cat-file: split --batch input lines on whitespace

If we get an input line to --batch or --batch-check that
looks like "HEAD foo bar", we will currently feed the whole
thing to get_sha1(). This means that to use --batch-check
with `rev-list --objects`, one must pre-process the input,
like:

git rev-list --objects HEAD |
cut -d' ' -f1 |
git cat-file --batch-check

Besides being more typing and slightly less efficient to
invoke `cut`, the result loses information: we no longer
know which path each object was found at.

This patch teaches cat-file to split input lines at the
first whitespace. Everything to the left of the whitespace
is considered an object name, and everything to the right is
made available as the %(reset) atom. So you can now do:

git rev-list --objects HEAD |
git cat-file --batch-check='%(objectsize) %(rest)'

to collect object sizes at particular paths.

Even if %(rest) is not used, we always do the whitespace
split (which means you can simply eliminate the `cut`
command from the first example above).

This whitespace split is backwards compatible for any
reasonable input. Object names cannot contain spaces, so any
input with spaces would have resulted in a "missing" line.
The only input hurt is if somebody really expected input of
the form "HEAD is a fine-looking ref!" to fail; it will now
parse HEAD, and make "is a fine-looking ref!" available as
%(rest).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index 10fbc6a373758437f23ef80245b3bd9e164add1f..3ddec0b65ba82dbfdf10569e4c7ec2ac148e08b4 100644 (file)
--- a/Documentation/git-cat-file.txt
+++ b/Documentation/git-cat-file.txt
@@ -88,8 +88,10 @@ BATCH OUTPUT
 If `--batch` or `--batch-check` is given, `cat-file` will read objects
 from stdin, one per line, and print information about them.
 
 If `--batch` or `--batch-check` is given, `cat-file` will read objects
 from stdin, one per line, and print information about them.
 

-Each line is considered as a whole object name, and is parsed as if
-given to linkgit:git-rev-parse[1].
+Each line is split at the first whitespace boundary. All characters
+before that whitespace are considered as a whole object name, and are
+parsed as if given to linkgit:git-rev-parse[1]. Characters after that
+whitespace can be accessed using the `%(rest)` atom (see below).

 
 You can specify the information shown for each object by using a custom
 `<format>`. The `<format>` is copied literally to stdout for each
 
 You can specify the information shown for each object by using a custom
 `<format>`. The `<format>` is copied literally to stdout for each


@@ -110,6 +112,10 @@ newline. The available atoms are:
        The size, in bytes, that the object takes up on disk. See the
        note about on-disk sizes in the `CAVEATS` section below.
 
        The size, in bytes, that the object takes up on disk. See the
        note about on-disk sizes in the `CAVEATS` section below.
 

+`rest`::
+       The text (if any) found after the first run of whitespace on the
+       input line (i.e., the "rest" of the line).
+

 If no format is specified, the default format is `%(objectname)
 %(objecttype) %(objectsize)`.
 
 If no format is specified, the default format is `%(objectname)
 %(objecttype) %(objectsize)`.
 

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 11fa8c08bc149df3504d67b270ea7deb44dbdc5e..0e64b4159c4f8a81ed1d346631f6c3894297ceeb 100644 (file)
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -119,6 +119,7 @@ struct expand_data {
        enum object_type type;
        unsigned long size;
        unsigned long disk_size;
        enum object_type type;
        unsigned long size;
        unsigned long disk_size;

+       const char *rest;

 
        /*
         * If mark_query is true, we do not expand anything, but rather
 
        /*
         * If mark_query is true, we do not expand anything, but rather


@@ -161,6 +162,9 @@ static void expand_atom(struct strbuf *sb, const char *atom, int len,
                        data->info.disk_sizep = &data->disk_size;
                else
                        strbuf_addf(sb, "%lu", data->disk_size);
                        data->info.disk_sizep = &data->disk_size;
                else
                        strbuf_addf(sb, "%lu", data->disk_size);

+       } else if (is_atom("rest", atom, len)) {
+               if (!data->mark_query && data->rest)
+                       strbuf_addstr(sb, data->rest);

        } else
                die("unknown format element: %.*s", len, atom);
 }
        } else
                die("unknown format element: %.*s", len, atom);
 }


@@ -263,7 +267,21 @@ static int batch_objects(struct batch_options *opt)
        data.mark_query = 0;
 
        while (strbuf_getline(&buf, stdin, '\n') != EOF) {
        data.mark_query = 0;
 
        while (strbuf_getline(&buf, stdin, '\n') != EOF) {

-               int error = batch_one_object(buf.buf, opt, &data);
+               char *p;
+               int error;
+
+               /*
+                * Split at first whitespace, tying off the beginning of the
+                * string and saving the remainder (or NULL) in data.rest.
+                */
+               p = strpbrk(buf.buf, " \t");
+               if (p) {
+                       while (*p && strchr(" \t", *p))
+                               *p++ = '\0';
+               }
+               data.rest = p;
+
+               error = batch_one_object(buf.buf, opt, &data);

                if (error)
                        return error;
        }
                if (error)
                        return error;
        }

diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
index 4e911fb43d8ea2c699b3a836547b618274db6e05..d499d02a29f3ec5fb15d86835d24ccabd322df56 100755 (executable)
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@ -78,6 +78,13 @@ $content"
        echo $sha1 | git cat-file --batch-check="%(objecttype) %(objectname)" >actual &&
        test_cmp expect actual
     '
        echo $sha1 | git cat-file --batch-check="%(objecttype) %(objectname)" >actual &&
        test_cmp expect actual
     '

+
+    test_expect_success '--batch-check with %(rest)' '
+       echo "$type this is some extra content" >expect &&
+       echo "$sha1    this is some extra content" |
+               git cat-file --batch-check="%(objecttype) %(rest)" >actual &&
+       test_cmp expect actual
+    '

 }
 
 hello_content="Hello World"
 }
 
 hello_content="Hello World"