Merge branch 'jk/cached-textconv'

* jk/cached-textconv:
  diff: avoid useless filespec population
  diff: cache textconv output
  textconv: refactor calls to run_textconv
  introduce notes-cache interface
  make commit_tree a library function

Author: gitster

Documentation/gitattributes.txt

@@ -414,6 +414,26 @@ because it quickly conveys the changes you have made), you
 should generate it separately and send it as a comment _in
 addition to_ the usual binary diff that you might send.
 
+Because text conversion can be slow, especially when doing a
+large number of them with `git log -p`, git provides a mechanism
+to cache the output and use it in future diffs.  To enable
+caching, set the "cachetextconv" variable in your diff driver's
+config. For example:
+
+------------------------
+[diff "jpg"]
+	textconv = exif
+	cachetextconv = true
+------------------------
+
+This will cache the result of running "exif" on each blob
+indefinitely. If you change the textconv config variable for a
+diff driver, git will automatically invalidate the cache entries
+and re-run the textconv filter. If you want to invalidate the
+cache manually (e.g., because your version of "exif" was updated
+and now produces better output), you can remove the cache
+manually with `git update-ref -d refs/notes/textconv/jpg` (where
+"jpg" is the name of the diff driver, as in the example above).
 
 Performing a three-way merge
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Makefile

@@ -486,6 +486,7 @@ LIB_H += log-tree.h
 LIB_H += mailmap.h
 LIB_H += merge-recursive.h
 LIB_H += notes.h
+LIB_H += notes-cache.h
 LIB_H += object.h
 LIB_H += pack.h
 LIB_H += pack-refs.h
@@ -575,6 +576,7 @@ LIB_OBJS += merge-file.o
 LIB_OBJS += merge-recursive.o
 LIB_OBJS += name-hash.o
 LIB_OBJS += notes.o
+LIB_OBJS += notes-cache.o
 LIB_OBJS += object.o
 LIB_OBJS += pack-check.o
 LIB_OBJS += pack-refs.o

builtin.h

@@ -16,9 +16,6 @@ extern const char *help_unknown_cmd(const char *cmd);
 extern void prune_packed_objects(int);
 extern int fmt_merge_msg(int merge_summary, struct strbuf *in,
 	struct strbuf *out);
-extern int commit_tree(const char *msg, unsigned char *tree,
-		struct commit_list *parents, unsigned char *ret,
-		const char *author);
 extern int commit_notes(struct notes_tree *t, const char *msg);
 
 struct notes_rewrite_cfg {

builtin/commit-tree.c

@@ -9,19 +9,6 @@
 #include "builtin.h"
 #include "utf8.h"
 
-/*
- * FIXME! Share the code with "write-tree.c"
- */
-static void check_valid(unsigned char *sha1, enum object_type expect)
-{
-	enum object_type type = sha1_object_info(sha1, NULL);
-	if (type < 0)
-		die("%s is not a valid object", sha1_to_hex(sha1));
-	if (type != expect)
-		die("%s is not a valid '%s' object", sha1_to_hex(sha1),
-		    typename(expect));
-}
-
 static const char commit_tree_usage[] = "git commit-tree <sha1> [-p <sha1>]* < changelog";
 
 static void new_parent(struct commit *parent, struct commit_list **parents_p)
@@ -38,61 +25,6 @@ static void new_parent(struct commit *parent, struct commit_list **parents_p)
 	commit_list_insert(parent, parents_p);
 }
 
-static const char commit_utf8_warn[] =
-"Warning: commit message does not conform to UTF-8.\n"
-"You may want to amend it after fixing the message, or set the config\n"
-"variable i18n.commitencoding to the encoding your project uses.\n";
-
-int commit_tree(const char *msg, unsigned char *tree,
-		struct commit_list *parents, unsigned char *ret,
-		const char *author)
-{
-	int result;
-	int encoding_is_utf8;
-	struct strbuf buffer;
-
-	check_valid(tree, OBJ_TREE);
-
-	/* Not having i18n.commitencoding is the same as having utf-8 */
-	encoding_is_utf8 = is_encoding_utf8(git_commit_encoding);
-
-	strbuf_init(&buffer, 8192); /* should avoid reallocs for the headers */
-	strbuf_addf(&buffer, "tree %s\n", sha1_to_hex(tree));
-
-	/*
-	 * NOTE! This ordering means that the same exact tree merged with a
-	 * different order of parents will be a _different_ changeset even
-	 * if everything else stays the same.
-	 */
-	while (parents) {
-		struct commit_list *next = parents->next;
-		strbuf_addf(&buffer, "parent %s\n",
-			sha1_to_hex(parents->item->object.sha1));
-		free(parents);
-		parents = next;
-	}
-
-	/* Person/date information */
-	if (!author)
-		author = git_author_info(IDENT_ERROR_ON_NO_NAME);
-	strbuf_addf(&buffer, "author %s\n", author);
-	strbuf_addf(&buffer, "committer %s\n", git_committer_info(IDENT_ERROR_ON_NO_NAME));
-	if (!encoding_is_utf8)
-		strbuf_addf(&buffer, "encoding %s\n", git_commit_encoding);
-	strbuf_addch(&buffer, '\n');
-
-	/* And add the comment */
-	strbuf_addstr(&buffer, msg);
-
-	/* And check the encoding */
-	if (encoding_is_utf8 && !is_utf8(buffer.buf))
-		fprintf(stderr, commit_utf8_warn);
-
-	result = write_sha1_file(buffer.buf, buffer.len, commit_type, ret);
-	strbuf_release(&buffer);
-	return result;
-}
-
 int cmd_commit_tree(int argc, const char **argv, const char *prefix)
 {
 	int i;
@@ -117,7 +49,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix)
 
 		if (get_sha1(b, sha1))
 			die("Not a valid object name %s", b);
-		check_valid(sha1, OBJ_COMMIT);
+		assert_sha1_type(sha1, OBJ_COMMIT);
 		new_parent(lookup_commit(sha1), &parents);
 	}
 

cache.h

@@ -718,6 +718,8 @@ extern int has_loose_object_nonlocal(const unsigned char *sha1);
 
 extern int has_pack_index(const unsigned char *sha1);
 
+extern void assert_sha1_type(const unsigned char *sha1, enum object_type expect);
+
 extern const signed char hexval_table[256];
 static inline unsigned int hexval(unsigned char c)
 {

commit.c

@@ -790,3 +790,58 @@ struct commit_list *reduce_heads(struct commit_list *heads)
 	free(other);
 	return result;
 }
+
+static const char commit_utf8_warn[] =
+"Warning: commit message does not conform to UTF-8.\n"
+"You may want to amend it after fixing the message, or set the config\n"
+"variable i18n.commitencoding to the encoding your project uses.\n";
+
+int commit_tree(const char *msg, unsigned char *tree,
+		struct commit_list *parents, unsigned char *ret,
+		const char *author)
+{
+	int result;
+	int encoding_is_utf8;
+	struct strbuf buffer;
+
+	assert_sha1_type(tree, OBJ_TREE);
+
+	/* Not having i18n.commitencoding is the same as having utf-8 */
+	encoding_is_utf8 = is_encoding_utf8(git_commit_encoding);
+
+	strbuf_init(&buffer, 8192); /* should avoid reallocs for the headers */
+	strbuf_addf(&buffer, "tree %s\n", sha1_to_hex(tree));
+
+	/*
+	 * NOTE! This ordering means that the same exact tree merged with a
+	 * different order of parents will be a _different_ changeset even
+	 * if everything else stays the same.
+	 */
+	while (parents) {
+		struct commit_list *next = parents->next;
+		strbuf_addf(&buffer, "parent %s\n",
+			sha1_to_hex(parents->item->object.sha1));
+		free(parents);
+		parents = next;
+	}
+
+	/* Person/date information */
+	if (!author)
+		author = git_author_info(IDENT_ERROR_ON_NO_NAME);
+	strbuf_addf(&buffer, "author %s\n", author);
+	strbuf_addf(&buffer, "committer %s\n", git_committer_info(IDENT_ERROR_ON_NO_NAME));
+	if (!encoding_is_utf8)
+		strbuf_addf(&buffer, "encoding %s\n", git_commit_encoding);
+	strbuf_addch(&buffer, '\n');
+
+	/* And add the comment */
+	strbuf_addstr(&buffer, msg);
+
+	/* And check the encoding */
+	if (encoding_is_utf8 && !is_utf8(buffer.buf))
+		fprintf(stderr, commit_utf8_warn);
+
+	result = write_sha1_file(buffer.buf, buffer.len, commit_type, ret);
+	strbuf_release(&buffer);
+	return result;
+}

commit.h

@@ -163,4 +163,8 @@ static inline int single_parent(struct commit *commit)
 
 struct commit_list *reduce_heads(struct commit_list *heads);
 
+extern int commit_tree(const char *msg, unsigned char *tree,
+		struct commit_list *parents, unsigned char *ret,
+		const char *author);
+
 #endif /* COMMIT_H */