git apply: option to ignore whitespace differences

Introduce --ignore-whitespace option and corresponding config bool to
ignore whitespace differences while applying patches, akin to the
'patch' program.

'git am', 'git rebase' and the bash git completion are made aware of
this option.

Signed-off-by: Giuseppe Bilotta <giuseppe.bilotta@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 166 insertions, 7 deletions

diff --git a/builtin-apply.c b/builtin-apply.c
index dc0ff5e08a..d9303578b6 100644
--- a/builtin-apply.c
+++ b/builtin-apply.c
@@ -61,6 +61,13 @@ static enum ws_error_action {
 static int whitespace_error;
 static int squelch_whitespace_errors = 5;
 static int applied_after_fixing_ws;
+
+static enum ws_ignore {
+	ignore_ws_none,
+	ignore_ws_change,
+} ws_ignore_action = ignore_ws_none;
+
+
 static const char *patch_input_file;
 static const char *root;
 static int root_len;
@@ -97,6 +104,21 @@ static void parse_whitespace_option(const char *option)
 	die("unrecognized whitespace option '%s'", option);
 }
 
+static void parse_ignorewhitespace_option(const char *option)
+{
+	if (!option || !strcmp(option, "no") ||
+	    !strcmp(option, "false") || !strcmp(option, "never") ||
+	    !strcmp(option, "none")) {
+		ws_ignore_action = ignore_ws_none;
+		return;
+	}
+	if (!strcmp(option, "change")) {
+		ws_ignore_action = ignore_ws_change;
+		return;
+	}
+	die("unrecognized whitespace ignore option '%s'", option);
+}
+
 static void set_default_whitespace_mode(const char *whitespace_option)
 {
 	if (!whitespace_option && !apply_default_whitespace)
@@ -214,6 +236,62 @@ static uint32_t hash_line(const char *cp, size_t len)
 	return h;
 }
 
+/*
+ * Compare lines s1 of length n1 and s2 of length n2, ignoring
+ * whitespace difference. Returns 1 if they match, 0 otherwise
+ */
+static int fuzzy_matchlines(const char *s1, size_t n1,
+			    const char *s2, size_t n2)
+{
+	const char *last1 = s1 + n1 - 1;
+	const char *last2 = s2 + n2 - 1;
+	int result = 0;
+
+	if (n1 < 0 || n2 < 0)
+		return 0;
+
+	/* ignore line endings */
+	while ((*last1 == '\r') || (*last1 == '\n'))
+		last1--;
+	while ((*last2 == '\r') || (*last2 == '\n'))
+		last2--;
+
+	/* skip leading whitespace */
+	while (isspace(*s1) && (s1 <= last1))
+		s1++;
+	while (isspace(*s2) && (s2 <= last2))
+		s2++;
+	/* early return if both lines are empty */
+	if ((s1 > last1) && (s2 > last2))
+		return 1;
+	while (!result) {
+		result = *s1++ - *s2++;
+		/*
+		 * Skip whitespace inside. We check for whitespace on
+		 * both buffers because we don't want "a b" to match
+		 * "ab"
+		 */
+		if (isspace(*s1) && isspace(*s2)) {
+			while (isspace(*s1) && s1 <= last1)
+				s1++;
+			while (isspace(*s2) && s2 <= last2)
+				s2++;
+		}
+		/*
+		 * If we reached the end on one side only,
+		 * lines don't match
+		 */
+		if (
+		    ((s2 > last2) && (s1 <= last1)) ||
+		    ((s1 > last1) && (s2 <= last2)))
+			return 0;
+		if ((s1 > last1) && (s2 > last2))
+			break;
+	}
+
+	return !result;
+}
+
 static void add_line_info(struct image *img, const char *bol, size_t len, unsigned flag)
 {
 	ALLOC_GROW(img->line_allocated, img->nr + 1, img->alloc);
@@ -1592,10 +1670,17 @@ static int read_old_data(struct stat *st, const char *path, struct strbuf *buf)
 	}
 }
 
+/*
+ * Update the preimage, and the common lines in postimage,
+ * from buffer buf of length len. If postlen is 0 the postimage
+ * is updated in place, otherwise it's updated on a new buffer
+ * of length postlen
+ */
+
 static void update_pre_post_images(struct image *preimage,
 				   struct image *postimage,
 				   char *buf,
-				   size_t len)
+				   size_t len, size_t postlen)
 {
 	int i, ctx;
 	char *new, *old, *fixed;
@@ -1614,11 +1699,19 @@ static void update_pre_post_images(struct image *preimage,
 	*preimage = fixed_preimage;
 
 	/*
-	 * Adjust the common context lines in postimage, in place.
-	 * This is possible because whitespace fixing does not make
-	 * the string grow.
+	 * Adjust the common context lines in postimage. This can be
+	 * done in-place when we are just doing whitespace fixing,
+	 * which does not make the string grow, but needs a new buffer
+	 * when ignoring whitespace causes the update, since in this case
+	 * we could have e.g. tabs converted to multiple spaces.
+	 * We trust the caller to tell us if the update can be done
+	 * in place (postlen==0) or not.
 	 */
-	new = old = postimage->buf;
+	old = postimage->buf;
+	if (postlen)
+		new = postimage->buf = xmalloc(postlen);
+	else
+		new = old;
 	fixed = preimage->buf;
 	for (i = ctx = 0; i < postimage->nr; i++) {
 		size_t len = postimage->line[i].len;
@@ -1693,12 +1786,58 @@ static int match_fragment(struct image *img,
 	    !memcmp(img->buf + try, preimage->buf, preimage->len))
 		return 1;
 
+	/*
+	 * No exact match. If we are ignoring whitespace, run a line-by-line
+	 * fuzzy matching. We collect all the line length information because
+	 * we need it to adjust whitespace if we match.
+	 */
+	if (ws_ignore_action == ignore_ws_change) {
+		size_t imgoff = 0;
+		size_t preoff = 0;
+		size_t postlen = postimage->len;
+		size_t imglen[preimage->nr];
+		for (i = 0; i < preimage->nr; i++) {
+			size_t prelen = preimage->line[i].len;
+
+			imglen[i] = img->line[try_lno+i].len;
+			if (!fuzzy_matchlines(
+				img->buf + try + imgoff, imglen[i],
+				preimage->buf + preoff, prelen))
+				return 0;
+			if (preimage->line[i].flag & LINE_COMMON)
+				postlen += imglen[i] - prelen;
+			imgoff += imglen[i];
+			preoff += prelen;
+		}
+
+		/*
+		 * Ok, the preimage matches with whitespace fuzz. Update it and
+		 * the common postimage lines to use the same whitespace as the
+		 * target. imgoff now holds the true length of the target that
+		 * matches the preimage, and we need to update the line lengths
+		 * of the preimage to match the target ones.
+		 */
+		fixed_buf = xmalloc(imgoff);
+		memcpy(fixed_buf, img->buf + try, imgoff);
+		for (i = 0; i < preimage->nr; i++)
+			preimage->line[i].len = imglen[i];
+
+		/*
+		 * Update the preimage buffer and the postimage context lines.
+		 */
+		update_pre_post_images(preimage, postimage,
+				fixed_buf, imgoff, postlen);
+		return 1;
+	}
+
 	if (ws_error_action != correct_ws_error)
 		return 0;
 
 	/*
 	 * The hunk does not apply byte-by-byte, but the hash says
-	 * it might with whitespace fuzz.
+	 * it might with whitespace fuzz. We haven't been asked to
+	 * ignore whitespace, we were asked to correct whitespace
+	 * errors, so let's try matching after whitespace correction.
 	 */
 	fixed_buf = xmalloc(preimage->len + 1);
 	buf = fixed_buf;
@@ -1750,7 +1889,7 @@ static int match_fragment(struct image *img,
 	 * hunk match.  Update the context lines in the postimage.
 	 */
 	update_pre_post_images(preimage, postimage,
-			       fixed_buf, buf - fixed_buf);
+			       fixed_buf, buf - fixed_buf, 0);
 	return 1;
 
  unmatch_exit:
@@ -3192,6 +3331,8 @@ static int git_apply_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "apply.whitespace"))
 		return git_config_string(&apply_default_whitespace, var, value);
+	else if (!strcmp(var, "apply.ignorewhitespace"))
+		return git_config_string(&apply_default_ignorewhitespace, var, value);
 	return git_default_config(var, value, cb);
 }
 
@@ -3228,6 +3369,16 @@ static int option_parse_z(const struct option *opt,
 	return 0;
 }
 
+static int option_parse_space_change(const struct option *opt,
+			  const char *arg, int unset)
+{
+	if (unset)
+		ws_ignore_action = ignore_ws_none;
+	else
+		ws_ignore_action = ignore_ws_change;
+	return 0;
+}
+
 static int option_parse_whitespace(const struct option *opt,
 				   const char *arg, int unset)
 {
@@ -3304,6 +3455,12 @@ int cmd_apply(int argc, const char **argv, const char *unused_prefix)
 		{ OPTION_CALLBACK, 0, "whitespace", &whitespace_option, "action",
 			"detect new or modified lines that have whitespace errors",
 			0, option_parse_whitespace },
+		{ OPTION_CALLBACK, 0, "ignore-space-change", NULL, NULL,
+			"ignore changes in whitespace when finding context",
+			PARSE_OPT_NOARG, option_parse_space_change },
+		{ OPTION_CALLBACK, 0, "ignore-whitespace", NULL, NULL,
+			"ignore changes in whitespace when finding context",
+			PARSE_OPT_NOARG, option_parse_space_change },
 		OPT_BOOLEAN('R', "reverse", &apply_in_reverse,
 			"apply the patch in reverse"),
 		OPT_BOOLEAN(0, "unidiff-zero", &unidiff_zero,
@@ -3328,6 +3485,8 @@ int cmd_apply(int argc, const char **argv, const char *unused_prefix)
 	git_config(git_apply_config, NULL);
 	if (apply_default_whitespace)
 		parse_whitespace_option(apply_default_whitespace);
+	if (apply_default_ignorewhitespace)
+		parse_ignorewhitespace_option(apply_default_ignorewhitespace);
 
 	argc = parse_options(argc, argv, prefix, builtin_apply_options,
 			apply_usage, 0);