Thell Fowler <git@xxxxxxxxxxxxx> writes:
>> Or we can just move the final else clause up and start the function like
>> this:
>>
>> int i1, i2;
>>
>> if (!(flags & XDF_WHITESPACE_FLAGS))
>> return s1 == s2 && !memcmp(l1, l2, s1);
>>
>> i1 = i2 = 0;
>> if (flags & XDF_IGNORE_WHITESPACE) {
>> ...
>>
>> that would get rid of two unnecessary clearing of variables (i1 and i2,
>> even though I suspect that the compiler _could_ optimize them out without
>> such an change), and three flags-bit check in the most common case of not
>> ignoring any whitespaces.
>>
>
> HA! That's a nifty way to do that with the variables.
My tentative draft to replace the "how about this" patch further reworks
the loop structure and currently looks like this.
It adds net 15 lines but among that 12 lines are comments, which is not so
bad.
-- >8 --
Subject: [PATCH] xutils: Fix xdl_recmatch() on incomplete lines
Thell Fowler noticed that various "ignore whitespace" options to git diff
do not work well on an incomplete line.
The loop control of the function responsible for these bugs was extremely
difficult to follow. This patch restructures the loops for three variants
of "ignore whitespace" logic.
The basic idea of the re-written logic is:
- A loop runs while the characters from both strings we are looking at
match. We declare unmatch immediately when we find something that does
not match and return false from the function. We break out of the loop
if we ran out of either side of the string.
The way we skip spaces inside this loop varies depending on the style
of ignoring whitespaces.
- After the above loop breaks, we know that the parts of the strings we
inspected so far match, ignoring the whitespaces. The lines can match
only if the remainder consists of nothing but whitespaces. This part
of the logic is shared across all three styles.
The new code is more obvious and should be much easier to follow.
Tested-by: Thell Fowler <git@xxxxxxxxxxxxx>
Signed-off-by: Junio C Hamano <gitster@xxxxxxxxx>
---
xdiff/xutils.c | 77 +++++++++++++++++++++++++++++++++----------------------
1 files changed, 46 insertions(+), 31 deletions(-)
diff --git a/xdiff/xutils.c b/xdiff/xutils.c
index 9411fa9..eb7b597 100644
--- a/xdiff/xutils.c
+++ b/xdiff/xutils.c
@@ -190,48 +190,63 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
{
int i1, i2;
+ if (!(flags & XDF_WHITESPACE_FLAGS))
+ return s1 == s2 && !memcmp(l1, l2, s1);
+
+ i1 = 0;
+ i2 = 0;
+
+ /*
+ * -w matches everything that matches with -b, and -b in turn
+ * matches everything that matches with --ignore-space-at-eol.
+ *
+ * Each flavor of ignoring needs different logic to skip whitespaces
+ * while we have both sides to compare.
+ */
if (flags & XDF_IGNORE_WHITESPACE) {
- for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) {
- if (isspace(l1[i1]))
- while (isspace(l1[i1]) && i1 < s1)
- i1++;
- if (isspace(l2[i2]))
- while (isspace(l2[i2]) && i2 < s2)
- i2++;
- if (i1 < s1 && i2 < s2 && l1[i1++] != l2[i2++])
+ goto skip_ws;
+ while (i1 < s1 && i2 < s2) {
+ if (l1[i1++] != l2[i2++])
return 0;
+ skip_ws:
+ while (i1 < s1 && isspace(l1[i1]))
+ i1++;
+ while (i2 < s2 && isspace(l2[i2]))
+ i2++;
}
- return (i1 >= s1 && i2 >= s2);
} else if (flags & XDF_IGNORE_WHITESPACE_CHANGE) {
- for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) {
- if (isspace(l1[i1])) {
- if (!isspace(l2[i2]))
- return 0;
- while (isspace(l1[i1]) && i1 < s1)
- i1++;
- while (isspace(l2[i2]) && i2 < s2)
- i2++;
- } else if (l1[i1++] != l2[i2++])
- return 0;
- }
- return (i1 >= s1 && i2 >= s2);
- } else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL) {
- for (i1 = i2 = 0; i1 < s1 && i2 < s2; ) {
- if (l1[i1] != l2[i2]) {
+ while (i1 < s1 && i2 < s2) {
+ if (isspace(l1[i1]) && isspace(l2[i2])) {
+ /* Skip matching spaces and try again */
while (i1 < s1 && isspace(l1[i1]))
i1++;
while (i2 < s2 && isspace(l2[i2]))
i2++;
- if (i1 < s1 || i2 < s2)
- return 0;
- return 1;
+ continue;
}
+ if (l1[i1++] != l2[i2++])
+ return 0;
+ }
+ } else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL) {
+ while (i1 < s1 && i2 < s2 && l1[i1++] == l2[i2++])
+ ; /* keep going */
+ }
+
+ /*
+ * After running out of one side, the remaining side must have
+ * nothing but whitespace for the lines to match.
+ */
+ if (i1 < s1) {
+ while (i1 < s1 && isspace(l1[i1]))
i1++;
+ return (s1 == i1);
+ }
+ if (i2 < s2) {
+ while (i2 < s2 && isspace(l2[i2]))
i2++;
- }
- return i1 >= s1 && i2 >= s2;
- } else
- return s1 == s2 && !memcmp(l1, l2, s1);
+ return (s2 == i2);
+ }
+ return 1;
}
static unsigned long xdl_hash_record_with_whitespace(char const **data,
--
1.6.4.1.255.g5556a
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html