git-commit-vandalism/userdiff.c
Jeff King 9cb92c390c diff: add filter for converting binary to text
When diffing binary files, it is sometimes nice to see the
differences of a canonical text form rather than either a
binary patch or simply "binary files differ."

Until now, the only option for doing this was to define an
external diff command to perform the diff. This was a lot of
work, since the external command needed to take care of
doing the diff itself (including mode changes), and lost the
benefit of git's colorization and other options.

This patch adds a text conversion option, which converts a
file to its canonical format before performing the diff.
This is less flexible than an arbitrary external diff, but
is much less work to set up. For example:

  $ echo '*.jpg diff=exif' >>.gitattributes
  $ git config diff.exif.textconv exiftool
  $ git config diff.exif.binary false

allows one to see jpg diffs represented by the text output
of exiftool.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-18 08:02:55 -07:00

176 lines
4.4 KiB
C

#include "userdiff.h"
#include "cache.h"
#include "attr.h"
static struct userdiff_driver *drivers;
static int ndrivers;
static int drivers_alloc;
#define FUNCNAME(name, pattern) \
{ name, NULL, -1, { pattern, REG_EXTENDED } }
static struct userdiff_driver builtin_drivers[] = {
FUNCNAME("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$"),
FUNCNAME("java",
"!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
"^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$"),
FUNCNAME("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_].*)$\n"
/* C functions */
"^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$\n"
/* Objective-C class/protocol definitions */
"^(@(implementation|interface|protocol)[ \t].*)$"),
FUNCNAME("pascal",
"^((procedure|function|constructor|destructor|interface|"
"implementation|initialization|finalization)[ \t]*.*)$"
"\n"
"^(.*=[ \t]*(class|record).*)$"),
FUNCNAME("php", "^[\t ]*((function|class).*)"),
FUNCNAME("python", "^[ \t]*((class|def)[ \t].*)$"),
FUNCNAME("ruby", "^[ \t]*((class|module|def)[ \t].*)$"),
FUNCNAME("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$"),
FUNCNAME("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$"),
{ "default", NULL, -1, { NULL, 0 } },
};
#undef FUNCNAME
static struct userdiff_driver driver_true = {
"diff=true",
NULL,
0,
{ NULL, 0 }
};
static struct userdiff_driver driver_false = {
"!diff",
NULL,
1,
{ NULL, 0 }
};
static struct userdiff_driver *userdiff_find_by_namelen(const char *k, int len)
{
int i;
for (i = 0; i < ndrivers; i++) {
struct userdiff_driver *drv = drivers + i;
if (!strncmp(drv->name, k, len) && !drv->name[len])
return drv;
}
for (i = 0; i < ARRAY_SIZE(builtin_drivers); i++) {
struct userdiff_driver *drv = builtin_drivers + i;
if (!strncmp(drv->name, k, len) && !drv->name[len])
return drv;
}
return NULL;
}
static struct userdiff_driver *parse_driver(const char *var,
const char *value, const char *type)
{
struct userdiff_driver *drv;
const char *dot;
const char *name;
int namelen;
if (prefixcmp(var, "diff."))
return NULL;
dot = strrchr(var, '.');
if (dot == var + 4)
return NULL;
if (strcmp(type, dot+1))
return NULL;
name = var + 5;
namelen = dot - name;
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;
}
return drv;
}
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;
return 1;
}
static int parse_string(const char **d, const char *k, const char *v)
{
if (git_config_string(d, k, v) < 0)
return -1;
return 1;
}
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);
return 1;
}
int userdiff_config_basic(const char *k, const char *v)
{
struct userdiff_driver *drv;
if ((drv = parse_driver(k, v, "funcname")))
return parse_funcname(&drv->funcname, k, v, 0);
if ((drv = parse_driver(k, v, "xfuncname")))
return parse_funcname(&drv->funcname, k, v, REG_EXTENDED);
if ((drv = parse_driver(k, v, "binary")))
return parse_tristate(&drv->binary, k, v);
return 0;
}
int userdiff_config_porcelain(const char *k, const char *v)
{
struct userdiff_driver *drv;
if ((drv = parse_driver(k, v, "command")))
return parse_string(&drv->external, k, v);
if ((drv = parse_driver(k, v, "textconv")))
return parse_string(&drv->textconv, 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(const char *path)
{
static struct git_attr *attr;
struct git_attr_check check;
if (!attr)
attr = git_attr("diff", 4);
check.attr = attr;
if (!path)
return NULL;
if (git_checkattr(path, 1, &check))
return NULL;
if (ATTR_TRUE(check.value))
return &driver_true;
if (ATTR_FALSE(check.value))
return &driver_false;
if (ATTR_UNSET(check.value))
return NULL;
return userdiff_find_by_name(check.value);
}