Not even "less" shows nbsp as anything special nor unusual, so eyeballing
with "git log -p" after applying a patch that accidentally had it where a
regular SP should be, breaking compilation, would not help.
This only handles "diff", not "apply" yet.
Signed-off-by: Junio C Hamano <gitster@xxxxxxxxx>
---
* This is the moral equivalent of the earlier patch, but based on the two
clean-ups. If we do not consider nbsp an error, at least we should
count it just like an ordinary SP that takes one display column, and if
we do not like indenting with non-TAB or trailing whitespaces, we
should complain loudly, which was the topic of 2/3.
cache.h | 18 ++++++-----
t/t4019-diff-wserror.sh | 8 ++--
ws.c | 72 ++++++++++++++++++++++++++++++++++++++++++----
3 files changed, 79 insertions(+), 19 deletions(-)
diff --git a/cache.h b/cache.h
index dd34fed..4f58587 100644
--- a/cache.h
+++ b/cache.h
@@ -1122,17 +1122,19 @@ void shift_tree_by(const unsigned char *, const unsigned char *, unsigned char *
/*
* whitespace rules.
* used by both diff and apply
- * last two digits are tab width
+ * last 6-bits are tab width
*/
-#define WS_BLANK_AT_EOL 0100
-#define WS_SPACE_BEFORE_TAB 0200
-#define WS_INDENT_WITH_NON_TAB 0400
-#define WS_CR_AT_EOL 01000
-#define WS_BLANK_AT_EOF 02000
-#define WS_TAB_IN_INDENT 04000
+#define WS_TAB_WIDTH_MASK 077
+#define WS_BLANK_AT_EOL (1<< 6)
+#define WS_SPACE_BEFORE_TAB (1<< 7)
+#define WS_INDENT_WITH_NON_TAB (1<< 8)
+#define WS_CR_AT_EOL (1<< 9)
+#define WS_BLANK_AT_EOF (1<<10)
+#define WS_TAB_IN_INDENT (1<<11)
+#define WS_NBSP (1<<12)
#define WS_TRAILING_SPACE (WS_BLANK_AT_EOL|WS_BLANK_AT_EOF)
#define WS_DEFAULT_RULE (WS_TRAILING_SPACE|WS_SPACE_BEFORE_TAB|8)
-#define WS_TAB_WIDTH_MASK 077
+
extern unsigned whitespace_rule_cfg;
extern unsigned whitespace_rule(const char *);
extern unsigned parse_whitespace_rule(const char *);
diff --git a/t/t4019-diff-wserror.sh b/t/t4019-diff-wserror.sh
index 665f693..8c7fea2 100755
--- a/t/t4019-diff-wserror.sh
+++ b/t/t4019-diff-wserror.sh
@@ -56,7 +56,7 @@ test_expect_success default '
grep End error >/dev/null
'
-test_expect_success 'default (attribute)' '
+test_expect_success 'default (attribute) -- must check all available rule' '
test_might_fail git config --unset core.whitespace &&
echo "F whitespace" >.gitattributes &&
@@ -68,7 +68,7 @@ test_expect_success 'default (attribute)' '
grep Return error >/dev/null &&
grep No normal >/dev/null &&
grep Enough error >/dev/null &&
- grep Bit normal >/dev/null &&
+ grep Bit error >/dev/null &&
grep End error >/dev/null
'
@@ -83,8 +83,8 @@ test_expect_success 'default, tabwidth=10 (attribute)' '
grep With error >/dev/null &&
grep Return error >/dev/null &&
grep No normal >/dev/null &&
- grep Enough normal >/dev/null &&
- grep Bit normal >/dev/null &&
+ grep Enough error >/dev/null &&
+ grep Bit error >/dev/null &&
grep End error >/dev/null
'
diff --git a/ws.c b/ws.c
index 68c7599..53e263d 100644
--- a/ws.c
+++ b/ws.c
@@ -20,6 +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_NBSP, 0, 0 },
};
unsigned parse_whitespace_rule(const char *string)
@@ -141,6 +142,8 @@ char *whitespace_error_string(unsigned ws)
add_err_item(&err, "indent with spaces");
if (ws & WS_TAB_IN_INDENT)
add_err_item(&err, "tab in indent");
+ if (ws & WS_NBSP)
+ add_err_item(&err, " in source");
return strbuf_detach(&err, NULL);
}
@@ -150,6 +153,45 @@ static int is_nbsp(const 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) {
+ /* number of bytes in the leading segment w/o nbsp error */
+ int ok;
+ 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) {
+ /* do not bother bundling consecutive ones */
+ 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,
@@ -173,6 +215,24 @@ 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--) {
@@ -245,13 +305,11 @@ 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) {
--
1.7.5.3.503.g893a4
--
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