From: Junio C Hamano <gitster@pobox.com>
Date: Tue, 21 Mar 2017 22:03:29 +0000 (-0700)
Subject: Merge branch 'rs/commit-parsing-optim' into maint
X-Git-Tag: v2.12.2~13
X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/d6bc22e64b9572f72b2eb26fa1ce9d697d9d0d8e?ds=inline;hp=-c

Merge branch 'rs/commit-parsing-optim' into maint

The code that parses header fields in the commit object has been
updated for (micro)performance and code hygiene.

* rs/commit-parsing-optim:
commit: don't check for space twice when looking for header
commit: be more precise when searching for headers
---

d6bc22e64b9572f72b2eb26fa1ce9d697d9d0d8e
diff --combined commit.c
index 2cf85158b4,609d597a8d..fab8269731
--- a/commit.c
+++ b/commit.c
@@@ -1308,11 -1308,11 +1308,11 @@@ void for_each_mergetag(each_mergetag_f
  
  static inline int standard_header_field(const char *field, size_t len)
  {
- 	return ((len == 4 && !memcmp(field, "tree ", 5)) ||
- 		(len == 6 && !memcmp(field, "parent ", 7)) ||
- 		(len == 6 && !memcmp(field, "author ", 7)) ||
- 		(len == 9 && !memcmp(field, "committer ", 10)) ||
- 		(len == 8 && !memcmp(field, "encoding ", 9)));
+ 	return ((len == 4 && !memcmp(field, "tree", 4)) ||
+ 		(len == 6 && !memcmp(field, "parent", 6)) ||
+ 		(len == 6 && !memcmp(field, "author", 6)) ||
+ 		(len == 9 && !memcmp(field, "committer", 9)) ||
+ 		(len == 8 && !memcmp(field, "encoding", 8)));
  }
  
  static int excluded_header_field(const char *field, size_t len, const char **exclude)
@@@ -1322,8 -1322,7 +1322,7 @@@
  
  	while (*exclude) {
  		size_t xlen = strlen(*exclude);
- 		if (len == xlen &&
- 		    !memcmp(field, *exclude, xlen) && field[xlen] == ' ')
+ 		if (len == xlen && !memcmp(field, *exclude, xlen))
  			return 1;
  		exclude++;
  	}
@@@ -1354,12 -1353,11 +1353,11 @@@ static struct commit_extra_header *read
  		strbuf_reset(&buf);
  		it = NULL;
  
- 		eof = strchr(line, ' ');
- 		if (next <= eof)
+ 		eof = memchr(line, ' ', next - line);
+ 		if (!eof)
  			eof = next;
- 
- 		if (standard_header_field(line, eof - line) ||
- 		    excluded_header_field(line, eof - line, exclude))
+ 		else if (standard_header_field(line, eof - line) ||
+ 			 excluded_header_field(line, eof - line, exclude))
  			continue;
  
  		it = xcalloc(1, sizeof(*it));
@@@ -1511,9 -1509,9 +1509,9 @@@ static int verify_utf8(struct strbuf *b
  }
  
  static const char commit_utf8_warn[] =
 -"Warning: commit message did not conform to UTF-8.\n"
 -"You may want to amend it after fixing the message, or set the config\n"
 -"variable i18n.commitencoding to the encoding your project uses.\n";
 +N_("Warning: commit message did not conform to UTF-8.\n"
 +   "You may want to amend it after fixing the message, or set the config\n"
 +   "variable i18n.commitencoding to the encoding your project uses.\n");
  
  int commit_tree_extended(const char *msg, size_t msg_len,
  			 const unsigned char *tree,
@@@ -1566,7 -1564,7 +1564,7 @@@
  
  	/* And check the encoding */
  	if (encoding_is_utf8 && !verify_utf8(&buffer))
 -		fprintf(stderr, commit_utf8_warn);
 +		fprintf(stderr, _(commit_utf8_warn));
  
  	if (sign_commit && do_sign_commit(&buffer, sign_commit))
  		return -1;
@@@ -1649,7 -1647,7 +1647,7 @@@ const char *find_commit_header(const ch
  }
  
  /*
 - * Inspect sb and determine the true "end" of the log message, in
 + * 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: line.  Ignored are
   * trailing comment lines and blank lines, and also the traditional
   * "Conflicts:" block that is not commented out, so that we can use
@@@ -1659,37 -1657,37 +1657,37 @@@
   * Returns the number of bytes from the tail to ignore, to be fed as
   * the second parameter to append_signoff().
   */
 -int ignore_non_trailer(struct strbuf *sb)
 +int ignore_non_trailer(const char *buf, size_t len)
  {
  	int boc = 0;
  	int bol = 0;
  	int in_old_conflicts_block = 0;
  
 -	while (bol < sb->len) {
 -		char *next_line;
 +	while (bol < len) {
 +		const char *next_line = memchr(buf + bol, '\n', len - bol);
  
 -		if (!(next_line = memchr(sb->buf + bol, '\n', sb->len - bol)))
 -			next_line = sb->buf + sb->len;
 +		if (!next_line)
 +			next_line = buf + len;
  		else
  			next_line++;
  
 -		if (sb->buf[bol] == comment_line_char || sb->buf[bol] == '\n') {
 +		if (buf[bol] == comment_line_char || buf[bol] == '\n') {
  			/* is this the first of the run of comments? */
  			if (!boc)
  				boc = bol;
  			/* otherwise, it is just continuing */
 -		} else if (starts_with(sb->buf + bol, "Conflicts:\n")) {
 +		} else if (starts_with(buf + bol, "Conflicts:\n")) {
  			in_old_conflicts_block = 1;
  			if (!boc)
  				boc = bol;
 -		} else if (in_old_conflicts_block && sb->buf[bol] == '\t') {
 +		} else if (in_old_conflicts_block && buf[bol] == '\t') {
  			; /* a pathname in the conflicts block */
  		} else if (boc) {
  			/* the previous was not trailing comment */
  			boc = 0;
  			in_old_conflicts_block = 0;
  		}
 -		bol = next_line - sb->buf;
 +		bol = next_line - buf;
  	}
 -	return boc ? sb->len - boc : 0;
 +	return boc ? len - boc : 0;
  }