git/environment.c
Steffen Prohaska 21e5ad50fc 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 13:07:28 -08:00

138 lines
3.6 KiB
C

/*
* We put all the git config variables in this same object
* file, so that programs can link against the config parser
* without having to link against all the rest of git.
*
* In particular, no need to bring in libz etc unless needed,
* even if you might want to know where the git directory etc
* are.
*/
#include "cache.h"
char git_default_email[MAX_GITNAME];
char git_default_name[MAX_GITNAME];
int trust_executable_bit = 1;
int quote_path_fully = 1;
int has_symlinks = 1;
int assume_unchanged;
int prefer_symlink_refs;
int is_bare_repository_cfg = -1; /* unspecified */
int log_all_ref_updates = -1; /* unspecified */
int warn_ambiguous_refs = 1;
int repository_format_version;
const char *git_commit_encoding;
const char *git_log_output_encoding;
int shared_repository = PERM_UMASK;
const char *apply_default_whitespace;
int zlib_compression_level = Z_BEST_SPEED;
int core_compression_level;
int core_compression_seen;
size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE;
size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT;
size_t delta_base_cache_limit = 16 * 1024 * 1024;
char *pager_program;
int pager_use_color = 1;
char *editor_program;
char *excludes_file;
int auto_crlf = 0; /* 1: both ways, -1: only when adding git objects */
enum safe_crlf safe_crlf = SAFE_CRLF_WARN;
unsigned whitespace_rule_cfg = WS_DEFAULT_RULE;
/* This is set by setup_git_dir_gently() and/or git_default_config() */
char *git_work_tree_cfg;
static const char *work_tree;
static const char *git_dir;
static char *git_object_dir, *git_index_file, *git_refs_dir, *git_graft_file;
static void setup_git_env(void)
{
git_dir = getenv(GIT_DIR_ENVIRONMENT);
if (!git_dir)
git_dir = DEFAULT_GIT_DIR_ENVIRONMENT;
git_object_dir = getenv(DB_ENVIRONMENT);
if (!git_object_dir) {
git_object_dir = xmalloc(strlen(git_dir) + 9);
sprintf(git_object_dir, "%s/objects", git_dir);
}
git_refs_dir = xmalloc(strlen(git_dir) + 6);
sprintf(git_refs_dir, "%s/refs", git_dir);
git_index_file = getenv(INDEX_ENVIRONMENT);
if (!git_index_file) {
git_index_file = xmalloc(strlen(git_dir) + 7);
sprintf(git_index_file, "%s/index", git_dir);
}
git_graft_file = getenv(GRAFT_ENVIRONMENT);
if (!git_graft_file)
git_graft_file = xstrdup(git_path("info/grafts"));
}
int is_bare_repository(void)
{
/* if core.bare is not 'false', let's see if there is a work tree */
return is_bare_repository_cfg && !get_git_work_tree();
}
const char *get_git_dir(void)
{
if (!git_dir)
setup_git_env();
return git_dir;
}
const char *get_git_work_tree(void)
{
static int initialized = 0;
if (!initialized) {
work_tree = getenv(GIT_WORK_TREE_ENVIRONMENT);
/* core.bare = true overrides implicit and config work tree */
if (!work_tree && is_bare_repository_cfg < 1) {
work_tree = git_work_tree_cfg;
/* make_absolute_path also normalizes the path */
if (work_tree && !is_absolute_path(work_tree))
work_tree = xstrdup(make_absolute_path(git_path(work_tree)));
} else if (work_tree)
work_tree = xstrdup(make_absolute_path(work_tree));
initialized = 1;
if (work_tree)
is_bare_repository_cfg = 0;
}
return work_tree;
}
char *get_object_directory(void)
{
if (!git_object_dir)
setup_git_env();
return git_object_dir;
}
char *get_refs_directory(void)
{
if (!git_refs_dir)
setup_git_env();
return git_refs_dir;
}
char *get_index_file(void)
{
if (!git_index_file)
setup_git_env();
return git_index_file;
}
char *get_graft_file(void)
{
if (!git_graft_file)
setup_git_env();
return git_graft_file;
}
int set_git_dir(const char *path)
{
if (setenv(GIT_DIR_ENVIRONMENT, path, 1))
return error("Could not set GIT_DIR to '%s'", path);
setup_git_env();
return 0;
}