Junio C Hamano <gitster@xxxxxxxxx> writes:
> Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> writes:
>
>> Now, very arguably this is not a git issue at all. Having the odd nbsp
>> be more visible in my other tools would have been fine - either 'less'
>> showing it (the way it shows other control characters) or my terminal
>> making some visual distinction. That said, I think it's something that
>> git could perhaps protect against a bit.
>
> Yeah. I would have expected that "git log -p" would at least show after
> the fact, relying on "less" being aware about it, but that does not seem
> to be the case. Setting my pager to "cat -e" is the only workaround I can
> think of right now (shows "M-BM- " there), but of course that wouldn't be
> practical at all. We want to notice this during patch application.
The "diff" side would look like this. I am tempted to change all the
"char *line" to "unsigned char *line", before updating "apply", though...
.gitattributes | 2 +-
ws.c | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++------
2 files changed, 68 insertions(+), 9 deletions(-)
diff --git a/.gitattributes b/.gitattributes
index 5e98806..b4459b0 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,3 +1,3 @@
* whitespace=!indent,trail,space
-*.[ch] whitespace=indent,trail,space
+*.[ch] whitespace=indent,trail,space,nbsp
*.sh whitespace=indent,trail,space
diff --git a/ws.c b/ws.c
index 01762cc..4766d6f 100644
--- a/ws.c
+++ b/ws.c
@@ -20,7 +20,7 @@ static struct whitespace_rule {
{ "blank-at-eol", WS_BLANK_AT_EOL, 0 },
{ "blank-at-eof", WS_BLANK_AT_EOF, 0 },
{ "tab-in-indent", WS_TAB_IN_INDENT, 0, 1 },
- { "nbsp", WS_NSBP, 0, 0 },
+ { "nbsp", WS_NBSP, 0, 0 },
};
unsigned parse_whitespace_rule(const char *string)
@@ -147,6 +147,49 @@ char *whitespace_error_string(unsigned ws)
return strbuf_detach(&err, NULL);
}
+static inline int is_nbsp(const char *at_)
+{
+ const unsigned char *at = (const unsigned char *)at_;
+ return at[0] == 0xc2 && at[1] == 0xa0;
+}
+
+/*
+ * Show line while highlighting nbsp "Â" (c2a0) if ws is set
+ */
+static void emit_with_nbsp_hilite(FILE *stream,
+ const char *set, const char *reset,
+ const char *ws,
+ const char *line, int len)
+{
+ if (!len)
+ return;
+ while (len) {
+ int ok; /* leading segment without problematic nbsp */
+ if (!ws) {
+ ok = len;
+ } else {
+ for (ok = 0; ok < len; ok++) {
+ if (ok < len - 1 && is_nbsp(line + ok))
+ break;
+ }
+ }
+ if (ok) {
+ fputs(set, stream);
+ fwrite(line, ok, 1, stream);
+ fputs(reset, stream);
+ }
+ line += ok;
+ len -= ok;
+ if (len) {
+ fputs(ws, stream);
+ fwrite(line, 2, 1, stream);
+ fputs(reset, stream);
+ line += 2;
+ len -= 2;
+ }
+ }
+}
+
/* If stream is non-NULL, emits the line after checking. */
static unsigned ws_check_emit_1(const char *line, int len, unsigned ws_rule,
FILE *stream, const char *set,
@@ -170,6 +213,24 @@ static unsigned ws_check_emit_1(const char *line, int len, unsigned ws_rule,
len--;
}
+ /* Check for nbsp in UTF-8 (c2a0) */
+ if (ws_rule & WS_NBSP) {
+ for (i = 1; i < len; i++) {
+ switch (line[i] & 0xff) {
+ case 0xc2:
+ break;
+ case 0xa0:
+ if ((line[i-1] & 0xff) == 0xc2) {
+ result |= WS_NBSP;
+ continue;
+ }
+ /* fallthru */
+ default:
+ i++;
+ }
+ }
+ }
+
/* Check for trailing whitespace. */
if (ws_rule & WS_BLANK_AT_EOL) {
for (i = len - 1; i >= 0; i--) {
@@ -230,13 +291,11 @@ static unsigned ws_check_emit_1(const char *line, int len, unsigned ws_rule,
* The non-highlighted part ends at "trailing_whitespace".
*/
- /* Emit non-highlighted (middle) segment. */
- if (trailing_whitespace - written > 0) {
- fputs(set, stream);
- fwrite(line + written,
- trailing_whitespace - written, 1, stream);
- fputs(reset, stream);
- }
+ /* Emit middle segment, highlighting nbsp as needed */
+ emit_with_nbsp_hilite(stream, set, reset,
+ (result & WS_NBSP) ? ws : NULL,
+ line + written,
+ trailing_whitespace - written);
/* Highlight errors in trailing whitespace. */
if (trailing_whitespace != len) {
--
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