[PATCH] precompose-utf8: do not call checks for non-ascii utf8

2012-08-20 Thread Junio C Hamano
As suggested by Linus, this function is not checking UTF-8-ness of the
string; it only is seeing if it is pure US-ASCII.

Signed-off-by: Junio C Hamano gits...@pobox.com
---

 * Just for completeness, this on top.

 compat/precompose_utf8.c | 16 
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/compat/precompose_utf8.c b/compat/precompose_utf8.c
index 3190d50..8cf5955 100644
--- a/compat/precompose_utf8.c
+++ b/compat/precompose_utf8.c
@@ -13,20 +13,20 @@ typedef char *iconv_ibp;
 static const char *repo_encoding = UTF-8;
 static const char *path_encoding = UTF-8-MAC;
 
-static size_t has_utf8(const char *s, size_t maxlen, size_t *strlen_c)
+static size_t has_non_ascii(const char *s, size_t maxlen, size_t *strlen_c)
 {
-   const uint8_t *utf8p = (const uint8_t *)s;
+   const uint8_t *ptr = (const uint8_t *)s;
size_t strlen_chars = 0;
size_t ret = 0;
 
-   if (!utf8p || !*utf8p)
+   if (!ptr || !*ptr)
return 0;
 
-   while (*utf8p  maxlen) {
-   if (*utf8p  0x80)
+   while (*ptr  maxlen) {
+   if (*ptr  0x80)
ret++;
strlen_chars++;
-   utf8p++;
+   ptr++;
maxlen--;
}
if (strlen_c)
@@ -77,7 +77,7 @@ void precompose_argv(int argc, const char **argv)
while (i  argc) {
size_t namelen;
oldarg = argv[i];
-   if (has_utf8(oldarg, (size_t)-1, namelen)) {
+   if (has_non_ascii(oldarg, (size_t)-1, namelen)) {
newarg = reencode_string_iconv(oldarg, namelen, 
ic_precompose);
if (newarg)
argv[i] = newarg;
@@ -130,7 +130,7 @@ struct dirent_prec_psx *precompose_utf8_readdir(PREC_DIR 
*prec_dir)
prec_dir-dirent_nfc-d_ino  = res-d_ino;
prec_dir-dirent_nfc-d_type = res-d_type;
 
-   if ((precomposed_unicode == 1)  has_utf8(res-d_name, 
(size_t)-1, NULL)) {
+   if ((precomposed_unicode == 1)  has_non_ascii(res-d_name, 
(size_t)-1, NULL)) {
if (prec_dir-ic_precompose == (iconv_t)-1) {
die(iconv_open(%s,%s) failed, but needed:\n
precomposed unicode is not 
supported.\n
-- 
1.7.12.129.g11de995

--
To unsubscribe from this list: send the line unsubscribe git in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html


Re: [PATCH] precompose-utf8: do not call checks for non-ascii utf8

2012-08-20 Thread Torsten Bögershausen

On 08/20/2012 08:13 PM, Junio C Hamano wrote:

As suggested by Linus, this function is not checking UTF-8-ness of the
string; it only is seeing if it is pure US-ASCII.

Signed-off-by: Junio C Hamano gits...@pobox.com
---

  * Just for completeness, this on top.

  compat/precompose_utf8.c | 16 
  1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/compat/precompose_utf8.c b/compat/precompose_utf8.c
index 3190d50..8cf5955 100644
--- a/compat/precompose_utf8.c
+++ b/compat/precompose_utf8.c
@@ -13,20 +13,20 @@ typedef char *iconv_ibp;
  static const char *repo_encoding = UTF-8;
  static const char *path_encoding = UTF-8-MAC;

-static size_t has_utf8(const char *s, size_t maxlen, size_t *strlen_c)
+static size_t has_non_ascii(const char *s, size_t maxlen, size_t *strlen_c)
  {
-   const uint8_t *utf8p = (const uint8_t *)s;
+   const uint8_t *ptr = (const uint8_t *)s;
size_t strlen_chars = 0;
size_t ret = 0;

-   if (!utf8p || !*utf8p)
+   if (!ptr || !*ptr)
return 0;

-   while (*utf8p  maxlen) {
-   if (*utf8p  0x80)
+   while (*ptr  maxlen) {
+   if (*ptr  0x80)
ret++;
strlen_chars++;
-   utf8p++;
+   ptr++;
maxlen--;
}
if (strlen_c)
@@ -77,7 +77,7 @@ void precompose_argv(int argc, const char **argv)
while (i  argc) {
size_t namelen;
oldarg = argv[i];
-   if (has_utf8(oldarg, (size_t)-1, namelen)) {
+   if (has_non_ascii(oldarg, (size_t)-1, namelen)) {
newarg = reencode_string_iconv(oldarg, namelen, 
ic_precompose);
if (newarg)
argv[i] = newarg;
@@ -130,7 +130,7 @@ struct dirent_prec_psx *precompose_utf8_readdir(PREC_DIR 
*prec_dir)
prec_dir-dirent_nfc-d_ino  = res-d_ino;
prec_dir-dirent_nfc-d_type = res-d_type;

-   if ((precomposed_unicode == 1)  has_utf8(res-d_name, 
(size_t)-1, NULL)) {
+   if ((precomposed_unicode == 1)  has_non_ascii(res-d_name, 
(size_t)-1, NULL)) {
if (prec_dir-ic_precompose == (iconv_t)-1) {
die(iconv_open(%s,%s) failed, but needed:\n
precomposed unicode is not 
supported.\n


Thanks Junio,
that partly obsoletes the patch I'm working on.
And as I didn't manage to catch up, may I send the result of my review?

a) in readdir we die() when iconv_open() fails, and we could/should do 
that in void precompose_argv() as well?


b) Should die(txt) be converted into die(_(txt)) to be able to 
translate the message?


c) We can remove the save/restore of errno at one place, similar to this:


@@ -106,11 +106,8 @@ PREC_DIR *precompose_utf8_opendir(const char *dirname)
free(prec_dir-dirent_nfc);
free(prec_dir);
return NULL;
-   } else {
-   int ret_errno = errno;
+   } else
prec_dir-ic_precompose = (iconv_t)-1;
-   errno = ret_errno;
-   }





--
To unsubscribe from this list: send the line unsubscribe git in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html