shortlog: replace hand-parsing of author with pretty-printer

When gathering the author and oneline subject for each
commit, we hand-parse the commit headers to find the
"author" line, and then continue past to the blank line at
the end of the header.

We can replace this tricky hand-parsing by simply asking the
pretty-printer for the relevant items. This also decouples
the author and oneline parsing, opening up some new
optimizations in further commits.

One reason to avoid the pretty-printer is that it might be
less efficient than hand-parsing. However, I measured no
slowdown at all running "git shortlog -ns HEAD" on
linux.git.

As a bonus, we also fix a memory leak in the (uncommon) case
that the author field is blank.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Jeff King 2016-01-18 15:02:48 -05:00 committed by Junio C Hamano
parent 50250491bd
commit 2db6b83d18

View File

@ -113,45 +113,35 @@ static void read_from_stdin(struct shortlog *log)
void shortlog_add_commit(struct shortlog *log, struct commit *commit)
{
const char *author = NULL, *buffer;
struct strbuf buf = STRBUF_INIT;
struct strbuf ufbuf = STRBUF_INIT;
struct strbuf author = STRBUF_INIT;
struct strbuf oneline = STRBUF_INIT;
struct pretty_print_context ctx = {0};
pp_commit_easy(CMIT_FMT_RAW, commit, &buf);
buffer = buf.buf;
while (*buffer && *buffer != '\n') {
const char *eol = strchr(buffer, '\n');
ctx.fmt = CMIT_FMT_USERFORMAT;
ctx.abbrev = log->abbrev;
ctx.subject = "";
ctx.after_subject = "";
ctx.date_mode.type = DATE_NORMAL;
ctx.output_encoding = get_log_output_encoding();
if (eol == NULL)
eol = buffer + strlen(buffer);
else
eol++;
if (starts_with(buffer, "author "))
author = buffer + 7;
buffer = eol;
}
if (!author) {
format_commit_message(commit, "%an <%ae>", &author, &ctx);
/* we can detect a total failure only by seeing " <>" in the output */
if (author.len <= 3) {
warning(_("Missing author: %s"),
oid_to_hex(&commit->object.oid));
return;
goto out;
}
if (log->user_format) {
struct pretty_print_context ctx = {0};
ctx.fmt = CMIT_FMT_USERFORMAT;
ctx.abbrev = log->abbrev;
ctx.subject = "";
ctx.after_subject = "";
ctx.date_mode.type = DATE_NORMAL;
ctx.output_encoding = get_log_output_encoding();
pretty_print_commit(&ctx, commit, &ufbuf);
buffer = ufbuf.buf;
} else if (*buffer) {
buffer++;
}
insert_one_record(log, author, !*buffer ? "<none>" : buffer);
strbuf_release(&ufbuf);
strbuf_release(&buf);
if (log->user_format)
pretty_print_commit(&ctx, commit, &oneline);
else
format_commit_message(commit, "%s", &oneline, &ctx);
insert_one_record(log, author.buf, oneline.len ? oneline.buf : "<none>");
out:
strbuf_release(&author);
strbuf_release(&oneline);
}
static void get_from_rev(struct rev_info *rev, struct shortlog *log)