Re: [PATCH] Use FIX_UTF8_MAC to enable conversion from UTF8-MAC to UTF8

[Mark Junker <mjscod@web.de>]

[-- Attachment #1: Type: text/plain, Size: 836 bytes --]

Junio C Hamano schrieb:

> You memcpy() what the library gave you in *result to the
> statically allocated "temp".  d_name[] in "temp" comes from the
> structure definition in the user visible include file, which
> could be much shorter than what the library gave you in *result.
> The structure definition I showed in my message you are
> responding to illustrates the issue.  If MacOS uses a similar
> trick to define d_name[256] and sometimes returns much longer
> name in *result, you are truncating the name by copying only the
> first part of the structure and first 256 bytes of d_name[]. 

Now I understand what you mean. Ok, I'll try to change this and make 
this work on other platforms too.

I didn't know that the readdir function is allowed to return something 
longer for d_name than the specified length.

Regards,
Mark


[-- Attachment #2.1: Type: application/applefile, Size: 1503 bytes --]

[-- Attachment #2.2: 0001-Use-FIX_UTF8_#7B1A40.patch --]
[-- Type: application/octet-stream, Size: 3345 bytes --]

From 239de834a4d67b4176a8dbf5504fa2f335989aaa Mon Sep 17 00:00:00 2001
From: Mark Junker <mjscod@web.de>
Date: Sun, 20 Jan 2008 16:59:32 +0100
Subject: [PATCH] Use FIX_UTF8_MAC to enable conversion from UTF8-MAC to UTF8

Signed-off-by: Mark Junker <mjscod@web.de>
---
 Makefile          |    5 +++++
 compat/readdir.c  |   30 ++++++++++++++++++++++++++++++
 git-compat-util.h |    5 +++++
 setup.c           |   12 ++++++++++++
 4 files changed, 52 insertions(+), 0 deletions(-)

diff --git a/Makefile b/Makefile
index 5aac0c0..e55914e 100644
--- a/Makefile
+++ b/Makefile
@@ -417,6 +417,7 @@ ifeq ($(uname_S),Darwin)
 	endif
 	NO_STRLCPY = YesPlease
 	NO_MEMMEM = YesPlease
+	FIX_UTF8_MAC = YesPlease
 endif
 ifeq ($(uname_S),SunOS)
 	NEEDS_SOCKET = YesPlease
@@ -616,6 +617,10 @@ ifdef NO_STRLCPY
 	COMPAT_CFLAGS += -DNO_STRLCPY
 	COMPAT_OBJS += compat/strlcpy.o
 endif
+ifdef FIX_UTF8_MAC
+	COMPAT_CFLAGS += -DFIX_UTF8_MAC
+	COMPAT_OBJS += compat/readdir.o
+endif
 ifdef NO_STRTOUMAX
 	COMPAT_CFLAGS += -DNO_STRTOUMAX
 	COMPAT_OBJS += compat/strtoumax.o
diff --git a/compat/readdir.c b/compat/readdir.c
new file mode 100644
index 0000000..96a724a
--- /dev/null
+++ b/compat/readdir.c
@@ -0,0 +1,30 @@
+#include "../git-compat-util.h"
+#include "../utf8.h"
+
+#undef readdir
+
+static struct dirent *temp_dirent = NULL;
+static size_t temp_dirent_length = 0;
+
+struct dirent *gitreaddir(DIR *dirp)
+{
+	struct dirent *result = readdir(dirp);
+	if (result != NULL) {
+		char *utf8 = reencode_string(result->d_name, "UTF8", "UTF8-MAC");
+		if (utf8 != NULL) {
+			size_t utf8_len = strlen(utf8);
+			/* Create a copy of the dirent data only if conversion is possible. */
+			if (result->d_reclen > temp_dirent_length) {
+				/* Ensure that the buffer is large enough and avoid
+				 * too much allocations. */
+				temp_dirent_length = result->d_reclen;
+				temp_dirent = realloc(temp_dirent, temp_dirent_length);
+			}
+			memcpy(temp_dirent, result, result->d_reclen);
+			memcpy(temp_dirent->d_name, utf8, utf8_len + 1);
+			free(utf8);
+			result = temp_dirent;
+		}
+	}
+	return result;
+}
diff --git a/git-compat-util.h b/git-compat-util.h
index b6ef544..cd0233d 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -202,6 +202,11 @@ void *gitmemmem(const void *haystack, size_t haystacklen,
                 const void *needle, size_t needlelen);
 #endif
 
+#ifdef FIX_UTF8_MAC
+#define readdir gitreaddir
+struct dirent *gitreaddir(DIR *dirp);
+#endif
+
 #ifdef __GLIBC_PREREQ
 #if __GLIBC_PREREQ(2, 1)
 #define HAVE_STRCHRNUL
diff --git a/setup.c b/setup.c
index adede16..4cec28b 100644
--- a/setup.c
+++ b/setup.c
@@ -1,5 +1,8 @@
 #include "cache.h"
 #include "dir.h"
+#ifdef FIX_UTF8_MAC
+#include "utf8.h"
+#endif
 
 static int inside_git_dir = -1;
 static int inside_work_tree = -1;
@@ -131,6 +134,15 @@ const char **get_pathspec(const char *prefix, const char **pathspec)
 	p = pathspec;
 	prefixlen = prefix ? strlen(prefix) : 0;
 	do {
+#ifdef FIX_UTF8_MAC
+		/* Reencode as UTF8 (composed) to have a counterpart for the
+		 * readdir-replacement on MacOS X.
+		 */
+		char *utf8 = reencode_string(entry, "UTF8", "UTF8-MAC");
+		if (utf8 != NULL) {
+			entry = utf8;
+		}
+#endif
 		*p = prefix_path(prefix, prefixlen, entry);
 	} while ((entry = *++p) != NULL);
 	return (const char **) pathspec;
-- 
1.5.4.rc3.38.g8166