char *cmd;
} *user_diff, **user_diff_tail;
+static void read_config_if_needed(void)
+{
+ if (!user_diff_tail) {
+ user_diff_tail = &user_diff;
+ git_config(git_diff_ui_config);
+ }
+}
+
/*
* Currently there is only "diff.<drivername>.command" variable;
* because there are "diff.color.<slot>" variables, we are parsing
return 0;
}
+/*
+ * '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.
+ */
+static struct funcname_pattern {
+ char *name;
+ char *pattern;
+ struct funcname_pattern *next;
+} *funcname_pattern_list;
+
+static int parse_funcname_pattern(const char *var, const char *ep, const char *value)
+{
+ const char *name;
+ int namelen;
+ struct funcname_pattern *pp;
+
+ name = var + 5; /* "diff." */
+ namelen = ep - name;
+
+ for (pp = funcname_pattern_list; pp; pp = pp->next)
+ if (!strncmp(pp->name, name, namelen) && !pp->name[namelen])
+ break;
+ if (!pp) {
+ char *namebuf;
+ pp = xcalloc(1, sizeof(*pp));
+ namebuf = xmalloc(namelen + 1);
+ memcpy(namebuf, name, namelen);
+ namebuf[namelen] = 0;
+ pp->name = namebuf;
+ pp->next = funcname_pattern_list;
+ funcname_pattern_list = pp;
+ }
+ if (pp->pattern)
+ free(pp->pattern);
+ pp->pattern = xstrdup(value);
+ return 0;
+}
+
/*
* These are to give UI layer defaults.
* The core-level commands such as git-diff-files should
if (!prefixcmp(var, "diff.")) {
const char *ep = strrchr(var, '.');
- if (ep != var + 4 && !strcmp(ep, ".command"))
- return parse_lldiff_command(var, ep, value);
+ if (ep != var + 4) {
+ if (!strcmp(ep, ".command"))
+ return parse_lldiff_command(var, ep, value);
+ if (!strcmp(ep, ".funcname"))
+ return parse_funcname_pattern(var, ep, value);
+ }
}
if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
int slot = parse_diff_color_slot(var, 11);
mmfile_t minus, plus;
int i;
+ memset(&xecfg, 0, sizeof(xecfg));
minus.size = diff_words->minus.text.size;
minus.ptr = xmalloc(minus.size);
memcpy(minus.ptr, diff_words->minus.text.ptr, minus.size);
xpp.flags = XDF_NEED_MINIMAL;
xecfg.ctxlen = diff_words->minus.alloc + diff_words->plus.alloc;
- xecfg.flags = 0;
ecb.outf = xdiff_outf;
ecb.priv = diff_words;
diff_words->xm.consume = fn_out_diff_words_aux;
{
static struct git_attr *attr_diff;
- if (!attr_diff)
+ if (!attr_diff) {
attr_diff = git_attr("diff", 4);
- check->attr = attr_diff;
+ }
+ check[0].attr = attr_diff;
}
-#define FIRST_FEW_BYTES 8000
-static int file_is_binary(struct diff_filespec *one)
+static void diff_filespec_check_attr(struct diff_filespec *one)
{
- unsigned long sz;
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 = attr_diff_check.value;
+ const char *value;
+
+ /* binaryness */
+ value = attr_diff_check.value;
if (ATTR_TRUE(value))
- return 0;
+ ;
else if (ATTR_FALSE(value))
- return 1;
+ 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 (!one->data) {
- if (!DIFF_FILE_VALID(one))
- return 0;
- diff_populate_filespec(one, 0);
+ 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);
}
- sz = one->size;
- if (FIRST_FEW_BYTES < sz)
- sz = FIRST_FEW_BYTES;
- return !!memchr(one->data, 0, sz);
+}
+
+int diff_filespec_is_binary(struct diff_filespec *one)
+{
+ diff_filespec_check_attr(one);
+ return one->is_binary;
+}
+
+static const char *funcname_pattern(const char *ident)
+{
+ struct funcname_pattern *pp;
+
+ read_config_if_needed();
+ for (pp = funcname_pattern_list; pp; pp = pp->next)
+ if (!strcmp(ident, pp->name))
+ return pp->pattern;
+ return NULL;
+}
+
+static struct builtin_funcname_pattern {
+ const char *name;
+ const char *pattern;
+} builtin_funcname_pattern[] = {
+ { "java", "!^[ ]*\\(catch\\|do\\|for\\|if\\|instanceof\\|"
+ "new\\|return\\|switch\\|throw\\|while\\)\n"
+ "^[ ]*\\(\\([ ]*"
+ "[A-Za-z_][A-Za-z_0-9]*\\)\\{2,\\}"
+ "[ ]*([^;]*$\\)" },
+ { "tex", "^\\(\\\\\\(sub\\)*section{.*\\)$" },
+};
+
+static const char *diff_funcname_pattern(struct diff_filespec *one)
+{
+ const char *ident, *pattern;
+ 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. */
+ pattern = funcname_pattern(ident);
+ if (pattern)
+ return pattern;
+
+ /*
+ * And define built-in fallback patterns here. Note that
+ * these can be overriden 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].pattern;
+
+ return NULL;
}
static void builtin_diff(const char *name_a,
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
- if (!o->text && (file_is_binary(one) || file_is_binary(two))) {
+ if (!o->text &&
+ (diff_filespec_is_binary(one) || diff_filespec_is_binary(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 char *funcname_pattern;
+ funcname_pattern = diff_funcname_pattern(one);
+ if (!funcname_pattern)
+ funcname_pattern = diff_funcname_pattern(two);
+
+ memset(&xecfg, 0, sizeof(xecfg));
memset(&ecbdata, 0, sizeof(ecbdata));
ecbdata.label_path = lbl;
ecbdata.color_diff = o->color_diff;
xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
xecfg.ctxlen = o->context;
xecfg.flags = XDL_EMIT_FUNCNAMES;
+ if (funcname_pattern)
+ xdiff_set_find_func(&xecfg, funcname_pattern);
if (!diffopts)
;
else if (!prefixcmp(diffopts, "--unified="))
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
- if (file_is_binary(one) || file_is_binary(two)) {
+ if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
data->is_binary = 1;
data->added = mf2.size;
data->deleted = mf1.size;
xdemitconf_t xecfg;
xdemitcb_t ecb;
+ memset(&xecfg, 0, sizeof(xecfg));
xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
- xecfg.ctxlen = 0;
- xecfg.flags = 0;
ecb.outf = xdiff_outf;
ecb.priv = diffstat;
xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
- if (file_is_binary(two))
+ if (diff_filespec_is_binary(two))
goto free_and_return;
else {
/* Crazy xdl interfaces.. */
xdemitconf_t xecfg;
xdemitcb_t ecb;
+ memset(&xecfg, 0, sizeof(xecfg));
xpp.flags = XDF_NEED_MINIMAL;
- xecfg.ctxlen = 0;
- xecfg.flags = 0;
ecb.outf = xdiff_outf;
ecb.priv = &data;
xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
if (size_only && 0 < s->size)
return 0;
- if (S_ISDIRLNK(s->mode))
+ if (S_ISGITLINK(s->mode))
return diff_populate_gitlink(s, size_only);
if (!s->sha1_valid ||
fd = git_mkstemp(temp->tmp_path, PATH_MAX, ".diff_XXXXXX");
if (fd < 0)
- die("unable to create temp-file");
+ die("unable to create temp-file: %s", strerror(errno));
if (write_in_full(fd, blob, size) != size)
die("unable to write temp-file");
close(fd);
!ATTR_UNSET(value)) {
struct ll_diff_driver *drv;
- if (!user_diff_tail) {
- user_diff_tail = &user_diff;
- git_config(git_diff_ui_config);
- }
+ read_config_if_needed();
for (drv = user_diff; drv; drv = drv->next)
if (!strcmp(drv->name, value))
return drv->cmd;
hashclr(one->sha1);
}
+static int similarity_index(struct diff_filepair *p)
+{
+ return p->score * 100 / MAX_SCORE;
+}
+
static void run_diff(struct diff_filepair *p, struct diff_options *o)
{
const char *pgm = external_diff();
"similarity index %d%%\n"
"copy from %s\n"
"copy to %s\n",
- (int)(0.5 + p->score * 100.0/MAX_SCORE),
- name_munged, other_munged);
+ similarity_index(p), name_munged, other_munged);
break;
case DIFF_STATUS_RENAMED:
len += snprintf(msg + len, sizeof(msg) - len,
"similarity index %d%%\n"
"rename from %s\n"
"rename to %s\n",
- (int)(0.5 + p->score * 100.0/MAX_SCORE),
- name_munged, other_munged);
+ similarity_index(p), name_munged, other_munged);
break;
case DIFF_STATUS_MODIFIED:
if (p->score) {
len += snprintf(msg + len, sizeof(msg) - len,
"dissimilarity index %d%%\n",
- (int)(0.5 + p->score *
- 100.0/MAX_SCORE));
+ similarity_index(p));
complete_rewrite = 1;
break;
}
if (o->binary) {
mmfile_t mf;
- if ((!fill_mmfile(&mf, one) && file_is_binary(one)) ||
- (!fill_mmfile(&mf, two) && file_is_binary(two)))
+ if ((!fill_mmfile(&mf, one) && diff_filespec_is_binary(one)) ||
+ (!fill_mmfile(&mf, two) && diff_filespec_is_binary(two)))
abbrev = 40;
}
len += snprintf(msg + len, sizeof(msg) - len,
return 1;
}
+static int diff_scoreopt_parse(const char *opt);
+
int diff_opt_parse(struct diff_options *options, const char **av, int ac)
{
const char *arg = av[0];
options->detect_rename = DIFF_DETECT_RENAME;
}
else if (!prefixcmp(arg, "-C")) {
+ if (options->detect_rename == DIFF_DETECT_COPY)
+ options->find_copies_harder = 1;
if ((options->rename_score =
diff_scoreopt_parse(arg)) == -1)
return -1;
}
else if (!strcmp(arg, "--find-copies-harder"))
options->find_copies_harder = 1;
+ else if (!strcmp(arg, "--follow"))
+ options->follow_renames = 1;
else if (!strcmp(arg, "--abbrev"))
options->abbrev = DEFAULT_ABBREV;
else if (!prefixcmp(arg, "--abbrev=")) {
options->exit_with_status = 1;
else if (!strcmp(arg, "--quiet"))
options->quiet = 1;
+ else if (!strcmp(arg, "--ext-diff"))
+ options->allow_external = 1;
+ else if (!strcmp(arg, "--no-ext-diff"))
+ options->allow_external = 0;
else
return 0;
return 1;
return (int)((num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale));
}
-int diff_scoreopt_parse(const char *opt)
+static int diff_scoreopt_parse(const char *opt)
{
int opt1, opt2, cmd;
}
if (p->score)
- sprintf(status, "%c%03d", p->status,
- (int)(0.5 + p->score * 100.0/MAX_SCORE));
+ sprintf(status, "%c%03d", p->status, similarity_index(p));
else {
status[0] = p->status;
status[1] = 0;
printf("%s ",
diff_unique_abbrev(p->two->sha1, abbrev));
}
- printf("%s%c%s", status, inter_name_termination, path_one);
+ printf("%s%c%s", status, inter_name_termination,
+ two_paths || p->one->mode ? path_one : path_two);
if (two_paths)
printf("%c%s", inter_name_termination, path_two);
putchar(line_termination);
{
char *names = pprint_rename(p->one->path, p->two->path);
- printf(" %s %s (%d%%)\n", renamecopy, names,
- (int)(0.5 + p->score * 100.0/MAX_SCORE));
+ printf(" %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
free(names);
show_mode_change(p, 0);
}
if (p->score) {
char *name = quote_one(p->two->path);
printf(" rewrite %s (%d%%)\n", name,
- (int)(0.5 + p->score * 100.0/MAX_SCORE));
+ similarity_index(p));
free(name);
show_mode_change(p, 0);
} else show_mode_change(p, 1);
struct diff_filepair *p = q->queue[i];
int len1, len2;
+ memset(&xecfg, 0, sizeof(xecfg));
if (p->status == 0)
return error("internal diff status error");
if (p->status == DIFF_STATUS_UNKNOWN)
return error("unable to read files to diff");
/* Maybe hash p->two? into the patch id? */
- if (file_is_binary(p->two))
+ if (diff_filespec_is_binary(p->two))
continue;
len1 = remove_space(p->one->path, strlen(p->one->path));
*q = outq;
}
+static void diffcore_skip_stat_unmatch(struct diff_options *diffopt)
+{
+ int i;
+ struct diff_queue_struct *q = &diff_queued_diff;
+ struct diff_queue_struct outq;
+ outq.queue = NULL;
+ outq.nr = outq.alloc = 0;
+
+ for (i = 0; i < q->nr; i++) {
+ struct diff_filepair *p = q->queue[i];
+
+ /*
+ * 1. Entries that come from stat info dirtyness
+ * always have both sides (iow, not create/delete),
+ * one side of the object name is unknown, with
+ * the same mode and size. Keep the ones that
+ * do not match these criteria. They have real
+ * differences.
+ *
+ * 2. At this point, the file is known to be modified,
+ * with the same mode and size, and the object
+ * name of one side is unknown. Need to inspect
+ * the identical contents.
+ */
+ if (!DIFF_FILE_VALID(p->one) || /* (1) */
+ !DIFF_FILE_VALID(p->two) ||
+ (p->one->sha1_valid && p->two->sha1_valid) ||
+ (p->one->mode != p->two->mode) ||
+ diff_populate_filespec(p->one, 1) ||
+ diff_populate_filespec(p->two, 1) ||
+ (p->one->size != p->two->size) ||
+
+ diff_populate_filespec(p->one, 0) || /* (2) */
+ diff_populate_filespec(p->two, 0) ||
+ memcmp(p->one->data, p->two->data, p->one->size))
+ diff_q(&outq, p);
+ else {
+ /*
+ * The caller can subtract 1 from skip_stat_unmatch
+ * to determine how many paths were dirty only
+ * due to stat info mismatch.
+ */
+ if (!diffopt->no_index)
+ diffopt->skip_stat_unmatch++;
+ diff_free_filepair(p);
+ }
+ }
+ free(q->queue);
+ *q = outq;
+}
+
void diffcore_std(struct diff_options *options)
{
if (options->quiet)
return;
+
+ if (options->skip_stat_unmatch && !options->find_copies_harder)
+ diffcore_skip_stat_unmatch(options);
if (options->break_opt != -1)
diffcore_break(options->break_opt);
if (options->detect_rename)
* entries to the diff-core. They will be prefixed
* with something like '=' or '*' (I haven't decided
* which but should not make any difference).
- * Feeding the same new and old to diff_change()
+ * Feeding the same new and old to diff_change()
* also has the same effect.
* Before the final output happens, they are pruned after
* merged into rename/copy pairs as appropriate.
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
- const char *base, const char *path)
+ const char *base, const char *path)
{
char concatpath[PATH_MAX];
struct diff_filespec *one, *two;