1 files changed, 27 insertions, 166 deletions

diff --git a/fast-import.c b/fast-import.c
index 4d55910ab9..b7ba755c2b 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -1,157 +1,3 @@
-/*
-(See Documentation/git-fast-import.txt for maintained documentation.)
-Format of STDIN stream:
-
-  stream ::= cmd*;
-
-  cmd ::= new_blob
-        | new_commit
-        | new_tag
-        | reset_branch
-        | checkpoint
-        | progress
-        ;
-
-  new_blob ::= 'blob' lf
-    mark?
-    file_content;
-  file_content ::= data;
-
-  new_commit ::= 'commit' sp ref_str lf
-    mark?
-    ('author' (sp name)? sp '<' email '>' sp when lf)?
-    'committer' (sp name)? sp '<' email '>' sp when lf
-    commit_msg
-    ('from' sp commit-ish lf)?
-    ('merge' sp commit-ish lf)*
-    (file_change | ls)*
-    lf?;
-  commit_msg ::= data;
-
-  ls ::= 'ls' sp '"' quoted(path) '"' lf;
-
-  file_change ::= file_clr
-    | file_del
-    | file_rnm
-    | file_cpy
-    | file_obm
-    | file_inm;
-  file_clr ::= 'deleteall' lf;
-  file_del ::= 'D' sp path_str lf;
-  file_rnm ::= 'R' sp path_str sp path_str lf;
-  file_cpy ::= 'C' sp path_str sp path_str lf;
-  file_obm ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf;
-  file_inm ::= 'M' sp mode sp 'inline' sp path_str lf
-    data;
-  note_obm ::= 'N' sp (hexsha1 | idnum) sp commit-ish lf;
-  note_inm ::= 'N' sp 'inline' sp commit-ish lf
-    data;
-
-  new_tag ::= 'tag' sp tag_str lf
-    'from' sp commit-ish lf
-    ('tagger' (sp name)? sp '<' email '>' sp when lf)?
-    tag_msg;
-  tag_msg ::= data;
-
-  reset_branch ::= 'reset' sp ref_str lf
-    ('from' sp commit-ish lf)?
-    lf?;
-
-  checkpoint ::= 'checkpoint' lf
-    lf?;
-
-  progress ::= 'progress' sp not_lf* lf
-    lf?;
-
-     # note: the first idnum in a stream should be 1 and subsequent
-     # idnums should not have gaps between values as this will cause
-     # the stream parser to reserve space for the gapped values.  An
-     # idnum can be updated in the future to a new object by issuing
-     # a new mark directive with the old idnum.
-     #
-  mark ::= 'mark' sp idnum lf;
-  data ::= (delimited_data | exact_data)
-    lf?;
-
-    # note: delim may be any string but must not contain lf.
-    # data_line may contain any data but must not be exactly
-    # delim.
-  delimited_data ::= 'data' sp '<<' delim lf
-    (data_line lf)*
-    delim lf;
-
-     # note: declen indicates the length of binary_data in bytes.
-     # declen does not include the lf preceding the binary data.
-     #
-  exact_data ::= 'data' sp declen lf
-    binary_data;
-
-     # note: quoted strings are C-style quoting supporting \c for
-     # common escapes of 'c' (e..g \n, \t, \\, \") or \nnn where nnn
-     # is the signed byte value in octal.  Note that the only
-     # characters which must actually be escaped to protect the
-     # stream formatting is: \, " and LF.  Otherwise these values
-     # are UTF8.
-     #
-  commit-ish  ::= (ref_str | hexsha1 | sha1exp_str | idnum);
-  ref_str     ::= ref;
-  sha1exp_str ::= sha1exp;
-  tag_str     ::= tag;
-  path_str    ::= path    | '"' quoted(path)    '"' ;
-  mode        ::= '100644' | '644'
-                | '100755' | '755'
-                | '120000'
-                ;
-
-  declen ::= # unsigned 32 bit value, ascii base10 notation;
-  bigint ::= # unsigned integer value, ascii base10 notation;
-  binary_data ::= # file content, not interpreted;
-
-  when         ::= raw_when | rfc2822_when;
-  raw_when     ::= ts sp tz;
-  rfc2822_when ::= # Valid RFC 2822 date and time;
-
-  sp ::= # ASCII space character;
-  lf ::= # ASCII newline (LF) character;
-
-     # note: a colon (':') must precede the numerical value assigned to
-     # an idnum.  This is to distinguish it from a ref or tag name as
-     # GIT does not permit ':' in ref or tag strings.
-     #
-  idnum   ::= ':' bigint;
-  path    ::= # GIT style file path, e.g. "a/b/c";
-  ref     ::= # GIT ref name, e.g. "refs/heads/MOZ_GECKO_EXPERIMENT";
-  tag     ::= # GIT tag name, e.g. "FIREFOX_1_5";
-  sha1exp ::= # Any valid GIT SHA1 expression;
-  hexsha1 ::= # SHA1 in hexadecimal format;
-
-     # note: name and email are UTF8 strings, however name must not
-     # contain '<' or lf and email must not contain any of the
-     # following: '<', '>', lf.
-     #
-  name  ::= # valid GIT author/committer name;
-  email ::= # valid GIT author/committer email;
-  ts    ::= # time since the epoch in seconds, ascii base10 notation;
-  tz    ::= # GIT style timezone;
-
-     # note: comments, get-mark, ls-tree, and cat-blob requests may
-     # appear anywhere in the input, except within a data command. Any
-     # form of the data command always escapes the related input from
-     # comment processing.
-     #
-     # In case it is not clear, the '#' that starts the comment
-     # must be the first character on that line (an lf
-     # preceded it).
-     #
-
-  get_mark ::= 'get-mark' sp idnum lf;
-  cat_blob ::= 'cat-blob' sp (hexsha1 | idnum) lf;
-  ls_tree  ::= 'ls' sp (hexsha1 | idnum) sp path_str lf;
-
-  comment ::= '#' not_lf* lf;
-  not_lf  ::= # Any byte that is not ASCII newline (LF);
-*/
-
 #include "builtin.h"
 #include "cache.h"
 #include "repository.h"
@@ -171,6 +17,7 @@ Format of STDIN stream:
 #include "packfile.h"
 #include "object-store.h"
 #include "mem-pool.h"
+#include "commit-reach.h"
 
 #define PACK_ID_BITS 16
 #define MAX_PACK_ID ((1<<PACK_ID_BITS)-1)
@@ -572,7 +419,7 @@ static struct object_entry *find_object(struct object_id *oid)
 	unsigned int h = oid->hash[0] << 8 | oid->hash[1];
 	struct object_entry *e;
 	for (e = object_table[h]; e; e = e->next)
-		if (!oidcmp(oid, &e->idx.oid))
+		if (oideq(oid, &e->idx.oid))
 			return e;
 	return NULL;
 }
@@ -583,7 +430,7 @@ static struct object_entry *insert_object(struct object_id *oid)
 	struct object_entry *e = object_table[h];
 
 	while (e) {
-		if (!oidcmp(oid, &e->idx.oid))
+		if (oideq(oid, &e->idx.oid))
 			return e;
 		e = e->next;
 	}
@@ -1068,7 +915,7 @@ static int store_object(
 		duplicate_count_by_type[type]++;
 		return 1;
 	} else if (find_sha1_pack(oid.hash,
-				  get_packed_git(the_repository))) {
+				  get_all_packs(the_repository))) {
 		e->type = type;
 		e->pack_id = MAX_PACK_ID;
 		e->idx.offset = 1; /* just not zero! */
@@ -1076,7 +923,7 @@ static int store_object(
 		return 1;
 	}
 
-	if (last && last->data.buf && last->depth < max_depth
+	if (last && last->data.len && last->data.buf && last->depth < max_depth
 		&& dat->len > the_hash_algo->rawsz) {
 
 		delta_count_attempts_by_type[type]++;
@@ -1266,7 +1113,7 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark)
 		truncate_pack(&checkpoint);
 
 	} else if (find_sha1_pack(oid.hash,
-				  get_packed_git(the_repository))) {
+				  get_all_packs(the_repository))) {
 		e->type = OBJ_BLOB;
 		e->pack_id = MAX_PACK_ID;
 		e->idx.offset = 1; /* just not zero! */
@@ -1533,7 +1380,7 @@ static int tree_content_set(
 			if (!*slash1) {
 				if (!S_ISDIR(mode)
 						&& e->versions[1].mode == mode
-						&& !oidcmp(&e->versions[1].oid, oid))
+						&& oideq(&e->versions[1].oid, oid))
 					return 0;
 				e->versions[1].mode = mode;
 				oidcpy(&e->versions[1].oid, oid);
@@ -1724,8 +1571,10 @@ static int update_branch(struct branch *b)
 	if (!force_update && !is_null_oid(&old_oid)) {
 		struct commit *old_cmit, *new_cmit;
 
-		old_cmit = lookup_commit_reference_gently(&old_oid, 0);
-		new_cmit = lookup_commit_reference_gently(&b->oid, 0);
+		old_cmit = lookup_commit_reference_gently(the_repository,
+							  &old_oid, 0);
+		new_cmit = lookup_commit_reference_gently(the_repository,
+							  &b->oid, 0);
 		if (!old_cmit || !new_cmit)
 			return error("Branch %s is missing commits.", b->name);
 
@@ -1965,6 +1814,13 @@ static void parse_mark(void)
 		next_mark = 0;
 }
 
+static void parse_original_identifier(void)
+{
+	const char *v;
+	if (skip_prefix(command_buf.buf, "original-oid ", &v))
+		read_next_command();
+}
+
 static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res)
 {
 	const char *data;
@@ -2107,6 +1963,7 @@ static void parse_new_blob(void)
 {
 	read_next_command();
 	parse_mark();
+	parse_original_identifier();
 	parse_and_store_blob(&last_blob, NULL, next_mark);
 }
 
@@ -2647,7 +2504,7 @@ static int parse_from(struct branch *b)
 		struct object_entry *oe = find_mark(idnum);
 		if (oe->type != OBJ_COMMIT)
 			die("Mark :%" PRIuMAX " not a commit", idnum);
-		if (oidcmp(&b->oid, &oe->idx.oid)) {
+		if (!oideq(&b->oid, &oe->idx.oid)) {
 			oidcpy(&b->oid, &oe->idx.oid);
 			if (oe->pack_id != MAX_PACK_ID) {
 				unsigned long size;
@@ -2665,7 +2522,7 @@ static int parse_from(struct branch *b)
 	else
 		die("Invalid ref name or SHA1 expression: %s", from);
 
-	if (b->branch_tree.tree && oidcmp(&oid, &b->branch_tree.versions[1].oid)) {
+	if (b->branch_tree.tree && !oideq(&oid, &b->branch_tree.versions[1].oid)) {
 		release_tree_content_recursive(b->branch_tree.tree);
 		b->branch_tree.tree = NULL;
 	}
@@ -2730,6 +2587,7 @@ static void parse_new_commit(const char *arg)
 
 	read_next_command();
 	parse_mark();
+	parse_original_identifier();
 	if (skip_prefix(command_buf.buf, "author ", &v)) {
 		author = parse_ident(v);
 		read_next_command();
@@ -2862,6 +2720,9 @@ static void parse_new_tag(const char *arg)
 		die("Invalid ref name or SHA1 expression: %s", from);
 	read_next_command();
 
+	/* original-oid ... */
+	parse_original_identifier();
+
 	/* tagger ... */
 	if (skip_prefix(command_buf.buf, "tagger ", &v)) {
 		tagger = parse_ident(v);
@@ -2952,8 +2813,8 @@ static void cat_blob(struct object_entry *oe, struct object_id *oid)
 		die("Object %s is a %s but a blob was expected.",
 		    oid_to_hex(oid), type_name(type));
 	strbuf_reset(&line);
-	strbuf_addf(&line, "%s %s %lu\n", oid_to_hex(oid),
-						type_name(type), size);
+	strbuf_addf(&line, "%s %s %"PRIuMAX"\n", oid_to_hex(oid),
+		    type_name(type), (uintmax_t)size);
 	cat_blob_write(line.buf, line.len);
 	strbuf_release(&line);
 	cat_blob_write(buf, size);