Re: [PATCH] t3910: show failure of core.precomposeunicode with decomposed filenames

From

Torsten Bögershausen <tboegi@web.de>

Date

May 7, 2014, 19:16 UTC

Message-ID

<536A8698.3000208@web.de>

In-Reply-To

<20140505214658.GA16971@sigill.intra.peff.net>

>>   2. Do all index filename comparisons under Mac OS X using a UTF-8 aware
>>      comparison function regardless if core.precomposeunicode is set.
>>      This would probably have bad performance, and somewhat
>>      defeats the point of converting the filenames at the
>>      readdir level in the first place.
> 
> Right, I'm concerned about performance here, but I wonder if we can
> reuse the name-hash solutions from ignorecase.

diff --git a/compat/precompose_utf8.c b/compat/precompose_utf8.c
index 95fe849..c807f38 100644
--- a/compat/precompose_utf8.c
+++ b/compat/precompose_utf8.c
@@ -57,6 +57,22 @@ void probe_utf8_pathname_composition(char *path, int len)
 }
 
 
+char *inverscompose_str_len(const char *in, size_t insz, int *outsz)
+{
+	char *prec_str = NULL;
+
+	if (has_non_ascii(in, insz, NULL)) {
+		int old_errno = errno;
+		prec_str = reencode_string_len(in, (int)insz,
+					       precomposed_unicode ? path_encoding : repo_encoding,
+					       precomposed_unicode ? repo_encoding : path_encoding,
+					       outsz);
+		errno = old_errno;
+	}
+	return prec_str;
+}
+
+
 void precompose_argv(int argc, const char **argv)
 {
 	int i = 0;
diff --git a/compat/precompose_utf8.h b/compat/precompose_utf8.h
index 3b73585..b9ac099 100644
--- a/compat/precompose_utf8.h
+++ b/compat/precompose_utf8.h
@@ -26,6 +26,7 @@ typedef struct {
 	struct dirent_prec_psx *dirent_nfc;
 } PREC_DIR;
 
+char *inverscompose_str_len(const char *in, size_t insz, int *outsz);
 void precompose_argv(int argc, const char **argv);
 void probe_utf8_pathname_composition(char *, int);
 
diff --git a/git-compat-util.h b/git-compat-util.h
index f6d3a46..5ae5f57 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -177,7 +177,7 @@ typedef unsigned long uintptr_t;
 #ifdef PRECOMPOSE_UNICODE
 #include "compat/precompose_utf8.h"
 #else
-#define precompose_str(in,i_nfd2nfc)
+#define inverscompose_str_len(s,i,o) NULL
 #define precompose_argv(c,v)
 #define probe_utf8_pathname_composition(a,b)
 #endif
diff --git a/name-hash.c b/name-hash.c
index 97444d0..3c4a4ee 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -210,7 +210,7 @@ struct cache_entry *index_dir_exists(struct index_state *istate, const char *nam
 	return NULL;
 }
 
-struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int icase)
+static struct cache_entry *index_file_exists_int(struct index_state *istate, const char *name, int namelen, int icase)
 {
 	struct cache_entry *ce;
 	struct hashmap_entry key;
@@ -227,6 +227,25 @@ struct cache_entry *index_file_exists(struct index_state *istate, const char *na
 	return NULL;
 }
 
+
+struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int icase)
+{
+	struct cache_entry *ce;
+	ce = index_file_exists_int(istate, name, namelen, icase);
+	if (ce)
+		return ce;
+	else {
+		int prec_len;
+		char *prec_name = inverscompose_str_len(name, namelen, &prec_len);
+		if (prec_name) {
+			ce = index_file_exists_int(istate, prec_name, prec_len, icase);
+			free(prec_name);
+		}
+	}
+	return ce;
+}
+
+
 void free_name_hash(struct index_state *istate)
 {
 	if (!istate->name_hash_initialized)
diff --git a/t/t3910-mac-os-precompose.sh b/t/t3910-mac-os-precompose.sh
index e4ba601..4414658 100755
--- a/t/t3910-mac-os-precompose.sh
+++ b/t/t3910-mac-os-precompose.sh
@@ -140,6 +140,22 @@ test_expect_success "Add long precomposed filename" '
 	git add * &&
 	git commit -m "Long filename"
 '
+
+test_expect_success 'handle existing decomposed filenames' '
+	git checkout master &&
+	git reset --hard &&
+	git checkout -b exist_decomposed &&
+	echo content >"verbatim.$Adiarnfd" &&
+	git -c core.precomposeunicode=false add "verbatim.$Adiarnfd" &&
+	git commit -m "existing decomposed file" &&
+	echo \"verbatim.A\\314\\210\" >expect &&
+	git ls-files >actual &&
+	test_cmp expect actual &&
+	>expect &&
+	git status | grep verbatim || : >actual &&
+	test_cmp expect actual
+'
+
 # Test if the global core.precomposeunicode stops autosensing
 # Must be the last test case
 test_expect_success "respect git config --global core.precomposeunicode" '
diff --git a/utf8.c b/utf8.c
index 77c28d4..fb8a99a 100644
--- a/utf8.c
+++ b/utf8.c
@@ -519,7 +519,7 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outs
 	char *out, *outpos;
 	iconv_ibp cp;
 
-	outsz = insz;
+	outsz = 3*insz; /* for decompose */
 	outalloc = outsz + 1; /* for terminating NUL */
 	out = xmalloc(outalloc);
 	outpos = out;