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;
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)
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);
}
}
+/*
+ * 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;
*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;
!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;
* 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:
{
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);
}
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)
{
{ 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,
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);
--- /dev/null
+#!/bin/sh
+#
+# Copyright (c) 2009 Giuseppe Bilotta
+#
+
+test_description='git-apply --ignore-whitespace.
+
+'
+. ./test-lib.sh
+
+# This primes main.c file that indents without using HT at all.
+# Various patches with HT and other spaces are attempted in the test.
+
+cat > patch1.patch <<\EOF
+diff --git a/main.c b/main.c
+new file mode 100644
+--- /dev/null
++++ b/main.c
+@@ -0,0 +1,22 @@
++#include <stdio.h>
++
++void print_int(int num);
++int func(int num);
++
++int main() {
++ int i;
++
++ for (i = 0; i < 10; i++) {
++ print_int(func(i)); /* stuff */
++ }
++
++ return 0;
++}
++
++int func(int num) {
++ return num * num;
++}
++
++void print_int(int num) {
++ printf("%d", num);
++}
+EOF
+
+# Since whitespace is very significant and we want to prevent whitespace
+# mangling when creating this test from a patch, we protect 'fixable'
+# whitespace by replacing spaces with Z and replacing them at patch
+# creation time, hence the sed trick.
+
+# This patch will fail unless whitespace differences are being ignored
+
+sed -e 's/Z/ /g' > patch2.patch <<\EOF
+diff --git a/main.c b/main.c
+--- a/main.c
++++ b/main.c
+@@ -10,6 +10,8 @@
+Z print_int(func(i)); /* stuff */
+Z }
+Z
++ printf("\n");
++
+Z return 0;
+Z}
+Z
+EOF
+
+# This patch will fail even if whitespace differences are being ignored,
+# because of the missing string at EOL. TODO: this testcase should be
+# improved by creating a line that has the same hash with and without
+# the final string.
+
+sed -e 's/Z/ /g' > patch3.patch <<\EOF
+diff --git a/main.c b/main.c
+--- a/main.c
++++ b/main.c
+@@ -10,3 +10,4 @@
+Z for (i = 0; i < 10; i++) {
+Z print_int(func(i));Z
++ /* stuff */
+Z }
+EOF
+
+# This patch will fail even if whitespace differences are being ignored,
+# because of the missing EOL at EOF.
+
+sed -e 's/Z/ /g' > patch4.patch <<\EOF
+diff --git a/main.c b/main.c
+--- a/main.c
++++ b/main.c
+@@ -21,1 +21,1 @@
+- };Z
+\ No newline at end of file
++ };
+EOF
+
+# This patch will fail unless whitespace differences are being ignored.
+
+sed -e 's/Z/ /g' > patch5.patch <<\EOF
+diff --git a/main.c b/main.c
+--- a/main.c
++++ b/main.c
+@@ -2,2 +2,3 @@
+Z void print_int(int num);
++ /* a comment */
+Z int func(int num);
+EOF
+
+# And this is how the final output should be. Patches introduce
+# HTs but the original SP indents are mostly kept.
+
+sed -e 's/T/ /g' > main.c.final <<\EOF
+#include <stdio.h>
+
+void print_int(int num);
+T/* a comment */
+int func(int num);
+
+int main() {
+ int i;
+
+ for (i = 0; i < 10; i++) {
+ print_int(func(i)); /* stuff */
+ }
+
+Tprintf("\n");
+
+ return 0;
+}
+
+int func(int num) {
+ return num * num;
+}
+
+void print_int(int num) {
+ printf("%d", num);
+}
+EOF
+
+test_expect_success 'file creation' '
+ git-apply patch1.patch
+'
+
+test_expect_success 'patch2 fails (retab)' '
+ test_must_fail git-apply patch2.patch
+'
+
+test_expect_success 'patch2 applies with --ignore-whitespace' '
+ git-apply --ignore-whitespace patch2.patch
+'
+
+test_expect_success 'patch2 reverse applies with --ignore-space-change' '
+ git-apply -R --ignore-space-change patch2.patch
+'
+
+git config apply.ignorewhitespace change
+
+test_expect_success 'patch2 applies (apply.ignorewhitespace = change)' '
+ git-apply patch2.patch
+'
+
+test_expect_success 'patch3 fails (missing string at EOL)' '
+ test_must_fail git-apply patch3.patch
+'
+
+test_expect_success 'patch4 fails (missing EOL at EOF)' '
+ test_must_fail git-apply patch4.patch
+'
+
+test_expect_success 'patch5 applies (leading whitespace)' '
+ git-apply patch5.patch
+'
+
+test_expect_success 'patches do not mangle whitespace' '
+ test_cmp main.c main.c.final
+'
+
+test_expect_success 're-create file (with --ignore-whitespace)' '
+ rm -f main.c &&
+ git-apply patch1.patch
+'
+
+test_expect_success 'patch5 fails (--no-ignore-whitespace)' '
+ test_must_fail git-apply --no-ignore-whitespace patch5.patch
+'
+
+test_done