cat-file: add --batch-check=<format>
The `cat-file --batch-check` command can be used to quickly get information about a large number of objects. However, it provides a fixed set of information. This patch adds an optional <format> option to --batch-check to allow a caller to specify which items they are interested in, and in which order to output them. This is not very exciting for now, since we provide the same limited set that you could already get. However, it opens the door to adding new format items in the future without breaking backwards compatibility (or forcing callers to pay the cost to calculate uninteresting items). Since the --batch option shares code with --batch-check, it receives the same feature, though it is less likely to be of interest there. The format atom names are chosen to match their counterparts in for-each-ref. Though we do not (yet) share any code with for-each-ref's formatter, this keeps the interface as consistent as possible, and may help later on if the implementations are unified. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Jeff King committed
Jul 10, 2013 at 07:45 UTC
93d2a607ba05fba31442941d0425019120993846
3 files changed
+142
-26
Documentation/git-cat-file.txt
+44
-11
@@ -58,12 +58,16 @@ OPTIONS
58
to apply the filter to the content recorded in the index at <path>.
59
60
--batch::
61
- Print the SHA-1, type, size, and contents of each object provided on
62
- stdin. May not be combined with any other options or arguments.
61
+--batch=<format>::
62
+ Print object information and contents for each object provided
63
+ on stdin. May not be combined with any other options or arguments.
64
+ See the section `BATCH OUTPUT` below for details.
65
66
--batch-check::
65
- Print the SHA-1, type, and size of each object provided on stdin. May not
66
- be combined with any other options or arguments.
67
+--batch-check=<format>::
68
+ Print object information for each object provided on stdin. May
69
+ not be combined with any other options or arguments. See the
70
+ section `BATCH OUTPUT` below for details.
71
72
OUTPUT
73
------
@@ -78,23 +82,52 @@ If '-p' is specified, the contents of <object> are pretty-printed.
82
If <type> is specified, the raw (though uncompressed) contents of the <object>
83
will be returned.
84
81
-If '--batch' is specified, output of the following form is printed for each
82
-object specified on stdin:
85
+BATCH OUTPUT
86
+------------
87
+
88
+If `--batch` or `--batch-check` is given, `cat-file` will read objects
89
+from stdin, one per line, and print information about them.
90
+
91
+Each line is considered as a whole object name, and is parsed as if
92
+given to linkgit:git-rev-parse[1].
93
+
94
+You can specify the information shown for each object by using a custom
95
+`<format>`. The `<format>` is copied literally to stdout for each
96
+object, with placeholders of the form `%(atom)` expanded, followed by a
97
+newline. The available atoms are:
98
+
99
+`objectname`::
100
+ The 40-hex object name of the object.
101
+
102
+`objecttype`::
103
+ The type of of the object (the same as `cat-file -t` reports).
104
+
105
+`objectsize`::
106
+ The size, in bytes, of the object (the same as `cat-file -s`
107
+ reports).
108
+
109
+If no format is specified, the default format is `%(objectname)
110
+%(objecttype) %(objectsize)`.
111
+
112
+If `--batch` is specified, the object information is followed by the
113
+object contents (consisting of `%(objectsize)` bytes), followed by a
114
+newline.
115
+
116
+For example, `--batch` without a custom format would produce:
117
118
------------
119
<sha1> SP <type> SP <size> LF
120
<contents> LF
121
------------
122
89
-If '--batch-check' is specified, output of the following form is printed for
90
-each object specified on stdin:
123
+Whereas `--batch-check='%(objectname) %(objecttype)'` would produce:
124
125
------------
93
-<sha1> SP <type> SP <size> LF
126
+<sha1> SP <type> LF
127
------------
128
96
-For both '--batch' and '--batch-check', output of the following form is printed
97
-for each object specified on stdin that does not exist in the repository:
129
+If a name is specified on stdin that cannot be resolved to an object in
130
+the repository, then `cat-file` will ignore any custom format and print:
131
132
------------
133
<object> SP missing LF
builtin/cat-file.c
+92
-15
@@ -114,6 +114,66 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
114
return 0;
115
}
116
117
+struct expand_data {
118
+ unsigned char sha1[20];
119
+ enum object_type type;
120
+ unsigned long size;
121
+
122
+ /*
123
+ * If mark_query is true, we do not expand anything, but rather
124
+ * just mark the object_info with items we wish to query.
125
+ */
126
+ int mark_query;
127
+
128
+ /*
129
+ * After a mark_query run, this object_info is set up to be
130
+ * passed to sha1_object_info_extended. It will point to the data
131
+ * elements above, so you can retrieve the response from there.
132
+ */
133
+ struct object_info info;
134
+};
135
+
136
+static int is_atom(const char *atom, const char *s, int slen)
137
+{
138
+ int alen = strlen(atom);
139
+ return alen == slen && !memcmp(atom, s, alen);
140
+}
141
+
142
+static void expand_atom(struct strbuf *sb, const char *atom, int len,
143
+ void *vdata)
144
+{
145
+ struct expand_data *data = vdata;
146
+
147
+ if (is_atom("objectname", atom, len)) {
148
+ if (!data->mark_query)
149
+ strbuf_addstr(sb, sha1_to_hex(data->sha1));
150
+ } else if (is_atom("objecttype", atom, len)) {
151
+ if (!data->mark_query)
152
+ strbuf_addstr(sb, typename(data->type));
153
+ } else if (is_atom("objectsize", atom, len)) {
154
+ if (data->mark_query)
155
+ data->info.sizep = &data->size;
156
+ else
157
+ strbuf_addf(sb, "%lu", data->size);
158
+ } else
159
+ die("unknown format element: %.*s", len, atom);
160
+}
161
+
162
+static size_t expand_format(struct strbuf *sb, const char *start, void *data)
163
+{
164
+ const char *end;
165
+
166
+ if (*start != '(')
167
+ return 0;
168
+ end = strchr(start + 1, ')');
169
+ if (!end)
170
+ die("format element '%s' does not end in ')'", start);
171
+
172
+ expand_atom(sb, start + 1, end - start - 1, data);
173
+
174
+ return end - start + 1;
175
+}
176
+
177
static void print_object_or_die(int fd, const unsigned char *sha1,
178
enum object_type type, unsigned long size)
179
{
@@ -142,35 +202,37 @@ static void print_object_or_die(int fd, const unsigned char *sha1,
202
struct batch_options {
203
int enabled;
204
int print_contents;
205
+ const char *format;
206
};
207
147
-static int batch_one_object(const char *obj_name, struct batch_options *opt)
208
+static int batch_one_object(const char *obj_name, struct batch_options *opt,
209
+ struct expand_data *data)
210
{
149
- unsigned char sha1[20];
150
- enum object_type type = 0;
151
- unsigned long size;
211
+ struct strbuf buf = STRBUF_INIT;
212
213
if (!obj_name)
214
return 1;
215
156
- if (get_sha1(obj_name, sha1)) {
216
+ if (get_sha1(obj_name, data->sha1)) {
217
printf("%s missing\n", obj_name);
218
fflush(stdout);
219
return 0;
220
}
221
162
- type = sha1_object_info(sha1, &size);
163
- if (type <= 0) {
222
+ data->type = sha1_object_info_extended(data->sha1, &data->info);
223
+ if (data->type <= 0) {
224
printf("%s missing\n", obj_name);
225
fflush(stdout);
226
return 0;
227
}
228
169
- printf("%s %s %lu\n", sha1_to_hex(sha1), typename(type), size);
170
- fflush(stdout);
229
+ strbuf_expand(&buf, opt->format, expand_format, data);
230
+ strbuf_addch(&buf, '\n');
231
+ write_or_die(1, buf.buf, buf.len);
232
+ strbuf_release(&buf);
233
234
if (opt->print_contents) {
173
- print_object_or_die(1, sha1, type, size);
235
+ print_object_or_die(1, data->sha1, data->type, data->size);
236
write_or_die(1, "\n", 1);
237
}
238
return 0;
@@ -179,9 +241,23 @@ static int batch_one_object(const char *obj_name, struct batch_options *opt)
241
static int batch_objects(struct batch_options *opt)
242
{
243
struct strbuf buf = STRBUF_INIT;
244
+ struct expand_data data;
245
+
246
+ if (!opt->format)
247
+ opt->format = "%(objectname) %(objecttype) %(objectsize)";
248
+
249
+ /*
250
+ * Expand once with our special mark_query flag, which will prime the
251
+ * object_info to be handed to sha1_object_info_extended for each
252
+ * object.
253
+ */
254
+ memset(&data, 0, sizeof(data));
255
+ data.mark_query = 1;
256
+ strbuf_expand(&buf, opt->format, expand_format, &data);
257
+ data.mark_query = 0;
258
259
while (strbuf_getline(&buf, stdin, '\n') != EOF) {
184
- int error = batch_one_object(buf.buf, opt);
260
+ int error = batch_one_object(buf.buf, opt, &data);
261
if (error)
262
return error;
263
}
@@ -216,6 +292,7 @@ static int batch_option_callback(const struct option *opt,
292
293
bo->enabled = 1;
294
bo->print_contents = !strcmp(opt->long_name, "batch");
295
+ bo->format = arg;
296
297
return 0;
298
}
@@ -235,12 +312,12 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
312
OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
313
OPT_SET_INT(0, "textconv", &opt,
314
N_("for blob objects, run textconv on object's content"), 'c'),
238
- { OPTION_CALLBACK, 0, "batch", &batch, NULL,
315
+ { OPTION_CALLBACK, 0, "batch", &batch, "format",
316
N_("show info and content of objects fed from the standard input"),
240
- PARSE_OPT_NOARG, batch_option_callback },
241
- { OPTION_CALLBACK, 0, "batch-check", &batch, NULL,
317
+ PARSE_OPT_OPTARG, batch_option_callback },
318
+ { OPTION_CALLBACK, 0, "batch-check", &batch, "format",
319
N_("show info about objects fed from the standard input"),
243
- PARSE_OPT_NOARG, batch_option_callback },
320
+ PARSE_OPT_OPTARG, batch_option_callback },
321
OPT_END()
322
};
323
t/t1006-cat-file.sh
+6
@@ -72,6 +72,12 @@ $content"
72
echo_without_newline $sha1 | git cat-file --batch-check >actual &&
73
test_cmp expect actual
74
'
75
+
76
+ test_expect_success "custom --batch-check format" '
77
+ echo "$type $sha1" >expect &&
78
+ echo $sha1 | git cat-file --batch-check="%(objecttype) %(objectname)" >actual &&
79
+ test_cmp expect actual
80
+ '
81
}
82
83
hello_content="Hello World"