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

Use FIX_UTF8_MAC to enable conversion from UTF8-MAC to UTF8 for readdir 
and get_pathspec.

I had to change get_pathspec too because otherwise git-add wouldn't work 
anymore because it uses the output of get_pathspec as strings to compare 
with the output of readdir.

I'm quite unsure because this is my first patch for the git project and 
I have several questions:

1. Is FIX_UTF8_MAC the right name for this "feature"?
2. Do I have to introduce a configuration option for this "feature"?

Signed-off-by: Mark Junker <redacted>
---
  Makefile          |    5 +++++
  compat/readdir.c  |   26 ++++++++++++++++++++++++++
  git-compat-util.h |    5 +++++
  setup.c           |   12 ++++++++++++
  4 files changed, 48 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..045cfef
--- /dev/null
+++ b/compat/readdir.c

@@ -0,0 +1,26 @@
+#include "../git-compat-util.h"
+#include "../utf8.h"
+
+#undef readdir
+
+static struct dirent temp;
+
+struct dirent *gitreaddir(DIR *dirp)
+{
+	size_t utf8_len;
+	char *utf8;
+	struct dirent *result;
+	result = readdir(dirp);
+	if (result != NULL) {
+		memcpy(&temp, result, sizeof(struct dirent));
+		utf8 = reencode_string(temp.d_name, "UTF8", "UTF8-MAC");
+		if (utf8 != NULL) {
+			utf8_len = strlen(utf8);
+			temp.d_namlen = (u_int8_t) utf8_len;
+			memcpy(temp.d_name, utf8, utf8_len + 1);
+			free(utf8);
+			result = &temp;
+		}
+	}
+	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.rc3.40.gebe4

Sorry, the patch was broken (TABS were converted to spaces).

Signed-off-by: Mark Junker <redacted>
---
  Makefile          |    5 +++++
  compat/readdir.c  |   26 ++++++++++++++++++++++++++
  git-compat-util.h |    5 +++++
  setup.c           |   12 ++++++++++++
  4 files changed, 48 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..045cfef
--- /dev/null
+++ b/compat/readdir.c

@@ -0,0 +1,26 @@
+#include "../git-compat-util.h"
+#include "../utf8.h"
+
+#undef readdir
+
+static struct dirent temp;
+
+struct dirent *gitreaddir(DIR *dirp)
+{
+	size_t utf8_len;
+	char *utf8;
+	struct dirent *result;
+	result = readdir(dirp);
+	if (result != NULL) {
+		memcpy(&temp, result, sizeof(struct dirent));
+		utf8 = reencode_string(temp.d_name, "UTF8", "UTF8-MAC");
+		if (utf8 != NULL) {
+			utf8_len = strlen(utf8);
+			temp.d_namlen = (u_int8_t) utf8_len;
+			memcpy(temp.d_name, utf8, utf8_len + 1);
+			free(utf8);
+			result = &temp;
+		}
+	}
+	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.rc3.40.gebe4

ARGH! Sorry, I'll try it again later - when I fixed this stupid implicit 
conversion of TAB to SPC ...

Regards,
Mark

Hi,

here's the patch again - sent as an attachment. Sorry for any inconvenience.

Regards,
Mark

Hi,

On Mon, 21 Jan 2008, Mark Junker wrote:

Use FIX_UTF8_MAC to enable conversion from UTF8-MAC to UTF8 for readdir 
and get_pathspec.

I had to change get_pathspec too because otherwise git-add wouldn't work 
anymore because it uses the output of get_pathspec as strings to compare 
with the output of readdir.

I'm quite unsure because this is my first patch for the git project and 
I have several questions:

1. Is FIX_UTF8_MAC the right name for this "feature"?
2. Do I have to introduce a configuration option for this "feature"?

Signed-off-by: Mark Junker <redacted>

I hate three facts about this patch:

- it is too specific to the MacOSX filesystem issues (and better 
  alternatives have _already_ been proposed),

- it is a new feature and not a bug fix, very, _very_ late in the rc 
  cycle,

- it contains questions in the commit message? WTF?  Should it not be 
  marked as PATCH/RFC, possibly without a signoff to make sure that you 
  want to discuss it first?

It's possible I am grumpy because everybody and her dog seems to work on 
her little projects, while I listen to Junio and try to work with/on 
"master" already since a month.

Ciao,
Dscho

Johannes Schindelin schrieb:

- it is too specific to the MacOSX filesystem issues (and better 
  alternatives have _already_ been proposed),

I know that there were proposed alternatives but I like to use git on 
MacOSX now and not in XY months.

- it is a new feature and not a bug fix, very, _very_ late in the rc 
  cycle,

It was never meant for inclusion now. I know that this is post-1.5.4 stuff.

Regards,
Mark

Hi,

On Mon, 21 Jan 2008, Mark Junker wrote:

Johannes Schindelin schrieb:

quoted

- it is too specific to the MacOSX filesystem issues (and better 
alternatives have _already_ been proposed),

I know that there were proposed alternatives but I like to use git on 
MacOSX now and not in XY months.

quoted

- it is a new feature and not a bug fix, very, _very_ late in the rc 
cycle,

It was never meant for inclusion now. I know that this is post-1.5.4 
stuff.

In this case, I am going to work on my suggestion myself.

Now.

Ciao,
Dscho

Hi,

On Mon, 21 Jan 2008, Johannes Schindelin wrote:

On Mon, 21 Jan 2008, Mark Junker wrote:

quoted

Johannes Schindelin schrieb:

quoted

- it is too specific to the MacOSX filesystem issues (and better 
alternatives have _already_ been proposed),

I know that there were proposed alternatives but I like to use git on 
MacOSX now and not in XY months.

quoted

- it is a new feature and not a bug fix, very, _very_ late in the rc 
cycle,

It was never meant for inclusion now. I know that this is post-1.5.4 
stuff.

In this case, I am going to work on my suggestion myself.

Now.

I retract that.  Although I put some work into it, I agree that it is post 
1.5.4.

Plus, I do not want anybody to think that shouting and being a PITA buys 
him anything.

Ciao,
Dscho