shortlog: support arbitrary commit format `--group`s
In addition to generating a shortlog based on committer, author, or the identity in one or more specified trailers, it can be useful to generate a shortlog based on an arbitrary commit format. This can be used, for example, to generate a distribution of commit activity over time, like so: $ git shortlog --group='%cd' --date='format:%Y-%m' -s v2.37.0.. 117 2022-06 274 2022-07 324 2022-08 263 2022-09 7 2022-10 Arbitrary commit formats can be used. In fact, `git shortlog`'s default behavior (to count by commit authors) can be emulated as follows: $ git shortlog --group='%aN <%aE>' ... and future patches will make the default behavior (as well as `--committer`, and `--group=trailer:<trailer>`) special cases of the more flexible `--group` option. Note also that the SHORTLOG_GROUP_FORMAT enum value is used only to designate that `--group:<format>` is in use when in stdin mode to declare that the combination is invalid. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Taylor Blau committed
Oct 24, 2022 at 14:55 UTC
3dc95e09e1355ebde472bd5be37aa7b29ef774d3
4 files changed
+78
-2
Documentation/git-shortlog.txt
+4
-1
@@ -50,7 +50,7 @@ OPTIONS
50
--date=<format>::
51
Show dates formatted according to the given date string. (See
52
the `--date` option in the "Commit Formatting" section of
53
- linkgit:git-log[1]).
53
+ linkgit:git-log[1]). Useful with `--group=format:<format>`.
54
55
--group=<type>::
56
Group commits based on `<type>`. If no `--group` option is
@@ -64,6 +64,9 @@ OPTIONS
64
example, if your project uses `Reviewed-by` trailers, you might want
65
to see who has been reviewing with
66
`git shortlog -ns --group=trailer:reviewed-by`.
67
+ - `format:<format>`, any string accepted by the `--format` option of
68
+ 'git log'. (See the "PRETTY FORMATS" section of
69
+ linkgit:git-log[1].)
70
+
71
Note that commits that do not include the trailer will not be counted.
72
Likewise, commits with multiple trailers (e.g., multiple signoffs) may
builtin/shortlog.c
+40
-1
@@ -133,6 +133,8 @@ static void read_from_stdin(struct shortlog *log)
133
break;
134
case SHORTLOG_GROUP_TRAILER:
135
die(_("using %s with stdin is not supported"), "--group=trailer");
136
+ case SHORTLOG_GROUP_FORMAT:
137
+ die(_("using %s with stdin is not supported"), "--group=format");
138
default:
139
BUG("unhandled shortlog group");
140
}
@@ -203,6 +205,32 @@ static void insert_records_from_trailers(struct shortlog *log,
205
unuse_commit_buffer(commit, commit_buffer);
206
}
207
208
+static int shortlog_needs_dedup(const struct shortlog *log)
209
+{
210
+ return HAS_MULTI_BITS(log->groups) || log->format.nr > 1 || log->trailers.nr;
211
+}
212
+
213
+static void insert_records_from_format(struct shortlog *log,
214
+ struct strset *dups,
215
+ struct commit *commit,
216
+ struct pretty_print_context *ctx,
217
+ const char *oneline)
218
+{
219
+ struct strbuf buf = STRBUF_INIT;
220
+ struct string_list_item *item;
221
+
222
+ for_each_string_list_item(item, &log->format) {
223
+ strbuf_reset(&buf);
224
+
225
+ format_commit_message(commit, item->string, &buf, ctx);
226
+
227
+ if (!shortlog_needs_dedup(log) || strset_add(dups, buf.buf))
228
+ insert_one_record(log, buf.buf, oneline);
229
+ }
230
+
231
+ strbuf_release(&buf);
232
+}
233
+
234
void shortlog_add_commit(struct shortlog *log, struct commit *commit)
235
{
236
struct strbuf ident = STRBUF_INIT;
@@ -244,6 +272,7 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
272
insert_one_record(log, ident.buf, oneline_str);
273
}
274
insert_records_from_trailers(log, &dups, commit, &ctx, oneline_str);
275
+ insert_records_from_format(log, &dups, commit, &ctx, oneline_str);
276
277
strset_clear(&dups);
278
strbuf_release(&ident);
@@ -315,6 +344,7 @@ static int parse_group_option(const struct option *opt, const char *arg, int uns
344
if (unset) {
345
log->groups = 0;
346
string_list_clear(&log->trailers, 0);
347
+ string_list_clear(&log->format, 0);
348
} else if (!strcasecmp(arg, "author"))
349
log->groups |= SHORTLOG_GROUP_AUTHOR;
350
else if (!strcasecmp(arg, "committer"))
@@ -322,8 +352,15 @@ static int parse_group_option(const struct option *opt, const char *arg, int uns
352
else if (skip_prefix(arg, "trailer:", &field)) {
353
log->groups |= SHORTLOG_GROUP_TRAILER;
354
string_list_append(&log->trailers, field);
325
- } else
355
+ } else if (skip_prefix(arg, "format:", &field)) {
356
+ log->groups |= SHORTLOG_GROUP_FORMAT;
357
+ string_list_append(&log->format, field);
358
+ } else if (strchr(arg, '%')) {
359
+ log->groups |= SHORTLOG_GROUP_FORMAT;
360
+ string_list_append(&log->format, arg);
361
+ } else {
362
return error(_("unknown group type: %s"), arg);
363
+ }
364
365
return 0;
366
}
@@ -341,6 +378,7 @@ void shortlog_init(struct shortlog *log)
378
log->in2 = DEFAULT_INDENT2;
379
log->trailers.strdup_strings = 1;
380
log->trailers.cmp = strcasecmp;
381
+ log->format.strdup_strings = 1;
382
}
383
384
int cmd_shortlog(int argc, const char **argv, const char *prefix)
@@ -481,4 +519,5 @@ void shortlog_output(struct shortlog *log)
519
log->list.strdup_strings = 1;
520
string_list_clear(&log->list, 1);
521
clear_mailmap(&log->mailmap);
522
+ string_list_clear(&log->format, 0);
523
}
shortlog.h
+2
@@ -22,8 +22,10 @@ struct shortlog {
22
SHORTLOG_GROUP_AUTHOR = (1 << 0),
23
SHORTLOG_GROUP_COMMITTER = (1 << 1),
24
SHORTLOG_GROUP_TRAILER = (1 << 2),
25
+ SHORTLOG_GROUP_FORMAT = (1 << 3),
26
} groups;
27
struct string_list trailers;
28
+ struct string_list format;
29
30
int email;
31
struct string_list mailmap;
t/t4201-shortlog.sh
+32
@@ -244,6 +244,26 @@ test_expect_success 'shortlog --group=trailer:signed-off-by' '
244
test_cmp expect actual
245
'
246
247
+test_expect_success 'shortlog --group=format' '
248
+ git shortlog -s --date="format:%Y" --group="format:%cN (%cd)" \
249
+ HEAD >actual &&
250
+ cat >expect <<-\EOF &&
251
+ 4 C O Mitter (2005)
252
+ 1 Sin Nombre (2005)
253
+ EOF
254
+ test_cmp expect actual
255
+'
256
+
257
+test_expect_success 'shortlog --group=<format> DWIM' '
258
+ git shortlog -s --date="format:%Y" --group="%cN (%cd)" HEAD >actual &&
259
+ test_cmp expect actual
260
+'
261
+
262
+test_expect_success 'shortlog bogus --group' '
263
+ test_must_fail git shortlog --group=bogus HEAD 2>err &&
264
+ grep "unknown group type" err
265
+'
266
+
267
test_expect_success 'trailer idents are split' '
268
cat >expect <<-\EOF &&
269
2 C O Mitter
@@ -326,6 +346,18 @@ test_expect_success 'shortlog can match multiple groups' '
346
test_cmp expect actual
347
'
348
349
+test_expect_success 'shortlog can match multiple format groups' '
350
+ GIT_COMMITTER_NAME="$GIT_AUTHOR_NAME" \
351
+ git commit --allow-empty -m "identical names" &&
352
+ test_tick &&
353
+ cat >expect <<-\EOF &&
354
+ 2 A U Thor
355
+ 1 C O Mitter
356
+ EOF
357
+ git shortlog -ns --group="%cn" --group="%an" -2 HEAD >actual &&
358
+ test_cmp expect actual
359
+'
360
+
361
test_expect_success 'set up option selection tests' '
362
git commit --allow-empty -F - <<-\EOF
363
subject