![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
| author | Junio C Hamano <gitster@pobox.com> | |
| Mon, 23 May 2011 17:27:42 +0000 (10:27 -0700) | ||
| committer | Junio C Hamano <gitster@pobox.com> | |
| Mon, 23 May 2011 17:27:42 +0000 (10:27 -0700) |
* jm/maint-diff-words-with-sbe:
do not read beyond end of malloc'd buffer
do not read beyond end of malloc'd buffer
| 1 | 2 | |||
|---|---|---|---|---|
| diff.c | patch | | diff1 | | diff2 | | blob | history |
diff --combined diff.c
index ba5f7aa2173a7494b56395bfd88ab6228b5ed1fe,f90c7a896b814930952c42a7acde55fa8cf20e2b..8f4815bfd7d798f2a99131cd2e79155e933c7876
+++ b/diff.c
#endif
static int diff_detect_rename_default;
-static int diff_rename_limit_default = 200;
+static int diff_rename_limit_default = 400;
static int diff_suppress_blank_empty;
int diff_use_color_default = -1;
static const char *diff_word_regex_cfg;
int diff_auto_refresh_index = 1;
static int diff_mnemonic_prefix;
static int diff_no_prefix;
+static int diff_dirstat_permille_default = 30;
static struct diff_options default_diff_options;
static char diff_colors[][COLOR_MAXLEN] = {
return -1;
}
+static int parse_dirstat_params(struct diff_options *options, const char *params,
+ struct strbuf *errmsg)
+{
+ const char *p = params;
+ int p_len, ret = 0;
+
+ while (*p) {
+ p_len = strchrnul(p, ',') - p;
+ if (!memcmp(p, "changes", p_len)) {
+ DIFF_OPT_CLR(options, DIRSTAT_BY_LINE);
+ DIFF_OPT_CLR(options, DIRSTAT_BY_FILE);
+ } else if (!memcmp(p, "lines", p_len)) {
+ DIFF_OPT_SET(options, DIRSTAT_BY_LINE);
+ DIFF_OPT_CLR(options, DIRSTAT_BY_FILE);
+ } else if (!memcmp(p, "files", p_len)) {
+ DIFF_OPT_CLR(options, DIRSTAT_BY_LINE);
+ DIFF_OPT_SET(options, DIRSTAT_BY_FILE);
+ } else if (!memcmp(p, "noncumulative", p_len)) {
+ DIFF_OPT_CLR(options, DIRSTAT_CUMULATIVE);
+ } else if (!memcmp(p, "cumulative", p_len)) {
+ DIFF_OPT_SET(options, DIRSTAT_CUMULATIVE);
+ } else if (isdigit(*p)) {
+ char *end;
+ int permille = strtoul(p, &end, 10) * 10;
+ if (*end == '.' && isdigit(*++end)) {
+ /* only use first digit */
+ permille += *end - '0';
+ /* .. and ignore any further digits */
+ while (isdigit(*++end))
+ ; /* nothing */
+ }
+ if (end - p == p_len)
+ options->dirstat_permille = permille;
+ else {
+ strbuf_addf(errmsg, _(" Failed to parse dirstat cut-off percentage '%.*s'\n"),
+ p_len, p);
+ ret++;
+ }
+ } else {
+ strbuf_addf(errmsg, _(" Unknown dirstat parameter '%.*s'\n"),
+ p_len, p);
+ ret++;
+ }
+
+ p += p_len;
+
+ if (*p)
+ p++; /* more parameters, swallow separator */
+ }
+ return ret;
+}
+
static int git_config_rename(const char *var, const char *value)
{
if (!value)
return 0;
}
+ if (!strcmp(var, "diff.dirstat")) {
+ struct strbuf errmsg = STRBUF_INIT;
+ default_diff_options.dirstat_permille = diff_dirstat_permille_default;
+ if (parse_dirstat_params(&default_diff_options, value, &errmsg))
+ warning(_("Found errors in 'diff.dirstat' config variable:\n%s"),
+ errmsg.buf);
+ strbuf_release(&errmsg);
+ diff_dirstat_permille_default = default_diff_options.dirstat_permille;
+ return 0;
+ }
+
if (!prefixcmp(var, "submodule."))
return parse_submodule_config_option(var, value);
return 0;
}
+/* like fill_mmfile, but only for size, so we can avoid retrieving blob */
+static unsigned long diff_filespec_size(struct diff_filespec *one)
+{
+ if (!DIFF_FILE_VALID(one))
+ return 0;
+ diff_populate_filespec(one, 1);
+ return one->size;
+}
+
static int count_trailing_blank(mmfile_t *mf, unsigned ws_rule)
{
char *ptr = mf->ptr;
line_prefix, metainfo, a_name.buf, name_a_tab, reset,
line_prefix, metainfo, b_name.buf, name_b_tab, reset,
line_prefix, fraginfo);
- print_line_count(o->file, lc_a);
+ if (!o->irreversible_delete)
+ print_line_count(o->file, lc_a);
+ else
+ fprintf(o->file, "?,?");
fprintf(o->file, " +");
print_line_count(o->file, lc_b);
fprintf(o->file, " @@%s\n", reset);
- if (lc_a)
+ if (lc_a && !o->irreversible_delete)
emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
if (lc_b)
emit_rewrite_lines(&ecbdata, '+', data_two, size_two);
buffer->text.ptr[buffer->text.size] = '\0';
}
-struct diff_words_style_elem
-{
+struct diff_words_style_elem {
const char *prefix;
const char *suffix;
const char *color; /* NULL; filled in by the setup code if
* color is enabled */
};
-struct diff_words_style
-{
+struct diff_words_style {
enum diff_words_type type;
struct diff_words_style_elem new, old, ctx;
const char *newline;
};
-struct diff_words_style diff_words_styles[] = {
+static struct diff_words_style diff_words_styles[] = {
{ DIFF_WORDS_PORCELAIN, {"+", "\n"}, {"-", "\n"}, {" ", "\n"}, "~\n" },
{ DIFF_WORDS_PLAIN, {"{+", "+}"}, {"[-", "-]"}, {"", ""}, "\n" },
{ DIFF_WORDS_COLOR, {"", ""}, {"", ""}, {"", ""}, "\n" }
emit_line(ecbdata->opt, plain, reset, line, len);
fputs("~\n", ecbdata->opt->file);
} else {
- /* don't print the prefix character */
- emit_line(ecbdata->opt, plain, reset, line+1, len-1);
+ /*
+ * Skip the prefix character, if any. With
+ * diff_suppress_blank_empty, there may be
+ * none.
+ */
+ if (line[0] != '\n') {
+ line++;
+ len--;
+ }
+ emit_line(ecbdata->opt, plain, reset, line, len);
}
return;
}
uintmax_t max_change = 0, max_len = 0;
int total_files = data->nr;
int width, name_width;
- const char *reset, *set, *add_c, *del_c;
+ const char *reset, *add_c, *del_c;
const char *line_prefix = "";
struct strbuf *msg = NULL;
/* Find the longest filename and max number of changes */
reset = diff_get_color_opt(options, DIFF_RESET);
- set = diff_get_color_opt(options, DIFF_PLAIN);
add_c = diff_get_color_opt(options, DIFF_FILE_NEW);
del_c = diff_get_color_opt(options, DIFF_FILE_OLD);
struct dirstat_dir {
struct dirstat_file *files;
- int alloc, nr, percent, cumulative;
+ int alloc, nr, permille, cumulative;
};
static long gather_dirstat(struct diff_options *opt, struct dirstat_dir *dir,
* under this directory (sources == 1).
*/
if (baselen && sources != 1) {
- int permille = this_dir * 1000 / changed;
- if (permille) {
- int percent = permille / 10;
- if (percent >= dir->percent) {
+ if (this_dir) {
+ int permille = this_dir * 1000 / changed;
+ if (permille >= dir->permille) {
fprintf(opt->file, "%s%4d.%01d%% %.*s\n", line_prefix,
- percent, permille % 10, baselen, base);
+ permille / 10, permille % 10, baselen, base);
if (!dir->cumulative)
return 0;
}
dir.files = NULL;
dir.alloc = 0;
dir.nr = 0;
- dir.percent = options->dirstat_percent;
+ dir.permille = options->dirstat_permille;
dir.cumulative = DIFF_OPT_TST(options, DIRSTAT_CUMULATIVE);
changed = 0;
struct diff_filepair *p = q->queue[i];
const char *name;
unsigned long copied, added, damage;
+ int content_changed;
+
+ name = p->two->path ? p->two->path : p->one->path;
+
+ if (p->one->sha1_valid && p->two->sha1_valid)
+ content_changed = hashcmp(p->one->sha1, p->two->sha1);
+ else
+ content_changed = 1;
+
+ if (!content_changed) {
+ /*
+ * The SHA1 has not changed, so pre-/post-content is
+ * identical. We can therefore skip looking at the
+ * file contents altogether.
+ */
+ damage = 0;
+ goto found_damage;
+ }
- name = p->one->path ? p->one->path : p->two->path;
+ if (DIFF_OPT_TST(options, DIRSTAT_BY_FILE)) {
+ /*
+ * In --dirstat-by-file mode, we don't really need to
+ * look at the actual file contents at all.
+ * The fact that the SHA1 changed is enough for us to
+ * add this file to the list of results
+ * (with each file contributing equal damage).
+ */
+ damage = 1;
+ goto found_damage;
+ }
if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
diff_populate_filespec(p->one, 0);
/*
* Original minus copied is the removed material,
* added is the new material. They are both damages
- * made to the preimage. In --dirstat-by-file mode, count
- * damaged files, not damaged lines. This is done by
- * counting only a single damaged line per file.
+ * made to the preimage.
+ * If the resulting damage is zero, we know that
+ * diffcore_count_changes() considers the two entries to
+ * be identical, but since content_changed is true, we
+ * know that there must have been _some_ kind of change,
+ * so we force all entries to have damage > 0.
*/
damage = (p->one->size - copied) + added;
- if (DIFF_OPT_TST(options, DIRSTAT_BY_FILE) && damage > 0)
+ if (!damage)
damage = 1;
+found_damage:
ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc);
dir.files[dir.nr].name = name;
dir.files[dir.nr].changed = damage;
gather_dirstat(options, &dir, changed, "", 0);
}
+static void show_dirstat_by_line(struct diffstat_t *data, struct diff_options *options)
+{
+ int i;
+ unsigned long changed;
+ struct dirstat_dir dir;
+
+ if (data->nr == 0)
+ return;
+
+ dir.files = NULL;
+ dir.alloc = 0;
+ dir.nr = 0;
+ dir.permille = options->dirstat_permille;
+ dir.cumulative = DIFF_OPT_TST(options, DIRSTAT_CUMULATIVE);
+
+ changed = 0;
+ for (i = 0; i < data->nr; i++) {
+ struct diffstat_file *file = data->files[i];
+ unsigned long damage = file->added + file->deleted;
+ if (file->is_binary)
+ /*
+ * binary files counts bytes, not lines. Must find some
+ * way to normalize binary bytes vs. textual lines.
+ * The following heuristic assumes that there are 64
+ * bytes per "line".
+ * This is stupid and ugly, but very cheap...
+ */
+ damage = (damage + 63) / 64;
+ ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc);
+ dir.files[dir.nr].name = file->name;
+ dir.files[dir.nr].changed = damage;
+ changed += damage;
+ dir.nr++;
+ }
+
+ /* This can happen even with many files, if everything was renames */
+ if (!changed)
+ return;
+
+ /* Show all directories with more than x% of the changes */
+ qsort(dir.files, dir.nr, sizeof(dir.files[0]), dirstat_compare);
+ gather_dirstat(options, &dir, changed, "", 0);
+}
+
static void free_diffstat_info(struct diffstat_t *diffstat)
{
int i;
}
}
- if (!DIFF_OPT_TST(o, TEXT) &&
+ if (o->irreversible_delete && lbl[1][0] == '/') {
+ fprintf(o->file, "%s", header.buf);
+ strbuf_reset(&header);
+ goto free_ab_and_return;
+ } else if (!DIFF_OPT_TST(o, TEXT) &&
( (!textconv_one && diff_filespec_is_binary(one)) ||
(!textconv_two && diff_filespec_is_binary(two)) )) {
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
fprintf(o->file, "%sBinary files %s and %s differ\n",
line_prefix, lbl[0], lbl[1]);
o->found_changes = 1;
- }
- else {
+ } else {
/* Crazy xdl interfaces.. */
const char *diffopts = getenv("GIT_DIFF_OPTS");
xpparam_t xpp;
data->is_unmerged = 1;
return;
}
- if (complete_rewrite) {
+
+ if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
+ data->is_binary = 1;
+ data->added = diff_filespec_size(two);
+ data->deleted = diff_filespec_size(one);
+ }
+
+ else if (complete_rewrite) {
diff_populate_filespec(one, 0);
diff_populate_filespec(two, 0);
data->deleted = count_lines(one->data, one->size);
data->added = count_lines(two->data, two->size);
- goto free_and_return;
}
- if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
- die("unable to read files to diff");
- if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
- data->is_binary = 1;
- data->added = mf2.size;
- data->deleted = mf1.size;
- } else {
+ else {
/* Crazy xdl interfaces.. */
xpparam_t xpp;
xdemitconf_t xecfg;
+ if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
+ die("unable to read files to diff");
+
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
xpp.flags = o->xdl_opts;
&xpp, &xecfg);
}
- free_and_return:
diff_free_filespec_data(one);
diff_free_filespec_data(two);
}
options->line_termination = '\n';
options->break_opt = -1;
options->rename_limit = -1;
- options->dirstat_percent = 3;
+ options->dirstat_permille = diff_dirstat_permille_default;
options->context = 3;
options->change = diff_change;
return argcount;
}
+static int parse_dirstat_opt(struct diff_options *options, const char *params)
+{
+ struct strbuf errmsg = STRBUF_INIT;
+ if (parse_dirstat_params(options, params, &errmsg))
+ die(_("Failed to parse --dirstat/-X option parameter:\n%s"),
+ errmsg.buf);
+ strbuf_release(&errmsg);
+ /*
+ * The caller knows a dirstat-related option is given from the command
+ * line; allow it to say "return this_function();"
+ */
+ options->output_format |= DIFF_FORMAT_DIRSTAT;
+ return 1;
+}
+
int diff_opt_parse(struct diff_options *options, const char **av, int ac)
{
const char *arg = av[0];
options->output_format |= DIFF_FORMAT_NUMSTAT;
else if (!strcmp(arg, "--shortstat"))
options->output_format |= DIFF_FORMAT_SHORTSTAT;
- else if (opt_arg(arg, 'X', "dirstat", &options->dirstat_percent))
- options->output_format |= DIFF_FORMAT_DIRSTAT;
- else if (!strcmp(arg, "--cumulative")) {
- options->output_format |= DIFF_FORMAT_DIRSTAT;
- DIFF_OPT_SET(options, DIRSTAT_CUMULATIVE);
- } else if (opt_arg(arg, 0, "dirstat-by-file",
- &options->dirstat_percent)) {
- options->output_format |= DIFF_FORMAT_DIRSTAT;
- DIFF_OPT_SET(options, DIRSTAT_BY_FILE);
+ else if (!strcmp(arg, "-X") || !strcmp(arg, "--dirstat"))
+ return parse_dirstat_opt(options, "");
+ else if (!prefixcmp(arg, "-X"))
+ return parse_dirstat_opt(options, arg + 2);
+ else if (!prefixcmp(arg, "--dirstat="))
+ return parse_dirstat_opt(options, arg + 10);
+ else if (!strcmp(arg, "--cumulative"))
+ return parse_dirstat_opt(options, "cumulative");
+ else if (!strcmp(arg, "--dirstat-by-file"))
+ return parse_dirstat_opt(options, "files");
+ else if (!prefixcmp(arg, "--dirstat-by-file=")) {
+ parse_dirstat_opt(options, "files");
+ return parse_dirstat_opt(options, arg + 18);
}
else if (!strcmp(arg, "--check"))
options->output_format |= DIFF_FORMAT_CHECKDIFF;
return error("invalid argument to -M: %s", arg+2);
options->detect_rename = DIFF_DETECT_RENAME;
}
+ else if (!strcmp(arg, "-D") || !strcmp(arg, "--irreversible-delete")) {
+ options->irreversible_delete = 1;
+ }
else if (!prefixcmp(arg, "-C") || !prefixcmp(arg, "--find-copies=") ||
!strcmp(arg, "--find-copies")) {
if (options->detect_rename == DIFF_DETECT_COPY)
return 1;
}
+static const char rename_limit_warning[] =
+"inexact rename detection was skipped due to too many files.";
+
+static const char degrade_cc_to_c_warning[] =
+"only found copies from modified paths due to too many files.";
+
+static const char rename_limit_advice[] =
+"you may want to set your %s variable to at least "
+"%d and retry the command.";
+
+void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc)
+{
+ if (degraded_cc)
+ warning(degrade_cc_to_c_warning);
+ else if (needed)
+ warning(rename_limit_warning);
+ else
+ return;
+ if (0 < needed && needed < 32767)
+ warning(rename_limit_advice, varname, needed);
+}
+
void diff_flush(struct diff_options *options)
{
struct diff_queue_struct *q = &diff_queued_diff;
int i, output_format = options->output_format;
int separator = 0;
+ int dirstat_by_line = 0;
/*
* Order: raw, stat, summary, patch
separator++;
}
- if (output_format & (DIFF_FORMAT_DIFFSTAT|DIFF_FORMAT_SHORTSTAT|DIFF_FORMAT_NUMSTAT)) {
+ if (output_format & DIFF_FORMAT_DIRSTAT && DIFF_OPT_TST(options, DIRSTAT_BY_LINE))
+ dirstat_by_line = 1;
+
+ if (output_format & (DIFF_FORMAT_DIFFSTAT|DIFF_FORMAT_SHORTSTAT|DIFF_FORMAT_NUMSTAT) ||
+ dirstat_by_line) {
struct diffstat_t diffstat;
memset(&diffstat, 0, sizeof(struct diffstat_t));
show_stats(&diffstat, options);
if (output_format & DIFF_FORMAT_SHORTSTAT)
show_shortstats(&diffstat, options);
+ if (output_format & DIFF_FORMAT_DIRSTAT)
+ show_dirstat_by_line(&diffstat, options);
free_diffstat_info(&diffstat);
separator++;
}
- if (output_format & DIFF_FORMAT_DIRSTAT)
+ if ((output_format & DIFF_FORMAT_DIRSTAT) && !dirstat_by_line)
show_dirstat(options);
if (output_format & DIFF_FORMAT_SUMMARY && !is_summary_empty(q)) {
int diff_result_code(struct diff_options *opt, int status)
{
int result = 0;
+
+ diff_warn_rename_limit("diff.renamelimit",
+ opt->needed_rename_limit,
+ opt->degraded_cc_to_c);
if (!DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
!(opt->output_format & DIFF_FORMAT_CHECKDIFF))
return status;
DIFF_OPT_SET(options, HAS_CHANGES);
}
-void diff_unmerge(struct diff_options *options,
- const char *path,
- unsigned mode, const unsigned char *sha1)
+struct diff_filepair *diff_unmerge(struct diff_options *options, const char *path)
{
+ struct diff_filepair *pair;
struct diff_filespec *one, *two;
if (options->prefix &&
strncmp(path, options->prefix, options->prefix_length))
- return;
+ return NULL;
one = alloc_filespec(path);
two = alloc_filespec(path);
- fill_filespec(one, sha1, mode);
- diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1;
+ pair = diff_queue(&diff_queued_diff, one, two);
+ pair->is_unmerged = 1;
+ return pair;
}
static char *run_textconv(const char *pgm, struct diff_filespec *spec,