diff-options: add --stat (take 2)

Now, you can say "git diff --stat" (to get an idea how many changes are
uncommitted), or "git log --stat".

Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>

Signed-off-by: Junio C Hamano <junkio@cox.net>

1 files changed, 217 insertions, 5 deletions

diff --git a/diff.c b/diff.c
index a14e6644c..14ffc774f 100644
--- a/diff.c
+++ b/diff.c
@@ -8,7 +8,7 @@
 #include "quote.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "xdiff/xdiff.h"
+#include "xdiff-interface.h"
 
 static int use_size_cache;
 
@@ -195,6 +195,137 @@ static int fn_out(void *priv, mmbuffer_t *mb, int nbuf)
 	return 0;
 }
 
+struct diffstat_t {
+	struct xdiff_emit_state xm;
+
+	int nr;
+	int alloc;
+	struct diffstat_file {
+		char *name;
+		unsigned int added, deleted;
+	} **files;
+};
+
+static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat,
+		const char *name)
+{
+	struct diffstat_file *x;
+	x = xcalloc(sizeof (*x), 1);
+	if (diffstat->nr == diffstat->alloc) {
+		diffstat->alloc = alloc_nr(diffstat->alloc);
+		diffstat->files = xrealloc(diffstat->files,
+				diffstat->alloc * sizeof(x));
+	}
+	diffstat->files[diffstat->nr++] = x;
+	x->name = strdup(name);
+	return x;
+}
+
+static void diffstat_consume(void *priv, char *line, unsigned long len)
+{
+	struct diffstat_t *diffstat = priv;
+	struct diffstat_file *x = diffstat->files[diffstat->nr - 1];
+
+	if (line[0] == '+')
+		x->added++;
+	else if (line[0] == '-')
+		x->deleted++;
+}
+
+static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++";
+static const char minuses[]= "----------------------------------------------------------------------";
+
+static void show_stats(struct diffstat_t* data)
+{
+	char *prefix = "";
+	int i, len, add, del, total, adds = 0, dels = 0;
+	int max, max_change = 0, max_len = 0;
+	int total_files = data->nr;
+
+	if (data->nr == 0)
+		return;
+
+	printf("---\n");
+
+	for (i = 0; i < data->nr; i++) {
+		struct diffstat_file *file = data->files[i];
+
+		if (max_change < file->added + file->deleted)
+			max_change = file->added + file->deleted;
+		len = strlen(file->name);
+		if (max_len < len)
+			max_len = len;
+	}
+
+	for (i = 0; i < data->nr; i++) {
+		char *name = data->files[i]->name;
+		int added = data->files[i]->added;
+		int deleted = data->files[i]->deleted;
+
+		if (0 < (len = quote_c_style(name, NULL, NULL, 0))) {
+			char *qname = xmalloc(len + 1);
+			quote_c_style(name, qname, NULL, 0);
+			free(name);
+			name = qname;
+		}
+
+		/*
+		 * "scale" the filename
+		 */
+		len = strlen(name);
+		max = max_len;
+		if (max > 50)
+			max = 50;
+		if (len > max) {
+			char *slash;
+			prefix = "...";
+			max -= 3;
+			name += len - max;
+			slash = strchr(name, '/');
+			if (slash)
+				name = slash;
+		}
+		len = max;
+
+		/*
+		 * scale the add/delete
+		 */
+		max = max_change;
+		if (max + len > 70)
+			max = 70 - len;
+
+		if (added < 0) {
+			/* binary file */
+			printf(" %s%-*s |  Bin\n", prefix, len, name);
+			continue;
+		} else if (added + deleted == 0) {
+			total_files--;
+			continue;
+		}
+
+		add = added;
+		del = deleted;
+		total = add + del;
+		adds += add;
+		dels += del;
+
+		if (max_change > 0) {
+			total = (total * max + max_change / 2) / max_change;
+			add = (add * max + max_change / 2) / max_change;
+			del = total - add;
+		}
+		/* TODO: binary */
+		printf(" %s%-*s |%5d %.*s%.*s\n", prefix,
+				len, name, added + deleted,
+				add, pluses, del, minuses);
+		free(name);
+		free(data->files[i]);
+	}
+	free(data->files);
+	printf(" %d files changed, %d insertions(+), %d deletions(-)\n",
+			total_files, adds, dels);
+}
+
 #define FIRST_FEW_BYTES 8000
 static int mmfile_is_binary(mmfile_t *mf)
 {
@@ -286,6 +417,35 @@ static void builtin_diff(const char *name_a,
 	return;
 }
 
+static void builtin_diffstat(const char *name_a, const char *name_b,
+		struct diff_filespec *one, struct diff_filespec *two,
+		struct diffstat_t *diffstat)
+{
+	mmfile_t mf1, mf2;
+	struct diffstat_file *data;
+
+	data = diffstat_add(diffstat, name_a ? name_a : name_b);
+
+	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
+		die("unable to read files to diff");
+
+	if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2))
+		data->added = -1;
+	else {
+		/* Crazy xdl interfaces.. */
+		xpparam_t xpp;
+		xdemitconf_t xecfg;
+		xdemitcb_t ecb;
+
+		xpp.flags = XDF_NEED_MINIMAL;
+		xecfg.ctxlen = 3;
+		xecfg.flags = XDL_EMIT_FUNCNAMES;
+		ecb.outf = xdiff_outf;
+		ecb.priv = diffstat;
+		xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
+	}
+}
+
 struct diff_filespec *alloc_filespec(const char *path)
 {
 	int namelen = strlen(path);
@@ -819,6 +979,27 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 	free(other_munged);
 }
 
+static void run_diffstat(struct diff_filepair *p, struct diff_options *o,
+		struct diffstat_t *diffstat)
+{
+	const char *name;
+	const char *other;
+
+	if (DIFF_PAIR_UNMERGED(p)) {
+		/* unmerged */
+		builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat);
+		return;
+	}
+
+	name = p->one->path;
+	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
+
+	diff_fill_sha1_info(p->one);
+	diff_fill_sha1_info(p->two);
+
+	builtin_diffstat(name, other, p->one, p->two, diffstat);
+}
+
 void diff_setup(struct diff_options *options)
 {
 	memset(options, 0, sizeof(*options));
@@ -866,6 +1047,8 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		options->output_format = DIFF_FORMAT_PATCH;
 		options->with_raw = 1;
 	}
+	else if (!strcmp(arg, "--stat"))
+		options->output_format = DIFF_FORMAT_DIFFSTAT;
 	else if (!strcmp(arg, "-z"))
 		options->line_termination = 0;
 	else if (!strncmp(arg, "-l", 2))
@@ -1160,11 +1343,24 @@ static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o)
 
 	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
 	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
-		return; /* no tree diffs in patch format */ 
+		return; /* no tree diffs in patch format */
 
 	run_diff(p, o);
 }
 
+static void diff_flush_stat(struct diff_filepair *p, struct diff_options *o,
+		struct diffstat_t *diffstat)
+{
+	if (diff_unmodified_pair(p))
+		return;
+
+	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
+	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
+		return; /* no tree diffs in patch format */
+
+	run_diffstat(p, o, diffstat);
+}
+
 int diff_queue_is_empty(void)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
@@ -1276,7 +1472,8 @@ static void diff_resolve_rename_copy(void)
 
 static void flush_one_pair(struct diff_filepair *p,
 			   int diff_output_format,
-			   struct diff_options *options)
+			   struct diff_options *options,
+			   struct diffstat_t *diffstat)
 {
 	int inter_name_termination = '\t';
 	int line_termination = options->line_termination;
@@ -1291,6 +1488,9 @@ static void flush_one_pair(struct diff_filepair *p,
 		break;
 	default:
 		switch (diff_output_format) {
+		case DIFF_FORMAT_DIFFSTAT:
+			diff_flush_stat(p, options, diffstat);
+			break;
 		case DIFF_FORMAT_PATCH:
 			diff_flush_patch(p, options);
 			break;
@@ -1316,19 +1516,31 @@ void diff_flush(struct diff_options *options)
 	struct diff_queue_struct *q = &diff_queued_diff;
 	int i;
 	int diff_output_format = options->output_format;
+	struct diffstat_t *diffstat = NULL;
+
+	if (diff_output_format == DIFF_FORMAT_DIFFSTAT) {
+		diffstat = xcalloc(sizeof (struct diffstat_t), 1);
+		diffstat->xm.consume = diffstat_consume;
+	}
 
 	if (options->with_raw) {
 		for (i = 0; i < q->nr; i++) {
 			struct diff_filepair *p = q->queue[i];
-			flush_one_pair(p, DIFF_FORMAT_RAW, options);
+			flush_one_pair(p, DIFF_FORMAT_RAW, options, NULL);
 		}
 		putchar(options->line_termination);
 	}
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
-		flush_one_pair(p, diff_output_format, options);
+		flush_one_pair(p, diff_output_format, options, diffstat);
 		diff_free_filepair(p);
 	}
+
+	if (diffstat) {
+		show_stats(diffstat);
+		free(diffstat);
+	}
+
 	free(q->queue);
 	q->queue = NULL;
 	q->nr = q->alloc = 0;