X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=diff.c;h=306bcd9807803f37dd742ff5c479c4875c454e03;hb=5f93926c3c5c4fe1def39de82076bc69ec89c058;hp=a6cbf44f443bf5dffb29576e1f426a252cc9eba9;hpb=81e50eabf06dd68e8e62a9b697eaf60904c58b22;p=git.git

diff --git a/diff.c b/diff.c
index a6cbf44f..306bcd98 100644
--- a/diff.c
+++ b/diff.c
@@ -4,25 +4,60 @@
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <signal.h>
-#include <limits.h>
 #include "cache.h"
+#include "quote.h"
 #include "diff.h"
 #include "diffcore.h"
 
 static const char *diff_opts = "-pu";
-static unsigned char null_sha1[20] = { 0, };
 
-static int reverse_diff;
-static int generate_patch;
-static int line_termination = '\n';
-static int inter_name_termination = '\t';
-static const char **pathspec;
-static int speccnt;
+static int use_size_cache;
+
+static char *quote_one(const char *str)
+{
+	int needlen;
+	char *xp;
+
+	if (!str)
+		return NULL;
+	needlen = quote_c_style(str, NULL, NULL, 0);
+	if (!needlen)
+		return strdup(str);
+	xp = xmalloc(needlen + 1);
+	quote_c_style(str, xp, NULL, 0);
+	return xp;
+}
+
+static char *quote_two(const char *one, const char *two)
+{
+	int need_one = quote_c_style(one, NULL, NULL, 1);
+	int need_two = quote_c_style(two, NULL, NULL, 1);
+	char *xp;
+
+	if (need_one + need_two) {
+		if (!need_one) need_one = strlen(one);
+		if (!need_two) need_one = strlen(two);
+
+		xp = xmalloc(need_one + need_two + 3);
+		xp[0] = '"';
+		quote_c_style(one, xp + 1, NULL, 1);
+		quote_c_style(two, xp + need_one + 1, NULL, 1);
+		strcpy(xp + need_one + need_two + 1, "\"");
+		return xp;
+	}
+	need_one = strlen(one);
+	need_two = strlen(two);
+	xp = xmalloc(need_one + need_two + 1);
+	strcpy(xp, one);
+	strcpy(xp + need_one, two);
+	return xp;
+}
 
 static const char *external_diff(void)
 {
 	static const char *external_diff_cmd = NULL;
 	static int done_preparing = 0;
+	const char *env_diff_opts;
 
 	if (done_preparing)
 		return external_diff_cmd;
@@ -35,125 +70,176 @@ static const char *external_diff(void)
 	 *
 	 * GIT_DIFF_OPTS="-c";
 	 */
-	if (gitenv("GIT_EXTERNAL_DIFF"))
-		external_diff_cmd = gitenv("GIT_EXTERNAL_DIFF");
+	external_diff_cmd = getenv("GIT_EXTERNAL_DIFF");
 
 	/* In case external diff fails... */
-	diff_opts = gitenv("GIT_DIFF_OPTS") ? : diff_opts;
+	env_diff_opts = getenv("GIT_DIFF_OPTS");
+	if (env_diff_opts) diff_opts = env_diff_opts;
 
 	done_preparing = 1;
 	return external_diff_cmd;
 }
 
-/* Help to copy the thing properly quoted for the shell safety.
- * any single quote is replaced with '\'', and the caller is
- * expected to enclose the result within a single quote pair.
- *
- * E.g.
- *  original     sq_expand     result
- *  name     ==> name      ==> 'name'
- *  a b      ==> a b       ==> 'a b'
- *  a'b      ==> a'\''b    ==> 'a'\''b'
- */
-static char *sq_expand(const char *src)
-{
-	static char *buf = NULL;
-	int cnt, c;
-	const char *cp;
-	char *bp;
-
-	/* count bytes needed to store the quoted string. */
-	for (cnt = 1, cp = src; *cp; cnt++, cp++)
-		if (*cp == '\'')
-			cnt += 3;
-
-	buf = xmalloc(cnt);
-	bp = buf;
-	while ((c = *src++)) {
-		if (c != '\'')
-			*bp++ = c;
-		else {
-			bp = strcpy(bp, "'\\''");
-			bp += 4;
-		}
-	}
-	*bp = 0;
-	return buf;
-}
+#define TEMPFILE_PATH_LEN		50
 
 static struct diff_tempfile {
 	const char *name; /* filename external diff should read from */
 	char hex[41];
 	char mode[10];
-	char tmp_path[50];
+	char tmp_path[TEMPFILE_PATH_LEN];
 } diff_temp[2];
 
+static int count_lines(const char *filename)
+{
+	FILE *in;
+	int count, ch, completely_empty = 1, nl_just_seen = 0;
+	in = fopen(filename, "r");
+	count = 0;
+	while ((ch = fgetc(in)) != EOF)
+		if (ch == '\n') {
+			count++;
+			nl_just_seen = 1;
+			completely_empty = 0;
+		}
+		else {
+			nl_just_seen = 0;
+			completely_empty = 0;
+		}
+	fclose(in);
+	if (completely_empty)
+		return 0;
+	if (!nl_just_seen)
+		count++; /* no trailing newline */
+	return count;
+}
+
+static void print_line_count(int count)
+{
+	switch (count) {
+	case 0:
+		printf("0,0");
+		break;
+	case 1:
+		printf("1");
+		break;
+	default:
+		printf("1,%d", count);
+		break;
+	}
+}
+
+static void copy_file(int prefix, const char *filename)
+{
+	FILE *in;
+	int ch, nl_just_seen = 1;
+	in = fopen(filename, "r");
+	while ((ch = fgetc(in)) != EOF) {
+		if (nl_just_seen)
+			putchar(prefix);
+		putchar(ch);
+		if (ch == '\n')
+			nl_just_seen = 1;
+		else
+			nl_just_seen = 0;
+	}
+	fclose(in);
+	if (!nl_just_seen)
+		printf("\n\\ No newline at end of file\n");
+}
+
+static void emit_rewrite_diff(const char *name_a,
+			      const char *name_b,
+			      struct diff_tempfile *temp)
+{
+	/* Use temp[i].name as input, name_a and name_b as labels */
+	int lc_a, lc_b;
+	lc_a = count_lines(temp[0].name);
+	lc_b = count_lines(temp[1].name);
+	printf("--- %s\n+++ %s\n@@ -", name_a, name_b);
+	print_line_count(lc_a);
+	printf(" +");
+	print_line_count(lc_b);
+	printf(" @@\n");
+	if (lc_a)
+		copy_file('-', temp[0].name);
+	if (lc_b)
+		copy_file('+', temp[1].name);
+}
+
 static void builtin_diff(const char *name_a,
 			 const char *name_b,
 			 struct diff_tempfile *temp,
-			 const char *xfrm_msg)
+			 const char *xfrm_msg,
+			 int complete_rewrite)
 {
 	int i, next_at, cmd_size;
-	const char *diff_cmd = "diff -L'%s%s' -L'%s%s'";
-	const char *diff_arg  = "'%s' '%s'||:"; /* "||:" is to return 0 */
+	const char *const diff_cmd = "diff -L%s -L%s";
+	const char *const diff_arg  = "-- %s %s||:"; /* "||:" is to return 0 */
 	const char *input_name_sq[2];
-	const char *path0[2];
-	const char *path1[2];
-	const char *name_sq[2];
+	const char *label_path[2];
 	char *cmd;
 
-	name_sq[0] = sq_expand(name_a);
-	name_sq[1] = sq_expand(name_b);
-
-	/* diff_cmd and diff_arg have 6 %s in total which makes
-	 * the sum of these strings 12 bytes larger than required.
+	/* diff_cmd and diff_arg have 4 %s in total which makes
+	 * the sum of these strings 8 bytes larger than required.
 	 * we use 2 spaces around diff-opts, and we need to count
-	 * terminating NUL, so we subtract 9 here.
+	 * terminating NUL; we used to subtract 5 here, but we do not
+	 * care about small leaks in this subprocess that is about
+	 * to exec "diff" anymore.
 	 */
-	cmd_size = (strlen(diff_cmd) + strlen(diff_opts) +
-			strlen(diff_arg) - 9);
+	cmd_size = (strlen(diff_cmd) + strlen(diff_opts) + strlen(diff_arg)
+		    + 128);
+
 	for (i = 0; i < 2; i++) {
-		input_name_sq[i] = sq_expand(temp[i].name);
-		if (!strcmp(temp[i].name, "/dev/null")) {
-			path0[i] = "/dev/null";
-			path1[i] = "";
-		} else {
-			path0[i] = i ? "b/" : "a/";
-			path1[i] = name_sq[i];
-		}
-		cmd_size += (strlen(path0[i]) + strlen(path1[i]) +
-			     strlen(input_name_sq[i]));
+		input_name_sq[i] = sq_quote(temp[i].name);
+		if (!strcmp(temp[i].name, "/dev/null"))
+			label_path[i] = "/dev/null";
+		else if (!i)
+			label_path[i] = sq_quote(quote_two("a/", name_a));
+		else
+			label_path[i] = sq_quote(quote_two("b/", name_b));
+		cmd_size += (strlen(label_path[i]) + strlen(input_name_sq[i]));
 	}
 
 	cmd = xmalloc(cmd_size);
 
 	next_at = 0;
 	next_at += snprintf(cmd+next_at, cmd_size-next_at,
-			    diff_cmd,
-			    path0[0], path1[0], path0[1], path1[1]);
+			    diff_cmd, label_path[0], label_path[1]);
 	next_at += snprintf(cmd+next_at, cmd_size-next_at,
 			    " %s ", diff_opts);
 	next_at += snprintf(cmd+next_at, cmd_size-next_at,
 			    diff_arg, input_name_sq[0], input_name_sq[1]);
 
-	printf("diff --git a/%s b/%s\n", name_a, name_b);
-	if (!path1[0][0])
+	printf("diff --git %s %s\n",
+	       quote_two("a/", name_a), quote_two("b/", name_b));
+	if (label_path[0][0] == '/') {
+		/* dev/null */
 		printf("new file mode %s\n", temp[1].mode);
-	else if (!path1[1][0])
+		if (xfrm_msg && xfrm_msg[0])
+			puts(xfrm_msg);
+	}
+	else if (label_path[1][0] == '/') {
 		printf("deleted file mode %s\n", temp[0].mode);
+		if (xfrm_msg && xfrm_msg[0])
+			puts(xfrm_msg);
+	}
 	else {
 		if (strcmp(temp[0].mode, temp[1].mode)) {
 			printf("old mode %s\n", temp[0].mode);
 			printf("new mode %s\n", temp[1].mode);
 		}
 		if (xfrm_msg && xfrm_msg[0])
-			fputs(xfrm_msg, stdout);
-
+			puts(xfrm_msg);
 		if (strncmp(temp[0].mode, temp[1].mode, 3))
 			/* we do not run diff between different kind
 			 * of objects.
 			 */
 			exit(0);
+		if (complete_rewrite) {
+			fflush(NULL);
+			emit_rewrite_diff(name_a, name_b, temp);
+			exit(0);
+		}
 	}
 	fflush(NULL);
 	execlp("/bin/sh","sh", "-c", cmd, NULL);
@@ -163,22 +249,18 @@ struct diff_filespec *alloc_filespec(const char *path)
 {
 	int namelen = strlen(path);
 	struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1);
+
+	memset(spec, 0, sizeof(*spec));
 	spec->path = (char *)(spec + 1);
-	strcpy(spec->path, path);
-	spec->should_free = spec->should_munmap = 0;
-	spec->xfrm_flags = 0;
-	spec->size = 0;
-	spec->data = 0;
-	spec->mode = 0;
-	memset(spec->sha1, 0, 20);
+	memcpy(spec->path, path, namelen+1);
 	return spec;
 }
 
 void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
 		   unsigned short mode)
 {
-	if (mode) { /* just playing defensive */
-		spec->mode = mode;
+	if (mode) {
+		spec->mode = DIFF_FILE_CANON_MODE(mode);
 		memcpy(spec->sha1, sha1, 20);
 		spec->sha1_valid = !!memcmp(sha1, null_sha1, 20);
 	}
@@ -228,12 +310,61 @@ static int work_tree_matches(const char *name, const unsigned char *sha1)
 	return 1;
 }
 
+static struct sha1_size_cache {
+	unsigned char sha1[20];
+	unsigned long size;
+} **sha1_size_cache;
+static int sha1_size_cache_nr, sha1_size_cache_alloc;
+
+static struct sha1_size_cache *locate_size_cache(unsigned char *sha1,
+						 int find_only,
+						 unsigned long size)
+{
+	int first, last;
+	struct sha1_size_cache *e;
+
+	first = 0;
+	last = sha1_size_cache_nr;
+	while (last > first) {
+		int cmp, next = (last + first) >> 1;
+		e = sha1_size_cache[next];
+		cmp = memcmp(e->sha1, sha1, 20);
+		if (!cmp)
+			return e;
+		if (cmp < 0) {
+			last = next;
+			continue;
+		}
+		first = next+1;
+	}
+	/* not found */
+	if (find_only)
+		return NULL;
+	/* insert to make it at "first" */
+	if (sha1_size_cache_alloc <= sha1_size_cache_nr) {
+		sha1_size_cache_alloc = alloc_nr(sha1_size_cache_alloc);
+		sha1_size_cache = xrealloc(sha1_size_cache,
+					   sha1_size_cache_alloc *
+					   sizeof(*sha1_size_cache));
+	}
+	sha1_size_cache_nr++;
+	if (first < sha1_size_cache_nr)
+		memmove(sha1_size_cache + first + 1, sha1_size_cache + first,
+			(sha1_size_cache_nr - first - 1) *
+			sizeof(*sha1_size_cache));
+	e = xmalloc(sizeof(struct sha1_size_cache));
+	sha1_size_cache[first] = e;
+	memcpy(e->sha1, sha1, 20);
+	e->size = size;
+	return e;
+}
+
 /*
  * While doing rename detection and pickaxe operation, we may need to
  * grab the data for the blob (or file) for our own in-core comparison.
  * diff_filespec has data and size fields for this purpose.
  */
-int diff_populate_filespec(struct diff_filespec *s)
+int diff_populate_filespec(struct diff_filespec *s, int size_only)
 {
 	int err = 0;
 	if (!DIFF_FILE_VALID(s))
@@ -241,6 +372,9 @@ int diff_populate_filespec(struct diff_filespec *s)
 	if (S_ISDIR(s->mode))
 		return -1;
 
+	if (!use_size_cache)
+		size_only = 0;
+
 	if (s->data)
 		return err;
 	if (!s->sha1_valid ||
@@ -260,6 +394,8 @@ int diff_populate_filespec(struct diff_filespec *s)
 		s->size = st.st_size;
 		if (!s->size)
 			goto empty;
+		if (size_only)
+			return 0;
 		if (S_ISLNK(st.st_mode)) {
 			int ret;
 			s->data = xmalloc(s->size);
@@ -275,13 +411,28 @@ int diff_populate_filespec(struct diff_filespec *s)
 		if (fd < 0)
 			goto err_empty;
 		s->data = mmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0);
-		s->should_munmap = 1;
 		close(fd);
+		if (s->data == MAP_FAILED)
+			goto err_empty;
+		s->should_munmap = 1;
 	}
 	else {
 		char type[20];
-		s->data = read_sha1_file(s->sha1, type, &s->size);
-		s->should_free = 1;
+		struct sha1_size_cache *e;
+
+		if (size_only) {
+			e = locate_size_cache(s->sha1, 1, 0);
+			if (e) {
+				s->size = e->size;
+				return 0;
+			}
+			if (!sha1_object_info(s->sha1, type, &s->size))
+				locate_size_cache(s->sha1, 0, s->size);
+		}
+		else {
+			s->data = read_sha1_file(s->sha1, type, &s->size);
+			s->should_free = 1;
+		}
 	}
 	return 0;
 }
@@ -293,19 +444,18 @@ void diff_free_filespec_data(struct diff_filespec *s)
 	else if (s->should_munmap)
 		munmap(s->data, s->size);
 	s->should_free = s->should_munmap = 0;
-	s->data = 0;
+	s->data = NULL;
 }
 
 static void prep_temp_blob(struct diff_tempfile *temp,
 			   void *blob,
 			   unsigned long size,
-			   unsigned char *sha1,
+			   const unsigned char *sha1,
 			   int mode)
 {
 	int fd;
 
-	strcpy(temp->tmp_path, ".diff_XXXXXX");
-	fd = mkstemp(temp->tmp_path);
+	fd = git_mkstemp(temp->tmp_path, TEMPFILE_PATH_LEN, ".diff_XXXXXX");
 	if (fd < 0)
 		die("unable to create temp-file");
 	if (write(fd, blob, size) != size)
@@ -361,13 +511,18 @@ static void prepare_temp_file(const char *name,
 				strcpy(temp->hex, sha1_to_hex(null_sha1));
 			else
 				strcpy(temp->hex, sha1_to_hex(one->sha1));
-			sprintf(temp->mode, "%06o",
-				S_IFREG |ce_permissions(st.st_mode));
+			/* Even though we may sometimes borrow the
+			 * contents from the work tree, we always want
+			 * one->mode.  mode is trustworthy even when
+			 * !(one->sha1_valid), as long as
+			 * DIFF_FILE_VALID(one).
+			 */
+			sprintf(temp->mode, "%06o", one->mode);
 		}
 		return;
 	}
 	else {
-		if (diff_populate_filespec(one))
+		if (diff_populate_filespec(one, 0))
 			die("cannot read data blob for %s", one->path);
 		prep_temp_blob(temp, one->data, one->size,
 			       one->sha1, one->mode);
@@ -390,48 +545,30 @@ static void remove_tempfile_on_signal(int signo)
 	remove_tempfile();
 }
 
-static int matches_pathspec(const char *name)
-{
-	int i;
-	int namelen;
-
-	if (speccnt == 0)
-		return 1;
-
-	namelen = strlen(name);
-	for (i = 0; i < speccnt; i++) {
-		int speclen = strlen(pathspec[i]);
-		if (! strncmp(pathspec[i], name, speclen) &&
-		    speclen <= namelen &&
-		    (name[speclen] == 0 || name[speclen] == '/'))
-			return 1;
-	}
-	return 0;
-}
-
 /* An external diff command takes:
  *
  * diff-cmd name infile1 infile1-sha1 infile1-mode \
  *               infile2 infile2-sha1 infile2-mode [ rename-to ]
  *
  */
-static void run_external_diff(const char *name,
+static void run_external_diff(const char *pgm,
+			      const char *name,
 			      const char *other,
 			      struct diff_filespec *one,
 			      struct diff_filespec *two,
-			      const char *xfrm_msg)
+			      const char *xfrm_msg,
+			      int complete_rewrite)
 {
 	struct diff_tempfile *temp = diff_temp;
 	pid_t pid;
 	int status;
 	static int atexit_asked = 0;
+	const char *othername;
 
-	if (!matches_pathspec(name) && (!other || !matches_pathspec(other)))
-		return;
-
+	othername = (other? other : name);
 	if (one && two) {
 		prepare_temp_file(name, &temp[0], one);
-		prepare_temp_file(other ? : name, &temp[1], two);
+		prepare_temp_file(othername, &temp[1], two);
 		if (! atexit_asked &&
 		    (temp[0].name == temp[0].tmp_path ||
 		     temp[1].name == temp[1].tmp_path)) {
@@ -446,7 +583,6 @@ static void run_external_diff(const char *name,
 	if (pid < 0)
 		die("unable to fork");
 	if (!pid) {
-		const char *pgm = external_diff();
 		if (pgm) {
 			if (one && two) {
 				const char *exec_arg[10];
@@ -463,7 +599,7 @@ static void run_external_diff(const char *name,
 					*arg++ = other;
 					*arg++ = xfrm_msg;
 				}
-				*arg = 0;
+				*arg = NULL;
 				execvp(pgm, (char *const*) exec_arg);
 			}
 			else
@@ -473,7 +609,8 @@ static void run_external_diff(const char *name,
 		 * otherwise we use the built-in one.
 		 */
 		if (one && two)
-			builtin_diff(name, other ? : name, temp, xfrm_msg);
+			builtin_diff(name, othername, temp, xfrm_msg,
+				     complete_rewrite);
 		else
 			printf("* Unmerged path %s\n", name);
 		exit(0);
@@ -496,103 +633,373 @@ static void run_external_diff(const char *name,
 	remove_tempfile();
 }
 
-int diff_scoreopt_parse(const char *opt)
+static void diff_fill_sha1_info(struct diff_filespec *one)
+{
+	if (DIFF_FILE_VALID(one)) {
+		if (!one->sha1_valid) {
+			struct stat st;
+			if (stat(one->path, &st) < 0)
+				die("stat %s", one->path);
+			if (index_path(one->sha1, one->path, &st, 0))
+				die("cannot hash %s\n", one->path);
+		}
+	}
+	else
+		memset(one->sha1, 0, 20);
+}
+
+static void run_diff(struct diff_filepair *p)
+{
+	const char *pgm = external_diff();
+	char msg[PATH_MAX*2+300], *xfrm_msg;
+	struct diff_filespec *one;
+	struct diff_filespec *two;
+	const char *name;
+	const char *other;
+	char *name_munged, *other_munged;
+	int complete_rewrite = 0;
+	int len;
+
+	if (DIFF_PAIR_UNMERGED(p)) {
+		/* unmerged */
+		run_external_diff(pgm, p->one->path, NULL, NULL, NULL, NULL,
+				  0);
+		return;
+	}
+
+	name = p->one->path;
+	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
+	name_munged = quote_one(name);
+	other_munged = quote_one(other);
+	one = p->one; two = p->two;
+
+	diff_fill_sha1_info(one);
+	diff_fill_sha1_info(two);
+
+	len = 0;
+	switch (p->status) {
+	case DIFF_STATUS_COPIED:
+		len += snprintf(msg + len, sizeof(msg) - len,
+				"similarity index %d%%\n"
+				"copy from %s\n"
+				"copy to %s\n",
+				(int)(0.5 + p->score * 100.0/MAX_SCORE),
+				name_munged, other_munged);
+		break;
+	case DIFF_STATUS_RENAMED:
+		len += snprintf(msg + len, sizeof(msg) - len,
+				"similarity index %d%%\n"
+				"rename from %s\n"
+				"rename to %s\n",
+				(int)(0.5 + p->score * 100.0/MAX_SCORE),
+				name_munged, other_munged);
+		break;
+	case DIFF_STATUS_MODIFIED:
+		if (p->score) {
+			len += snprintf(msg + len, sizeof(msg) - len,
+					"dissimilarity index %d%%\n",
+					(int)(0.5 + p->score *
+					      100.0/MAX_SCORE));
+			complete_rewrite = 1;
+			break;
+		}
+		/* fallthru */
+	default:
+		/* nothing */
+		;
+	}
+
+	if (memcmp(one->sha1, two->sha1, 20)) {
+		char one_sha1[41];
+		memcpy(one_sha1, sha1_to_hex(one->sha1), 41);
+
+		len += snprintf(msg + len, sizeof(msg) - len,
+				"index %.7s..%.7s", one_sha1,
+				sha1_to_hex(two->sha1));
+		if (one->mode == two->mode)
+			len += snprintf(msg + len, sizeof(msg) - len,
+					" %06o", one->mode);
+		len += snprintf(msg + len, sizeof(msg) - len, "\n");
+	}
+
+	if (len)
+		msg[--len] = 0;
+	xfrm_msg = len ? msg : NULL;
+
+	if (!pgm &&
+	    DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) &&
+	    (S_IFMT & one->mode) != (S_IFMT & two->mode)) {
+		/* a filepair that changes between file and symlink
+		 * needs to be split into deletion and creation.
+		 */
+		struct diff_filespec *null = alloc_filespec(two->path);
+		run_external_diff(NULL, name, other, one, null, xfrm_msg, 0);
+		free(null);
+		null = alloc_filespec(one->path);
+		run_external_diff(NULL, name, other, null, two, xfrm_msg, 0);
+		free(null);
+	}
+	else
+		run_external_diff(pgm, name, other, one, two, xfrm_msg,
+				  complete_rewrite);
+
+	free(name_munged);
+	free(other_munged);
+}
+
+void diff_setup(struct diff_options *options)
+{
+	memset(options, 0, sizeof(*options));
+	options->output_format = DIFF_FORMAT_RAW;
+	options->line_termination = '\n';
+	options->break_opt = -1;
+	options->rename_limit = -1;
+}
+
+int diff_setup_done(struct diff_options *options)
 {
-	int diglen, num, scale, i;
-	if (opt[0] != '-' || (opt[1] != 'M' && opt[1] != 'C'))
-		return -1; /* that is not a -M nor -C option */
-	diglen = strspn(opt+2, "0123456789");
-	if (diglen == 0 || strlen(opt+2) != diglen)
-		return 0; /* use default */
-	sscanf(opt+2, "%d", &num);
-	for (i = 0, scale = 1; i < diglen; i++)
-		scale *= 10;
+	if ((options->find_copies_harder || 0 <= options->rename_limit) &&
+	    options->detect_rename != DIFF_DETECT_COPY)
+		return -1;
+	if (options->setup & DIFF_SETUP_USE_CACHE) {
+		if (!active_cache)
+			/* read-cache does not die even when it fails
+			 * so it is safe for us to do this here.  Also
+			 * it does not smudge active_cache or active_nr
+			 * when it fails, so we do not have to worry about
+			 * cleaning it up oufselves either.
+			 */
+			read_cache();
+	}
+	if (options->setup & DIFF_SETUP_USE_SIZE_CACHE)
+		use_size_cache = 1;
+
+	return 0;
+}
+
+int diff_opt_parse(struct diff_options *options, const char **av, int ac)
+{
+	const char *arg = av[0];
+	if (!strcmp(arg, "-p") || !strcmp(arg, "-u"))
+		options->output_format = DIFF_FORMAT_PATCH;
+	else if (!strcmp(arg, "-z"))
+		options->line_termination = 0;
+	else if (!strncmp(arg, "-l", 2))
+		options->rename_limit = strtoul(arg+2, NULL, 10);
+	else if (!strcmp(arg, "--name-only"))
+		options->output_format = DIFF_FORMAT_NAME;
+	else if (!strcmp(arg, "--name-status"))
+		options->output_format = DIFF_FORMAT_NAME_STATUS;
+	else if (!strcmp(arg, "-R"))
+		options->reverse_diff = 1;
+	else if (!strncmp(arg, "-S", 2))
+		options->pickaxe = arg + 2;
+	else if (!strcmp(arg, "-s"))
+		options->output_format = DIFF_FORMAT_NO_OUTPUT;
+	else if (!strncmp(arg, "-O", 2))
+		options->orderfile = arg + 2;
+	else if (!strncmp(arg, "--diff-filter=", 14))
+		options->filter = arg + 14;
+	else if (!strcmp(arg, "--pickaxe-all"))
+		options->pickaxe_opts = DIFF_PICKAXE_ALL;
+	else if (!strncmp(arg, "-B", 2)) {
+		if ((options->break_opt =
+		     diff_scoreopt_parse(arg)) == -1)
+			return -1;
+	}
+	else if (!strncmp(arg, "-M", 2)) {
+		if ((options->rename_score =
+		     diff_scoreopt_parse(arg)) == -1)
+			return -1;
+		options->detect_rename = DIFF_DETECT_RENAME;
+	}
+	else if (!strncmp(arg, "-C", 2)) {
+		if ((options->rename_score =
+		     diff_scoreopt_parse(arg)) == -1)
+			return -1;
+		options->detect_rename = DIFF_DETECT_COPY;
+	}
+	else if (!strcmp(arg, "--find-copies-harder"))
+		options->find_copies_harder = 1;
+	else
+		return 0;
+	return 1;
+}
+
+static int parse_num(const char **cp_p)
+{
+	int num, scale, ch, cnt;
+	const char *cp = *cp_p;
+
+	cnt = num = 0;
+	scale = 1;
+	while ('0' <= (ch = *cp) && ch <= '9') {
+		if (cnt++ < 5) {
+			/* We simply ignore more than 5 digits precision. */
+			scale *= 10;
+			num = num * 10 + ch - '0';
+		}
+		cp++;
+	}
+	*cp_p = cp;
 
 	/* user says num divided by scale and we say internally that
 	 * is MAX_SCORE * num / scale.
 	 */
-	return MAX_SCORE * num / scale;
+	return (MAX_SCORE * num / scale);
 }
 
-void diff_setup(int reverse_diff_, int diff_output_style)
+int diff_scoreopt_parse(const char *opt)
 {
-	reverse_diff = reverse_diff_;
-	generate_patch = 0;
-	switch (diff_output_style) {
-	case DIFF_FORMAT_HUMAN:
-		line_termination = '\n';
-		inter_name_termination = '\t';
-		break;
-	case DIFF_FORMAT_MACHINE:
-		line_termination = inter_name_termination = 0;
-		break;
-	case DIFF_FORMAT_PATCH:
-		generate_patch = 1;
-		break;
+	int opt1, opt2, cmd;
+
+	if (*opt++ != '-')
+		return -1;
+	cmd = *opt++;
+	if (cmd != 'M' && cmd != 'C' && cmd != 'B')
+		return -1; /* that is not a -M, -C nor -B option */
+
+	opt1 = parse_num(&opt);
+	if (cmd != 'B')
+		opt2 = 0;
+	else {
+		if (*opt == 0)
+			opt2 = 0;
+		else if (*opt != '/')
+			return -1; /* we expect -B80/99 or -B80 */
+		else {
+			opt++;
+			opt2 = parse_num(&opt);
+		}
 	}
+	if (*opt != 0)
+		return -1;
+	return opt1 | (opt2 << 16);
 }
 
 struct diff_queue_struct diff_queued_diff;
 
-struct diff_filepair *diff_queue(struct diff_queue_struct *queue,
-				  struct diff_filespec *one,
-				  struct diff_filespec *two)
+void diff_q(struct diff_queue_struct *queue, struct diff_filepair *dp)
 {
-	struct diff_filepair *dp = xmalloc(sizeof(*dp));
-	dp->one = one;
-	dp->two = two;
-	dp->xfrm_msg = 0;
-	dp->orig_order = queue->nr;
-	dp->xfrm_work = 0;
 	if (queue->alloc <= queue->nr) {
 		queue->alloc = alloc_nr(queue->alloc);
 		queue->queue = xrealloc(queue->queue,
-				       sizeof(dp) * queue->alloc);
+					sizeof(dp) * queue->alloc);
 	}
 	queue->queue[queue->nr++] = dp;
+}
+
+struct diff_filepair *diff_queue(struct diff_queue_struct *queue,
+				 struct diff_filespec *one,
+				 struct diff_filespec *two)
+{
+	struct diff_filepair *dp = xmalloc(sizeof(*dp));
+	dp->one = one;
+	dp->two = two;
+	dp->score = 0;
+	dp->status = 0;
+	dp->source_stays = 0;
+	dp->broken_pair = 0;
+	if (queue)
+		diff_q(queue, dp);
 	return dp;
 }
 
-static void diff_flush_raw(struct diff_filepair *p)
+void diff_free_filepair(struct diff_filepair *p)
 {
-	/*
-	 * We used to reject rename/copy but new diff-raw can express them.
-	 */
-	printf(":%06o %06o %s ",
-	       p->one->mode, p->two->mode, sha1_to_hex(p->one->sha1));
-	printf("%s%c%s%c%s%c",
-	       sha1_to_hex(p->two->sha1), inter_name_termination,
-	       p->one->path, inter_name_termination,
-	       p->two->path, line_termination);
+	diff_free_filespec_data(p->one);
+	diff_free_filespec_data(p->two);
+	free(p->one);
+	free(p->two);
+	free(p);
 }
 
-static void diff_flush_patch(struct diff_filepair *p)
+static void diff_flush_raw(struct diff_filepair *p,
+			   int line_termination,
+			   int inter_name_termination,
+			   int output_format)
 {
-	const char *name, *other;
+	int two_paths;
+	char status[10];
+	const char *path_one, *path_two;
+
+	path_one = p->one->path;
+	path_two = p->two->path;
+	if (line_termination) {
+		path_one = quote_one(path_one);
+		path_two = quote_one(path_two);
+	}
 
-	name = p->one->path;
-	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
-	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
-	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
-		return; /* no tree diffs in patch format */ 
+	if (p->score)
+		sprintf(status, "%c%03d", p->status,
+			(int)(0.5 + p->score * 100.0/MAX_SCORE));
+	else {
+		status[0] = p->status;
+		status[1] = 0;
+	}
+	switch (p->status) {
+	case DIFF_STATUS_COPIED:
+	case DIFF_STATUS_RENAMED:
+		two_paths = 1;
+		break;
+	case DIFF_STATUS_ADDED:
+	case DIFF_STATUS_DELETED:
+		two_paths = 0;
+		break;
+	default:
+		two_paths = 0;
+		break;
+	}
+	if (output_format != DIFF_FORMAT_NAME_STATUS) {
+		printf(":%06o %06o %s ",
+		       p->one->mode, p->two->mode, sha1_to_hex(p->one->sha1));
+		printf("%s ", sha1_to_hex(p->two->sha1));
+	}
+	printf("%s%c%s", status, inter_name_termination, path_one);
+	if (two_paths)
+		printf("%c%s", inter_name_termination, path_two);
+	putchar(line_termination);
+	if (path_one != p->one->path)
+		free((void*)path_one);
+	if (path_two != p->two->path)
+		free((void*)path_two);
+}
+
+static void diff_flush_name(struct diff_filepair *p,
+			    int inter_name_termination,
+			    int line_termination)
+{
+	char *path = p->two->path;
 
-	run_external_diff(name, other, p->one, p->two, p->xfrm_msg);
+	if (line_termination)
+		path = quote_one(p->two->path);
+	else
+		path = p->two->path;
+	printf("%s%c", path, line_termination);
+	if (p->two->path != path)
+		free(path);
 }
 
-static int identical(struct diff_filespec *one, struct diff_filespec *two)
+int diff_unmodified_pair(struct diff_filepair *p)
 {
 	/* This function is written stricter than necessary to support
 	 * the currently implemented transformers, but the idea is to
 	 * let transformers to produce diff_filepairs any way they want,
 	 * and filter and clean them up here before producing the output.
 	 */
+	struct diff_filespec *one, *two;
+
+	if (DIFF_PAIR_UNMERGED(p))
+		return 0; /* unmerged is interesting */
 
-	if (!DIFF_FILE_VALID(one) && !DIFF_FILE_VALID(two))
-		return 1; /* not interesting */
+	one = p->one;
+	two = p->two;
 
-	/* deletion, addition, mode change and renames are all interesting. */
+	/* deletion, addition, mode or type change
+	 * and rename are all interesting.
+	 */
 	if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) ||
-	    (one->mode != two->mode) ||
+	    DIFF_PAIR_MODE_CHANGED(p) ||
 	    strcmp(one->path, two->path))
 		return 0;
 
@@ -607,53 +1014,254 @@ static int identical(struct diff_filespec *one, struct diff_filespec *two)
 	return 0;
 }
 
-static void diff_flush_one(struct diff_filepair *p)
+static void diff_flush_patch(struct diff_filepair *p)
 {
-	if (identical(p->one, p->two))
+	if (diff_unmodified_pair(p))
 		return;
-	if (generate_patch)
-		diff_flush_patch(p);
-	else
-		diff_flush_raw(p);
+
+	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
+	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
+		return; /* no tree diffs in patch format */ 
+
+	run_diff(p);
 }
 
 int diff_queue_is_empty(void)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
 	int i;
+	for (i = 0; i < q->nr; i++)
+		if (!diff_unmodified_pair(q->queue[i]))
+			return 0;
+	return 1;
+}
+
+#if DIFF_DEBUG
+void diff_debug_filespec(struct diff_filespec *s, int x, const char *one)
+{
+	fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n",
+		x, one ? one : "",
+		s->path,
+		DIFF_FILE_VALID(s) ? "valid" : "invalid",
+		s->mode,
+		s->sha1_valid ? sha1_to_hex(s->sha1) : "");
+	fprintf(stderr, "queue[%d] %s size %lu flags %d\n",
+		x, one ? one : "",
+		s->size, s->xfrm_flags);
+}
+
+void diff_debug_filepair(const struct diff_filepair *p, int i)
+{
+	diff_debug_filespec(p->one, i, "one");
+	diff_debug_filespec(p->two, i, "two");
+	fprintf(stderr, "score %d, status %c stays %d broken %d\n",
+		p->score, p->status ? p->status : '?',
+		p->source_stays, p->broken_pair);
+}
 
+void diff_debug_queue(const char *msg, struct diff_queue_struct *q)
+{
+	int i;
+	if (msg)
+		fprintf(stderr, "%s\n", msg);
+	fprintf(stderr, "q->nr = %d\n", q->nr);
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
-		if (!identical(p->one, p->two))
-			return 0;
+		diff_debug_filepair(p, i);
 	}
-	return 1;
 }
+#endif
 
-void diff_flush(const char **pathspec_, int speccnt_)
+static void diff_resolve_rename_copy(void)
 {
+	int i, j;
+	struct diff_filepair *p, *pp;
 	struct diff_queue_struct *q = &diff_queued_diff;
-	int i;
 
-	pathspec = pathspec_;
-	speccnt = speccnt_;
+	diff_debug_queue("resolve-rename-copy", q);
 
-	for (i = 0; i < q->nr; i++)
-		diff_flush_one(q->queue[i]);
+	for (i = 0; i < q->nr; i++) {
+		p = q->queue[i];
+		p->status = 0; /* undecided */
+		if (DIFF_PAIR_UNMERGED(p))
+			p->status = DIFF_STATUS_UNMERGED;
+		else if (!DIFF_FILE_VALID(p->one))
+			p->status = DIFF_STATUS_ADDED;
+		else if (!DIFF_FILE_VALID(p->two))
+			p->status = DIFF_STATUS_DELETED;
+		else if (DIFF_PAIR_TYPE_CHANGED(p))
+			p->status = DIFF_STATUS_TYPE_CHANGED;
+
+		/* from this point on, we are dealing with a pair
+		 * whose both sides are valid and of the same type, i.e.
+		 * either in-place edit or rename/copy edit.
+		 */
+		else if (DIFF_PAIR_RENAME(p)) {
+			if (p->source_stays) {
+				p->status = DIFF_STATUS_COPIED;
+				continue;
+			}
+			/* See if there is some other filepair that
+			 * copies from the same source as us.  If so
+			 * we are a copy.  Otherwise we are either a
+			 * copy if the path stays, or a rename if it
+			 * does not, but we already handled "stays" case.
+			 */
+			for (j = i + 1; j < q->nr; j++) {
+				pp = q->queue[j];
+				if (strcmp(pp->one->path, p->one->path))
+					continue; /* not us */
+				if (!DIFF_PAIR_RENAME(pp))
+					continue; /* not a rename/copy */
+				/* pp is a rename/copy from the same source */
+				p->status = DIFF_STATUS_COPIED;
+				break;
+			}
+			if (!p->status)
+				p->status = DIFF_STATUS_RENAMED;
+		}
+		else if (memcmp(p->one->sha1, p->two->sha1, 20) ||
+			 p->one->mode != p->two->mode)
+			p->status = DIFF_STATUS_MODIFIED;
+		else {
+			/* This is a "no-change" entry and should not
+			 * happen anymore, but prepare for broken callers.
+			 */
+			error("feeding unmodified %s to diffcore",
+			      p->one->path);
+			p->status = DIFF_STATUS_UNKNOWN;
+		}
+	}
+	diff_debug_queue("resolve-rename-copy done", q);
+}
+
+void diff_flush(struct diff_options *options)
+{
+	struct diff_queue_struct *q = &diff_queued_diff;
+	int i;
+	int inter_name_termination = '\t';
+	int diff_output_format = options->output_format;
+	int line_termination = options->line_termination;
+
+	if (!line_termination)
+		inter_name_termination = 0;
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
-		diff_free_filespec_data(p->one);
-		diff_free_filespec_data(p->two);
-		free(p->xfrm_msg);
-		free(p);
+		if ((diff_output_format == DIFF_FORMAT_NO_OUTPUT) ||
+		    (p->status == DIFF_STATUS_UNKNOWN))
+			continue;
+		if (p->status == 0)
+			die("internal error in diff-resolve-rename-copy");
+		switch (diff_output_format) {
+		case DIFF_FORMAT_PATCH:
+			diff_flush_patch(p);
+			break;
+		case DIFF_FORMAT_RAW:
+		case DIFF_FORMAT_NAME_STATUS:
+			diff_flush_raw(p, line_termination,
+				       inter_name_termination,
+				       diff_output_format);
+			break;
+		case DIFF_FORMAT_NAME:
+			diff_flush_name(p,
+					inter_name_termination,
+					line_termination);
+			break;
+		}
+		diff_free_filepair(q->queue[i]);
 	}
 	free(q->queue);
 	q->queue = NULL;
 	q->nr = q->alloc = 0;
 }
 
-void diff_addremove(int addremove, unsigned mode,
+static void diffcore_apply_filter(const char *filter)
+{
+	int i;
+	struct diff_queue_struct *q = &diff_queued_diff;
+	struct diff_queue_struct outq;
+	outq.queue = NULL;
+	outq.nr = outq.alloc = 0;
+
+	if (!filter)
+		return;
+
+	if (strchr(filter, DIFF_STATUS_FILTER_AON)) {
+		int found;
+		for (i = found = 0; !found && i < q->nr; i++) {
+			struct diff_filepair *p = q->queue[i];
+			if (((p->status == DIFF_STATUS_MODIFIED) &&
+			     ((p->score &&
+			       strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
+			      (!p->score &&
+			       strchr(filter, DIFF_STATUS_MODIFIED)))) ||
+			    ((p->status != DIFF_STATUS_MODIFIED) &&
+			     strchr(filter, p->status)))
+				found++;
+		}
+		if (found)
+			return;
+
+		/* otherwise we will clear the whole queue
+		 * by copying the empty outq at the end of this
+		 * function, but first clear the current entries
+		 * in the queue.
+		 */
+		for (i = 0; i < q->nr; i++)
+			diff_free_filepair(q->queue[i]);
+	}
+	else {
+		/* Only the matching ones */
+		for (i = 0; i < q->nr; i++) {
+			struct diff_filepair *p = q->queue[i];
+
+			if (((p->status == DIFF_STATUS_MODIFIED) &&
+			     ((p->score &&
+			       strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
+			      (!p->score &&
+			       strchr(filter, DIFF_STATUS_MODIFIED)))) ||
+			    ((p->status != DIFF_STATUS_MODIFIED) &&
+			     strchr(filter, p->status)))
+				diff_q(&outq, p);
+			else
+				diff_free_filepair(p);
+		}
+	}
+	free(q->queue);
+	*q = outq;
+}
+
+void diffcore_std(struct diff_options *options)
+{
+	if (options->paths && options->paths[0])
+		diffcore_pathspec(options->paths);
+	if (options->break_opt != -1)
+		diffcore_break(options->break_opt);
+	if (options->detect_rename)
+		diffcore_rename(options);
+	if (options->break_opt != -1)
+		diffcore_merge_broken();
+	if (options->pickaxe)
+		diffcore_pickaxe(options->pickaxe, options->pickaxe_opts);
+	if (options->orderfile)
+		diffcore_order(options->orderfile);
+	diff_resolve_rename_copy();
+	diffcore_apply_filter(options->filter);
+}
+
+
+void diffcore_std_no_resolve(struct diff_options *options)
+{
+	if (options->pickaxe)
+		diffcore_pickaxe(options->pickaxe, options->pickaxe_opts);
+	if (options->orderfile)
+		diffcore_order(options->orderfile);
+	diffcore_apply_filter(options->filter);
+}
+
+void diff_addremove(struct diff_options *options,
+		    int addremove, unsigned mode,
 		    const unsigned char *sha1,
 		    const char *base, const char *path)
 {
@@ -667,12 +1275,12 @@ void diff_addremove(int addremove, unsigned mode,
 	 * entries to the diff-core.  They will be prefixed
 	 * with something like '=' or '*' (I haven't decided
 	 * which but should not make any difference).
-	 * Feeding the same new and old to diff_change() should
-	 * also have the same effect.  diff_flush() should
-	 * filter the identical ones out at the final output
-	 * stage.
+	 * Feeding the same new and old to diff_change() 
+	 * also has the same effect.
+	 * Before the final output happens, they are pruned after
+	 * merged into rename/copy pairs as appropriate.
 	 */
-	if (reverse_diff)
+	if (options->reverse_diff)
 		addremove = (addremove == '+' ? '-' :
 			     addremove == '-' ? '+' : addremove);
 
@@ -689,31 +1297,8 @@ void diff_addremove(int addremove, unsigned mode,
 	diff_queue(&diff_queued_diff, one, two);
 }
 
-void diff_guif(unsigned old_mode,
-	       unsigned new_mode,
-	       const unsigned char *old_sha1,
-	       const unsigned char *new_sha1,
-	       const char *old_path,
-	       const char *new_path)
-{
-	struct diff_filespec *one, *two;
-
-	if (reverse_diff) {
-		unsigned tmp;
-		const unsigned char *tmp_c;
-		tmp = old_mode; old_mode = new_mode; new_mode = tmp;
-		tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c;
-	}
-	one = alloc_filespec(old_path);
-	two = alloc_filespec(new_path);
-	if (old_mode)
-		fill_filespec(one, old_sha1, old_mode);
-	if (new_mode)
-		fill_filespec(two, new_sha1, new_mode);
-	diff_queue(&diff_queued_diff, one, two);
-}
-
-void diff_change(unsigned old_mode, unsigned new_mode,
+void diff_change(struct diff_options *options,
+		 unsigned old_mode, unsigned new_mode,
 		 const unsigned char *old_sha1,
 		 const unsigned char *new_sha1,
 		 const char *base, const char *path) 
@@ -721,7 +1306,7 @@ void diff_change(unsigned old_mode, unsigned new_mode,
 	char concatpath[PATH_MAX];
 	struct diff_filespec *one, *two;
 
-	if (reverse_diff) {
+	if (options->reverse_diff) {
 		unsigned tmp;
 		const unsigned char *tmp_c;
 		tmp = old_mode; old_mode = new_mode; new_mode = tmp;
@@ -737,10 +1322,11 @@ void diff_change(unsigned old_mode, unsigned new_mode,
 	diff_queue(&diff_queued_diff, one, two);
 }
 
-void diff_unmerge(const char *path)
+void diff_unmerge(struct diff_options *options,
+		  const char *path)
 {
-	if (generate_patch)
-		run_external_diff(path, NULL, NULL, NULL, NULL);
-	else
-		printf("U %s%c", path, line_termination);
+	struct diff_filespec *one, *two;
+	one = alloc_filespec(path);
+	two = alloc_filespec(path);
+	diff_queue(&diff_queued_diff, one, two);
 }