Merge branch 'jh/dirstat-lines'

gitster · gitster · commit df54e2bfd6af · 2011-05-13T11:01:32.000-07:00
* jh/dirstat-lines:
  Mark dirstat error messages for translation
  Improve error handling when parsing dirstat parameters
  New --dirstat=lines mode, doing dirstat analysis based on diffstat
  Allow specifying --dirstat cut-off percentage as a floating point number
  Add config variable for specifying default --dirstat behavior
  Refactor --dirstat parsing; deprecate --cumulative and --dirstat-by-file
  Make --dirstat=0 output directories that contribute &lt; 0.1% of changes
  Add several testcases for --dirstat and friends
diff --git a/Documentation/diff-config.txt b/Documentation/diff-config.txt
@@ -8,6 +8,50 @@ diff.autorefreshindex::
 	affects only 'git diff' Porcelain, and not lower level
 	'diff' commands such as 'git diff-files'.
 
+diff.dirstat::
+	A comma separated list of `--dirstat` parameters specifying the
+	default behavior of the `--dirstat` option to linkgit:git-diff[1]`
+	and friends. The defaults can be overridden on the command line
+	(using `--dirstat=<param1,param2,...>`). The fallback defaults
+	(when not changed by `diff.dirstat`) are `changes,noncumulative,3`.
+	The following parameters are available:
++
+--
+`changes`;;
+	Compute the dirstat numbers by counting the lines that have been
+	removed from the source, or added to the destination. This ignores
+	the amount of pure code movements within a file.  In other words,
+	rearranging lines in a file is not counted as much as other changes.
+	This is the default behavior when no parameter is given.
+`lines`;;
+	Compute the dirstat numbers by doing the regular line-based diff
+	analysis, and summing the removed/added line counts. (For binary
+	files, count 64-byte chunks instead, since binary files have no
+	natural concept of lines). This is a more expensive `--dirstat`
+	behavior than the `changes` behavior, but it does count rearranged
+	lines within a file as much as other changes. The resulting output
+	is consistent with what you get from the other `--*stat` options.
+`files`;;
+	Compute the dirstat numbers by counting the number of files changed.
+	Each changed file counts equally in the dirstat analysis. This is
+	the computationally cheapest `--dirstat` behavior, since it does
+	not have to look at the file contents at all.
+`cumulative`;;
+	Count changes in a child directory for the parent directory as well.
+	Note that when using `cumulative`, the sum of the percentages
+	reported may exceed 100%. The default (non-cumulative) behavior can
+	be specified with the `noncumulative` parameter.
+<limit>;;
+	An integer parameter specifies a cut-off percent (3% by default).
+	Directories contributing less than this percentage of the changes
+	are not shown in the output.
+--
++
+Example: The following will count changed files, while ignoring
+directories with less than 10% of the total amount of changed files,
+and accumulating child directory counts in the parent directories:
+`files,10,cumulative`.
+
 diff.external::
 	If this config variable is set, diff generation is not
 	performed using the internal diff machinery, but using the
diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
@@ -66,19 +66,49 @@ endif::git-format-patch[]
 	number of modified files, as well as number of added and deleted
 	lines.
 
---dirstat[=<limit>]::
-	Output the distribution of relative amount of changes (number of lines added or
-	removed) for each sub-directory. Directories with changes below
-	a cut-off percent (3% by default) are not shown. The cut-off percent
-	can be set with `--dirstat=<limit>`. Changes in a child directory are not
-	counted for the parent directory, unless `--cumulative` is used.
+--dirstat[=<param1,param2,...>]::
+	Output the distribution of relative amount of changes for each
+	sub-directory. The behavior of `--dirstat` can be customized by
+	passing it a comma separated list of parameters.
+	The defaults are controlled by the `diff.dirstat` configuration
+	variable (see linkgit:git-config[1]).
+	The following parameters are available:
 +
-Note that the `--dirstat` option computes the changes while ignoring
-the amount of pure code movements within a file.  In other words,
-rearranging lines in a file is not counted as much as other changes.
-
---dirstat-by-file[=<limit>]::
-	Same as `--dirstat`, but counts changed files instead of lines.
+--
+`changes`;;
+	Compute the dirstat numbers by counting the lines that have been
+	removed from the source, or added to the destination. This ignores
+	the amount of pure code movements within a file.  In other words,
+	rearranging lines in a file is not counted as much as other changes.
+	This is the default behavior when no parameter is given.
+`lines`;;
+	Compute the dirstat numbers by doing the regular line-based diff
+	analysis, and summing the removed/added line counts. (For binary
+	files, count 64-byte chunks instead, since binary files have no
+	natural concept of lines). This is a more expensive `--dirstat`
+	behavior than the `changes` behavior, but it does count rearranged
+	lines within a file as much as other changes. The resulting output
+	is consistent with what you get from the other `--*stat` options.
+`files`;;
+	Compute the dirstat numbers by counting the number of files changed.
+	Each changed file counts equally in the dirstat analysis. This is
+	the computationally cheapest `--dirstat` behavior, since it does
+	not have to look at the file contents at all.
+`cumulative`;;
+	Count changes in a child directory for the parent directory as well.
+	Note that when using `cumulative`, the sum of the percentages
+	reported may exceed 100%. The default (non-cumulative) behavior can
+	be specified with the `noncumulative` parameter.
+<limit>;;
+	An integer parameter specifies a cut-off percent (3% by default).
+	Directories contributing less than this percentage of the changes
+	are not shown in the output.
+--
++
+Example: The following will count changed files, while ignoring
+directories with less than 10% of the total amount of changed files,
+and accumulating child directory counts in the parent directories:
+`--dirstat=files,10,cumulative`.
 
 --summary::
 	Output a condensed summary of extended header information
diff --git a/diff.c b/diff.c
@@ -31,6 +31,7 @@ static const char *external_diff_cmd_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] = {
@@ -66,6 +67,58 @@ static int parse_diff_color_slot(const char *var, int ofs)
 	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)
@@ -145,6 +198,17 @@ int git_diff_basic_config(const char *var, const char *value, void *cb)
 		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);
 
@@ -1455,7 +1519,7 @@ struct dirstat_file {
 
 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,
@@ -1502,12 +1566,11 @@ 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;
 			}
@@ -1533,7 +1596,7 @@ static void show_dirstat(struct diff_options *options)
 	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;
@@ -1622,6 +1685,50 @@ static void show_dirstat(struct diff_options *options)
 	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;
@@ -2891,7 +2998,7 @@ void diff_setup(struct diff_options *options)
 	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;
@@ -3149,6 +3256,21 @@ static int stat_opt(struct diff_options *options, const char **av)
 	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];
@@ -3168,15 +3290,19 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		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;
@@ -4023,6 +4149,7 @@ 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
@@ -4043,7 +4170,11 @@ void diff_flush(struct diff_options *options)
 		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));
@@ -4058,10 +4189,12 @@ void diff_flush(struct diff_options *options)
 			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)) {
diff --git a/diff.h b/diff.h
@@ -78,6 +78,7 @@ typedef struct strbuf *(*diff_prefix_fn_t)(struct diff_options *opt, void *data)
 #define DIFF_OPT_IGNORE_UNTRACKED_IN_SUBMODULES (1 << 25)
 #define DIFF_OPT_IGNORE_DIRTY_SUBMODULES (1 << 26)
 #define DIFF_OPT_OVERRIDE_SUBMODULE_CONFIG (1 << 27)
+#define DIFF_OPT_DIRSTAT_BY_LINE     (1 << 28)
 
 #define DIFF_OPT_TST(opts, flag)    ((opts)->flags & DIFF_OPT_##flag)
 #define DIFF_OPT_SET(opts, flag)    ((opts)->flags |= DIFF_OPT_##flag)
@@ -114,7 +115,7 @@ struct diff_options {
 	int needed_rename_limit;
 	int degraded_cc_to_c;
 	int show_rename_progress;
-	int dirstat_percent;
+	int dirstat_permille;
 	int setup;
 	int abbrev;
 	const char *prefix;
diff --git a/t/t4047-diff-dirstat.sh b/t/t4047-diff-dirstat.sh
