git/builtin/shortlog.c
Jeff King 1ab03a57e1 shortlog: skip format/parse roundtrip for internal traversal
The original git-shortlog command parsed the output of
git-log, and the logic went something like this:

  1. Read stdin looking for "author" lines.

  2. Parse the identity into its name/email bits.

  3. Apply mailmap to the name/email.

  4. Reformat the identity into a single buffer that is our
     "key" for grouping entries (either a name by default,
     or "name <email>" if --email was given).

The first part happens in read_from_stdin(), and the other
three steps are part of insert_one_record().

When we do an internal traversal, we just swap out the stdin
read in step 1 for reading the commit objects ourselves.
Prior to 2db6b83d18 (shortlog: replace hand-parsing of
author with pretty-printer, 2016-01-18), that made sense; we
still had to parse the ident in the commit message.

But after that commit, we use pretty.c's "%an <%ae>" to get
the author ident (for simplicity). Which means that the
pretty printer is doing a parse/format under the hood, and
then we parse the result, apply the mailmap, and format the
result again.

Instead, we can just ask pretty.c to do all of those steps
for us (including the mailmap via "%aN <%aE>", and not
formatting the address when --email is missing).

And then we can push steps 2-4 into read_from_stdin(). This
speeds up "git shortlog -ns" on linux.git by about 3%, and
eliminates a leak in insert_one_record() of the namemailbuf
strbuf.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-09 01:57:03 +09:00

370 lines
9.6 KiB
C

#include "builtin.h"
#include "cache.h"
#include "config.h"
#include "commit.h"
#include "diff.h"
#include "string-list.h"
#include "revision.h"
#include "utf8.h"
#include "mailmap.h"
#include "shortlog.h"
#include "parse-options.h"
static char const * const shortlog_usage[] = {
N_("git shortlog [<options>] [<revision-range>] [[--] [<path>...]]"),
NULL
};
/*
* The util field of our string_list_items will contain one of two things:
*
* - if --summary is not in use, it will point to a string list of the
* oneline subjects assigned to this author
*
* - if --summary is in use, we don't need that list; we only need to know
* its size. So we abuse the pointer slot to store our integer counter.
*
* This macro accesses the latter.
*/
#define UTIL_TO_INT(x) ((intptr_t)(x)->util)
static int compare_by_counter(const void *a1, const void *a2)
{
const struct string_list_item *i1 = a1, *i2 = a2;
return UTIL_TO_INT(i2) - UTIL_TO_INT(i1);
}
static int compare_by_list(const void *a1, const void *a2)
{
const struct string_list_item *i1 = a1, *i2 = a2;
const struct string_list *l1 = i1->util, *l2 = i2->util;
if (l1->nr < l2->nr)
return 1;
else if (l1->nr == l2->nr)
return 0;
else
return -1;
}
static void insert_one_record(struct shortlog *log,
const char *author,
const char *oneline)
{
struct string_list_item *item;
item = string_list_insert(&log->list, author);
if (log->summary)
item->util = (void *)(UTIL_TO_INT(item) + 1);
else {
const char *dot3 = log->common_repo_prefix;
char *buffer, *p;
struct strbuf subject = STRBUF_INIT;
const char *eol;
/* Skip any leading whitespace, including any blank lines. */
while (*oneline && isspace(*oneline))
oneline++;
eol = strchr(oneline, '\n');
if (!eol)
eol = oneline + strlen(oneline);
if (starts_with(oneline, "[PATCH")) {
char *eob = strchr(oneline, ']');
if (eob && (!eol || eob < eol))
oneline = eob + 1;
}
while (*oneline && isspace(*oneline) && *oneline != '\n')
oneline++;
format_subject(&subject, oneline, " ");
buffer = strbuf_detach(&subject, NULL);
if (dot3) {
int dot3len = strlen(dot3);
if (dot3len > 5) {
while ((p = strstr(buffer, dot3)) != NULL) {
int taillen = strlen(p) - dot3len;
memcpy(p, "/.../", 5);
memmove(p + 5, p + dot3len, taillen + 1);
}
}
}
if (item->util == NULL)
item->util = xcalloc(1, sizeof(struct string_list));
string_list_append(item->util, buffer);
}
}
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 " };
const char **match;
match = log->committer ? committer_match : author_match;
while (strbuf_getline_lf(&author, stdin) != EOF) {
const char *v;
if (!skip_prefix(author.buf, match[0], &v) &&
!skip_prefix(author.buf, match[1], &v))
continue;
while (strbuf_getline_lf(&oneline, stdin) != EOF &&
oneline.len)
; /* discard headers */
while (strbuf_getline_lf(&oneline, stdin) != EOF &&
!oneline.len)
; /* discard blanks */
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);
}
void shortlog_add_commit(struct shortlog *log, struct commit *commit)
{
struct strbuf author = STRBUF_INIT;
struct strbuf oneline = STRBUF_INIT;
struct pretty_print_context ctx = {0};
const char *fmt;
ctx.fmt = CMIT_FMT_USERFORMAT;
ctx.abbrev = log->abbrev;
ctx.print_email_subject = 1;
ctx.date_mode.type = DATE_NORMAL;
ctx.output_encoding = get_log_output_encoding();
fmt = log->committer ?
(log->email ? "%cN <%cE>" : "%cN") :
(log->email ? "%aN <%aE>" : "%aN");
format_commit_message(commit, fmt, &author, &ctx);
if (!log->summary) {
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>");
strbuf_release(&author);
strbuf_release(&oneline);
}
static void get_from_rev(struct rev_info *rev, struct shortlog *log)
{
struct commit *commit;
if (prepare_revision_walk(rev))
die(_("revision walk setup failed"));
while ((commit = get_revision(rev)) != NULL)
shortlog_add_commit(log, commit);
}
static int parse_uint(char const **arg, int comma, int defval)
{
unsigned long ul;
int ret;
char *endp;
ul = strtoul(*arg, &endp, 10);
if (*endp && *endp != comma)
return -1;
if (ul > INT_MAX)
return -1;
ret = *arg == endp ? defval : (int)ul;
*arg = *endp ? endp + 1 : endp;
return ret;
}
static const char wrap_arg_usage[] = "-w[<width>[,<indent1>[,<indent2>]]]";
#define DEFAULT_WRAPLEN 76
#define DEFAULT_INDENT1 6
#define DEFAULT_INDENT2 9
static int parse_wrap_args(const struct option *opt, const char *arg, int unset)
{
struct shortlog *log = opt->value;
log->wrap_lines = !unset;
if (unset)
return 0;
if (!arg) {
log->wrap = DEFAULT_WRAPLEN;
log->in1 = DEFAULT_INDENT1;
log->in2 = DEFAULT_INDENT2;
return 0;
}
log->wrap = parse_uint(&arg, ',', DEFAULT_WRAPLEN);
log->in1 = parse_uint(&arg, ',', DEFAULT_INDENT1);
log->in2 = parse_uint(&arg, '\0', DEFAULT_INDENT2);
if (log->wrap < 0 || log->in1 < 0 || log->in2 < 0)
return error(wrap_arg_usage);
if (log->wrap &&
((log->in1 && log->wrap <= log->in1) ||
(log->in2 && log->wrap <= log->in2)))
return error(wrap_arg_usage);
return 0;
}
void shortlog_init(struct shortlog *log)
{
memset(log, 0, sizeof(*log));
read_mailmap(&log->mailmap, &log->common_repo_prefix);
log->list.strdup_strings = 1;
log->wrap = DEFAULT_WRAPLEN;
log->in1 = DEFAULT_INDENT1;
log->in2 = DEFAULT_INDENT2;
}
int cmd_shortlog(int argc, const char **argv, const char *prefix)
{
struct shortlog log = { STRING_LIST_INIT_NODUP };
struct rev_info rev;
int nongit = !startup_info->have_repository;
const struct option options[] = {
OPT_BOOL('c', "committer", &log.committer,
N_("Group by committer rather than author")),
OPT_BOOL('n', "numbered", &log.sort_by_number,
N_("sort output according to the number of commits per author")),
OPT_BOOL('s', "summary", &log.summary,
N_("Suppress commit descriptions, only provides commit count")),
OPT_BOOL('e', "email", &log.email,
N_("Show the email address of each author")),
{ OPTION_CALLBACK, 'w', NULL, &log, N_("w[,i1[,i2]]"),
N_("Linewrap output"), PARSE_OPT_OPTARG, &parse_wrap_args },
OPT_END(),
};
struct parse_opt_ctx_t ctx;
git_config(git_default_config, NULL);
shortlog_init(&log);
init_revisions(&rev, prefix);
parse_options_start(&ctx, argc, argv, prefix, options,
PARSE_OPT_KEEP_DASHDASH | PARSE_OPT_KEEP_ARGV0);
for (;;) {
switch (parse_options_step(&ctx, options, shortlog_usage)) {
case PARSE_OPT_HELP:
exit(129);
case PARSE_OPT_DONE:
goto parse_done;
}
parse_revision_opt(&rev, &ctx, options, shortlog_usage);
}
parse_done:
argc = parse_options_end(&ctx);
if (setup_revisions(argc, argv, &rev, NULL) != 1) {
error(_("unrecognized argument: %s"), argv[1]);
usage_with_options(shortlog_usage, options);
}
log.user_format = rev.commit_format == CMIT_FMT_USERFORMAT;
log.abbrev = rev.abbrev;
log.file = rev.diffopt.file;
/* assume HEAD if from a tty */
if (!nongit && !rev.pending.nr && isatty(0))
add_head_to_pending(&rev);
if (rev.pending.nr == 0) {
if (isatty(0))
fprintf(stderr, _("(reading log message from standard input)\n"));
read_from_stdin(&log);
}
else
get_from_rev(&rev, &log);
shortlog_output(&log);
if (log.file != stdout)
fclose(log.file);
return 0;
}
static void add_wrapped_shortlog_msg(struct strbuf *sb, const char *s,
const struct shortlog *log)
{
strbuf_add_wrapped_text(sb, s, log->in1, log->in2, log->wrap);
strbuf_addch(sb, '\n');
}
void shortlog_output(struct shortlog *log)
{
int i, j;
struct strbuf sb = STRBUF_INIT;
if (log->sort_by_number)
QSORT(log->list.items, log->list.nr,
log->summary ? compare_by_counter : compare_by_list);
for (i = 0; i < log->list.nr; i++) {
const struct string_list_item *item = &log->list.items[i];
if (log->summary) {
fprintf(log->file, "%6d\t%s\n",
(int)UTIL_TO_INT(item), item->string);
} else {
struct string_list *onelines = item->util;
fprintf(log->file, "%s (%d):\n",
item->string, onelines->nr);
for (j = onelines->nr - 1; j >= 0; j--) {
const char *msg = onelines->items[j].string;
if (log->wrap_lines) {
strbuf_reset(&sb);
add_wrapped_shortlog_msg(&sb, msg, log);
fwrite(sb.buf, sb.len, 1, log->file);
}
else
fprintf(log->file, " %s\n", msg);
}
putc('\n', log->file);
onelines->strdup_strings = 1;
string_list_clear(onelines, 0);
free(onelines);
}
log->list.items[i].util = NULL;
}
strbuf_release(&sb);
log->list.strdup_strings = 1;
string_list_clear(&log->list, 1);
clear_mailmap(&log->mailmap);
}