[PATCH v4] receive-pack.c: consolidate find header logic

["John Cai via GitGitGadget" <gitgitgadget@gmail.com>]

From: John Cai <johncai86@gmail.com>

There are two functions that have very similar logic of finding a header
value. find_commit_header, and find_header. We can conslidate the logic
by introducing a new function find_header_mem, which is equivalent to
find_commit_header except it takes a len parameter that determines how
many bytes will be read. find_commit_header and find_header can then both
call find_header_mem.

This reduces duplicate logic, as the logic for finding header values
can now all live in one place.

Signed-off-by: John Cai <johncai86@gmail.com>
---
    Consolidate find_header logic into one function
    
    This addresses the NEEDSWORK comment in builtin/receive-pack.c:
    
     /**
       * NEEDSWORK: reuse find_commit_header() from jk/commit-author-parsing
       * after dropping "_commit" from its name and possibly moving it out
       * of commit.c
       **/
    
    
    There are two functions that have very similar logic of finding a header
    value. find_commit_header, and find_header. We can conslidate the logic
    by introducing a new function find_header_mem, which is equivalent to
    find_commit_header except it takes a len parameter that determines how
    many bytes will be read. find_commit_header and find_header can then
    both call find_header_mem.
    
    This reduces duplicate logic, as the logic for finding header values can
    now all live in one place.
    
    Changes since v4:
    
     * added NEEDSWORK block detailing what needs to be done to clean up
       find_header_mem
    
    Changes since v3:
    
     * fixed verbiage in commit message
     * adjusted style of an if block (based on Junio's feedback)

Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-git-1125%2Fjohn-cai%2Fjc%2Freplace-find-header-v4
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-git-1125/john-cai/jc/replace-find-header-v4
Pull-Request: https://github.com/git/git/pull/1125

Range-diff vs v3:

 1:  463df42e7e0 ! 1:  a7b00022b00 receive-pack.c: consolidate find header logic
     @@ Commit message
      
          There are two functions that have very similar logic of finding a header
          value. find_commit_header, and find_header. We can conslidate the logic
     -    by using find_commit_header and replacing the logic in find_header.
     -
     -    Introduce a new function find_header_max, which is equivalent to
     +    by introducing a new function find_header_mem, which is equivalent to
          find_commit_header except it takes a len parameter that determines how
     -    many bytes to read. find_commit_header can then call find_header_max
     -    with 0 as the len.
     +    many bytes will be read. find_commit_header and find_header can then both
     +    call find_header_mem.
      
     -    This cleans up duplicate logic, as the logic for finding header values
     -    is now all in one place.
     +    This reduces duplicate logic, as the logic for finding header values
     +    can now all live in one place.
      
          Signed-off-by: John Cai <johncai86@gmail.com>
      
     @@ builtin/receive-pack.c: static char *prepare_push_cert_nonce(const char *path, t
      +	size_t out_len;
      +	const char *val = find_header_mem(msg, len, key, &out_len);
      +
     -+	if (val == NULL)
     ++	if (!val)
      +		return NULL;
      +
      +	if (next_line)
     @@ commit.c: struct commit_list **commit_list_append(struct commit *commit,
       	const char *line = msg;
       
      -	while (line) {
     ++	/*
     ++	 * NEEDSWORK: Between line[0] and msg[len], there may not be a LF nor NUL
     ++	 * at all, and strchrnul() will scan beyond the range we were given
     ++	 * Make this operation safer and abide by the contract to only read up to len.
     ++	 */
      +	while (line && line < msg + len) {
       		const char *eol = strchrnul(line, '\n');
       


 builtin/receive-pack.c | 33 ++++++++++-----------------------
 commit.c               | 14 ++++++++++++--
 commit.h               |  5 +++++
 3 files changed, 27 insertions(+), 25 deletions(-)

diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c
index 9f4a0b816cf..5c2732a0d07 100644
--- a/builtin/receive-pack.c
+++ b/builtin/receive-pack.c
@@ -581,32 +581,19 @@ static char *prepare_push_cert_nonce(const char *path, timestamp_t stamp)
 	return strbuf_detach(&buf, NULL);
 }
 
-/*
- * NEEDSWORK: reuse find_commit_header() from jk/commit-author-parsing
- * after dropping "_commit" from its name and possibly moving it out
- * of commit.c
- */
 static char *find_header(const char *msg, size_t len, const char *key,
 			 const char **next_line)
 {
-	int key_len = strlen(key);
-	const char *line = msg;
-
-	while (line && line < msg + len) {
-		const char *eol = strchrnul(line, '\n');
-
-		if ((msg + len <= eol) || line == eol)
-			return NULL;
-		if (line + key_len < eol &&
-		    !memcmp(line, key, key_len) && line[key_len] == ' ') {
-			int offset = key_len + 1;
-			if (next_line)
-				*next_line = *eol ? eol + 1 : eol;
-			return xmemdupz(line + offset, (eol - line) - offset);
-		}
-		line = *eol ? eol + 1 : NULL;
-	}
-	return NULL;
+	size_t out_len;
+	const char *val = find_header_mem(msg, len, key, &out_len);
+
+	if (!val)
+		return NULL;
+
+	if (next_line)
+		*next_line = val + out_len + 1;
+
+	return xmemdupz(val, out_len);
 }
 
 /*
diff --git a/commit.c b/commit.c
index a348f085b2b..5ece03e6373 100644
--- a/commit.c
+++ b/commit.c
@@ -1631,12 +1631,18 @@ struct commit_list **commit_list_append(struct commit *commit,
 	return &new_commit->next;
 }
 
-const char *find_commit_header(const char *msg, const char *key, size_t *out_len)
+const char *find_header_mem(const char *msg, size_t len,
+			const char *key, size_t *out_len)
 {
 	int key_len = strlen(key);
 	const char *line = msg;
 
-	while (line) {
+	/*
+	 * NEEDSWORK: Between line[0] and msg[len], there may not be a LF nor NUL
+	 * at all, and strchrnul() will scan beyond the range we were given
+	 * Make this operation safer and abide by the contract to only read up to len.
+	 */
+	while (line && line < msg + len) {
 		const char *eol = strchrnul(line, '\n');
 
 		if (line == eol)
@@ -1653,6 +1659,10 @@ const char *find_commit_header(const char *msg, const char *key, size_t *out_len
 	return NULL;
 }
 
+const char *find_commit_header(const char *msg, const char *key, size_t *out_len)
+{
+	return find_header_mem(msg, strlen(msg), key, out_len);
+}
 /*
  * Inspect the given string and determine the true "end" of the log message, in
  * order to find where to put a new Signed-off-by trailer.  Ignored are
diff --git a/commit.h b/commit.h
index 3ea32766bcb..38cc5426615 100644
--- a/commit.h
+++ b/commit.h
@@ -290,12 +290,17 @@ void free_commit_extra_headers(struct commit_extra_header *extra);
 
 /*
  * Search the commit object contents given by "msg" for the header "key".
+ * Reads up to "len" bytes of "msg".
  * Returns a pointer to the start of the header contents, or NULL. The length
  * of the header, up to the first newline, is returned via out_len.
  *
  * Note that some headers (like mergetag) may be multi-line. It is the caller's
  * responsibility to parse further in this case!
  */
+const char *find_header_mem(const char *msg, size_t len,
+			const char *key,
+			size_t *out_len);
+
 const char *find_commit_header(const char *msg, const char *key,
 			       size_t *out_len);
 

base-commit: c8b2ade48c204690119936ada89cd938c476c5c2
-- 
gitgitgadget