From: Lars Schneider <larsxschnei...@gmail.com>
Hi,
Patches 1-5,9 are preparation and helper functions.
Patch 6-8,10 are the actual change. Patch 8 is new.
This series depends on Torsten's 8462ff43e4 (convert_to_git():
safe_crlf/checksafe becomes int conv_flags, 2018-01-13) which is
already in master.
Changes since v10:
* rename startscase_with() to istarts_with() (Duy)
* validate_encoding() advises the canonical form of the UTF
encoding name to the user (Junio)
--> I added it this as a separate commit that you could be dropped
if desired by the reviewers.
* fix documentation for roundtrip check (Junio)
* use isspace() to check whitespace/tab delimiter
in core.checkRoundtripEncoding (Junio)
* remove dead code in roundtrip check (Junio)
* fix invalid # in comment (Eric)
* detect UTF8 and UTF-8 as default encoding (Eric)
* make asterisk stick to the variable, not type (Junio)
* print an error if "w-t-e" does not have a proper value (Junio)
--> BTW: I noticed that the attribute is not set to "git_attr__false"
even if I define "-working-tree-encoding". I haven't investigated
further yet. Might that be a bug? If yes, then this should be
addresses in a separate patch series.
Thanks,
Lars
RFC:
https://public-inbox.org/git/bdb9b884-6d17-4be3-a83c-f67e2afa2...@gmail.com/
v1:
https://public-inbox.org/git/20171211155023.1405-1-lars.schnei...@autodesk.com/
v2:
https://public-inbox.org/git/20171229152222.39680-1-lars.schnei...@autodesk.com/
v3:
https://public-inbox.org/git/20180106004808.77513-1-lars.schnei...@autodesk.com/
v4:
https://public-inbox.org/git/20180120152418.52859-1-lars.schnei...@autodesk.com/
v5: https://public-inbox.org/git/20180129201855.9182-1-tbo...@web.de/
v6:
https://public-inbox.org/git/20180209132830.55385-1-lars.schnei...@autodesk.com/
v7:
https://public-inbox.org/git/20180215152711.158-1-lars.schnei...@autodesk.com/
v8:
https://public-inbox.org/git/20180224162801.98860-1-lars.schnei...@autodesk.com/
v9:
https://public-inbox.org/git/20180304201418.60958-1-lars.schnei...@autodesk.com/
v10:
https://public-inbox.org/git/20180307173026.30058-1-lars.schnei...@autodesk.com/
Base Ref:
Web-Diff: https://github.com/larsxschneider/git/commit/afc02ce2e0
Checkout: git fetch https://github.com/larsxschneider/git encoding-v11 && git
checkout afc02ce2e0
### Interdiff (v10..v11):
diff --git a/Documentation/config.txt b/Documentation/config.txt
index d7a56054a5..7dcac9b540 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -531,10 +531,10 @@ core.autocrlf::
in which case no output conversion is performed.
core.checkRoundtripEncoding::
- A comma separated list of encodings that Git performs UTF-8 round
- trip checks on if they are used in an `working-tree-encoding`
- attribute (see linkgit:gitattributes[5]). The default value is
- `SHIFT-JIS`.
+ A comma and/or whitespace separated list of encodings that Git
+ performs UTF-8 round trip checks on if they are used in an
+ `working-tree-encoding` attribute (see linkgit:gitattributes[5]).
+ The default value is `SHIFT-JIS`.
core.symlinks::
If false, symbolic links are checked out as small plain files that
diff --git a/convert.c b/convert.c
index e861f1abbc..c2d24882c1 100644
--- a/convert.c
+++ b/convert.c
@@ -270,7 +270,7 @@ static int validate_encoding(const char *path, const char
*enc,
const char *data, size_t len, int die_on_error)
{
/* We only check for UTF here as UTF?? can be an alias for UTF-?? */
- if (startscase_with(enc, "UTF")) {
+ if (istarts_with(enc, "UTF")) {
/*
* Check for detectable errors in UTF encodings
*/
@@ -284,12 +284,15 @@ static int validate_encoding(const char *path, const char
*enc,
*/
const char *advise_msg = _(
"The file '%s' contains a byte order "
- "mark (BOM). Please use %s as "
+ "mark (BOM). Please use UTF-%s as "
"working-tree-encoding.");
- char *upper_enc = xstrdup_toupper(enc);
- upper_enc[strlen(upper_enc)-2] = '\0';
- advise(advise_msg, path, upper_enc);
- free(upper_enc);
+ const char *stripped = "";
+ char *upper = xstrdup_toupper(enc);
+ upper[strlen(upper)-2] = '\0';
+ if (!skip_prefix(upper, "UTF-", &stripped))
+ skip_prefix(stripped, "UTF", &stripped);
+ advise(advise_msg, path, stripped);
+ free(upper);
if (die_on_error)
die(error_msg, path, enc);
else {
@@ -301,12 +304,15 @@ static int validate_encoding(const char *path, const char
*enc,
"BOM is required in '%s' if encoded as %s");
const char *advise_msg = _(
"The file '%s' is missing a byte order "
- "mark (BOM). Please use %sBE or %sLE "
+ "mark (BOM). Please use UTF-%sBE or UTF-%sLE "
"(depending on the byte order) as "
"working-tree-encoding.");
- char *upper_enc = xstrdup_toupper(enc);
- advise(advise_msg, path, upper_enc, upper_enc);
- free(upper_enc);
+ const char *stripped = "";
+ char *upper = xstrdup_toupper(enc);
+ if (!skip_prefix(upper, "UTF-", &stripped))
+ skip_prefix(stripped, "UTF", &stripped);
+ advise(advise_msg, path, stripped, stripped);
+ free(upper);
if (die_on_error)
die(error_msg, path, enc);
else {
@@ -344,8 +350,8 @@ static void trace_encoding(const char *context, const char
*path,
static int check_roundtrip(const char *enc_name)
{
/*
- * check_roundtrip_encoding contains a string of space and/or
- * comma separated encodings (eg. "UTF-16, ASCII, CP1125").
+ * check_roundtrip_encoding contains a string of comma and/or
+ * space separated encodings (eg. "UTF-16, ASCII, CP1125").
* Search for the given encoding in that string.
*/
const char *found = strcasestr(check_roundtrip_encoding, enc_name);
@@ -362,8 +368,7 @@ static int check_roundtrip(const char* enc_name)
* that it is prefixed with a space or comma
*/
found == check_roundtrip_encoding || (
- found > check_roundtrip_encoding &&
- (*(found-1) == ' ' || *(found-1) == ',')
+ (isspace(found[-1]) || found[-1] == ',')
)
) && (
/*
@@ -373,7 +378,7 @@ static int check_roundtrip(const char* enc_name)
*/
next == check_roundtrip_encoding + len || (
next < check_roundtrip_encoding + len &&
- (*next == ' ' || *next == ',')
+ (isspace(next[0]) || next[0] == ',')
)
));
}
@@ -1213,12 +1218,16 @@ static const char *git_path_check_encoding(struct
attr_check_item *check)
{
const char *value = check->value;
- if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value) ||
- !strlen(value))
+ if (ATTR_UNSET(value) || !strlen(value))
return NULL;
+ if (ATTR_TRUE(value) || ATTR_FALSE(value)) {
+ error(_("working-tree-encoding attribute requires a value"));
+ return NULL;
+ }
+
/* Don't encode to the default encoding */
- if (!strcasecmp(value, default_encoding))
+ if (is_encoding_utf8(value) && is_encoding_utf8(default_encoding))
return NULL;
return value;
diff --git a/git-compat-util.h b/git-compat-util.h
index f648da0c11..95c9b34832 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -455,7 +455,7 @@ extern void (*get_warn_routine(void))(const char *warn,
va_list params);
extern void set_die_is_recursing_routine(int (*routine)(void));
extern int starts_with(const char *str, const char *prefix);
-extern int startscase_with(const char *str, const char *prefix);
+extern int istarts_with(const char *str, const char *prefix);
/*
* If the string "str" begins with the string found in "prefix", return 1.
diff --git a/strbuf.c b/strbuf.c
index 5779a2d591..99812b8488 100644
--- a/strbuf.c
+++ b/strbuf.c
@@ -11,7 +11,7 @@ int starts_with(const char *str, const char *prefix)
return 0;
}
-int startscase_with(const char *str, const char *prefix)
+int istarts_with(const char *str, const char *prefix)
{
for (; ; str++, prefix++)
if (!*prefix)
diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh
index 7cff41a350..07089bba2e 100755
--- a/t/t0028-working-tree-encoding.sh
+++ b/t/t0028-working-tree-encoding.sh
@@ -68,7 +68,7 @@ do
test_when_finished "git reset --hard HEAD" &&
echo "*.utf${i}be text working-tree-encoding=utf-${i}be"
>>.gitattributes &&
- echo "*.utf${i}le text working-tree-encoding=utf-${i}le"
>>.gitattributes &&
+ echo "*.utf${i}le text working-tree-encoding=utf-${i}LE"
>>.gitattributes &&
# Here we add a UTF-16 (resp. UTF-32) files with BOM
(big/little-endian)
# but we tell Git to treat it as UTF-16BE/UTF-16LE (resp.
UTF-32).
@@ -76,18 +76,22 @@ do
cp bebom.utf${i}be.raw bebom.utf${i}be &&
test_must_fail git add bebom.utf${i}be 2>err.out &&
test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out
&&
+ test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out &&
cp lebom.utf${i}le.raw lebom.utf${i}be &&
test_must_fail git add lebom.utf${i}be 2>err.out &&
test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out
&&
+ test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out &&
cp bebom.utf${i}be.raw bebom.utf${i}le &&
test_must_fail git add bebom.utf${i}le 2>err.out &&
- test_i18ngrep "fatal: BOM is prohibited .* utf-${i}le" err.out
&&
+ test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out
&&
+ test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out &&
cp lebom.utf${i}le.raw lebom.utf${i}le &&
test_must_fail git add lebom.utf${i}le 2>err.out &&
- test_i18ngrep "fatal: BOM is prohibited .* utf-${i}le" err.out
+ test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out
&&
+ test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out
'
test_expect_success "check required UTF-${i} BOM" '
@@ -98,10 +102,12 @@ do
cp nobom.utf${i}be.raw nobom.utf${i} &&
test_must_fail git add nobom.utf${i} 2>err.out &&
test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out &&
+ test_i18ngrep "use UTF-${i}BE or UTF-${i}LE" err.out &&
cp nobom.utf${i}le.raw nobom.utf${i} &&
test_must_fail git add nobom.utf${i} 2>err.out &&
- test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out
+ test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out &&
+ test_i18ngrep "use UTF-${i}BE or UTF-${i}LE" err.out
'
test_expect_success "eol conversion for UTF-${i} encoded files on
checkout" '
@@ -143,9 +149,20 @@ done
test_expect_success 'check unsupported encodings' '
test_when_finished "git reset --hard HEAD" &&
- echo "*.nothing text working-tree-encoding=" >>.gitattributes &&
- printf "nothing" >t.nothing &&
- git add t.nothing &&
+ echo "*.set text working-tree-encoding" >>.gitattributes &&
+ printf "set" >t.set &&
+ git add t.set 2>err.out &&
+ test_i18ngrep "error: working-tree-encoding attribute requires a value"
err.out &&
+
+ echo "*.unset text -working-tree-encoding" >>.gitattributes &&
+ printf "unset" >t.unset &&
+ git add t.unset 2>err.out &&
+ test_i18ngrep "error: working-tree-encoding attribute requires a value"
err.out &&
+
+ echo "*.empty text working-tree-encoding=" >>.gitattributes &&
+ printf "empty" >t.empty &&
+ git add t.empty 2>err.out &&
+ test_i18ngrep "error: working-tree-encoding attribute requires a value"
err.out &&
echo "*.garbage text working-tree-encoding=garbage" >>.gitattributes &&
printf "garbage" >t.garbage &&
### Patches
Lars Schneider (10):
strbuf: remove unnecessary NUL assignment in xstrdup_tolower()
strbuf: add xstrdup_toupper()
strbuf: add a case insensitive starts_with()
utf8: add function to detect prohibited UTF-16/32 BOM
utf8: add function to detect a missing UTF-16/32 BOM
convert: add 'working-tree-encoding' attribute
convert: check for detectable errors in UTF encodings
convert: advise canonical UTF encoding names
convert: add tracing for 'working-tree-encoding' attribute
convert: add round trip check based on 'core.checkRoundtripEncoding'
Documentation/config.txt | 6 +
Documentation/gitattributes.txt | 88 +++++++++++++
config.c | 5 +
convert.c | 277 ++++++++++++++++++++++++++++++++++++++-
convert.h | 2 +
environment.c | 1 +
git-compat-util.h | 1 +
sha1_file.c | 2 +-
strbuf.c | 22 +++-
strbuf.h | 1 +
t/t0028-working-tree-encoding.sh | 247 ++++++++++++++++++++++++++++++++++
utf8.c | 39 ++++++
utf8.h | 28 ++++
13 files changed, 716 insertions(+), 3 deletions(-)
create mode 100755 t/t0028-working-tree-encoding.sh
base-commit: 8a2f0888555ce46ac87452b194dec5cb66fb1417
--
2.16.2
