1 files changed, 210 insertions, 164 deletions

diff --git a/tree-diff.c b/tree-diff.c
index d978428910..b3cc2e4753 100644
--- a/tree-diff.c
+++ b/tree-diff.c
@@ -3,64 +3,26 @@
  */
 #include "cache.h"
 #include "diff.h"
+#include "diffcore.h"
+#include "tree.h"
 
-// What paths are we interested in?
-static int nr_paths = 0;
-static const char **paths = NULL;
-static int *pathlens = NULL;
+static void show_entry(struct diff_options *opt, const char *prefix,
+		       struct tree_desc *desc, struct strbuf *base);
 
-void update_tree_entry(struct tree_desc *desc)
-{
-	void *buf = desc->buf;
-	unsigned long size = desc->size;
-	int len = strlen(buf) + 1 + 20;
-
-	if (size < len)
-		die("corrupt tree file");
-	desc->buf = buf + len;
-	desc->size = size - len;
-}
-
-const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep)
-{
-	void *tree = desc->buf;
-	unsigned long size = desc->size;
-	int len = strlen(tree)+1;
-	const unsigned char *sha1 = tree + len;
-	const char *path = strchr(tree, ' ');
-	unsigned int mode;
-
-	if (!path || size < len + 20 || sscanf(tree, "%o", &mode) != 1)
-		die("corrupt tree file");
-	*pathp = path+1;
-	*modep = DIFF_FILE_CANON_MODE(mode);
-	return sha1;
-}
-
-static char *malloc_base(const char *base, const char *path, int pathlen)
-{
-	int baselen = strlen(base);
-	char *newbase = xmalloc(baselen + pathlen + 2);
-	memcpy(newbase, base, baselen);
-	memcpy(newbase + baselen, path, pathlen);
-	memcpy(newbase + baselen + pathlen, "/", 2);
-	return newbase;
-}
-
-static int show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc, const char *base);
-
-static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt)
+static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2,
+			      struct strbuf *base, struct diff_options *opt)
 {
 	unsigned mode1, mode2;
 	const char *path1, *path2;
 	const unsigned char *sha1, *sha2;
 	int cmp, pathlen1, pathlen2;
+	int old_baselen = base->len;
 
 	sha1 = tree_entry_extract(t1, &path1, &mode1);
 	sha2 = tree_entry_extract(t2, &path2, &mode2);
 
-	pathlen1 = strlen(path1);
-	pathlen2 = strlen(path2);
+	pathlen1 = tree_entry_len(path1, sha1);
+	pathlen2 = tree_entry_len(path2, sha2);
 	cmp = base_name_compare(path1, pathlen1, mode1, path2, pathlen2, mode2);
 	if (cmp < 0) {
 		show_entry(opt, "-", t1, base);
@@ -70,8 +32,7 @@ static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const
 		show_entry(opt, "+", t2, base);
 		return 1;
 	}
-	if (!opt->find_copies_harder &&
-	    !memcmp(sha1, sha2, 20) && mode1 == mode2)
+	if (!DIFF_OPT_TST(opt, FIND_COPIES_HARDER) && !hashcmp(sha1, sha2) && mode1 == mode2)
 		return 0;
 
 	/*
@@ -84,135 +45,122 @@ static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const
 		return 0;
 	}
 
-	if (opt->recursive && S_ISDIR(mode1)) {
-		int retval;
-		char *newbase = malloc_base(base, path1, pathlen1);
-		if (opt->tree_in_recursive)
+	strbuf_add(base, path1, pathlen1);
+	if (DIFF_OPT_TST(opt, RECURSIVE) && S_ISDIR(mode1)) {
+		if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE)) {
 			opt->change(opt, mode1, mode2,
-				    sha1, sha2, base, path1);
-		retval = diff_tree_sha1(sha1, sha2, newbase, opt);
-		free(newbase);
-		return retval;
+				    sha1, sha2, base->buf, 0, 0);
+		}
+		strbuf_addch(base, '/');
+		diff_tree_sha1(sha1, sha2, base->buf, opt);
+	} else {
+		opt->change(opt, mode1, mode2, sha1, sha2, base->buf, 0, 0);
 	}
-
-	opt->change(opt, mode1, mode2, sha1, sha2, base, path1);
+	strbuf_setlen(base, old_baselen);
 	return 0;
 }
 
-static int interesting(struct tree_desc *desc, const char *base)
+/* A whole sub-tree went away or appeared */
+static void show_tree(struct diff_options *opt, const char *prefix,
+		      struct tree_desc *desc, struct strbuf *base)
 {
-	const char *path;
-	unsigned mode;
-	int i;
-	int baselen, pathlen;
-
-	if (!nr_paths)
-		return 1;
-
-	(void)tree_entry_extract(desc, &path, &mode);
-
-	pathlen = strlen(path);
-	baselen = strlen(base);
-
-	for (i=0; i < nr_paths; i++) {
-		const char *match = paths[i];
-		int matchlen = pathlens[i];
-
-		if (baselen >= matchlen) {
-			/* If it doesn't match, move along... */
-			if (strncmp(base, match, matchlen))
-				continue;
-
-			/* The base is a subdirectory of a path which was specified. */
-			return 1;
-		}
-
-		/* Does the base match? */
-		if (strncmp(base, match, baselen))
-			continue;
-
-		match += baselen;
-		matchlen -= baselen;
-
-		if (pathlen > matchlen)
-			continue;
-
-		if (matchlen > pathlen) {
-			if (match[pathlen] != '/')
-				continue;
-			if (!S_ISDIR(mode))
+	int match = 0;
+	for (; desc->size; update_tree_entry(desc)) {
+		if (match != 2) {
+			match = tree_entry_interesting(&desc->entry, base, 0,
+						       &opt->pathspec);
+			if (match < 0)
+				break;
+			if (match == 0)
 				continue;
 		}
-
-		if (strncmp(path, match, pathlen))
-			continue;
-
-		return 1;
-	}
-	return 0; /* No matches */
-}
-
-/* A whole sub-tree went away or appeared */
-static void show_tree(struct diff_options *opt, const char *prefix, struct tree_desc *desc, const char *base)
-{
-	while (desc->size) {
-		if (interesting(desc, base))
-			show_entry(opt, prefix, desc, base);
-		update_tree_entry(desc);
+		show_entry(opt, prefix, desc, base);
 	}
 }
 
 /* A file entry went away or appeared */
-static int show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc, const char *base)
+static void show_entry(struct diff_options *opt, const char *prefix,
+		       struct tree_desc *desc, struct strbuf *base)
 {
 	unsigned mode;
 	const char *path;
 	const unsigned char *sha1 = tree_entry_extract(desc, &path, &mode);
+	int pathlen = tree_entry_len(path, sha1);
+	int old_baselen = base->len;
 
-	if (opt->recursive && S_ISDIR(mode)) {
-		char type[20];
-		char *newbase = malloc_base(base, path, strlen(path));
+	strbuf_add(base, path, pathlen);
+	if (DIFF_OPT_TST(opt, RECURSIVE) && S_ISDIR(mode)) {
+		enum object_type type;
 		struct tree_desc inner;
 		void *tree;
+		unsigned long size;
 
-		tree = read_sha1_file(sha1, type, &inner.size);
-		if (!tree || strcmp(type, "tree"))
+		tree = read_sha1_file(sha1, &type, &size);
+		if (!tree || type != OBJ_TREE)
 			die("corrupt tree sha %s", sha1_to_hex(sha1));
 
-		inner.buf = tree;
-		show_tree(opt, prefix, &inner, newbase);
+		if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE))
+			opt->add_remove(opt, *prefix, mode, sha1, base->buf, 0);
 
+		strbuf_addch(base, '/');
+
+		init_tree_desc(&inner, tree, size);
+		show_tree(opt, prefix, &inner, base);
 		free(tree);
-		free(newbase);
-		return 0;
-	}
+	} else
+		opt->add_remove(opt, prefix[0], mode, sha1, base->buf, 0);
 
-	opt->add_remove(opt, prefix[0], mode, sha1, base, path);
-	return 0;
+	strbuf_setlen(base, old_baselen);
 }
 
-int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt)
+static void skip_uninteresting(struct tree_desc *t, struct strbuf *base,
+			       struct diff_options *opt, int *match)
 {
-	while (t1->size | t2->size) {
-		if (nr_paths && t1->size && !interesting(t1, base)) {
-			update_tree_entry(t1);
-			continue;
+	while (t->size) {
+		*match = tree_entry_interesting(&t->entry, base, 0, &opt->pathspec);
+		if (*match) {
+			if (*match < 0)
+				t->size = 0;
+			break;
 		}
-		if (nr_paths && t2->size && !interesting(t2, base)) {
-			update_tree_entry(t2);
-			continue;
+		update_tree_entry(t);
+	}
+}
+
+int diff_tree(struct tree_desc *t1, struct tree_desc *t2,
+	      const char *base_str, struct diff_options *opt)
+{
+	struct strbuf base;
+	int baselen = strlen(base_str);
+	int t1_match = 0, t2_match = 0;
+
+	/* Enable recursion indefinitely */
+	opt->pathspec.recursive = DIFF_OPT_TST(opt, RECURSIVE);
+	opt->pathspec.max_depth = -1;
+
+	strbuf_init(&base, PATH_MAX);
+	strbuf_add(&base, base_str, baselen);
+
+	for (;;) {
+		if (diff_can_quit_early(opt))
+			break;
+		if (opt->pathspec.nr) {
+			skip_uninteresting(t1, &base, opt, &t1_match);
+			skip_uninteresting(t2, &base, opt, &t2_match);
 		}
 		if (!t1->size) {
-			show_entry(opt, "+", t2, base);
+			if (!t2->size)
+				break;
+			show_entry(opt, "+", t2, &base);
 			update_tree_entry(t2);
 			continue;
 		}
 		if (!t2->size) {
-			show_entry(opt, "-", t1, base);
+			show_entry(opt, "-", t1, &base);
 			update_tree_entry(t1);
 			continue;
 		}
-		switch (compare_tree_entry(t1, t2, base, opt)) {
+		switch (compare_tree_entry(t1, t2, &base, opt)) {
 		case -1:
 			update_tree_entry(t1);
 			continue;
@@ -223,52 +171,150 @@ int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, stru
 			update_tree_entry(t2);
 			continue;
 		}
-		die("git-diff-tree: internal error");
+		die("git diff-tree: internal error");
 	}
+
+	strbuf_release(&base);
 	return 0;
 }
 
+/*
+ * Does it look like the resulting diff might be due to a rename?
+ *  - single entry
+ *  - not a valid previous file
+ */
+static inline int diff_might_be_rename(void)
+{
+	return diff_queued_diff.nr == 1 &&
+		!DIFF_FILE_VALID(diff_queued_diff.queue[0]->one);
+}
+
+static void try_to_follow_renames(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt)
+{
+	struct diff_options diff_opts;
+	struct diff_queue_struct *q = &diff_queued_diff;
+	struct diff_filepair *choice;
+	const char *paths[1];
+	int i;
+
+	/* Remove the file creation entry from the diff queue, and remember it */
+	choice = q->queue[0];
+	q->nr = 0;
+
+	diff_setup(&diff_opts);
+	DIFF_OPT_SET(&diff_opts, RECURSIVE);
+	DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER);
+	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
+	diff_opts.single_follow = opt->pathspec.raw[0];
+	diff_opts.break_opt = opt->break_opt;
+	paths[0] = NULL;
+	diff_tree_setup_paths(paths, &diff_opts);
+	if (diff_setup_done(&diff_opts) < 0)
+		die("unable to set up diff options to follow renames");
+	diff_tree(t1, t2, base, &diff_opts);
+	diffcore_std(&diff_opts);
+	diff_tree_release_paths(&diff_opts);
+
+	/* Go through the new set of filepairing, and see if we find a more interesting one */
+	opt->found_follow = 0;
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+
+		/*
+		 * Found a source? Not only do we use that for the new
+		 * diff_queued_diff, we will also use that as the path in
+		 * the future!
+		 */
+		if ((p->status == 'R' || p->status == 'C') &&
+		    !strcmp(p->two->path, opt->pathspec.raw[0])) {
+			/* Switch the file-pairs around */
+			q->queue[i] = choice;
+			choice = p;
+
+			/* Update the path we use from now on.. */
+			diff_tree_release_paths(opt);
+			opt->pathspec.raw[0] = xstrdup(p->one->path);
+			diff_tree_setup_paths(opt->pathspec.raw, opt);
+
+			/*
+			 * The caller expects us to return a set of vanilla
+			 * filepairs to let a later call to diffcore_std()
+			 * it makes to sort the renames out (among other
+			 * things), but we already have found renames
+			 * ourselves; signal diffcore_std() not to muck with
+			 * rename information.
+			 */
+			opt->found_follow = 1;
+			break;
+		}
+	}
+
+	/*
+	 * Then, discard all the non-relevant file pairs...
+	 */
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		diff_free_filepair(p);
+	}
+
+	/*
+	 * .. and re-instate the one we want (which might be either the
+	 * original one, or the rename/copy we found)
+	 */
+	q->queue[0] = choice;
+	q->nr = 1;
+}
+
 int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const char *base, struct diff_options *opt)
 {
 	void *tree1, *tree2;
 	struct tree_desc t1, t2;
+	unsigned long size1, size2;
 	int retval;
 
-	tree1 = read_object_with_reference(old, "tree", &t1.size, NULL);
+	tree1 = read_object_with_reference(old, tree_type, &size1, NULL);
 	if (!tree1)
 		die("unable to read source tree (%s)", sha1_to_hex(old));
-	tree2 = read_object_with_reference(new, "tree", &t2.size, NULL);
+	tree2 = read_object_with_reference(new, tree_type, &size2, NULL);
 	if (!tree2)
 		die("unable to read destination tree (%s)", sha1_to_hex(new));
-	t1.buf = tree1;
-	t2.buf = tree2;
+	init_tree_desc(&t1, tree1, size1);
+	init_tree_desc(&t2, tree2, size2);
 	retval = diff_tree(&t1, &t2, base, opt);
+	if (!*base && DIFF_OPT_TST(opt, FOLLOW_RENAMES) && diff_might_be_rename()) {
+		init_tree_desc(&t1, tree1, size1);
+		init_tree_desc(&t2, tree2, size2);
+		try_to_follow_renames(&t1, &t2, base, opt);
+	}
 	free(tree1);
 	free(tree2);
 	return retval;
 }
 
-static int count_paths(const char **paths)
+int diff_root_tree_sha1(const unsigned char *new, const char *base, struct diff_options *opt)
+{
+	int retval;
+	void *tree;
+	unsigned long size;
+	struct tree_desc empty, real;
+
+	tree = read_object_with_reference(new, tree_type, &size, NULL);
+	if (!tree)
+		die("unable to read root tree (%s)", sha1_to_hex(new));
+	init_tree_desc(&real, tree, size);
+
+	init_tree_desc(&empty, "", 0);
+	retval = diff_tree(&empty, &real, base, opt);
+	free(tree);
+	return retval;
+}
+
+void diff_tree_release_paths(struct diff_options *opt)
 {
-	int i = 0;
-	while (*paths++)
-		i++;
-	return i;
+	free_pathspec(&opt->pathspec);
 }
 
-void diff_tree_setup_paths(const char **p)
+void diff_tree_setup_paths(const char **p, struct diff_options *opt)
 {
-	if (p) {
-		int i;
-
-		paths = p;
-		nr_paths = count_paths(paths);
-		if (nr_paths == 0) {
-			pathlens = NULL;
-			return;
-		}
-		pathlens = xmalloc(nr_paths * sizeof(int));
-		for (i=0; i<nr_paths; i++)
-			pathlens[i] = strlen(paths[i]);
-	}
+	init_pathspec(&opt->pathspec, p);
 }