diff: add filter for converting binary to text

When diffing binary files, it is sometimes nice to see the
differences of a canonical text form rather than either a
binary patch or simply "binary files differ."

Until now, the only option for doing this was to define an
external diff command to perform the diff. This was a lot of
work, since the external command needed to take care of
doing the diff itself (including mode changes), and lost the
benefit of git's colorization and other options.

This patch adds a text conversion option, which converts a
file to its canonical format before performing the diff.
This is less flexible than an arbitrary external diff, but
is much less work to set up. For example:

  $ echo '*.jpg diff=exif' >>.gitattributes
  $ git config diff.exif.textconv exiftool
  $ git config diff.exif.binary false

allows one to see jpg diffs represented by the text output
of exiftool.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>

diff --git a/diff.c b/diff.c
index dabd7f50ec28ed804cf5cace06cf72753be562ae..e368fef14fdccf63fc3525349841ae93aea93046 100644 (file)
--- a/diff.c
+++ b/diff.c
@@ -38,6 +38,9 @@ static char diff_colors[][COLOR_MAXLEN] = {
        "\033[41m",     /* WHITESPACE (red background) */
 };
 
+static void diff_filespec_load_driver(struct diff_filespec *one);
+static char *run_textconv(const char *, struct diff_filespec *, size_t *);
+
 static int parse_diff_color_slot(const char *var, int ofs)
 {
        if (!strcasecmp(var+ofs, "plain"))
@@ -290,8 +293,19 @@ static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
        }
        else if (diff_populate_filespec(one, 0))
                return -1;
-       mf->ptr = one->data;
-       mf->size = one->size;
+
+       diff_filespec_load_driver(one);
+       if (one->driver->textconv) {
+               size_t size;
+               mf->ptr = run_textconv(one->driver->textconv, one, &size);
+               if (!mf->ptr)
+                       return -1;
+               mf->size = size;
+       }
+       else {
+               mf->ptr = one->data;
+               mf->size = one->size;
+       }
        return 0;
 }
 
@@ -3373,3 +3387,34 @@ void diff_unmerge(struct diff_options *options,
        fill_filespec(one, sha1, mode);
        diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1;
 }
+
+static char *run_textconv(const char *pgm, struct diff_filespec *spec,
+               size_t *outsize)
+{
+       struct diff_tempfile temp;
+       const char *argv[3];
+       const char **arg = argv;
+       struct child_process child;
+       struct strbuf buf = STRBUF_INIT;
+
+       prepare_temp_file(spec->path, &temp, spec);
+       *arg++ = pgm;
+       *arg++ = temp.name;
+       *arg = NULL;
+
+       memset(&child, 0, sizeof(child));
+       child.argv = argv;
+       child.out = -1;
+       if (start_command(&child) != 0 ||
+           strbuf_read(&buf, child.out, 0) < 0 ||
+           finish_command(&child) != 0) {
+               if (temp.name == temp.tmp_path)
+                       unlink(temp.name);
+               error("error running textconv command '%s'", pgm);
+               return NULL;
+       }
+       if (temp.name == temp.tmp_path)
+               unlink(temp.name);
+
+       return strbuf_detach(&buf, outsize);
+}

diff --git a/userdiff.c b/userdiff.c
index 58478a6912200b6c5784e443072c4427bb8386f5..d95257ab3bd4fafa59b3ed2aa58c480de274227d 100644 (file)
--- a/userdiff.c
+++ b/userdiff.c
@@ -140,6 +140,8 @@ int userdiff_config_porcelain(const char *k, const char *v)
 
        if ((drv = parse_driver(k, v, "command")))
                return parse_string(&drv->external, k, v);
+       if ((drv = parse_driver(k, v, "textconv")))
+               return parse_string(&drv->textconv, k, v);
 
        return 0;
 }

diff --git a/userdiff.h b/userdiff.h
index 1c1eb042b44fc9e5085c34ffbd06e7e55043580b..f29c18ffb302dc009d438a08800c4aa202fd2f12 100644 (file)
--- a/userdiff.h
+++ b/userdiff.h
@@ -11,6 +11,7 @@ struct userdiff_driver {
        const char *external;
        int binary;
        struct userdiff_funcname funcname;
+       const char *textconv;
 };
 
 int userdiff_config_basic(const char *k, const char *v);