Made repo.py a package to allow better localization of functions and utilities - the repo module got rather large

5 files changed, 260 insertions, 237 deletions

diff --git a/lib/git/index/__init__.py b/lib/git/index/__init__.py
index 13f874b0..fe4a7f59 100644
--- a/lib/git/index/__init__.py
+++ b/lib/git/index/__init__.py
@@ -1,4 +1,4 @@
-"""Initialize the index module"""
+"""Initialize the index package"""
 
 from base import *
 from typ import *
\ No newline at end of file
diff --git a/lib/git/refs.py b/lib/git/refs.py
index 8b773ae7..be094d01 100644
--- a/lib/git/refs.py
+++ b/lib/git/refs.py
@@ -208,9 +208,8 @@ class SymbolicReference(object):
 			try:
 				write_value = ref.commit.hexsha
 			except AttributeError:
-				sha = str(ref)
 				try:
-					obj = Object.new_from_sha(self.repo, hex_to_bin(sha))
+					obj = self.repo.rev_parse(ref+"^{}")	# optionally deref tags
 					if obj.type != "commit":
 						raise TypeError("Invalid object type behind sha: %s" % sha)
 					write_value = obj.hexsha
diff --git a/lib/git/repo/__init__.py b/lib/git/repo/__init__.py
new file mode 100644
index 00000000..8902a254
--- /dev/null
+++ b/lib/git/repo/__init__.py
@@ -0,0 +1,3 @@
+"""Initialize the Repo package"""
+
+from base import *
\ No newline at end of file
diff --git a/lib/git/repo.py b/lib/git/repo/base.py
index e9dfabcd..976a68bf 100644
--- a/lib/git/repo.py
+++ b/lib/git/repo/base.py
@@ -4,28 +4,32 @@
 # This module is part of GitPython and is released under
 # the BSD License: http://www.opensource.org/licenses/bsd-license.php
 
-from exc import InvalidGitRepositoryError, NoSuchPathError
-from cmd import Git
-from objects import Actor
-from refs import *
-from index import IndexFile
-from objects import *
-from config import GitConfigParser
-from remote import Remote
-from string import digits
-from db import (
+from git.exc import InvalidGitRepositoryError, NoSuchPathError
+from git.cmd import Git
+from git.objects import Actor
+from git.refs import *
+from git.index import IndexFile
+from git.objects import *
+from git.config import GitConfigParser
+from git.remote import Remote
+from git.db import (
 				GitCmdObjectDB, 
 				GitDB
 				)
 
-from gitdb.exc import BadObject
+
 from gitdb.util import (
 							join,
-							isdir, 
 							isfile,
-							join,
 							hex_to_bin
 						)
+
+from fun import (
+					rev_parse,
+					is_git_dir,
+					touch
+				)
+
 import os
 import sys
 import re
@@ -33,23 +37,6 @@ import re
 
 __all__ = ('Repo', )
 
-def touch(filename):
-	fp = open(filename, "a")
-	fp.close()
-
-def is_git_dir(d):
-	""" This is taken from the git setup.c:is_git_directory
-	function."""
-
-	if isdir(d) and \
-			isdir(join(d, 'objects')) and \
-			isdir(join(d, 'refs')):
-		headref = join(d, 'HEAD')
-		return isfile(headref) or \
-				(os.path.islink(headref) and
-				os.readlink(headref).startswith('refs'))
-	return False
-
 
 class Repo(object):
 	"""Represents a git repository and allows you to query references, 
@@ -112,7 +99,7 @@ class Repo(object):
 				self.git_dir = curpath
 				self._working_tree_dir = os.path.dirname(curpath)
 				break
-			gitpath = os.path.join(curpath, '.git')
+			gitpath = join(curpath, '.git')
 			if is_git_dir(gitpath):
 				self.git_dir = gitpath
 				self._working_tree_dir = curpath
@@ -142,7 +129,7 @@ class Repo(object):
 		self.git = Git(self.working_dir)
 		
 		# special handling, in special times
-		args = [os.path.join(self.git_dir, 'objects')]
+		args = [join(self.git_dir, 'objects')]
 		if issubclass(odbt, GitCmdObjectDB):
 			args.append(self.git)
 		self.odb = odbt(*args)
@@ -163,11 +150,11 @@ class Repo(object):
 
 	# Description property
 	def _get_description(self):
-		filename = os.path.join(self.git_dir, 'description')
+		filename = join(self.git_dir, 'description')
 		return file(filename).read().rstrip()
 
 	def _set_description(self, descr):
-		filename = os.path.join(self.git_dir, 'description')
+		filename = join(self.git_dir, 'description')
 		file(filename, 'w').write(descr+'\n')
 
 	description = property(_get_description, _set_description,
@@ -396,11 +383,11 @@ class Repo(object):
 		return Commit.iter_items(self, rev, paths, **kwargs)
 
 	def _get_daemon_export(self):
-		filename = os.path.join(self.git_dir, self.DAEMON_EXPORT_FILE)
+		filename = join(self.git_dir, self.DAEMON_EXPORT_FILE)
 		return os.path.exists(filename)
 
 	def _set_daemon_export(self, value):
-		filename = os.path.join(self.git_dir, self.DAEMON_EXPORT_FILE)
+		filename = join(self.git_dir, self.DAEMON_EXPORT_FILE)
 		fileexists = os.path.exists(filename)
 		if value and not fileexists:
 			touch(filename)
@@ -416,7 +403,7 @@ class Repo(object):
 		"""The list of alternates for this repo from which objects can be retrieved
 
 		:return: list of strings being pathnames of alternates"""
-		alternates_path = os.path.join(self.git_dir, 'objects', 'info', 'alternates')
+		alternates_path = join(self.git_dir, 'objects', 'info', 'alternates')
 
 		if os.path.exists(alternates_path):
 			try:
@@ -439,9 +426,9 @@ class Repo(object):
 		:note:
 			The method does not check for the existance of the paths in alts
 			as the caller is responsible."""
-		alternates_path = os.path.join(self.git_dir, 'objects', 'info', 'alternates') 
+		alternates_path = join(self.git_dir, 'objects', 'info', 'alternates') 
 		if not alts:
-			if os.path.isfile(alternates_path):
+			if isfile(alternates_path):
 				os.remove(alternates_path)
 		else:
 			try:
@@ -469,7 +456,7 @@ class Repo(object):
 		default_args = ('--abbrev=40', '--full-index', '--raw')
 		if index: 
 			# diff index against HEAD
-			if os.path.isfile(self.index.path) and self.head.is_valid() and \
+			if isfile(self.index.path) and self.head.is_valid() and \
 				len(self.git.diff('HEAD', '--cached', *default_args)):
 				return True
 		# END index handling
@@ -677,7 +664,7 @@ class Repo(object):
 		# our git command could have a different working dir than our actual 
 		# environment, hence we prepend its working dir if required
 		if not os.path.isabs(path) and self.git.working_dir:
-			path = os.path.join(self.git._working_dir, path)
+			path = join(self.git._working_dir, path)
 		return Repo(os.path.abspath(path), odbt = odbt)
 
 
@@ -696,203 +683,13 @@ class Repo(object):
 		if treeish is None:
 			treeish = self.active_branch
 		if prefix and 'prefix' not in kwargs:
-			kwargs['prefix'] = prefix
+			kwargs['prefix'] = prefix 
 		kwargs['output_stream'] = ostream
 		
 		self.git.archive(treeish, **kwargs)
 		return self
+	
+	rev_parse = rev_parse
 		
-	def rev_parse(self, rev):
-		"""
-		:return: Object at the given revision, either Commit, Tag, Tree or Blob
-		:param rev: git-rev-parse compatible revision specification, please see
-			http://www.kernel.org/pub/software/scm/git/docs/git-rev-parse.html
-			for details
-		:note: Currently there is no access to the rev-log, rev-specs may only contain
-			topological tokens such ~ and ^.
-		:raise BadObject: if the given revision could not be found"""
-		if '@' in rev:
-			raise ValueError("There is no rev-log support yet")
-		
-		
-		# colon search mode ?
-		if rev.startswith(':/'):
-			# colon search mode
-			raise NotImplementedError("commit by message search ( regex )")
-		# END handle search
-		
-		# return object specified by the given name
-		def name_to_object(name):
-			hexsha = None
-			
-			# is it a hexsha ? Try the most common ones, which is 7 to 40
-			if self.re_hexsha_shortened.match(name):
-				if len(name) != 40:
-					# find long sha for short sha
-					raise NotImplementedError("short sha parsing")
-				else:
-					hexsha = name
-				# END handle short shas
-			else:
-				for base in ('%s', 'refs/%s', 'refs/tags/%s', 'refs/heads/%s', 'refs/remotes/%s', 'refs/remotes/%s/HEAD'):
-					try:
-						hexsha = SymbolicReference.dereference_recursive(self, base % name)
-						break
-					except ValueError:
-						pass
-				# END for each base
-			# END handle hexsha
-			
-			# tried everything ? fail
-			if hexsha is None:
-				# it could also be a very short ( less than 7 ) hexsha, which 
-				# wasnt tested in the first run
-				if len(name) < 7 and self.re_hexsha_domain.match(name):
-					raise NotImplementedError()	
-				# END try short name 
-				raise BadObject(name)
-			# END assert hexsha was found
-			
-			return Object.new_from_sha(self, hex_to_bin(hexsha))
-		# END object by name
-		
-		def deref_tag(tag):
-			while True:
-				try:
-					tag = tag.object
-				except AttributeError:
-					break
-			# END dereference tag
-			return tag
-		
-		def to_commit(obj):
-			if obj.type == 'tag':
-				obj = deref_tag(obj)
-				
-			if obj.type != "commit":
-				raise ValueError("Cannot convert object %r to type commit" % obj)
-			# END verify type
-			return obj
-		# END commit converter
-		
-		obj = None
-		output_type = "commit"
-		start = 0
-		parsed_to = 0
-		lr = len(rev)
-		while start < lr:
-			if rev[start] not in "^~:":
-				start += 1
-				continue
-			# END handle start
-			
-			if obj is None:
-				# token is a rev name
-				obj = name_to_object(rev[:start])
-			# END initialize obj on first token
-			
-			token = rev[start]
-			start += 1
-			
-			# try to parse {type}
-			if start < lr and rev[start] == '{':
-				end = rev.find('}', start)
-				if end == -1:
-					raise ValueError("Missing closing brace to define type in %s" % rev)
-				output_type = rev[start+1:end]	# exclude brace
-				
-				# handle type 
-				if output_type == 'commit':
-					pass # default
-				elif output_type == 'tree':
-					try:
-						obj = to_commit(obj).tree
-					except (AttributeError, ValueError):
-						pass	# error raised later
-					# END exception handling
-				elif output_type in ('', 'blob'):
-					if obj.type == 'tag':
-						obj = deref_tag(obj)
-					else:
-						# cannot do anything for non-tags
-						pass
-					# END handle tag
-				else:
-					raise ValueError("Invalid output type: %s ( in %s )"  % (output_type, rev))
-				# END handle output type
-				
-				# empty output types don't require any specific type, its just about dereferencing tags
-				if output_type and obj.type != output_type:
-					raise ValueError("Could not accomodate requested object type %r, got %s" % (output_type, obj.type))
-				# END verify ouput type
-				
-				start = end+1					# skip brace
-				parsed_to = start
-				continue
-			# END parse type
-			
-			# try to parse a number
-			num = 0
-			if token != ":":
-				found_digit = False
-				while start < lr:
-					if rev[start] in digits:
-						num = num * 10 + int(rev[start])
-						start += 1
-						found_digit = True
-					else:
-						break
-					# END handle number
-				# END number parse loop
-				
-				# no explicit number given, 1 is the default
-				# It could be 0 though 
-				if not found_digit:
-					num = 1
-				# END set default num
-			# END number parsing only if non-blob mode
-			
-			
-			parsed_to = start
-			# handle hiererarchy walk
-			try:
-				if token == "~":
-					obj = to_commit(obj)
-					for item in xrange(num):
-						obj = obj.parents[0]
-					# END for each history item to walk
-				elif token == "^":
-					obj = to_commit(obj)
-					# must be n'th parent
-					if num:
-						obj = obj.parents[num-1]
-				elif token == ":":
-					if obj.type != "tree":
-						obj = obj.tree
-					# END get tree type
-					obj = obj[rev[start:]]
-					parsed_to = lr
-				else:
-					raise ValueError("Invalid token: %r" % token)
-				# END end handle tag
-			except (IndexError, AttributeError):
-				raise BadObject("Invalid Revision in %s" % rev)
-			# END exception handling
-		# END parse loop
-		
-		# still no obj ? Its probably a simple name
-		if obj is None:
-			obj = name_to_object(rev)
-			parsed_to = lr
-		# END handle simple name
-		
-		if obj is None:
-			raise ValueError("Revision specifier could not be parsed: %s" % rev)
-
-		if parsed_to != lr:
-			raise ValueError("Didn't consume complete rev spec %s, consumed part: %s" % (rev, rev[:parsed_to]))
-		
-		return obj
-
 	def __repr__(self):
 		return '<git.Repo "%s">' % self.git_dir
diff --git a/lib/git/repo/fun.py b/lib/git/repo/fun.py
new file mode 100644
index 00000000..ab2eb8be
--- /dev/null
+++ b/lib/git/repo/fun.py
@@ -0,0 +1,224 @@
+"""Package with general repository related functions"""
+
+from gitdb.exc import BadObject
+from git.refs import SymbolicReference
+from git.objects import Object
+from gitdb.util import (
+							join,
+							isdir, 
+							isfile,
+							hex_to_bin
+						)
+
+from string import digits
+
+__all__ = ('rev_parse', 'is_git_dir', 'touch')
+
+def touch(filename):
+	fp = open(filename, "a")
+	fp.close()
+
+def is_git_dir(d):
+	""" This is taken from the git setup.c:is_git_directory
+	function."""
+	if isdir(d) and \
+			isdir(join(d, 'objects')) and \
+			isdir(join(d, 'refs')):
+		headref = join(d, 'HEAD')
+		return isfile(headref) or \
+				(os.path.islink(headref) and
+				os.readlink(headref).startswith('refs'))
+	return False
+
+def name_to_object(repo, name):
+	""":return: object specified by the given name, hexshas ( short and long )
+		as well as references are supported"""
+	hexsha = None
+	
+	# is it a hexsha ? Try the most common ones, which is 7 to 40
+	if repo.re_hexsha_shortened.match(name):
+		if len(name) != 40:
+			# find long sha for short sha
+			raise NotImplementedError("short sha parsing")
+		else:
+			hexsha = name
+		# END handle short shas
+	else:
+		for base in ('%s', 'refs/%s', 'refs/tags/%s', 'refs/heads/%s', 'refs/remotes/%s', 'refs/remotes/%s/HEAD'):
+			try:
+				hexsha = SymbolicReference.dereference_recursive(repo, base % name)
+				break
+			except ValueError:
+				pass
+		# END for each base
+	# END handle hexsha
+	
+	# tried everything ? fail
+	if hexsha is None:
+		# it could also be a very short ( less than 7 ) hexsha, which 
+		# wasnt tested in the first run
+		if len(name) < 7 and repo.re_hexsha_domain.match(name):
+			raise NotImplementedError()
+		# END try short name 
+		raise BadObject(name)
+	# END assert hexsha was found
+	
+	return Object.new_from_sha(repo, hex_to_bin(hexsha))
+
+def deref_tag(tag):
+	"""Recursively dereerence a tag and return the resulting object"""
+	while True:
+		try:
+			tag = tag.object
+		except AttributeError:
+			break
+	# END dereference tag
+	return tag
+
+def to_commit(obj):
+	"""Convert the given object to a commit if possible and return it"""
+	if obj.type == 'tag':
+		obj = deref_tag(obj)
+		
+	if obj.type != "commit":
+		raise ValueError("Cannot convert object %r to type commit" % obj)
+	# END verify type
+	return obj
+
+def rev_parse(repo, rev):
+	"""
+	:return: Object at the given revision, either Commit, Tag, Tree or Blob
+	:param rev: git-rev-parse compatible revision specification, please see
+		http://www.kernel.org/pub/software/scm/git/docs/git-rev-parse.html
+		for details
+	:note: Currently there is no access to the rev-log, rev-specs may only contain
+		topological tokens such ~ and ^.
+	:raise BadObject: if the given revision could not be found"""
+	if '@' in rev:
+		raise ValueError("There is no rev-log support yet")
+	
+	
+	# colon search mode ?
+	if rev.startswith(':/'):
+		# colon search mode
+		raise NotImplementedError("commit by message search ( regex )")
+	# END handle search
+	
+	obj = None
+	output_type = "commit"
+	start = 0
+	parsed_to = 0
+	lr = len(rev)
+	while start < lr:
+		if rev[start] not in "^~:":
+			start += 1
+			continue
+		# END handle start
+		
+		if obj is None:
+			# token is a rev name
+			obj = name_to_object(repo, rev[:start])
+		# END initialize obj on first token
+		
+		token = rev[start]
+		start += 1
+		
+		# try to parse {type}
+		if start < lr and rev[start] == '{':
+			end = rev.find('}', start)
+			if end == -1:
+				raise ValueError("Missing closing brace to define type in %s" % rev)
+			output_type = rev[start+1:end]	# exclude brace
+			
+			# handle type 
+			if output_type == 'commit':
+				pass # default
+			elif output_type == 'tree':
+				try:
+					obj = to_commit(obj).tree
+				except (AttributeError, ValueError):
+					pass	# error raised later
+				# END exception handling
+			elif output_type in ('', 'blob'):
+				if obj.type == 'tag':
+					obj = deref_tag(obj)
+				else:
+					# cannot do anything for non-tags
+					pass
+				# END handle tag
+			else:
+				raise ValueError("Invalid output type: %s ( in %s )"  % (output_type, rev))
+			# END handle output type
+			
+			# empty output types don't require any specific type, its just about dereferencing tags
+			if output_type and obj.type != output_type:
+				raise ValueError("Could not accomodate requested object type %r, got %s" % (output_type, obj.type))
+			# END verify ouput type
+			
+			start = end+1					# skip brace
+			parsed_to = start
+			continue
+		# END parse type
+		
+		# try to parse a number
+		num = 0
+		if token != ":":
+			found_digit = False
+			while start < lr:
+				if rev[start] in digits:
+					num = num * 10 + int(rev[start])
+					start += 1
+					found_digit = True
+				else:
+					break
+				# END handle number
+			# END number parse loop
+			
+			# no explicit number given, 1 is the default
+			# It could be 0 though 
+			if not found_digit:
+				num = 1
+			# END set default num
+		# END number parsing only if non-blob mode
+		
+		
+		parsed_to = start
+		# handle hiererarchy walk
+		try:
+			if token == "~":
+				obj = to_commit(obj)
+				for item in xrange(num):
+					obj = obj.parents[0]
+				# END for each history item to walk
+			elif token == "^":
+				obj = to_commit(obj)
+				# must be n'th parent
+				if num:
+					obj = obj.parents[num-1]
+			elif token == ":":
+				if obj.type != "tree":
+					obj = obj.tree
+				# END get tree type
+				obj = obj[rev[start:]]
+				parsed_to = lr
+			else:
+				raise ValueError("Invalid token: %r" % token)
+			# END end handle tag
+		except (IndexError, AttributeError):
+			raise BadObject("Invalid Revision in %s" % rev)
+		# END exception handling
+	# END parse loop
+	
+	# still no obj ? Its probably a simple name
+	if obj is None:
+		obj = name_to_object(repo, rev)
+		parsed_to = lr
+	# END handle simple name
+	
+	if obj is None:
+		raise ValueError("Revision specifier could not be parsed: %s" % rev)
+
+	if parsed_to != lr:
+		raise ValueError("Didn't consume complete rev spec %s, consumed part: %s" % (rev, rev[:parsed_to]))
+	
+	return obj