unintentionally unreadable (for example with EIO on a flaky filesystem, or with ENOMEM due to a DoS attack). Usually ~/.gitconfig and ~/.config/git are readable by the current user, and if they aren't then it would be easy to fix those permissions, so the damage from adding this check should have been minimal. Unfortunately the access() check often trips when git is being run as a server. A daemon (such as inetd or git-daemon) starts as "root", creates a listening socket, and then drops privileges, meaning that when git commands are invoked they cannot access $HOME and die with fatal: unable to access '/root/.config/git/config': Permission denied Any patch to fix this would have one of three problems: 1. We annoy sysadmins who need to take an extra step to handle HOME when dropping privileges (the current behavior, or any other proposal that they have to opt into). 2. We annoy sysadmins who want to set HOME when dropping privileges, either by making what they want to do impossible, or making them set an extra variable or option to accomplish what used to work (e.g., a patch to git-daemon to set HOME when --user is passed). 3. We loosen the check, so some cases which might be noteworthy are not caught. This patch is of type (3). Treat user and xdg configuration that are inaccessible due to permissions (EACCES) as though no user configuration was provided at all. An alternative method would be to check if $HOME is readable, but that would not help in cases where the user who dropped privileges had a globally readable HOME with only .config or .gitconfig being private. This does not change the behavior when /etc/gitconfig or .git/config is unreadable (since those are more serious configuration errors), nor when ~/.gitconfig or ~/.config/git is unreadable due to problems other than permissions. Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-12 21:03:18 +00:00
if (!access_or_die(path, R_OK, 0)) {
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
if (++inc->depth > MAX_INCLUDE_DEPTH)
die(_(include_depth_advice), MAX_INCLUDE_DEPTH, path,
!cf ? "<unknown>" :
cf->name ? cf->name :
"the command line");
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
ret = git_config_from_file(git_config_include, path, inc);
inc->depth--;
}
strbuf_release(&buf);
free(expanded);
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
return ret;
}
static void add_trailing_starstar_for_dir(struct strbuf *pat)
{
if (pat->len && is_dir_sep(pat->buf[pat->len - 1]))
strbuf_addstr(pat, "**");
}
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
static int prepare_include_condition_pattern(struct strbuf *pat)
{
struct strbuf path = STRBUF_INIT;
char *expanded;
int prefix = 0;
expanded = expand_user_path(pat->buf, 1);
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
if (expanded) {
strbuf_reset(pat);
strbuf_addstr(pat, expanded);
free(expanded);
}
if (pat->buf[0] == '.' && is_dir_sep(pat->buf[1])) {
const char *slash;
if (!cf || !cf->path)
return error(_("relative config include "
"conditionals must come from files"));
strbuf_realpath(&path, cf->path, 1);
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
slash = find_last_dir_sep(path.buf);
if (!slash)
BUG("how is this possible?");
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
strbuf_splice(pat, 0, 1, path.buf, slash - path.buf);
prefix = slash - path.buf + 1 /* slash */;
} else if (!is_absolute_path(pat->buf))
strbuf_insertstr(pat, 0, "**/");
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
add_trailing_starstar_for_dir(pat);
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
strbuf_release(&path);
return prefix;
}
static int include_by_gitdir(const struct config_options *opts,
const char *cond, size_t cond_len, int icase)
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
{
struct strbuf text = STRBUF_INIT;
struct strbuf pattern = STRBUF_INIT;
int ret = 0, prefix;
const char *git_dir;
int already_tried_absolute = 0;
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
if (opts->git_dir)
git_dir = opts->git_dir;
else
goto done;
strbuf_realpath(&text, git_dir, 1);
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
strbuf_add(&pattern, cond, cond_len);
prefix = prepare_include_condition_pattern(&pattern);
again:
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
if (prefix < 0)
goto done;
if (prefix > 0) {
/*
* perform literal matching on the prefix part so that
* any wildcard character in it can't create side effects.
*/
if (text.len < prefix)
goto done;
if (!icase && strncmp(pattern.buf, text.buf, prefix))
goto done;
if (icase && strncasecmp(pattern.buf, text.buf, prefix))
goto done;
}
ret = !wildmatch(pattern.buf + prefix, text.buf + prefix,
WM_PATHNAME | (icase ? WM_CASEFOLD : 0));
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
if (!ret && !already_tried_absolute) {
/*
* We've tried e.g. matching gitdir:~/work, but if
* ~/work is a symlink to /mnt/storage/work
* strbuf_realpath() will expand it, so the rule won't
* match. Let's match against a
* strbuf_add_absolute_path() version of the path,
* which'll do the right thing
*/
strbuf_reset(&text);
strbuf_add_absolute_path(&text, git_dir);
already_tried_absolute = 1;
goto again;
}
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
done:
strbuf_release(&pattern);
strbuf_release(&text);
return ret;
}
static int include_by_branch(const char *cond, size_t cond_len)
{
int flags;
int ret;
struct strbuf pattern = STRBUF_INIT;
const char *refname = !the_repository->gitdir ?
config: work around bug with includeif:onbranch and early config Since 07b2c0eacac (config: learn the "onbranch:" includeIf condition, 2019-06-05), there is a potential catch-22 in the early config path: if the `include.onbranch:` feature is used, Git assumes that the Git directory has been initialized already. However, in the early config code path that is not true. One way to trigger this is to call the following commands in any repository: git config includeif.onbranch:refs/heads/master.path broken git help -a The symptom triggered by the `git help -a` invocation reads like this: BUG: refs.c:1851: attempting to get main_ref_store outside of repository Let's work around this, simply by ignoring the `includeif.onbranch:` setting when parsing the config when the ref store has not been initialized (yet). Technically, there is a way to solve this properly: teach the refs machinery to initialize the ref_store from a given gitdir/commondir pair (which we _do_ have in the early config code path), and then use that in `include_by_branch()`. This, however, is a pretty involved project, and we're already in the feature freeze for Git v2.23.0. Note: when calling above-mentioned two commands _outside_ of any Git worktree (passing the `--global` flag to `git config`, as there is obviously no repository config available), at the point when `include_by_branch()` is called, `the_repository` is `NULL`, therefore we have to be extra careful not to dereference it in that case. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-07-31 20:06:42 +00:00
NULL : resolve_ref_unsafe("HEAD", 0, NULL, &flags);
const char *shortname;
if (!refname || !(flags & REF_ISSYMREF) ||
!skip_prefix(refname, "refs/heads/", &shortname))
return 0;
strbuf_add(&pattern, cond, cond_len);
add_trailing_starstar_for_dir(&pattern);
ret = !wildmatch(pattern.buf, shortname, WM_PATHNAME);
strbuf_release(&pattern);
return ret;
}
static int include_condition_is_true(const struct config_options *opts,
const char *cond, size_t cond_len)
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
{
if (skip_prefix_mem(cond, cond_len, "gitdir:", &cond, &cond_len))
return include_by_gitdir(opts, cond, cond_len, 0);
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
else if (skip_prefix_mem(cond, cond_len, "gitdir/i:", &cond, &cond_len))
return include_by_gitdir(opts, cond, cond_len, 1);
else if (skip_prefix_mem(cond, cond_len, "onbranch:", &cond, &cond_len))
return include_by_branch(cond, cond_len);
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
/* unknown conditionals are always false */
return 0;
}
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
int git_config_include(const char *var, const char *value, void *data)
{
struct config_include_data *inc = data;
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
const char *cond, *key;
size_t cond_len;
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
int ret;
/*
* Pass along all values, including "include" directives; this makes it
* possible to query information on the includes themselves.
*/
ret = inc->fn(var, value, inc->data);
if (ret < 0)
return ret;
if (!strcmp(var, "include.path"))
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
ret = handle_path_include(value, inc);
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
if (!parse_config_key(var, "includeif", &cond, &cond_len, &key) &&
(cond && include_condition_is_true(inc->opts, cond, cond_len)) &&
config: add conditional include Sometimes a set of repositories want to share configuration settings among themselves that are distinct from other such sets of repositories. A user may work on two projects, each of which have multiple repositories, and use one user.email for one project while using another for the other. Setting $GIT_DIR/.config works, but if the penalty of forgetting to update $GIT_DIR/.config is high (especially when you end up cloning often), it may not be the best way to go. Having the settings in ~/.gitconfig, which would work for just one set of repositories, would not well in such a situation. Having separate ${HOME}s may add more problems than it solves. Extend the include.path mechanism that lets a config file include another config file, so that the inclusion can be done only when some conditions hold. Then ~/.gitconfig can say "include config-project-A only when working on project-A" for each project A the user works on. In this patch, the only supported grouping is based on $GIT_DIR (in absolute path), so you would need to group repositories by directory, or something like that to take advantage of it. We already have include.path for unconditional includes. This patch goes with includeIf.<condition>.path to make it clearer that a condition is required. The new config has the same backward compatibility approach as include.path: older git versions that don't understand includeIf will simply ignore them. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-01 11:26:31 +00:00
!strcmp(key, "path"))
ret = handle_path_include(value, inc);
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
return ret;
}
static void git_config_push_split_parameter(const char *key, const char *value)
{
struct strbuf env = STRBUF_INIT;
const char *old = getenv(CONFIG_DATA_ENVIRONMENT);
git_config_push_parameter: handle empty GIT_CONFIG_PARAMETERS The "git -c var=value" option stuffs the config value into $GIT_CONFIG_PARAMETERS, so that sub-processes can see it. When the config is later read via git_config() or similar, we parse it back out of that variable. The parsing end is a little bit picky; it assumes that each entry was generated with sq_quote_buf(), and that there is no extraneous whitespace. On the generating end, we are careful to append to an existing $GIT_CONFIG_PARAMETERS variable if it exists. However, our test for "should we add a space separator" is too liberal: it will add one even if the environment variable exists but is empty. As a result, you might end up with: GIT_CONFIG_PARAMETERS=" 'core.foo=bar'" which the parser will choke on. This was hard to trigger in older versions of git, since we only set the variable when we had something to put into it (though you could certainly trigger it manually). But since 14111fc (git: submodule honor -c credential.* from command line, 2016-02-29), the submodule code will unconditionally put the $GIT_CONFIG_PARAMETERS variable into the environment of any operation in the submodule, whether it is empty or not. So any of those operations which themselves use "git -c" will generate the unparseable value and fail. We can easily fix it by catching this case on the generating side. While we're adding a test, let's also check that multiple layers of "git -c" work, which was previously not tested at all. Reported-by: Shin Fan <shinfan@google.com> Signed-off-by: Jeff King <peff@peff.net> Reviewed-by: Jonathan Nieder <jrnieder@gmail.com> Tested-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-03-22 19:50:51 +00:00
if (old && *old) {
strbuf_addstr(&env, old);
strbuf_addch(&env, ' ');
}
sq_quote_buf(&env, key);
strbuf_addch(&env, '=');
if (value)
sq_quote_buf(&env, value);
setenv(CONFIG_DATA_ENVIRONMENT, env.buf, 1);
strbuf_release(&env);
}
void git_config_push_parameter(const char *text)
{
const char *value;
/*
* When we see:
*
* section.subsection=with=equals.key=value
*
* we cannot tell if it means:
*
* [section "subsection=with=equals"]
* key = value
*
* or:
*
* [section]
* subsection = with=equals.key=value
*
* We parse left-to-right for the first "=", meaning we'll prefer to
* keep the value intact over the subsection. This is historical, but
* also sensible since values are more likely to contain odd or
* untrusted input than a section name.
*
* A missing equals is explicitly allowed (as a bool-only entry).
*/
value = strchr(text, '=');
if (value) {
char *key = xmemdupz(text, value - text);
git_config_push_split_parameter(key, value + 1);
free(key);
} else {
git_config_push_split_parameter(text, NULL);
}
}
void git_config_push_env(const char *spec)
{
char *key;
const char *env_name;
const char *env_value;
env_name = strrchr(spec, '=');
if (!env_name)
die(_("invalid config format: %s"), spec);
key = xmemdupz(spec, env_name - spec);
env_name++;
if (!*env_name)
die(_("missing environment variable name for configuration '%.*s'"),
(int)(env_name - spec - 1), spec);
env_value = getenv(env_name);
if (!env_value)
die(_("missing environment variable '%s' for configuration '%.*s'"),
env_name, (int)(env_name - spec - 1), spec);
git_config_push_split_parameter(key, env_value);
free(key);
}
static inline int iskeychar(int c)
{
return isalnum(c) || c == '-';
}
/*
* Auxiliary function to sanity-check and split the key into the section
* identifier and variable name.
*
* Returns 0 on success, -1 when there is an invalid character in the key and
* -2 if there is no section name in the key.
*
* store_key - pointer to char* which will hold a copy of the key with
* lowercase section and variable name
* baselen - pointer to size_t which will hold the length of the
* section + subsection part, can be NULL
*/
static int git_config_parse_key_1(const char *key, char **store_key, size_t *baselen_, int quiet)
{
size_t i, baselen;
int dot;
const char *last_dot = strrchr(key, '.');
/*
* Since "key" actually contains the section name and the real
* key name separated by a dot, we have to know where the dot is.
*/
if (last_dot == NULL || last_dot == key) {
if (!quiet)
error(_("key does not contain a section: %s"), key);
return -CONFIG_NO_SECTION_OR_NAME;
}
if (!last_dot[1]) {
if (!quiet)
error(_("key does not contain variable name: %s"), key);
return -CONFIG_NO_SECTION_OR_NAME;
}
baselen = last_dot - key;
if (baselen_)
*baselen_ = baselen;
/*
* Validate the key and while at it, lower case it for matching.
*/
if (store_key)
*store_key = xmallocz(strlen(key));
dot = 0;
for (i = 0; key[i]; i++) {
unsigned char c = key[i];
if (c == '.')
dot = 1;
/* Leave the extended basename untouched.. */
if (!dot || i > baselen) {
if (!iskeychar(c) ||
(i == baselen + 1 && !isalpha(c))) {
if (!quiet)
error(_("invalid key: %s"), key);
goto out_free_ret_1;
}
c = tolower(c);
} else if (c == '\n') {
if (!quiet)
error(_("invalid key (newline): %s"), key);
goto out_free_ret_1;
}
if (store_key)
(*store_key)[i] = c;
}
return 0;
out_free_ret_1:
if (store_key) {
FREE_AND_NULL(*store_key);
}
return -CONFIG_INVALID_KEY;
}
int git_config_parse_key(const char *key, char **store_key, size_t *baselen)
{
return git_config_parse_key_1(key, store_key, baselen, 0);
}
int git_config_key_is_valid(const char *key)
{
return !git_config_parse_key_1(key, NULL, NULL, 1);
}
static int config_parse_pair(const char *key, const char *value,
config_fn_t fn, void *data)
{
char *canonical_name;
int ret;
if (!strlen(key))
return error(_("empty config key"));
if (git_config_parse_key(key, &canonical_name, NULL))
return -1;
ret = (fn(canonical_name, value, data) < 0) ? -1 : 0;
free(canonical_name);
return ret;
}
int git_config_parse_parameter(const char *text,
config_fn_t fn, void *data)
{
const char *value;
struct strbuf **pair;
int ret;
pair = strbuf_split_str(text, '=', 2);
if (!pair[0])
return error(_("bogus config parameter: %s"), text);
if (pair[0]->len && pair[0]->buf[pair[0]->len - 1] == '=') {
strbuf_setlen(pair[0], pair[0]->len - 1);
value = pair[1] ? pair[1]->buf : "";
} else {
value = NULL;
}
strbuf_trim(pair[0]);
if (!pair[0]->len) {
strbuf_list_free(pair);
return error(_("bogus config parameter: %s"), text);
}
ret = config_parse_pair(pair[0]->buf, value, fn, data);
strbuf_list_free(pair);
return ret;
}
config: parse more robust format in GIT_CONFIG_PARAMETERS When we stuff config options into GIT_CONFIG_PARAMETERS, we shell-quote each one as a single unit, like: 'section.one=value1' 'section.two=value2' On the reading side, we de-quote to get the individual strings, and then parse them by splitting on the first "=" we find. This format is ambiguous, because an "=" may appear in a subsection. So the config represented in a file by both: [section "subsection=with=equals"] key = value and: [section] subsection = with=equals.key=value ends up in this flattened format like: 'section.subsection=with=equals.key=value' and we can't tell which was desired. We have traditionally resolved this by taking the first "=" we see starting from the left, meaning that we allowed arbitrary content in the value, but not in the subsection. Let's make our environment format a bit more robust by separately quoting the key and value. That turns those examples into: 'section.subsection=with=equals.key'='value' and: 'section.subsection'='with=equals.key=value' respectively, and we can tell the difference between them. We can detect which format is in use for any given element of the list based on the presence of the unquoted "=". That means we can continue to allow the old format to work to support any callers which manually used the old format, and we can even intermingle the two formats. The old format wasn't documented, and nobody was supposed to be using it. But it's likely that such callers exist in the wild, so it's nice if we can avoid breaking them. Likewise, it may be possible to trigger an older version of "git -c" that runs a script that calls into a newer version of "git -c"; that new version would see the intermingled format. This does create one complication, which is that the obvious format in the new scheme for [section] some-bool is: 'section.some-bool' with no equals. We'd mistake that for an old-style variable. And it even has the same meaning in the old style, but: [section "with=equals"] some-bool does not. It would be: 'section.with=equals=some-bool' which we'd take to mean: [section] with = equals=some-bool in the old, ambiguous style. Likewise, we can't use: 'section.some-bool'='' because that's ambiguous with an actual empty string. Instead, we'll again use the shell-quoting to give us a hint, and use: 'section.some-bool'= to show that we have no value. Note that this commit just expands the reading side. We'll start writing the new format via "git -c" in a future patch. In the meantime, the existing "git -c" tests will make sure we didn't break reading the old format. But we'll also add some explicit coverage of the two formats to make sure we continue to handle the old one after we move the writing side over. And one final note: since we're now using the shell-quoting as a semantically meaningful hint, this closes the door to us ever allowing arbitrary shell quoting, like: 'a'shell'would'be'ok'with'this'.key=value But we have never supported that (only what sq_quote() would produce), and we are probably better off keeping things simple, robust, and backwards-compatible, than trying to make it easier for humans. We'll continue not to advertise the format of the variable to users, and instead keep "git -c" as the recommended mechanism for setting config (even if we are trying to be kind not to break users who may be relying on the current undocumented format). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-12 12:27:06 +00:00
static int parse_config_env_list(char *env, config_fn_t fn, void *data)
{
char *cur = env;
while (cur && *cur) {
const char *key = sq_dequote_step(cur, &cur);
if (!key)
return error(_("bogus format in %s"),
CONFIG_DATA_ENVIRONMENT);
if (!cur || isspace(*cur)) {
/* old-style 'key=value' */
if (git_config_parse_parameter(key, fn, data) < 0)
return -1;
}
else if (*cur == '=') {
/* new-style 'key'='value' */
const char *value;
cur++;
if (*cur == '\'') {
/* quoted value */
value = sq_dequote_step(cur, &cur);
if (!value || (cur && !isspace(*cur))) {
return error(_("bogus format in %s"),
CONFIG_DATA_ENVIRONMENT);
}
} else if (!*cur || isspace(*cur)) {
/* implicit bool: 'key'= */
value = NULL;
} else {
return error(_("bogus format in %s"),
CONFIG_DATA_ENVIRONMENT);
}
if (config_parse_pair(key, value, fn, data) < 0)
return -1;
}
else {
/* unknown format */
return error(_("bogus format in %s"),
CONFIG_DATA_ENVIRONMENT);
}
if (cur) {
while (isspace(*cur))
cur++;
}
}
return 0;
}
int git_config_from_parameters(config_fn_t fn, void *data)
{
const char *env;
struct strbuf envvar = STRBUF_INIT;
struct strvec to_free = STRVEC_INIT;
int ret = 0;
char *envw = NULL;
struct config_source source;
memset(&source, 0, sizeof(source));
source.prev = cf;
source.origin_type = CONFIG_ORIGIN_CMDLINE;
cf = &source;
env = getenv(CONFIG_COUNT_ENVIRONMENT);
if (env) {
unsigned long count;
char *endp;
int i;
count = strtoul(env, &endp, 10);
if (*endp) {
ret = error(_("bogus count in %s"), CONFIG_COUNT_ENVIRONMENT);
goto out;
}
if (count > INT_MAX) {
ret = error(_("too many entries in %s"), CONFIG_COUNT_ENVIRONMENT);
goto out;
}
for (i = 0; i < count; i++) {
const char *key, *value;
strbuf_addf(&envvar, "GIT_CONFIG_KEY_%d", i);
key = getenv_safe(&to_free, envvar.buf);
if (!key) {
ret = error(_("missing config key %s"), envvar.buf);
goto out;
}
strbuf_reset(&envvar);
strbuf_addf(&envvar, "GIT_CONFIG_VALUE_%d", i);
value = getenv_safe(&to_free, envvar.buf);
if (!value) {
ret = error(_("missing config value %s"), envvar.buf);
goto out;
}
strbuf_reset(&envvar);
if (config_parse_pair(key, value, fn, data) < 0) {
ret = -1;
goto out;
}
}
}
env = getenv(CONFIG_DATA_ENVIRONMENT);
if (env) {
/* sq_dequote will write over it */
envw = xstrdup(env);
if (parse_config_env_list(envw, fn, data) < 0) {
ret = -1;
goto out;
}
}
out:
strbuf_release(&envvar);
strvec_clear(&to_free);
free(envw);
cf = source.prev;
return ret;
}
static int get_next_char(void)
{
int c = cf->do_fgetc(cf);
if (c == '\r') {
/* DOS like systems */
c = cf->do_fgetc(cf);
if (c != '\n') {
if (c != EOF)
cf->do_ungetc(c, cf);
c = '\r';
}
}
config: reject parsing of files over INT_MAX While the last few commits have made it possible for the config parser to handle config files up to the limits of size_t, the rest of the code isn't really ready for this. In particular, we often feed the keys as strings into printf "%s" format specifiers. And because the printf family of functions must return an int to specify the result, they complain. Here are two concrete examples (using glibc; we're in uncharted territory here so results may vary): Generate a gigantic .gitmodules file like this: git submodule add /some/other/repo foo { printf '[submodule "' perl -e 'print "a" x 2**31' echo '"]path = foo' } >.gitmodules git commit -m 'huge gitmodule' then try this: $ git show BUG: strbuf.c:397: your vsnprintf is broken (returned -1) The problem is that we end up calling: strbuf_addf(&sb, "submodule.%s.ignore", submodule_name); which relies on vsnprintf(), and that function has no way to report back a size larger than INT_MAX. Taking that same file, try this: git config --file=.gitmodules --list --name-only On my system it produces an output with exactly 4GB of spaces. I confirmed in a debugger that we reach the config callback with the key intact: it's 2147483663 bytes and full of a's. But when we print it with this call: printf("%s%c", key_, term); we just get the spaces. So given the fact that these are insane cases which we have no need to support, the weird behavior from feeding the results to printf even if the code is careful, and the possibility of uncareful code introducing its own integer truncation issues, let's just declare INT_MAX as a limit for parsing config files. We'll enforce the limit in get_next_char(), which generalizes over all sources (blobs, files, etc) and covers any element we're parsing (whether section, key, value, etc). For simplicity, the limit is over the length of the _whole_ file, so you couldn't have two 1GB values in the same file. This should be perfectly fine, as the expected size for config files is generally kilobytes at most. With this patch both cases above will yield: fatal: bad config line 1 in file .gitmodules That's not an amazing error message, but the parser isn't set up to provide specific messages (it just breaks out of the parsing loop and gives that generic error even if see a syntactic issue). And we really wouldn't expect to see this case outside of somebody maliciously probing the limits of the config system. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-04-10 19:50:07 +00:00
if (c != EOF && ++cf->total_len > INT_MAX) {
/*
* This is an absurdly long config file; refuse to parse
* further in order to protect downstream code from integer
* overflows. Note that we can't return an error specifically,
* but we can mark EOF and put trash in the return value,
* which will trigger a parse error.
*/
cf->eof = 1;
return 0;
}
if (c == '\n')
cf->linenr++;
if (c == EOF) {
cf->eof = 1;
cf->linenr++;
c = '\n';
}
return c;
}
static char *parse_value(void)
{
int quote = 0, comment = 0, space = 0;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
strbuf_reset(&cf->value);
for (;;) {
int c = get_next_char();
if (c == '\n') {
if (quote) {
cf->linenr--;
return NULL;
}
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
return cf->value.buf;
}
if (comment)
continue;
if (isspace(c) && !quote) {
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
if (cf->value.len)
space++;
continue;
}
if (!quote) {
if (c == ';' || c == '#') {
comment = 1;
continue;
}
}
for (; space; space--)
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
strbuf_addch(&cf->value, ' ');
if (c == '\\') {
c = get_next_char();
switch (c) {
case '\n':
continue;
case 't':
c = '\t';
break;
case 'b':
c = '\b';
break;
case 'n':
c = '\n';
break;
/* Some characters escape as themselves */
case '\\': case '"':
break;
/* Reject unknown escape sequences */
default:
return NULL;
}
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
strbuf_addch(&cf->value, c);
continue;
}
if (c == '"') {
quote = 1-quote;
continue;
}
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
strbuf_addch(&cf->value, c);
}
}
static int get_value(config_fn_t fn, void *data, struct strbuf *name)
{
int c;
char *value;
int ret;
/* Get the full name */
for (;;) {
c = get_next_char();
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
if (cf->eof)
break;
if (!iskeychar(c))
break;
strbuf_addch(name, tolower(c));
}
while (c == ' ' || c == '\t')
c = get_next_char();
value = NULL;
if (c != '\n') {
if (c != '=')
return -1;
value = parse_value();
if (!value)
return -1;
}
/*
* We already consumed the \n, but we need linenr to point to
* the line we just parsed during the call to fn to get
* accurate line number in error messages.
*/
cf->linenr--;
ret = fn(name->buf, value, data);
if (ret >= 0)
cf->linenr++;
return ret;
}
static int get_extended_base_var(struct strbuf *name, int c)
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
{
cf->subsection_case_sensitive = 0;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
do {
if (c == '\n')
goto error_incomplete_line;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
c = get_next_char();
} while (isspace(c));
/* We require the format to be '[base "extension"]' */
if (c != '"')
return -1;
strbuf_addch(name, '.');
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
for (;;) {
int c = get_next_char();
if (c == '\n')
goto error_incomplete_line;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
if (c == '"')
break;
if (c == '\\') {
c = get_next_char();
if (c == '\n')
goto error_incomplete_line;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
}
strbuf_addch(name, c);
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
}
/* Final ']' */
if (get_next_char() != ']')
return -1;
return 0;
error_incomplete_line:
cf->linenr--;
return -1;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
}
static int get_base_var(struct strbuf *name)
{
cf->subsection_case_sensitive = 1;
for (;;) {
int c = get_next_char();
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
if (cf->eof)
return -1;
if (c == ']')
return 0;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
if (isspace(c))
return get_extended_base_var(name, c);
if (!iskeychar(c) && c != '.')
return -1;
strbuf_addch(name, tolower(c));
}
}
struct parse_event_data {
enum config_event_t previous_type;
size_t previous_offset;
const struct config_options *opts;
};
static int do_event(enum config_event_t type, struct parse_event_data *data)
{
size_t offset;
if (!data->opts || !data->opts->event_fn)
return 0;
if (type == CONFIG_EVENT_WHITESPACE &&
data->previous_type == type)
return 0;
offset = cf->do_ftell(cf);
/*
* At EOF, the parser always "inserts" an extra '\n', therefore
* the end offset of the event is the current file position, otherwise
* we will already have advanced to the next event.
*/
if (type != CONFIG_EVENT_EOF)
offset--;
if (data->previous_type != CONFIG_EVENT_EOF &&
data->opts->event_fn(data->previous_type, data->previous_offset,
offset, data->opts->event_fn_data) < 0)
return -1;
data->previous_type = type;
data->previous_offset = offset;
return 0;
}
static int git_parse_source(config_fn_t fn, void *data,
const struct config_options *opts)
{
int comment = 0;
config: use size_t to store parsed variable baselen Most of the config parsing infrastructure is limited in what it can parse only by the size of memory, because it parses character by character, building up strbufs for keys, values, etc. One exception is the "baselen" value we keep in git_parse_source(), which is an int. That stores the length of the section.subsection base, to which we can then append individual key names (by truncating back to the baselen with strbuf_setlen(), and then appending characters for the key name). But because it's an int, if we see an absurdly long section or subsection, we may overflow the integer, wrapping negative. That negative value is then implicitly cast to a size_t when we pass it to strbuf_setlen(), creating a very large value and triggering a BUG. For example: $ { printf '[foo "' perl -e 'print "a" x 2**31' echo '"]bar = value' } >huge $ git config --file=huge --list fatal: BUG: strbuf_setlen() beyond buffer While this is obviously a silly case that we don't care about supporting, it's worth fixing it by switching to a size_t for a few reasons: - we should try to avoid hitting BUG assertions at all - avoiding integer truncation or overflow sets a good example and makes it easier to audit the code for more important issues - the BUG outcome is what happens in _this_ instance, because we wrap negative. If we used a 2**32 subsection, we'd wrap to a small positive value and actually generate wrong output (the subsection of our key would be truncated). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-04-10 19:47:51 +00:00
size_t baselen = 0;
struct strbuf *var = &cf->var;
int error_return = 0;
char *error_msg = NULL;
/* U+FEFF Byte Order Mark in UTF8 */
const char *bomptr = utf8_bom;
/* For the parser event callback */
struct parse_event_data event_data = {
CONFIG_EVENT_EOF, 0, opts
};
for (;;) {
int c;
c = get_next_char();
if (bomptr && *bomptr) {
/* We are at the file beginning; skip UTF8-encoded BOM
* if present. Sane editors won't put this in on their
* own, but e.g. Windows Notepad will do it happily. */
if (c == (*bomptr & 0377)) {
bomptr++;
continue;
} else {
/* Do not tolerate partial BOM. */
if (bomptr != utf8_bom)
break;
/* No BOM at file beginning. Cool. */
bomptr = NULL;
}
}
if (c == '\n') {
if (cf->eof) {
if (do_event(CONFIG_EVENT_EOF, &event_data) < 0)
return -1;
return 0;
}
if (do_event(CONFIG_EVENT_WHITESPACE, &event_data) < 0)
return -1;
comment = 0;
continue;
}
if (comment)
continue;
if (isspace(c)) {
if (do_event(CONFIG_EVENT_WHITESPACE, &event_data) < 0)
return -1;
continue;
}
if (c == '#' || c == ';') {
if (do_event(CONFIG_EVENT_COMMENT, &event_data) < 0)
return -1;
comment = 1;
continue;
}
if (c == '[') {
if (do_event(CONFIG_EVENT_SECTION, &event_data) < 0)
return -1;
/* Reset prior to determining a new stem */
strbuf_reset(var);
if (get_base_var(var) < 0 || var->len < 1)
break;
strbuf_addch(var, '.');
baselen = var->len;
continue;
}
if (!isalpha(c))
break;
if (do_event(CONFIG_EVENT_ENTRY, &event_data) < 0)
return -1;
/*
* Truncate the var name back to the section header
* stem prior to grabbing the suffix part of the name
* and the value.
*/
strbuf_setlen(var, baselen);
strbuf_addch(var, tolower(c));
if (get_value(fn, data, var) < 0)
break;
}
if (do_event(CONFIG_EVENT_ERROR, &event_data) < 0)
return -1;
switch (cf->origin_type) {
case CONFIG_ORIGIN_BLOB:
error_msg = xstrfmt(_("bad config line %d in blob %s"),
cf->linenr, cf->name);
break;
case CONFIG_ORIGIN_FILE:
error_msg = xstrfmt(_("bad config line %d in file %s"),
cf->linenr, cf->name);
break;
case CONFIG_ORIGIN_STDIN:
error_msg = xstrfmt(_("bad config line %d in standard input"),
cf->linenr);
break;
case CONFIG_ORIGIN_SUBMODULE_BLOB:
error_msg = xstrfmt(_("bad config line %d in submodule-blob %s"),
cf->linenr, cf->name);
break;
case CONFIG_ORIGIN_CMDLINE:
error_msg = xstrfmt(_("bad config line %d in command line %s"),
cf->linenr, cf->name);
break;
default:
error_msg = xstrfmt(_("bad config line %d in %s"),
cf->linenr, cf->name);
}
switch (opts && opts->error_action ?
opts->error_action :
cf->default_error_action) {
case CONFIG_ERROR_DIE:
die("%s", error_msg);
break;
case CONFIG_ERROR_ERROR:
error_return = error("%s", error_msg);
break;
case CONFIG_ERROR_SILENT:
error_return = -1;
break;
case CONFIG_ERROR_UNSET:
BUG("config error action unset");
}
free(error_msg);
return error_return;
}
static uintmax_t get_unit_factor(const char *end)
{
if (!*end)
return 1;
else if (!strcasecmp(end, "k"))
return 1024;
else if (!strcasecmp(end, "m"))
return 1024 * 1024;
else if (!strcasecmp(end, "g"))
return 1024 * 1024 * 1024;
return 0;
}
static int git_parse_signed(const char *value, intmax_t *ret, intmax_t max)
{
if (value && *value) {
char *end;
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
intmax_t val;
uintmax_t uval;
uintmax_t factor;
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
errno = 0;
val = strtoimax(value, &end, 0);
if (errno == ERANGE)
return 0;
factor = get_unit_factor(end);
if (!factor) {
errno = EINVAL;
return 0;
}
uval = val < 0 ? -val : val;
if (unsigned_mult_overflows(factor, uval) ||
factor * uval > max) {
errno = ERANGE;
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
return 0;
}
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
val *= factor;
*ret = val;
return 1;
}
errno = EINVAL;
return 0;
}
static int git_parse_unsigned(const char *value, uintmax_t *ret, uintmax_t max)
{
if (value && *value) {
char *end;
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
uintmax_t val;
uintmax_t factor;
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
errno = 0;
val = strtoumax(value, &end, 0);
if (errno == ERANGE)
return 0;
factor = get_unit_factor(end);
if (!factor) {
errno = EINVAL;
return 0;
}
if (unsigned_mult_overflows(factor, val) ||
factor * val > max) {
errno = ERANGE;
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
return 0;
}
val *= factor;
*ret = val;
return 1;
}
errno = EINVAL;
return 0;
}
static int git_parse_int(const char *value, int *ret)
{
intmax_t tmp;
if (!git_parse_signed(value, &tmp, maximum_signed_value_of_type(int)))
return 0;
*ret = tmp;
return 1;
}
git-config: always treat --int as 64-bit internally When you run "git config --int", the maximum size of integer you get depends on how git was compiled, and what it considers to be an "int". This is almost useful, because your scripts calling "git config" will behave similarly to git internally. But relying on this is dubious; you have to actually know how git treats each value internally (e.g., int versus unsigned long), which is not documented and is subject to change. And even if you know it is "unsigned long", we do not have a git-config option to match that behavior. Furthermore, you may simply be asking git to store a value on your behalf (e.g., configuration for a hook). In that case, the relevant range check has nothing at all to do with git, but rather with whatever scripting tools you are using (and git has no way of knowing what the appropriate range is there). Not only is the range check useless, but it is actively harmful, as there is no way at all for scripts to look at config variables with large values. For instance, one cannot reliably get the value of pack.packSizeLimit via git-config. On an LP64 system, git happily uses a 64-bit "unsigned long" internally to represent the value, but the script cannot read any value over 2G. Ideally, the "--int" option would simply represent an arbitrarily large integer. For practical purposes, however, a 64-bit integer is large enough, and is much easier to implement (and if somebody overflows it, we will still notice the problem, and not simply return garbage). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-09-08 08:40:02 +00:00
static int git_parse_int64(const char *value, int64_t *ret)
{
intmax_t tmp;
if (!git_parse_signed(value, &tmp, maximum_signed_value_of_type(int64_t)))
return 0;
*ret = tmp;
return 1;
}
int git_parse_ulong(const char *value, unsigned long *ret)
{
uintmax_t tmp;
if (!git_parse_unsigned(value, &tmp, maximum_unsigned_value_of_type(long)))
return 0;
*ret = tmp;
return 1;
}
int git_parse_ssize_t(const char *value, ssize_t *ret)
{
intmax_t tmp;
if (!git_parse_signed(value, &tmp, maximum_signed_value_of_type(ssize_t)))
return 0;
*ret = tmp;
return 1;
}
NORETURN
static void die_bad_number(const char *name, const char *value)
{
const char *error_type = (errno == ERANGE) ?
N_("out of range") : N_("invalid unit");
const char *bad_numeric = N_("bad numeric config value '%s' for '%s': %s");
if (!value)
value = "";
if (!(cf && cf->name))
die(_(bad_numeric), value, name, _(error_type));
switch (cf->origin_type) {
case CONFIG_ORIGIN_BLOB:
die(_("bad numeric config value '%s' for '%s' in blob %s: %s"),
value, name, cf->name, _(error_type));
case CONFIG_ORIGIN_FILE:
die(_("bad numeric config value '%s' for '%s' in file %s: %s"),
value, name, cf->name, _(error_type));
case CONFIG_ORIGIN_STDIN:
die(_("bad numeric config value '%s' for '%s' in standard input: %s"),
value, name, _(error_type));
case CONFIG_ORIGIN_SUBMODULE_BLOB:
die(_("bad numeric config value '%s' for '%s' in submodule-blob %s: %s"),
value, name, cf->name, _(error_type));
case CONFIG_ORIGIN_CMDLINE:
die(_("bad numeric config value '%s' for '%s' in command line %s: %s"),
value, name, cf->name, _(error_type));
default:
die(_("bad numeric config value '%s' for '%s' in %s: %s"),
value, name, cf->name, _(error_type));
}
}
int git_config_int(const char *name, const char *value)
{
int ret;
if (!git_parse_int(value, &ret))
die_bad_number(name, value);
return ret;
}
git-config: always treat --int as 64-bit internally When you run "git config --int", the maximum size of integer you get depends on how git was compiled, and what it considers to be an "int". This is almost useful, because your scripts calling "git config" will behave similarly to git internally. But relying on this is dubious; you have to actually know how git treats each value internally (e.g., int versus unsigned long), which is not documented and is subject to change. And even if you know it is "unsigned long", we do not have a git-config option to match that behavior. Furthermore, you may simply be asking git to store a value on your behalf (e.g., configuration for a hook). In that case, the relevant range check has nothing at all to do with git, but rather with whatever scripting tools you are using (and git has no way of knowing what the appropriate range is there). Not only is the range check useless, but it is actively harmful, as there is no way at all for scripts to look at config variables with large values. For instance, one cannot reliably get the value of pack.packSizeLimit via git-config. On an LP64 system, git happily uses a 64-bit "unsigned long" internally to represent the value, but the script cannot read any value over 2G. Ideally, the "--int" option would simply represent an arbitrarily large integer. For practical purposes, however, a 64-bit integer is large enough, and is much easier to implement (and if somebody overflows it, we will still notice the problem, and not simply return garbage). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-09-08 08:40:02 +00:00
int64_t git_config_int64(const char *name, const char *value)
{
int64_t ret;
if (!git_parse_int64(value, &ret))
die_bad_number(name, value);
return ret;
}
unsigned long git_config_ulong(const char *name, const char *value)
{
unsigned long ret;
if (!git_parse_ulong(value, &ret))
die_bad_number(name, value);
return ret;
}
ssize_t git_config_ssize_t(const char *name, const char *value)
{
ssize_t ret;
if (!git_parse_ssize_t(value, &ret))
die_bad_number(name, value);
return ret;
}
static int git_parse_maybe_bool_text(const char *value)
{
if (!value)
return 1;
if (!*value)
return 0;
if (!strcasecmp(value, "true")
|| !strcasecmp(value, "yes")
|| !strcasecmp(value, "on"))
return 1;
if (!strcasecmp(value, "false")
|| !strcasecmp(value, "no")
|| !strcasecmp(value, "off"))
return 0;
return -1;
}
int git_parse_maybe_bool(const char *value)
{
int v = git_parse_maybe_bool_text(value);
if (0 <= v)
return v;
if (git_parse_int(value, &v))
return !!v;
return -1;
}
int git_config_bool_or_int(const char *name, const char *value, int *is_bool)
{
int v = git_parse_maybe_bool_text(value);
if (0 <= v) {
*is_bool = 1;
return v;
}
*is_bool = 0;
return git_config_int(name, value);
}
int git_config_bool(const char *name, const char *value)
{
int v = git_parse_maybe_bool(value);
if (v < 0)
die(_("bad boolean config value '%s' for '%s'"), value, name);
return v;
}
int git_config_string(const char **dest, const char *var, const char *value)
{
if (!value)
return config_error_nonbool(var);
*dest = xstrdup(value);
return 0;
}
int git_config_pathname(const char **dest, const char *var, const char *value)
{
if (!value)
return config_error_nonbool(var);
*dest = expand_user_path(value, 0);
if (!*dest)
die(_("failed to expand user dir in: '%s'"), value);
return 0;
}
int git_config_expiry_date(timestamp_t *timestamp, const char *var, const char *value)
{
if (!value)
return config_error_nonbool(var);
if (parse_expiry_date(value, timestamp))
return error(_("'%s' for '%s' is not a valid timestamp"),
value, var);
return 0;
}
int git_config_color(char *dest, const char *var, const char *value)
{
if (!value)
return config_error_nonbool(var);
if (color_parse(value, dest) < 0)
return -1;
return 0;
}
static int git_default_core_config(const char *var, const char *value, void *cb)
{
/* This needs a better name */
if (!strcmp(var, "core.filemode")) {
trust_executable_bit = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.trustctime")) {
trust_ctime = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.checkstat")) {
if (!strcasecmp(value, "default"))
check_stat = 1;
else if (!strcasecmp(value, "minimal"))
check_stat = 0;
}
if (!strcmp(var, "core.quotepath")) {
quote_path_fully = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.symlinks")) {
has_symlinks = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.ignorecase")) {
ignore_case = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.attributesfile"))
return git_config_pathname(&git_attributes_file, var, value);
if (!strcmp(var, "core.hookspath"))
return git_config_pathname(&git_hooks_path, var, value);
if (!strcmp(var, "core.bare")) {
is_bare_repository_cfg = git_config_bool(var, value);
return 0;
}
"Assume unchanged" git This adds "assume unchanged" logic, started by this message in the list discussion recently: <Pine.LNX.4.64.0601311807470.7301@g5.osdl.org> This is a workaround for filesystems that do not have lstat() that is quick enough for the index mechanism to take advantage of. On the paths marked as "assumed to be unchanged", the user needs to explicitly use update-index to register the object name to be in the next commit. You can use two new options to update-index to set and reset the CE_VALID bit: git-update-index --assume-unchanged path... git-update-index --no-assume-unchanged path... These forms manipulate only the CE_VALID bit; it does not change the object name recorded in the index file. Nor they add a new entry to the index. When the configuration variable "core.ignorestat = true" is set, the index entries are marked with CE_VALID bit automatically after: - update-index to explicitly register the current object name to the index file. - when update-index --refresh finds the path to be up-to-date. - when tools like read-tree -u and apply --index update the working tree file and register the current object name to the index file. The flag is dropped upon read-tree that does not check out the index entry. This happens regardless of the core.ignorestat settings. Index entries marked with CE_VALID bit are assumed to be unchanged most of the time. However, there are cases that CE_VALID bit is ignored for the sake of safety and usability: - while "git-read-tree -m" or git-apply need to make sure that the paths involved in the merge do not have local modifications. This sacrifices performance for safety. - when git-checkout-index -f -q -u -a tries to see if it needs to checkout the paths. Otherwise you can never check anything out ;-). - when git-update-index --really-refresh (a new flag) tries to see if the index entry is up to date. You can start with everything marked as CE_VALID and run this once to drop CE_VALID bit for paths that are modified. Most notably, "update-index --refresh" honours CE_VALID and does not actively stat, so after you modified a file in the working tree, update-index --refresh would not notice until you tell the index about it with "git-update-index path" or "git-update-index --no-assume-unchanged path". This version is not expected to be perfect. I think diff between index and/or tree and working files may need some adjustment, and there probably needs other cases we should automatically unmark paths that are marked to be CE_VALID. But the basics seem to work, and ready to be tested by people who asked for this feature. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-02-09 05:15:24 +00:00
if (!strcmp(var, "core.ignorestat")) {
assume_unchanged = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.prefersymlinkrefs")) {
prefer_symlink_refs = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.logallrefupdates")) {
if (value && !strcasecmp(value, "always"))
log_all_ref_updates = LOG_REFS_ALWAYS;
else if (git_config_bool(var, value))
log_all_ref_updates = LOG_REFS_NORMAL;
else
log_all_ref_updates = LOG_REFS_NONE;
return 0;
}
if (!strcmp(var, "core.warnambiguousrefs")) {
warn_ambiguous_refs = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.abbrev")) {
if (!value)
return config_error_nonbool(var);
if (!strcasecmp(value, "auto"))
default_abbrev = -1;
else if (!git_parse_maybe_bool_text(value))
default_abbrev = the_hash_algo->hexsz;
else {
int abbrev = git_config_int(var, value);
if (abbrev < minimum_abbrev || abbrev > the_hash_algo->hexsz)
return error(_("abbrev length out of range: %d"), abbrev);
default_abbrev = abbrev;
}
return 0;
}
if (!strcmp(var, "core.disambiguate"))
return set_disambiguate_hint_config(var, value);
Custom compression levels for objects and packs Add config variables pack.compression and core.loosecompression , and switch --compression=level to pack-objects. Loose objects will be compressed using core.loosecompression if set, else core.compression if set, else Z_BEST_SPEED. Packed objects will be compressed using --compression=level if seen, else pack.compression if set, else core.compression if set, else Z_DEFAULT_COMPRESSION. This is the "pack compression level". Loose objects added to a pack undeltified will be recompressed to the pack compression level if it is unequal to the current loose compression level by the preceding rules, or if the loose object was written while core.legacyheaders = true. Newly deltified loose objects are always compressed to the current pack compression level. Previously packed objects added to a pack are recompressed to the current pack compression level exactly when their deltification status changes, since the previous pack data cannot be reused. In either case, the --no-reuse-object switch from the first patch below will always force recompression to the current pack compression level, instead of assuming the pack compression level hasn't changed and pack data can be reused when possible. This applies on top of the following patches from Nicolas Pitre: [PATCH] allow for undeltified objects not to be reused [PATCH] make "repack -f" imply "pack-objects --no-reuse-object" Signed-off-by: Dana L. How <danahow@gmail.com> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-05-09 20:56:50 +00:00
if (!strcmp(var, "core.loosecompression")) {
int level = git_config_int(var, value);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die(_("bad zlib compression level %d"), level);
zlib_compression_level = level;
Custom compression levels for objects and packs Add config variables pack.compression and core.loosecompression , and switch --compression=level to pack-objects. Loose objects will be compressed using core.loosecompression if set, else core.compression if set, else Z_BEST_SPEED. Packed objects will be compressed using --compression=level if seen, else pack.compression if set, else core.compression if set, else Z_DEFAULT_COMPRESSION. This is the "pack compression level". Loose objects added to a pack undeltified will be recompressed to the pack compression level if it is unequal to the current loose compression level by the preceding rules, or if the loose object was written while core.legacyheaders = true. Newly deltified loose objects are always compressed to the current pack compression level. Previously packed objects added to a pack are recompressed to the current pack compression level exactly when their deltification status changes, since the previous pack data cannot be reused. In either case, the --no-reuse-object switch from the first patch below will always force recompression to the current pack compression level, instead of assuming the pack compression level hasn't changed and pack data can be reused when possible. This applies on top of the following patches from Nicolas Pitre: [PATCH] allow for undeltified objects not to be reused [PATCH] make "repack -f" imply "pack-objects --no-reuse-object" Signed-off-by: Dana L. How <danahow@gmail.com> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-05-09 20:56:50 +00:00
zlib_compression_seen = 1;
return 0;
}
if (!strcmp(var, "core.compression")) {
int level = git_config_int(var, value);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die(_("bad zlib compression level %d"), level);
Custom compression levels for objects and packs Add config variables pack.compression and core.loosecompression , and switch --compression=level to pack-objects. Loose objects will be compressed using core.loosecompression if set, else core.compression if set, else Z_BEST_SPEED. Packed objects will be compressed using --compression=level if seen, else pack.compression if set, else core.compression if set, else Z_DEFAULT_COMPRESSION. This is the "pack compression level". Loose objects added to a pack undeltified will be recompressed to the pack compression level if it is unequal to the current loose compression level by the preceding rules, or if the loose object was written while core.legacyheaders = true. Newly deltified loose objects are always compressed to the current pack compression level. Previously packed objects added to a pack are recompressed to the current pack compression level exactly when their deltification status changes, since the previous pack data cannot be reused. In either case, the --no-reuse-object switch from the first patch below will always force recompression to the current pack compression level, instead of assuming the pack compression level hasn't changed and pack data can be reused when possible. This applies on top of the following patches from Nicolas Pitre: [PATCH] allow for undeltified objects not to be reused [PATCH] make "repack -f" imply "pack-objects --no-reuse-object" Signed-off-by: Dana L. How <danahow@gmail.com> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-05-09 20:56:50 +00:00
core_compression_level = level;
core_compression_seen = 1;
if (!zlib_compression_seen)
zlib_compression_level = level;
if (!pack_compression_seen)
pack_compression_level = level;
return 0;
}
Fully activate the sliding window pack access. This finally turns on the sliding window behavior for packfile data access by mapping limited size windows and chaining them under the packed_git->windows list. We consider a given byte offset to be within the window only if there would be at least 20 bytes (one hash worth of data) accessible after the requested offset. This range selection relates to the contract that use_pack() makes with its callers, allowing them to access one hash or one object header without needing to call use_pack() for every byte of data obtained. In the worst case scenario we will map the same page of data twice into memory: once at the end of one window and once again at the start of the next window. This duplicate page mapping will happen only when an object header or a delta base reference is spanned over the end of a window and is always limited to just one page of duplication, as no sane operating system will ever have a page size smaller than a hash. I am assuming that the possible wasted page of virtual address space is going to perform faster than the alternatives, which would be to copy the object header or ref delta into a temporary buffer prior to parsing, or to check the window range on every byte during header parsing. We may decide to revisit this decision in the future since this is just a gut instinct decision and has not actually been proven out by experimental testing. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-23 07:34:28 +00:00
if (!strcmp(var, "core.packedgitwindowsize")) {
int pgsz_x2 = getpagesize() * 2;
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
packed_git_window_size = git_config_ulong(var, value);
/* This value must be multiple of (pagesize * 2) */
packed_git_window_size /= pgsz_x2;
if (packed_git_window_size < 1)
packed_git_window_size = 1;
packed_git_window_size *= pgsz_x2;
Fully activate the sliding window pack access. This finally turns on the sliding window behavior for packfile data access by mapping limited size windows and chaining them under the packed_git->windows list. We consider a given byte offset to be within the window only if there would be at least 20 bytes (one hash worth of data) accessible after the requested offset. This range selection relates to the contract that use_pack() makes with its callers, allowing them to access one hash or one object header without needing to call use_pack() for every byte of data obtained. In the worst case scenario we will map the same page of data twice into memory: once at the end of one window and once again at the start of the next window. This duplicate page mapping will happen only when an object header or a delta base reference is spanned over the end of a window and is always limited to just one page of duplication, as no sane operating system will ever have a page size smaller than a hash. I am assuming that the possible wasted page of virtual address space is going to perform faster than the alternatives, which would be to copy the object header or ref delta into a temporary buffer prior to parsing, or to check the window range on every byte during header parsing. We may decide to revisit this decision in the future since this is just a gut instinct decision and has not actually been proven out by experimental testing. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-23 07:34:28 +00:00
return 0;
}
if (!strcmp(var, "core.bigfilethreshold")) {
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
big_file_threshold = git_config_ulong(var, value);
return 0;
}
if (!strcmp(var, "core.packedgitlimit")) {
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
packed_git_limit = git_config_ulong(var, value);
return 0;
}
if (!strcmp(var, "core.deltabasecachelimit")) {
Support sizes >=2G in various config options accepting 'g' sizes. The config options core.packedGitWindowSize, core.packedGitLimit, core.deltaBaseCacheLimit, core.bigFileThreshold, pack.windowMemory and pack.packSizeLimit all claim to support suffixes up to and including 'g'. This implies that they should accept sizes >=2G on 64-bit systems: certainly, specifying a size of 3g should not silently be translated to zero or transformed into a large negative value due to integer overflow. However, due to use of git_config_int() rather than git_config_ulong(), that is exactly what happens: % git config core.bigFileThreshold 2g % git gc --aggressive # with extra debugging code to print out # core.bigfilethreshold after parsing bigfilethreshold: -2147483648 [...] This is probably irrelevant for core.deltaBaseCacheLimit, but is problematic for the other values. (It is particularly problematic for core.packedGitLimit, which can't even be set to its default value in the config file due to this bug.) This fixes things for 32-bit platforms as well. They get the usual bad config error if an overlarge value is specified, e.g.: fatal: bad config value for 'core.bigfilethreshold' in /home/nix/.gitconfig This is detected in all cases, even if the 32-bit platform has no size larger than 'long'. For signed integral configuration values, we also detect the case where the value is too large for the signed type but not the unsigned type. Signed-off-by: Nick Alcock <nix@esperi.org.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-11-02 15:46:23 +00:00
delta_base_cache_limit = git_config_ulong(var, value);
return 0;
}
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-13 19:07:23 +00:00
if (!strcmp(var, "core.autocrlf")) {
if (value && !strcasecmp(value, "input")) {
auto_crlf = AUTO_CRLF_INPUT;
return 0;
}
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-13 19:07:23 +00:00
auto_crlf = git_config_bool(var, value);
return 0;
}
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 11:25:58 +00:00
if (!strcmp(var, "core.safecrlf")) {
int eol_rndtrp_die;
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 11:25:58 +00:00
if (value && !strcasecmp(value, "warn")) {
global_conv_flags_eol = CONV_EOL_RNDTRP_WARN;
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 11:25:58 +00:00
return 0;
}
eol_rndtrp_die = git_config_bool(var, value);
global_conv_flags_eol = eol_rndtrp_die ?
CONV_EOL_RNDTRP_DIE : 0;
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 11:25:58 +00:00
return 0;
}
if (!strcmp(var, "core.eol")) {
if (value && !strcasecmp(value, "lf"))
core_eol = EOL_LF;
else if (value && !strcasecmp(value, "crlf"))
core_eol = EOL_CRLF;
else if (value && !strcasecmp(value, "native"))
core_eol = EOL_NATIVE;
else
core_eol = EOL_UNSET;
return 0;
}
if (!strcmp(var, "core.checkroundtripencoding")) {
check_roundtrip_encoding = xstrdup(value);
return 0;
}
if (!strcmp(var, "core.notesref")) {
notes_ref_name = xstrdup(value);
return 0;
}
if (!strcmp(var, "core.editor"))
return git_config_string(&editor_program, var, value);
if (!strcmp(var, "core.commentchar")) {
if (!value)
return config_error_nonbool(var);
else if (!strcasecmp(value, "auto"))
auto_comment_line_char = 1;
else if (value[0] && !value[1]) {
comment_line_char = value[0];
auto_comment_line_char = 0;
} else
return error(_("core.commentChar should only be one character"));
return 0;
}
if (!strcmp(var, "core.askpass"))
return git_config_string(&askpass_program, var, value);
if (!strcmp(var, "core.excludesfile"))
return git_config_pathname(&excludes_file, var, value);
if (!strcmp(var, "core.whitespace")) {
if (!value)
return config_error_nonbool(var);
whitespace_rule_cfg = parse_whitespace_rule(value);
return 0;
}
if (!strcmp(var, "core.fsyncobjectfiles")) {
fsync_object_files = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.preloadindex")) {
core_preload_index = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.createobject")) {
if (!strcmp(value, "rename"))
object_creation_mode = OBJECT_CREATION_USES_RENAMES;
else if (!strcmp(value, "link"))
object_creation_mode = OBJECT_CREATION_USES_HARDLINKS;
else
die(_("invalid mode for object creation: %s"), value);
return 0;
}
if (!strcmp(var, "core.sparsecheckout")) {
core_apply_sparse_checkout = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.sparsecheckoutcone")) {
core_sparse_checkout_cone = git_config_bool(var, value);
return 0;
}
git on Mac OS and precomposed unicode Mac OS X mangles file names containing unicode on file systems HFS+, VFAT or SAMBA. When a file using unicode code points outside ASCII is created on a HFS+ drive, the file name is converted into decomposed unicode and written to disk. No conversion is done if the file name is already decomposed unicode. Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same result as open("\x41\xcc\x88",...) with a decomposed "Ä". As a consequence, readdir() returns the file names in decomposed unicode, even if the user expects precomposed unicode. Unlike on HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in precomposed unicode, but readdir() still returns file names in decomposed unicode. When a git repository is stored on a network share using SAMBA, file names are send over the wire and written to disk on the remote system in precomposed unicode, but Mac OS X readdir() returns decomposed unicode to be compatible with its behaviour on HFS+ and VFAT. The unicode decomposition causes many problems: - The names "git add" and other commands get from the end user may often be precomposed form (the decomposed form is not easily input from the keyboard), but when the commands read from the filesystem to see what it is going to update the index with already is on the filesystem, readdir() will give decomposed form, which is different. - Similarly "git log", "git mv" and all other commands that need to compare pathnames found on the command line (often but not always precomposed form; a command line input resulting from globbing may be in decomposed) with pathnames found in the tree objects (should be precomposed form to be compatible with other systems and for consistency in general). - The same for names stored in the index, which should be precomposed, that may need to be compared with the names read from readdir(). NFS mounted from Linux is fully transparent and does not suffer from the above. As Mac OS X treats precomposed and decomposed file names as equal, we can - wrap readdir() on Mac OS X to return the precomposed form, and - normalize decomposed form given from the command line also to the precomposed form, to ensure that all pathnames used in Git are always in the precomposed form. This behaviour can be requested by setting "core.precomposedunicode" configuration variable to true. The code in compat/precomposed_utf8.c implements basically 4 new functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(), precomposed_utf8_closedir() and precompose_argv(). The first three are to wrap opendir(3), readdir(3), and closedir(3) functions. The argv[] conversion allows to use the TAB filename completion done by the shell on command line. It tolerates other tools which use readdir() to feed decomposed file names into git. When creating a new git repository with "git init" or "git clone", "core.precomposedunicode" will be set "false". The user needs to activate this feature manually. She typically sets core.precomposedunicode to "true" on HFS and VFAT, or file systems mounted via SAMBA. Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 13:50:25 +00:00
if (!strcmp(var, "core.precomposeunicode")) {
precomposed_unicode = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.protecthfs")) {
protect_hfs = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.protectntfs")) {
protect_ntfs = git_config_bool(var, value);
return 0;
git on Mac OS and precomposed unicode Mac OS X mangles file names containing unicode on file systems HFS+, VFAT or SAMBA. When a file using unicode code points outside ASCII is created on a HFS+ drive, the file name is converted into decomposed unicode and written to disk. No conversion is done if the file name is already decomposed unicode. Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same result as open("\x41\xcc\x88",...) with a decomposed "Ä". As a consequence, readdir() returns the file names in decomposed unicode, even if the user expects precomposed unicode. Unlike on HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in precomposed unicode, but readdir() still returns file names in decomposed unicode. When a git repository is stored on a network share using SAMBA, file names are send over the wire and written to disk on the remote system in precomposed unicode, but Mac OS X readdir() returns decomposed unicode to be compatible with its behaviour on HFS+ and VFAT. The unicode decomposition causes many problems: - The names "git add" and other commands get from the end user may often be precomposed form (the decomposed form is not easily input from the keyboard), but when the commands read from the filesystem to see what it is going to update the index with already is on the filesystem, readdir() will give decomposed form, which is different. - Similarly "git log", "git mv" and all other commands that need to compare pathnames found on the command line (often but not always precomposed form; a command line input resulting from globbing may be in decomposed) with pathnames found in the tree objects (should be precomposed form to be compatible with other systems and for consistency in general). - The same for names stored in the index, which should be precomposed, that may need to be compared with the names read from readdir(). NFS mounted from Linux is fully transparent and does not suffer from the above. As Mac OS X treats precomposed and decomposed file names as equal, we can - wrap readdir() on Mac OS X to return the precomposed form, and - normalize decomposed form given from the command line also to the precomposed form, to ensure that all pathnames used in Git are always in the precomposed form. This behaviour can be requested by setting "core.precomposedunicode" configuration variable to true. The code in compat/precomposed_utf8.c implements basically 4 new functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(), precomposed_utf8_closedir() and precompose_argv(). The first three are to wrap opendir(3), readdir(3), and closedir(3) functions. The argv[] conversion allows to use the TAB filename completion done by the shell on command line. It tolerates other tools which use readdir() to feed decomposed file names into git. When creating a new git repository with "git init" or "git clone", "core.precomposedunicode" will be set "false". The user needs to activate this feature manually. She typically sets core.precomposedunicode to "true" on HFS and VFAT, or file systems mounted via SAMBA. Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 13:50:25 +00:00
}
if (!strcmp(var, "core.usereplacerefs")) {
read_replace_refs = git_config_bool(var, value);
return 0;
}
/* Add other config variables here and to Documentation/config.txt. */
return platform_core_config(var, value, cb);
}
static int git_default_i18n_config(const char *var, const char *value)
{
if (!strcmp(var, "i18n.commitencoding"))
return git_config_string(&git_commit_encoding, var, value);
if (!strcmp(var, "i18n.logoutputencoding"))
return git_config_string(&git_log_output_encoding, var, value);
/* Add other config variables here and to Documentation/config.txt. */
return 0;
}
core.excludesfile clean-up There are inconsistencies in the way commands currently handle the core.excludesfile configuration variable. The problem is the variable is too new to be noticed by anything other than git-add and git-status. * git-ls-files does not notice any of the "ignore" files by default, as it predates the standardized set of ignore files. The calling scripts established the convention to use .git/info/exclude, .gitignore, and later core.excludesfile. * git-add and git-status know about it because they call add_excludes_from_file() directly with their own notion of which standard set of ignore files to use. This is just a stupid duplication of code that need to be updated every time the definition of the standard set of ignore files is changed. * git-read-tree takes --exclude-per-directory=<gitignore>, not because the flexibility was needed. Again, this was because the option predates the standardization of the ignore files. * git-merge-recursive uses hardcoded per-directory .gitignore and nothing else. git-clean (scripted version) does not honor core.* because its call to underlying ls-files does not know about it. git-clean in C (parked in 'pu') doesn't either. We probably could change git-ls-files to use the standard set when no excludes are specified on the command line and ignore processing was asked, or something like that, but that will be a change in semantics and might break people's scripts in a subtle way. I am somewhat reluctant to make such a change. On the other hand, I think it makes perfect sense to fix git-read-tree, git-merge-recursive and git-clean to follow the same rule as other commands. I do not think of a valid use case to give an exclude-per-directory that is nonstandard to read-tree command, outside a "negative" test in the t1004 test script. This patch is the first step to untangle this mess. The next step would be to teach read-tree, merge-recursive and clean (in C) to use setup_standard_excludes(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 08:05:00 +00:00
static int git_default_branch_config(const char *var, const char *value)
{
if (!strcmp(var, "branch.autosetupmerge")) {
if (value && !strcasecmp(value, "always")) {
git_branch_track = BRANCH_TRACK_ALWAYS;
return 0;
}
git_branch_track = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "branch.autosetuprebase")) {
if (!value)
return config_error_nonbool(var);
else if (!strcmp(value, "never"))
autorebase = AUTOREBASE_NEVER;
else if (!strcmp(value, "local"))
autorebase = AUTOREBASE_LOCAL;
else if (!strcmp(value, "remote"))
autorebase = AUTOREBASE_REMOTE;
else if (!strcmp(value, "always"))
autorebase = AUTOREBASE_ALWAYS;
else
return error(_("malformed value for %s"), var);
return 0;
}
/* Add other config variables here and to Documentation/config.txt. */
return 0;
}
static int git_default_push_config(const char *var, const char *value)
{
if (!strcmp(var, "push.default")) {
if (!value)
return config_error_nonbool(var);
else if (!strcmp(value, "nothing"))
push_default = PUSH_DEFAULT_NOTHING;
else if (!strcmp(value, "matching"))
push_default = PUSH_DEFAULT_MATCHING;
else if (!strcmp(value, "simple"))
push_default = PUSH_DEFAULT_SIMPLE;
else if (!strcmp(value, "upstream"))
push_default = PUSH_DEFAULT_UPSTREAM;
else if (!strcmp(value, "tracking")) /* deprecated */
push_default = PUSH_DEFAULT_UPSTREAM;
else if (!strcmp(value, "current"))
push_default = PUSH_DEFAULT_CURRENT;
else {
error(_("malformed value for %s: %s"), var, value);
return error(_("must be one of nothing, matching, simple, "
"upstream or current"));
}
return 0;
}
/* Add other config variables here and to Documentation/config.txt. */
return 0;
}
static int git_default_mailmap_config(const char *var, const char *value)
{
if (!strcmp(var, "mailmap.file"))
return git_config_pathname(&git_mailmap_file, var, value);
if (!strcmp(var, "mailmap.blob"))
return git_config_string(&git_mailmap_blob, var, value);
/* Add other config variables here and to Documentation/config.txt. */
return 0;
}
int git_default_config(const char *var, const char *value, void *cb)
{
if (starts_with(var, "core."))
return git_default_core_config(var, value, cb);
if (starts_with(var, "user.") ||
starts_with(var, "author.") ||
starts_with(var, "committer."))
return git_ident_config(var, value, cb);
if (starts_with(var, "i18n."))
return git_default_i18n_config(var, value);
if (starts_with(var, "branch."))
return git_default_branch_config(var, value);
if (starts_with(var, "push."))
return git_default_push_config(var, value);
if (starts_with(var, "mailmap."))
return git_default_mailmap_config(var, value);
if (starts_with(var, "advice.") || starts_with(var, "color.advice"))
return git_default_advice_config(var, value);
if (!strcmp(var, "pager.color") || !strcmp(var, "color.pager")) {
pager_use_color = git_config_bool(var,value);
return 0;
}
if (!strcmp(var, "pack.packsizelimit")) {
pack_size_limit_cfg = git_config_ulong(var, value);
return 0;
}
if (!strcmp(var, "pack.compression")) {
int level = git_config_int(var, value);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die(_("bad pack compression level %d"), level);
pack_compression_level = level;
pack_compression_seen = 1;
return 0;
}
/* Add other config variables here and to Documentation/config.txt. */
return 0;
}
/*
* All source specific fields in the union, die_on_error, name and the callbacks
* fgetc, ungetc, ftell of top need to be initialized before calling
* this function.
*/
static int do_config_from(struct config_source *top, config_fn_t fn, void *data,
const struct config_options *opts)
{
int ret;
/* push config-file parsing state stack */
top->prev = cf;
top->linenr = 1;
top->eof = 0;
config: reject parsing of files over INT_MAX While the last few commits have made it possible for the config parser to handle config files up to the limits of size_t, the rest of the code isn't really ready for this. In particular, we often feed the keys as strings into printf "%s" format specifiers. And because the printf family of functions must return an int to specify the result, they complain. Here are two concrete examples (using glibc; we're in uncharted territory here so results may vary): Generate a gigantic .gitmodules file like this: git submodule add /some/other/repo foo { printf '[submodule "' perl -e 'print "a" x 2**31' echo '"]path = foo' } >.gitmodules git commit -m 'huge gitmodule' then try this: $ git show BUG: strbuf.c:397: your vsnprintf is broken (returned -1) The problem is that we end up calling: strbuf_addf(&sb, "submodule.%s.ignore", submodule_name); which relies on vsnprintf(), and that function has no way to report back a size larger than INT_MAX. Taking that same file, try this: git config --file=.gitmodules --list --name-only On my system it produces an output with exactly 4GB of spaces. I confirmed in a debugger that we reach the config callback with the key intact: it's 2147483663 bytes and full of a's. But when we print it with this call: printf("%s%c", key_, term); we just get the spaces. So given the fact that these are insane cases which we have no need to support, the weird behavior from feeding the results to printf even if the code is careful, and the possibility of uncareful code introducing its own integer truncation issues, let's just declare INT_MAX as a limit for parsing config files. We'll enforce the limit in get_next_char(), which generalizes over all sources (blobs, files, etc) and covers any element we're parsing (whether section, key, value, etc). For simplicity, the limit is over the length of the _whole_ file, so you couldn't have two 1GB values in the same file. This should be perfectly fine, as the expected size for config files is generally kilobytes at most. With this patch both cases above will yield: fatal: bad config line 1 in file .gitmodules That's not an amazing error message, but the parser isn't set up to provide specific messages (it just breaks out of the parsing loop and gives that generic error even if see a syntactic issue). And we really wouldn't expect to see this case outside of somebody maliciously probing the limits of the config system. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-04-10 19:50:07 +00:00
top->total_len = 0;
strbuf_init(&top->value, 1024);
strbuf_init(&top->var, 1024);
cf = top;
ret = git_parse_source(fn, data, opts);
/* pop config-file parsing state stack */
strbuf_release(&top->value);
strbuf_release(&top->var);
cf = top->prev;
return ret;
}
static int do_config_from_file(config_fn_t fn,
const enum config_origin_type origin_type,
const char *name, const char *path, FILE *f,
void *data, const struct config_options *opts)
{
struct config_source top;
int ret;
top.u.file = f;
top.origin_type = origin_type;
top.name = name;
top.path = path;
top.default_error_action = CONFIG_ERROR_DIE;
top.do_fgetc = config_file_fgetc;
top.do_ungetc = config_file_ungetc;
top.do_ftell = config_file_ftell;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
flockfile(f);
ret = do_config_from(&top, fn, data, opts);
funlockfile(f);
return ret;
}
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
static int git_config_from_stdin(config_fn_t fn, void *data)
{
return do_config_from_file(fn, CONFIG_ORIGIN_STDIN, "", NULL, stdin,
data, NULL);
}
int git_config_from_file_with_options(config_fn_t fn, const char *filename,
void *data,
const struct config_options *opts)
{
int ret = -1;
FILE *f;
config.c: Make git_config() work correctly when called recursively On Cygwin, this fixes a test failure in t3301-notes.sh (test 98, "git notes copy --for-rewrite (disabled)"). The test failure is caused by a recursive call to git_config() which has the effect of skipping to the end-of-file while processing the "notes.rewriteref" config variable. Thus, any config variables that appear after "notes.rewriteref" are simply ignored by git_config(). Also, we note that the original FILE handle is leaked as a result of the recursive call. The recursive call to git_config() is due to the "schizophrenic stat" functions on cygwin, where one of two different implementations of the l/stat functions is selected lazily, depending on some config variables. In this case, the init_copy_notes_for_rewrite() function calls git_config() with the notes_rewrite_config() callback function. This callback, while processing the "notes.rewriteref" variable, in turn calls string_list_add_refs_by_glob() to process the associated ref value. This eventually leads to a call to the get_ref_dir() function, which in turn calls stat(). On cygwin, the stat() macro leads to an indirect call to cygwin_stat_stub() which, via init_stat(), then calls git_config() in order to determine which l/stat implementation to bind to. In order to solve this problem, we modify git_config() so that the global state variables used by the config reading code is packaged up and managed on a local state stack. Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-16 20:24:51 +00:00
f = fopen_or_warn(filename, "r");
if (f) {
ret = do_config_from_file(fn, CONFIG_ORIGIN_FILE, filename,
filename, f, data, opts);
fclose(f);
}
return ret;
}
int git_config_from_file(config_fn_t fn, const char *filename, void *data)
{
return git_config_from_file_with_options(fn, filename, data, NULL);
}
int git_config_from_mem(config_fn_t fn,
const enum config_origin_type origin_type,
const char *name, const char *buf, size_t len,
void *data, const struct config_options *opts)
{
struct config_source top;
top.u.buf.buf = buf;
top.u.buf.len = len;
top.u.buf.pos = 0;
top.origin_type = origin_type;
top.name = name;
top.path = NULL;
top.default_error_action = CONFIG_ERROR_ERROR;
top.do_fgetc = config_buf_fgetc;
top.do_ungetc = config_buf_ungetc;
top.do_ftell = config_buf_ftell;
return do_config_from(&top, fn, data, opts);
}
int git_config_from_blob_oid(config_fn_t fn,
const char *name,
const struct object_id *oid,
void *data)
{
enum object_type type;
char *buf;
unsigned long size;
int ret;
buf = read_object_file(oid, &type, &size);
if (!buf)
return error(_("unable to load config blob object '%s'"), name);
if (type != OBJ_BLOB) {
free(buf);
return error(_("reference '%s' does not point to a blob"), name);
}
ret = git_config_from_mem(fn, CONFIG_ORIGIN_BLOB, name, buf, size,
data, NULL);
free(buf);
return ret;
}
static int git_config_from_blob_ref(config_fn_t fn,
const char *name,
void *data)
{
struct object_id oid;
if (get_oid(name, &oid) < 0)
return error(_("unable to resolve config blob '%s'"), name);
return git_config_from_blob_oid(fn, name, &oid, data);
}
char *git_system_config(void)
{
config: allow overriding of global and system configuration In order to have git run in a fully controlled environment without any misconfiguration, it may be desirable for users or scripts to override global- and system-level configuration files. We already have a way of doing this, which is to unset both HOME and XDG_CONFIG_HOME environment variables and to set `GIT_CONFIG_NOGLOBAL=true`. This is quite kludgy, and unsetting the first two variables likely has an impact on other executables spawned by such a script. The obvious way to fix this would be to introduce `GIT_CONFIG_NOGLOBAL` as an equivalent to `GIT_CONFIG_NOSYSTEM`. But in the past, it has turned out that this design is inflexible: we cannot test system-level parsing of the git configuration in our test harness because there is no way to change its location, so all tests run with `GIT_CONFIG_NOSYSTEM` set. Instead of doing the same mistake with `GIT_CONFIG_NOGLOBAL`, introduce two new variables `GIT_CONFIG_GLOBAL` and `GIT_CONFIG_SYSTEM`: - If unset, git continues to use the usual locations. - If set to a specific path, we skip reading the normal configuration files and instead take the path. By setting the path to `/dev/null`, no configuration will be loaded for the respective level. This implements the usecase where we want to execute code in a sanitized environment without any potential misconfigurations via `/dev/null`, but is more flexible and allows for more usecases than simply adding `GIT_CONFIG_NOGLOBAL`. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-04-19 12:31:16 +00:00
char *system_config = xstrdup_or_null(getenv("GIT_CONFIG_SYSTEM"));
if (!system_config)
system_config = system_path(ETC_GITCONFIG);
normalize_path_copy(system_config, system_config);
return system_config;
}
config: allow overriding of global and system configuration In order to have git run in a fully controlled environment without any misconfiguration, it may be desirable for users or scripts to override global- and system-level configuration files. We already have a way of doing this, which is to unset both HOME and XDG_CONFIG_HOME environment variables and to set `GIT_CONFIG_NOGLOBAL=true`. This is quite kludgy, and unsetting the first two variables likely has an impact on other executables spawned by such a script. The obvious way to fix this would be to introduce `GIT_CONFIG_NOGLOBAL` as an equivalent to `GIT_CONFIG_NOSYSTEM`. But in the past, it has turned out that this design is inflexible: we cannot test system-level parsing of the git configuration in our test harness because there is no way to change its location, so all tests run with `GIT_CONFIG_NOSYSTEM` set. Instead of doing the same mistake with `GIT_CONFIG_NOGLOBAL`, introduce two new variables `GIT_CONFIG_GLOBAL` and `GIT_CONFIG_SYSTEM`: - If unset, git continues to use the usual locations. - If set to a specific path, we skip reading the normal configuration files and instead take the path. By setting the path to `/dev/null`, no configuration will be loaded for the respective level. This implements the usecase where we want to execute code in a sanitized environment without any potential misconfigurations via `/dev/null`, but is more flexible and allows for more usecases than simply adding `GIT_CONFIG_NOGLOBAL`. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-04-19 12:31:16 +00:00
void git_global_config(char **user_out, char **xdg_out)
{
config: allow overriding of global and system configuration In order to have git run in a fully controlled environment without any misconfiguration, it may be desirable for users or scripts to override global- and system-level configuration files. We already have a way of doing this, which is to unset both HOME and XDG_CONFIG_HOME environment variables and to set `GIT_CONFIG_NOGLOBAL=true`. This is quite kludgy, and unsetting the first two variables likely has an impact on other executables spawned by such a script. The obvious way to fix this would be to introduce `GIT_CONFIG_NOGLOBAL` as an equivalent to `GIT_CONFIG_NOSYSTEM`. But in the past, it has turned out that this design is inflexible: we cannot test system-level parsing of the git configuration in our test harness because there is no way to change its location, so all tests run with `GIT_CONFIG_NOSYSTEM` set. Instead of doing the same mistake with `GIT_CONFIG_NOGLOBAL`, introduce two new variables `GIT_CONFIG_GLOBAL` and `GIT_CONFIG_SYSTEM`: - If unset, git continues to use the usual locations. - If set to a specific path, we skip reading the normal configuration files and instead take the path. By setting the path to `/dev/null`, no configuration will be loaded for the respective level. This implements the usecase where we want to execute code in a sanitized environment without any potential misconfigurations via `/dev/null`, but is more flexible and allows for more usecases than simply adding `GIT_CONFIG_NOGLOBAL`. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-04-19 12:31:16 +00:00
char *user_config = xstrdup_or_null(getenv("GIT_CONFIG_GLOBAL"));
char *xdg_config = NULL;
if (!user_config) {
user_config = expand_user_path("~/.gitconfig", 0);
xdg_config = xdg_config_home("config");
}
*user_out = user_config;
*xdg_out = xdg_config;
}
/*
* Parse environment variable 'k' as a boolean (in various
* possible spellings); if missing, use the default value 'def'.
*/
int git_env_bool(const char *k, int def)
{
const char *v = getenv(k);
return v ? git_config_bool(k, v) : def;
}
/*
* Parse environment variable 'k' as ulong with possibly a unit
* suffix; if missing, use the default value 'val'.
*/
unsigned long git_env_ulong(const char *k, unsigned long val)
{
const char *v = getenv(k);
if (v && !git_parse_ulong(v, &val))
die(_("failed to parse %s"), k);
return val;
}
int git_config_system(void)
{
return !git_env_bool("GIT_CONFIG_NOSYSTEM", 0);
}
static int do_git_config_sequence(const struct config_options *opts,
config_fn_t fn, void *data)
{
int ret = 0;
char *system_config = git_system_config();
char *xdg_config = NULL;
char *user_config = NULL;
char *repo_config;
enum config_scope prev_parsing_scope = current_parsing_scope;
if (opts->commondir)
repo_config = mkpathdup("%s/config", opts->commondir);
else if (opts->git_dir)
BUG("git_dir without commondir");
else
repo_config = NULL;
current_parsing_scope = CONFIG_SCOPE_SYSTEM;
if (git_config_system() && system_config &&
!access_or_die(system_config, R_OK,
opts->system_gently ? ACCESS_EACCES_OK : 0))
ret += git_config_from_file(fn, system_config, data);
current_parsing_scope = CONFIG_SCOPE_GLOBAL;
git_global_config(&user_config, &xdg_config);
if (xdg_config && !access_or_die(xdg_config, R_OK, ACCESS_EACCES_OK))
ret += git_config_from_file(fn, xdg_config, data);
if (user_config && !access_or_die(user_config, R_OK, ACCESS_EACCES_OK))
ret += git_config_from_file(fn, user_config, data);
current_parsing_scope = CONFIG_SCOPE_LOCAL;
if (!opts->ignore_repo && repo_config &&
!access_or_die(repo_config, R_OK, 0))
ret += git_config_from_file(fn, repo_config, data);
current_parsing_scope = CONFIG_SCOPE_WORKTREE;
if (!opts->ignore_worktree && repository_format_worktree_config) {
worktree: add per-worktree config files A new repo extension is added, worktreeConfig. When it is present: - Repository config reading by default includes $GIT_DIR/config _and_ $GIT_DIR/config.worktree. "config" file remains shared in multiple worktree setup. - The special treatment for core.bare and core.worktree, to stay effective only in main worktree, is gone. These config settings are supposed to be in config.worktree. This extension is most useful in multiple worktree setup because you now have an option to store per-worktree config (which is either .git/config.worktree for main worktree, or .git/worktrees/xx/config.worktree for linked ones). This extension can be used in single worktree mode, even though it's pretty much useless (but this can happen after you remove all linked worktrees and move back to single worktree). "git config" reads from both "config" and "config.worktree" by default (i.e. without either --user, --file...) when this extension is present. Default writes still go to "config", not "config.worktree". A new option --worktree is added for that (*). Since a new repo extension is introduced, existing git binaries should refuse to access to the repo (both from main and linked worktrees). So they will not misread the config file (i.e. skip the config.worktree part). They may still accidentally write to the config file anyway if they use with "git config --file <path>". This design places a bet on the assumption that the majority of config variables are shared so it is the default mode. A safer move would be default writes go to per-worktree file, so that accidental changes are isolated. (*) "git config --worktree" points back to "config" file when this extension is not present and there is only one worktree so that it works in any both single and multiple worktree setups. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-10-21 14:02:28 +00:00
char *path = git_pathdup("config.worktree");
if (!access_or_die(path, R_OK, 0))
ret += git_config_from_file(fn, path, data);
free(path);
}
current_parsing_scope = CONFIG_SCOPE_COMMAND;
if (!opts->ignore_cmdline && git_config_from_parameters(fn, data) < 0)
die(_("unable to parse command-line config"));
current_parsing_scope = prev_parsing_scope;
free(system_config);
free(xdg_config);
free(user_config);
free(repo_config);
return ret;
}
int config_with_options(config_fn_t fn, void *data,
struct git_config_source *config_source,
const struct config_options *opts)
{
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
struct config_include_data inc = CONFIG_INCLUDE_INIT;
if (opts->respect_includes) {
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
inc.fn = fn;
inc.data = data;
inc.opts = opts;
config: add include directive It can be useful to split your ~/.gitconfig across multiple files. For example, you might have a "main" file which is used on many machines, but a small set of per-machine tweaks. Or you may want to make some of your config public (e.g., clever aliases) while keeping other data back (e.g., your name or other identifying information). Or you may want to include a number of config options in some subset of your repos without copying and pasting (e.g., you want to reference them from the .git/config of participating repos). This patch introduces an include directive for config files. It looks like: [include] path = /path/to/file This is syntactically backwards-compatible with existing git config parsers (i.e., they will see it as another config entry and ignore it unless you are looking up include.path). The implementation provides a "git_config_include" callback which wraps regular config callbacks. Callers can pass it to git_config_from_file, and it will transparently follow any include directives, passing all of the discovered options to the real callback. Include directives are turned on automatically for "regular" git config parsing. This includes calls to git_config, as well as calls to the "git config" program that do not specify a single file (e.g., using "-f", "--global", etc). They are not turned on in other cases, including: 1. Parsing of other config-like files, like .gitmodules. There isn't a real need, and I'd rather be conservative and avoid unnecessary incompatibility or confusion. 2. Reading single files via "git config". This is for two reasons: a. backwards compatibility with scripts looking at config-like files. b. inspection of a specific file probably means you care about just what's in that file, not a general lookup for "do we have this value anywhere at all". If that is not the case, the caller can always specify "--includes". 3. Writing files via "git config"; we want to treat include.* variables as literal items to be copied (or modified), and not expand them. So "git config --unset-all foo.bar" would operate _only_ on .git/config, not any of its included files (just as it also does not operate on ~/.gitconfig). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-06 09:54:04 +00:00
fn = git_config_include;
data = &inc;
}
if (config_source)
current_parsing_scope = config_source->scope;
/*
* If we have a specific filename, use it. Otherwise, follow the
* regular lookup sequence.
*/
if (config_source && config_source->use_stdin)
return git_config_from_stdin(fn, data);
else if (config_source && config_source->file)
return git_config_from_file(fn, config_source->file, data);
else if (config_source && config_source->blob)
return git_config_from_blob_ref(fn, config_source->blob, data);
return do_git_config_sequence(opts, fn, data);
}
static void configset_iter(struct config_set *cs, config_fn_t fn, void *data)
{
int i, value_index;
struct string_list *values;
struct config_set_element *entry;
struct configset_list *list = &cs->list;
for (i = 0; i < list->nr; i++) {
entry = list->items[i].e;
value_index = list->items[i].value_index;
values = &entry->value_list;
current_config_kvi = values->items[value_index].util;
if (fn(entry->key, values->items[value_index].string, data) < 0)
git_die_config_linenr(entry->key,
current_config_kvi->filename,
current_config_kvi->linenr);
current_config_kvi = NULL;
}
}
void read_early_config(config_fn_t cb, void *data)
{
struct config_options opts = {0};
struct strbuf commondir = STRBUF_INIT;
struct strbuf gitdir = STRBUF_INIT;
opts.respect_includes = 1;
if (have_git_dir()) {
opts.commondir = get_git_common_dir();
opts.git_dir = get_git_dir();
/*
* When setup_git_directory() was not yet asked to discover the
* GIT_DIR, we ask discover_git_directory() to figure out whether there
* is any repository config we should use (but unlike
* setup_git_directory_gently(), no global state is changed, most
* notably, the current working directory is still the same after the
* call).
*/
} else if (!discover_git_directory(&commondir, &gitdir)) {
opts.commondir = commondir.buf;
opts.git_dir = gitdir.buf;
}
config_with_options(cb, data, NULL, &opts);
strbuf_release(&commondir);
strbuf_release(&gitdir);
}
/*
* Read config but only enumerate system and global settings.
* Omit any repo-local, worktree-local, or command-line settings.
*/
void read_very_early_config(config_fn_t cb, void *data)
{
struct config_options opts = { 0 };
opts.respect_includes = 1;
opts.ignore_repo = 1;
opts.ignore_worktree = 1;
opts.ignore_cmdline = 1;
opts.system_gently = 1;
config_with_options(cb, data, NULL, &opts);
}
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
static struct config_set_element *configset_find_element(struct config_set *cs, const char *key)
{
struct config_set_element k;
struct config_set_element *found_entry;
char *normalized_key;
/*
* `key` may come from the user, so normalize it before using it
* for querying entries from the hashmap.
*/
if (git_config_parse_key(key, &normalized_key, NULL))
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
return NULL;
hashmap_entry_init(&k.ent, strhash(normalized_key));
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
k.key = normalized_key;
found_entry = hashmap_get_entry(&cs->config_hash, &k, ent, NULL);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
free(normalized_key);
return found_entry;
}
static int configset_add_value(struct config_set *cs, const char *key, const char *value)
{
struct config_set_element *e;
struct string_list_item *si;
struct configset_list_item *l_item;
struct key_value_info *kv_info = xmalloc(sizeof(*kv_info));
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
e = configset_find_element(cs, key);
/*
* Since the keys are being fed by git_config*() callback mechanism, they
* are already normalized. So simply add them without any further munging.
*/
if (!e) {
e = xmalloc(sizeof(*e));
hashmap_entry_init(&e->ent, strhash(key));
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
e->key = xstrdup(key);
string_list_init_dup(&e->value_list);
hashmap_add(&cs->config_hash, &e->ent);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
si = string_list_append_nodup(&e->value_list, xstrdup_or_null(value));
ALLOC_GROW(cs->list.items, cs->list.nr + 1, cs->list.alloc);
l_item = &cs->list.items[cs->list.nr++];
l_item->e = e;
l_item->value_index = e->value_list.nr - 1;
if (!cf)
BUG("configset_add_value has no source");
if (cf->name) {
kv_info->filename = strintern(cf->name);
kv_info->linenr = cf->linenr;
kv_info->origin_type = cf->origin_type;
} else {
/* for values read from `git_config_from_parameters()` */
kv_info->filename = NULL;
kv_info->linenr = -1;
kv_info->origin_type = CONFIG_ORIGIN_CMDLINE;
}
kv_info->scope = current_parsing_scope;
si->util = kv_info;
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
return 0;
}
static int config_set_element_cmp(const void *unused_cmp_data,
const struct hashmap_entry *eptr,
const struct hashmap_entry *entry_or_key,
const void *unused_keydata)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
const struct config_set_element *e1, *e2;
e1 = container_of(eptr, const struct config_set_element, ent);
e2 = container_of(entry_or_key, const struct config_set_element, ent);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
return strcmp(e1->key, e2->key);
}
void git_configset_init(struct config_set *cs)
{
hashmap_init(&cs->config_hash, config_set_element_cmp, NULL, 0);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
cs->hash_initialized = 1;
cs->list.nr = 0;
cs->list.alloc = 0;
cs->list.items = NULL;
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
void git_configset_clear(struct config_set *cs)
{
struct config_set_element *entry;
struct hashmap_iter iter;
if (!cs->hash_initialized)
return;
hashmap_for_each_entry(&cs->config_hash, &iter, entry,
ent /* member name */) {
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
free(entry->key);
string_list_clear(&entry->value_list, 1);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
hashmap_clear_and_free(&cs->config_hash, struct config_set_element, ent);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
cs->hash_initialized = 0;
free(cs->list.items);
cs->list.nr = 0;
cs->list.alloc = 0;
cs->list.items = NULL;
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
static int config_set_callback(const char *key, const char *value, void *cb)
{
struct config_set *cs = cb;
configset_add_value(cs, key, value);
return 0;
}
int git_configset_add_file(struct config_set *cs, const char *filename)
{
return git_config_from_file(config_set_callback, filename, cs);
}
int git_configset_get_value(struct config_set *cs, const char *key, const char **value)
{
const struct string_list *values = NULL;
/*
* Follows "last one wins" semantic, i.e., if there are multiple matches for the
* queried key in the files of the configset, the value returned will be the last
* value in the value list for that key.
*/
values = git_configset_get_value_multi(cs, key);
if (!values)
return 1;
assert(values->nr > 0);
*value = values->items[values->nr - 1].string;
return 0;
}
const struct string_list *git_configset_get_value_multi(struct config_set *cs, const char *key)
{
struct config_set_element *e = configset_find_element(cs, key);
return e ? &e->value_list : NULL;
}
config: drop git_config_get_string_const() As evidenced by the leak fixes in the previous commit, the "const" in git_config_get_string_const() clearly misleads people into thinking that it does not allocate a copy of the string. We can fix this by renaming it, but it's easier still to just drop it. Of the four remaining callers: - The one in git_config_parse_expiry() still needs to allocate, since that's what its callers expect. We can just use the non-const version and cast our pointer. Slightly ugly, but the damage is contained in one spot. - The two in apply are writing to global "const char *" variables, and need to continue allocating. We often mark these as const because we assign default string literals to them. But in this case we don't do that, so we can just declare them as real "char *" pointers and use the non-const version. - The call in checkout doesn't actually need a copy; it can just use the non-allocating "tmp" version of the function. The function is also mentioned in the MyFirstContribution document. We can swap that call out for the non-allocating "tmp" variant, which fits well in the example given. We'll drop the "configset" and "repo" variants, as well (which are unused). Note that this frees up the "const" name, so we could rename the "tmp" variant back to that. But let's give some time for topics in flight to adapt to the new code before doing so (if we do it too soon, the function semantics will change but the compiler won't alert us). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 21:33:11 +00:00
int git_configset_get_string(struct config_set *cs, const char *key, char **dest)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
const char *value;
if (!git_configset_get_value(cs, key, &value))
config: drop git_config_get_string_const() As evidenced by the leak fixes in the previous commit, the "const" in git_config_get_string_const() clearly misleads people into thinking that it does not allocate a copy of the string. We can fix this by renaming it, but it's easier still to just drop it. Of the four remaining callers: - The one in git_config_parse_expiry() still needs to allocate, since that's what its callers expect. We can just use the non-const version and cast our pointer. Slightly ugly, but the damage is contained in one spot. - The two in apply are writing to global "const char *" variables, and need to continue allocating. We often mark these as const because we assign default string literals to them. But in this case we don't do that, so we can just declare them as real "char *" pointers and use the non-const version. - The call in checkout doesn't actually need a copy; it can just use the non-allocating "tmp" version of the function. The function is also mentioned in the MyFirstContribution document. We can swap that call out for the non-allocating "tmp" variant, which fits well in the example given. We'll drop the "configset" and "repo" variants, as well (which are unused). Note that this frees up the "const" name, so we could rename the "tmp" variant back to that. But let's give some time for topics in flight to adapt to the new code before doing so (if we do it too soon, the function semantics will change but the compiler won't alert us). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 21:33:11 +00:00
return git_config_string((const char **)dest, key, value);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
else
return 1;
}
config: fix leaks from git_config_get_string_const() There are two functions to get a single config string: - git_config_get_string() - git_config_get_string_const() One might naively think that the first one allocates a new string and the second one just points us to the internal configset storage. But in fact they both allocate a new copy; the second one exists only to avoid having to cast when using it with a const global which we never intend to free. The documentation for the function explains that clearly, but it seems I'm not alone in being surprised by this. Of 17 calls to the function, 13 of them leak the resulting value. We could obviously fix these by adding the appropriate free(). But it would be simpler still if we actually had a non-allocating way to get the string. There's git_config_get_value() but that doesn't quite do what we want. If the config key is present but is a boolean with no value (e.g., "[foo]bar" in the file), then we'll get NULL (whereas the string versions will print an error and die). So let's introduce a new variant, git_config_get_string_tmp(), that behaves as these callers expect. We need a new name because we have new semantics but the same function signature (so even if we converted the four remaining callers, topics in flight might be surprised). The "tmp" is because this value should only be held onto for a short time. In practice it's rare for us to clear and refresh the configset, invalidating the pointer, but hopefully the "tmp" makes callers think about the lifetime. In each of the converted cases here the value only needs to last within the local function or its immediate caller. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-14 16:17:36 +00:00
int git_configset_get_string_tmp(struct config_set *cs, const char *key,
const char **dest)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
config: fix leaks from git_config_get_string_const() There are two functions to get a single config string: - git_config_get_string() - git_config_get_string_const() One might naively think that the first one allocates a new string and the second one just points us to the internal configset storage. But in fact they both allocate a new copy; the second one exists only to avoid having to cast when using it with a const global which we never intend to free. The documentation for the function explains that clearly, but it seems I'm not alone in being surprised by this. Of 17 calls to the function, 13 of them leak the resulting value. We could obviously fix these by adding the appropriate free(). But it would be simpler still if we actually had a non-allocating way to get the string. There's git_config_get_value() but that doesn't quite do what we want. If the config key is present but is a boolean with no value (e.g., "[foo]bar" in the file), then we'll get NULL (whereas the string versions will print an error and die). So let's introduce a new variant, git_config_get_string_tmp(), that behaves as these callers expect. We need a new name because we have new semantics but the same function signature (so even if we converted the four remaining callers, topics in flight might be surprised). The "tmp" is because this value should only be held onto for a short time. In practice it's rare for us to clear and refresh the configset, invalidating the pointer, but hopefully the "tmp" makes callers think about the lifetime. In each of the converted cases here the value only needs to last within the local function or its immediate caller. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-14 16:17:36 +00:00
const char *value;
if (!git_configset_get_value(cs, key, &value)) {
if (!value)
return config_error_nonbool(key);
*dest = value;
return 0;
} else {
return 1;
}
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int git_configset_get_int(struct config_set *cs, const char *key, int *dest)
{
const char *value;
if (!git_configset_get_value(cs, key, &value)) {
*dest = git_config_int(key, value);
return 0;
} else
return 1;
}
int git_configset_get_ulong(struct config_set *cs, const char *key, unsigned long *dest)
{
const char *value;
if (!git_configset_get_value(cs, key, &value)) {
*dest = git_config_ulong(key, value);
return 0;
} else
return 1;
}
int git_configset_get_bool(struct config_set *cs, const char *key, int *dest)
{
const char *value;
if (!git_configset_get_value(cs, key, &value)) {
*dest = git_config_bool(key, value);
return 0;
} else
return 1;
}
int git_configset_get_bool_or_int(struct config_set *cs, const char *key,
int *is_bool, int *dest)
{
const char *value;
if (!git_configset_get_value(cs, key, &value)) {
*dest = git_config_bool_or_int(key, value, is_bool);
return 0;
} else
return 1;
}
int git_configset_get_maybe_bool(struct config_set *cs, const char *key, int *dest)
{
const char *value;
if (!git_configset_get_value(cs, key, &value)) {
*dest = git_parse_maybe_bool(value);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
if (*dest == -1)
return -1;
return 0;
} else
return 1;
}
int git_configset_get_pathname(struct config_set *cs, const char *key, const char **dest)
{
const char *value;
if (!git_configset_get_value(cs, key, &value))
return git_config_pathname(dest, key, value);
else
return 1;
}
/* Functions use to read configuration from a repository */
static void repo_read_config(struct repository *repo)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
struct config_options opts = { 0 };
opts.respect_includes = 1;
opts.commondir = repo->commondir;
opts.git_dir = repo->gitdir;
if (!repo->config)
CALLOC_ARRAY(repo->config, 1);
else
git_configset_clear(repo->config);
git_configset_init(repo->config);
if (config_with_options(config_set_callback, repo->config, NULL, &opts) < 0)
/*
* config_with_options() normally returns only
* zero, as most errors are fatal, and
* non-fatal potential errors are guarded by "if"
* statements that are entered only when no error is
* possible.
*
* If we ever encounter a non-fatal error, it means
* something went really wrong and we should stop
* immediately.
*/
die(_("unknown error occurred while reading the configuration files"));
}
static void git_config_check_init(struct repository *repo)
{
if (repo->config && repo->config->hash_initialized)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
return;
repo_read_config(repo);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
static void repo_config_clear(struct repository *repo)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
if (!repo->config || !repo->config->hash_initialized)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
return;
git_configset_clear(repo->config);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
void repo_config(struct repository *repo, config_fn_t fn, void *data)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
git_config_check_init(repo);
configset_iter(repo->config, fn, data);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int repo_config_get_value(struct repository *repo,
const char *key, const char **value)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
git_config_check_init(repo);
return git_configset_get_value(repo->config, key, value);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
const struct string_list *repo_config_get_value_multi(struct repository *repo,
const char *key)
{
git_config_check_init(repo);
return git_configset_get_value_multi(repo->config, key);
}
config: drop git_config_get_string_const() As evidenced by the leak fixes in the previous commit, the "const" in git_config_get_string_const() clearly misleads people into thinking that it does not allocate a copy of the string. We can fix this by renaming it, but it's easier still to just drop it. Of the four remaining callers: - The one in git_config_parse_expiry() still needs to allocate, since that's what its callers expect. We can just use the non-const version and cast our pointer. Slightly ugly, but the damage is contained in one spot. - The two in apply are writing to global "const char *" variables, and need to continue allocating. We often mark these as const because we assign default string literals to them. But in this case we don't do that, so we can just declare them as real "char *" pointers and use the non-const version. - The call in checkout doesn't actually need a copy; it can just use the non-allocating "tmp" version of the function. The function is also mentioned in the MyFirstContribution document. We can swap that call out for the non-allocating "tmp" variant, which fits well in the example given. We'll drop the "configset" and "repo" variants, as well (which are unused). Note that this frees up the "const" name, so we could rename the "tmp" variant back to that. But let's give some time for topics in flight to adapt to the new code before doing so (if we do it too soon, the function semantics will change but the compiler won't alert us). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 21:33:11 +00:00
int repo_config_get_string(struct repository *repo,
const char *key, char **dest)
{
int ret;
git_config_check_init(repo);
config: drop git_config_get_string_const() As evidenced by the leak fixes in the previous commit, the "const" in git_config_get_string_const() clearly misleads people into thinking that it does not allocate a copy of the string. We can fix this by renaming it, but it's easier still to just drop it. Of the four remaining callers: - The one in git_config_parse_expiry() still needs to allocate, since that's what its callers expect. We can just use the non-const version and cast our pointer. Slightly ugly, but the damage is contained in one spot. - The two in apply are writing to global "const char *" variables, and need to continue allocating. We often mark these as const because we assign default string literals to them. But in this case we don't do that, so we can just declare them as real "char *" pointers and use the non-const version. - The call in checkout doesn't actually need a copy; it can just use the non-allocating "tmp" version of the function. The function is also mentioned in the MyFirstContribution document. We can swap that call out for the non-allocating "tmp" variant, which fits well in the example given. We'll drop the "configset" and "repo" variants, as well (which are unused). Note that this frees up the "const" name, so we could rename the "tmp" variant back to that. But let's give some time for topics in flight to adapt to the new code before doing so (if we do it too soon, the function semantics will change but the compiler won't alert us). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 21:33:11 +00:00
ret = git_configset_get_string(repo->config, key, dest);
if (ret < 0)
git_die_config(key, NULL);
return ret;
}
config: fix leaks from git_config_get_string_const() There are two functions to get a single config string: - git_config_get_string() - git_config_get_string_const() One might naively think that the first one allocates a new string and the second one just points us to the internal configset storage. But in fact they both allocate a new copy; the second one exists only to avoid having to cast when using it with a const global which we never intend to free. The documentation for the function explains that clearly, but it seems I'm not alone in being surprised by this. Of 17 calls to the function, 13 of them leak the resulting value. We could obviously fix these by adding the appropriate free(). But it would be simpler still if we actually had a non-allocating way to get the string. There's git_config_get_value() but that doesn't quite do what we want. If the config key is present but is a boolean with no value (e.g., "[foo]bar" in the file), then we'll get NULL (whereas the string versions will print an error and die). So let's introduce a new variant, git_config_get_string_tmp(), that behaves as these callers expect. We need a new name because we have new semantics but the same function signature (so even if we converted the four remaining callers, topics in flight might be surprised). The "tmp" is because this value should only be held onto for a short time. In practice it's rare for us to clear and refresh the configset, invalidating the pointer, but hopefully the "tmp" makes callers think about the lifetime. In each of the converted cases here the value only needs to last within the local function or its immediate caller. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-14 16:17:36 +00:00
int repo_config_get_string_tmp(struct repository *repo,
const char *key, const char **dest)
{
config: fix leaks from git_config_get_string_const() There are two functions to get a single config string: - git_config_get_string() - git_config_get_string_const() One might naively think that the first one allocates a new string and the second one just points us to the internal configset storage. But in fact they both allocate a new copy; the second one exists only to avoid having to cast when using it with a const global which we never intend to free. The documentation for the function explains that clearly, but it seems I'm not alone in being surprised by this. Of 17 calls to the function, 13 of them leak the resulting value. We could obviously fix these by adding the appropriate free(). But it would be simpler still if we actually had a non-allocating way to get the string. There's git_config_get_value() but that doesn't quite do what we want. If the config key is present but is a boolean with no value (e.g., "[foo]bar" in the file), then we'll get NULL (whereas the string versions will print an error and die). So let's introduce a new variant, git_config_get_string_tmp(), that behaves as these callers expect. We need a new name because we have new semantics but the same function signature (so even if we converted the four remaining callers, topics in flight might be surprised). The "tmp" is because this value should only be held onto for a short time. In practice it's rare for us to clear and refresh the configset, invalidating the pointer, but hopefully the "tmp" makes callers think about the lifetime. In each of the converted cases here the value only needs to last within the local function or its immediate caller. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-14 16:17:36 +00:00
int ret;
git_config_check_init(repo);
config: fix leaks from git_config_get_string_const() There are two functions to get a single config string: - git_config_get_string() - git_config_get_string_const() One might naively think that the first one allocates a new string and the second one just points us to the internal configset storage. But in fact they both allocate a new copy; the second one exists only to avoid having to cast when using it with a const global which we never intend to free. The documentation for the function explains that clearly, but it seems I'm not alone in being surprised by this. Of 17 calls to the function, 13 of them leak the resulting value. We could obviously fix these by adding the appropriate free(). But it would be simpler still if we actually had a non-allocating way to get the string. There's git_config_get_value() but that doesn't quite do what we want. If the config key is present but is a boolean with no value (e.g., "[foo]bar" in the file), then we'll get NULL (whereas the string versions will print an error and die). So let's introduce a new variant, git_config_get_string_tmp(), that behaves as these callers expect. We need a new name because we have new semantics but the same function signature (so even if we converted the four remaining callers, topics in flight might be surprised). The "tmp" is because this value should only be held onto for a short time. In practice it's rare for us to clear and refresh the configset, invalidating the pointer, but hopefully the "tmp" makes callers think about the lifetime. In each of the converted cases here the value only needs to last within the local function or its immediate caller. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-14 16:17:36 +00:00
ret = git_configset_get_string_tmp(repo->config, key, dest);
if (ret < 0)
git_die_config(key, NULL);
return ret;
}
int repo_config_get_int(struct repository *repo,
const char *key, int *dest)
{
git_config_check_init(repo);
return git_configset_get_int(repo->config, key, dest);
}
int repo_config_get_ulong(struct repository *repo,
const char *key, unsigned long *dest)
{
git_config_check_init(repo);
return git_configset_get_ulong(repo->config, key, dest);
}
int repo_config_get_bool(struct repository *repo,
const char *key, int *dest)
{
git_config_check_init(repo);
return git_configset_get_bool(repo->config, key, dest);
}
int repo_config_get_bool_or_int(struct repository *repo,
const char *key, int *is_bool, int *dest)
{
git_config_check_init(repo);
return git_configset_get_bool_or_int(repo->config, key, is_bool, dest);
}
int repo_config_get_maybe_bool(struct repository *repo,
const char *key, int *dest)
{
git_config_check_init(repo);
return git_configset_get_maybe_bool(repo->config, key, dest);
}
int repo_config_get_pathname(struct repository *repo,
const char *key, const char **dest)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
int ret;
git_config_check_init(repo);
ret = git_configset_get_pathname(repo->config, key, dest);
if (ret < 0)
git_die_config(key, NULL);
return ret;
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
/* Functions used historically to read configuration from 'the_repository' */
void git_config(config_fn_t fn, void *data)
{
repo_config(the_repository, fn, data);
}
void git_config_clear(void)
{
repo_config_clear(the_repository);
}
int git_config_get_value(const char *key, const char **value)
{
return repo_config_get_value(the_repository, key, value);
}
const struct string_list *git_config_get_value_multi(const char *key)
{
return repo_config_get_value_multi(the_repository, key);
}
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
int git_config_get_string(const char *key, char **dest)
{
return repo_config_get_string(the_repository, key, dest);
}
config: fix leaks from git_config_get_string_const() There are two functions to get a single config string: - git_config_get_string() - git_config_get_string_const() One might naively think that the first one allocates a new string and the second one just points us to the internal configset storage. But in fact they both allocate a new copy; the second one exists only to avoid having to cast when using it with a const global which we never intend to free. The documentation for the function explains that clearly, but it seems I'm not alone in being surprised by this. Of 17 calls to the function, 13 of them leak the resulting value. We could obviously fix these by adding the appropriate free(). But it would be simpler still if we actually had a non-allocating way to get the string. There's git_config_get_value() but that doesn't quite do what we want. If the config key is present but is a boolean with no value (e.g., "[foo]bar" in the file), then we'll get NULL (whereas the string versions will print an error and die). So let's introduce a new variant, git_config_get_string_tmp(), that behaves as these callers expect. We need a new name because we have new semantics but the same function signature (so even if we converted the four remaining callers, topics in flight might be surprised). The "tmp" is because this value should only be held onto for a short time. In practice it's rare for us to clear and refresh the configset, invalidating the pointer, but hopefully the "tmp" makes callers think about the lifetime. In each of the converted cases here the value only needs to last within the local function or its immediate caller. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-14 16:17:36 +00:00
int git_config_get_string_tmp(const char *key, const char **dest)
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
{
config: fix leaks from git_config_get_string_const() There are two functions to get a single config string: - git_config_get_string() - git_config_get_string_const() One might naively think that the first one allocates a new string and the second one just points us to the internal configset storage. But in fact they both allocate a new copy; the second one exists only to avoid having to cast when using it with a const global which we never intend to free. The documentation for the function explains that clearly, but it seems I'm not alone in being surprised by this. Of 17 calls to the function, 13 of them leak the resulting value. We could obviously fix these by adding the appropriate free(). But it would be simpler still if we actually had a non-allocating way to get the string. There's git_config_get_value() but that doesn't quite do what we want. If the config key is present but is a boolean with no value (e.g., "[foo]bar" in the file), then we'll get NULL (whereas the string versions will print an error and die). So let's introduce a new variant, git_config_get_string_tmp(), that behaves as these callers expect. We need a new name because we have new semantics but the same function signature (so even if we converted the four remaining callers, topics in flight might be surprised). The "tmp" is because this value should only be held onto for a short time. In practice it's rare for us to clear and refresh the configset, invalidating the pointer, but hopefully the "tmp" makes callers think about the lifetime. In each of the converted cases here the value only needs to last within the local function or its immediate caller. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-14 16:17:36 +00:00
return repo_config_get_string_tmp(the_repository, key, dest);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int git_config_get_int(const char *key, int *dest)
{
return repo_config_get_int(the_repository, key, dest);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int git_config_get_ulong(const char *key, unsigned long *dest)
{
return repo_config_get_ulong(the_repository, key, dest);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int git_config_get_bool(const char *key, int *dest)
{
return repo_config_get_bool(the_repository, key, dest);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int git_config_get_bool_or_int(const char *key, int *is_bool, int *dest)
{
return repo_config_get_bool_or_int(the_repository, key, is_bool, dest);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int git_config_get_maybe_bool(const char *key, int *dest)
{
return repo_config_get_maybe_bool(the_repository, key, dest);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
int git_config_get_pathname(const char *key, const char **dest)
{
return repo_config_get_pathname(the_repository, key, dest);
}
int git_config_get_expiry(const char *key, const char **output)
{
config: drop git_config_get_string_const() As evidenced by the leak fixes in the previous commit, the "const" in git_config_get_string_const() clearly misleads people into thinking that it does not allocate a copy of the string. We can fix this by renaming it, but it's easier still to just drop it. Of the four remaining callers: - The one in git_config_parse_expiry() still needs to allocate, since that's what its callers expect. We can just use the non-const version and cast our pointer. Slightly ugly, but the damage is contained in one spot. - The two in apply are writing to global "const char *" variables, and need to continue allocating. We often mark these as const because we assign default string literals to them. But in this case we don't do that, so we can just declare them as real "char *" pointers and use the non-const version. - The call in checkout doesn't actually need a copy; it can just use the non-allocating "tmp" version of the function. The function is also mentioned in the MyFirstContribution document. We can swap that call out for the non-allocating "tmp" variant, which fits well in the example given. We'll drop the "configset" and "repo" variants, as well (which are unused). Note that this frees up the "const" name, so we could rename the "tmp" variant back to that. But let's give some time for topics in flight to adapt to the new code before doing so (if we do it too soon, the function semantics will change but the compiler won't alert us). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 21:33:11 +00:00
int ret = git_config_get_string(key, (char **)output);
if (ret)
return ret;
if (strcmp(*output, "now")) {
timestamp_t now = approxidate("now");
if (approxidate(*output) >= now)
git_die_config(key, _("Invalid %s: '%s'"), key, *output);
}
return ret;
}
int git_config_get_expiry_in_days(const char *key, timestamp_t *expiry, timestamp_t now)
{
const char *expiry_string;
intmax_t days;
timestamp_t when;
if (git_config_get_string_tmp(key, &expiry_string))
return 1; /* no such thing */
if (git_parse_signed(expiry_string, &days, maximum_signed_value_of_type(int))) {
const int scale = 86400;
*expiry = now - days * scale;
return 0;
}
if (!parse_expiry_date(expiry_string, &when)) {
*expiry = when;
return 0;
}
return -1; /* thing exists but cannot be parsed */
}
int git_config_get_split_index(void)
{
int val;
if (!git_config_get_maybe_bool("core.splitindex", &val))
return val;
return -1; /* default value */
}
int git_config_get_max_percent_split_change(void)
{
int val = -1;
if (!git_config_get_int("splitindex.maxpercentchange", &val)) {
if (0 <= val && val <= 100)
return val;
return error(_("splitIndex.maxPercentChange value '%d' "
"should be between 0 and 100"), val);
}
return -1; /* default value */
}
int git_config_get_fsmonitor(void)
{
if (git_config_get_pathname("core.fsmonitor", &core_fsmonitor))
core_fsmonitor = getenv("GIT_TEST_FSMONITOR");
if (core_fsmonitor && !*core_fsmonitor)
core_fsmonitor = NULL;
if (core_fsmonitor)
return 1;
return 0;
}
index: make index.threads=true enable ieot and eoie If a user explicitly sets [index] threads = true to read the index using multiple threads, ensure that index writes include the offset table by default to make that possible. This ensures that the user's intent of turning on threading is respected. In other words, permit the following configurations: - index.threads and index.recordOffsetTable unspecified: do not write the offset table yet (to avoid alarming the user with "ignoring IEOT extension" messages when an older version of Git accesses the repository) but do make use of multiple threads to read the index if the supporting offset table is present. This can also be requested explicitly by setting index.threads=true, 0, or >1 and index.recordOffsetTable=false. - index.threads=false or 1: do not write the offset table, and do not make use of the offset table. One can set index.recordOffsetTable=false as well, to be more explicit. - index.threads=true, 0, or >1 and index.recordOffsetTable unspecified: write the offset table and make use of threads at read time. This can also be requested by setting index.threads=true, 0, >1, or unspecified and index.recordOffsetTable=true. Fortunately the complication is temporary: once most Git installations have upgraded to a version with support for the IEOT and EOIE extensions, we can flip the defaults for index.recordEndOfIndexEntries and index.recordOffsetTable to true and eliminate the settings. Helped-by: Ben Peart <benpeart@microsoft.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-20 06:14:26 +00:00
int git_config_get_index_threads(int *dest)
{
index: make index.threads=true enable ieot and eoie If a user explicitly sets [index] threads = true to read the index using multiple threads, ensure that index writes include the offset table by default to make that possible. This ensures that the user's intent of turning on threading is respected. In other words, permit the following configurations: - index.threads and index.recordOffsetTable unspecified: do not write the offset table yet (to avoid alarming the user with "ignoring IEOT extension" messages when an older version of Git accesses the repository) but do make use of multiple threads to read the index if the supporting offset table is present. This can also be requested explicitly by setting index.threads=true, 0, or >1 and index.recordOffsetTable=false. - index.threads=false or 1: do not write the offset table, and do not make use of the offset table. One can set index.recordOffsetTable=false as well, to be more explicit. - index.threads=true, 0, or >1 and index.recordOffsetTable unspecified: write the offset table and make use of threads at read time. This can also be requested by setting index.threads=true, 0, >1, or unspecified and index.recordOffsetTable=true. Fortunately the complication is temporary: once most Git installations have upgraded to a version with support for the IEOT and EOIE extensions, we can flip the defaults for index.recordEndOfIndexEntries and index.recordOffsetTable to true and eliminate the settings. Helped-by: Ben Peart <benpeart@microsoft.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-20 06:14:26 +00:00
int is_bool, val;
val = git_env_ulong("GIT_TEST_INDEX_THREADS", 0);
index: make index.threads=true enable ieot and eoie If a user explicitly sets [index] threads = true to read the index using multiple threads, ensure that index writes include the offset table by default to make that possible. This ensures that the user's intent of turning on threading is respected. In other words, permit the following configurations: - index.threads and index.recordOffsetTable unspecified: do not write the offset table yet (to avoid alarming the user with "ignoring IEOT extension" messages when an older version of Git accesses the repository) but do make use of multiple threads to read the index if the supporting offset table is present. This can also be requested explicitly by setting index.threads=true, 0, or >1 and index.recordOffsetTable=false. - index.threads=false or 1: do not write the offset table, and do not make use of the offset table. One can set index.recordOffsetTable=false as well, to be more explicit. - index.threads=true, 0, or >1 and index.recordOffsetTable unspecified: write the offset table and make use of threads at read time. This can also be requested by setting index.threads=true, 0, >1, or unspecified and index.recordOffsetTable=true. Fortunately the complication is temporary: once most Git installations have upgraded to a version with support for the IEOT and EOIE extensions, we can flip the defaults for index.recordEndOfIndexEntries and index.recordOffsetTable to true and eliminate the settings. Helped-by: Ben Peart <benpeart@microsoft.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-20 06:14:26 +00:00
if (val) {
*dest = val;
return 0;
}
if (!git_config_get_bool_or_int("index.threads", &is_bool, &val)) {
if (is_bool)
index: make index.threads=true enable ieot and eoie If a user explicitly sets [index] threads = true to read the index using multiple threads, ensure that index writes include the offset table by default to make that possible. This ensures that the user's intent of turning on threading is respected. In other words, permit the following configurations: - index.threads and index.recordOffsetTable unspecified: do not write the offset table yet (to avoid alarming the user with "ignoring IEOT extension" messages when an older version of Git accesses the repository) but do make use of multiple threads to read the index if the supporting offset table is present. This can also be requested explicitly by setting index.threads=true, 0, or >1 and index.recordOffsetTable=false. - index.threads=false or 1: do not write the offset table, and do not make use of the offset table. One can set index.recordOffsetTable=false as well, to be more explicit. - index.threads=true, 0, or >1 and index.recordOffsetTable unspecified: write the offset table and make use of threads at read time. This can also be requested by setting index.threads=true, 0, >1, or unspecified and index.recordOffsetTable=true. Fortunately the complication is temporary: once most Git installations have upgraded to a version with support for the IEOT and EOIE extensions, we can flip the defaults for index.recordEndOfIndexEntries and index.recordOffsetTable to true and eliminate the settings. Helped-by: Ben Peart <benpeart@microsoft.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-20 06:14:26 +00:00
*dest = val ? 0 : 1;
else
index: make index.threads=true enable ieot and eoie If a user explicitly sets [index] threads = true to read the index using multiple threads, ensure that index writes include the offset table by default to make that possible. This ensures that the user's intent of turning on threading is respected. In other words, permit the following configurations: - index.threads and index.recordOffsetTable unspecified: do not write the offset table yet (to avoid alarming the user with "ignoring IEOT extension" messages when an older version of Git accesses the repository) but do make use of multiple threads to read the index if the supporting offset table is present. This can also be requested explicitly by setting index.threads=true, 0, or >1 and index.recordOffsetTable=false. - index.threads=false or 1: do not write the offset table, and do not make use of the offset table. One can set index.recordOffsetTable=false as well, to be more explicit. - index.threads=true, 0, or >1 and index.recordOffsetTable unspecified: write the offset table and make use of threads at read time. This can also be requested by setting index.threads=true, 0, >1, or unspecified and index.recordOffsetTable=true. Fortunately the complication is temporary: once most Git installations have upgraded to a version with support for the IEOT and EOIE extensions, we can flip the defaults for index.recordEndOfIndexEntries and index.recordOffsetTable to true and eliminate the settings. Helped-by: Ben Peart <benpeart@microsoft.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-20 06:14:26 +00:00
*dest = val;
return 0;
}
index: make index.threads=true enable ieot and eoie If a user explicitly sets [index] threads = true to read the index using multiple threads, ensure that index writes include the offset table by default to make that possible. This ensures that the user's intent of turning on threading is respected. In other words, permit the following configurations: - index.threads and index.recordOffsetTable unspecified: do not write the offset table yet (to avoid alarming the user with "ignoring IEOT extension" messages when an older version of Git accesses the repository) but do make use of multiple threads to read the index if the supporting offset table is present. This can also be requested explicitly by setting index.threads=true, 0, or >1 and index.recordOffsetTable=false. - index.threads=false or 1: do not write the offset table, and do not make use of the offset table. One can set index.recordOffsetTable=false as well, to be more explicit. - index.threads=true, 0, or >1 and index.recordOffsetTable unspecified: write the offset table and make use of threads at read time. This can also be requested by setting index.threads=true, 0, >1, or unspecified and index.recordOffsetTable=true. Fortunately the complication is temporary: once most Git installations have upgraded to a version with support for the IEOT and EOIE extensions, we can flip the defaults for index.recordEndOfIndexEntries and index.recordOffsetTable to true and eliminate the settings. Helped-by: Ben Peart <benpeart@microsoft.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-20 06:14:26 +00:00
return 1;
}
NORETURN
void git_die_config_linenr(const char *key, const char *filename, int linenr)
{
if (!filename)
die(_("unable to parse '%s' from command-line config"), key);
else
die(_("bad config variable '%s' in file '%s' at line %d"),
key, filename, linenr);
}
NORETURN __attribute__((format(printf, 2, 3)))
void git_die_config(const char *key, const char *err, ...)
{
const struct string_list *values;
struct key_value_info *kv_info;
if (err) {
va_list params;
va_start(params, err);
vreportf("error: ", err, params);
va_end(params);
}
values = git_config_get_value_multi(key);
kv_info = values->items[values->nr - 1].util;
git_die_config_linenr(key, kv_info->filename, kv_info->linenr);
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
}
/*
* Find all the stuff for git_config_set() below.
*/
struct config_store_data {
size_t baselen;
char *key;
int do_not_match;
const char *fixed_value;
regex_t *value_pattern;
int multi_replace;
struct {
size_t begin, end;
enum config_event_t type;
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
int is_keys_section;
} *parsed;
unsigned int parsed_nr, parsed_alloc, *seen, seen_nr, seen_alloc;
unsigned int key_seen:1, section_seen:1, is_keys_section:1;
};
static void config_store_data_clear(struct config_store_data *store)
{
free(store->key);
if (store->value_pattern != NULL &&
store->value_pattern != CONFIG_REGEX_NONE) {
regfree(store->value_pattern);
free(store->value_pattern);
}
free(store->parsed);
free(store->seen);
memset(store, 0, sizeof(*store));
}
static int matches(const char *key, const char *value,
const struct config_store_data *store)
{
if (strcmp(key, store->key))
return 0; /* not ours */
if (store->fixed_value)
return !strcmp(store->fixed_value, value);
if (!store->value_pattern)
return 1; /* always matches */
if (store->value_pattern == CONFIG_REGEX_NONE)
return 0; /* never matches */
return store->do_not_match ^
(value && !regexec(store->value_pattern, value, 0, NULL, 0));
}
static int store_aux_event(enum config_event_t type,
size_t begin, size_t end, void *data)
{
struct config_store_data *store = data;
ALLOC_GROW(store->parsed, store->parsed_nr + 1, store->parsed_alloc);
store->parsed[store->parsed_nr].begin = begin;
store->parsed[store->parsed_nr].end = end;
store->parsed[store->parsed_nr].type = type;
if (type == CONFIG_EVENT_SECTION) {
int (*cmpfn)(const char *, const char *, size_t);
if (cf->var.len < 2 || cf->var.buf[cf->var.len - 1] != '.')
return error(_("invalid section name '%s'"), cf->var.buf);
if (cf->subsection_case_sensitive)
cmpfn = strncasecmp;
else
cmpfn = strncmp;
/* Is this the section we were looking for? */
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
store->is_keys_section =
store->parsed[store->parsed_nr].is_keys_section =
cf->var.len - 1 == store->baselen &&
!cmpfn(cf->var.buf, store->key, store->baselen);
if (store->is_keys_section) {
store->section_seen = 1;
ALLOC_GROW(store->seen, store->seen_nr + 1,
store->seen_alloc);
store->seen[store->seen_nr] = store->parsed_nr;
}
}
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
store->parsed_nr++;
return 0;
}
static int store_aux(const char *key, const char *value, void *cb)
{
struct config_store_data *store = cb;
if (store->key_seen) {
if (matches(key, value, store)) {
if (store->seen_nr == 1 && store->multi_replace == 0) {
warning(_("%s has multiple values"), key);
}
ALLOC_GROW(store->seen, store->seen_nr + 1,
store->seen_alloc);
store->seen[store->seen_nr] = store->parsed_nr;
store->seen_nr++;
}
} else if (store->is_keys_section) {
/*
* Do not increment matches yet: this may not be a match, but we
* are in the desired section.
*/
ALLOC_GROW(store->seen, store->seen_nr + 1, store->seen_alloc);
store->seen[store->seen_nr] = store->parsed_nr;
store->section_seen = 1;
if (matches(key, value, store)) {
store->seen_nr++;
store->key_seen = 1;
}
}
return 0;
}
static int write_error(const char *filename)
{
error(_("failed to write new configuration file %s"), filename);
/* Same error code as "failed to rename". */
return 4;
}
static struct strbuf store_create_section(const char *key,
const struct config_store_data *store)
{
const char *dot;
size_t i;
struct strbuf sb = STRBUF_INIT;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
dot = memchr(key, '.', store->baselen);
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
if (dot) {
strbuf_addf(&sb, "[%.*s \"", (int)(dot - key), key);
for (i = dot - key + 1; i < store->baselen; i++) {
if (key[i] == '"' || key[i] == '\\')
strbuf_addch(&sb, '\\');
strbuf_addch(&sb, key[i]);
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
}
strbuf_addstr(&sb, "\"]\n");
} else {
strbuf_addch(&sb, '[');
strbuf_add(&sb, key, store->baselen);
strbuf_addstr(&sb, "]\n");
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-09 19:24:02 +00:00
}
return sb;
}
static ssize_t write_section(int fd, const char *key,
const struct config_store_data *store)
{
struct strbuf sb = store_create_section(key, store);
ssize_t ret;
ret = write_in_full(fd, sb.buf, sb.len);
strbuf_release(&sb);
return ret;
}
static ssize_t write_pair(int fd, const char *key, const char *value,
const struct config_store_data *store)
{
int i;
ssize_t ret;
const char *quote = "";
struct strbuf sb = STRBUF_INIT;
/*
* Check to see if the value needs to be surrounded with a dq pair.
* Note that problematic characters are always backslash-quoted; this
* check is about not losing leading or trailing SP and strings that
* follow beginning-of-comment characters (i.e. ';' and '#') by the
* configuration parser.
*/
if (value[0] == ' ')
quote = "\"";
for (i = 0; value[i]; i++)
if (value[i] == ';' || value[i] == '#')
quote = "\"";
if (i && value[i - 1] == ' ')
quote = "\"";
strbuf_addf(&sb, "\t%s = %s", key + store->baselen + 1, quote);
for (i = 0; value[i]; i++)
switch (value[i]) {
case '\n':
strbuf_addstr(&sb, "\\n");
break;
case '\t':
strbuf_addstr(&sb, "\\t");
break;
case '"':
case '\\':
strbuf_addch(&sb, '\\');
consistently use "fallthrough" comments in switches Gcc 7 adds -Wimplicit-fallthrough, which can warn when a switch case falls through to the next case. The general idea is that the compiler can't tell if this was intentional or not, so you should annotate any intentional fall-throughs as such, leaving it to complain about any unannotated ones. There's a GNU __attribute__ which can be used for annotation, but of course we'd have to #ifdef it away on non-gcc compilers. Gcc will also recognize specially-formatted comments, which matches our current practice. Let's extend that practice to all of the unannotated sites (which I did look over and verify that they were behaving as intended). Ideally in each case we'd actually give some reasons in the comment about why we're falling through, or what we're falling through to. And gcc does support that with -Wimplicit-fallthrough=2, which relaxes the comment pattern matching to anything that contains "fallthrough" (or a variety of spelling variants). However, this isn't the default for -Wimplicit-fallthrough, nor for -Wextra. In the name of simplicity, it's probably better for us to support the default level, which requires "fallthrough" to be the only thing in the comment (modulo some window dressing like "else" and some punctuation; see the gcc manual for the complete set of patterns). This patch suppresses all warnings due to -Wimplicit-fallthrough. We might eventually want to add that to the DEVELOPER Makefile knob, but we should probably wait until gcc 7 is more widely adopted (since earlier versions will complain about the unknown warning type). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-21 06:25:41 +00:00
/* fallthrough */
default:
strbuf_addch(&sb, value[i]);
break;
}
strbuf_addf(&sb, "%s\n", quote);
ret = write_in_full(fd, sb.buf, sb.len);
strbuf_release(&sb);
return ret;
}
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
/*
* If we are about to unset the last key(s) in a section, and if there are
* no comments surrounding (or included in) the section, we will want to
* extend begin/end to remove the entire section.
*
* Note: the parameter `seen_ptr` points to the index into the store.seen
* array. * This index may be incremented if a section has more than one
* entry (which all are to be removed).
*/
static void maybe_remove_section(struct config_store_data *store,
size_t *begin_offset, size_t *end_offset,
int *seen_ptr)
{
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
size_t begin;
int i, seen, section_seen = 0;
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
/*
* First, ensure that this is the first key, and that there are no
* comments before the entry nor before the section header.
*/
seen = *seen_ptr;
for (i = store->seen[seen]; i > 0; i--) {
enum config_event_t type = store->parsed[i - 1].type;
if (type == CONFIG_EVENT_COMMENT)
/* There is a comment before this entry or section */
return;
if (type == CONFIG_EVENT_ENTRY) {
if (!section_seen)
/* This is not the section's first entry. */
return;
/* We encountered no comment before the section. */
break;
}
if (type == CONFIG_EVENT_SECTION) {
if (!store->parsed[i - 1].is_keys_section)
break;
section_seen = 1;
}
}
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
begin = store->parsed[i].begin;
/*
* Next, make sure that we are removing the last key(s) in the section,
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
* and that there are no comments that are possibly about the current
* section.
*/
for (i = store->seen[seen] + 1; i < store->parsed_nr; i++) {
enum config_event_t type = store->parsed[i].type;
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
if (type == CONFIG_EVENT_COMMENT)
return;
if (type == CONFIG_EVENT_SECTION) {
if (store->parsed[i].is_keys_section)
continue;
break;
}
if (type == CONFIG_EVENT_ENTRY) {
if (++seen < store->seen_nr &&
i == store->seen[seen])
/* We want to remove this entry, too */
continue;
/* There is another entry in this section. */
return;
}
}
/*
* We are really removing the last entry/entries from this section, and
* there are no enclosed or surrounding comments. Remove the entire,
* now-empty section.
*/
*seen_ptr = seen;
*begin_offset = begin;
if (i < store->parsed_nr)
*end_offset = store->parsed[i].begin;
else
*end_offset = store->parsed[store->parsed_nr - 1].end;
}
int git_config_set_in_file_gently(const char *config_filename,
const char *key, const char *value)
{
return git_config_set_multivar_in_file_gently(config_filename, key, value, NULL, 0);
}
void git_config_set_in_file(const char *config_filename,
const char *key, const char *value)
{
git_config_set_multivar_in_file(config_filename, key, value, NULL, 0);
}
int git_config_set_gently(const char *key, const char *value)
{
return git_config_set_multivar_gently(key, value, NULL, 0);
}
void git_config_set(const char *key, const char *value)
{
git_config_set_multivar(key, value, NULL, 0);
trace2_cmd_set_config(key, value);
}
/*
* If value==NULL, unset in (remove from) config,
* if value_pattern!=NULL, disregard key/value pairs where value does not match.
* if value_pattern==CONFIG_REGEX_NONE, do not match any existing values
* (only add a new one)
* if flags contains the CONFIG_FLAGS_MULTI_REPLACE flag, all matching
* key/values are removed before a single new pair is written. If the
* flag is not present, then replace only the first match.
*
* Returns 0 on success.
*
* This function does this:
*
* - it locks the config file by creating ".git/config.lock"
*
* - it then parses the config using store_aux() as validator to find
* the position on the key/value pair to replace. If it is to be unset,
* it must be found exactly once.
*
* - the config file is mmap()ed and the part before the match (if any) is
* written to the lock file, then the changed part and the rest.
*
* - the config file is removed and the lock file rename()d to it.
*
*/
int git_config_set_multivar_in_file_gently(const char *config_filename,
const char *key, const char *value,
const char *value_pattern,
unsigned flags)
{
int fd = -1, in_fd = -1;
int ret;
struct lock_file lock = LOCK_INIT;
char *filename_buf = NULL;
char *contents = NULL;
size_t contents_sz;
struct config_store_data store;
memset(&store, 0, sizeof(store));
/* parse-key returns negative; flip the sign to feed exit(3) */
ret = 0 - git_config_parse_key(key, &store.key, &store.baselen);
if (ret)
goto out_free;
store.multi_replace = (flags & CONFIG_FLAGS_MULTI_REPLACE) != 0;
if (!config_filename)
config_filename = filename_buf = git_pathdup("config");
/*
* The lock serves a purpose in addition to locking: the new
* contents of .git/config will be written into it.
*/
fd = hold_lock_file_for_update(&lock, config_filename, 0);
if (fd < 0) {
error_errno(_("could not lock config file %s"), config_filename);
ret = CONFIG_NO_LOCK;
goto out_free;
}
/*
* If .git/config does not exist yet, write a minimal version.
*/
in_fd = open(config_filename, O_RDONLY);
if ( in_fd < 0 ) {
if ( ENOENT != errno ) {
error_errno(_("opening %s"), config_filename);
ret = CONFIG_INVALID_FILE; /* same as "invalid config file" */
goto out_free;
}
/* if nothing to unset, error out */
if (value == NULL) {
ret = CONFIG_NOTHING_SET;
goto out_free;
}
free(store.key);
store.key = xstrdup(key);
if (write_section(fd, key, &store) < 0 ||
write_pair(fd, key, value, &store) < 0)
goto write_err_out;
} else {
struct stat st;
size_t copy_begin, copy_end;
int i, new_line = 0;
struct config_options opts;
if (value_pattern == NULL)
store.value_pattern = NULL;
else if (value_pattern == CONFIG_REGEX_NONE)
store.value_pattern = CONFIG_REGEX_NONE;
else if (flags & CONFIG_FLAGS_FIXED_VALUE)
store.fixed_value = value_pattern;
else {
if (value_pattern[0] == '!') {
store.do_not_match = 1;
value_pattern++;
} else
store.do_not_match = 0;
store.value_pattern = (regex_t*)xmalloc(sizeof(regex_t));
if (regcomp(store.value_pattern, value_pattern,
REG_EXTENDED)) {
error(_("invalid pattern: %s"), value_pattern);
FREE_AND_NULL(store.value_pattern);
ret = CONFIG_INVALID_PATTERN;
goto out_free;
}
}
ALLOC_GROW(store.parsed, 1, store.parsed_alloc);
store.parsed[0].end = 0;
memset(&opts, 0, sizeof(opts));
opts.event_fn = store_aux_event;
opts.event_fn_data = &store;
/*
* After this, store.parsed will contain offsets of all the
* parsed elements, and store.seen will contain a list of
* matches, as indices into store.parsed.
*
* As a side effect, we make sure to transform only a valid
* existing config file.
*/
if (git_config_from_file_with_options(store_aux,
config_filename,
&store, &opts)) {
error(_("invalid config file %s"), config_filename);
ret = CONFIG_INVALID_FILE;
goto out_free;
}
/* if nothing to unset, or too many matches, error out */
if ((store.seen_nr == 0 && value == NULL) ||
(store.seen_nr > 1 && !store.multi_replace)) {
ret = CONFIG_NOTHING_SET;
goto out_free;
}
if (fstat(in_fd, &st) == -1) {
error_errno(_("fstat on %s failed"), config_filename);
ret = CONFIG_INVALID_FILE;
goto out_free;
}
contents_sz = xsize_t(st.st_size);
contents = xmmap_gently(NULL, contents_sz, PROT_READ,
MAP_PRIVATE, in_fd, 0);
if (contents == MAP_FAILED) {
if (errno == ENODEV && S_ISDIR(st.st_mode))
errno = EISDIR;
error_errno(_("unable to mmap '%s'%s"),
config_filename, mmap_os_err());
ret = CONFIG_INVALID_FILE;
contents = NULL;
goto out_free;
}
close(in_fd);
in_fd = -1;
if (chmod(get_lock_file_path(&lock), st.st_mode & 07777) < 0) {
error_errno(_("chmod on %s failed"), get_lock_file_path(&lock));
ret = CONFIG_NO_WRITE;
goto out_free;
}
if (store.seen_nr == 0) {
if (!store.seen_alloc) {
/* Did not see key nor section */
ALLOC_GROW(store.seen, 1, store.seen_alloc);
store.seen[0] = store.parsed_nr
- !!store.parsed_nr;
}
store.seen_nr = 1;
}
for (i = 0, copy_begin = 0; i < store.seen_nr; i++) {
size_t replace_end;
int j = store.seen[i];
new_line = 0;
if (!store.key_seen) {
copy_end = store.parsed[j].end;
/* include '\n' when copying section header */
if (copy_end > 0 && copy_end < contents_sz &&
contents[copy_end - 1] != '\n' &&
contents[copy_end] == '\n')
copy_end++;
replace_end = copy_end;
} else {
replace_end = store.parsed[j].end;
copy_end = store.parsed[j].begin;
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
if (!value)
maybe_remove_section(&store,
git config --unset: remove empty sections (in the common case) The original reasoning for not removing section headers upon removal of the last entry went like this: the user could have added comments about the section, or about the entries therein, and if there were other comments there, we would not know whether we should remove them. In particular, a concocted example was presented that looked like this (and was added to t1300): # some generic comment on the configuration file itself # a comment specific to this "section" section. [section] # some intervening lines # that should also be dropped key = value # please be careful when you update the above variable The ideal thing for `git config --unset section.key` in this case would be to leave only the first line behind, because all the other comments are now obsolete. However, this is unfeasible, short of adding a complete Natural Language Processing module to Git, which seems not only a lot of work, but a totally unreasonable feature (for little benefit to most users). Now, the real kicker about this problem is: most users do not edit their config files at all! In their use case, the config looks like this instead: [section] key = value ... and it is totally obvious what should happen if the entry is removed: the entire section should vanish. Let's generalize this observation to this conservative strategy: if we are removing the last entry from a section, and there are no comments inside that section nor surrounding it, then remove the entire section. Otherwise behave as before: leave the now-empty section (including those comments, even ones about the now-deleted entry). We have to be extra careful to handle the case where more than one entry is removed: any subset of them might be the last entries of their respective sections (and if there are no comments in or around that section, the section should be removed, too). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-04-09 08:32:24 +00:00
&copy_end,
&replace_end, &i);
/*
* Swallow preceding white-space on the same
* line.
*/
while (copy_end > 0 ) {
char c = contents[copy_end - 1];
if (isspace(c) && c != '\n')
copy_end--;
else
break;
}
}
if (copy_end > 0 && contents[copy_end-1] != '\n')
new_line = 1;
/* write the first part of the config */
if (copy_end > copy_begin) {
if (write_in_full(fd, contents + copy_begin,
config: avoid "write_in_full(fd, buf, len) < len" pattern The return type of write_in_full() is a signed ssize_t, because we may return "-1" on failure (even if we succeeded in writing some bytes). But "len" itself is may be an unsigned type (the function takes a size_t, but of course we may have something else in the calling function). So while it seems like: if (write_in_full(fd, buf, len) < len) die_errno("write error"); would trigger on error, it won't if "len" is unsigned. The compiler sees a signed/unsigned comparison and promotes the signed value, resulting in (size_t)-1, the highest possible size_t (or again, whatever type the caller has). This cannot possibly be smaller than "len", and so the conditional can never trigger. I scoured the code base for cases of this, but it turns out that these two in git_config_set_multivar_in_file_gently() are the only ones. Here our "len" is the difference between two size_t variables, making the result an unsigned size_t. We can fix this by just checking for a negative return value directly, as write_in_full() will never return any value except -1 or the full count. There's no addition to the test suite here, since you need to convince write() to fail in order to see the problem. The simplest reproduction recipe I came up with is to trigger ENOSPC: # make a limited-size filesystem dd if=/dev/zero of=small.disk bs=1M count=1 mke2fs small.disk mkdir mnt sudo mount -o loop small.disk mnt cd mnt sudo chown $USER:$USER . # make a config file with some content git config --file=config one.key value git config --file=config two.key value # now fill up the disk dd if=/dev/zero of=fill # and try to delete a key, which requires copying the rest # of the file to config.lock, and will fail on write() git config --file=config --unset two.key That final command should (and does after this patch) produce an error message due to the failed write, and leave the file intact. Instead, it silently ignores the failure and renames config.lock into place, leaving you with a totally empty config file! Reported-by: demerphq <demerphq@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Reviewed-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-13 18:15:16 +00:00
copy_end - copy_begin) < 0)
goto write_err_out;
if (new_line &&
avoid "write_in_full(fd, buf, len) != len" pattern The return value of write_in_full() is either "-1", or the requested number of bytes[1]. If we make a partial write before seeing an error, we still return -1, not a partial value. This goes back to f6aa66cb95 (write_in_full: really write in full or return error on disk full., 2007-01-11). So checking anything except "was the return value negative" is pointless. And there are a couple of reasons not to do so: 1. It can do a funny signed/unsigned comparison. If your "len" is signed (e.g., a size_t) then the compiler will promote the "-1" to its unsigned variant. This works out for "!= len" (unless you really were trying to write the maximum size_t bytes), but is a bug if you check "< len" (an example of which was fixed recently in config.c). We should avoid promoting the mental model that you need to check the length at all, so that new sites are not tempted to copy us. 2. Checking for a negative value is shorter to type, especially when the length is an expression. 3. Linus says so. In d34cf19b89 (Clean up write_in_full() users, 2007-01-11), right after the write_in_full() semantics were changed, he wrote: I really wish every "write_in_full()" user would just check against "<0" now, but this fixes the nasty and stupid ones. Appeals to authority aside, this makes it clear that writing it this way does not have an intentional benefit. It's a historical curiosity that we never bothered to clean up (and which was undoubtedly cargo-culted into new sites). So let's convert these obviously-correct cases (this includes write_str_in_full(), which is just a wrapper for write_in_full()). [1] A careful reader may notice there is one way that write_in_full() can return a different value. If we ask write() to write N bytes and get a return value that is _larger_ than N, we could return a larger total. But besides the fact that this would imply a totally broken version of write(), it would already invoke undefined behavior. Our internal remaining counter is an unsigned size_t, which means that subtracting too many byte will wrap it around to a very large number. So we'll instantly begin reading off the end of the buffer, trying to write gigabytes (or petabytes) of data. Signed-off-by: Jeff King <peff@peff.net> Reviewed-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-13 17:16:03 +00:00
write_str_in_full(fd, "\n") < 0)
goto write_err_out;
}
copy_begin = replace_end;
}
/* write the pair (value == NULL means unset) */
if (value != NULL) {
if (!store.section_seen) {
if (write_section(fd, key, &store) < 0)
goto write_err_out;
}
if (write_pair(fd, key, value, &store) < 0)
goto write_err_out;
}
/* write the rest of the config */
if (copy_begin < contents_sz)
if (write_in_full(fd, contents + copy_begin,
config: avoid "write_in_full(fd, buf, len) < len" pattern The return type of write_in_full() is a signed ssize_t, because we may return "-1" on failure (even if we succeeded in writing some bytes). But "len" itself is may be an unsigned type (the function takes a size_t, but of course we may have something else in the calling function). So while it seems like: if (write_in_full(fd, buf, len) < len) die_errno("write error"); would trigger on error, it won't if "len" is unsigned. The compiler sees a signed/unsigned comparison and promotes the signed value, resulting in (size_t)-1, the highest possible size_t (or again, whatever type the caller has). This cannot possibly be smaller than "len", and so the conditional can never trigger. I scoured the code base for cases of this, but it turns out that these two in git_config_set_multivar_in_file_gently() are the only ones. Here our "len" is the difference between two size_t variables, making the result an unsigned size_t. We can fix this by just checking for a negative return value directly, as write_in_full() will never return any value except -1 or the full count. There's no addition to the test suite here, since you need to convince write() to fail in order to see the problem. The simplest reproduction recipe I came up with is to trigger ENOSPC: # make a limited-size filesystem dd if=/dev/zero of=small.disk bs=1M count=1 mke2fs small.disk mkdir mnt sudo mount -o loop small.disk mnt cd mnt sudo chown $USER:$USER . # make a config file with some content git config --file=config one.key value git config --file=config two.key value # now fill up the disk dd if=/dev/zero of=fill # and try to delete a key, which requires copying the rest # of the file to config.lock, and will fail on write() git config --file=config --unset two.key That final command should (and does after this patch) produce an error message due to the failed write, and leave the file intact. Instead, it silently ignores the failure and renames config.lock into place, leaving you with a totally empty config file! Reported-by: demerphq <demerphq@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Reviewed-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-13 18:15:16 +00:00
contents_sz - copy_begin) < 0)
goto write_err_out;
munmap(contents, contents_sz);
contents = NULL;
}
if (commit_lock_file(&lock) < 0) {
error_errno(_("could not write config file %s"), config_filename);
ret = CONFIG_NO_WRITE;
goto out_free;
}
ret = 0;
add `config_set` API for caching config-like files Currently `git_config()` uses a callback mechanism and file rereads for config values. Due to this approach, it is not uncommon for the config files to be parsed several times during the run of a git program, with different callbacks picking out different variables useful to themselves. Add a `config_set`, that can be used to construct an in-memory cache for config-like files that the caller specifies (i.e., files like `.gitmodules`, `~/.gitconfig` etc.). Add two external functions `git_configset_get_value` and `git_configset_get_value_multi` for querying from the config sets. `git_configset_get_value` follows `last one wins` semantic (i.e. if there are multiple matches for the queried key in the files of the configset the value returned will be the last entry in `value_list`). `git_configset_get_value_multi` returns a list of values sorted in order of increasing priority (i.e. last match will be at the end of the list). Add type specific query functions like `git_configset_get_bool` and similar. Add a default `config_set`, `the_config_set` to cache all key-value pairs read from usual config files (repo specific .git/config, user wide ~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set` is populated using `git_config()`. Add two external functions `git_config_get_value` and `git_config_get_value_multi` for querying in a non-callback manner from `the_config_set`. Also, add type specific query functions that are implemented as a thin wrapper around the `config_set` API. Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr> Signed-off-by: Tanay Abhra <tanayabh@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-28 10:10:38 +00:00
/* Invalidate the config cache */
git_config_clear();
out_free:
rollback_lock_file(&lock);
free(filename_buf);
if (contents)
munmap(contents, contents_sz);
if (in_fd >= 0)
close(in_fd);
config_store_data_clear(&store);
return ret;
write_err_out:
ret = write_error(get_lock_file_path(&lock));
goto out_free;
}
void git_config_set_multivar_in_file(const char *config_filename,
const char *key, const char *value,
const char *value_pattern, unsigned flags)
{
if (!git_config_set_multivar_in_file_gently(config_filename, key, value,
value_pattern, flags))
return;
if (value)
die(_("could not set '%s' to '%s'"), key, value);
else
die(_("could not unset '%s'"), key);
}
int git_config_set_multivar_gently(const char *key, const char *value,
const char *value_pattern, unsigned flags)
{
return git_config_set_multivar_in_file_gently(NULL, key, value, value_pattern,
flags);
}
void git_config_set_multivar(const char *key, const char *value,
const char *value_pattern, unsigned flags)
{
git_config_set_multivar_in_file(NULL, key, value, value_pattern,
flags);
}
static int section_name_match (const char *buf, const char *name)
{
int i = 0, j = 0, dot = 0;
if (buf[i] != '[')
return 0;
for (i = 1; buf[i] && buf[i] != ']'; i++) {
if (!dot && isspace(buf[i])) {
dot = 1;
if (name[j++] != '.')
break;
for (i++; isspace(buf[i]); i++)
; /* do nothing */
if (buf[i] != '"')
break;
continue;
}
if (buf[i] == '\\' && dot)
i++;
else if (buf[i] == '"' && dot) {
for (i++; isspace(buf[i]); i++)
; /* do_nothing */
break;
}
if (buf[i] != name[j++])
break;
}
if (buf[i] == ']' && name[j] == 0) {
/*
* We match, now just find the right length offset by
* gobbling up any whitespace after it, as well
*/
i++;
for (; buf[i] && isspace(buf[i]); i++)
; /* do nothing */
return i;
}
return 0;
}
static int section_name_is_ok(const char *name)
{
/* Empty section names are bogus. */
if (!*name)
return 0;
/*
* Before a dot, we must be alphanumeric or dash. After the first dot,
* anything goes, so we can stop checking.
*/
for (; *name && *name != '.'; name++)
if (*name != '-' && !isalnum(*name))
return 0;
return 1;
}
/* if new_name == NULL, the section is removed instead */
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
static int git_config_copy_or_rename_section_in_file(const char *config_filename,
const char *old_name,
const char *new_name, int copy)
{
int ret = 0, remove = 0;
char *filename_buf = NULL;
struct lock_file lock = LOCK_INIT;
int out_fd;
char buf[1024];
FILE *config_file = NULL;
struct stat st;
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
struct strbuf copystr = STRBUF_INIT;
struct config_store_data store;
memset(&store, 0, sizeof(store));
if (new_name && !section_name_is_ok(new_name)) {
ret = error(_("invalid section name: %s"), new_name);
goto out_no_rollback;
}
if (!config_filename)
config_filename = filename_buf = git_pathdup("config");
out_fd = hold_lock_file_for_update(&lock, config_filename, 0);
if (out_fd < 0) {
ret = error(_("could not lock config file %s"), config_filename);
goto out;
}
if (!(config_file = fopen(config_filename, "rb"))) {
ret = warn_on_fopen_errors(config_filename);
if (ret)
goto out;
/* no config file means nothing to rename, no error */
goto commit_and_out;
}
if (fstat(fileno(config_file), &st) == -1) {
ret = error_errno(_("fstat on %s failed"), config_filename);
goto out;
}
if (chmod(get_lock_file_path(&lock), st.st_mode & 07777) < 0) {
ret = error_errno(_("chmod on %s failed"),
get_lock_file_path(&lock));
goto out;
}
while (fgets(buf, sizeof(buf), config_file)) {
config: work around gcc-10 -Wstringop-overflow warning Compiling with gcc-10, -O2, and -fsanitize=undefined results in a compiler warning: config.c: In function ‘git_config_copy_or_rename_section_in_file’: config.c:3170:17: error: writing 1 byte into a region of size 0 [-Werror=stringop-overflow=] 3170 | output[0] = '\t'; | ~~~~~~~~~~^~~~~~ config.c:3076:7: note: at offset -1 to object ‘buf’ with size 1024 declared here 3076 | char buf[1024]; | ^~~ This is a false positive. The interesting lines of code are: int i; char *output = buf; ... for (i = 0; buf[i] && isspace(buf[i]); i++) ; /* do nothing */ ... int offset; offset = section_name_match(&buf[i], old_name); if (offset > 0) { ... output += offset + i; if (strlen(output) > 0) { /* * More content means there's * a declaration to put on the * next line; indent with a * tab */ output -= 1; output[0] = '\t'; } } So we do assign output to buf initially. Later we increment it based on "offset" and "i" and then subtract "1" from it. That latter step is what the compiler is complaining about; it could lead to going off the left side of the array if "output == buf" at the moment of the subtraction. For that to be the case, then "offset + i" would have to be 0. But that can't happen: - we know that "offset" is at least 1, since we're in a conditional block that checks that - we know that "i" is not negative, since it started at 0 and only incremented over whitespace So the sum must be at least 1, and therefore it's OK to subtract one from "output". But that's not quite the whole story. Since "i" is an int, it could in theory be possible to overflow to negative (when counting whitespace on a very large string). But we know that's impossible because we're counting the 1024-byte buffer we just fed to fgets(), so it can never be larger than that. Switching the type of "i" to "unsigned" makes the warning go away, so let's do that. Arguably size_t is an even better type (for this and for the other length fields), but switching to it produces a similar but distinct warning: config.c: In function ‘git_config_copy_or_rename_section_in_file’: config.c:3170:13: error: array subscript -1 is outside array bounds of ‘char[1024]’ [-Werror=array-bounds] 3170 | output[0] = '\t'; | ~~~~~~^~~ config.c:3076:7: note: while referencing ‘buf’ 3076 | char buf[1024]; | ^~~ If we were to ever switch off of fgets() to strbuf_getline() or similar, we'd probably need to use size_t to avoid other overflow problems. But for now we know we're safe because of the small fixed size of our buffer. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-04 07:43:53 +00:00
unsigned i;
int length;
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
int is_section = 0;
char *output = buf;
for (i = 0; buf[i] && isspace(buf[i]); i++)
; /* do nothing */
if (buf[i] == '[') {
/* it's a section */
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
int offset;
is_section = 1;
/*
* When encountering a new section under -c we
* need to flush out any section we're already
* coping and begin anew. There might be
* multiple [branch "$name"] sections.
*/
if (copystr.len > 0) {
if (write_in_full(out_fd, copystr.buf, copystr.len) < 0) {
ret = write_error(get_lock_file_path(&lock));
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
goto out;
}
strbuf_reset(&copystr);
}
offset = section_name_match(&buf[i], old_name);
if (offset > 0) {
ret++;
if (new_name == NULL) {
remove = 1;
continue;
}
store.baselen = strlen(new_name);
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
if (!copy) {
if (write_section(out_fd, new_name, &store) < 0) {
ret = write_error(get_lock_file_path(&lock));
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
goto out;
}
/*
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
* We wrote out the new section, with
* a newline, now skip the old
* section's length
*/
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
output += offset + i;
if (strlen(output) > 0) {
/*
* More content means there's
* a declaration to put on the
* next line; indent with a
* tab
*/
output -= 1;
output[0] = '\t';
}
} else {
copystr = store_create_section(new_name, &store);
}
}
remove = 0;
}
if (remove)
continue;
length = strlen(output);
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
if (!is_section && copystr.len > 0) {
strbuf_add(&copystr, output, length);
}
avoid "write_in_full(fd, buf, len) != len" pattern The return value of write_in_full() is either "-1", or the requested number of bytes[1]. If we make a partial write before seeing an error, we still return -1, not a partial value. This goes back to f6aa66cb95 (write_in_full: really write in full or return error on disk full., 2007-01-11). So checking anything except "was the return value negative" is pointless. And there are a couple of reasons not to do so: 1. It can do a funny signed/unsigned comparison. If your "len" is signed (e.g., a size_t) then the compiler will promote the "-1" to its unsigned variant. This works out for "!= len" (unless you really were trying to write the maximum size_t bytes), but is a bug if you check "< len" (an example of which was fixed recently in config.c). We should avoid promoting the mental model that you need to check the length at all, so that new sites are not tempted to copy us. 2. Checking for a negative value is shorter to type, especially when the length is an expression. 3. Linus says so. In d34cf19b89 (Clean up write_in_full() users, 2007-01-11), right after the write_in_full() semantics were changed, he wrote: I really wish every "write_in_full()" user would just check against "<0" now, but this fixes the nasty and stupid ones. Appeals to authority aside, this makes it clear that writing it this way does not have an intentional benefit. It's a historical curiosity that we never bothered to clean up (and which was undoubtedly cargo-culted into new sites). So let's convert these obviously-correct cases (this includes write_str_in_full(), which is just a wrapper for write_in_full()). [1] A careful reader may notice there is one way that write_in_full() can return a different value. If we ask write() to write N bytes and get a return value that is _larger_ than N, we could return a larger total. But besides the fact that this would imply a totally broken version of write(), it would already invoke undefined behavior. Our internal remaining counter is an unsigned size_t, which means that subtracting too many byte will wrap it around to a very large number. So we'll instantly begin reading off the end of the buffer, trying to write gigabytes (or petabytes) of data. Signed-off-by: Jeff King <peff@peff.net> Reviewed-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-13 17:16:03 +00:00
if (write_in_full(out_fd, output, length) < 0) {
ret = write_error(get_lock_file_path(&lock));
goto out;
}
}
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
/*
* Copy a trailing section at the end of the config, won't be
* flushed by the usual "flush because we have a new section
* logic in the loop above.
*/
if (copystr.len > 0) {
if (write_in_full(out_fd, copystr.buf, copystr.len) < 0) {
ret = write_error(get_lock_file_path(&lock));
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
goto out;
}
strbuf_reset(&copystr);
}
fclose(config_file);
config_file = NULL;
commit_and_out:
if (commit_lock_file(&lock) < 0)
ret = error_errno(_("could not write config file %s"),
config_filename);
out:
if (config_file)
fclose(config_file);
rollback_lock_file(&lock);
out_no_rollback:
free(filename_buf);
config_store_data_clear(&store);
return ret;
}
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
int git_config_rename_section_in_file(const char *config_filename,
const char *old_name, const char *new_name)
{
return git_config_copy_or_rename_section_in_file(config_filename,
old_name, new_name, 0);
}
int git_config_rename_section(const char *old_name, const char *new_name)
{
return git_config_rename_section_in_file(NULL, old_name, new_name);
}
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 21:19:16 +00:00
int git_config_copy_section_in_file(const char *config_filename,
const char *old_name, const char *new_name)
{
return git_config_copy_or_rename_section_in_file(config_filename,
old_name, new_name, 1);
}
int git_config_copy_section(const char *old_name, const char *new_name)
{
return git_config_copy_section_in_file(NULL, old_name, new_name);
}
/*
* Call this to report error for your variable that should not
* get a boolean value (i.e. "[my] var" means "true").
*/
#undef config_error_nonbool
int config_error_nonbool(const char *var)
{
return error(_("missing value for '%s'"), var);
}
int parse_config_key(const char *var,
const char *section,
const char **subsection, size_t *subsection_len,
const char **key)
{
const char *dot;
/* Does it start with "section." ? */
if (!skip_prefix(var, section, &var) || *var != '.')
return -1;
/*
* Find the key; we don't know yet if we have a subsection, but we must
* parse backwards from the end, since the subsection may have dots in
* it, too.
*/
dot = strrchr(var, '.');
*key = dot + 1;
/* Did we have a subsection at all? */
if (dot == var) {
if (subsection) {
*subsection = NULL;
*subsection_len = 0;
}
}
else {
if (!subsection)
return -1;
*subsection = var + 1;
*subsection_len = dot - *subsection;
}
return 0;
}
const char *current_config_origin_type(void)
{
int type;
if (current_config_kvi)
type = current_config_kvi->origin_type;
else if(cf)
type = cf->origin_type;
else
BUG("current_config_origin_type called outside config callback");
switch (type) {
case CONFIG_ORIGIN_BLOB:
return "blob";
case CONFIG_ORIGIN_FILE:
return "file";
case CONFIG_ORIGIN_STDIN:
return "standard input";
case CONFIG_ORIGIN_SUBMODULE_BLOB:
return "submodule-blob";
case CONFIG_ORIGIN_CMDLINE:
return "command line";
default:
BUG("unknown config origin type");
}
}
const char *config_scope_name(enum config_scope scope)
{
switch (scope) {
case CONFIG_SCOPE_SYSTEM:
return "system";
case CONFIG_SCOPE_GLOBAL:
return "global";
case CONFIG_SCOPE_LOCAL:
return "local";
case CONFIG_SCOPE_WORKTREE:
return "worktree";
case CONFIG_SCOPE_COMMAND:
return "command";
case CONFIG_SCOPE_SUBMODULE:
return "submodule";
default:
return "unknown";
}
}
const char *current_config_name(void)
{
const char *name;
if (current_config_kvi)
name = current_config_kvi->filename;
else if (cf)
name = cf->name;
else
BUG("current_config_name called outside config callback");
return name ? name : "";
}
enum config_scope current_config_scope(void)
{
if (current_config_kvi)
return current_config_kvi->scope;
else
return current_parsing_scope;
}
int current_config_line(void)
{
if (current_config_kvi)
return current_config_kvi->linenr;
else
return cf->linenr;
}
int lookup_config(const char **mapping, int nr_mapping, const char *var)
{
int i;
for (i = 0; i < nr_mapping; i++) {
const char *name = mapping[i];
if (name && !strcasecmp(var, name))
return i;
}
return -1;
}