1 files changed, 274 insertions, 110 deletions

diff --git a/combine-diff.c b/combine-diff.c
index 6288485965..24ca7e2334 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -10,15 +10,15 @@
 #include "refs.h"
 #include "userdiff.h"
 #include "sha1-array.h"
+#include "revision.h"
 
 static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr, int n, int num_parent)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
-	struct combine_diff_path *p;
-	int i;
+	struct combine_diff_path *p, **tail = &curr;
+	int i, cmp;
 
 	if (!n) {
-		struct combine_diff_path *list = NULL, **tail = &list;
 		for (i = 0; i < q->nr; i++) {
 			int len;
 			const char *path;
@@ -30,7 +30,6 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr,
 			p->path = (char *) &(p->parent[num_parent]);
 			memcpy(p->path, path, len);
 			p->path[len] = 0;
-			p->len = len;
 			p->next = NULL;
 			memset(p->parent, 0,
 			       sizeof(p->parent[0]) * num_parent);
@@ -43,47 +42,61 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr,
 			*tail = p;
 			tail = &p->next;
 		}
-		return list;
+		return curr;
 	}
 
-	for (p = curr; p; p = p->next) {
-		int found = 0;
-		if (!p->len)
+	/*
+	 * paths in curr (linked list) and q->queue[] (array) are
+	 * both sorted in the tree order.
+	 */
+	i = 0;
+	while ((p = *tail) != NULL) {
+		cmp = ((i >= q->nr)
+		       ? -1 : strcmp(p->path, q->queue[i]->two->path));
+
+		if (cmp < 0) {
+			/* p->path not in q->queue[]; drop it */
+			*tail = p->next;
+			free(p);
 			continue;
-		for (i = 0; i < q->nr; i++) {
-			const char *path;
-			int len;
+		}
 
-			if (diff_unmodified_pair(q->queue[i]))
-				continue;
-			path = q->queue[i]->two->path;
-			len = strlen(path);
-			if (len == p->len && !memcmp(path, p->path, len)) {
-				found = 1;
-				hashcpy(p->parent[n].sha1, q->queue[i]->one->sha1);
-				p->parent[n].mode = q->queue[i]->one->mode;
-				p->parent[n].status = q->queue[i]->status;
-				break;
-			}
+		if (cmp > 0) {
+			/* q->queue[i] not in p->path; skip it */
+			i++;
+			continue;
 		}
-		if (!found)
-			p->len = 0;
+
+		hashcpy(p->parent[n].sha1, q->queue[i]->one->sha1);
+		p->parent[n].mode = q->queue[i]->one->mode;
+		p->parent[n].status = q->queue[i]->status;
+
+		tail = &p->next;
+		i++;
 	}
 	return curr;
 }
 
 /* Lines lost from parent */
 struct lline {
-	struct lline *next;
+	struct lline *next, *prev;
 	int len;
 	unsigned long parent_map;
 	char line[FLEX_ARRAY];
 };
 
+/* Lines lost from current parent (before coalescing) */
+struct plost {
+	struct lline *lost_head, *lost_tail;
+	int len;
+};
+
 /* Lines surviving in the merge result */
 struct sline {
-	struct lline *lost_head, **lost_tail;
-	struct lline *next_lost;
+	/* Accumulated and coalesced lost lines */
+	struct lline *lost;
+	int lenlost;
+	struct plost plost;
 	char *bol;
 	int len;
 	/* bit 0 up to (N-1) are on if the parent has this line (i.e.
@@ -95,34 +108,6 @@ struct sline {
 	unsigned long *p_lno;
 };
 
-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;
-
-	if (S_ISGITLINK(mode)) {
-		blob = xmalloc(100);
-		*size = snprintf(blob, 100,
-				 "Subproject commit %s\n", sha1_to_hex(sha1));
-	} else if (is_null_sha1(sha1)) {
-		/* 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)
-			die("object '%s' is not a blob!", sha1_to_hex(sha1));
-	}
-	return blob;
-}
-
 static int match_string_spaces(const char *line1, int len1,
 			       const char *line2, int len2,
 			       long flags)
@@ -163,36 +148,180 @@ static int match_string_spaces(const char *line1, int len1,
 	return 0;
 }
 
-static void append_lost(struct sline *sline, int n, const char *line, int len, long flags)
+enum coalesce_direction { MATCH, BASE, NEW };
+
+/* Coalesce new lines into base by finding LCS */
+static struct lline *coalesce_lines(struct lline *base, int *lenbase,
+				    struct lline *new, int lennew,
+				    unsigned long parent, long flags)
 {
-	struct lline *lline;
-	unsigned long this_mask = (1UL<<n);
-	if (line[len-1] == '\n')
-		len--;
+	int **lcs;
+	enum coalesce_direction **directions;
+	struct lline *baseend, *newend = NULL;
+	int i, j, origbaselen = *lenbase;
 
-	/* Check to see if we can squash things */
-	if (sline->lost_head) {
-		lline = sline->next_lost;
-		while (lline) {
-			if (match_string_spaces(lline->line, lline->len,
-						line, len, flags)) {
-				lline->parent_map |= this_mask;
-				sline->next_lost = lline->next;
-				return;
+	if (new == NULL)
+		return base;
+
+	if (base == NULL) {
+		*lenbase = lennew;
+		return new;
+	}
+
+	/*
+	 * Coalesce new lines into base by finding the LCS
+	 * - Create the table to run dynamic programming
+	 * - Compute the LCS
+	 * - Then reverse read the direction structure:
+	 *   - If we have MATCH, assign parent to base flag, and consume
+	 *   both baseend and newend
+	 *   - Else if we have BASE, consume baseend
+	 *   - Else if we have NEW, insert newend lline into base and
+	 *   consume newend
+	 */
+	lcs = xcalloc(origbaselen + 1, sizeof(int*));
+	directions = xcalloc(origbaselen + 1, sizeof(enum coalesce_direction*));
+	for (i = 0; i < origbaselen + 1; i++) {
+		lcs[i] = xcalloc(lennew + 1, sizeof(int));
+		directions[i] = xcalloc(lennew + 1, sizeof(enum coalesce_direction));
+		directions[i][0] = BASE;
+	}
+	for (j = 1; j < lennew + 1; j++)
+		directions[0][j] = NEW;
+
+	for (i = 1, baseend = base; i < origbaselen + 1; i++) {
+		for (j = 1, newend = new; j < lennew + 1; j++) {
+			if (match_string_spaces(baseend->line, baseend->len,
+						newend->line, newend->len, flags)) {
+				lcs[i][j] = lcs[i - 1][j - 1] + 1;
+				directions[i][j] = MATCH;
+			} else if (lcs[i][j - 1] >= lcs[i - 1][j]) {
+				lcs[i][j] = lcs[i][j - 1];
+				directions[i][j] = NEW;
+			} else {
+				lcs[i][j] = lcs[i - 1][j];
+				directions[i][j] = BASE;
 			}
-			lline = lline->next;
+			if (newend->next)
+				newend = newend->next;
 		}
+		if (baseend->next)
+			baseend = baseend->next;
 	}
 
+	for (i = 0; i < origbaselen + 1; i++)
+		free(lcs[i]);
+	free(lcs);
+
+	/* At this point, baseend and newend point to the end of each lists */
+	i--;
+	j--;
+	while (i != 0 || j != 0) {
+		if (directions[i][j] == MATCH) {
+			baseend->parent_map |= 1<<parent;
+			baseend = baseend->prev;
+			newend = newend->prev;
+			i--;
+			j--;
+		} else if (directions[i][j] == NEW) {
+			struct lline *lline;
+
+			lline = newend;
+			/* Remove lline from new list and update newend */
+			if (lline->prev)
+				lline->prev->next = lline->next;
+			else
+				new = lline->next;
+			if (lline->next)
+				lline->next->prev = lline->prev;
+
+			newend = lline->prev;
+			j--;
+
+			/* Add lline to base list */
+			if (baseend) {
+				lline->next = baseend->next;
+				lline->prev = baseend;
+				if (lline->prev)
+					lline->prev->next = lline;
+			}
+			else {
+				lline->next = base;
+				base = lline;
+			}
+			(*lenbase)++;
+
+			if (lline->next)
+				lline->next->prev = lline;
+
+		} else {
+			baseend = baseend->prev;
+			i--;
+		}
+	}
+
+	newend = new;
+	while (newend) {
+		struct lline *lline = newend;
+		newend = newend->next;
+		free(lline);
+	}
+
+	for (i = 0; i < origbaselen + 1; i++)
+		free(directions[i]);
+	free(directions);
+
+	return base;
+}
+
+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;
+
+	if (S_ISGITLINK(mode)) {
+		blob = xmalloc(100);
+		*size = snprintf(blob, 100,
+				 "Subproject commit %s\n", sha1_to_hex(sha1));
+	} else if (is_null_sha1(sha1)) {
+		/* 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)
+			die("object '%s' is not a blob!", sha1_to_hex(sha1));
+	}
+	return blob;
+}
+
+static void append_lost(struct sline *sline, int n, const char *line, int len)
+{
+	struct lline *lline;
+	unsigned long this_mask = (1UL<<n);
+	if (line[len-1] == '\n')
+		len--;
+
 	lline = xmalloc(sizeof(*lline) + len + 1);
 	lline->len = len;
 	lline->next = NULL;
+	lline->prev = sline->plost.lost_tail;
+	if (lline->prev)
+		lline->prev->next = lline;
+	else
+		sline->plost.lost_head = lline;
+	sline->plost.lost_tail = lline;
+	sline->plost.len++;
 	lline->parent_map = this_mask;
 	memcpy(lline->line, line, len);
 	lline->line[len] = 0;
-	*sline->lost_tail = lline;
-	sline->lost_tail = &lline->next;
-	sline->next_lost = NULL;
 }
 
 struct combine_diff_state {
@@ -203,7 +332,6 @@ struct combine_diff_state {
 	int n;
 	struct sline *sline;
 	struct sline *lost_bucket;
-	long flags;
 };
 
 static void consume_line(void *state_, char *line, unsigned long len)
@@ -236,14 +364,13 @@ static void consume_line(void *state_, char *line, unsigned long len)
 				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)
 		return; /* not in any hunk yet */
 	switch (line[0]) {
 	case '-':
-		append_lost(state->lost_bucket, state->n, line+1, len-1, state->flags);
+		append_lost(state->lost_bucket, state->n, line+1, len-1);
 		break;
 	case '+':
 		state->sline[state->lno-1].flag |= state->nmask;
@@ -276,7 +403,6 @@ static void combine_diff(const unsigned char *parent, unsigned int mode,
 	xpp.flags = flags;
 	memset(&xecfg, 0, sizeof(xecfg));
 	memset(&state, 0, sizeof(state));
-	state.flags = flags;
 	state.nmask = nmask;
 	state.sline = sline;
 	state.lno = 1;
@@ -298,8 +424,18 @@ static void combine_diff(const unsigned char *parent, unsigned int mode,
 		struct lline *ll;
 		sline[lno].p_lno[n] = p_lno;
 
+		/* Coalesce new lines */
+		if (sline[lno].plost.lost_head) {
+			struct sline *sl = &sline[lno];
+			sl->lost = coalesce_lines(sl->lost, &sl->lenlost,
+						  sl->plost.lost_head,
+						  sl->plost.len, n, flags);
+			sl->plost.lost_head = sl->plost.lost_tail = NULL;
+			sl->plost.len = 0;
+		}
+
 		/* How many lines would this sline advance the p_lno? */
-		ll = sline[lno].lost_head;
+		ll = sline[lno].lost;
 		while (ll) {
 			if (ll->parent_map & nmask)
 				p_lno++; /* '-' means parent had it */
@@ -319,7 +455,7 @@ static int interesting(struct sline *sline, unsigned long all_mask)
 	/* If some parents lost lines here, or if we have added to
 	 * some parent, it is interesting.
 	 */
-	return ((sline->flag & all_mask) || sline->lost_head);
+	return ((sline->flag & all_mask) || sline->lost);
 }
 
 static unsigned long adjust_hunk_tail(struct sline *sline,
@@ -387,8 +523,11 @@ static int give_context(struct sline *sline, unsigned long cnt, int num_parent)
 		unsigned long k;
 
 		/* Paint a few lines before the first interesting line. */
-		while (j < i)
-			sline[j++].flag |= mark | no_pre_delete;
+		while (j < i) {
+			if (!(sline[j].flag & mark))
+				sline[j].flag |= no_pre_delete;
+			sline[j++].flag |= mark;
+		}
 
 	again:
 		/* we know up to i is to be included.  where does the
@@ -502,7 +641,7 @@ static int make_hunks(struct sline *sline, unsigned long cnt,
 		has_interesting = 0;
 		for (j = i; j < hunk_end && !has_interesting; j++) {
 			unsigned long this_diff = sline[j].flag & all_mask;
-			struct lline *ll = sline[j].lost_head;
+			struct lline *ll = sline[j].lost;
 			if (this_diff) {
 				/* This has some changes.  Is it the
 				 * same as others?
@@ -656,7 +795,7 @@ static void dump_sline(struct sline *sline, const char *line_prefix,
 			int j;
 			unsigned long p_mask;
 			struct sline *sl = &sline[lno++];
-			ll = (sl->flag & no_pre_delete) ? NULL : sl->lost_head;
+			ll = (sl->flag & no_pre_delete) ? NULL : sl->lost;
 			while (ll) {
 				printf("%s%s", line_prefix, c_old);
 				for (j = 0; j < num_parent; j++) {
@@ -707,7 +846,7 @@ static void reuse_combine_diff(struct sline *sline, unsigned long cnt,
 	jmask = (1UL<<j);
 
 	for (lno = 0; lno <= cnt; lno++) {
-		struct lline *ll = sline->lost_head;
+		struct lline *ll = sline->lost;
 		sline->p_lno[i] = sline->p_lno[j];
 		while (ll) {
 			if (ll->parent_map & jmask)
@@ -966,10 +1105,6 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 
 	sline = xcalloc(cnt+2, sizeof(*sline));
 	sline[0].bol = result;
-	for (lno = 0; lno <= cnt + 1; lno++) {
-		sline[lno].lost_tail = &sline[lno].lost_head;
-		sline[lno].flag = 0;
-	}
 	for (lno = 0, cp = result; cp < result + result_size; cp++) {
 		if (*cp == '\n') {
 			sline[lno].len = cp - sline[lno].bol;
@@ -1019,8 +1154,8 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 	free(result);
 
 	for (lno = 0; lno < cnt; lno++) {
-		if (sline[lno].lost_head) {
-			struct lline *ll = sline[lno].lost_head;
+		if (sline[lno].lost) {
+			struct lline *ll = sline[lno].lost;
 			while (ll) {
 				struct lline *tmp = ll;
 				ll = ll->next;
@@ -1088,8 +1223,6 @@ void show_combined_diff(struct combine_diff_path *p,
 {
 	struct diff_options *opt = &rev->diffopt;
 
-	if (!p->len)
-		return;
 	if (opt->output_format & (DIFF_FORMAT_RAW |
 				  DIFF_FORMAT_NAME |
 				  DIFF_FORMAT_NAME_STATUS))
@@ -1153,17 +1286,21 @@ static void handle_combined_callback(struct diff_options *opt,
 	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;
+	for (i = 0, p = paths; p; p = p->next)
 		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);
 }
 
+static const char *path_path(void *obj)
+{
+	struct combine_diff_path *path = (struct combine_diff_path *)obj;
+
+	return path->path;
+}
+
 void diff_tree_combined(const unsigned char *sha1,
 			const struct sha1_array *parents,
 			int dense,
@@ -1175,9 +1312,12 @@ void diff_tree_combined(const unsigned char *sha1,
 	int i, num_paths, needsep, show_log_first, num_parent = parents->nr;
 
 	diffopts = *opt;
+	copy_pathspec(&diffopts.pathspec, &opt->pathspec);
 	diffopts.output_format = DIFF_FORMAT_NO_OUTPUT;
 	DIFF_OPT_SET(&diffopts, RECURSIVE);
 	DIFF_OPT_CLR(&diffopts, ALLOW_EXTERNAL);
+	/* tell diff_tree to emit paths in sorted (=tree) order */
+	diffopts.orderfile = NULL;
 
 	show_log_first = !!rev->loginfo && !rev->no_commit_id;
 	needsep = 0;
@@ -1203,22 +1343,46 @@ void diff_tree_combined(const unsigned char *sha1,
 				printf("%s%c", diff_line_prefix(opt),
 				       opt->line_termination);
 		}
+
+		/* if showing diff, show it in requested order */
+		if (diffopts.output_format != DIFF_FORMAT_NO_OUTPUT &&
+		    opt->orderfile) {
+			diffcore_order(opt->orderfile);
+		}
+
 		diff_flush(&diffopts);
 	}
 
-	/* find out surviving paths */
-	for (num_paths = 0, p = paths; p; p = p->next) {
-		if (p->len)
-			num_paths++;
+	/* find out number of surviving paths */
+	for (num_paths = 0, p = paths; p; p = p->next)
+		num_paths++;
+
+	/* order paths according to diffcore_order */
+	if (opt->orderfile && num_paths) {
+		struct obj_order *o;
+
+		o = xmalloc(sizeof(*o) * num_paths);
+		for (i = 0, p = paths; p; p = p->next, i++)
+			o[i].obj = p;
+		order_objects(opt->orderfile, path_path, o, num_paths);
+		for (i = 0; i < num_paths - 1; i++) {
+			p = o[i].obj;
+			p->next = o[i+1].obj;
+		}
+
+		p = o[num_paths-1].obj;
+		p->next = NULL;
+		paths = o[0].obj;
+		free(o);
 	}
+
+
 	if (num_paths) {
 		if (opt->output_format & (DIFF_FORMAT_RAW |
 					  DIFF_FORMAT_NAME |
 					  DIFF_FORMAT_NAME_STATUS)) {
-			for (p = paths; p; p = p->next) {
-				if (p->len)
-					show_raw_diff(p, num_parent, rev);
-			}
+			for (p = paths; p; p = p->next)
+				show_raw_diff(p, num_parent, rev);
 			needsep = 1;
 		}
 		else if (opt->output_format &
@@ -1231,11 +1395,9 @@ void diff_tree_combined(const unsigned char *sha1,
 			if (needsep)
 				printf("%s%c", diff_line_prefix(opt),
 				       opt->line_termination);
-			for (p = paths; p; p = p->next) {
-				if (p->len)
-					show_patch_diff(p, num_parent, dense,
-							0, rev);
-			}
+			for (p = paths; p; p = p->next)
+				show_patch_diff(p, num_parent, dense,
+						0, rev);
 		}
 	}
 
@@ -1245,12 +1407,14 @@ void diff_tree_combined(const unsigned char *sha1,
 		paths = paths->next;
 		free(tmp);
 	}
+
+	free_pathspec(&diffopts.pathspec);
 }
 
 void diff_tree_combined_merge(const struct commit *commit, int dense,
 			      struct rev_info *rev)
 {
-	struct commit_list *parent = commit->parents;
+	struct commit_list *parent = get_saved_parents(rev, commit);
 	struct sha1_array parents = SHA1_ARRAY_INIT;
 
 	while (parent) {