Merge branch 'maint'

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index b43a0c50403403b5dcf6b415dea092ee64b66558..41afaa534b02d8f8089973f3949ba507bd3cf94b 100644 (file)
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -118,6 +118,8 @@ struct expand_data {
        unsigned char sha1[20];
        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
@@ -125,6 +127,13 @@ struct expand_data {
         */
        int mark_query;
 
+       /*
+        * Whether to split the input on whitespace before feeding it to
+        * get_sha1; this is decided during the mark_query phase based on
+        * whether we have a %(rest) token in our format.
+        */
+       int split_on_whitespace;
+
        /*
         * After a mark_query run, this object_info is set up to be
         * passed to sha1_object_info_extended. It will point to the data
@@ -148,13 +157,25 @@ static void expand_atom(struct strbuf *sb, const char *atom, int len,
                if (!data->mark_query)
                        strbuf_addstr(sb, sha1_to_hex(data->sha1));
        } else if (is_atom("objecttype", atom, len)) {
-               if (!data->mark_query)
+               if (data->mark_query)
+                       data->info.typep = &data->type;
+               else
                        strbuf_addstr(sb, typename(data->type));
        } else if (is_atom("objectsize", atom, len)) {
                if (data->mark_query)
                        data->info.sizep = &data->size;
                else
                        strbuf_addf(sb, "%lu", data->size);
+       } else if (is_atom("objectsize:disk", atom, len)) {
+               if (data->mark_query)
+                       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->split_on_whitespace = 1;
+               else if (data->rest)
+                       strbuf_addstr(sb, data->rest);
        } else
                die("unknown format element: %.*s", len, atom);
 }
@@ -219,8 +240,7 @@ static int batch_one_object(const char *obj_name, struct batch_options *opt,
                return 0;
        }
 
-       data->type = sha1_object_info_extended(data->sha1, &data->info);
-       if (data->type <= 0) {
+       if (sha1_object_info_extended(data->sha1, &data->info) < 0) {
                printf("%s missing\n", obj_name);
                fflush(stdout);
                return 0;
@@ -256,8 +276,33 @@ static int batch_objects(struct batch_options *opt)
        strbuf_expand(&buf, opt->format, expand_format, &data);
        data.mark_query = 0;
 
+       /*
+        * We are going to call get_sha1 on a potentially very large number of
+        * objects. In most large cases, these will be actual object sha1s. The
+        * cost to double-check that each one is not also a ref (just so we can
+        * warn) ends up dwarfing the actual cost of the object lookups
+        * themselves. We can work around it by just turning off the warning.
+        */
+       warn_on_object_refname_ambiguity = 0;
+
        while (strbuf_getline(&buf, stdin, '\n') != EOF) {
-               int error = batch_one_object(buf.buf, opt, &data);
+               int error;
+
+               if (data.split_on_whitespace) {
+                       /*
+                        * Split at first whitespace, tying off the beginning
+                        * of the string and saving the remainder (or NULL) in
+                        * data.rest.
+                        */
+                       char *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;
        }