git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v2 2/3] convert: ce_compare_data() checks for a sha1 of a path

From
tboegi@web.de <tboegi@web.de>
Date
May 15, 2016, 13:02 UTC
Message-ID
<1463317349-2710-1-git-send-email-tboegi@web.de>
In-Reply-To
<20160513134953.GE2345@dinwoodie.org>
From: Torsten Bögershausen <tboegi@web.de>

To compare a file in working tree with the index, convert_to_git() is used, the the result is hashed and the hash value compared with ce->sha1.

Deep down would_convert_crlf_at_commit() is invoked, to check if CRLF are converted or not: When a CRLF had been in the index before, CRLF in the working tree are not converted.

While in a merge, a file name in the working tree has different blobs in the index with different hash values. Forwarding ce->sha1 from ce_compare_data() into crlf_to_git() makes sure the would_convert_crlf_at_commit() looks at the appropriate blob.

Signed-off-by: Torsten Bögershausen <tboegi@web.de>
---
 cache.h      |  1 +
 convert.c    | 34 ++++++++++++++++++++++------------
 convert.h    | 23 +++++++++++++++++++----
 read-cache.c |  4 +++-
 sha1_file.c  | 17 +++++++++++++----
 5 files changed, 58 insertions(+), 21 deletions(-)
diff --git a/cache.h b/cache.h
index 15a2a10..a5136c0 100644
--- a/cache.h
+++ b/cache.h
@@ -605,6 +605,7 @@ extern int ie_modified(const struct index_state *, const struct cache_entry *, s
 
 #define HASH_WRITE_OBJECT 1
 #define HASH_FORMAT_CHECK 2
+#define HASH_CE_HAS_SHA1  4
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags);
 extern int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags);
 
diff --git a/convert.c b/convert.c
index f524b8d..c972d14 100644
--- a/convert.c
+++ b/convert.c
@@ -217,21 +217,28 @@ static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
 	}
 }
 
-static int has_cr_in_index(const char *path)
+static int has_cr_in_index(const char *path, const unsigned char *sha1)
 {
 	unsigned long sz;
 	void *data;
-	int has_cr;
-
-	data = read_blob_data_from_cache(path, &sz);
+	int has_cr = 0;
+	enum object_type type;
+	if (!sha1)
+		sha1 = get_sha1_from_cache(path);
+	if (!sha1)
+		return 0;
+	data = read_sha1_file(sha1, &type, &sz);
 	if (!data)
 		return 0;
-	has_cr = memchr(data, '\r', sz) != NULL;
+	if (type == OBJ_BLOB)
+		has_cr = memchr(data, '\r', sz) != NULL;
+
 	free(data);
 	return has_cr;
 }
 
-static int crlf_to_git(const char *path, const char *src, size_t len,
+static int crlf_to_git(const char *path, const unsigned char *sha1,
+		       const char *src, size_t len,
 		       struct strbuf *buf,
 		       enum crlf_action crlf_action, enum safe_crlf checksafe)
 {
@@ -260,7 +267,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 			 * If the file in the index has any CR in it, do not convert.
 			 * This is the new safer autocrlf handling.
 			 */
-			if (has_cr_in_index(path))
+			if (has_cr_in_index(path, sha1))
 				return 0;
 		}
 	}
@@ -852,8 +859,9 @@ const char *get_convert_attr_ascii(const char *path)
 	return "";
 }
 
-int convert_to_git(const char *path, const char *src, size_t len,
-                   struct strbuf *dst, enum safe_crlf checksafe)
+int convert_to_git_ce_sha1(const char *path, const unsigned char *sha1,
+			   const char *src, size_t len,
+			   struct strbuf *dst, enum safe_crlf checksafe)
 {
 	int ret = 0;
 	const char *filter = NULL;
@@ -874,7 +882,7 @@ int convert_to_git(const char *path, const char *src, size_t len,
 		src = dst->buf;
 		len = dst->len;
 	}
-	ret |= crlf_to_git(path, src, len, dst, ca.crlf_action, checksafe);
+	ret |= crlf_to_git(path, sha1, src, len, dst, ca.crlf_action, checksafe);
 	if (ret && dst) {
 		src = dst->buf;
 		len = dst->len;
@@ -882,7 +890,9 @@ int convert_to_git(const char *path, const char *src, size_t len,
 	return ret | ident_to_git(path, src, len, dst, ca.ident);
 }
 
-void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
+void convert_to_git_filter_fd(const char *path,
+			      const unsigned char *sha1,
+			      int fd, struct strbuf *dst,
 			      enum safe_crlf checksafe)
 {
 	struct conv_attrs ca;
@@ -894,7 +904,7 @@ void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
 	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv->clean))
 		die("%s: clean filter '%s' failed", path, ca.drv->name);
 
-	crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe);
+	crlf_to_git(path, sha1, dst->buf, dst->len, dst, ca.crlf_action, checksafe);
 	ident_to_git(path, dst->buf, dst->len, dst, ca.ident);
 }
 
diff --git a/convert.h b/convert.h
index ccf436b..1634d37 100644
--- a/convert.h
+++ b/convert.h
@@ -37,8 +37,16 @@ extern const char *get_wt_convert_stats_ascii(const char *path);
 extern const char *get_convert_attr_ascii(const char *path);
 
 /* returns 1 if *dst was used */
-extern int convert_to_git(const char *path, const char *src, size_t len,
-			  struct strbuf *dst, enum safe_crlf checksafe);
+extern int convert_to_git_ce_sha1(const char *path, const unsigned char *sha1,
+				  const char *src, size_t len,
+				  struct strbuf *dst, enum safe_crlf checksafe);
+
+static inline int convert_to_git(const char *path, const char *src, size_t len,
+				 struct strbuf *dst, enum safe_crlf checksafe)
+{
+	return convert_to_git_ce_sha1(path, NULL, src, len, dst, checksafe);
+}
+
 extern int convert_to_working_tree(const char *path, const char *src,
 				   size_t len, struct strbuf *dst);
 extern int renormalize_buffer(const char *path, const char *src, size_t len,
@@ -47,9 +55,16 @@ static inline int would_convert_to_git(const char *path)
 {
 	return convert_to_git(path, NULL, 0, NULL, 0);
 }
+static inline int would_convert_to_git_ce_sha1(const char *path,
+					       const unsigned char *sha1)
+{
+	return convert_to_git_ce_sha1(path, sha1, NULL, 0, NULL, 0);
+}
+
 /* Precondition: would_convert_to_git_filter_fd(path) == true */
-extern void convert_to_git_filter_fd(const char *path, int fd,
-				     struct strbuf *dst,
+extern void convert_to_git_filter_fd(const char *path,
+				     const unsigned char *sha1,
+				     int fd, struct strbuf *dst,
 				     enum safe_crlf checksafe);
 extern int would_convert_to_git_filter_fd(const char *path);
 
diff --git a/read-cache.c b/read-cache.c
index a3ef967..0ebc237 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -163,7 +163,9 @@ static int ce_compare_data(const struct cache_entry *ce, struct stat *st)
 
 	if (fd >= 0) {
 		unsigned char sha1[20];
-		if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0))
+		unsigned flags = HASH_CE_HAS_SHA1;
+		memcpy(sha1, ce->sha1, sizeof(sha1));
+		if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, flags))
 			match = hashcmp(sha1, ce->sha1);
 		/* index_fd() closed the file descriptor already */
 	}
diff --git a/sha1_file.c b/sha1_file.c
index d0f2aa0..dd013d5 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -3275,6 +3275,7 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 {
 	int ret, re_allocated = 0;
 	int write_object = flags & HASH_WRITE_OBJECT;
+	const int valid_sha1 = flags & HASH_CE_HAS_SHA1;
 
 	if (!type)
 		type = OBJ_BLOB;
@@ -3284,8 +3285,11 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 	 */
 	if ((type == OBJ_BLOB) && path) {
 		struct strbuf nbuf = STRBUF_INIT;
-		if (convert_to_git(path, buf, size, &nbuf,
-				   write_object ? safe_crlf : SAFE_CRLF_FALSE)) {
+		if (convert_to_git_ce_sha1(path,
+					   valid_sha1 ? sha1 : NULL,
+					   buf, size, &nbuf,
+					   write_object ? safe_crlf : SAFE_CRLF_FALSE)){
+
 			buf = strbuf_detach(&nbuf, &size);
 			re_allocated = 1;
 		}
@@ -3313,12 +3317,15 @@ static int index_stream_convert_blob(unsigned char *sha1, int fd,
 {
 	int ret;
 	const int write_object = flags & HASH_WRITE_OBJECT;
+	const int valid_sha1 = flags & HASH_CE_HAS_SHA1;
 	struct strbuf sbuf = STRBUF_INIT;
 
 	assert(path);
 	assert(would_convert_to_git_filter_fd(path));
 
-	convert_to_git_filter_fd(path, fd, &sbuf,
+	convert_to_git_filter_fd(path,
+				 valid_sha1 ? sha1 : NULL,
+				 fd, &sbuf,
 				 write_object ? safe_crlf : SAFE_CRLF_FALSE);
 
 	if (write_object)
@@ -3396,6 +3403,8 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
 	     enum object_type type, const char *path, unsigned flags)
 {
 	int ret;
+	const unsigned char *sha1_ce;
+	sha1_ce = flags & HASH_CE_HAS_SHA1 ? sha1 : NULL;
 
 	/*
 	 * Call xsize_t() only when needed to avoid potentially unnecessary
@@ -3406,7 +3415,7 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
 	else if (!S_ISREG(st->st_mode))
 		ret = index_pipe(sha1, fd, type, path, flags);
 	else if (st->st_size <= big_file_threshold || type != OBJ_BLOB ||
-		 (path && would_convert_to_git(path)))
+		 (path && would_convert_to_git_ce_sha1(path,sha1_ce)))
 		ret = index_core(sha1, fd, xsize_t(st->st_size), type, path,
 				 flags);
 	else

-- 
2.0.0.rc1.6318.g0c2c796
Previous: tboegi@web.deNext: tboegi@web.de
Message 52 of 53 in “Bug report: Duplicate CRLF rewrite warnings on commit”
  1. Adam DinwoodieMay 13, 2016
  2. Junio C HamanoMay 13, 2016
  3. Torsten BögershausenMay 14, 2016
  4. Adam DinwoodieMay 14, 2016
  5. Jeff KingMay 13, 2016
  6. Junio C HamanoMay 13, 2016
  7. Jeff KingMay 13, 2016
  8. 0/1 Quickfix ?No duplicate CRLF rewrite warnings on committboegi@web.de, May 15, 2016
  9. 1/1 No duplicate CRLF rewrite warnings on committboegi@web.de, May 15, 2016
  10. Eric SunshineMay 15, 2016
  11. 0/3 CRLF-Handling: bug fix around ce_compare_data()tboegi@web.de, May 15, 2016
  12. 1/3 t6038; use crlf on all platformstboegi@web.de, May 15, 2016
  13. Eric SunshineMay 15, 2016
  14. 2/3 read-cache: factor out get_sha1_from_index() helpertboegi@web.de, May 15, 2016
  15. Eric SunshineMay 15, 2016
  16. 3/3 convert: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 15, 2016
  17. Eric SunshineMay 15, 2016
  18. Junio C HamanoMay 15, 2016
  19. 0/1 CRLF-Handling: bug fix around ce_compare_data()tboegi@web.de, May 16, 2016
  20. Junio C HamanoMay 16, 2016
  21. Torsten BögershausenMay 17, 2016
  22. 1/1 t6038; use crlf on all platformstboegi@web.de, May 17, 2016
  23. Junio C HamanoMay 17, 2016
  24. 0/2 CRLF: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 17, 2016
  25. 1/2 read-cache: factor out get_sha1_from_index() helpertboegi@web.de, May 17, 2016
  26. 2/2 convert: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 17, 2016
  27. Junio C HamanoMay 17, 2016
  28. Torsten BögershausenMay 18, 2016
  29. Torsten BögershausenMay 18, 2016
  30. 0/2 CRLF: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 19, 2016
  31. Junio C HamanoMay 19, 2016
  32. 1/2 read-cache: factor out get_sha1_from_index() helpertboegi@web.de, May 19, 2016
  33. 2/2 convert: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 19, 2016
  34. Junio C HamanoMay 19, 2016
  35. 1/2 read-cache: factor out get_sha1_from_index() helpertboegi@web.de, May 20, 2016
  36. 2/2 convert: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 20, 2016
  37. Junio C HamanoMay 20, 2016
  38. 1/2 read-cache: factor out get_sha1_from_index() helpertboegi@web.de, May 21, 2016
  39. 2/2 convert: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 21, 2016
  40. Junio C HamanoMay 24, 2016
  41. 1/1 convert: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 16, 2016
  42. 0/1 t6038-merge-text-auto.shtboegi@web.de, May 30, 2016
  43. Junio C HamanoMay 30, 2016
  44. Junio C HamanoMay 30, 2016
  45. 1/1 t6038: different eol for "Merge addition of text=auto"tboegi@web.de, May 30, 2016
  46. 0/3 unified auto CRLF handling, V2tboegi@web.de, Jun 7, 2016
  47. 1/3 convert: unify the "auto" handling of CRLFtboegi@web.de, Jun 7, 2016
  48. 2/3 read-cache: factor out get_sha1_from_index() helpertboegi@web.de, Jun 7, 2016
  49. 3/3 Correct ce_compare_data() in a middle of a mergetboegi@web.de, Jun 7, 2016
  50. 0/3 CRLF-Handling: bug fix around ce_compare_data()tboegi@web.de, May 15, 2016
  51. 1/3 read-cache: factor out get_sha1_from_index() helpertboegi@web.de, May 15, 2016
  52. 2/3 convert: ce_compare_data() checks for a sha1 of a pathtboegi@web.de, May 15, 2016
  53. 3/3 t6038; use crlf on all platformstboegi@web.de, May 15, 2016

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.