Merge branch 'sr/vcs-helper'

* sr/vcs-helper:
  tests: handle NO_PYTHON setting
  builtin-push: don't access freed transport->url
  Add Python support library for remote helpers
  Basic build infrastructure for Python scripts
  Allow helpers to report in "list" command that the ref is unchanged
  Fix various memory leaks in transport-helper.c
  Allow helper to map private ref names into normal names
  Add support for "import" helper command
  Allow specifying the remote helper in the url
  Add a config option for remotes to specify a foreign vcs
  Allow fetch to modify refs
  Use a function to determine whether a remote is valid
  Allow programs to not depend on remotes having urls
  Fix memory leak in helper method for disconnect

Conflicts:
	Documentation/git-remote-helpers.txt
	Makefile
	builtin-ls-remote.c
	builtin-push.c
	transport-helper.c

Documentation/config.txt

@@ -1461,6 +1461,10 @@ remote.<name>.tagopt::
 	Setting this value to \--no-tags disables automatic tag following when
 	fetching from remote <name>
 
+remote.<name>.vcs::
+	Setting this to a value <vcs> will cause git to interact with
+	the remote with the git-remote-<vcs> helper.
+
 remotes.<group>::
 	The list of remotes which are fetched by "git remote update
 	<group>".  See linkgit:git-remote[1].

Documentation/git-remote-helpers.txt

@@ -79,6 +79,17 @@ style string if it contains an LF.
 +
 Supported if the helper has the "push" capability.
 
+'import' <name>::
+	Produces a fast-import stream which imports the current value
+	of the named ref. It may additionally import other refs as
+	needed to construct the history efficiently. The script writes
+	to a helper-specific private namespace. The value of the named
+	ref should be written to a location in this namespace derived
+	by applying the refspecs from the "refspec" capability to the
+	name of the ref.
++
+Supported if the helper has the "import" capability.
+
 If a fatal error occurs, the program writes the error message to
 stderr and exits. The caller should expect that a suitable error
 message has been printed if the child closes the connection without
@@ -99,6 +110,19 @@ CAPABILITIES
 'push'::
 	This helper supports the 'push' command.
 
+'import'::
+	This helper supports the 'import' command.
+
+'refspec' 'spec'::
+	When using the import command, expect the source ref to have
+	been written to the destination ref. The earliest applicable
+	refspec takes precedence. For example
+	"refs/heads/*:refs/svn/origin/branches/*" means that, after an
+	"import refs/heads/name", the script has written to
+	refs/svn/origin/branches/name. If this capability is used at
+	all, it must cover all refs reported by the list command; if
+	it is not used, it is effectively "*:*"
+
 REF LIST ATTRIBUTES
 -------------------
 
@@ -107,6 +131,10 @@ REF LIST ATTRIBUTES
 	commands.  A helper might chose to acquire the ref list by
 	opening a different type of connection to the destination.
 
+'unchanged'::
+	This ref is unchanged since the last import or fetch, although
+	the helper cannot necessarily determine what value that produced.
+
 OPTIONS
 -------
 'option verbosity' <N>::

Makefile

@@ -168,6 +168,8 @@ all::
 #
 # Define NO_PERL if you do not want Perl scripts or libraries at all.
 #
+# Define NO_PYTHON if you do not want Python scripts or libraries at all.
+#
 # Define NO_TCLTK if you do not want Tcl/Tk GUI.
 #
 # The TCL_PATH variable governs the location of the Tcl interpreter
@@ -341,6 +343,7 @@ LIB_H =
 LIB_OBJS =
 PROGRAMS =
 SCRIPT_PERL =
+SCRIPT_PYTHON =
 SCRIPT_SH =
 TEST_PROGRAMS =
 
@@ -379,6 +382,7 @@ SCRIPT_PERL += git-svn.perl
 
 SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \
 	  $(patsubst %.perl,%,$(SCRIPT_PERL)) \
+	  $(patsubst %.py,%,$(SCRIPT_PYTHON)) \
 	  git-instaweb
 
 # Empty...
@@ -434,8 +438,12 @@ endif
 ifndef PERL_PATH
 	PERL_PATH = /usr/bin/perl
 endif
+ifndef PYTHON_PATH
+	PYTHON_PATH = /usr/bin/python
+endif
 
 export PERL_PATH
+export PYTHON_PATH
 
 LIB_FILE=libgit.a
 XDIFF_LIB=xdiff/lib.a
@@ -1346,6 +1354,10 @@ ifeq ($(PERL_PATH),)
 NO_PERL=NoThanks
 endif
 
+ifeq ($(PYTHON_PATH),)
+NO_PYTHON=NoThanks
+endif
+
 QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
 QUIET_SUBDIR1  =
 
@@ -1393,6 +1405,7 @@ prefix_SQ = $(subst ','\'',$(prefix))
 
 SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
 PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
+PYTHON_PATH_SQ = $(subst ','\'',$(PYTHON_PATH))
 TCLTK_PATH_SQ = $(subst ','\'',$(TCLTK_PATH))
 
 LIBS = $(GITLIBS) $(EXTLIBS)
@@ -1439,6 +1452,9 @@ ifndef NO_TCLTK
 endif
 ifndef NO_PERL
 	$(QUIET_SUBDIR0)perl $(QUIET_SUBDIR1) PERL_PATH='$(PERL_PATH_SQ)' prefix='$(prefix_SQ)' all
+endif
+ifndef NO_PYTHON
+	$(QUIET_SUBDIR0)git_remote_helpers $(QUIET_SUBDIR1) PYTHON_PATH='$(PYTHON_PATH_SQ)' prefix='$(prefix_SQ)' all
 endif
 	$(QUIET_SUBDIR0)templates $(QUIET_SUBDIR1)
 
@@ -1566,11 +1582,41 @@ $(patsubst %.perl,%,$(SCRIPT_PERL)) git-instaweb: % : unimplemented.sh
 	mv $@+ $@
 endif # NO_PERL
 
+
 ifdef JSMIN
 gitweb/gitweb.min.js: gitweb/gitweb.js
 	$(QUIET_GEN)$(JSMIN) <$< >$@
 endif # JSMIN
 
+ifndef NO_PYTHON
+$(patsubst %.py,%,$(SCRIPT_PYTHON)): GIT-CFLAGS
+$(patsubst %.py,%,$(SCRIPT_PYTHON)): % : %.py
+	$(QUIET_GEN)$(RM) $@ $@+ && \
+	INSTLIBDIR=`MAKEFLAGS= $(MAKE) -C git_remote_helpers -s \
+		--no-print-directory prefix='$(prefix_SQ)' DESTDIR='$(DESTDIR_SQ)' \
+		instlibdir` && \
+	sed -e '1{' \
+	    -e '	s|#!.*python|#!$(PYTHON_PATH_SQ)|' \
+	    -e '}' \
+	    -e 's|^import sys.*|&; \\\
+	           import os; \\\
+	           sys.path[0] = os.environ.has_key("GITPYTHONLIB") and \\\
+	                         os.environ["GITPYTHONLIB"] or \\\
+	                         "@@INSTLIBDIR@@"|' \
+	    -e 's|@@INSTLIBDIR@@|'"$$INSTLIBDIR"'|g' \
+	    $@.py >$@+ && \
+	chmod +x $@+ && \
+	mv $@+ $@
+else # NO_PYTHON
+$(patsubst %.py,%,$(SCRIPT_PYTHON)): % : unimplemented.sh
+	$(QUIET_GEN)$(RM) $@ $@+ && \
+	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
+	    -e 's|@@REASON@@|NO_PYTHON=$(NO_PYTHON)|g' \
+	    unimplemented.sh >$@+ && \
+	chmod +x $@+ && \
+	mv $@+ $@
+endif # NO_PYTHON
+
 configure: configure.ac
 	$(QUIET_GEN)$(RM) $@ $<+ && \
 	sed -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \
@@ -1697,6 +1743,7 @@ GIT-BUILD-OPTIONS: .FORCE-GIT-BUILD-OPTIONS
 	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
 	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
 	@echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@
+	@echo NO_PYTHON=\''$(subst ','\'',$(subst ','\'',$(NO_PYTHON)))'\' >>$@
 
 ### Detect Tck/Tk interpreter path changes
 ifndef NO_TCLTK
@@ -1796,6 +1843,9 @@ install: all
 ifndef NO_PERL
 	$(MAKE) -C perl prefix='$(prefix_SQ)' DESTDIR='$(DESTDIR_SQ)' install
 endif
+ifndef NO_PYTHON
+	$(MAKE) -C git_remote_helpers prefix='$(prefix_SQ)' DESTDIR='$(DESTDIR_SQ)' install
+endif
 ifndef NO_TCLTK
 	$(MAKE) -C gitk-git install
 	$(MAKE) -C git-gui gitexecdir='$(gitexec_instdir_SQ)' install
@@ -1912,6 +1962,9 @@ clean:
 ifndef NO_PERL
 	$(RM) gitweb/gitweb.cgi
 	$(MAKE) -C perl clean
+endif
+ifndef NO_PYTHON
+	$(MAKE) -C git_remote_helpers clean
 endif
 	$(MAKE) -C templates/ clean
 	$(MAKE) -C t/ clean

builtin-clone.c

@@ -362,9 +362,10 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	const char *repo_name, *repo, *work_tree, *git_dir;
 	char *path, *dir;
 	int dest_exists;
-	const struct ref *refs, *remote_head, *mapped_refs;
+	const struct ref *refs, *remote_head;
 	const struct ref *remote_head_points_at;
 	const struct ref *our_head_points_at;
+	struct ref *mapped_refs;
 	struct strbuf key = STRBUF_INIT, value = STRBUF_INIT;
 	struct strbuf branch_top = STRBUF_INIT, reflog_msg = STRBUF_INIT;
 	struct transport *transport = NULL;

builtin-fetch.c

@@ -322,7 +322,10 @@ static int store_updated_refs(const char *raw_url, const char *remote_name,
 	if (!fp)
 		return error("cannot open %s: %s\n", filename, strerror(errno));
 
-	url = transport_anonymize_url(raw_url);
+	if (raw_url)
+		url = transport_anonymize_url(raw_url);
+	else
+		url = xstrdup("foreign");
 	for (rm = ref_map; rm; rm = rm->next) {
 		struct ref *ref = NULL;
 
@@ -819,7 +822,7 @@ static int fetch_one(struct remote *remote, int argc, const char **argv)
 	if (!remote)
 		die("Where do you want to fetch from today?");
 
-	transport = transport_get(remote, remote->url[0]);
+	transport = transport_get(remote, NULL);
 	if (verbosity >= 2)
 		transport->verbose = verbosity <= 3 ? verbosity : 3;
 	if (verbosity < 0)

builtin-ls-remote.c

@@ -89,7 +89,7 @@ int cmd_ls_remote(int argc, const char **argv, const char *prefix)
 	remote = remote_get(dest);
 	if (!remote->url_nr)
 		die("remote %s has no configured URL", dest);
-	transport = transport_get(remote, remote->url[0]);
+	transport = transport_get(remote, NULL);
 	if (uploadpack != NULL)
 		transport_set_option(transport, TRANS_OPT_UPLOADPACK, uploadpack);
 

builtin-push.c

@@ -87,6 +87,37 @@ static void setup_default_push_refspecs(void)
 	}
 }
 
+static int push_with_options(struct transport *transport, int flags)
+{
+	int err;
+	int nonfastforward;
+	if (receivepack)
+		transport_set_option(transport,
+				     TRANS_OPT_RECEIVEPACK, receivepack);
+	if (thin)
+		transport_set_option(transport, TRANS_OPT_THIN, "yes");
+
+	if (flags & TRANSPORT_PUSH_VERBOSE)
+		fprintf(stderr, "Pushing to %s\n", transport->url);
+	err = transport_push(transport, refspec_nr, refspec, flags,
+			     &nonfastforward);
+	if (err != 0)
+		error("failed to push some refs to '%s'", transport->url);
+
+	err |= transport_disconnect(transport);
+
+	if (!err)
+		return 0;
+
+	if (nonfastforward && advice_push_nonfastforward) {
+		printf("To prevent you from losing history, non-fast-forward updates were rejected\n"
+		       "Merge the remote changes before pushing again.  See the 'non-fast-forward'\n"
+		       "section of 'git push --help' for details.\n");
+	}
+
+	return 1;
+}
+
 static int do_push(const char *repo, int flags)
 {
 	int i, errs;
@@ -135,33 +166,19 @@ static int do_push(const char *repo, int flags)
 		url = remote->url;
 		url_nr = remote->url_nr;
 	}
-	for (i = 0; i < url_nr; i++) {
+	if (url_nr) {
-		struct transport *transport =
+		for (i = 0; i < url_nr; i++) {
-			transport_get(remote, url[i]);
+			struct transport *transport =
-		int err;
+				transport_get(remote, url[i]);
-		int nonfastforward;
+			if (push_with_options(transport, flags))
-		if (receivepack)
+				errs++;
-			transport_set_option(transport,
-					     TRANS_OPT_RECEIVEPACK, receivepack);
-		if (thin)
-			transport_set_option(transport, TRANS_OPT_THIN, "yes");
-
-		if (flags & TRANSPORT_PUSH_VERBOSE)
-			fprintf(stderr, "Pushing to %s\n", url[i]);
-		err = transport_push(transport, refspec_nr, refspec, flags,
-				     &nonfastforward);
-		err |= transport_disconnect(transport);
-
-		if (!err)
-			continue;
-
-		error("failed to push some refs to '%s'", url[i]);
-		if (nonfastforward && advice_push_nonfastforward) {
-			printf("To prevent you from losing history, non-fast-forward updates were rejected\n"
-			       "Merge the remote changes before pushing again.  See the 'non-fast-forward'\n"
-			       "section of 'git push --help' for details.\n");
 		}
-		errs++;
+	} else {
+		struct transport *transport =
+			transport_get(remote, NULL);
+
+		if (push_with_options(transport, flags))
+			errs++;
 	}
 	return !!errs;
 }

configure.ac

@@ -276,6 +276,9 @@ GIT_ARG_SET_PATH(shell)
 # Define PERL_PATH to provide path to Perl.
 GIT_ARG_SET_PATH(perl)
 #
+# Define PYTHON_PATH to provide path to Python.
+GIT_ARG_SET_PATH(python)
+#
 # Define ZLIB_PATH to provide path to zlib.
 GIT_ARG_SET_PATH(zlib)
 #

git_remote_helpers/.gitignore

@@ -0,0 +1,2 @@
+/build
+/dist

git_remote_helpers/Makefile

@@ -0,0 +1,35 @@
+#
+# Makefile for the git_remote_helpers python support modules
+#
+pysetupfile:=setup.py
+
+# Shell quote (do not use $(call) to accommodate ancient setups);
+DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
+
+ifndef PYTHON_PATH
+	PYTHON_PATH = /usr/bin/python
+endif
+ifndef prefix
+	prefix = $(HOME)
+endif
+ifndef V
+	QUIET = @
+	QUIETSETUP = --quiet
+endif
+
+PYLIBDIR=$(shell $(PYTHON_PATH) -c \
+	 "import sys; \
+	 print 'lib/python%i.%i/site-packages' % sys.version_info[:2]")
+
+all: $(pysetupfile)
+	$(QUIET)$(PYTHON_PATH) $(pysetupfile) $(QUIETSETUP) build
+
+install: $(pysetupfile)
+	$(PYTHON_PATH) $(pysetupfile) install --prefix $(DESTDIR_SQ)$(prefix)
+
+instlibdir: $(pysetupfile)
+	@echo "$(DESTDIR_SQ)$(prefix)/$(PYLIBDIR)"
+
+clean:
+	$(QUIET)$(PYTHON_PATH) $(pysetupfile) $(QUIETSETUP) clean -a
+	$(RM) *.pyo *.pyc

git_remote_helpers/__init__.py

@@ -0,0 +1,16 @@
+#!/usr/bin/env python
+
+"""Support library package for git remote helpers.
+
+Git remote helpers are helper commands that interfaces with a non-git
+repository to provide automatic import of non-git history into a Git
+repository.
+
+This package provides the support library needed by these helpers..
+The following modules are included:
+
+- git.git - Interaction with Git repositories
+
+- util - General utility functionality use by the other modules in
+         this package, and also used directly by the helpers.
+"""

git_remote_helpers/git/git.py

@@ -0,0 +1,678 @@
+#!/usr/bin/env python
+
+"""Functionality for interacting with Git repositories.
+
+This module provides classes for interfacing with a Git repository.
+"""
+
+import os
+import re
+import time
+from binascii import hexlify
+from cStringIO import StringIO
+import unittest
+
+from git_remote_helpers.util import debug, error, die, start_command, run_command
+
+
+def get_git_dir ():
+    """Return the path to the GIT_DIR for this repo."""
+    args = ("git", "rev-parse", "--git-dir")
+    exit_code, output, errors = run_command(args)
+    if exit_code:
+        die("Failed to retrieve git dir")
+    assert not errors
+    return output.strip()
+
+
+def parse_git_config ():
+    """Return a dict containing the parsed version of 'git config -l'."""
+    exit_code, output, errors = run_command(("git", "config", "-z", "-l"))
+    if exit_code:
+        die("Failed to retrieve git configuration")
+    assert not errors
+    return dict([e.split('\n', 1) for e in output.split("\0") if e])
+
+
+def git_config_bool (value):
+    """Convert the given git config string value to True or False.
+
+    Raise ValueError if the given string was not recognized as a
+    boolean value.
+
+    """
+    norm_value = str(value).strip().lower()
+    if norm_value in ("true", "1", "yes", "on", ""):
+        return True
+    if norm_value in ("false", "0", "no", "off", "none"):
+        return False
+    raise ValueError("Failed to parse '%s' into a boolean value" % (value))
+
+
+def valid_git_ref (ref_name):
+    """Return True iff the given ref name is a valid git ref name."""
+    # The following is a reimplementation of the git check-ref-format
+    # command.  The rules were derived from the git check-ref-format(1)
+    # manual page.  This code should be replaced by a call to
+    # check_ref_format() in the git library, when such is available.
+    if ref_name.endswith('/') or \
+       ref_name.startswith('.') or \
+       ref_name.count('/.') or \
+       ref_name.count('..') or \
+       ref_name.endswith('.lock'):
+        return False
+    for c in ref_name:
+        if ord(c) < 0x20 or ord(c) == 0x7f or c in " ~^:?*[":
+            return False
+    return True
+
+
+class GitObjectFetcher(object):
+
+    """Provide parsed access to 'git cat-file --batch'.
+
+    This provides a read-only interface to the Git object database.
+
+    """
+
+    def __init__ (self):
+        """Initiate a 'git cat-file --batch' session."""
+        self.queue = []  # List of object names to be submitted
+        self.in_transit = None  # Object name currently in transit
+
+        # 'git cat-file --batch' produces binary output which is likely
+        # to be corrupted by the default "rU"-mode pipe opened by
+        # start_command.  (Mode == "rU" does universal new-line
+        # conversion, which mangles carriage returns.) Therefore, we
+        # open an explicitly binary-safe pipe for transferring the
+        # output from 'git cat-file --batch'.
+        pipe_r_fd, pipe_w_fd = os.pipe()
+        pipe_r = os.fdopen(pipe_r_fd, "rb")
+        pipe_w = os.fdopen(pipe_w_fd, "wb")
+        self.proc = start_command(("git", "cat-file", "--batch"),
+                                  stdout = pipe_w)
+        self.f = pipe_r
+
+    def __del__ (self):
+        """Verify completed communication with 'git cat-file --batch'."""
+        assert not self.queue
+        assert self.in_transit is None
+        self.proc.stdin.close()
+        assert self.proc.wait() == 0  # Zero exit code
+        assert self.f.read() == ""  # No remaining output
+
+    def _submit_next_object (self):
+        """Submit queue items to the 'git cat-file --batch' process.
+
+        If there are items in the queue, and there is currently no item
+        currently in 'transit', then pop the first item off the queue,
+        and submit it.
+
+        """
+        if self.queue and self.in_transit is None:
+            self.in_transit = self.queue.pop(0)
+            print >> self.proc.stdin, self.in_transit[0]
+
+    def push (self, obj, callback):
+        """Push the given object name onto the queue.
+
+        The given callback function will at some point in the future
+        be called exactly once with the following arguments:
+        - self - this GitObjectFetcher instance
+        - obj  - the object name provided to push()
+        - sha1 - the SHA1 of the object, if 'None' obj is missing
+        - t    - the type of the object (tag/commit/tree/blob)
+        - size - the size of the object in bytes
+        - data - the object contents
+
+        """
+        self.queue.append((obj, callback))
+        self._submit_next_object()  # (Re)start queue processing
+
+    def process_next_entry (self):
+        """Read the next entry off the queue and invoke callback."""
+        obj, cb = self.in_transit
+        self.in_transit = None
+        header = self.f.readline()
+        if header == "%s missing\n" % (obj):
+            cb(self, obj, None, None, None, None)
+            return
+        sha1, t, size = header.split(" ")
+        assert len(sha1) == 40
+        assert t in ("tag", "commit", "tree", "blob")
+        assert size.endswith("\n")
+        size = int(size.strip())
+        data = self.f.read(size)
+        assert self.f.read(1) == "\n"
+        cb(self, obj, sha1, t, size, data)
+        self._submit_next_object()
+
+    def process (self):
+        """Process the current queue until empty."""
+        while self.in_transit is not None:
+            self.process_next_entry()
+
+    # High-level convenience methods:
+
+    def get_sha1 (self, objspec):
+        """Return the SHA1 of the object specified by 'objspec'.
+
+        Return None if 'objspec' does not specify an existing object.
+
+        """
+        class _ObjHandler(object):
+            """Helper class for getting the returned SHA1."""
+            def __init__ (self, parser):
+                self.parser = parser
+                self.sha1 = None
+
+            def __call__ (self, parser, obj, sha1, t, size, data):
+                # FIXME: Many unused arguments. Could this be cheaper?
+                assert parser == self.parser
+                self.sha1 = sha1
+
+        handler = _ObjHandler(self)
+        self.push(objspec, handler)
+        self.process()
+        return handler.sha1
+
+    def open_obj (self, objspec):
+        """Return a file object wrapping the contents of a named object.
+
+        The caller is responsible for calling .close() on the returned
+        file object.
+
+        Raise KeyError if 'objspec' does not exist in the repo.
+
+        """
+        class _ObjHandler(object):
+            """Helper class for parsing the returned git object."""
+            def __init__ (self, parser):
+                """Set up helper."""
+                self.parser = parser
+                self.contents = StringIO()
+                self.err = None
+
+            def __call__ (self, parser, obj, sha1, t, size, data):
+                """Git object callback (see GitObjectFetcher documentation)."""
+                assert parser == self.parser
+                if not sha1:  # Missing object
+                    self.err = "Missing object '%s'" % obj
+                else:
+                    assert size == len(data)
+                    self.contents.write(data)
+
+        handler = _ObjHandler(self)
+        self.push(objspec, handler)
+        self.process()
+        if handler.err:
+            raise KeyError(handler.err)
+        handler.contents.seek(0)
+        return handler.contents
+
+    def walk_tree (self, tree_objspec, callback, prefix = ""):
+        """Recursively walk the given Git tree object.
+
+        Recursively walk all subtrees of the given tree object, and
+        invoke the given callback passing three arguments:
+        (path, mode, data) with the path, permission bits, and contents
+        of all the blobs found in the entire tree structure.
+
+        """
+        class _ObjHandler(object):
+            """Helper class for walking a git tree structure."""
+            def __init__ (self, parser, cb, path, mode = None):
+                """Set up helper."""
+                self.parser = parser
+                self.cb = cb
+                self.path = path
+                self.mode = mode
+                self.err = None
+
+            def parse_tree (self, treedata):
+                """Parse tree object data, yield tree entries.
+
+                Each tree entry is a 3-tuple (mode, sha1, path)
+
+                self.path is prepended to all paths yielded
+                from this method.
+
+                """
+                while treedata:
+                    mode = int(treedata[:6], 10)
+                    # Turn 100xxx into xxx
+                    if mode > 100000:
+                        mode -= 100000
+                    assert treedata[6] == " "
+                    i = treedata.find("\0", 7)
+                    assert i > 0
+                    path = treedata[7:i]
+                    sha1 = hexlify(treedata[i + 1: i + 21])
+                    yield (mode, sha1, self.path + path)
+                    treedata = treedata[i + 21:]
+
+            def __call__ (self, parser, obj, sha1, t, size, data):
+                """Git object callback (see GitObjectFetcher documentation)."""
+                assert parser == self.parser
+                if not sha1:  # Missing object
+                    self.err = "Missing object '%s'" % (obj)
+                    return
+                assert size == len(data)
+                if t == "tree":
+                    if self.path:
+                        self.path += "/"
+                    # Recurse into all blobs and subtrees
+                    for m, s, p in self.parse_tree(data):
+                        parser.push(s,
+                                    self.__class__(self.parser, self.cb, p, m))
+                elif t == "blob":
+                    self.cb(self.path, self.mode, data)
+                else:
+                    raise ValueError("Unknown object type '%s'" % (t))
+
+        self.push(tree_objspec, _ObjHandler(self, callback, prefix))
+        self.process()
+
+
+class GitRefMap(object):
+
+    """Map Git ref names to the Git object names they currently point to.
+
+    Behaves like a dictionary of Git ref names -> Git object names.
+
+    """
+
+    def __init__ (self, obj_fetcher):
+        """Create a new Git ref -> object map."""
+        self.obj_fetcher = obj_fetcher
+        self._cache = {}  # dict: refname -> objname
+
+    def _load (self, ref):
+        """Retrieve the object currently bound to the given ref.
+
+        The name of the object pointed to by the given ref is stored
+        into this mapping, and also returned.
+
+        """
+        if ref not in self._cache:
+            self._cache[ref] = self.obj_fetcher.get_sha1(ref)
+        return self._cache[ref]
+
+    def __contains__ (self, refname):
+        """Return True if the given refname is present in this cache."""
+        return bool(self._load(refname))
+
+    def __getitem__ (self, refname):
+        """Return the git object name pointed to by the given refname."""
+        commit = self._load(refname)
+        if commit is None:
+            raise KeyError("Unknown ref '%s'" % (refname))
+        return commit
+
+    def get (self, refname, default = None):
+        """Return the git object name pointed to by the given refname."""
+        commit = self._load(refname)
+        if commit is None:
+            return default
+        return commit
+
+
+class GitFICommit(object):
+
+    """Encapsulate the data in a Git fast-import commit command."""
+
+    SHA1RE = re.compile(r'^[0-9a-f]{40}$')
+
+    @classmethod
+    def parse_mode (cls, mode):
+        """Verify the given git file mode, and return it as a string."""
+        assert mode in (644, 755, 100644, 100755, 120000)
+        return "%i" % (mode)
+
+    @classmethod
+    def parse_objname (cls, objname):
+        """Return the given object name (or mark number) as a string."""
+        if isinstance(objname, int):  # Object name is a mark number
+            assert objname > 0
+            return ":%i" % (objname)
+
+        # No existence check is done, only checks for valid format
+        assert cls.SHA1RE.match(objname)  # Object name is valid SHA1
+        return objname
+
+    @classmethod
+    def quote_path (cls, path):
+        """Return a quoted version of the given path."""
+        path = path.replace("\\", "\\\\")
+        path = path.replace("\n", "\\n")
+        path = path.replace('"', '\\"')
+        return '"%s"' % (path)
+
+    @classmethod
+    def parse_path (cls, path):
+        """Verify that the given path is valid, and quote it, if needed."""
+        assert not isinstance(path, int)  # Cannot be a mark number
+
+        # These checks verify the rules on the fast-import man page
+        assert not path.count("//")
+        assert not path.endswith("/")
+        assert not path.startswith("/")
+        assert not path.count("/./")
+        assert not path.count("/../")
+        assert not path.endswith("/.")
+        assert not path.endswith("/..")
+        assert not path.startswith("./")
+        assert not path.startswith("../")
+
+        if path.count('"') + path.count('\n') + path.count('\\'):
+            return cls.quote_path(path)
+        return path
+
+    def __init__ (self, name, email, timestamp, timezone, message):
+        """Create a new Git fast-import commit, with the given metadata."""
+        self.name = name
+        self.email = email
+        self.timestamp = timestamp
+        self.timezone = timezone
+        self.message = message
+        self.pathops = []  # List of path operations in this commit
+
+    def modify (self, mode, blobname, path):
+        """Add a file modification to this Git fast-import commit."""
+        self.pathops.append(("M",
+                             self.parse_mode(mode),
+                             self.parse_objname(blobname),
+                             self.parse_path(path)))
+
+    def delete (self, path):
+        """Add a file deletion to this Git fast-import commit."""
+        self.pathops.append(("D", self.parse_path(path)))
+
+    def copy (self, path, newpath):
+        """Add a file copy to this Git fast-import commit."""
+        self.pathops.append(("C",
+                             self.parse_path(path),
+                             self.parse_path(newpath)))
+
+    def rename (self, path, newpath):
+        """Add a file rename to this Git fast-import commit."""
+        self.pathops.append(("R",
+                             self.parse_path(path),
+                             self.parse_path(newpath)))
+
+    def note (self, blobname, commit):
+        """Add a note object to this Git fast-import commit."""
+        self.pathops.append(("N",
+                             self.parse_objname(blobname),
+                             self.parse_objname(commit)))
+
+    def deleteall (self):
+        """Delete all files in this Git fast-import commit."""
+        self.pathops.append("deleteall")
+
+
+class TestGitFICommit(unittest.TestCase):
+
+    """GitFICommit selftests."""
+
+    def test_basic (self):
+        """GitFICommit basic selftests."""
+
+        def expect_fail (method, data):
+            """Verify that the method(data) raises an AssertionError."""
+            try:
+                method(data)
+            except AssertionError:
+                return
+            raise AssertionError("Failed test for invalid data '%s(%s)'" %
+                                 (method.__name__, repr(data)))
+
+    def test_parse_mode (self):
+        """GitFICommit.parse_mode() selftests."""
+        self.assertEqual(GitFICommit.parse_mode(644), "644")
+        self.assertEqual(GitFICommit.parse_mode(755), "755")
+        self.assertEqual(GitFICommit.parse_mode(100644), "100644")
+        self.assertEqual(GitFICommit.parse_mode(100755), "100755")
+        self.assertEqual(GitFICommit.parse_mode(120000), "120000")
+        self.assertRaises(AssertionError, GitFICommit.parse_mode, 0)
+        self.assertRaises(AssertionError, GitFICommit.parse_mode, 123)
+        self.assertRaises(AssertionError, GitFICommit.parse_mode, 600)
+        self.assertRaises(AssertionError, GitFICommit.parse_mode, "644")
+        self.assertRaises(AssertionError, GitFICommit.parse_mode, "abc")
+
+    def test_parse_objname (self):
+        """GitFICommit.parse_objname() selftests."""
+        self.assertEqual(GitFICommit.parse_objname(1), ":1")
+        self.assertRaises(AssertionError, GitFICommit.parse_objname, 0)
+        self.assertRaises(AssertionError, GitFICommit.parse_objname, -1)
+        self.assertEqual(GitFICommit.parse_objname("0123456789" * 4),
+                         "0123456789" * 4)
+        self.assertEqual(GitFICommit.parse_objname("2468abcdef" * 4),
+                         "2468abcdef" * 4)
+        self.assertRaises(AssertionError, GitFICommit.parse_objname,
+                          "abcdefghij" * 4)
+
+    def test_parse_path (self):
+        """GitFICommit.parse_path() selftests."""
+        self.assertEqual(GitFICommit.parse_path("foo/bar"), "foo/bar")
+        self.assertEqual(GitFICommit.parse_path("path/with\n and \" in it"),
+                         '"path/with\\n and \\" in it"')
+        self.assertRaises(AssertionError, GitFICommit.parse_path, 1)
+        self.assertRaises(AssertionError, GitFICommit.parse_path, 0)
+        self.assertRaises(AssertionError, GitFICommit.parse_path, -1)
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "foo//bar")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "foo/bar/")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "/foo/bar")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "foo/./bar")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "foo/../bar")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "foo/bar/.")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "foo/bar/..")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "./foo/bar")
+        self.assertRaises(AssertionError, GitFICommit.parse_path, "../foo/bar")
+
+
+class GitFastImport(object):
+
+    """Encapsulate communication with git fast-import."""
+
+    def __init__ (self, f, obj_fetcher, last_mark = 0):
+        """Set up self to communicate with a fast-import process through f."""
+        self.f = f  # File object where fast-import stream is written
+        self.obj_fetcher = obj_fetcher  # GitObjectFetcher instance
+        self.next_mark = last_mark + 1  # Next mark number
+        self.refs = set()  # Keep track of the refnames we've seen
+
+    def comment (self, s):
+        """Write the given comment in the fast-import stream."""
+        assert "\n" not in s, "Malformed comment: '%s'" % (s)
+        self.f.write("# %s\n" % (s))
+
+    def commit (self, ref, commitdata):
+        """Make a commit on the given ref, with the given GitFICommit.
+
+        Return the mark number identifying this commit.
+
+        """
+        self.f.write("""\
+commit %(ref)s
+mark :%(mark)i
+committer %(name)s <%(email)s> %(timestamp)i %(timezone)s
+data %(msgLength)i
+%(msg)s
+""" % {
+    'ref': ref,
+    'mark': self.next_mark,
+    'name': commitdata.name,
+    'email': commitdata.email,
+    'timestamp': commitdata.timestamp,
+    'timezone': commitdata.timezone,
+    'msgLength': len(commitdata.message),
+    'msg': commitdata.message,
+})
+
+        if ref not in self.refs:
+            self.refs.add(ref)
+            parent = ref + "^0"
+            if self.obj_fetcher.get_sha1(parent):
+                self.f.write("from %s\n" % (parent))
+
+        for op in commitdata.pathops:
+            self.f.write(" ".join(op))
+            self.f.write("\n")
+        self.f.write("\n")
+        retval = self.next_mark
+        self.next_mark += 1
+        return retval
+
+    def blob (self, data):
+        """Import the given blob.
+
+        Return the mark number identifying this blob.
+
+        """
+        self.f.write("blob\nmark :%i\ndata %i\n%s\n" %
+                     (self.next_mark, len(data), data))
+        retval = self.next_mark
+        self.next_mark += 1
+        return retval
+
+    def reset (self, ref, objname):
+        """Reset the given ref to point at the given Git object."""
+        self.f.write("reset %s\nfrom %s\n\n" %
+                     (ref, GitFICommit.parse_objname(objname)))
+        if ref not in self.refs:
+            self.refs.add(ref)
+
+
+class GitNotes(object):
+
+    """Encapsulate access to Git notes.
+
+    Simulates a dictionary of object name (SHA1) -> Git note mappings.
+
+    """
+
+    def __init__ (self, notes_ref, obj_fetcher):
+        """Create a new Git notes interface, bound to the given notes ref."""
+        self.notes_ref = notes_ref
+        self.obj_fetcher = obj_fetcher  # Used to get objects from repo
+        self.imports = []  # list: (objname, note data blob name) tuples
+
+    def __del__ (self):
+        """Verify that self.commit_notes() was called before destruction."""
+        if self.imports:
+            error("Missing call to self.commit_notes().")
+            error("%i notes are not committed!", len(self.imports))
+
+    def _load (self, objname):
+        """Return the note data associated with the given git object.
+
+        The note data is returned in string form. If no note is found
+        for the given object, None is returned.
+
+        """
+        try:
+            f = self.obj_fetcher.open_obj("%s:%s" % (self.notes_ref, objname))
+            ret = f.read()
+            f.close()
+        except KeyError:
+            ret = None
+        return ret
+
+    def __getitem__ (self, objname):
+        """Return the note contents associated with the given object.
+
+        Raise KeyError if given object has no associated note.
+
+        """
+        blobdata = self._load(objname)
+        if blobdata is None:
+            raise KeyError("Object '%s' has no note" % (objname))
+        return blobdata
+
+    def get (self, objname, default = None):
+        """Return the note contents associated with the given object.
+
+        Return given default if given object has no associated note.
+
+        """
+        blobdata = self._load(objname)
+        if blobdata is None:
+            return default
+        return blobdata
+
+    def import_note (self, objname, data, gfi):
+        """Tell git fast-import to store data as a note for objname.
+
+        This method uses the given GitFastImport object to create a
+        blob containing the given note data.  Also an entry mapping the
+        given object name to the created blob is stored until
+        commit_notes() is called.
+
+        Note that this method only works if it is later followed by a
+        call to self.commit_notes() (which produces the note commit
+        that refers to the blob produced here).
+
+        """
+        if not data.endswith("\n"):
+            data += "\n"
+        gfi.comment("Importing note for object %s" % (objname))
+        mark = gfi.blob(data)
+        self.imports.append((objname, mark))
+
+    def commit_notes (self, gfi, author, message):
+        """Produce a git fast-import note commit for the imported notes.
+
+        This method uses the given GitFastImport object to create a
+        commit on the notes ref, introducing the notes previously
+        submitted to import_note().
+
+        """
+        if not self.imports:
+            return
+        commitdata = GitFICommit(author[0], author[1],
+                                 time.time(), "0000", message)
+        for objname, blobname in self.imports:
+            assert isinstance(objname, int) and objname > 0
+            assert isinstance(blobname, int) and blobname > 0
+            commitdata.note(blobname, objname)
+        gfi.commit(self.notes_ref, commitdata)
+        self.imports = []
+
+
+class GitCachedNotes(GitNotes):
+
+    """Encapsulate access to Git notes (cached version).
+
+    Only use this class if no caching is done at a higher level.
+
+    Simulates a dictionary of object name (SHA1) -> Git note mappings.
+
+    """
+
+    def __init__ (self, notes_ref, obj_fetcher):
+        """Set up a caching wrapper around GitNotes."""
+        GitNotes.__init__(self, notes_ref, obj_fetcher)
+        self._cache = {}  # Cache: object name -> note data
+
+    def __del__ (self):
+        """Verify that GitNotes' destructor is called."""
+        GitNotes.__del__(self)
+
+    def _load (self, objname):
+        """Extend GitNotes._load() with a local objname -> note cache."""
+        if objname not in self._cache:
+            self._cache[objname] = GitNotes._load(self, objname)
+        return self._cache[objname]
+
+    def import_note (self, objname, data, gfi):
+        """Extend GitNotes.import_note() with a local objname -> note cache."""
+        if not data.endswith("\n"):
+            data += "\n"
+        assert objname not in self._cache
+        self._cache[objname] = data
+        GitNotes.import_note(self, objname, data, gfi)
+
+
+if __name__ == '__main__':
+    unittest.main()

git_remote_helpers/setup.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+
+"""Distutils build/install script for the git_remote_helpers package."""
+
+from distutils.core import setup
+
+setup(
+    name = 'git_remote_helpers',
+    version = '0.1.0',
+    description = 'Git remote helper program for non-git repositories',
+    license = 'GPLv2',
+    author = 'The Git Community',
+    author_email = 'git@vger.kernel.org',
+    url = 'http://www.git-scm.com/',
+    package_dir = {'git_remote_helpers': ''},
+    packages = ['git_remote_helpers', 'git_remote_helpers.git'],
+)

git_remote_helpers/util.py

@@ -0,0 +1,194 @@
+#!/usr/bin/env python
+
+"""Misc. useful functionality used by the rest of this package.
+
+This module provides common functionality used by the other modules in
+this package.
+
+"""
+
+import sys
+import os
+import subprocess
+
+
+# Whether or not to show debug messages
+DEBUG = False
+
+def notify(msg, *args):
+    """Print a message to stderr."""
+    print >> sys.stderr, msg % args
+
+def debug (msg, *args):
+    """Print a debug message to stderr when DEBUG is enabled."""
+    if DEBUG:
+        print >> sys.stderr, msg % args
+
+def error (msg, *args):
+    """Print an error message to stderr."""
+    print >> sys.stderr, "ERROR:", msg % args
+
+def warn(msg, *args):
+    """Print a warning message to stderr."""
+    print >> sys.stderr, "warning:", msg % args
+
+def die (msg, *args):
+    """Print as error message to stderr and exit the program."""
+    error(msg, *args)
+    sys.exit(1)
+
+
+class ProgressIndicator(object):
+
+    """Simple progress indicator.
+
+    Displayed as a spinning character by default, but can be customized
+    by passing custom messages that overrides the spinning character.
+
+    """
+
+    States = ("|", "/", "-", "\\")
+
+    def __init__ (self, prefix = "", f = sys.stdout):
+        """Create a new ProgressIndicator, bound to the given file object."""
+        self.n = 0  # Simple progress counter
+        self.f = f  # Progress is written to this file object
+        self.prev_len = 0  # Length of previous msg (to be overwritten)
+        self.prefix = prefix  # Prefix prepended to each progress message
+        self.prefix_lens = [] # Stack of prefix string lengths
+
+    def pushprefix (self, prefix):
+        """Append the given prefix onto the prefix stack."""
+        self.prefix_lens.append(len(self.prefix))
+        self.prefix += prefix
+
+    def popprefix (self):
+        """Remove the last prefix from the prefix stack."""
+        prev_len = self.prefix_lens.pop()
+        self.prefix = self.prefix[:prev_len]
+
+    def __call__ (self, msg = None, lf = False):
+        """Indicate progress, possibly with a custom message."""
+        if msg is None:
+            msg = self.States[self.n % len(self.States)]
+        msg = self.prefix + msg
+        print >> self.f, "\r%-*s" % (self.prev_len, msg),
+        self.prev_len = len(msg.expandtabs())
+        if lf:
+            print >> self.f
+            self.prev_len = 0
+        self.n += 1
+
+    def finish (self, msg = "done", noprefix = False):
+        """Finalize progress indication with the given message."""
+        if noprefix:
+            self.prefix = ""
+        self(msg, True)
+
+
+def start_command (args, cwd = None, shell = False, add_env = None,
+                   stdin = subprocess.PIPE, stdout = subprocess.PIPE,
+                   stderr = subprocess.PIPE):
+    """Start the given command, and return a subprocess object.
+
+    This provides a simpler interface to the subprocess module.
+
+    """
+    env = None
+    if add_env is not None:
+        env = os.environ.copy()
+        env.update(add_env)
+    return subprocess.Popen(args, bufsize = 1, stdin = stdin, stdout = stdout,
+                            stderr = stderr, cwd = cwd, shell = shell,
+                            env = env, universal_newlines = True)
+
+
+def run_command (args, cwd = None, shell = False, add_env = None,
+                 flag_error = True):
+    """Run the given command to completion, and return its results.
+
+    This provides a simpler interface to the subprocess module.
+
+    The results are formatted as a 3-tuple: (exit_code, output, errors)
+
+    If flag_error is enabled, Error messages will be produced if the
+    subprocess terminated with a non-zero exit code and/or stderr
+    output.
+
+    The other arguments are passed on to start_command().
+
+    """
+    process = start_command(args, cwd, shell, add_env)
+    (output, errors) = process.communicate()
+    exit_code = process.returncode
+    if flag_error and errors:
+        error("'%s' returned errors:\n---\n%s---", " ".join(args), errors)
+    if flag_error and exit_code:
+        error("'%s' returned exit code %i", " ".join(args), exit_code)
+    return (exit_code, output, errors)
+
+
+def file_reader_method (missing_ok = False):
+    """Decorator for simplifying reading of files.
+
+    If missing_ok is True, a failure to open a file for reading will
+    not raise the usual IOError, but instead the wrapped method will be
+    called with f == None.  The method must in this case properly
+    handle f == None.
+
+    """
+    def _wrap (method):
+        """Teach given method to handle both filenames and file objects.
+
+        The given method must take a file object as its second argument
+        (the first argument being 'self', of course).  This decorator
+        will take a filename given as the second argument and promote
+        it to a file object.
+
+        """
+        def _wrapped_method (self, filename, *args, **kwargs):
+            if isinstance(filename, file):
+                f = filename
+            else:
+                try:
+                    f = open(filename, 'r')
+                except IOError:
+                    if missing_ok:
+                        f = None
+                    else:
+                        raise
+            try:
+                return method(self, f, *args, **kwargs)
+            finally:
+                if not isinstance(filename, file) and f:
+                    f.close()
+        return _wrapped_method
+    return _wrap
+
+
+def file_writer_method (method):
+    """Decorator for simplifying writing of files.
+
+    Enables the given method to handle both filenames and file objects.
+
+    The given method must take a file object as its second argument
+    (the first argument being 'self', of course).  This decorator will
+    take a filename given as the second argument and promote it to a
+    file object.
+
+    """
+    def _new_method (self, filename, *args, **kwargs):
+        if isinstance(filename, file):
+            f = filename
+        else:
+            # Make sure the containing directory exists
+            parent_dir = os.path.dirname(filename)
+            if not os.path.isdir(parent_dir):
+                os.makedirs(parent_dir)
+            f = open(filename, 'w')
+        try:
+            return method(self, f, *args, **kwargs)
+        finally:
+            if not isinstance(filename, file):
+                f.close()
+    return _new_method

remote.c

@@ -53,6 +53,11 @@ static struct rewrites rewrites_push;
 #define BUF_SIZE (2048)
 static char buffer[BUF_SIZE];
 
+static int valid_remote(const struct remote *remote)
+{
+	return (!!remote->url) || (!!remote->foreign_vcs);
+}
+
 static const char *alias_url(const char *url, struct rewrites *r)
 {
 	int i, j;
@@ -441,6 +446,8 @@ static int handle_config(const char *key, const char *value, void *cb)
 	} else if (!strcmp(subkey, ".proxy")) {
 		return git_config_string((const char **)&remote->http_proxy,
 					 key, value);
+	} else if (!strcmp(subkey, ".vcs")) {
+		return git_config_string(&remote->foreign_vcs, key, value);
 	}
 	return 0;
 }
@@ -668,6 +675,16 @@ static struct refspec *parse_push_refspec(int nr_refspec, const char **refspec)
 	return parse_refspec_internal(nr_refspec, refspec, 0, 0);
 }
 
+void free_refspec(int nr_refspec, struct refspec *refspec)
+{
+	int i;
+	for (i = 0; i < nr_refspec; i++) {
+		free(refspec[i].src);
+		free(refspec[i].dst);
+	}
+	free(refspec);
+}
+
 static int valid_remote_nick(const char *name)
 {
 	if (!name[0] || is_dot_or_dotdot(name))
@@ -690,14 +707,14 @@ struct remote *remote_get(const char *name)
 
 	ret = make_remote(name, 0);
 	if (valid_remote_nick(name)) {
-		if (!ret->url)
+		if (!valid_remote(ret))
 			read_remotes_file(ret);
-		if (!ret->url)
+		if (!valid_remote(ret))
 			read_branches_file(ret);
 	}
-	if (name_given && !ret->url)
+	if (name_given && !valid_remote(ret))
 		add_url_alias(ret, name);
-	if (!ret->url)
+	if (!valid_remote(ret))
 		return NULL;
 	ret->fetch = parse_fetch_refspec(ret->fetch_refspec_nr, ret->fetch_refspec);
 	ret->push = parse_push_refspec(ret->push_refspec_nr, ret->push_refspec);
@@ -810,6 +827,23 @@ static int match_name_with_pattern(const char *key, const char *name,
 	return ret;
 }
 
+char *apply_refspecs(struct refspec *refspecs, int nr_refspec,
+		     const char *name)
+{
+	int i;
+	char *ret = NULL;
+	for (i = 0; i < nr_refspec; i++) {
+		struct refspec *refspec = refspecs + i;
+		if (refspec->pattern) {
+			if (match_name_with_pattern(refspec->src, name,
+						    refspec->dst, &ret))
+				return ret;
+		} else if (!strcmp(refspec->src, name))
+			return strdup(refspec->dst);
+	}
+	return NULL;
+}
+
 int remote_find_tracking(struct remote *remote, struct refspec *refspec)
 {
 	int find_src = refspec->src == NULL;

remote.h

@@ -11,6 +11,8 @@ struct remote {
 	const char *name;
 	int origin;
 
+	const char *foreign_vcs;
+
 	const char **url;
 	int url_nr;
 	int url_alloc;
@@ -89,6 +91,11 @@ void ref_remove_duplicates(struct ref *ref_map);
 int valid_fetch_refspec(const char *refspec);
 struct refspec *parse_fetch_refspec(int nr_refspec, const char **refspec);
 
+void free_refspec(int nr_refspec, struct refspec *refspec);
+
+char *apply_refspecs(struct refspec *refspecs, int nr_refspec,
+		     const char *name);
+
 int match_refs(struct ref *src, struct ref **dst,
 	       int nr_refspec, const char **refspec, int all);
 

t/test-lib.sh

@@ -632,20 +632,29 @@ GIT_CONFIG_NOSYSTEM=1
 GIT_CONFIG_NOGLOBAL=1
 export PATH GIT_EXEC_PATH GIT_TEMPLATE_DIR GIT_CONFIG_NOSYSTEM GIT_CONFIG_NOGLOBAL
 
+. ../GIT-BUILD-OPTIONS
+
 GITPERLLIB=$(pwd)/../perl/blib/lib:$(pwd)/../perl/blib/arch/auto/Git
 export GITPERLLIB
 test -d ../templates/blt || {
 	error "You haven't built things yet, have you?"
 }
 
+if test -z "$GIT_TEST_INSTALLED" && test -z "$NO_PYTHON"
+then
+	GITPYTHONLIB="$(pwd)/../git_remote_helpers/build/lib"
+	export GITPYTHONLIB
+	test -d ../git_remote_helpers/build || {
+		error "You haven't built git_remote_helpers yet, have you?"
+	}
+fi
+
 if ! test -x ../test-chmtime; then
 	echo >&2 'You need to build test-chmtime:'
 	echo >&2 'Run "make test-chmtime" in the source (toplevel) directory'
 	exit 1
 fi
 
-. ../GIT-BUILD-OPTIONS
-
 # Test repository
 test="trash directory.$(basename "$0" .sh)"
 test -n "$root" && test="$root/$test"
@@ -729,6 +738,7 @@ case $(uname -s) in
 esac
 
 test -z "$NO_PERL" && test_set_prereq PERL
+test -z "$NO_PYTHON" && test_set_prereq PYTHON
 
 # test whether the filesystem supports symbolic links
 ln -s x y 2>/dev/null && test -h y 2>/dev/null && test_set_prereq SYMLINKS

transport-helper.c

@@ -6,6 +6,7 @@
 #include "diff.h"
 #include "revision.h"
 #include "quote.h"
+#include "remote.h"
 
 struct helper_data
 {
@@ -13,8 +14,12 @@ struct helper_data
 	struct child_process *helper;
 	FILE *out;
 	unsigned fetch : 1,
+		import : 1,
 		option : 1,
 		push : 1;
+	/* These go from remote name (as in "list") to private name */
+	struct refspec *refspecs;
+	int refspec_nr;
 };
 
 static struct child_process *get_helper(struct transport *transport)
@@ -22,6 +27,9 @@ static struct child_process *get_helper(struct transport *transport)
 	struct helper_data *data = transport->data;
 	struct strbuf buf = STRBUF_INIT;
 	struct child_process *helper;
+	const char **refspecs = NULL;
+	int refspec_nr = 0;
+	int refspec_alloc = 0;
 
 	if (data->helper)
 		return data->helper;
@@ -55,7 +63,25 @@ static struct child_process *get_helper(struct transport *transport)
 			data->option = 1;
 		if (!strcmp(buf.buf, "push"))
 			data->push = 1;
+		if (!strcmp(buf.buf, "import"))
+			data->import = 1;
+		if (!data->refspecs && !prefixcmp(buf.buf, "refspec ")) {
+			ALLOC_GROW(refspecs,
+				   refspec_nr + 1,
+				   refspec_alloc);
+			refspecs[refspec_nr++] = strdup(buf.buf + strlen("refspec "));
+		}
 	}
+	if (refspecs) {
+		int i;
+		data->refspec_nr = refspec_nr;
+		data->refspecs = parse_fetch_refspec(refspec_nr, refspecs);
+		for (i = 0; i < refspec_nr; i++) {
+			free((char *)refspecs[i]);
+		}
+		free(refspecs);
+	}
+	strbuf_release(&buf);
 	return data->helper;
 }
 
@@ -72,7 +98,6 @@ static int disconnect_helper(struct transport *transport)
 		free(data->helper);
 		data->helper = NULL;
 	}
-	free(data);
 	return 0;
 }
 
@@ -154,8 +179,18 @@ static void standard_options(struct transport *t)
 	set_helper_option(t, "verbosity", buf);
 }
 
+static int release_helper(struct transport *transport)
+{
+	struct helper_data *data = transport->data;
+	free_refspec(data->refspec_nr, data->refspecs);
+	data->refspecs = NULL;
+	disconnect_helper(transport);
+	free(transport->data);
+	return 0;
+}
+
 static int fetch_with_fetch(struct transport *transport,
-			    int nr_heads, const struct ref **to_fetch)
+			    int nr_heads, struct ref **to_fetch)
 {
 	struct helper_data *data = transport->data;
 	int i;
@@ -197,8 +232,64 @@ static int fetch_with_fetch(struct transport *transport,
 	return 0;
 }
 
+static int get_importer(struct transport *transport, struct child_process *fastimport)
+{
+	struct child_process *helper = get_helper(transport);
+	memset(fastimport, 0, sizeof(*fastimport));
+	fastimport->in = helper->out;
+	fastimport->argv = xcalloc(5, sizeof(*fastimport->argv));
+	fastimport->argv[0] = "fast-import";
+	fastimport->argv[1] = "--quiet";
+
+	fastimport->git_cmd = 1;
+	return start_command(fastimport);
+}
+
+static int fetch_with_import(struct transport *transport,
+			     int nr_heads, struct ref **to_fetch)
+{
+	struct child_process fastimport;
+	struct child_process *helper = get_helper(transport);
+	struct helper_data *data = transport->data;
+	int i;
+	struct ref *posn;
+	struct strbuf buf = STRBUF_INIT;
+
+	if (get_importer(transport, &fastimport))
+		die("Couldn't run fast-import");
+
+	for (i = 0; i < nr_heads; i++) {
+		posn = to_fetch[i];
+		if (posn->status & REF_STATUS_UPTODATE)
+			continue;
+
+		strbuf_addf(&buf, "import %s\n", posn->name);
+		write_in_full(helper->in, buf.buf, buf.len);
+		strbuf_reset(&buf);
+	}
+	disconnect_helper(transport);
+	finish_command(&fastimport);
+	free(fastimport.argv);
+	fastimport.argv = NULL;
+
+	for (i = 0; i < nr_heads; i++) {
+		char *private;
+		posn = to_fetch[i];
+		if (posn->status & REF_STATUS_UPTODATE)
+			continue;
+		if (data->refspecs)
+			private = apply_refspecs(data->refspecs, data->refspec_nr, posn->name);
+		else
+			private = strdup(posn->name);
+		read_ref(private, posn->old_sha1);
+		free(private);
+	}
+	strbuf_release(&buf);
+	return 0;
+}
+
 static int fetch(struct transport *transport,
-		 int nr_heads, const struct ref **to_fetch)
+		 int nr_heads, struct ref **to_fetch)
 {
 	struct helper_data *data = transport->data;
 	int i, count;
@@ -214,6 +305,9 @@ static int fetch(struct transport *transport,
 	if (data->fetch)
 		return fetch_with_fetch(transport, nr_heads, to_fetch);
 
+	if (data->import)
+		return fetch_with_import(transport, nr_heads, to_fetch);
+
 	return -1;
 }
 
@@ -343,6 +437,22 @@ static int push_refs(struct transport *transport,
 	return 0;
 }
 
+static int has_attribute(const char *attrs, const char *attr) {
+	int len;
+	if (!attrs)
+		return 0;
+
+	len = strlen(attr);
+	for (;;) {
+		const char *space = strchrnul(attrs, ' ');
+		if (len == space - attrs && !strncmp(attrs, attr, len))
+			return 1;
+		if (!*space)
+			return 0;
+		attrs = space + 1;
+	}
+}
+
 static struct ref *get_refs_list(struct transport *transport, int for_push)
 {
 	struct helper_data *data = transport->data;
@@ -379,6 +489,12 @@ static struct ref *get_refs_list(struct transport *transport, int for_push)
 			(*tail)->symref = xstrdup(buf.buf + 1);
 		else if (buf.buf[0] != '?')
 			get_sha1_hex(buf.buf, (*tail)->old_sha1);
+		if (eon) {
+			if (has_attribute(eon + 1, "unchanged")) {
+				(*tail)->status |= REF_STATUS_UPTODATE;
+				read_ref((*tail)->name, (*tail)->old_sha1);
+			}
+		}
 		tail = &((*tail)->next);
 	}
 	strbuf_release(&buf);
@@ -399,6 +515,6 @@ int transport_helper_init(struct transport *transport, const char *name)
 	transport->get_refs_list = get_refs_list;
 	transport->fetch = fetch;
 	transport->push_refs = push_refs;
-	transport->disconnect = disconnect_helper;
+	transport->disconnect = release_helper;
 	return 0;
 }

transport.c

@@ -204,7 +204,7 @@ static struct ref *get_refs_via_rsync(struct transport *transport, int for_push)
 }
 
 static int fetch_objs_via_rsync(struct transport *transport,
-				int nr_objs, const struct ref **to_fetch)
+				int nr_objs, struct ref **to_fetch)
 {
 	struct strbuf buf = STRBUF_INIT;
 	struct child_process rsync;
@@ -379,7 +379,7 @@ static struct ref *get_refs_from_bundle(struct transport *transport, int for_pus
 }
 
 static int fetch_refs_from_bundle(struct transport *transport,
-			       int nr_heads, const struct ref **to_fetch)
+			       int nr_heads, struct ref **to_fetch)
 {
 	struct bundle_transport_data *data = transport->data;
 	return unbundle(&data->header, data->fd);
@@ -457,7 +457,7 @@ static struct ref *get_refs_via_connect(struct transport *transport, int for_pus
 }
 
 static int fetch_refs_via_pack(struct transport *transport,
-			       int nr_heads, const struct ref **to_fetch)
+			       int nr_heads, struct ref **to_fetch)
 {
 	struct git_transport_data *data = transport->data;
 	char **heads = xmalloc(nr_heads * sizeof(*heads));
@@ -788,8 +788,26 @@ struct transport *transport_get(struct remote *remote, const char *url)
 		die("No remote provided to transport_get()");
 
 	ret->remote = remote;
+
+	if (!url && remote && remote->url)
+		url = remote->url[0];
 	ret->url = url;
 
+	/* maybe it is a foreign URL? */
+	if (url) {
+		const char *p = url;
+
+		while (isalnum(*p))
+			p++;
+		if (!prefixcmp(p, "::"))
+			remote->foreign_vcs = xstrndup(url, p - url);
+	}
+
+	if (remote && remote->foreign_vcs) {
+		transport_helper_init(ret, remote->foreign_vcs);
+		return ret;
+	}
+
 	if (!prefixcmp(url, "rsync:")) {
 		ret->get_refs_list = get_refs_via_rsync;
 		ret->fetch = fetch_objs_via_rsync;
@@ -896,16 +914,17 @@ const struct ref *transport_get_remote_refs(struct transport *transport)
 	return transport->remote_refs;
 }
 
-int transport_fetch_refs(struct transport *transport, const struct ref *refs)
+int transport_fetch_refs(struct transport *transport, struct ref *refs)
 {
 	int rc;
 	int nr_heads = 0, nr_alloc = 0, nr_refs = 0;
-	const struct ref **heads = NULL;
+	struct ref **heads = NULL;
-	const struct ref *rm;
+	struct ref *rm;
 
 	for (rm = refs; rm; rm = rm->next) {
 		nr_refs++;
 		if (rm->peer_ref &&
+		    !is_null_sha1(rm->old_sha1) &&
 		    !hashcmp(rm->peer_ref->old_sha1, rm->old_sha1))
 			continue;
 		ALLOC_GROW(heads, nr_heads + 1, nr_alloc);

transport.h

@@ -18,11 +18,48 @@ struct transport {
 	int (*set_option)(struct transport *connection, const char *name,
 			  const char *value);
 
+	/**
+	 * Returns a list of the remote side's refs. In order to allow
+	 * the transport to try to share connections, for_push is a
+	 * hint as to whether the ultimate operation is a push or a fetch.
+	 *
+	 * If the transport is able to determine the remote hash for
+	 * the ref without a huge amount of effort, it should store it
+	 * in the ref's old_sha1 field; otherwise it should be all 0.
+	 **/
 	struct ref *(*get_refs_list)(struct transport *transport, int for_push);
-	int (*fetch)(struct transport *transport, int refs_nr, const struct ref **refs);
+
+	/**
+	 * Fetch the objects for the given refs. Note that this gets
+	 * an array, and should ignore the list structure.
+	 *
+	 * If the transport did not get hashes for refs in
+	 * get_refs_list(), it should set the old_sha1 fields in the
+	 * provided refs now.
+	 **/
+	int (*fetch)(struct transport *transport, int refs_nr, struct ref **refs);
+
+	/**
+	 * Push the objects and refs. Send the necessary objects, and
+	 * then, for any refs where peer_ref is set and
+	 * peer_ref->new_sha1 is different from old_sha1, tell the
+	 * remote side to update each ref in the list from old_sha1 to
+	 * peer_ref->new_sha1.
+	 *
+	 * Where possible, set the status for each ref appropriately.
+	 *
+	 * The transport must modify new_sha1 in the ref to the new
+	 * value if the remote accepted the change. Note that this
+	 * could be a different value from peer_ref->new_sha1 if the
+	 * process involved generating new commits.
+	 **/
 	int (*push_refs)(struct transport *transport, struct ref *refs, int flags);
 	int (*push)(struct transport *connection, int refspec_nr, const char **refspec, int flags);
 
+	/** get_refs_list(), fetch(), and push_refs() can keep
+	 * resources (such as a connection) reserved for futher
+	 * use. disconnect() releases these resources.
+	 **/
 	int (*disconnect)(struct transport *connection);
 	char *pack_lockfile;
 	signed verbose : 3;
@@ -74,7 +111,7 @@ int transport_push(struct transport *connection,
 
 const struct ref *transport_get_remote_refs(struct transport *transport);
 
-int transport_fetch_refs(struct transport *transport, const struct ref *refs);
+int transport_fetch_refs(struct transport *transport, struct ref *refs);
 void transport_unlock_pack(struct transport *transport);
 int transport_disconnect(struct transport *transport);
 char *transport_anonymize_url(const char *url);