1 files changed, 677 insertions, 213 deletions

diff --git a/combine-diff.c b/combine-diff.c
index 0682acd50d..3b92c44880 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -5,7 +5,12 @@
 #include "diffcore.h"
 #include "quote.h"
 #include "xdiff-interface.h"
+#include "xdiff/xmacros.h"
 #include "log-tree.h"
+#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)
 {
@@ -23,7 +28,7 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr,
 			path = q->queue[i]->two->path;
 			len = strlen(path);
 			p = xmalloc(combine_diff_path_size(num_parent, len));
-			p->path = (char*) &(p->parent[num_parent]);
+			p->path = (char *) &(p->parent[num_parent]);
 			memcpy(p->path, path, len);
 			p->path[len] = 0;
 			p->len = len;
@@ -31,9 +36,9 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr,
 			memset(p->parent, 0,
 			       sizeof(p->parent[0]) * num_parent);
 
-			memcpy(p->sha1, q->queue[i]->two->sha1, 20);
+			hashcpy(p->sha1, q->queue[i]->two->sha1);
 			p->mode = q->queue[i]->two->mode;
-			memcpy(p->parent[n].sha1, q->queue[i]->one->sha1, 20);
+			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;
@@ -56,8 +61,7 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr,
 			len = strlen(path);
 			if (len == p->len && !memcmp(path, p->path, len)) {
 				found = 1;
-				memcpy(p->parent[n].sha1,
-				       q->queue[i]->one->sha1, 20);
+				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;
@@ -71,37 +75,226 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *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;
+	/* 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.
 	 * we did not change it).
 	 * bit N is used for "interesting" lines, including context.
+	 * bit (N+1) is used for "do not show deletion before this".
 	 */
 	unsigned long flag;
 	unsigned long *p_lno;
 };
 
-static char *grab_blob(const unsigned char *sha1, unsigned long *size)
+static int match_string_spaces(const char *line1, int len1,
+			       const char *line2, int len2,
+			       long flags)
+{
+	if (flags & XDF_WHITESPACE_FLAGS) {
+		for (; len1 > 0 && XDL_ISSPACE(line1[len1 - 1]); len1--);
+		for (; len2 > 0 && XDL_ISSPACE(line2[len2 - 1]); len2--);
+	}
+
+	if (!(flags & (XDF_IGNORE_WHITESPACE | XDF_IGNORE_WHITESPACE_CHANGE)))
+		return (len1 == len2 && !memcmp(line1, line2, len1));
+
+	while (len1 > 0 && len2 > 0) {
+		len1--;
+		len2--;
+		if (XDL_ISSPACE(line1[len1]) || XDL_ISSPACE(line2[len2])) {
+			if ((flags & XDF_IGNORE_WHITESPACE_CHANGE) &&
+			    (!XDL_ISSPACE(line1[len1]) || !XDL_ISSPACE(line2[len2])))
+				return 0;
+
+			for (; len1 > 0 && XDL_ISSPACE(line1[len1]); len1--);
+			for (; len2 > 0 && XDL_ISSPACE(line2[len2]); len2--);
+		}
+		if (line1[len1] != line2[len2])
+			return 0;
+	}
+
+	if (flags & XDF_IGNORE_WHITESPACE) {
+		/* Consume remaining spaces */
+		for (; len1 > 0 && XDL_ISSPACE(line1[len1 - 1]); len1--);
+		for (; len2 > 0 && XDL_ISSPACE(line2[len2 - 1]); len2--);
+	}
+
+	/* We matched full line1 and line2 */
+	if (!len1 && !len2)
+		return 1;
+
+	return 0;
+}
+
+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)
+{
+	int **lcs;
+	enum coalesce_direction **directions;
+	struct lline *baseend, *newend = NULL;
+	int i, j, origbaselen = *lenbase;
+
+	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;
+			}
+			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;
-	char type[20];
-	if (is_null_sha1(sha1)) {
+	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));
 	}
-	blob = read_sha1_file(sha1, type, size);
-	if (strcmp(type, blob_type))
-		die("object '%s' is not a blob!", sha1_to_hex(sha1));
 	return blob;
 }
 
@@ -112,39 +305,22 @@ static void append_lost(struct sline *sline, int n, const char *line, int len)
 	if (line[len-1] == '\n')
 		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;
-		while (lline) {
-			if (lline->len == len &&
-			    !memcmp(lline->line, line, len)) {
-				lline->parent_map |= this_mask;
-				return;
-			}
-			lline = lline->next;
-		}
-	}
-
 	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;
 }
 
 struct combine_diff_state {
-	struct xdiff_emit_state xm;
-
 	unsigned int lno;
 	int ob, on, nb, nn;
 	unsigned long nmask;
@@ -163,20 +339,22 @@ 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,
@@ -197,38 +375,38 @@ static void consume_line(void *state_, char *line, unsigned long len)
 	}
 }
 
-static void combine_diff(const unsigned char *parent, mmfile_t *result_file,
+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, long flags)
 {
 	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, &sz);
+	parent_file.ptr = grab_blob(parent, mode, &sz, textconv, path);
 	parent_file.size = sz;
-	xpp.flags = XDF_NEED_MINIMAL;
-	xecfg.ctxlen = 0;
-	xecfg.flags = 0;
-	ecb.outf = xdiff_outf;
-	ecb.priv = &state;
+	memset(&xpp, 0, sizeof(xpp));
+	xpp.flags = flags;
+	memset(&xecfg, 0, sizeof(xecfg));
 	memset(&state, 0, sizeof(state));
-	state.xm.consume = consume_line;
 	state.nmask = nmask;
 	state.sline = sline;
 	state.lno = 1;
 	state.num_parent = num_parent;
 	state.n = n;
 
-	xdl_diff(&parent_file, result_file, &xpp, &xecfg, &ecb);
+	xdi_diff_outf(&parent_file, result_file, consume_line, &state,
+		      &xpp, &xecfg);
 	free(parent_file.ptr);
 
 	/* Assign line numbers for this parent.
@@ -242,8 +420,18 @@ static void combine_diff(const unsigned char *parent, mmfile_t *result_file,
 		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 */
@@ -263,7 +451,7 @@ 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,
@@ -310,6 +498,7 @@ static int give_context(struct sline *sline, unsigned long cnt, int num_parent)
 {
 	unsigned long all_mask = (1UL<<num_parent) - 1;
 	unsigned long mark = (1UL<<num_parent);
+	unsigned long no_pre_delete = (2UL<<num_parent);
 	unsigned long i;
 
 	/* Two groups of interesting lines may have a short gap of
@@ -330,8 +519,11 @@ 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)
+		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
@@ -409,7 +601,7 @@ 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;
@@ -445,7 +637,7 @@ 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?
@@ -483,34 +675,64 @@ static int make_hunks(struct sline *sline, unsigned long cnt,
 	return has_interesting;
 }
 
-static void show_parent_lno(struct sline *sline, unsigned long l0, unsigned long l1, int n)
+static void show_parent_lno(struct sline *sline, unsigned long l0, unsigned long l1, int n, unsigned long null_context)
 {
 	l0 = sline[l0].p_lno[n];
 	l1 = sline[l1].p_lno[n];
-	printf(" -%lu,%lu", l0, l1-l0);
+	printf(" -%lu,%lu", l0, l1-l0-null_context);
 }
 
-static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent,
-		       int use_color)
+static int hunk_comment_line(const char *bol)
+{
+	int ch;
+
+	if (!bol)
+		return 0;
+	ch = *bol & 0xff;
+	return (isalpha(ch) || ch == '_' || ch == '$');
+}
+
+static void show_line_to_eol(const char *line, int len, const char *reset)
+{
+	int saw_cr_at_eol = 0;
+	if (len < 0)
+		len = strlen(line);
+	saw_cr_at_eol = (len && line[len-1] == '\r');
+
+	printf("%.*s%s%s\n", len - saw_cr_at_eol, line,
+	       reset,
+	       saw_cr_at_eol ? "\r" : "");
+}
+
+static void dump_sline(struct sline *sline, const char *line_prefix,
+		       unsigned long cnt, int num_parent,
+		       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) {
-		struct sline *sl = &sline[lno];
 		unsigned long hunk_end;
 		unsigned long rlines;
-		while (lno <= cnt && !(sline[lno].flag & mark))
+		const char *hunk_comment = NULL;
+		unsigned long null_context = 0;
+
+		while (lno <= cnt && !(sline[lno].flag & mark)) {
+			if (hunk_comment_line(sline[lno].bol))
+				hunk_comment = sline[lno].bol;
 			lno++;
+		}
 		if (cnt < lno)
 			break;
 		else {
@@ -521,35 +743,79 @@ static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent,
 		rlines = hunk_end - lno;
 		if (cnt < hunk_end)
 			rlines--; /* pointing at the last delete hunk */
-		fputs(c_frag, stdout);
+
+		if (!context) {
+			/*
+			 * Even when running with --unified=0, all
+			 * lines in the hunk needs to be processed in
+			 * the loop below in order to show the
+			 * deletion recorded in lost_head.  However,
+			 * we do not want to show the resulting line
+			 * with all blank context markers in such a
+			 * case.  Compensate.
+			 */
+			unsigned long j;
+			for (j = lno; j < hunk_end; j++)
+				if (!(sline[j].flag & (mark-1)))
+					null_context++;
+			rlines -= null_context;
+		}
+
+		printf("%s%s", line_prefix, c_frag);
 		for (i = 0; i <= num_parent; i++) putchar(combine_marker);
 		for (i = 0; i < num_parent; i++)
-			show_parent_lno(sline, lno, hunk_end, i);
+			show_parent_lno(sline, lno, hunk_end, i, null_context);
 		printf(" +%lu,%lu ", lno+1, rlines);
 		for (i = 0; i <= num_parent; i++) putchar(combine_marker);
+
+		if (hunk_comment) {
+			int comment_end = 0;
+			for (i = 0; i < 40; i++) {
+				int ch = hunk_comment[i] & 0xff;
+				if (!ch || ch == '\n')
+					break;
+				if (!isspace(ch))
+				    comment_end = i;
+			}
+			if (comment_end)
+				printf("%s%s %s%s", c_reset,
+						    c_plain, c_reset,
+						    c_func);
+			for (i = 0; i < comment_end; i++)
+				putchar(hunk_comment[i]);
+		}
+
 		printf("%s\n", c_reset);
 		while (lno < hunk_end) {
 			struct lline *ll;
 			int j;
 			unsigned long p_mask;
-			sl = &sline[lno++];
-			ll = sl->lost_head;
+			struct sline *sl = &sline[lno++];
+			ll = (sl->flag & no_pre_delete) ? NULL : sl->lost;
 			while (ll) {
-				fputs(c_old, stdout);
+				printf("%s%s", line_prefix, c_old);
 				for (j = 0; j < num_parent; j++) {
 					if (ll->parent_map & (1UL<<j))
 						putchar('-');
 					else
 						putchar(' ');
 				}
-				printf("%s%s\n", ll->line, c_reset);
+				show_line_to_eol(ll->line, -1, c_reset);
 				ll = ll->next;
 			}
 			if (cnt < lno)
 				break;
 			p_mask = 1;
-			if (!(sl->flag & (mark-1)))
+			fputs(line_prefix, stdout);
+			if (!(sl->flag & (mark-1))) {
+				/*
+				 * This sline was here to hang the
+				 * lost lines in front of it.
+				 */
+				if (!context)
+					continue;
 				fputs(c_plain, stdout);
+			}
 			else
 				fputs(c_new, stdout);
 			for (j = 0; j < num_parent; j++) {
@@ -559,7 +825,7 @@ static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent,
 					putchar(' ');
 				p_mask <<= 1;
 			}
-			printf("%.*s%s\n", sl->len, sl->bol, c_reset);
+			show_line_to_eol(sl->bol, sl->len, c_reset);
 		}
 	}
 }
@@ -576,7 +842,7 @@ 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)
@@ -591,66 +857,241 @@ static void reuse_combine_diff(struct sline *sline, unsigned long cnt,
 	sline->p_lno[i] = sline->p_lno[j];
 }
 
-static void dump_quoted_path(const char *prefix, const char *path,
+static void dump_quoted_path(const char *head,
+			     const char *prefix,
+			     const char *path,
+			     const char *line_prefix,
 			     const char *c_meta, const char *c_reset)
 {
-	printf("%s%s", c_meta, prefix);
-	if (quote_c_style(path, NULL, NULL, 0))
-		quote_c_style(path, NULL, stdout, 0);
+	static struct strbuf buf = STRBUF_INIT;
+
+	strbuf_reset(&buf);
+	strbuf_addstr(&buf, line_prefix);
+	strbuf_addstr(&buf, c_meta);
+	strbuf_addstr(&buf, head);
+	quote_two_c_style(&buf, prefix, path, 0);
+	strbuf_addstr(&buf, c_reset);
+	puts(buf.buf);
+}
+
+static void show_combined_header(struct combine_diff_path *elem,
+				 int num_parent,
+				 int dense,
+				 struct rev_info *rev,
+				 const char *line_prefix,
+				 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, line_prefix, c_meta, c_reset);
+	printf("%s%sindex ", line_prefix, 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("%s%snew file mode %06o",
+			       line_prefix, c_meta, elem->mode);
+		else {
+			if (deleted)
+				printf("%s%sdeleted file ",
+				       line_prefix, 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",
+				 line_prefix, c_meta, c_reset);
+	else
+		dump_quoted_path("--- ", a_prefix, elem->path,
+				 line_prefix, c_meta, c_reset);
+	if (deleted)
+		dump_quoted_path("+++ ", "", "/dev/null",
+				 line_prefix, c_meta, c_reset);
 	else
-		printf("%s", path);
-	printf("%s\n", c_reset);
+		dump_quoted_path("+++ ", b_prefix, elem->path,
+				 line_prefix, 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 = opt->full_index ? 40 : DEFAULT_ABBREV;
 	mmfile_t result_file;
+	struct userdiff_driver *userdiff;
+	struct userdiff_driver *textconv = NULL;
+	int is_binary;
+	const char *line_prefix = diff_line_prefix(opt);
 
 	context = opt->context;
+	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, &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;
-		int fd;
-		if (0 <= (fd = open(elem->path, O_RDONLY)) &&
-		    !fstat(fd, &st)) {
-			int len = st.st_size;
-			int sz = 0;
+		int fd = -1;
+
+		if (lstat(elem->path, &st) < 0)
+			goto deleted_file;
+
+		if (S_ISLNK(st.st_mode)) {
+			struct strbuf buf = STRBUF_INIT;
+
+			if (strbuf_readlink(&buf, elem->path, st.st_size) < 0) {
+				error("readlink(%s): %s", elem->path,
+				      strerror(errno));
+				return;
+			}
+			result_size = buf.len;
+			result = strbuf_detach(&buf, NULL);
+			elem->mode = canon_mode(st.st_mode);
+		} 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, NULL, NULL);
+			else
+				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;
+			int is_file, i;
 
 			elem->mode = canon_mode(st.st_mode);
+			/* if symlinks don't work, assume symlink if all parents
+			 * are symlinks
+			 */
+			is_file = has_symlinks;
+			for (i = 0; !is_file && i < num_parent; i++)
+				is_file = !S_ISLNK(elem->parent[i].mode);
+			if (!is_file)
+				elem->mode = canon_mode(S_IFLNK);
+
 			result_size = len;
 			result = xmalloc(len + 1);
-			while (sz < len) {
-				int done = xread(fd, result+sz, len-sz);
-				if (done == 0)
-					break;
-				if (done < 0)
-					die("read error '%s'", elem->path);
-				sz += done;
-			}
+
+			done = read_in_full(fd, result, len);
+			if (done < 0)
+				die_errno("read error '%s'", elem->path);
+			else if (done < len)
+				die("early EOF '%s'", elem->path);
+
 			result[len] = 0;
+
+			/* If not a fake symlink, apply filters, e.g. autocrlf */
+			if (is_file) {
+				struct strbuf buf = STRBUF_INIT;
+
+				if (convert_to_git(elem->path, result, len, &buf, safe_crlf)) {
+					free(result);
+					result = strbuf_detach(&buf, &len);
+					result_size = len;
+				}
+			}
 		}
 		else {
-			/* deleted file */
+		deleted_file:
+			result_deleted = 1;
 			result_size = 0;
 			elem->mode = 0;
 			result = xcalloc(1, 1);
 		}
+
 		if (0 <= fd)
 			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,
+				     line_prefix, 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++;
@@ -660,10 +1101,6 @@ 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;
@@ -695,64 +1132,26 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 			}
 		}
 		if (i <= j)
-			combine_diff(elem->parent[i].sha1, &result_file, sline,
-				     cnt, i, num_parent);
-		if (elem->parent[i].mode != elem->mode)
-			mode_differs = 1;
+			combine_diff(elem->parent[i].sha1,
+				     elem->parent[i].mode,
+				     &result_file, sline,
+				     cnt, i, num_parent, result_deleted,
+				     textconv, elem->path, opt->xdl_opts);
 	}
 
 	show_hunks = make_hunks(sline, cnt, num_parent, dense);
 
 	if (show_hunks || mode_differs || working_tree_file) {
-		const char *abb;
-		int use_color = 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);
-
-		if (rev->loginfo)
-			show_log(rev, opt->msg_sep);
-		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) {
-			int added = !!elem->mode;
-			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 (!elem->mode)
-					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);
-		}
-		dump_quoted_path("--- a/", elem->path, c_meta, c_reset);
-		dump_quoted_path("+++ b/", elem->path, c_meta, c_reset);
-		dump_sline(sline, cnt, num_parent, opt->color_diff);
+		show_combined_header(elem, num_parent, dense, rev,
+				     line_prefix, mode_differs, 1);
+		dump_sline(sline, line_prefix, cnt, num_parent,
+			   opt->use_color, result_deleted);
 	}
 	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;
@@ -764,35 +1163,32 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 	free(sline);
 }
 
-#define COLONS "::::::::::::::::::::::::::::::::"
-
 static void show_raw_diff(struct combine_diff_path *p, int num_parent, struct rev_info *rev)
 {
 	struct diff_options *opt = &rev->diffopt;
-	int i, offset;
-	const char *prefix;
-	int line_termination, inter_name_termination;
+	int line_termination, inter_name_termination, i;
+	const char *line_prefix = diff_line_prefix(opt);
 
 	line_termination = opt->line_termination;
 	inter_name_termination = '\t';
 	if (!line_termination)
 		inter_name_termination = 0;
 
-	if (rev->loginfo)
-		show_log(rev, opt->msg_sep);
+	if (rev->loginfo && !rev->no_commit_id)
+		show_log(rev);
+
 
 	if (opt->output_format & DIFF_FORMAT_RAW) {
-		offset = strlen(COLONS) - num_parent;
-		if (offset < 0)
-			offset = 0;
-		prefix = COLONS + offset;
+		printf("%s", line_prefix);
+
+		/* As many colons as there are parents */
+		for (i = 0; i < num_parent; i++)
+			putchar(':');
 
 		/* Show the modes */
-		for (i = 0; i < num_parent; i++) {
-			printf("%s%06o", prefix, p->parent[i].mode);
-			prefix = " ";
-		}
-		printf("%s%06o", prefix, p->mode);
+		for (i = 0; i < num_parent; i++)
+			printf("%06o ", p->parent[i].mode);
+		printf("%06o", p->mode);
 
 		/* Show sha1's */
 		for (i = 0; i < num_parent; i++)
@@ -807,24 +1203,22 @@ static void show_raw_diff(struct combine_diff_path *p, int num_parent, struct re
 		putchar(inter_name_termination);
 	}
 
-	if (line_termination) {
-		if (quote_c_style(p->path, NULL, NULL, 0))
-			quote_c_style(p->path, NULL, stdout, 0);
-		else
-			printf("%s", p->path);
-		putchar(line_termination);
-	}
-	else {
-		printf("%s%c", p->path, line_termination);
-	}
+	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,
 		       struct rev_info *rev)
 {
 	struct diff_options *opt = &rev->diffopt;
+
 	if (!p->len)
 		return;
 	if (opt->output_format & (DIFF_FORMAT_RAW |
@@ -832,43 +1226,114 @@ 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;
+	copy_pathspec(&diffopts.pathspec, &opt->pathspec);
 	diffopts.output_format = DIFF_FORMAT_NO_OUTPUT;
-	diffopts.recursive = 1;
+	DIFF_OPT_SET(&diffopts, RECURSIVE);
+	DIFF_OPT_CLR(&diffopts, ALLOW_EXTERNAL);
 
-	show_log_first = !!rev->loginfo;
+	show_log_first = !!rev->loginfo && !rev->no_commit_id;
 	needsep = 0;
 	/* find set of paths that everybody touches */
 	for (i = 0; i < num_parent; i++) {
 		/* show stat against the first parent even
 		 * when doing combined diff.
 		 */
-		if (i == 0 && opt->output_format & DIFF_FORMAT_DIFFSTAT)
-			diffopts.output_format = DIFF_FORMAT_DIFFSTAT;
+		int stat_opt = (opt->output_format &
+				(DIFF_FORMAT_NUMSTAT|DIFF_FORMAT_DIFFSTAT));
+		if (i == 0 && stat_opt)
+			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);
 
 		if (show_log_first && i == 0) {
-			show_log(rev, opt->msg_sep);
+			show_log(rev);
+
 			if (rev->verbose_header && opt->output_format)
-				putchar(opt->line_termination);
+				printf("%s%c", diff_line_prefix(opt),
+				       opt->line_termination);
 		}
 		diff_flush(&diffopts);
 	}
@@ -888,15 +1353,20 @@ void diff_tree_combined(const unsigned char *sha1,
 			}
 			needsep = 1;
 		}
-		else if (opt->output_format & DIFF_FORMAT_DIFFSTAT)
+		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);
+				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,
-							rev);
+							0, rev);
 			}
 		}
 	}
@@ -907,26 +1377,20 @@ void diff_tree_combined(const unsigned char *sha1,
 		paths = paths->next;
 		free(tmp);
 	}
+
+	free_pathspec(&diffopts.pathspec);
 }
 
-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++)
-		memcpy(parent + num_parent, parents->item->object.sha1, 20);
-	diff_tree_combined(sha1, parent, num_parent, dense, rev);
+	struct commit_list *parent = get_saved_parents(rev, commit);
+	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);
 }