1 files changed, 265 insertions, 123 deletions

diff --git a/combine-diff.c b/combine-diff.c
index 60d03676bb..bb1cc96c4e 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -7,6 +7,8 @@
 #include "xdiff-interface.h"
 #include "log-tree.h"
 #include "refs.h"
+#include "userdiff.h"
+#include "sha1-array.h"
 
 static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr, int n, int num_parent)
 {
@@ -80,6 +82,7 @@ struct lline {
 /* Lines surviving in the merge result */
 struct sline {
 	struct lline *lost_head, **lost_tail;
+	struct lline *next_lost;
 	char *bol;
 	int len;
 	/* bit 0 up to (N-1) are on if the parent has this line (i.e.
@@ -91,7 +94,9 @@ struct sline {
 	unsigned long *p_lno;
 };
 
-static char *grab_blob(const unsigned char *sha1, unsigned int mode, unsigned long *size)
+static char *grab_blob(const unsigned char *sha1, unsigned int mode,
+		       unsigned long *size, struct userdiff_driver *textconv,
+		       const char *path)
 {
 	char *blob;
 	enum object_type type;
@@ -104,6 +109,11 @@ static char *grab_blob(const unsigned char *sha1, unsigned int mode, unsigned lo
 		/* deleted blob */
 		*size = 0;
 		return xcalloc(1, 1);
+	} else if (textconv) {
+		struct diff_filespec *df = alloc_filespec(path);
+		fill_filespec(df, sha1, 1, mode);
+		*size = fill_textconv(textconv, df, &blob);
+		free_filespec(df);
 	} else {
 		blob = read_sha1_file(sha1, &type, size);
 		if (type != OBJ_BLOB)
@@ -121,18 +131,12 @@ static void append_lost(struct sline *sline, int n, const char *line, int len)
 
 	/* Check to see if we can squash things */
 	if (sline->lost_head) {
-		struct lline *last_one = NULL;
-		/* We cannot squash it with earlier one */
-		for (lline = sline->lost_head;
-		     lline;
-		     lline = lline->next)
-			if (lline->parent_map & this_mask)
-				last_one = lline;
-		lline = last_one ? last_one->next : sline->lost_head;
+		lline = sline->next_lost;
 		while (lline) {
 			if (lline->len == len &&
 			    !memcmp(lline->line, line, len)) {
 				lline->parent_map |= this_mask;
+				sline->next_lost = lline->next;
 				return;
 			}
 			lline = lline->next;
@@ -147,6 +151,7 @@ static void append_lost(struct sline *sline, int n, const char *line, int len)
 	lline->line[len] = 0;
 	*sline->lost_tail = lline;
 	sline->lost_tail = &lline->next;
+	sline->next_lost = NULL;
 }
 
 struct combine_diff_state {
@@ -168,25 +173,28 @@ static void consume_line(void *state_, char *line, unsigned long len)
 				      &state->nb, &state->nn))
 			return;
 		state->lno = state->nb;
-		if (!state->nb)
-			/* @@ -1,2 +0,0 @@ to remove the
-			 * first two lines...
-			 */
-			state->nb = 1;
-		if (state->nn == 0)
+		if (state->nn == 0) {
 			/* @@ -X,Y +N,0 @@ removed Y lines
 			 * that would have come *after* line N
 			 * in the result.  Our lost buckets hang
 			 * to the line after the removed lines,
+			 *
+			 * Note that this is correct even when N == 0,
+			 * in which case the hunk removes the first
+			 * line in the file.
 			 */
 			state->lost_bucket = &state->sline[state->nb];
-		else
+			if (!state->nb)
+				state->nb = 1;
+		} else {
 			state->lost_bucket = &state->sline[state->nb-1];
+		}
 		if (!state->sline[state->nb-1].p_lno)
 			state->sline[state->nb-1].p_lno =
 				xcalloc(state->num_parent,
 					sizeof(unsigned long));
 		state->sline[state->nb-1].p_lno[state->n] = state->ob;
+		state->lost_bucket->next_lost = state->lost_bucket->lost_head;
 		return;
 	}
 	if (!state->lost_bucket)
@@ -205,24 +213,25 @@ static void consume_line(void *state_, char *line, unsigned long len)
 static void combine_diff(const unsigned char *parent, unsigned int mode,
 			 mmfile_t *result_file,
 			 struct sline *sline, unsigned int cnt, int n,
-			 int num_parent)
+			 int num_parent, int result_deleted,
+			 struct userdiff_driver *textconv,
+			 const char *path)
 {
 	unsigned int p_lno, lno;
 	unsigned long nmask = (1UL << n);
 	xpparam_t xpp;
 	xdemitconf_t xecfg;
 	mmfile_t parent_file;
-	xdemitcb_t ecb;
 	struct combine_diff_state state;
 	unsigned long sz;
 
-	if (!cnt)
+	if (result_deleted)
 		return; /* result deleted */
 
-	parent_file.ptr = grab_blob(parent, mode, &sz);
+	parent_file.ptr = grab_blob(parent, mode, &sz, textconv, path);
 	parent_file.size = sz;
 	memset(&xpp, 0, sizeof(xpp));
-	xpp.flags = XDF_NEED_MINIMAL;
+	xpp.flags = 0;
 	memset(&xecfg, 0, sizeof(xecfg));
 	memset(&state, 0, sizeof(state));
 	state.nmask = nmask;
@@ -232,7 +241,7 @@ static void combine_diff(const unsigned char *parent, unsigned int mode,
 	state.n = n;
 
 	xdi_diff_outf(&parent_file, result_file, consume_line, &state,
-		      &xpp, &xecfg, &ecb);
+		      &xpp, &xecfg);
 	free(parent_file.ptr);
 
 	/* Assign line numbers for this parent.
@@ -414,7 +423,7 @@ static int make_hunks(struct sline *sline, unsigned long cnt,
 						     hunk_begin, j);
 				la = (la + context < cnt + 1) ?
 					(la + context) : cnt + 1;
-				while (j <= --la) {
+				while (la && j <= --la) {
 					if (sline[la].flag & mark) {
 						contin = 1;
 						break;
@@ -518,19 +527,20 @@ static void show_line_to_eol(const char *line, int len, const char *reset)
 }
 
 static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent,
-		       int use_color)
+		       int use_color, int result_deleted)
 {
 	unsigned long mark = (1UL<<num_parent);
 	unsigned long no_pre_delete = (2UL<<num_parent);
 	int i;
 	unsigned long lno = 0;
 	const char *c_frag = diff_get_color(use_color, DIFF_FRAGINFO);
+	const char *c_func = diff_get_color(use_color, DIFF_FUNCINFO);
 	const char *c_new = diff_get_color(use_color, DIFF_FILE_NEW);
 	const char *c_old = diff_get_color(use_color, DIFF_FILE_OLD);
 	const char *c_plain = diff_get_color(use_color, DIFF_PLAIN);
 	const char *c_reset = diff_get_color(use_color, DIFF_RESET);
 
-	if (!cnt)
+	if (result_deleted)
 		return; /* result deleted */
 
 	while (1) {
@@ -589,7 +599,9 @@ static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent,
 				    comment_end = i;
 			}
 			if (comment_end)
-				putchar(' ');
+				printf("%s%s %s%s", c_reset,
+						    c_plain, c_reset,
+						    c_func);
 			for (i = 0; i < comment_end; i++)
 				putchar(hunk_comment[i]);
 		}
@@ -680,27 +692,108 @@ static void dump_quoted_path(const char *head,
 	puts(buf.buf);
 }
 
+static void show_combined_header(struct combine_diff_path *elem,
+				 int num_parent,
+				 int dense,
+				 struct rev_info *rev,
+				 int mode_differs,
+				 int show_file_header)
+{
+	struct diff_options *opt = &rev->diffopt;
+	int abbrev = DIFF_OPT_TST(opt, FULL_INDEX) ? 40 : DEFAULT_ABBREV;
+	const char *a_prefix = opt->a_prefix ? opt->a_prefix : "a/";
+	const char *b_prefix = opt->b_prefix ? opt->b_prefix : "b/";
+	const char *c_meta = diff_get_color_opt(opt, DIFF_METAINFO);
+	const char *c_reset = diff_get_color_opt(opt, DIFF_RESET);
+	const char *abb;
+	int added = 0;
+	int deleted = 0;
+	int i;
+
+	if (rev->loginfo && !rev->no_commit_id)
+		show_log(rev);
+
+	dump_quoted_path(dense ? "diff --cc " : "diff --combined ",
+			 "", elem->path, c_meta, c_reset);
+	printf("%sindex ", c_meta);
+	for (i = 0; i < num_parent; i++) {
+		abb = find_unique_abbrev(elem->parent[i].sha1,
+					 abbrev);
+		printf("%s%s", i ? "," : "", abb);
+	}
+	abb = find_unique_abbrev(elem->sha1, abbrev);
+	printf("..%s%s\n", abb, c_reset);
+
+	if (mode_differs) {
+		deleted = !elem->mode;
+
+		/* We say it was added if nobody had it */
+		added = !deleted;
+		for (i = 0; added && i < num_parent; i++)
+			if (elem->parent[i].status !=
+			    DIFF_STATUS_ADDED)
+				added = 0;
+		if (added)
+			printf("%snew file mode %06o",
+			       c_meta, elem->mode);
+		else {
+			if (deleted)
+				printf("%sdeleted file ", c_meta);
+			printf("mode ");
+			for (i = 0; i < num_parent; i++) {
+				printf("%s%06o", i ? "," : "",
+				       elem->parent[i].mode);
+			}
+			if (elem->mode)
+				printf("..%06o", elem->mode);
+		}
+		printf("%s\n", c_reset);
+	}
+
+	if (!show_file_header)
+		return;
+
+	if (added)
+		dump_quoted_path("--- ", "", "/dev/null",
+				 c_meta, c_reset);
+	else
+		dump_quoted_path("--- ", a_prefix, elem->path,
+				 c_meta, c_reset);
+	if (deleted)
+		dump_quoted_path("+++ ", "", "/dev/null",
+				 c_meta, c_reset);
+	else
+		dump_quoted_path("+++ ", b_prefix, elem->path,
+				 c_meta, c_reset);
+}
+
 static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
-			    int dense, struct rev_info *rev)
+			    int dense, int working_tree_file,
+			    struct rev_info *rev)
 {
 	struct diff_options *opt = &rev->diffopt;
 	unsigned long result_size, cnt, lno;
+	int result_deleted = 0;
 	char *result, *cp;
 	struct sline *sline; /* survived lines */
 	int mode_differs = 0;
 	int i, show_hunks;
-	int working_tree_file = is_null_sha1(elem->sha1);
-	int abbrev = DIFF_OPT_TST(opt, FULL_INDEX) ? 40 : DEFAULT_ABBREV;
-	const char *a_prefix, *b_prefix;
 	mmfile_t result_file;
+	struct userdiff_driver *userdiff;
+	struct userdiff_driver *textconv = NULL;
+	int is_binary;
 
 	context = opt->context;
-	a_prefix = opt->a_prefix ? opt->a_prefix : "a/";
-	b_prefix = opt->b_prefix ? opt->b_prefix : "b/";
+	userdiff = userdiff_find_by_path(elem->path);
+	if (!userdiff)
+		userdiff = userdiff_find_by_name("default");
+	if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV))
+		textconv = userdiff_get_textconv(userdiff);
 
 	/* Read the result of merge first */
 	if (!working_tree_file)
-		result = grab_blob(elem->sha1, elem->mode, &result_size);
+		result = grab_blob(elem->sha1, elem->mode, &result_size,
+				   textconv, elem->path);
 	else {
 		/* Used by diff-tree to read from the working tree */
 		struct stat st;
@@ -723,9 +816,16 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 		} else if (S_ISDIR(st.st_mode)) {
 			unsigned char sha1[20];
 			if (resolve_gitlink_ref(elem->path, "HEAD", sha1) < 0)
-				result = grab_blob(elem->sha1, elem->mode, &result_size);
+				result = grab_blob(elem->sha1, elem->mode,
+						   &result_size, NULL, NULL);
 			else
-				result = grab_blob(sha1, elem->mode, &result_size);
+				result = grab_blob(sha1, elem->mode,
+						   &result_size, NULL, NULL);
+		} else if (textconv) {
+			struct diff_filespec *df = alloc_filespec(elem->path);
+			fill_filespec(df, null_sha1, 0, st.st_mode);
+			result_size = fill_textconv(textconv, df, &result);
+			free_filespec(df);
 		} else if (0 <= (fd = open(elem->path, O_RDONLY))) {
 			size_t len = xsize_t(st.st_size);
 			ssize_t done;
@@ -746,7 +846,7 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 
 			done = read_in_full(fd, result, len);
 			if (done < 0)
-				die("read error '%s'", elem->path);
+				die_errno("read error '%s'", elem->path);
 			else if (done < len)
 				die("early EOF '%s'", elem->path);
 
@@ -765,6 +865,7 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 		}
 		else {
 		deleted_file:
+			result_deleted = 1;
 			result_size = 0;
 			elem->mode = 0;
 			result = xcalloc(1, 1);
@@ -774,6 +875,38 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 			close(fd);
 	}
 
+	for (i = 0; i < num_parent; i++) {
+		if (elem->parent[i].mode != elem->mode) {
+			mode_differs = 1;
+			break;
+		}
+	}
+
+	if (textconv)
+		is_binary = 0;
+	else if (userdiff->binary != -1)
+		is_binary = userdiff->binary;
+	else {
+		is_binary = buffer_is_binary(result, result_size);
+		for (i = 0; !is_binary && i < num_parent; i++) {
+			char *buf;
+			unsigned long size;
+			buf = grab_blob(elem->parent[i].sha1,
+					elem->parent[i].mode,
+					&size, NULL, NULL);
+			if (buffer_is_binary(buf, size))
+				is_binary = 1;
+			free(buf);
+		}
+	}
+	if (is_binary) {
+		show_combined_header(elem, num_parent, dense, rev,
+				     mode_differs, 0);
+		printf("Binary files differ\n");
+		free(result);
+		return;
+	}
+
 	for (cnt = 0, cp = result; cp < result + result_size; cp++) {
 		if (*cp == '\n')
 			cnt++;
@@ -821,73 +954,17 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 			combine_diff(elem->parent[i].sha1,
 				     elem->parent[i].mode,
 				     &result_file, sline,
-				     cnt, i, num_parent);
-		if (elem->parent[i].mode != elem->mode)
-			mode_differs = 1;
+				     cnt, i, num_parent, result_deleted,
+				     textconv, elem->path);
 	}
 
 	show_hunks = make_hunks(sline, cnt, num_parent, dense);
 
 	if (show_hunks || mode_differs || working_tree_file) {
-		const char *abb;
-		int use_color = DIFF_OPT_TST(opt, COLOR_DIFF);
-		const char *c_meta = diff_get_color(use_color, DIFF_METAINFO);
-		const char *c_reset = diff_get_color(use_color, DIFF_RESET);
-		int added = 0;
-		int deleted = 0;
-
-		if (rev->loginfo && !rev->no_commit_id)
-			show_log(rev);
-		dump_quoted_path(dense ? "diff --cc " : "diff --combined ",
-				 "", elem->path, c_meta, c_reset);
-		printf("%sindex ", c_meta);
-		for (i = 0; i < num_parent; i++) {
-			abb = find_unique_abbrev(elem->parent[i].sha1,
-						 abbrev);
-			printf("%s%s", i ? "," : "", abb);
-		}
-		abb = find_unique_abbrev(elem->sha1, abbrev);
-		printf("..%s%s\n", abb, c_reset);
-
-		if (mode_differs) {
-			deleted = !elem->mode;
-
-			/* We say it was added if nobody had it */
-			added = !deleted;
-			for (i = 0; added && i < num_parent; i++)
-				if (elem->parent[i].status !=
-				    DIFF_STATUS_ADDED)
-					added = 0;
-			if (added)
-				printf("%snew file mode %06o",
-				       c_meta, elem->mode);
-			else {
-				if (deleted)
-					printf("%sdeleted file ", c_meta);
-				printf("mode ");
-				for (i = 0; i < num_parent; i++) {
-					printf("%s%06o", i ? "," : "",
-					       elem->parent[i].mode);
-				}
-				if (elem->mode)
-					printf("..%06o", elem->mode);
-			}
-			printf("%s\n", c_reset);
-		}
-		if (added)
-			dump_quoted_path("--- ", "", "/dev/null",
-					 c_meta, c_reset);
-		else
-			dump_quoted_path("--- ", a_prefix, elem->path,
-					 c_meta, c_reset);
-		if (deleted)
-			dump_quoted_path("+++ ", "", "/dev/null",
-					 c_meta, c_reset);
-		else
-			dump_quoted_path("+++ ", b_prefix, elem->path,
-					 c_meta, c_reset);
+		show_combined_header(elem, num_parent, dense, rev,
+				     mode_differs, 1);
 		dump_sline(sline, cnt, num_parent,
-			   DIFF_OPT_TST(opt, COLOR_DIFF));
+			   opt->use_color, result_deleted);
 	}
 	free(result);
 
@@ -951,6 +1028,12 @@ static void show_raw_diff(struct combine_diff_path *p, int num_parent, struct re
 	write_name_quoted(p->path, stdout, line_termination);
 }
 
+/*
+ * The result (p->elem) is from the working tree and their
+ * parents are typically from multiple stages during a merge
+ * (i.e. diff-files) or the state in HEAD and in the index
+ * (i.e. diff-index).
+ */
 void show_combined_diff(struct combine_diff_path *p,
 		       int num_parent,
 		       int dense,
@@ -964,19 +1047,84 @@ void show_combined_diff(struct combine_diff_path *p,
 				  DIFF_FORMAT_NAME_STATUS))
 		show_raw_diff(p, num_parent, rev);
 	else if (opt->output_format & DIFF_FORMAT_PATCH)
-		show_patch_diff(p, num_parent, dense, rev);
+		show_patch_diff(p, num_parent, dense, 1, rev);
+}
+
+static void free_combined_pair(struct diff_filepair *pair)
+{
+	free(pair->two);
+	free(pair);
+}
+
+/*
+ * A combine_diff_path expresses N parents on the LHS against 1 merge
+ * result. Synthesize a diff_filepair that has N entries on the "one"
+ * side and 1 entry on the "two" side.
+ *
+ * In the future, we might want to add more data to combine_diff_path
+ * so that we can fill fields we are ignoring (most notably, size) here,
+ * but currently nobody uses it, so this should suffice for now.
+ */
+static struct diff_filepair *combined_pair(struct combine_diff_path *p,
+					   int num_parent)
+{
+	int i;
+	struct diff_filepair *pair;
+	struct diff_filespec *pool;
+
+	pair = xmalloc(sizeof(*pair));
+	pool = xcalloc(num_parent + 1, sizeof(struct diff_filespec));
+	pair->one = pool + 1;
+	pair->two = pool;
+
+	for (i = 0; i < num_parent; i++) {
+		pair->one[i].path = p->path;
+		pair->one[i].mode = p->parent[i].mode;
+		hashcpy(pair->one[i].sha1, p->parent[i].sha1);
+		pair->one[i].sha1_valid = !is_null_sha1(p->parent[i].sha1);
+		pair->one[i].has_more_entries = 1;
+	}
+	pair->one[num_parent - 1].has_more_entries = 0;
+
+	pair->two->path = p->path;
+	pair->two->mode = p->mode;
+	hashcpy(pair->two->sha1, p->sha1);
+	pair->two->sha1_valid = !is_null_sha1(p->sha1);
+	return pair;
+}
+
+static void handle_combined_callback(struct diff_options *opt,
+				     struct combine_diff_path *paths,
+				     int num_parent,
+				     int num_paths)
+{
+	struct combine_diff_path *p;
+	struct diff_queue_struct q;
+	int i;
+
+	q.queue = xcalloc(num_paths, sizeof(struct diff_filepair *));
+	q.alloc = num_paths;
+	q.nr = num_paths;
+	for (i = 0, p = paths; p; p = p->next) {
+		if (!p->len)
+			continue;
+		q.queue[i++] = combined_pair(p, num_parent);
+	}
+	opt->format_callback(&q, opt, opt->format_callback_data);
+	for (i = 0; i < num_paths; i++)
+		free_combined_pair(q.queue[i]);
+	free(q.queue);
 }
 
 void diff_tree_combined(const unsigned char *sha1,
-			const unsigned char parent[][20],
-			int num_parent,
+			const struct sha1_array *parents,
 			int dense,
 			struct rev_info *rev)
 {
 	struct diff_options *opt = &rev->diffopt;
 	struct diff_options diffopts;
 	struct combine_diff_path *p, *paths = NULL;
-	int i, num_paths, needsep, show_log_first;
+	int i, num_paths, needsep, show_log_first, num_parent = parents->nr;
 
 	diffopts = *opt;
 	diffopts.output_format = DIFF_FORMAT_NO_OUTPUT;
@@ -996,7 +1144,7 @@ void diff_tree_combined(const unsigned char *sha1,
 			diffopts.output_format = stat_opt;
 		else
 			diffopts.output_format = DIFF_FORMAT_NO_OUTPUT;
-		diff_tree_sha1(parent[i], sha1, "", &diffopts);
+		diff_tree_sha1(parents->sha1[i], sha1, "", &diffopts);
 		diffcore_std(&diffopts);
 		paths = intersect_paths(paths, i, num_parent);
 
@@ -1026,13 +1174,16 @@ void diff_tree_combined(const unsigned char *sha1,
 		else if (opt->output_format &
 			 (DIFF_FORMAT_NUMSTAT|DIFF_FORMAT_DIFFSTAT))
 			needsep = 1;
+		else if (opt->output_format & DIFF_FORMAT_CALLBACK)
+			handle_combined_callback(opt, paths, num_parent, num_paths);
+
 		if (opt->output_format & DIFF_FORMAT_PATCH) {
 			if (needsep)
 				putchar(opt->line_termination);
 			for (p = paths; p; p = p->next) {
 				if (p->len)
 					show_patch_diff(p, num_parent, dense,
-							rev);
+							0, rev);
 			}
 		}
 	}
@@ -1045,25 +1196,16 @@ void diff_tree_combined(const unsigned char *sha1,
 	}
 }
 
-void diff_tree_combined_merge(const unsigned char *sha1,
-			     int dense, struct rev_info *rev)
+void diff_tree_combined_merge(const struct commit *commit, int dense,
+			      struct rev_info *rev)
 {
-	int num_parent;
-	const unsigned char (*parent)[20];
-	struct commit *commit = lookup_commit(sha1);
-	struct commit_list *parents;
-
-	/* count parents */
-	for (parents = commit->parents, num_parent = 0;
-	     parents;
-	     parents = parents->next, num_parent++)
-		; /* nothing */
-
-	parent = xmalloc(num_parent * sizeof(*parent));
-	for (parents = commit->parents, num_parent = 0;
-	     parents;
-	     parents = parents->next, num_parent++)
-		hashcpy((unsigned char *)(parent + num_parent),
-			parents->item->object.sha1);
-	diff_tree_combined(sha1, parent, num_parent, dense, rev);
+	struct commit_list *parent = commit->parents;
+	struct sha1_array parents = SHA1_ARRAY_INIT;
+
+	while (parent) {
+		sha1_array_append(&parents, parent->item->object.sha1);
+		parent = parent->next;
+	}
+	diff_tree_combined(commit->object.sha1, &parents, dense, rev);
+	sha1_array_clear(&parents);
 }