Re: [PATCH 27/34] shortlog: release strbuf after use in insert_one_record()

[Junio C Hamano <gitster@pobox.com>]

Jeff King <peff@peff.net> writes:

> IOW, something like the patch below, which pushes the re-parsing out to
> the stdin code-path, and lets the internal traversal format directly
> into the final buffer. It seems to be about 3% faster than the existing
> code, and fixes the leak (by dropping that variable entirely).

Wow, that is soooo logical a conclusion that I somewhat feel ashamed
that I didn't think of it myself.  

Nicely done.

>
> -Peff
>
> ---
> diff --git a/builtin/shortlog.c b/builtin/shortlog.c
> index 43c4799ea9..e29875b843 100644
> --- a/builtin/shortlog.c
> +++ b/builtin/shortlog.c
> @@ -52,26 +52,8 @@ static void insert_one_record(struct shortlog *log,
>  			      const char *oneline)
>  {
>  	struct string_list_item *item;
> -	const char *mailbuf, *namebuf;
> -	size_t namelen, maillen;
> -	struct strbuf namemailbuf = STRBUF_INIT;
> -	struct ident_split ident;
>  
> -	if (split_ident_line(&ident, author, strlen(author)))
> -		return;
> -
> -	namebuf = ident.name_begin;
> -	mailbuf = ident.mail_begin;
> -	namelen = ident.name_end - ident.name_begin;
> -	maillen = ident.mail_end - ident.mail_begin;
> -
> -	map_user(&log->mailmap, &mailbuf, &maillen, &namebuf, &namelen);
> -	strbuf_add(&namemailbuf, namebuf, namelen);
> -
> -	if (log->email)
> -		strbuf_addf(&namemailbuf, " <%.*s>", (int)maillen, mailbuf);
> -
> -	item = string_list_insert(&log->list, namemailbuf.buf);
> +	item = string_list_insert(&log->list, author);
>  
>  	if (log->summary)
>  		item->util = (void *)(UTIL_TO_INT(item) + 1);
> @@ -114,9 +96,33 @@ static void insert_one_record(struct shortlog *log,
>  	}
>  }
>  
> +static int parse_stdin_author(struct shortlog *log,
> +			       struct strbuf *out, const char *in)
> +{
> +	const char *mailbuf, *namebuf;
> +	size_t namelen, maillen;
> +	struct ident_split ident;
> +
> +	if (split_ident_line(&ident, in, strlen(in)))
> +		return -1;
> +
> +	namebuf = ident.name_begin;
> +	mailbuf = ident.mail_begin;
> +	namelen = ident.name_end - ident.name_begin;
> +	maillen = ident.mail_end - ident.mail_begin;
> +
> +	map_user(&log->mailmap, &mailbuf, &maillen, &namebuf, &namelen);
> +	strbuf_add(out, namebuf, namelen);
> +	if (log->email)
> +		strbuf_addf(out, " <%.*s>", (int)maillen, mailbuf);
> +
> +	return 0;
> +}
> +
>  static void read_from_stdin(struct shortlog *log)
>  {
>  	struct strbuf author = STRBUF_INIT;
> +	struct strbuf mapped_author = STRBUF_INIT;
>  	struct strbuf oneline = STRBUF_INIT;
>  	static const char *author_match[2] = { "Author: ", "author " };
>  	static const char *committer_match[2] = { "Commit: ", "committer " };
> @@ -134,9 +140,15 @@ static void read_from_stdin(struct shortlog *log)
>  		while (strbuf_getline_lf(&oneline, stdin) != EOF &&
>  		       !oneline.len)
>  			; /* discard blanks */
> -		insert_one_record(log, v, oneline.buf);
> +
> +		strbuf_reset(&mapped_author);
> +		if (parse_stdin_author(log, &mapped_author, v) < 0)
> +			continue;
> +
> +		insert_one_record(log, mapped_author.buf, oneline.buf);
>  	}
>  	strbuf_release(&author);
> +	strbuf_release(&mapped_author);
>  	strbuf_release(&oneline);
>  }
>  
> @@ -153,7 +165,9 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
>  	ctx.date_mode.type = DATE_NORMAL;
>  	ctx.output_encoding = get_log_output_encoding();
>  
> -	fmt = log->committer ? "%cn <%ce>" : "%an <%ae>";
> +	fmt = log->committer ?
> +		(log->email ? "%cN <%cE>" : "%cN") :
> +		(log->email ? "%aN <%aE>" : "%aN");
>  
>  	format_commit_message(commit, fmt, &author, &ctx);
>  	if (!log->summary) {