git/userdiff.c

482 lines
15 KiB
C
Raw Normal View History

#include "git-compat-util.h"
#include "alloc.h"
#include "config.h"
#include "userdiff.h"
#include "attr.h"
#include "strbuf.h"
static struct userdiff_driver *drivers;
static int ndrivers;
static int drivers_alloc;
#define PATTERNS(lang, rx, wrx) { \
.name = lang, \
.binary = -1, \
.funcname = { \
.pattern = rx, \
.cflags = REG_EXTENDED, \
}, \
.word_regex = wrx "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+", \
}
#define IPATTERN(lang, rx, wrx) { \
.name = lang, \
.binary = -1, \
.funcname = { \
.pattern = rx, \
.cflags = REG_EXTENDED | REG_ICASE, \
}, \
.word_regex = wrx "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+", \
}
/*
* Built-in drivers for various languages, sorted by their names
* (except that the "default" is left at the end).
*
* When writing or updating patterns, assume that the contents these
* patterns are applied to are syntactically correct. The patterns
* can be simple without implementing all syntactical corner cases, as
* long as they are sufficiently permissive.
*/
static struct userdiff_driver builtin_drivers[] = {
IPATTERN("ada",
"!^(.*[ \t])?(is[ \t]+new|renames|is[ \t]+separate)([ \t].*)?$\n"
"!^[ \t]*with[ \t].*$\n"
"^[ \t]*((procedure|function)[ \t]+.*)$\n"
"^[ \t]*((package|protected|task)[ \t]+.*)$",
/* -- */
"[a-zA-Z][a-zA-Z0-9_]*"
"|[-+]?[0-9][0-9#_.aAbBcCdDeEfF]*([eE][+-]?[0-9_]+)?"
"|=>|\\.\\.|\\*\\*|:=|/=|>=|<=|<<|>>|<>"),
PATTERNS("bash",
/* Optional leading indentation */
"^[ \t]*"
/* Start of captured text */
"("
"("
/* POSIX identifier with mandatory parentheses */
"[a-zA-Z_][a-zA-Z0-9_]*[ \t]*\\([ \t]*\\))"
"|"
/* Bashism identifier with optional parentheses */
"(function[ \t]+[a-zA-Z_][a-zA-Z0-9_]*(([ \t]*\\([ \t]*\\))|([ \t]+))"
")"
/* Optional whitespace */
"[ \t]*"
/* Compound command starting with `{`, `(`, `((` or `[[` */
"(\\{|\\(\\(?|\\[\\[)"
/* End of captured text */
")",
/* -- */
/* Characters not in the default $IFS value */
"[^ \t]+"),
PATTERNS("bibtex",
"(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
/* -- */
"[={}\"]|[^={}\" \t]+"),
PATTERNS("cpp",
/* Jump targets or access declarations */
"!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:[[:space:]]*($|/[/*])\n"
/* functions/methods, variables, and compounds at top level */
"^((::[[:space:]]*)?[A-Za-z_].*)$",
/* -- */
/* identifiers and keywords */
"[a-zA-Z_][a-zA-Z0-9_]*"
/* decimal and octal integers as well as floatingpoint numbers */
"|[0-9][0-9.]*([Ee][-+]?[0-9]+)?[fFlLuU]*"
/* hexadecimal and binary integers */
"|0[xXbB][0-9a-fA-F]+[lLuU]*"
/* floatingpoint numbers that begin with a decimal point */
"|\\.[0-9][0-9]*([Ee][-+]?[0-9]+)?[fFlL]?"
"|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->\\*?|\\.\\*|<=>"),
PATTERNS("csharp",
/* Keywords */
"!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n"
/* Methods and constructors */
"^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe|async)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[<>@._[:alnum:]]+[ \t]*\\(.*\\))[ \t]*$\n"
/* Properties */
"^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[@._[:alnum:]]+)[ \t]*$\n"
/* Type definitions */
"^[ \t]*(((static|public|internal|private|protected|new|unsafe|sealed|abstract|partial)[ \t]+)*(class|enum|interface|struct|record)[ \t]+.*)$\n"
/* Namespace */
"^[ \t]*(namespace[ \t]+.*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
IPATTERN("css",
"![:;][[:space:]]*$\n"
"^[:[@.#]?[_a-z0-9].*$",
/* -- */
/*
* This regex comes from W3C CSS specs. Should theoretically also
* allow ISO 10646 characters U+00A0 and higher,
* but they are not handled in this regex.
*/
"-?[_a-zA-Z][-_a-zA-Z0-9]*" /* identifiers */
"|-?[0-9]+|\\#[0-9a-fA-F]+" /* numbers */
),
PATTERNS("dts",
"!;\n"
"!=\n"
/* lines beginning with a word optionally preceded by '&' or the root */
"^[ \t]*((/[ \t]*\\{|&?[a-zA-Z_]).*)",
/* -- */
/* Property names and math operators */
"[a-zA-Z0-9,._+?#-]+"
"|[-+*/%&^|!~]|>>|<<|&&|\\|\\|"),
PATTERNS("elixir",
"^[ \t]*((def(macro|module|impl|protocol|p)?|test)[ \t].*)$",
/* -- */
/* Atoms, names, and module attributes */
"[@:]?[a-zA-Z0-9@_?!]+"
/* Numbers with specific base */
"|[-+]?0[xob][0-9a-fA-F]+"
/* Numbers */
"|[-+]?[0-9][0-9_.]*([eE][-+]?[0-9_]+)?"
/* Operators and atoms that represent them */
"|:?(\\+\\+|--|\\.\\.|~~~|<>|\\^\\^\\^|<?\\|>|<<<?|>?>>|<<?~|~>?>|<~>|<=|>=|===?|!==?|=~|&&&?|\\|\\|\\|?|=>|<-|\\\\\\\\|->)"
/* Not real operators, but should be grouped */
"|:?%[A-Za-z0-9_.]\\{\\}?"),
IPATTERN("fortran",
/* Don't match comment lines */
"!^([C*]|[ \t]*!)\n"
/* Don't match 'module procedure' lines */
"!^[ \t]*MODULE[ \t]+PROCEDURE[ \t]\n"
/* Program, module, block data */
"^[ \t]*((END[ \t]+)?(PROGRAM|MODULE|BLOCK[ \t]+DATA"
/* Subroutines and functions */
"|([^!'\" \t]+[ \t]+)*(SUBROUTINE|FUNCTION))[ \t]+[A-Z].*)$",
/* -- */
"[a-zA-Z][a-zA-Z0-9_]*"
"|\\.([Ee][Qq]|[Nn][Ee]|[Gg][TtEe]|[Ll][TtEe]|[Tt][Rr][Uu][Ee]|[Ff][Aa][Ll][Ss][Ee]|[Aa][Nn][Dd]|[Oo][Rr]|[Nn]?[Ee][Qq][Vv]|[Nn][Oo][Tt])\\."
/* numbers and format statements like 2E14.4, or ES12.6, 9X.
* Don't worry about format statements without leading digits since
* they would have been matched above as a variable anyway. */
"|[-+]?[0-9.]+([AaIiDdEeFfLlTtXx][Ss]?[-+]?[0-9.]*)?(_[a-zA-Z0-9][a-zA-Z0-9_]*)?"
"|//|\\*\\*|::|[/<>=]="),
IPATTERN("fountain",
"^((\\.[^.]|(int|ext|est|int\\.?/ext|i/e)[. ]).*)$",
/* -- */
"[^ \t-]+"),
PATTERNS("golang",
/* Functions */
"^[ \t]*(func[ \t]*.*(\\{[ \t]*)?)\n"
/* Structs and interfaces */
"^[ \t]*(type[ \t].*(struct|interface)[ \t]*(\\{[ \t]*)?)",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.eE]+i?|0[xX]?[0-9a-fA-F]+i?"
"|[-+*/<>%&^|=!:]=|--|\\+\\+|<<=?|>>=?|&\\^=?|&&|\\|\\||<-|\\.{3}"),
PATTERNS("html",
"^[ \t]*(<[Hh][1-6]([ \t].*)?>.*)$",
/* -- */
"[^<>= \t]+"),
PATTERNS("java",
"!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
/* Class, enum, interface, and record declarations */
"^[ \t]*(([a-z-]+[ \t]+)*(class|enum|interface|record)[ \t]+.*)$\n"
/* Method definitions; note that constructor signatures are not */
/* matched because they are indistinguishable from method calls. */
"^[ \t]*(([A-Za-z_<>&][][?&<>.,A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]="
"|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"),
PATTERNS("kotlin",
"^[ \t]*(([a-z]+[ \t]+)*(fun|class|interface)[ \t]+.*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
/* hexadecimal and binary numbers */
"|0[xXbB][0-9a-fA-F_]+[lLuU]*"
/* integers and floats */
"|[0-9][0-9_]*([.][0-9_]*)?([Ee][-+]?[0-9]+)?[fFlLuU]*"
/* floating point numbers beginning with decimal point */
"|[.][0-9][0-9_]*([Ee][-+]?[0-9]+)?[fFlLuU]?"
/* unary and binary operators */
"|[-+*/<>%&^|=!]==?|--|\\+\\+|<<=|>>=|&&|\\|\\||->|\\.\\*|!!|[?:.][.:]"),
PATTERNS("markdown",
"^ {0,3}#{1,6}[ \t].*",
/* -- */
"[^<>= \t]+"),
PATTERNS("matlab",
/*
* Octave pattern is mostly the same as matlab, except that '%%%' and
* '##' can also be used to begin code sections, in addition to '%%'
* that is understood by both.
*/
"^[[:space:]]*((classdef|function)[[:space:]].*)$|^(%%%?|##)[[:space:]].*$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*|[-+0-9.e]+|[=~<>]=|\\.[*/\\^']|\\|\\||&&"),
PATTERNS("objc",
/* Negate C statements that can look like functions */
"!^[ \t]*(do|for|if|else|return|switch|while)\n"
/* Objective-C methods */
"^[ \t]*([-+][ \t]*\\([ \t]*[A-Za-z_][A-Za-z_0-9* \t]*\\)[ \t]*[A-Za-z_].*)$\n"
/* C functions */
"^[ \t]*(([A-Za-z_][A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$\n"
/* Objective-C class/protocol definitions */
"^(@(implementation|interface|protocol)[ \t].*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
PATTERNS("pascal",
"^(((class[ \t]+)?(procedure|function)|constructor|destructor|interface"
"|implementation|initialization|finalization)[ \t]*.*)$\n"
"^(.*=[ \t]*(class|record).*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
"|<>|<=|>=|:=|\\.\\."),
PATTERNS("perl",
"^package .*\n"
"^sub [[:alnum:]_':]+[ \t]*"
"(\\([^)]*\\)[ \t]*)?" /* prototype */
/*
* Attributes. A regex can't count nested parentheses,
* so just slurp up whatever we see, taking care not
* to accept lines like "sub foo; # defined elsewhere".
*
* An attribute could contain a semicolon, but at that
* point it seems reasonable enough to give up.
*/
"(:[^;#]*)?"
"(\\{[ \t]*)?" /* brace can come here or on the next line */
"(#.*)?$\n" /* comment */
"^(BEGIN|END|INIT|CHECK|UNITCHECK|AUTOLOAD|DESTROY)[ \t]*"
"(\\{[ \t]*)?" /* brace can come here or on the next line */
"(#.*)?$\n"
"^=head[0-9] .*", /* POD */
/* -- */
"[[:alpha:]_'][[:alnum:]_']*"
"|0[xb]?[0-9a-fA-F_]*"
/* taking care not to interpret 3..5 as (3.)(.5) */
"|[0-9a-fA-F_]+(\\.[0-9a-fA-F_]+)?([eE][-+]?[0-9_]+)?"
"|=>|-[rwxoRWXOezsfdlpSugkbctTBMAC>]|~~|::"
"|&&=|\\|\\|=|//=|\\*\\*="
"|&&|\\|\\||//|\\+\\+|--|\\*\\*|\\.\\.\\.?"
"|[-+*/%.^&<>=!|]="
"|=~|!~"
"|<<|<>|<=>|>>"),
PATTERNS("php",
"^[\t ]*(((public|protected|private|static|abstract|final)[\t ]+)*function.*)$\n"
"^[\t ]*((((final|abstract)[\t ]+)?class|enum|interface|trait).*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
"|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"),
PATTERNS("python",
"^[ \t]*((class|(async[ \t]+)?def)[ \t].*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"),
/* -- */
PATTERNS("ruby",
"^[ \t]*((class|module|def)[ \t].*)$",
/* -- */
"(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
"|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"),
PATTERNS("rust",
"^[\t ]*((pub(\\([^\\)]+\\))?[\t ]+)?((async|const|unsafe|extern([\t ]+\"[^\"]+\"))[\t ]+)?(struct|enum|union|mod|trait|fn|impl|macro_rules!)[< \t]+[^;]*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[0-9][0-9_a-fA-Fiosuxz]*(\\.([0-9]*[eE][+-]?)?[0-9_fF]*)?"
"|[-+*\\/<>%&^|=!:]=|<<=?|>>=?|&&|\\|\\||->|=>|\\.{2}=|\\.{3}|::"),
PATTERNS("scheme",
"^[\t ]*(\\(((define|def(struct|syntax|class|method|rules|record|proto|alias)?)[-*/ \t]|(library|module|struct|class)[*+ \t]).*)$",
/*
* R7RS valid identifiers include any sequence enclosed
* within vertical lines having no backslashes
*/
"\\|([^\\\\]*)\\|"
/* All other words should be delimited by spaces or parentheses */
"|([^][)(}{[ \t])+"),
PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
"\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+"),
{ "default", NULL, NULL, -1, { NULL, 0 } },
};
#undef PATTERNS
#undef IPATTERN
static struct userdiff_driver driver_true = {
.name = "diff=true",
.binary = 0,
};
static struct userdiff_driver driver_false = {
.name = "!diff",
.binary = 1,
};
struct find_by_namelen_data {
const char *name;
size_t len;
struct userdiff_driver *driver;
};
static int userdiff_find_by_namelen_cb(struct userdiff_driver *driver,
enum userdiff_driver_type type UNUSED,
void *priv)
{
struct find_by_namelen_data *cb_data = priv;
if (!strncmp(driver->name, cb_data->name, cb_data->len) &&
!driver->name[cb_data->len]) {
cb_data->driver = driver;
return 1; /* tell the caller to stop iterating */
}
return 0;
}
static struct userdiff_driver *userdiff_find_by_namelen(const char *name, size_t len)
{
struct find_by_namelen_data udcbdata = {
.name = name,
.len = len,
};
for_each_userdiff_driver(userdiff_find_by_namelen_cb, &udcbdata);
return udcbdata.driver;
}
static int parse_funcname(struct userdiff_funcname *f, const char *k,
const char *v, int cflags)
{
if (git_config_string(&f->pattern, k, v) < 0)
return -1;
f->cflags = cflags;
drop odd return value semantics from userdiff_config When the userdiff_config function was introduced in be58e70 (diff: unify external diff and funcname parsing code, 2008-10-05), it used a return value convention unlike any other config callback. Like other callbacks, it used "-1" to signal error. But it returned "1" to indicate that it found something, and "0" otherwise; other callbacks simply returned "0" to indicate that no error occurred. This distinction was necessary at the time, because the userdiff namespace overlapped slightly with the color configuration namespace. So "diff.color.foo" could mean "the 'foo' slot of diff coloring" or "the 'foo' component of the "color" userdiff driver". Because the color-parsing code would die on an unknown color slot, we needed the userdiff code to indicate that it had matched the variable, letting us bypass the color-parsing code entirely. Later, in 8b8e862 (ignore unknown color configuration, 2009-12-12), the color-parsing code learned to silently ignore unknown slots. This means we no longer need to protect userdiff-matched variables from reaching the color-parsing code. We can therefore change the userdiff_config calling convention to a more normal one. This drops some code from each caller, which is nice. But more importantly, it reduces the cognitive load for readers who may wonder why userdiff_config is unlike every other config callback. There's no need to add a new test confirming that this works; t4020 already contains a test that sets diff.color.external. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 18:23:02 +00:00
return 0;
}
diff: introduce diff.<driver>.binary The "diff" gitattribute is somewhat overloaded right now. It can say one of three things: 1. this file is definitely binary, or definitely not (i.e., diff or !diff) 2. this file should use an external diff engine (i.e., diff=foo, diff.foo.command = custom-script) 3. this file should use particular funcname patterns (i.e., diff=foo, diff.foo.(x?)funcname = some-regex) Most of the time, there is no conflict between these uses, since using one implies that the other is irrelevant (e.g., an external diff engine will decide for itself whether the file is binary). However, there is at least one conflicting situation: there is no way to say "use the regular rules to determine whether this file is binary, but if we do diff it textually, use this funcname pattern." That is, currently setting diff=foo indicates that the file is definitely text. This patch introduces a "binary" config option for a diff driver, so that one can explicitly set diff.foo.binary. We default this value to "don't know". That is, setting a diff attribute to "foo" and using "diff.foo.funcname" will have no effect on the binaryness of a file. To get the current behavior, one can set diff.foo.binary to true. This patch also has one additional advantage: it cleans up the interface to the userdiff code a bit. Before, calling code had to know more about whether attributes were false, true, or unset to determine binaryness. Now that binaryness is a property of a driver, we can represent these situations just by passing back a driver struct. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-05 21:43:36 +00:00
static int parse_tristate(int *b, const char *k, const char *v)
{
if (v && !strcasecmp(v, "auto"))
*b = -1;
else
*b = git_config_bool(k, v);
drop odd return value semantics from userdiff_config When the userdiff_config function was introduced in be58e70 (diff: unify external diff and funcname parsing code, 2008-10-05), it used a return value convention unlike any other config callback. Like other callbacks, it used "-1" to signal error. But it returned "1" to indicate that it found something, and "0" otherwise; other callbacks simply returned "0" to indicate that no error occurred. This distinction was necessary at the time, because the userdiff namespace overlapped slightly with the color configuration namespace. So "diff.color.foo" could mean "the 'foo' slot of diff coloring" or "the 'foo' component of the "color" userdiff driver". Because the color-parsing code would die on an unknown color slot, we needed the userdiff code to indicate that it had matched the variable, letting us bypass the color-parsing code entirely. Later, in 8b8e862 (ignore unknown color configuration, 2009-12-12), the color-parsing code learned to silently ignore unknown slots. This means we no longer need to protect userdiff-matched variables from reaching the color-parsing code. We can therefore change the userdiff_config calling convention to a more normal one. This drops some code from each caller, which is nice. But more importantly, it reduces the cognitive load for readers who may wonder why userdiff_config is unlike every other config callback. There's no need to add a new test confirming that this works; t4020 already contains a test that sets diff.color.external. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 18:23:02 +00:00
return 0;
diff: introduce diff.<driver>.binary The "diff" gitattribute is somewhat overloaded right now. It can say one of three things: 1. this file is definitely binary, or definitely not (i.e., diff or !diff) 2. this file should use an external diff engine (i.e., diff=foo, diff.foo.command = custom-script) 3. this file should use particular funcname patterns (i.e., diff=foo, diff.foo.(x?)funcname = some-regex) Most of the time, there is no conflict between these uses, since using one implies that the other is irrelevant (e.g., an external diff engine will decide for itself whether the file is binary). However, there is at least one conflicting situation: there is no way to say "use the regular rules to determine whether this file is binary, but if we do diff it textually, use this funcname pattern." That is, currently setting diff=foo indicates that the file is definitely text. This patch introduces a "binary" config option for a diff driver, so that one can explicitly set diff.foo.binary. We default this value to "don't know". That is, setting a diff attribute to "foo" and using "diff.foo.funcname" will have no effect on the binaryness of a file. To get the current behavior, one can set diff.foo.binary to true. This patch also has one additional advantage: it cleans up the interface to the userdiff code a bit. Before, calling code had to know more about whether attributes were false, true, or unset to determine binaryness. Now that binaryness is a property of a driver, we can represent these situations just by passing back a driver struct. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-05 21:43:36 +00:00
}
static int parse_bool(int *b, const char *k, const char *v)
{
*b = git_config_bool(k, v);
drop odd return value semantics from userdiff_config When the userdiff_config function was introduced in be58e70 (diff: unify external diff and funcname parsing code, 2008-10-05), it used a return value convention unlike any other config callback. Like other callbacks, it used "-1" to signal error. But it returned "1" to indicate that it found something, and "0" otherwise; other callbacks simply returned "0" to indicate that no error occurred. This distinction was necessary at the time, because the userdiff namespace overlapped slightly with the color configuration namespace. So "diff.color.foo" could mean "the 'foo' slot of diff coloring" or "the 'foo' component of the "color" userdiff driver". Because the color-parsing code would die on an unknown color slot, we needed the userdiff code to indicate that it had matched the variable, letting us bypass the color-parsing code entirely. Later, in 8b8e862 (ignore unknown color configuration, 2009-12-12), the color-parsing code learned to silently ignore unknown slots. This means we no longer need to protect userdiff-matched variables from reaching the color-parsing code. We can therefore change the userdiff_config calling convention to a more normal one. This drops some code from each caller, which is nice. But more importantly, it reduces the cognitive load for readers who may wonder why userdiff_config is unlike every other config callback. There's no need to add a new test confirming that this works; t4020 already contains a test that sets diff.color.external. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 18:23:02 +00:00
return 0;
}
int userdiff_config(const char *k, const char *v)
{
struct userdiff_driver *drv;
const char *name, *type;
size_t namelen;
if (parse_config_key(k, "diff", &name, &namelen, &type) || !name)
return 0;
drv = userdiff_find_by_namelen(name, namelen);
if (!drv) {
ALLOC_GROW(drivers, ndrivers+1, drivers_alloc);
drv = &drivers[ndrivers++];
memset(drv, 0, sizeof(*drv));
drv->name = xmemdupz(name, namelen);
drv->binary = -1;
}
if (!strcmp(type, "funcname"))
return parse_funcname(&drv->funcname, k, v, 0);
if (!strcmp(type, "xfuncname"))
return parse_funcname(&drv->funcname, k, v, REG_EXTENDED);
if (!strcmp(type, "binary"))
diff: introduce diff.<driver>.binary The "diff" gitattribute is somewhat overloaded right now. It can say one of three things: 1. this file is definitely binary, or definitely not (i.e., diff or !diff) 2. this file should use an external diff engine (i.e., diff=foo, diff.foo.command = custom-script) 3. this file should use particular funcname patterns (i.e., diff=foo, diff.foo.(x?)funcname = some-regex) Most of the time, there is no conflict between these uses, since using one implies that the other is irrelevant (e.g., an external diff engine will decide for itself whether the file is binary). However, there is at least one conflicting situation: there is no way to say "use the regular rules to determine whether this file is binary, but if we do diff it textually, use this funcname pattern." That is, currently setting diff=foo indicates that the file is definitely text. This patch introduces a "binary" config option for a diff driver, so that one can explicitly set diff.foo.binary. We default this value to "don't know". That is, setting a diff attribute to "foo" and using "diff.foo.funcname" will have no effect on the binaryness of a file. To get the current behavior, one can set diff.foo.binary to true. This patch also has one additional advantage: it cleans up the interface to the userdiff code a bit. Before, calling code had to know more about whether attributes were false, true, or unset to determine binaryness. Now that binaryness is a property of a driver, we can represent these situations just by passing back a driver struct. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-05 21:43:36 +00:00
return parse_tristate(&drv->binary, k, v);
if (!strcmp(type, "command"))
drop odd return value semantics from userdiff_config When the userdiff_config function was introduced in be58e70 (diff: unify external diff and funcname parsing code, 2008-10-05), it used a return value convention unlike any other config callback. Like other callbacks, it used "-1" to signal error. But it returned "1" to indicate that it found something, and "0" otherwise; other callbacks simply returned "0" to indicate that no error occurred. This distinction was necessary at the time, because the userdiff namespace overlapped slightly with the color configuration namespace. So "diff.color.foo" could mean "the 'foo' slot of diff coloring" or "the 'foo' component of the "color" userdiff driver". Because the color-parsing code would die on an unknown color slot, we needed the userdiff code to indicate that it had matched the variable, letting us bypass the color-parsing code entirely. Later, in 8b8e862 (ignore unknown color configuration, 2009-12-12), the color-parsing code learned to silently ignore unknown slots. This means we no longer need to protect userdiff-matched variables from reaching the color-parsing code. We can therefore change the userdiff_config calling convention to a more normal one. This drops some code from each caller, which is nice. But more importantly, it reduces the cognitive load for readers who may wonder why userdiff_config is unlike every other config callback. There's no need to add a new test confirming that this works; t4020 already contains a test that sets diff.color.external. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 18:23:02 +00:00
return git_config_string(&drv->external, k, v);
if (!strcmp(type, "textconv"))
drop odd return value semantics from userdiff_config When the userdiff_config function was introduced in be58e70 (diff: unify external diff and funcname parsing code, 2008-10-05), it used a return value convention unlike any other config callback. Like other callbacks, it used "-1" to signal error. But it returned "1" to indicate that it found something, and "0" otherwise; other callbacks simply returned "0" to indicate that no error occurred. This distinction was necessary at the time, because the userdiff namespace overlapped slightly with the color configuration namespace. So "diff.color.foo" could mean "the 'foo' slot of diff coloring" or "the 'foo' component of the "color" userdiff driver". Because the color-parsing code would die on an unknown color slot, we needed the userdiff code to indicate that it had matched the variable, letting us bypass the color-parsing code entirely. Later, in 8b8e862 (ignore unknown color configuration, 2009-12-12), the color-parsing code learned to silently ignore unknown slots. This means we no longer need to protect userdiff-matched variables from reaching the color-parsing code. We can therefore change the userdiff_config calling convention to a more normal one. This drops some code from each caller, which is nice. But more importantly, it reduces the cognitive load for readers who may wonder why userdiff_config is unlike every other config callback. There's no need to add a new test confirming that this works; t4020 already contains a test that sets diff.color.external. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 18:23:02 +00:00
return git_config_string(&drv->textconv, k, v);
if (!strcmp(type, "cachetextconv"))
return parse_bool(&drv->textconv_want_cache, k, v);
if (!strcmp(type, "wordregex"))
drop odd return value semantics from userdiff_config When the userdiff_config function was introduced in be58e70 (diff: unify external diff and funcname parsing code, 2008-10-05), it used a return value convention unlike any other config callback. Like other callbacks, it used "-1" to signal error. But it returned "1" to indicate that it found something, and "0" otherwise; other callbacks simply returned "0" to indicate that no error occurred. This distinction was necessary at the time, because the userdiff namespace overlapped slightly with the color configuration namespace. So "diff.color.foo" could mean "the 'foo' slot of diff coloring" or "the 'foo' component of the "color" userdiff driver". Because the color-parsing code would die on an unknown color slot, we needed the userdiff code to indicate that it had matched the variable, letting us bypass the color-parsing code entirely. Later, in 8b8e862 (ignore unknown color configuration, 2009-12-12), the color-parsing code learned to silently ignore unknown slots. This means we no longer need to protect userdiff-matched variables from reaching the color-parsing code. We can therefore change the userdiff_config calling convention to a more normal one. This drops some code from each caller, which is nice. But more importantly, it reduces the cognitive load for readers who may wonder why userdiff_config is unlike every other config callback. There's no need to add a new test confirming that this works; t4020 already contains a test that sets diff.color.external. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 18:23:02 +00:00
return git_config_string(&drv->word_regex, k, v);
if (!strcmp(type, "algorithm"))
return git_config_string(&drv->algorithm, k, v);
return 0;
}
struct userdiff_driver *userdiff_find_by_name(const char *name)
{
int len = strlen(name);
return userdiff_find_by_namelen(name, len);
}
struct userdiff_driver *userdiff_find_by_path(struct index_state *istate,
const char *path)
{
static struct attr_check *check;
if (!check)
check = attr_check_initl("diff", NULL);
if (!path)
return NULL;
attr: add flag `--source` to work with tree-ish The contents of the .gitattributes files may evolve over time, but "git check-attr" always checks attributes against them in the working tree and/or in the index. It may be beneficial to optionally allow the users to check attributes taken from a commit other than HEAD against paths. Add a new flag `--source` which will allow users to check the attributes against a commit (actually any tree-ish would do). When the user uses this flag, we go through the stack of .gitattributes files but instead of checking the current working tree and/or in the index, we check the blobs from the provided tree-ish object. This allows the command to also be used in bare repositories. Since we use a tree-ish object, the user can pass "--source HEAD:subdirectory" and all the attributes will be looked up as if subdirectory was the root directory of the repository. We cannot simply use the `<rev>:<path>` syntax without the `--source` flag, similar to how it is used in `git show` because any non-flag parameter before `--` is treated as an attribute and any parameter after `--` is treated as a pathname. The change involves creating a new function `read_attr_from_blob`, which given the path reads the blob for the path against the provided source and parses the attributes line by line. This function is plugged into `read_attr()` function wherein we go through the stack of attributes files. Signed-off-by: Karthik Nayak <karthik.188@gmail.com> Signed-off-by: Toon Claes <toon@iotcl.com> Co-authored-by: toon@iotcl.com Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-01-14 08:30:38 +00:00
git_check_attr(istate, NULL, path, check);
if (ATTR_TRUE(check->items[0].value))
return &driver_true;
if (ATTR_FALSE(check->items[0].value))
return &driver_false;
if (ATTR_UNSET(check->items[0].value))
return NULL;
return userdiff_find_by_name(check->items[0].value);
}
struct userdiff_driver *userdiff_get_textconv(struct repository *r,
struct userdiff_driver *driver)
{
if (!driver->textconv)
return NULL;
if (driver->textconv_want_cache && !driver->textconv_cache) {
struct notes_cache *c = xmalloc(sizeof(*c));
struct strbuf name = STRBUF_INIT;
strbuf_addf(&name, "textconv/%s", driver->name);
notes_cache_init(r, c, name.buf, driver->textconv);
driver->textconv_cache = c;
strbuf_release(&name);
}
return driver;
}
static int for_each_userdiff_driver_list(each_userdiff_driver_fn fn,
enum userdiff_driver_type type, void *cb_data,
struct userdiff_driver *drv,
int drv_size)
{
int i;
int ret;
for (i = 0; i < drv_size; i++) {
struct userdiff_driver *item = drv + i;
if ((ret = fn(item, type, cb_data)))
return ret;
}
return 0;
}
int for_each_userdiff_driver(each_userdiff_driver_fn fn, void *cb_data)
{
int ret;
ret = for_each_userdiff_driver_list(fn, USERDIFF_DRIVER_TYPE_CUSTOM,
cb_data, drivers, ndrivers);
if (ret)
return ret;
ret = for_each_userdiff_driver_list(fn, USERDIFF_DRIVER_TYPE_BUILTIN,
cb_data, builtin_drivers,
ARRAY_SIZE(builtin_drivers));
if (ret)
return ret;
return 0;
}