cat-file: introduce the --filters option

The --filters option applies the convert_to_working_tree() filter for
the path when showing the contents of a regular file blob object;
the contents are written out as-is for other types of objects.

This feature comes in handy when a 3rd-party tool wants to work with
the contents of files from past revisions as if they had been checked
out, but without detouring via temporary files.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index 071029b4effac9bccb8ddf6821335af9830ed7ef..537d02c87ce63b5e82f07e84809548f5710c681e 100644 (file)
--- a/Documentation/git-cat-file.txt
+++ b/Documentation/git-cat-file.txt
@@ -9,15 +9,15 @@ git-cat-file - Provide content or type and size information for repository objec
 SYNOPSIS
 --------
 [verse]
 SYNOPSIS
 --------
 [verse]

-'git cat-file' (-t [--allow-unknown-type]| -s [--allow-unknown-type]| -e | -p | <type> | --textconv ) <object>
+'git cat-file' (-t [--allow-unknown-type]| -s [--allow-unknown-type]| -e | -p | <type> | --textconv | --filters ) <object>

 'git cat-file' (--batch | --batch-check) [--follow-symlinks]
 
 DESCRIPTION
 -----------
 In its first form, the command provides the content or the type of an object in
 the repository. The type is required unless `-t` or `-p` is used to find the
 'git cat-file' (--batch | --batch-check) [--follow-symlinks]
 
 DESCRIPTION
 -----------
 In its first form, the command provides the content or the type of an object in
 the repository. The type is required unless `-t` or `-p` is used to find the

-object type, or `-s` is used to find the object size, or `--textconv` is used
-(which implies type "blob").
+object type, or `-s` is used to find the object size, or `--textconv` or
+`--filters` is used (which imply type "blob").

 
 In the second form, a list of objects (separated by linefeeds) is provided on
 stdin, and the SHA-1, type, and size of each object is printed on stdout.
 
 In the second form, a list of objects (separated by linefeeds) is provided on
 stdin, and the SHA-1, type, and size of each object is printed on stdout.


@@ -58,6 +58,12 @@ OPTIONS
        order to apply the filter to the content recorded in the index at
        <path>.
 
        order to apply the filter to the content recorded in the index at
        <path>.
 

+--filters::
+       Show the content as converted by the filters configured in
+       the current working tree for the given <path> (i.e. smudge filters,
+       end-of-line conversion, etc). In this case, <object> has to be of
+       the form <tree-ish>:<path>, or :<path>.
+

 --batch::
 --batch=<format>::
        Print object information and contents for each object provided
 --batch::
 --batch=<format>::
        Print object information and contents for each object provided

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 2dfe6265f7df6099b51645fa67dbeeb3f4f567a4..96007cb1a010630a9e3fb2c9b2fba11a6b1c83e1 100644 (file)
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -20,6 +20,28 @@ struct batch_options {
        const char *format;
 };
 
        const char *format;
 };
 

+static int filter_object(const char *path, unsigned mode,
+                        const unsigned char *sha1,
+                        char **buf, unsigned long *size)
+{
+       enum object_type type;
+
+       *buf = read_sha1_file(sha1, &type, size);
+       if (!*buf)
+               return error(_("cannot read object %s '%s'"),
+                       sha1_to_hex(sha1), path);
+       if ((type == OBJ_BLOB) && S_ISREG(mode)) {
+               struct strbuf strbuf = STRBUF_INIT;
+               if (convert_to_working_tree(path, *buf, *size, &strbuf)) {
+                       free(*buf);
+                       *size = strbuf.len;
+                       *buf = strbuf_detach(&strbuf, NULL);
+               }
+       }
+
+       return 0;
+}
+

 static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
                        int unknown_type)
 {
 static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
                        int unknown_type)
 {


@@ -61,6 +83,16 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
        case 'e':
                return !has_sha1_file(sha1);
 
        case 'e':
                return !has_sha1_file(sha1);
 

+       case 'w':
+               if (!obj_context.path[0])
+                       die("git cat-file --filters %s: <object> must be "
+                           "<sha1:path>", obj_name);
+
+               if (filter_object(obj_context.path, obj_context.mode,
+                                 sha1, &buf, &size))
+                       return -1;
+               break;
+

        case 'c':
                if (!obj_context.path[0])
                        die("git cat-file --textconv %s: <object> must be <sha1:path>",
        case 'c':
                if (!obj_context.path[0])
                        die("git cat-file --textconv %s: <object> must be <sha1:path>",


@@ -440,7 +472,7 @@ static int batch_objects(struct batch_options *opt)
 }
 
 static const char * const cat_file_usage[] = {
 }
 
 static const char * const cat_file_usage[] = {

-       N_("git cat-file (-t [--allow-unknown-type]|-s [--allow-unknown-type]|-e|-p|<type>|--textconv) <object>"),
+       N_("git cat-file (-t [--allow-unknown-type]|-s [--allow-unknown-type]|-e|-p|<type>|--textconv|--filters) <object>"),

        N_("git cat-file (--batch | --batch-check) [--follow-symlinks]"),
        NULL
 };
        N_("git cat-file (--batch | --batch-check) [--follow-symlinks]"),
        NULL
 };


@@ -486,6 +518,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
                OPT_CMDMODE('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
                OPT_CMDMODE(0, "textconv", &opt,
                            N_("for blob objects, run textconv on object's content"), 'c'),
                OPT_CMDMODE('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
                OPT_CMDMODE(0, "textconv", &opt,
                            N_("for blob objects, run textconv on object's content"), 'c'),

+               OPT_CMDMODE(0, "filters", &opt,
+                           N_("for blob objects, run filters on object's content"), 'w'),

                OPT_BOOL(0, "allow-unknown-type", &unknown_type,
                          N_("allow -s and -t to work with broken/corrupt objects")),
                OPT_BOOL(0, "buffer", &batch.buffer_output, N_("buffer --batch output")),
                OPT_BOOL(0, "allow-unknown-type", &unknown_type,
                          N_("allow -s and -t to work with broken/corrupt objects")),
                OPT_BOOL(0, "buffer", &batch.buffer_output, N_("buffer --batch output")),

diff --git a/t/t8010-cat-file-filters.sh b/t/t8010-cat-file-filters.sh
new file mode 100755 (executable)
index 0000000..e466634
--- /dev/null
+++ b/t/t8010-cat-file-filters.sh
@@ -0,0 +1,34 @@
+#!/bin/sh
+
+test_description='git cat-file filters support'
+. ./test-lib.sh
+
+test_expect_success 'setup ' '
+       echo "*.txt eol=crlf diff=txt" >.gitattributes &&
+       echo "hello" | append_cr >world.txt &&
+       git add .gitattributes world.txt &&
+       test_tick &&
+       git commit -m "Initial commit"
+'
+
+has_cr () {
+       tr '\015' Q <"$1" | grep Q >/dev/null
+}
+
+test_expect_success 'no filters with `git show`' '
+       git show HEAD:world.txt >actual &&
+       ! has_cr actual
+
+'
+
+test_expect_success 'no filters with cat-file' '
+       git cat-file blob HEAD:world.txt >actual &&
+       ! has_cr actual
+'
+
+test_expect_success 'cat-file --filters converts to worktree version' '
+       git cat-file --filters HEAD:world.txt >actual &&
+       has_cr actual
+'
+
+test_done