apply --whitespace=fix: avoid running over the postimage buffer

Originally update-pre-post-images could assume that any whitespace
fixing will make the result only shorter by unexpanding runs of
leading SPs into HTs and removing trailing whitespaces at the end of
lines.  Updating the post-image we read from the patch to match the
actual result can be performed in-place under this assumption.
These days, however, we have tab-in-indent (aka Python) rule whose
result can be longer than the original, and we do need to allocate
a larger buffer than the input and replace the result.

Fortunately the support for lengthening rewrite was already added
when we began supporting "match while ignoring whitespace
differences" mode in 86c91f91794c (git apply: option to ignore
whitespace differences, 2009-08-04).  We only need to correctly
count the number of bytes necessary to hold the updated result and
tell the function to allocate a new buffer.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/builtin/apply.c b/builtin/apply.c
index 156b3ce..df773c7 100644 (file)
--- a/builtin/apply.c
+++ b/builtin/apply.c
@@ -2113,10 +2113,10 @@ static void update_pre_post_images(struct image *preimage,
 
        /*
         * 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.
+        * done in-place when we are shrinking it with whitespace
+        * fixing, but needs a new buffer when ignoring whitespace or
+        * expanding leading tabs to spaces.
+        *
         * We trust the caller to tell us if the update can be done
         * in place (postlen==0) or not.
         */
@@ -2172,7 +2172,7 @@ static int match_fragment(struct image *img,
        int i;
        char *fixed_buf, *buf, *orig, *target;
        struct strbuf fixed;
-       size_t fixed_len;
+       size_t fixed_len, postlen;
        int preimage_limit;
 
        if (preimage->nr + try_lno <= img->nr) {
@@ -2322,6 +2322,7 @@ static int match_fragment(struct image *img,
        strbuf_init(&fixed, preimage->len + 1);
        orig = preimage->buf;
        target = img->buf + try;
+       postlen = 0;
        for (i = 0; i < preimage_limit; i++) {
                size_t oldlen = preimage->line[i].len;
                size_t tgtlen = img->line[try_lno + i].len;
@@ -2349,6 +2350,7 @@ static int match_fragment(struct image *img,
                match = (tgtfix.len == fixed.len - fixstart &&
                         !memcmp(tgtfix.buf, fixed.buf + fixstart,
                                             fixed.len - fixstart));
+               postlen += tgtfix.len;
 
                strbuf_release(&tgtfix);
                if (!match)
@@ -2386,8 +2388,10 @@ static int match_fragment(struct image *img,
         * hunk match.  Update the context lines in the postimage.
         */
        fixed_buf = strbuf_detach(&fixed, &fixed_len);
+       if (postlen < postimage->len)
+               postlen = 0;
        update_pre_post_images(preimage, postimage,
-                              fixed_buf, fixed_len, 0);
+                              fixed_buf, fixed_len, postlen);
        return 1;
 
  unmatch_exit:

diff --git a/t/t4124-apply-ws-rule.sh b/t/t4124-apply-ws-rule.sh
index 6f6ee88..0bbcf06 100755 (executable)
--- a/t/t4124-apply-ws-rule.sh
+++ b/t/t4124-apply-ws-rule.sh
@@ -486,4 +486,30 @@ test_expect_success 'same, but with CR-LF line endings && cr-at-eol unset' '
        test_cmp one expect
 '
 
+test_expect_success 'whitespace=fix to expand' '
+       qz_to_tab_space >preimage <<-\EOF &&
+       QQa
+       QQb
+       QQc
+       ZZZZZZZZZZZZZZZZd
+       QQe
+       QQf
+       QQg
+       EOF
+       qz_to_tab_space >patch <<-\EOF &&
+       diff --git a/preimage b/preimage
+       --- a/preimage
+       +++ b/preimage
+       @@ -1,7 +1,6 @@
+        QQa
+        QQb
+        QQc
+       -QQd
+        QQe
+        QQf
+        QQg
+       EOF
+       git -c core.whitespace=tab-in-indent apply --whitespace=fix patch
+'
+
 test_done

diff --git a/t/t4150-am.sh b/t/t4150-am.sh
index cdafd7e..12f6b02 100755 (executable)
--- a/t/t4150-am.sh
+++ b/t/t4150-am.sh
@@ -17,7 +17,7 @@ test_expect_success 'setup: messages' '
        vero eos et accusam et justo duo dolores et ea rebum.
 
        EOF
-       q_to_tab <<-\EOF >>msg &&
+       qz_to_tab_space <<-\EOF >>msg &&
        QDuis autem vel eum iriure dolor in hendrerit in vulputate velit
        Qesse molestie consequat, vel illum dolore eu feugiat nulla facilisis
        Qat vero eros et accumsan et iusto odio dignissim qui blandit

diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh
index 8889ba5..dc070f8 100644 (file)
--- a/t/test-lib-functions.sh
+++ b/t/test-lib-functions.sh
@@ -87,8 +87,8 @@ q_to_cr () {
        tr Q '\015'
 }
 
-q_to_tab () {
-       tr Q '\011'
+qz_to_tab_space () {
+       tr QZ '\011\040'
 }
 
 append_cr () {