X-Git-Url: https://git.verplant.org/?a=blobdiff_plain;f=combine-diff.c;h=250de1c629e14bde19c2f011982d64d8ea16288d;hb=f22fd75c6a39a72d6bf20786ba889fb73038bec9;hp=243f96775aaa058581491544f53f05a3bd038cc0;hpb=ea726d02e9677a66586d7ffebe97f112ab6dab33;p=git.git

diff --git a/combine-diff.c b/combine-diff.c
index 243f9677..250de1c6 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -68,6 +68,7 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr,
 	return curr;
 }
 
+/* Lines lost from parent */
 struct lline {
 	struct lline *next;
 	int len;
@@ -75,11 +76,17 @@ struct lline {
 	char line[FLEX_ARRAY];
 };
 
+/* Lines surviving in the merge result */
 struct sline {
 	struct lline *lost_head, **lost_tail;
 	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.
+	 */
 	unsigned long flag;
+	unsigned long *p_lno;
 };
 
 static char *grab_blob(const unsigned char *sha1, unsigned long *size)
@@ -204,14 +211,14 @@ static void append_lost(struct sline *sline, int n, const char *line)
 }
 
 static void combine_diff(const unsigned char *parent, const char *ourtmp,
-			 struct sline *sline, int cnt, int n)
+			 struct sline *sline, int cnt, int n, int num_parent)
 {
 	FILE *in;
 	char parent_tmp[TMPPATHLEN];
 	char cmd[TMPPATHLEN * 2 + 1024];
 	char line[MAXLINELEN];
-	unsigned int lno, ob, on, nb, nn;
-	unsigned long pmask = ~(1UL << n);
+	unsigned int lno, ob, on, nb, nn, p_lno;
+	unsigned long nmask = (1UL << n);
 	struct sline *lost_bucket = NULL;
 
 	write_temp_blob(parent_tmp, parent);
@@ -219,7 +226,7 @@ static void combine_diff(const unsigned char *parent, const char *ourtmp,
 		parent_tmp, ourtmp);
 	in = popen(cmd, "r");
 	if (!in)
-		return;
+		die("cannot spawn %s", cmd);
 
 	lno = 1;
 	while (fgets(line, sizeof(line), in) != NULL) {
@@ -229,89 +236,75 @@ static void combine_diff(const unsigned char *parent, const char *ourtmp,
 					      &ob, &on, &nb, &nn))
 				break;
 			lno = nb;
-			if (!nb) {
+			if (!nb)
 				/* @@ -1,2 +0,0 @@ to remove the
 				 * first two lines...
 				 */
 				nb = 1;
-			}
-			lost_bucket = &sline[nb-1]; /* sline is 0 based */
+			if (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,
+				 */
+				lost_bucket = &sline[nb];
+			else
+				lost_bucket = &sline[nb-1];
+			if (!sline[nb-1].p_lno)
+				sline[nb-1].p_lno =
+					xcalloc(num_parent,
+						sizeof(unsigned long));
+			sline[nb-1].p_lno[n] = ob;
 			continue;
 		}
 		if (!lost_bucket)
-			continue;
+			continue; /* not in any hunk yet */
 		switch (line[0]) {
 		case '-':
 			append_lost(lost_bucket, n, line+1);
 			break;
 		case '+':
-			sline[lno-1].flag &= pmask;
+			sline[lno-1].flag |= nmask;
 			lno++;
 			break;
 		}
 	}
 	fclose(in);
 	unlink(parent_tmp);
-}
-
-static unsigned long context = 3;
-static char combine_marker = '@';
-
-static int interesting(struct sline *sline, unsigned long all_mask)
-{
-	return ((sline->flag & all_mask) != all_mask || sline->lost_head);
-}
-
-static unsigned long line_common_diff(struct sline *sline, unsigned long all_mask)
-{
-	/*
-	 * Look at the line and see from which parents we have the
-	 * same difference.
-	 */
-
-	/* Lower bits of sline->flag records if the parent had this
-	 * line, so XOR with all_mask gives us on-bits for parents we
-	 * have differences with.
-	 */
-	unsigned long common_adds = (sline->flag ^ all_mask) & all_mask;
-	unsigned long common_removes = all_mask;
 
-	/* If all the parents have this line, that also counts as
-	 * having the same difference.
+	/* Assign line numbers for this parent.
+	 *
+	 * sline[lno].p_lno[n] records the first line number
+	 * (counting from 1) for parent N if the final hunk display
+	 * started by showing sline[lno] (possibly showing the lost
+	 * lines attached to it first).
 	 */
-	if (!common_adds)
-		common_adds = all_mask;
-
-	if (sline->lost_head) {
-		/* Lost head list records the lines removed from
-		 * the parents, and parent_map records from which
-		 * parent the line was removed.
-		 */
+	for (lno = 0,  p_lno = 1; lno < cnt; lno++) {
 		struct lline *ll;
-		for (ll = sline->lost_head; ll; ll = ll->next) {
-			common_removes &= ll->parent_map;
+		sline[lno].p_lno[n] = p_lno;
+
+		/* How many lines would this sline advance the p_lno? */
+		ll = sline[lno].lost_head;
+		while (ll) {
+			if (ll->parent_map & nmask)
+				p_lno++; /* '-' means parent had it */
+			ll = ll->next;
 		}
+		if (!(sline[lno].flag & nmask))
+			p_lno++; /* no '+' means parent had it */
 	}
-	return common_adds & common_removes;
+	sline[lno].p_lno[n] = p_lno; /* trailer */
 }
 
-static unsigned long line_all_diff(struct sline *sline, unsigned long all_mask)
+static unsigned long context = 3;
+static char combine_marker = '@';
+
+static int interesting(struct sline *sline, unsigned long all_mask)
 {
-	/*
-	 * Look at the line and see from which parents we have some difference.
+	/* If some parents lost lines here, or if we have added to
+	 * some parent, it is interesting.
 	 */
-	unsigned long different = (sline->flag ^ all_mask) & all_mask;
-	if (sline->lost_head) {
-		/* Lost head list records the lines removed from
-		 * the parents, and parent_map records from which
-		 * parent the line was removed.
-		 */
-		struct lline *ll;
-		for (ll = sline->lost_head; ll; ll = ll->next) {
-			different |= ll->parent_map;
-		}
-	}
-	return different;
+	return ((sline->flag & all_mask) || sline->lost_head);
 }
 
 static unsigned long adjust_hunk_tail(struct sline *sline,
@@ -319,28 +312,35 @@ static unsigned long adjust_hunk_tail(struct sline *sline,
 				      unsigned long hunk_begin,
 				      unsigned long i)
 {
-	/* i points at the first uninteresting line.
-	 * If the last line of the hunk was interesting
-	 * only because it has some deletion, then
-	 * it is not all that interesting for the
-	 * purpose of giving trailing context lines.
+	/* i points at the first uninteresting line.  If the last line
+	 * of the hunk was interesting only because it has some
+	 * deletion, then it is not all that interesting for the
+	 * purpose of giving trailing context lines.  This is because
+	 * we output '-' line and then unmodified sline[i-1] itself in
+	 * that case which gives us one extra context line.
 	 */
-	if ((hunk_begin + 1 <= i) &&
-	    ((sline[i-1].flag & all_mask) == all_mask))
+	if ((hunk_begin + 1 <= i) && !(sline[i-1].flag & all_mask))
 		i--;
 	return i;
 }
 
-static unsigned long next_interesting(struct sline *sline,
-				      unsigned long mark,
-				      unsigned long i,
-				      unsigned long cnt,
-				      int uninteresting)
+static unsigned long find_next(struct sline *sline,
+			       unsigned long mark,
+			       unsigned long i,
+			       unsigned long cnt,
+			       int uninteresting)
 {
+	/* We have examined up to i-1 and are about to look at i.
+	 * Find next interesting or uninteresting line.  Here,
+	 * "interesting" does not mean interesting(), but marked by
+	 * the give_context() function below (i.e. it includes context
+	 * lines that are not interesting to interesting() function
+	 * that are surrounded by interesting() ones.
+	 */
 	while (i < cnt)
-		if (uninteresting ?
-		    !(sline[i].flag & mark) :
-		    (sline[i].flag & mark))
+		if (uninteresting
+		    ? !(sline[i].flag & mark)
+		    : (sline[i].flag & mark))
 			return i;
 		else
 			i++;
@@ -353,23 +353,37 @@ static int give_context(struct sline *sline, unsigned long cnt, int num_parent)
 	unsigned long mark = (1UL<<num_parent);
 	unsigned long i;
 
-	i = next_interesting(sline, mark, 0, cnt, 0);
+	/* Two groups of interesting lines may have a short gap of
+	 * unintersting lines.  Connect such groups to give them a
+	 * bit of context.
+	 *
+	 * We first start from what the interesting() function says,
+	 * and mark them with "mark", and paint context lines with the
+	 * mark.  So interesting() would still say false for such context
+	 * lines but they are treated as "interesting" in the end.
+	 */
+	i = find_next(sline, mark, 0, cnt, 0);
 	if (cnt <= i)
 		return 0;
 
 	while (i < cnt) {
 		unsigned long j = (context < i) ? (i - context) : 0;
 		unsigned long k;
+
+		/* Paint a few lines before the first interesting line. */
 		while (j < i)
 			sline[j++].flag |= mark;
 
 	again:
-		j = next_interesting(sline, mark, i, cnt, 1);
+		/* we know up to i is to be included.  where does the
+		 * next uninteresting one start?
+		 */
+		j = find_next(sline, mark, i, cnt, 1);
 		if (cnt <= j)
 			break; /* the rest are all interesting */
 
 		/* lookahead context lines */
-		k = next_interesting(sline, mark, j, cnt, 0);
+		k = find_next(sline, mark, j, cnt, 0);
 		j = adjust_hunk_tail(sline, all_mask, i, j);
 
 		if (k < j + context) {
@@ -383,7 +397,8 @@ static int give_context(struct sline *sline, unsigned long cnt, int num_parent)
 		}
 
 		/* j is the first uninteresting line and there is
-		 * no overlap beyond it within context lines.
+		 * no overlap beyond it within context lines.  Paint
+		 * the trailing edge a bit.
 		 */
 		i = k;
 		k = (j + context < cnt) ? j + context : cnt;
@@ -417,8 +432,7 @@ static int make_hunks(struct sline *sline, unsigned long cnt,
 	i = 0;
 	while (i < cnt) {
 		unsigned long j, hunk_begin, hunk_end;
-		int same, diff;
-		unsigned long same_diff, all_diff;
+		unsigned long same_diff;
 		while (i < cnt && !(sline[i].flag & mark))
 			i++;
 		if (cnt <= i)
@@ -449,23 +463,56 @@ static int make_hunks(struct sline *sline, unsigned long cnt,
 		}
 		hunk_end = j;
 
-		/* [i..hunk_end) are interesting.  Now does it have
-		 * the same change with all but one parent?
+		/* [i..hunk_end) are interesting.  Now is it really
+		 * interesting?  We check if there are only two versions
+		 * and the result matches one of them.  That is, we look
+		 * at:
+		 *   (+) line, which records lines added to which parents;
+		 *       this line appears in the result.
+		 *   (-) line, which records from what parents the line
+		 *       was removed; this line does not appear in the result.
+		 * then check the set of parents the result has difference
+		 * from, from all lines.  If there are lines that has
+		 * different set of parents that the result has differences
+		 * from, that means we have more than two versions.
+		 *
+		 * Even when we have only two versions, if the result does
+		 * not match any of the parents, the it should be considered
+		 * interesting.  In such a case, we would have all '+' line.
+		 * After passing the above "two versions" test, that would
+		 * appear as "the same set of parents" to be "all parents".
 		 */
-		same_diff = all_mask;
-		all_diff = 0;
-		for (j = i; j < hunk_end; j++) {
-			same_diff &= line_common_diff(sline + j, all_mask);
-			all_diff |= line_all_diff(sline + j, all_mask);
-		}
-		diff = same = 0;
-		for (j = 0; j < num_parent; j++) {
-			if (same_diff & (1UL<<j))
-				same++;
-			if (all_diff & (1UL<<j))
-				diff++;
+		same_diff = 0;
+		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;
+			if (this_diff) {
+				/* This has some changes.  Is it the
+				 * same as others?
+				 */
+				if (!same_diff)
+					same_diff = this_diff;
+				else if (same_diff != this_diff) {
+					has_interesting = 1;
+					break;
+				}
+			}
+			while (ll && !has_interesting) {
+				/* Lost this line from these parents;
+				 * who are they?  Are they the same?
+				 */
+				this_diff = ll->parent_map;
+				if (!same_diff)
+					same_diff = this_diff;
+				else if (same_diff != this_diff) {
+					has_interesting = 1;
+				}
+				ll = ll->next;
+			}
 		}
-		if ((num_parent - 1 <= same) || (diff == 1)) {
+
+		if (!has_interesting && same_diff != all_mask) {
 			/* This hunk is not that interesting after all */
 			for (j = hunk_begin; j < hunk_end; j++)
 				sline[j].flag &= ~mark;
@@ -477,11 +524,18 @@ static int make_hunks(struct sline *sline, unsigned long cnt,
 	return has_interesting;
 }
 
-static void dump_sline(struct sline *sline, int cnt, int num_parent)
+static void show_parent_lno(struct sline *sline, unsigned long l0, unsigned long l1, unsigned long cnt, int n)
+{
+	l0 = sline[l0].p_lno[n];
+	l1 = sline[l1].p_lno[n];
+	printf(" -%lu,%lu", l0, l1-l0);
+}
+
+static void dump_sline(struct sline *sline, unsigned long cnt, int num_parent)
 {
 	unsigned long mark = (1UL<<num_parent);
 	int i;
-	int lno = 0;
+	unsigned long lno = 0;
 
 	while (1) {
 		struct sline *sl = &sline[lno];
@@ -494,12 +548,15 @@ static void dump_sline(struct sline *sline, int cnt, int num_parent)
 			if (!(sline[hunk_end].flag & mark))
 				break;
 		for (i = 0; i <= num_parent; i++) putchar(combine_marker);
-		printf(" +%d,%d ", lno+1, hunk_end-lno);
+		for (i = 0; i < num_parent; i++)
+			show_parent_lno(sline, lno, hunk_end, cnt, i);
+		printf(" +%lu,%lu ", lno+1, hunk_end-lno);
 		for (i = 0; i <= num_parent; i++) putchar(combine_marker);
 		putchar('\n');
 		while (lno < hunk_end) {
 			struct lline *ll;
 			int j;
+			unsigned long p_mask;
 			sl = &sline[lno++];
 			ll = sl->lost_head;
 			while (ll) {
@@ -512,19 +569,46 @@ static void dump_sline(struct sline *sline, int cnt, int num_parent)
 				puts(ll->line);
 				ll = ll->next;
 			}
+			p_mask = 1;
 			for (j = 0; j < num_parent; j++) {
-				if ((1UL<<j) & sl->flag)
-					putchar(' ');
-				else
+				if (p_mask & sl->flag)
 					putchar('+');
+				else
+					putchar(' ');
+				p_mask <<= 1;
 			}
 			printf("%.*s\n", sl->len, sl->bol);
 		}
 	}
 }
 
+static void reuse_combine_diff(struct sline *sline, unsigned long cnt,
+			       int i, int j)
+{
+	/* We have already examined parent j and we know parent i
+	 * and parent j are the same, so reuse the combined result
+	 * of parent j for parent i.
+	 */
+	unsigned long lno, imask, jmask;
+	imask = (1UL<<i);
+	jmask = (1UL<<j);
+
+	for (lno = 0; lno < cnt; lno++) {
+		struct lline *ll = sline->lost_head;
+		sline->p_lno[i] = sline->p_lno[j];
+		while (ll) {
+			if (ll->parent_map & jmask)
+				ll->parent_map |= imask;
+			ll = ll->next;
+		}
+		if (sline->flag & jmask)
+			sline->flag |= imask;
+		sline++;
+	}
+}
+
 int show_combined_diff(struct combine_diff_path *elem, int num_parent,
-		       int dense, const char *header, int show_empty)
+		       int dense, const char *header)
 {
 	unsigned long size, cnt, lno;
 	char *result, *cp, *ep;
@@ -577,14 +661,14 @@ int show_combined_diff(struct combine_diff_path *elem, int num_parent,
 	if (result[size-1] != '\n')
 		cnt++; /* incomplete line */
 
-	sline = xcalloc(cnt, sizeof(*sline));
+	sline = xcalloc(cnt+1, sizeof(*sline));
 	ep = result;
 	sline[0].bol = result;
 	for (lno = 0, cp = result; cp - result < size; cp++) {
 		if (*cp == '\n') {
 			sline[lno].lost_tail = &sline[lno].lost_head;
 			sline[lno].len = cp - sline[lno].bol;
-			sline[lno].flag = (1UL<<num_parent) - 1;
+			sline[lno].flag = 0;
 			lno++;
 			if (lno < cnt)
 				sline[lno].bol = cp + 1;
@@ -593,25 +677,49 @@ int show_combined_diff(struct combine_diff_path *elem, int num_parent,
 	if (result[size-1] != '\n') {
 		sline[cnt-1].lost_tail = &sline[cnt-1].lost_head;
 		sline[cnt-1].len = size - (sline[cnt-1].bol - result);
-		sline[cnt-1].flag = (1UL<<num_parent) - 1;
+		sline[cnt-1].flag = 0;
 	}
 
-	for (i = 0; i < num_parent; i++)
-		combine_diff(elem->parent_sha1[i], ourtmp, sline, cnt, i);
+	sline[0].p_lno = xcalloc((cnt+1) * num_parent, sizeof(unsigned long));
+	for (lno = 0; lno < cnt; lno++)
+		sline[lno+1].p_lno = sline[lno].p_lno + num_parent;
+
+	for (i = 0; i < num_parent; i++) {
+		int j;
+		for (j = 0; j < i; j++) {
+			if (!memcmp(elem->parent_sha1[i],
+				    elem->parent_sha1[j], 20)) {
+				reuse_combine_diff(sline, cnt, i, j);
+				break;
+			}
+		}
+		if (i <= j)
+			combine_diff(elem->parent_sha1[i], ourtmp, sline,
+				     cnt, i, num_parent);
+	}
 
 	show_hunks = make_hunks(sline, cnt, num_parent, dense);
 
-	if (header && (show_hunks || show_empty)) {
-		shown_header++;
-		puts(header);
-	}
 	if (show_hunks) {
+		if (header) {
+			shown_header++;
+			puts(header);
+		}
 		printf("diff --%s ", dense ? "cc" : "combined");
 		if (quote_c_style(elem->path, NULL, NULL, 0))
 			quote_c_style(elem->path, NULL, stdout, 0);
 		else
 			printf("%s", elem->path);
 		putchar('\n');
+		printf("index ");
+		for (i = 0; i < num_parent; i++) {
+			printf("%s%s",
+			       i ? "," : "",
+			       find_unique_abbrev(elem->parent_sha1[i],
+						  DEFAULT_ABBREV));
+		}
+		printf("..%s\n",
+		       find_unique_abbrev(elem->sha1, DEFAULT_ABBREV));
 		dump_sline(sline, cnt, num_parent);
 	}
 	if (ourtmp == ourtmp_buf)
@@ -628,13 +736,13 @@ int show_combined_diff(struct combine_diff_path *elem, int num_parent,
 			}
 		}
 	}
+	free(sline[0].p_lno);
 	free(sline);
 	return shown_header;
 }
 
 int diff_tree_combined_merge(const unsigned char *sha1,
-			     const char *header,
-			     int show_empty_merge, int dense)
+			     const char *header, int dense)
 {
 	struct commit *commit = lookup_commit(sha1);
 	struct diff_options diffopts;
@@ -668,12 +776,11 @@ int diff_tree_combined_merge(const unsigned char *sha1,
 		if (p->len)
 			num_paths++;
 	}
-	if (num_paths || show_empty_merge) {
+	if (num_paths) {
 		for (p = paths; p; p = p->next) {
 			if (!p->len)
 				continue;
-			if (show_combined_diff(p, num_parent, dense, header,
-					       show_empty_merge))
+			if (show_combined_diff(p, num_parent, dense, header))
 				header = NULL;
 		}
 	}