![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
index f141e7c8ff661733c2be6652709cc60c3340100e..0484601f42a8aeac408d560091d341f571f231dd 100644 (file)
--- a/diff.c
+++ b/diff.c
#include "attr.h"
#include "run-command.h"
#include "utf8.h"
+#include "userdiff.h"
#ifdef NO_FAST_WORKING_DIRECTORY
#define FAST_WORKING_DIRECTORY 0
"\033[41m", /* WHITESPACE (red background) */
};
+static void diff_filespec_load_driver(struct diff_filespec *one);
+static char *run_textconv(const char *, struct diff_filespec *, size_t *);
+
static int parse_diff_color_slot(const char *var, int ofs)
{
if (!strcasecmp(var+ofs, "plain"))
die("bad config variable '%s'", var);
}
-static struct ll_diff_driver {
- const char *name;
- struct ll_diff_driver *next;
- const char *cmd;
-} *user_diff, **user_diff_tail;
-
-/*
- * Currently there is only "diff.<drivername>.command" variable;
- * because there are "diff.color.<slot>" variables, we are parsing
- * this in a bit convoluted way to allow low level diff driver
- * called "color".
- */
-static int parse_lldiff_command(const char *var, const char *ep, const char *value)
-{
- const char *name;
- int namelen;
- struct ll_diff_driver *drv;
-
- name = var + 5;
- namelen = ep - name;
- for (drv = user_diff; drv; drv = drv->next)
- if (!strncmp(drv->name, name, namelen) && !drv->name[namelen])
- break;
- if (!drv) {
- drv = xcalloc(1, sizeof(struct ll_diff_driver));
- drv->name = xmemdupz(name, namelen);
- if (!user_diff_tail)
- user_diff_tail = &user_diff;
- *user_diff_tail = drv;
- user_diff_tail = &(drv->next);
- }
-
- return git_config_string(&(drv->cmd), var, value);
-}
-
-/*
- * 'diff.<what>.funcname' attribute can be specified in the configuration
- * to define a customized regexp to find the beginning of a function to
- * be used for hunk header lines of "diff -p" style output.
- */
-struct funcname_pattern_entry {
- char *name;
- char *pattern;
- int cflags;
-};
-static struct funcname_pattern_list {
- struct funcname_pattern_list *next;
- struct funcname_pattern_entry e;
-} *funcname_pattern_list;
-
-static int parse_funcname_pattern(const char *var, const char *ep, const char *value, int cflags)
-{
- const char *name;
- int namelen;
- struct funcname_pattern_list *pp;
-
- name = var + 5; /* "diff." */
- namelen = ep - name;
-
- for (pp = funcname_pattern_list; pp; pp = pp->next)
- if (!strncmp(pp->e.name, name, namelen) && !pp->e.name[namelen])
- break;
- if (!pp) {
- pp = xcalloc(1, sizeof(*pp));
- pp->e.name = xmemdupz(name, namelen);
- pp->next = funcname_pattern_list;
- funcname_pattern_list = pp;
- }
- free(pp->e.pattern);
- pp->e.pattern = xstrdup(value);
- pp->e.cflags = cflags;
- return 0;
-}
-
/*
* These are to give UI layer defaults.
* The core-level commands such as git-diff-files should
}
if (!strcmp(var, "diff.external"))
return git_config_string(&external_diff_cmd_cfg, var, value);
- if (!prefixcmp(var, "diff.")) {
- const char *ep = strrchr(var, '.');
-
- if (ep != var + 4 && !strcmp(ep, ".command"))
- return parse_lldiff_command(var, ep, value);
- }
return git_diff_basic_config(var, value, cb);
}
return 0;
}
+ switch (userdiff_config(var, value)) {
+ case 0: break;
+ case -1: return -1;
+ default: return 0;
+ }
+
if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
int slot = parse_diff_color_slot(var, 11);
if (!value)
return 0;
}
- if (!prefixcmp(var, "diff.")) {
- const char *ep = strrchr(var, '.');
- if (ep != var + 4) {
- if (!strcmp(ep, ".funcname")) {
- if (!value)
- return config_error_nonbool(var);
- return parse_funcname_pattern(var, ep, value,
- 0);
- } else if (!strcmp(ep, ".xfuncname")) {
- if (!value)
- return config_error_nonbool(var);
- return parse_funcname_pattern(var, ep, value,
- REG_EXTENDED);
- }
- }
- }
-
return git_color_default_config(var, value, cb);
}
const char *name_b,
struct diff_filespec *one,
struct diff_filespec *two,
+ const char *textconv_one,
+ const char *textconv_two,
struct diff_options *o)
{
int lc_a, lc_b;
const char *reset = diff_get_color(color_diff, DIFF_RESET);
static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
const char *a_prefix, *b_prefix;
+ const char *data_one, *data_two;
+ size_t size_one, size_two;
if (diff_mnemonic_prefix && DIFF_OPT_TST(o, REVERSE_DIFF)) {
a_prefix = o->b_prefix;
diff_populate_filespec(one, 0);
diff_populate_filespec(two, 0);
- lc_a = count_lines(one->data, one->size);
- lc_b = count_lines(two->data, two->size);
+ if (textconv_one) {
+ data_one = run_textconv(textconv_one, one, &size_one);
+ if (!data_one)
+ die("unable to read files to diff");
+ }
+ else {
+ data_one = one->data;
+ size_one = one->size;
+ }
+ if (textconv_two) {
+ data_two = run_textconv(textconv_two, two, &size_two);
+ if (!data_two)
+ die("unable to read files to diff");
+ }
+ else {
+ data_two = two->data;
+ size_two = two->size;
+ }
+
+ lc_a = count_lines(data_one, size_one);
+ lc_b = count_lines(data_two, size_two);
fprintf(o->file,
"%s--- %s%s%s\n%s+++ %s%s%s\n%s@@ -",
metainfo, a_name.buf, name_a_tab, reset,
print_line_count(o->file, lc_b);
fprintf(o->file, " @@%s\n", reset);
if (lc_a)
- copy_file_with_prefix(o->file, '-', one->data, one->size, old, reset);
+ copy_file_with_prefix(o->file, '-', data_one, size_one, old, reset);
if (lc_b)
- copy_file_with_prefix(o->file, '+', two->data, two->size, new, reset);
+ copy_file_with_prefix(o->file, '+', data_two, size_two, new, reset);
}
static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
}
else if (diff_populate_filespec(one, 0))
return -1;
+
mf->ptr = one->data;
mf->size = one->size;
return 0;
emit_binary_diff_body(file, two, one);
}
-static void setup_diff_attr_check(struct git_attr_check *check)
+static void diff_filespec_load_driver(struct diff_filespec *one)
{
- static struct git_attr *attr_diff;
-
- if (!attr_diff) {
- attr_diff = git_attr("diff", 4);
- }
- check[0].attr = attr_diff;
-}
-
-static void diff_filespec_check_attr(struct diff_filespec *one)
-{
- struct git_attr_check attr_diff_check;
- int check_from_data = 0;
-
- if (one->checked_attr)
- return;
-
- setup_diff_attr_check(&attr_diff_check);
- one->is_binary = 0;
- one->funcname_pattern_ident = NULL;
-
- if (!git_checkattr(one->path, 1, &attr_diff_check)) {
- const char *value;
-
- /* binaryness */
- value = attr_diff_check.value;
- if (ATTR_TRUE(value))
- ;
- else if (ATTR_FALSE(value))
- one->is_binary = 1;
- else
- check_from_data = 1;
-
- /* funcname pattern ident */
- if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value))
- ;
- else
- one->funcname_pattern_ident = value;
- }
-
- if (check_from_data) {
- if (!one->data && DIFF_FILE_VALID(one))
- diff_populate_filespec(one, 0);
-
- if (one->data)
- one->is_binary = buffer_is_binary(one->data, one->size);
- }
+ if (!one->driver)
+ one->driver = userdiff_find_by_path(one->path);
+ if (!one->driver)
+ one->driver = userdiff_find_by_name("default");
}
int diff_filespec_is_binary(struct diff_filespec *one)
{
- diff_filespec_check_attr(one);
+ if (one->is_binary == -1) {
+ diff_filespec_load_driver(one);
+ if (one->driver->binary != -1)
+ one->is_binary = one->driver->binary;
+ else {
+ if (!one->data && DIFF_FILE_VALID(one))
+ diff_populate_filespec(one, 0);
+ if (one->data)
+ one->is_binary = buffer_is_binary(one->data,
+ one->size);
+ if (one->is_binary == -1)
+ one->is_binary = 0;
+ }
+ }
return one->is_binary;
}
-static const struct funcname_pattern_entry *funcname_pattern(const char *ident)
-{
- struct funcname_pattern_list *pp;
-
- for (pp = funcname_pattern_list; pp; pp = pp->next)
- if (!strcmp(ident, pp->e.name))
- return &pp->e;
- return NULL;
-}
-
-static const struct funcname_pattern_entry builtin_funcname_pattern[] = {
- { "bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
- REG_EXTENDED },
- { "html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$", REG_EXTENDED },
- { "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]*\\([^;]*)$",
- REG_EXTENDED },
- { "objc",
- /* Negate C statements that can look like functions */
- "!^[ \t]*(do|for|if|else|return|switch|while)\n"
- /* Objective-C methods */
- "^[ \t]*([-+][ \t]*\\([ \t]*[A-Za-z_][A-Za-z_0-9* \t]*\\)[ \t]*[A-Za-z_].*)$\n"
- /* C functions */
- "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$\n"
- /* Objective-C class/protocol definitions */
- "^(@(implementation|interface|protocol)[ \t].*)$",
- REG_EXTENDED },
- { "pascal",
- "^((procedure|function|constructor|destructor|interface|"
- "implementation|initialization|finalization)[ \t]*.*)$"
- "\n"
- "^(.*=[ \t]*(class|record).*)$",
- REG_EXTENDED },
- { "php", "^[\t ]*((function|class).*)", REG_EXTENDED },
- { "python", "^[ \t]*((class|def)[ \t].*)$", REG_EXTENDED },
- { "ruby", "^[ \t]*((class|module|def)[ \t].*)$",
- REG_EXTENDED },
- { "tex",
- "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
- REG_EXTENDED },
-};
-
-static const struct funcname_pattern_entry *diff_funcname_pattern(struct diff_filespec *one)
+static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespec *one)
{
- const char *ident;
- const struct funcname_pattern_entry *pe;
- int i;
-
- diff_filespec_check_attr(one);
- ident = one->funcname_pattern_ident;
-
- if (!ident)
- /*
- * If the config file has "funcname.default" defined, that
- * regexp is used; otherwise NULL is returned and xemit uses
- * the built-in default.
- */
- return funcname_pattern("default");
-
- /* Look up custom "funcname.$ident" regexp from config. */
- pe = funcname_pattern(ident);
- if (pe)
- return pe;
-
- /*
- * And define built-in fallback patterns here. Note that
- * these can be overridden by the user's config settings.
- */
- for (i = 0; i < ARRAY_SIZE(builtin_funcname_pattern); i++)
- if (!strcmp(ident, builtin_funcname_pattern[i].name))
- return &builtin_funcname_pattern[i];
-
- return NULL;
+ diff_filespec_load_driver(one);
+ return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
}
void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
@@ -1493,6 +1331,16 @@ void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const
options->b_prefix = b;
}
+static const char *get_textconv(struct diff_filespec *one)
+{
+ if (!DIFF_FILE_VALID(one))
+ return NULL;
+ if (!S_ISREG(one->mode))
+ return NULL;
+ diff_filespec_load_driver(one);
+ return one->driver->textconv;
+}
+
static void builtin_diff(const char *name_a,
const char *name_b,
struct diff_filespec *one,
const char *set = diff_get_color_opt(o, DIFF_METAINFO);
const char *reset = diff_get_color_opt(o, DIFF_RESET);
const char *a_prefix, *b_prefix;
+ const char *textconv_one = NULL, *textconv_two = NULL;
+
+ if (DIFF_OPT_TST(o, ALLOW_TEXTCONV)) {
+ textconv_one = get_textconv(one);
+ textconv_two = get_textconv(two);
+ }
diff_set_mnemonic_prefix(o, "a/", "b/");
if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
*/
if ((one->mode ^ two->mode) & S_IFMT)
goto free_ab_and_return;
- if (complete_rewrite) {
- emit_rewrite_diff(name_a, name_b, one, two, o);
+ if (complete_rewrite &&
+ (textconv_one || !diff_filespec_is_binary(one)) &&
+ (textconv_two || !diff_filespec_is_binary(two))) {
+ emit_rewrite_diff(name_a, name_b, one, two,
+ textconv_one, textconv_two, o);
o->found_changes = 1;
goto free_ab_and_return;
}
die("unable to read files to diff");
if (!DIFF_OPT_TST(o, TEXT) &&
- (diff_filespec_is_binary(one) || diff_filespec_is_binary(two))) {
+ ( (diff_filespec_is_binary(one) && !textconv_one) ||
+ (diff_filespec_is_binary(two) && !textconv_two) )) {
/* Quite common confusing case */
if (mf1.size == mf2.size &&
!memcmp(mf1.ptr, mf2.ptr, mf1.size))
xdemitconf_t xecfg;
xdemitcb_t ecb;
struct emit_callback ecbdata;
- const struct funcname_pattern_entry *pe;
+ const struct userdiff_funcname *pe;
+
+ if (textconv_one) {
+ size_t size;
+ mf1.ptr = run_textconv(textconv_one, one, &size);
+ if (!mf1.ptr)
+ die("unable to read files to diff");
+ mf1.size = size;
+ }
+ if (textconv_two) {
+ size_t size;
+ mf2.ptr = run_textconv(textconv_two, two, &size);
+ if (!mf2.ptr)
+ die("unable to read files to diff");
+ mf2.size = size;
+ }
pe = diff_funcname_pattern(one);
if (!pe)
&xpp, &xecfg, &ecb);
if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS))
free_diff_words_data(&ecbdata);
+ if (textconv_one)
+ free(mf1.ptr);
+ if (textconv_two)
+ free(mf2.ptr);
}
free_ab_and_return:
spec->path = (char *)(spec + 1);
memcpy(spec->path, path, namelen+1);
spec->count = 1;
+ spec->is_binary = -1;
return spec;
}
s->size = xsize_t(st.st_size);
if (!s->size)
goto empty;
- if (size_only)
- return 0;
if (S_ISLNK(st.st_mode)) {
- int ret;
- s->data = xmalloc(s->size);
- s->should_free = 1;
- ret = readlink(s->path, s->data, s->size);
- if (ret < 0) {
- free(s->data);
+ struct strbuf sb = STRBUF_INIT;
+
+ if (strbuf_readlink(&sb, s->path, s->size))
goto err_empty;
- }
+ s->size = sb.len;
+ s->data = strbuf_detach(&sb, NULL);
+ s->should_free = 1;
return 0;
}
+ if (size_only)
+ return 0;
fd = open(s->path, O_RDONLY);
if (fd < 0)
goto err_empty;
if (S_ISLNK(st.st_mode)) {
int ret;
char buf[PATH_MAX + 1]; /* ought to be SYMLINK_MAX */
- size_t sz = xsize_t(st.st_size);
- if (sizeof(buf) <= st.st_size)
- die("symlink too long: %s", name);
- ret = readlink(name, buf, sz);
+ ret = readlink(name, buf, sizeof(buf));
if (ret < 0)
die("readlink(%s)", name);
- prep_temp_blob(temp, buf, sz,
+ if (ret == sizeof(buf))
+ die("symlink too long: %s", name);
+ prep_temp_blob(temp, buf, ret,
(one->sha1_valid ?
one->sha1 : null_sha1),
(one->sha1_valid ?
}
}
-static const char *external_diff_attr(const char *name)
-{
- struct git_attr_check attr_diff_check;
-
- if (!name)
- return NULL;
-
- setup_diff_attr_check(&attr_diff_check);
- if (!git_checkattr(name, 1, &attr_diff_check)) {
- const char *value = attr_diff_check.value;
- if (!ATTR_TRUE(value) &&
- !ATTR_FALSE(value) &&
- !ATTR_UNSET(value)) {
- struct ll_diff_driver *drv;
-
- for (drv = user_diff; drv; drv = drv->next)
- if (!strcmp(drv->name, value))
- return drv->cmd;
- }
- }
- return NULL;
-}
-
static void run_diff_cmd(const char *pgm,
const char *name,
const char *other,
if (!DIFF_OPT_TST(o, ALLOW_EXTERNAL))
pgm = NULL;
else {
- const char *cmd = external_diff_attr(attr_path);
- if (cmd)
- pgm = cmd;
+ struct userdiff_driver *drv = userdiff_find_by_path(attr_path);
+ if (drv && drv->external)
+ pgm = drv->external;
}
if (pgm) {
DIFF_OPT_SET(options, ALLOW_EXTERNAL);
else if (!strcmp(arg, "--no-ext-diff"))
DIFF_OPT_CLR(options, ALLOW_EXTERNAL);
+ else if (!strcmp(arg, "--textconv"))
+ DIFF_OPT_SET(options, ALLOW_TEXTCONV);
+ else if (!strcmp(arg, "--no-textconv"))
+ DIFF_OPT_CLR(options, ALLOW_TEXTCONV);
else if (!strcmp(arg, "--ignore-submodules"))
DIFF_OPT_SET(options, IGNORE_SUBMODULES);
fill_filespec(one, sha1, mode);
diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1;
}
+
+static char *run_textconv(const char *pgm, struct diff_filespec *spec,
+ size_t *outsize)
+{
+ struct diff_tempfile temp;
+ const char *argv[3];
+ const char **arg = argv;
+ struct child_process child;
+ struct strbuf buf = STRBUF_INIT;
+
+ prepare_temp_file(spec->path, &temp, spec);
+ *arg++ = pgm;
+ *arg++ = temp.name;
+ *arg = NULL;
+
+ memset(&child, 0, sizeof(child));
+ child.argv = argv;
+ child.out = -1;
+ if (start_command(&child) != 0 ||
+ strbuf_read(&buf, child.out, 0) < 0 ||
+ finish_command(&child) != 0) {
+ if (temp.name == temp.tmp_path)
+ unlink(temp.name);
+ error("error running textconv command '%s'", pgm);
+ return NULL;
+ }
+ if (temp.name == temp.tmp_path)
+ unlink(temp.name);
+
+ return strbuf_detach(&buf, outsize);
+}