[PATCH 6/8] archive: use index instead of parsing tree directly

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

Currently:

 - "git archive" parses trees directly
 - attr mechanism does not support in-tree attributes

Making attr.c support in-tree attributes is quite a non-trivial task,
IMHO. Instead this patch makes "git archive" read tree to index first,
then start exporting from there.

One minor regression: "git archive" now will no longer generate
directory entries, only files.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive.c               |   66 ++++++++++++++++++++++++++++++++---------------
 t/t0024-crlf-archive.sh |    2 -
 2 files changed, 45 insertions(+), 23 deletions(-)

diff --git a/archive.c b/archive.c
index 5b54d95..402f6d4 100644
--- a/archive.c
+++ b/archive.c
@@ -4,6 +4,8 @@
 #include "attr.h"
 #include "archive.h"
 #include "parse-options.h"
+#include "unpack-trees.h"
+#include "dir.h"
 
 static char const * const archive_usage[] = {
 	"git archive [options] <tree-ish> [path...]",
@@ -167,7 +169,9 @@ int write_archive_entries(struct archiver_args *args,
 		write_archive_entry_fn_t write_entry)
 {
 	struct archiver_context context;
-	int err;
+	struct unpack_trees_options opts;
+	struct tree_desc t;
+	int i, prefix_len, err;
 
 	if (args->baselen > 0 && args->base[args->baselen - 1] == '/') {
 		size_t len = args->baselen;
@@ -185,11 +189,42 @@ int write_archive_entries(struct archiver_args *args,
 	context.args = args;
 	context.write_entry = write_entry;
 
-	err =  read_tree_recursive(args->tree, args->base, args->baselen, 0,
-			args->pathspec, write_archive_entry, &context);
-	if (err == READ_TREE_RECURSIVE)
-		err = 0;
-	return err;
+	memset(&opts, 0, sizeof(opts));
+	opts.index_only = 1;
+	opts.head_idx = -1;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
+	opts.fn = oneway_merge;
+	init_tree_desc(&t, args->tree->buffer, args->tree->size);
+	if (unpack_trees(1, &t, &opts))
+		return -1;
+	prefix_len = common_prefix(args->pathspec);
+	if (prefix_len)
+		prune_cache(args->pathspec[0], prefix_len);
+
+	for (i = 0;i < active_nr;i++) {
+		struct cache_entry *ce = active_cache[i];
+		const char **path;
+		const char *str, *prefix;
+		int match = 0;
+
+		if (!args->pathspec || !args->pathspec[0] || !*args->pathspec[0])
+			match = 1;
+
+		/* It's not really pathspec, so match_pathspec can't be used */
+		for (path = args->pathspec;!match && *path;path++) {
+			for (str = ce->name, prefix = *path;*prefix && *str == *prefix; str++, prefix++)
+				;
+			if (!*prefix && *str == '/')
+				match = 1;
+		}
+
+		if (match)
+			write_archive_entry(ce->sha1, args->base, args->baselen,
+					    ce->name, ce->ce_mode, ce_stage(ce),
+					    &context);
+	}
+	return 0;
 }
 
 static const struct archiver *lookup_archiver(const char *name)
@@ -207,9 +242,10 @@ static const struct archiver *lookup_archiver(const char *name)
 }
 
 static void parse_pathspec_arg(const char **pathspec,
-		struct archiver_args *ar_args)
+			       struct archiver_args *ar_args,
+			       const char *prefix)
 {
-	ar_args->pathspec = get_pathspec(ar_args->base, pathspec);
+	ar_args->pathspec = get_pathspec(prefix, pathspec);
 }
 
 static void parse_treeish_arg(const char **argv,
@@ -238,18 +274,6 @@ static void parse_treeish_arg(const char **argv,
 	if (tree == NULL)
 		die("not a tree object");
 
-	if (prefix) {
-		unsigned char tree_sha1[20];
-		unsigned int mode;
-		int err;
-
-		err = get_tree_entry(tree->object.sha1, prefix,
-				     tree_sha1, &mode);
-		if (err || !S_ISDIR(mode))
-			die("current working directory is untracked");
-
-		tree = parse_tree_indirect(tree_sha1);
-	}
 	ar_args->tree = tree;
 	ar_args->commit_sha1 = commit_sha1;
 	ar_args->commit = commit;
@@ -356,7 +380,7 @@ int write_archive(int argc, const char **argv, const char *prefix,
 		prefix = setup_git_directory();
 
 	parse_treeish_arg(argv, &args, prefix);
-	parse_pathspec_arg(argv + 1, &args);
+	parse_pathspec_arg(argv + 1, &args, prefix);
 
 	git_config(git_default_config, NULL);
 
diff --git a/t/t0024-crlf-archive.sh b/t/t0024-crlf-archive.sh
index 695ad5a..1cbe511 100755
--- a/t/t0024-crlf-archive.sh
+++ b/t/t0024-crlf-archive.sh
@@ -21,7 +21,6 @@ test_expect_success setup '
 
 cat <<\EOF > expected
 sample
-sub/
 sub/sample
 EOF
 
@@ -31,7 +30,6 @@ test_expect_success 'archive without subdir' '
 '
 
 cat <<\EOF > expected
-sub/
 sub/sample
 EOF
 
-- 
1.6.2.2.602.g83ee9f