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

1 files changed, 73 insertions, 46 deletions

diff --git a/diff.c b/diff.c
index e40c1271da..e49f14a924 100644
--- a/diff.c
+++ b/diff.c
@@ -44,7 +44,8 @@ static char diff_colors[][COLOR_MAXLEN] = {
 };
 
 static void diff_filespec_load_driver(struct diff_filespec *one);
-static char *run_textconv(const char *, struct diff_filespec *, size_t *);
+static size_t fill_textconv(struct userdiff_driver *driver,
+			    struct diff_filespec *df, char **outbuf);
 
 static int parse_diff_color_slot(const char *var, int ofs)
 {
@@ -466,8 +467,8 @@ static void emit_rewrite_diff(const char *name_a,
 			      const char *name_b,
 			      struct diff_filespec *one,
 			      struct diff_filespec *two,
-			      const char *textconv_one,
-			      const char *textconv_two,
+			      struct userdiff_driver *textconv_one,
+			      struct userdiff_driver *textconv_two,
 			      struct diff_options *o)
 {
 	int lc_a, lc_b;
@@ -478,7 +479,7 @@ static void emit_rewrite_diff(const char *name_a,
 	const char *reset = diff_get_color(color_diff, DIFF_RESET);
 	static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
 	const char *a_prefix, *b_prefix;
-	const char *data_one, *data_two;
+	char *data_one, *data_two;
 	size_t size_one, size_two;
 	struct emit_callback ecbdata;
 
@@ -500,26 +501,8 @@ static void emit_rewrite_diff(const char *name_a,
 	quote_two_c_style(&a_name, a_prefix, name_a, 0);
 	quote_two_c_style(&b_name, b_prefix, name_b, 0);
 
-	diff_populate_filespec(one, 0);
-	diff_populate_filespec(two, 0);
-	if (textconv_one) {
-		data_one = run_textconv(textconv_one, one, &size_one);
-		if (!data_one)
-			die("unable to read files to diff");
-	}
-	else {
-		data_one = one->data;
-		size_one = one->size;
-	}
-	if (textconv_two) {
-		data_two = run_textconv(textconv_two, two, &size_two);
-		if (!data_two)
-			die("unable to read files to diff");
-	}
-	else {
-		data_two = two->data;
-		size_two = two->size;
-	}
+	size_one = fill_textconv(textconv_one, one, &data_one);
+	size_two = fill_textconv(textconv_two, two, &data_two);
 
 	memset(&ecbdata, 0, sizeof(ecbdata));
 	ecbdata.color_diff = color_diff;
@@ -1585,14 +1568,26 @@ void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const
 		options->b_prefix = b;
 }
 
-static const char *get_textconv(struct diff_filespec *one)
+static struct userdiff_driver *get_textconv(struct diff_filespec *one)
 {
 	if (!DIFF_FILE_VALID(one))
 		return NULL;
 	if (!S_ISREG(one->mode))
 		return NULL;
 	diff_filespec_load_driver(one);
-	return one->driver->textconv;
+	if (!one->driver->textconv)
+		return NULL;
+
+	if (one->driver->textconv_want_cache && !one->driver->textconv_cache) {
+		struct notes_cache *c = xmalloc(sizeof(*c));
+		struct strbuf name = STRBUF_INIT;
+
+		strbuf_addf(&name, "textconv/%s", one->driver->name);
+		notes_cache_init(c, name.buf, one->driver->textconv);
+		one->driver->textconv_cache = c;
+	}
+
+	return one->driver;
 }
 
 static void builtin_diff(const char *name_a,
@@ -1609,7 +1604,8 @@ static void builtin_diff(const char *name_a,
 	const char *set = diff_get_color_opt(o, DIFF_METAINFO);
 	const char *reset = diff_get_color_opt(o, DIFF_RESET);
 	const char *a_prefix, *b_prefix;
-	const char *textconv_one = NULL, *textconv_two = NULL;
+	struct userdiff_driver *textconv_one = NULL;
+	struct userdiff_driver *textconv_two = NULL;
 	struct strbuf header = STRBUF_INIT;
 
 	if (DIFF_OPT_TST(o, SUBMODULE_LOG) &&
@@ -1683,12 +1679,11 @@ 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 (!DIFF_OPT_TST(o, TEXT) &&
-	    ( (diff_filespec_is_binary(one) && !textconv_one) ||
-	      (diff_filespec_is_binary(two) && !textconv_two) )) {
+	    ( (!textconv_one && diff_filespec_is_binary(one)) ||
+	      (!textconv_two && diff_filespec_is_binary(two)) )) {
+		if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
+			die("unable to read files to diff");
 		/* Quite common confusing case */
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size))
@@ -1715,20 +1710,8 @@ static void builtin_diff(const char *name_a,
 			strbuf_reset(&header);
 		}
 
-		if (textconv_one) {
-			size_t size;
-			mf1.ptr = run_textconv(textconv_one, one, &size);
-			if (!mf1.ptr)
-				die("unable to read files to diff");
-			mf1.size = size;
-		}
-		if (textconv_two) {
-			size_t size;
-			mf2.ptr = run_textconv(textconv_two, two, &size);
-			if (!mf2.ptr)
-				die("unable to read files to diff");
-			mf2.size = size;
-		}
+		mf1.size = fill_textconv(textconv_one, one, &mf1.ptr);
+		mf2.size = fill_textconv(textconv_two, two, &mf2.ptr);
 
 		pe = diff_funcname_pattern(one);
 		if (!pe)
@@ -3912,3 +3895,47 @@ static char *run_textconv(const char *pgm, struct diff_filespec *spec,
 
 	return strbuf_detach(&buf, outsize);
 }
+
+static size_t fill_textconv(struct userdiff_driver *driver,
+			    struct diff_filespec *df,
+			    char **outbuf)
+{
+	size_t size;
+
+	if (!driver || !driver->textconv) {
+		if (!DIFF_FILE_VALID(df)) {
+			*outbuf = "";
+			return 0;
+		}
+		if (diff_populate_filespec(df, 0))
+			die("unable to read files to diff");
+		*outbuf = df->data;
+		return df->size;
+	}
+
+	if (driver->textconv_cache) {
+		*outbuf = notes_cache_get(driver->textconv_cache, df->sha1,
+					  &size);
+		if (*outbuf)
+			return size;
+	}
+
+	*outbuf = run_textconv(driver->textconv, df, &size);
+	if (!*outbuf)
+		die("unable to read files to diff");
+
+	if (driver->textconv_cache) {
+		/* ignore errors, as we might be in a readonly repository */
+		notes_cache_put(driver->textconv_cache, df->sha1, *outbuf,
+				size);
+		/*
+		 * we could save up changes and flush them all at the end,
+		 * but we would need an extra call after all diffing is done.
+		 * Since generating a cache entry is the slow path anyway,
+		 * this extra overhead probably isn't a big deal.
+		 */
+		notes_cache_write(driver->textconv_cache);
+	}
+
+	return size;
+}