[PATCH v6 2/2] convert: ce_compare_data() checks for a sha1 of a path

[tboegi@web.de]

From: Torsten Bögershausen <tboegi@web.de>

To compare a file in working tree with the index, convert_to_git() is used,
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.

Forward sha1 from ce_compare_data() into convert_to_git().
All other callers use NULL, and the sha1 it is determined from path using
get_sha1_from_cache(path), this is the same handling as before.

Re-order the arguments for convert_to_git() according to their importance:
  `src`, `len` and `dst` are the place in memory, where the conversion is done
  `path` is the file name to look up the attributes.
  `sha1` is needed by the "new safer autocrlf handling".
  `checksafe` determines, if a warning is printed or an error is raised.

In the same spirit, forward the sha1 into would_convert_to_git().

While at it, rename has_cr_in_index() into blob_has_cr()

Signed-off-by: Torsten Bögershausen <tboegi@web.de>
Changes sinve v6:
 decrease the messiness with 12 %
 convert_to_git() has a re-ordered parameter list.
 Describe whats going on better in the commit msg.
 Cleanup: 0 -> SAFE_CRLF_FALSE at some places
---
 builtin/apply.c |  3 ++-
 builtin/blame.c |  2 +-
 cache.h         |  1 +
 combine-diff.c  |  4 +++-
 convert.c       | 38 +++++++++++++++++++++++++-------------
 convert.h       | 20 ++++++++++++++------
 diff.c          |  3 ++-
 dir.c           |  2 +-
 read-cache.c    |  4 +++-
 sha1_file.c     | 17 +++++++++++++----
 10 files changed, 65 insertions(+), 29 deletions(-)

diff --git a/builtin/apply.c b/builtin/apply.c
index 8e4da2e..c01654a 100644
--- a/builtin/apply.c
+++ b/builtin/apply.c
@@ -2140,7 +2140,8 @@ static int read_old_data(struct stat *st, const char *path, struct strbuf *buf)
 	case S_IFREG:
 		if (strbuf_read_file(buf, path, st->st_size) != st->st_size)
 			return error(_("unable to open or read %s"), path);
-		convert_to_git(path, buf->buf, buf->len, buf, 0);
+		convert_to_git(buf->buf, buf->len, buf,
+			       path, NULL, SAFE_CRLF_FALSE);
 		return 0;
 	default:
 		return -1;
diff --git a/builtin/blame.c b/builtin/blame.c
index 21f42b0..4a01e20 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -2377,7 +2377,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 		if (strbuf_read(&buf, 0, 0) < 0)
 			die_errno("failed to read from stdin");
 	}
-	convert_to_git(path, buf.buf, buf.len, &buf, 0);
+	convert_to_git(buf.buf, buf.len, &buf, path, NULL, SAFE_CRLF_FALSE);
 	origin->file.ptr = buf.buf;
 	origin->file.size = buf.len;
 	pretend_sha1_file(buf.buf, buf.len, OBJ_BLOB, origin->blob_sha1);
diff --git a/cache.h b/cache.h
index 15a2a10..868599e 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_USE_SHA_NOT_PATH 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/combine-diff.c b/combine-diff.c
index 0e1d4b0..cac4c81 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -1053,7 +1053,9 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 			if (is_file) {
 				struct strbuf buf = STRBUF_INIT;
 
-				if (convert_to_git(elem->path, result, len, &buf, safe_crlf)) {
+				if (convert_to_git(result, len, &buf,
+						   elem->path, NULL,
+						   safe_crlf)) {
 					free(result);
 					result = strbuf_detach(&buf, &len);
 					result_size = len;
diff --git a/convert.c b/convert.c
index f524b8d..a58bb26 100644
--- a/convert.c
+++ b/convert.c
@@ -217,21 +217,26 @@ static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
 	}
 }
 
-static int has_cr_in_index(const char *path)
+static int blob_has_cr(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)
+		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 +265,9 @@ 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 (!sha1)
+				sha1 = get_sha1_from_cache(path);
+			if (blob_has_cr(sha1))
 				return 0;
 		}
 	}
@@ -852,8 +859,10 @@ 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(const char *src, size_t len,
+		   struct strbuf *dst,
+		   const char *path, const unsigned char *sha1,
+		   enum safe_crlf checksafe)
 {
 	int ret = 0;
 	const char *filter = NULL;
@@ -874,7 +883,7 @@ 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 +891,9 @@ 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 +905,7 @@ 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);
 }
 
@@ -949,7 +960,8 @@ int renormalize_buffer(const char *path, const char *src, size_t len, struct str
 		src = dst->buf;
 		len = dst->len;
 	}
-	return ret | convert_to_git(path, src, len, dst, SAFE_CRLF_FALSE);
+	ret |= convert_to_git(src, len, dst, path, NULL, SAFE_CRLF_FALSE);
+	return ret;
 }
 
 /*****************************************************************
diff --git a/convert.h b/convert.h
index ccf436b..12fe767 100644
--- a/convert.h
+++ b/convert.h
@@ -37,19 +37,27 @@ 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(const char *src, size_t len,
+			  struct strbuf *dst,
+			  const char *path, const unsigned char *sha1,
+			  enum safe_crlf 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,
 			      struct strbuf *dst);
-static inline int would_convert_to_git(const char *path)
+
+static inline int would_convert_to_git(const char *path,
+				       const unsigned char *sha1)
 {
-	return convert_to_git(path, NULL, 0, NULL, 0);
+	return convert_to_git(NULL, 0, NULL, path, sha1, SAFE_CRLF_FALSE);
 }
+
+
 /* 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/diff.c b/diff.c
index d3734d3..9c00973 100644
--- a/diff.c
+++ b/diff.c
@@ -2810,7 +2810,8 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags)
 		/*
 		 * Convert from working tree format to canonical git format
 		 */
-		if (convert_to_git(s->path, s->data, s->size, &buf, crlf_warn)) {
+		if (convert_to_git(s->data, s->size, &buf, s->path, NULL,
+				   crlf_warn)) {
 			size_t size = 0;
 			munmap(s->data, s->size);
 			s->should_munmap = 0;
diff --git a/dir.c b/dir.c
index 656f272..5ac379d 100644
--- a/dir.c
+++ b/dir.c
@@ -713,7 +713,7 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 				 (pos = cache_name_pos(fname, strlen(fname))) >= 0 &&
 				 !ce_stage(active_cache[pos]) &&
 				 ce_uptodate(active_cache[pos]) &&
-				 !would_convert_to_git(fname))
+				 !would_convert_to_git(fname, NULL))
 				hashcpy(sha1_stat->sha1, active_cache[pos]->sha1);
 			else
 				hash_sha1_file(buf, size, "blob", sha1_stat->sha1);
diff --git a/read-cache.c b/read-cache.c
index a3ef967..c109b6d 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_USE_SHA_NOT_PATH;
+		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..48906b0 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_USE_SHA_NOT_PATH;
 
 	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(
+			    buf, size, &nbuf,path,
+			    valid_sha1 ? sha1 : NULL,
+			    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_USE_SHA_NOT_PATH;
 	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_USE_SHA_NOT_PATH ? 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(path,sha1_ce)))
 		ret = index_core(sha1, fd, xsize_t(st->st_size), type, path,
 				 flags);
 	else
-- 
2.0.0.rc1.6318.g0c2c796