X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=diff.c;h=cd6b0c4e0bb5efad828fa29e92e8729418401080;hb=689b4d552b8108d2c92c63258990ecd2bc791739;hp=e225de230599bb35d9fe5b219ff4b8e8de9bfd97;hpb=253e772edeb56092e0fad43ec0640658671313c5;p=git.git

diff --git a/diff.c b/diff.c
index e225de230..cd6b0c4e0 100644
--- a/diff.c
+++ b/diff.c
@@ -8,6 +8,7 @@
 #include "delta.h"
 #include "xdiff-interface.h"
 #include "color.h"
+#include "attr.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -15,8 +16,6 @@
 #define FAST_WORKING_DIRECTORY 1
 #endif
 
-static int use_size_cache;
-
 static int diff_detect_rename_default;
 static int diff_rename_limit_default = -1;
 static int diff_use_color_default;
@@ -51,6 +50,96 @@ static int parse_diff_color_slot(const char *var, int ofs)
 	die("bad config variable '%s'", var);
 }
 
+static struct ll_diff_driver {
+	const char *name;
+	struct ll_diff_driver *next;
+	char *cmd;
+} *user_diff, **user_diff_tail;
+
+static void read_config_if_needed(void)
+{
+	if (!user_diff_tail) {
+		user_diff_tail = &user_diff;
+		git_config(git_diff_ui_config);
+	}
+}
+
+/*
+ * Currently there is only "diff.<drivername>.command" variable;
+ * because there are "diff.color.<slot>" variables, we are parsing
+ * this in a bit convoluted way to allow low level diff driver
+ * called "color".
+ */
+static int parse_lldiff_command(const char *var, const char *ep, const char *value)
+{
+	const char *name;
+	int namelen;
+	struct ll_diff_driver *drv;
+
+	name = var + 5;
+	namelen = ep - name;
+	for (drv = user_diff; drv; drv = drv->next)
+		if (!strncmp(drv->name, name, namelen) && !drv->name[namelen])
+			break;
+	if (!drv) {
+		char *namebuf;
+		drv = xcalloc(1, sizeof(struct ll_diff_driver));
+		namebuf = xmalloc(namelen + 1);
+		memcpy(namebuf, name, namelen);
+		namebuf[namelen] = 0;
+		drv->name = namebuf;
+		drv->next = NULL;
+		if (!user_diff_tail)
+			user_diff_tail = &user_diff;
+		*user_diff_tail = drv;
+		user_diff_tail = &(drv->next);
+	}
+
+	if (!value)
+		return error("%s: lacks value", var);
+	drv->cmd = strdup(value);
+	return 0;
+}
+
+/*
+ * 'diff.<what>.funcname' attribute can be specified in the configuration
+ * to define a customized regexp to find the beginning of a function to
+ * be used for hunk header lines of "diff -p" style output.
+ */
+static struct funcname_pattern {
+	char *name;
+	char *pattern;
+	struct funcname_pattern *next;
+} *funcname_pattern_list;
+
+static int parse_funcname_pattern(const char *var, const char *ep, const char *value)
+{
+	const char *name;
+	int namelen;
+	struct funcname_pattern *pp;
+
+	name = var + 5; /* "diff." */
+	namelen = ep - name;
+
+	for (pp = funcname_pattern_list; pp; pp = pp->next)
+		if (!strncmp(pp->name, name, namelen) && !pp->name[namelen])
+			break;
+	if (!pp) {
+		char *namebuf;
+		pp = xcalloc(1, sizeof(*pp));
+		namebuf = xmalloc(namelen + 1);
+		memcpy(namebuf, name, namelen);
+		namebuf[namelen] = 0;
+		pp->name = namebuf;
+		pp->next = funcname_pattern_list;
+		funcname_pattern_list = pp;
+	}
+	if (pp->pattern)
+		free(pp->pattern);
+	pp->pattern = xstrdup(value);
+	return 0;
+}
+
 /*
  * These are to give UI layer defaults.
  * The core-level commands such as git-diff-files should
@@ -77,11 +166,22 @@ int git_diff_ui_config(const char *var, const char *value)
 			diff_detect_rename_default = DIFF_DETECT_RENAME;
 		return 0;
 	}
+	if (!prefixcmp(var, "diff.")) {
+		const char *ep = strrchr(var, '.');
+
+		if (ep != var + 4) {
+			if (!strcmp(ep, ".command"))
+				return parse_lldiff_command(var, ep, value);
+			if (!strcmp(ep, ".funcname"))
+				return parse_funcname_pattern(var, ep, value);
+		}
+	}
 	if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
 		int slot = parse_diff_color_slot(var, 11);
 		color_parse(value, var, diff_colors[slot]);
 		return 0;
 	}
+
 	return git_default_config(var, value);
 }
 
@@ -137,13 +237,11 @@ static const char *external_diff(void)
 	return external_diff_cmd;
 }
 
-#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[TEMPFILE_PATH_LEN];
+	char tmp_path[PATH_MAX];
 } diff_temp[2];
 
 static int count_lines(const char *data, int size)
@@ -343,6 +441,7 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	mmfile_t minus, plus;
 	int i;
 
+	memset(&xecfg, 0, sizeof(xecfg));
 	minus.size = diff_words->minus.text.size;
 	minus.ptr = xmalloc(minus.size);
 	memcpy(minus.ptr, diff_words->minus.text.ptr, minus.size);
@@ -361,7 +460,6 @@ static void diff_words_show(struct diff_words_data *diff_words)
 
 	xpp.flags = XDF_NEED_MINIMAL;
 	xecfg.ctxlen = diff_words->minus.alloc + diff_words->plus.alloc;
-	xecfg.flags = 0;
 	ecb.outf = xdiff_outf;
 	ecb.priv = diff_words;
 	diff_words->xm.consume = fn_out_diff_words_aux;
@@ -811,7 +909,12 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options)
 
 		if (data->files[i]->is_binary) {
 			show_name(prefix, name, len, reset, set);
-			printf("  Bin\n");
+			printf("  Bin ");
+			printf("%s%d%s", del_c, deleted, reset);
+			printf(" -> ");
+			printf("%s%d%s", add_c, added, reset);
+			printf(" bytes");
+			printf("\n");
 			goto free_diffstat_file;
 		}
 		else if (data->files[i]->is_unmerged) {
@@ -1046,13 +1149,115 @@ static void emit_binary_diff(mmfile_t *one, mmfile_t *two)
 	emit_binary_diff_body(two, one);
 }
 
-#define FIRST_FEW_BYTES 8000
-static int mmfile_is_binary(mmfile_t *mf)
+static void setup_diff_attr_check(struct git_attr_check *check)
 {
-	long sz = mf->size;
-	if (FIRST_FEW_BYTES < sz)
-		sz = FIRST_FEW_BYTES;
-	return !!memchr(mf->ptr, 0, sz);
+	static struct git_attr *attr_diff;
+
+	if (!attr_diff) {
+		attr_diff = git_attr("diff", 4);
+	}
+	check[0].attr = attr_diff;
+}
+
+static void diff_filespec_check_attr(struct diff_filespec *one)
+{
+	struct git_attr_check attr_diff_check;
+	int check_from_data = 0;
+
+	if (one->checked_attr)
+		return;
+
+	setup_diff_attr_check(&attr_diff_check);
+	one->is_binary = 0;
+	one->funcname_pattern_ident = NULL;
+
+	if (!git_checkattr(one->path, 1, &attr_diff_check)) {
+		const char *value;
+
+		/* binaryness */
+		value = attr_diff_check.value;
+		if (ATTR_TRUE(value))
+			;
+		else if (ATTR_FALSE(value))
+			one->is_binary = 1;
+		else
+			check_from_data = 1;
+
+		/* funcname pattern ident */
+		if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value))
+			;
+		else
+			one->funcname_pattern_ident = value;
+	}
+
+	if (check_from_data) {
+		if (!one->data && DIFF_FILE_VALID(one))
+			diff_populate_filespec(one, 0);
+
+		if (one->data)
+			one->is_binary = buffer_is_binary(one->data, one->size);
+	}
+}
+
+int diff_filespec_is_binary(struct diff_filespec *one)
+{
+	diff_filespec_check_attr(one);
+	return one->is_binary;
+}
+
+static const char *funcname_pattern(const char *ident)
+{
+	struct funcname_pattern *pp;
+
+	read_config_if_needed();
+	for (pp = funcname_pattern_list; pp; pp = pp->next)
+		if (!strcmp(ident, pp->name))
+			return pp->pattern;
+	return NULL;
+}
+
+static struct builtin_funcname_pattern {
+	const char *name;
+	const char *pattern;
+} builtin_funcname_pattern[] = {
+	{ "java", "!^[ 	]*\\(catch\\|do\\|for\\|if\\|instanceof\\|"
+			"new\\|return\\|switch\\|throw\\|while\\)\n"
+			"^[ 	]*\\(\\([ 	]*"
+			"[A-Za-z_][A-Za-z_0-9]*\\)\\{2,\\}"
+			"[ 	]*([^;]*$\\)" },
+	{ "tex", "^\\(\\\\\\(sub\\)*section{.*\\)$" },
+};
+
+static const char *diff_funcname_pattern(struct diff_filespec *one)
+{
+	const char *ident, *pattern;
+	int i;
+
+	diff_filespec_check_attr(one);
+	ident = one->funcname_pattern_ident;
+
+	if (!ident)
+		/*
+		 * If the config file has "funcname.default" defined, that
+		 * regexp is used; otherwise NULL is returned and xemit uses
+		 * the built-in default.
+		 */
+		return funcname_pattern("default");
+
+	/* Look up custom "funcname.$ident" regexp from config. */
+	pattern = funcname_pattern(ident);
+	if (pattern)
+		return pattern;
+
+	/*
+	 * And define built-in fallback patterns here.  Note that
+	 * these can be overriden by the user's config settings.
+	 */
+	for (i = 0; i < ARRAY_SIZE(builtin_funcname_pattern); i++)
+		if (!strcmp(ident, builtin_funcname_pattern[i].name))
+			return builtin_funcname_pattern[i].pattern;
+
+	return NULL;
 }
 
 static void builtin_diff(const char *name_a,
@@ -1109,7 +1314,8 @@ static void builtin_diff(const char *name_a,
 	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
 		die("unable to read files to diff");
 
-	if (!o->text && (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2))) {
+	if (!o->text &&
+	    (diff_filespec_is_binary(one) || diff_filespec_is_binary(two))) {
 		/* Quite common confusing case */
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size))
@@ -1128,7 +1334,13 @@ static void builtin_diff(const char *name_a,
 		xdemitconf_t xecfg;
 		xdemitcb_t ecb;
 		struct emit_callback ecbdata;
+		const char *funcname_pattern;
 
+		funcname_pattern = diff_funcname_pattern(one);
+		if (!funcname_pattern)
+			funcname_pattern = diff_funcname_pattern(two);
+
+		memset(&xecfg, 0, sizeof(xecfg));
 		memset(&ecbdata, 0, sizeof(ecbdata));
 		ecbdata.label_path = lbl;
 		ecbdata.color_diff = o->color_diff;
@@ -1136,6 +1348,8 @@ static void builtin_diff(const char *name_a,
 		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
 		xecfg.ctxlen = o->context;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
+		if (funcname_pattern)
+			xdiff_set_find_func(&xecfg, funcname_pattern);
 		if (!diffopts)
 			;
 		else if (!prefixcmp(diffopts, "--unified="))
@@ -1154,6 +1368,8 @@ static void builtin_diff(const char *name_a,
 	}
 
  free_ab_and_return:
+	diff_free_filespec_data(one);
+	diff_free_filespec_data(two);
 	free(a_one);
 	free(b_two);
 	return;
@@ -1180,26 +1396,31 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 		diff_populate_filespec(two, 0);
 		data->deleted = count_lines(one->data, one->size);
 		data->added = count_lines(two->data, two->size);
-		return;
+		goto free_and_return;
 	}
 	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
 		die("unable to read files to diff");
 
-	if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2))
+	if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
 		data->is_binary = 1;
-	else {
+		data->added = mf2.size;
+		data->deleted = mf1.size;
+	} else {
 		/* Crazy xdl interfaces.. */
 		xpparam_t xpp;
 		xdemitconf_t xecfg;
 		xdemitcb_t ecb;
 
+		memset(&xecfg, 0, sizeof(xecfg));
 		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
-		xecfg.ctxlen = 0;
-		xecfg.flags = 0;
 		ecb.outf = xdiff_outf;
 		ecb.priv = diffstat;
 		xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
 	}
+
+ free_and_return:
+	diff_free_filespec_data(one);
+	diff_free_filespec_data(two);
 }
 
 static void builtin_checkdiff(const char *name_a, const char *name_b,
@@ -1221,21 +1442,23 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
 	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
 		die("unable to read files to diff");
 
-	if (mmfile_is_binary(&mf2))
-		return;
+	if (diff_filespec_is_binary(two))
+		goto free_and_return;
 	else {
 		/* Crazy xdl interfaces.. */
 		xpparam_t xpp;
 		xdemitconf_t xecfg;
 		xdemitcb_t ecb;
 
+		memset(&xecfg, 0, sizeof(xecfg));
 		xpp.flags = XDF_NEED_MINIMAL;
-		xecfg.ctxlen = 0;
-		xecfg.flags = 0;
 		ecb.outf = xdiff_outf;
 		ecb.priv = &data;
 		xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
 	}
+ free_and_return:
+	diff_free_filespec_data(one);
+	diff_free_filespec_data(two);
 }
 
 struct diff_filespec *alloc_filespec(const char *path)
@@ -1260,7 +1483,7 @@ void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
 }
 
 /*
- * Given a name and sha1 pair, if the dircache tells us the file in
+ * Given a name and sha1 pair, if the index tells us the file in
  * the work tree has that object contents, return true, so that
  * prepare_temp_file() does not have to inflate and extract.
  */
@@ -1315,53 +1538,46 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 	return 1;
 }
 
-static struct sha1_size_cache {
-	unsigned char sha1[20];
+static int populate_from_stdin(struct diff_filespec *s)
+{
+#define INCREMENT 1024
+	char *buf;
 	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 = hashcmp(e->sha1, sha1);
-		if (!cmp)
-			return e;
-		if (cmp < 0) {
-			last = next;
-			continue;
-		}
-		first = next+1;
+	ssize_t got;
+
+	size = 0;
+	buf = NULL;
+	while (1) {
+		buf = xrealloc(buf, size + INCREMENT);
+		got = xread(0, buf + size, INCREMENT);
+		if (!got)
+			break; /* EOF */
+		if (got < 0)
+			return error("error while reading from stdin %s",
+				     strerror(errno));
+		size += got;
+	}
+	s->should_munmap = 0;
+	s->data = buf;
+	s->size = size;
+	s->should_free = 1;
+	return 0;
+}
+
+static int diff_populate_gitlink(struct diff_filespec *s, int size_only)
+{
+	int len;
+	char *data = xmalloc(100);
+	len = snprintf(data, 100,
+		"Subproject commit %s\n", sha1_to_hex(s->sha1));
+	s->data = data;
+	s->size = len;
+	s->should_free = 1;
+	if (size_only) {
+		s->data = NULL;
+		free(data);
 	}
-	/* 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;
-	hashcpy(e->sha1, sha1);
-	e->size = size;
-	return e;
+	return 0;
 }
 
 /*
@@ -1377,11 +1593,15 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 	if (S_ISDIR(s->mode))
 		return -1;
 
-	if (!use_size_cache)
-		size_only = 0;
-
 	if (s->data)
-		return err;
+		return 0;
+
+	if (size_only && 0 < s->size)
+		return 0;
+
+	if (S_ISGITLINK(s->mode))
+		return diff_populate_gitlink(s, size_only);
+
 	if (!s->sha1_valid ||
 	    reuse_worktree_file(s->path, s->sha1, 0)) {
 		struct stat st;
@@ -1389,6 +1609,9 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 		char *buf;
 		unsigned long size;
 
+		if (!strcmp(s->path, "-"))
+			return populate_from_stdin(s);
+
 		if (lstat(s->path, &st) < 0) {
 			if (errno == ENOENT) {
 			err_empty:
@@ -1399,7 +1622,7 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 				return err;
 			}
 		}
-		s->size = st.st_size;
+		s->size = xsize_t(st.st_size);
 		if (!s->size)
 			goto empty;
 		if (size_only)
@@ -1425,9 +1648,9 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 		/*
 		 * Convert from working tree format to canonical git format
 		 */
-		buf = s->data;
 		size = s->size;
-		if (convert_to_git(s->path, &buf, &size)) {
+		buf = convert_to_git(s->path, s->data, &size);
+		if (buf) {
 			munmap(s->data, s->size);
 			s->should_munmap = 0;
 			s->data = buf;
@@ -1437,18 +1660,8 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 	}
 	else {
 		enum object_type type;
-		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 (size_only)
 			type = sha1_object_info(s->sha1, &s->size);
-			if (type < 0)
-				locate_size_cache(s->sha1, 0, s->size);
-		}
 		else {
 			s->data = read_sha1_file(s->sha1, &type, &s->size);
 			s->should_free = 1;
@@ -1463,8 +1676,11 @@ void diff_free_filespec_data(struct diff_filespec *s)
 		free(s->data);
 	else if (s->should_munmap)
 		munmap(s->data, s->size);
-	s->should_free = s->should_munmap = 0;
-	s->data = NULL;
+
+	if (s->should_free || s->should_munmap) {
+		s->should_free = s->should_munmap = 0;
+		s->data = NULL;
+	}
 	free(s->cnt_data);
 	s->cnt_data = NULL;
 }
@@ -1477,7 +1693,7 @@ static void prep_temp_blob(struct diff_tempfile *temp,
 {
 	int fd;
 
-	fd = git_mkstemp(temp->tmp_path, TEMPFILE_PATH_LEN, ".diff_XXXXXX");
+	fd = git_mkstemp(temp->tmp_path, PATH_MAX, ".diff_XXXXXX");
 	if (fd < 0)
 		die("unable to create temp-file");
 	if (write_in_full(fd, blob, size) != size)
@@ -1515,12 +1731,13 @@ static void prepare_temp_file(const char *name,
 		if (S_ISLNK(st.st_mode)) {
 			int ret;
 			char buf[PATH_MAX + 1]; /* ought to be SYMLINK_MAX */
+			size_t sz = xsize_t(st.st_size);
 			if (sizeof(buf) <= st.st_size)
 				die("symlink too long: %s", name);
-			ret = readlink(name, buf, st.st_size);
+			ret = readlink(name, buf, sz);
 			if (ret < 0)
 				die("readlink(%s)", name);
-			prep_temp_blob(temp, buf, st.st_size,
+			prep_temp_blob(temp, buf, sz,
 				       (one->sha1_valid ?
 					one->sha1 : null_sha1),
 				       (one->sha1_valid ?
@@ -1663,6 +1880,27 @@ static void run_external_diff(const char *pgm,
 	}
 }
 
+static const char *external_diff_attr(const char *name)
+{
+	struct git_attr_check attr_diff_check;
+
+	setup_diff_attr_check(&attr_diff_check);
+	if (!git_checkattr(name, 1, &attr_diff_check)) {
+		const char *value = attr_diff_check.value;
+		if (!ATTR_TRUE(value) &&
+		    !ATTR_FALSE(value) &&
+		    !ATTR_UNSET(value)) {
+			struct ll_diff_driver *drv;
+
+			read_config_if_needed();
+			for (drv = user_diff; drv; drv = drv->next)
+				if (!strcmp(drv->name, value))
+					return drv->cmd;
+		}
+	}
+	return NULL;
+}
+
 static void run_diff_cmd(const char *pgm,
 			 const char *name,
 			 const char *other,
@@ -1672,6 +1910,14 @@ static void run_diff_cmd(const char *pgm,
 			 struct diff_options *o,
 			 int complete_rewrite)
 {
+	if (!o->allow_external)
+		pgm = NULL;
+	else {
+		const char *cmd = external_diff_attr(name);
+		if (cmd)
+			pgm = cmd;
+	}
+
 	if (pgm) {
 		run_external_diff(pgm, name, other, one, two, xfrm_msg,
 				  complete_rewrite);
@@ -1689,6 +1935,10 @@ static void diff_fill_sha1_info(struct diff_filespec *one)
 	if (DIFF_FILE_VALID(one)) {
 		if (!one->sha1_valid) {
 			struct stat st;
+			if (!strcmp(one->path, "-")) {
+				hashcpy(one->sha1, null_sha1);
+				return;
+			}
 			if (lstat(one->path, &st) < 0)
 				die("stat %s", one->path);
 			if (index_path(one->sha1, one->path, &st, 0))
@@ -1699,6 +1949,11 @@ static void diff_fill_sha1_info(struct diff_filespec *one)
 		hashclr(one->sha1);
 }
 
+static int similarity_index(struct diff_filepair *p)
+{
+	return p->score * 100 / MAX_SCORE;
+}
+
 static void run_diff(struct diff_filepair *p, struct diff_options *o)
 {
 	const char *pgm = external_diff();
@@ -1733,23 +1988,20 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 				"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);
+				similarity_index(p), 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);
+				similarity_index(p), 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));
+					similarity_index(p));
 			complete_rewrite = 1;
 			break;
 		}
@@ -1764,8 +2016,8 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 
 		if (o->binary) {
 			mmfile_t mf;
-			if ((!fill_mmfile(&mf, one) && mmfile_is_binary(&mf)) ||
-			    (!fill_mmfile(&mf, two) && mmfile_is_binary(&mf)))
+			if ((!fill_mmfile(&mf, one) && diff_filespec_is_binary(one)) ||
+			    (!fill_mmfile(&mf, two) && diff_filespec_is_binary(two)))
 				abbrev = 40;
 		}
 		len += snprintf(msg + len, sizeof(msg) - len,
@@ -1919,11 +2171,26 @@ int diff_setup_done(struct diff_options *options)
 			 */
 			read_cache();
 	}
-	if (options->setup & DIFF_SETUP_USE_SIZE_CACHE)
-		use_size_cache = 1;
 	if (options->abbrev <= 0 || 40 < options->abbrev)
 		options->abbrev = 40; /* full */
 
+	/*
+	 * It does not make sense to show the first hit we happened
+	 * to have found.  It does not make sense not to return with
+	 * exit code in such a case either.
+	 */
+	if (options->quiet) {
+		options->output_format = DIFF_FORMAT_NO_OUTPUT;
+		options->exit_with_status = 1;
+	}
+
+	/*
+	 * If we postprocess in diffcore, we cannot simply return
+	 * upon the first hit.  We need to run diff as usual.
+	 */
+	if (options->pickaxe || options->filter)
+		options->quiet = 0;
+
 	return 0;
 }
 
@@ -1974,6 +2241,8 @@ static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *va
 	return 1;
 }
 
+static int diff_scoreopt_parse(const char *opt);
+
 int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 {
 	const char *arg = av[0];
@@ -2070,6 +2339,8 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		options->detect_rename = DIFF_DETECT_RENAME;
 	}
 	else if (!prefixcmp(arg, "-C")) {
+		if (options->detect_rename == DIFF_DETECT_COPY)
+			options->find_copies_harder = 1;
 		if ((options->rename_score =
 		     diff_scoreopt_parse(arg)) == -1)
 			return -1;
@@ -2077,6 +2348,8 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	}
 	else if (!strcmp(arg, "--find-copies-harder"))
 		options->find_copies_harder = 1;
+	else if (!strcmp(arg, "--follow"))
+		options->follow_renames = 1;
 	else if (!strcmp(arg, "--abbrev"))
 		options->abbrev = DEFAULT_ABBREV;
 	else if (!prefixcmp(arg, "--abbrev=")) {
@@ -2100,6 +2373,14 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		options->color_diff = options->color_diff_words = 1;
 	else if (!strcmp(arg, "--no-renames"))
 		options->detect_rename = 0;
+	else if (!strcmp(arg, "--exit-code"))
+		options->exit_with_status = 1;
+	else if (!strcmp(arg, "--quiet"))
+		options->quiet = 1;
+	else if (!strcmp(arg, "--ext-diff"))
+		options->allow_external = 1;
+	else if (!strcmp(arg, "--no-ext-diff"))
+		options->allow_external = 0;
 	else
 		return 0;
 	return 1;
@@ -2138,10 +2419,10 @@ static int parse_num(const char **cp_p)
 	/* user says num divided by scale and we say internally that
 	 * is MAX_SCORE * num / scale.
 	 */
-	return (num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale);
+	return (int)((num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale));
 }
 
-int diff_scoreopt_parse(const char *opt)
+static int diff_scoreopt_parse(const char *opt)
 {
 	int opt1, opt2, cmd;
 
@@ -2248,8 +2529,7 @@ static void diff_flush_raw(struct diff_filepair *p,
 	}
 
 	if (p->score)
-		sprintf(status, "%c%03d", p->status,
-			(int)(0.5 + p->score * 100.0/MAX_SCORE));
+		sprintf(status, "%c%03d", p->status, similarity_index(p));
 	else {
 		status[0] = p->status;
 		status[1] = 0;
@@ -2274,7 +2554,8 @@ static void diff_flush_raw(struct diff_filepair *p,
 		printf("%s ",
 		       diff_unique_abbrev(p->two->sha1, abbrev));
 	}
-	printf("%s%c%s", status, inter_name_termination, path_one);
+	printf("%s%c%s", status, inter_name_termination,
+			two_paths || p->one->mode ?  path_one : path_two);
 	if (two_paths)
 		printf("%c%s", inter_name_termination, path_two);
 	putchar(line_termination);
@@ -2531,8 +2812,7 @@ static void show_rename_copy(const char *renamecopy, struct diff_filepair *p)
 {
 	char *names = pprint_rename(p->one->path, p->two->path);
 
-	printf(" %s %s (%d%%)\n", renamecopy, names,
-	       (int)(0.5 + p->score * 100.0/MAX_SCORE));
+	printf(" %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
 	free(names);
 	show_mode_change(p, 0);
 }
@@ -2556,7 +2836,7 @@ static void diff_summary(struct diff_filepair *p)
 		if (p->score) {
 			char *name = quote_one(p->two->path);
 			printf(" rewrite %s (%d%%)\n", name,
-				(int)(0.5 + p->score * 100.0/MAX_SCORE));
+			       similarity_index(p));
 			free(name);
 			show_mode_change(p, 0);
 		} else	show_mode_change(p, 1);
@@ -2620,6 +2900,7 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 		struct diff_filepair *p = q->queue[i];
 		int len1, len2;
 
+		memset(&xecfg, 0, sizeof(xecfg));
 		if (p->status == 0)
 			return error("internal diff status error");
 		if (p->status == DIFF_STATUS_UNKNOWN)
@@ -2639,7 +2920,7 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 			return error("unable to read files to diff");
 
 		/* Maybe hash p->two? into the patch id? */
-		if (mmfile_is_binary(&mf2))
+		if (diff_filespec_is_binary(p->two))
 			continue;
 
 		len1 = remove_space(p->one->path, strlen(p->one->path));
@@ -2864,6 +3145,9 @@ static void diffcore_apply_filter(const char *filter)
 
 void diffcore_std(struct diff_options *options)
 {
+	if (options->quiet)
+		return;
+
 	if (options->break_opt != -1)
 		diffcore_break(options->break_opt);
 	if (options->detect_rename)
@@ -2876,18 +3160,11 @@ void diffcore_std(struct diff_options *options)
 		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);
+	options->has_changes = !!diff_queued_diff.nr;
 }
 
+
 void diff_addremove(struct diff_options *options,
 		    int addremove, unsigned mode,
 		    const unsigned char *sha1,
@@ -2903,7 +3180,7 @@ void diff_addremove(struct diff_options *options,
 	 * 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() 
+	 * 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.
@@ -2923,13 +3200,14 @@ void diff_addremove(struct diff_options *options,
 		fill_filespec(two, sha1, mode);
 
 	diff_queue(&diff_queued_diff, one, two);
+	options->has_changes = 1;
 }
 
 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) 
+		 const char *base, const char *path)
 {
 	char concatpath[PATH_MAX];
 	struct diff_filespec *one, *two;
@@ -2948,6 +3226,7 @@ void diff_change(struct diff_options *options,
 	fill_filespec(two, new_sha1, new_mode);
 
 	diff_queue(&diff_queued_diff, one, two);
+	options->has_changes = 1;
 }
 
 void diff_unmerge(struct diff_options *options,