Submodule: Added dry_run and progress parameter to the update method. It is copatible to the RemoteProgress and should satisfy all progress needs. Dryrun will be useful in conjunction with the progress to verify the changes to be done

1 files changed, 122 insertions, 1 deletions

diff --git a/util.py b/util.py
index 42719233..8c0b6697 100644
--- a/util.py
+++ b/util.py
@@ -22,7 +22,8 @@ from gitdb.util import (
 
 __all__ = ( "stream_copy", "join_path", "to_native_path_windows", "to_native_path_linux", 
 			"join_path_native", "Stats", "IndexFileSHA1Writer", "Iterable", "IterableList", 
-			"BlockingLockFile", "LockFile", 'Actor', 'get_user_id', 'assure_directory_exists')
+			"BlockingLockFile", "LockFile", 'Actor', 'get_user_id', 'assure_directory_exists',
+			'RemoteProgress')
 
 #{ Utility Methods
 
@@ -77,6 +78,7 @@ def join_path_native(a, *p):
 	
 def assure_directory_exists(path, is_file=False):
 	"""Assure that the directory pointed to by path exists.
+	
 	:param is_file: If True, path is assumed to be a file and handled correctly.
 		Otherwise it must be a directory
 	:return: True if the directory was created, False if it already existed"""
@@ -103,6 +105,125 @@ def get_user_id():
 
 #{ Classes
 
+class RemoteProgress(object):
+	"""
+	Handler providing an interface to parse progress information emitted by git-push
+	and git-fetch and to dispatch callbacks allowing subclasses to react to the progress.
+	"""
+	_num_op_codes = 5
+	BEGIN, END, COUNTING, COMPRESSING, WRITING =  [1 << x for x in range(_num_op_codes)]
+	STAGE_MASK = BEGIN|END
+	OP_MASK = ~STAGE_MASK
+	
+	__slots__ = ("_cur_line", "_seen_ops")
+	re_op_absolute = re.compile("(remote: )?([\w\s]+):\s+()(\d+)()(.*)")
+	re_op_relative = re.compile("(remote: )?([\w\s]+):\s+(\d+)% \((\d+)/(\d+)\)(.*)")
+	
+	def __init__(self):
+		self._seen_ops = list()
+	
+	def _parse_progress_line(self, line):
+		"""Parse progress information from the given line as retrieved by git-push
+		or git-fetch
+		
+		:return: list(line, ...) list of lines that could not be processed"""
+		# handle
+		# Counting objects: 4, done. 
+		# Compressing objects:	50% (1/2)	\rCompressing objects: 100% (2/2)	\rCompressing objects: 100% (2/2), done.
+		self._cur_line = line
+		sub_lines = line.split('\r')
+		failed_lines = list()
+		for sline in sub_lines:
+			# find esacpe characters and cut them away - regex will not work with 
+			# them as they are non-ascii. As git might expect a tty, it will send them
+			last_valid_index = None
+			for i,c in enumerate(reversed(sline)):
+				if ord(c) < 32:
+					# its a slice index
+					last_valid_index = -i-1 
+				# END character was non-ascii
+			# END for each character in sline
+			if last_valid_index is not None:
+				sline = sline[:last_valid_index]
+			# END cut away invalid part
+			sline = sline.rstrip()
+			
+			cur_count, max_count = None, None
+			match = self.re_op_relative.match(sline)
+			if match is None:
+				match = self.re_op_absolute.match(sline)
+				
+			if not match:
+				self.line_dropped(sline)
+				failed_lines.append(sline)
+				continue
+			# END could not get match
+			
+			op_code = 0
+			remote, op_name, percent, cur_count, max_count, message = match.groups()
+			
+			# get operation id
+			if op_name == "Counting objects":
+				op_code |= self.COUNTING
+			elif op_name == "Compressing objects":
+				op_code |= self.COMPRESSING
+			elif op_name == "Writing objects":
+				op_code |= self.WRITING
+			else:
+				raise ValueError("Operation name %r unknown" % op_name)
+			
+			# figure out stage
+			if op_code not in self._seen_ops:
+				self._seen_ops.append(op_code)
+				op_code |= self.BEGIN
+			# END begin opcode
+			
+			if message is None:
+				message = ''
+			# END message handling
+			
+			message = message.strip()
+			done_token = ', done.'
+			if message.endswith(done_token):
+				op_code |= self.END
+				message = message[:-len(done_token)]
+			# END end message handling
+			
+			self.update(op_code, cur_count, max_count, message)
+		# END for each sub line
+		return failed_lines
+	
+	def line_dropped(self, line):
+		"""Called whenever a line could not be understood and was therefore dropped."""
+		pass
+	
+	def update(self, op_code, cur_count, max_count=None, message=''):
+		"""Called whenever the progress changes
+		
+		:param op_code:
+			Integer allowing to be compared against Operation IDs and stage IDs.
+			
+			Stage IDs are BEGIN and END. BEGIN will only be set once for each Operation 
+			ID as well as END. It may be that BEGIN and END are set at once in case only
+			one progress message was emitted due to the speed of the operation.
+			Between BEGIN and END, none of these flags will be set
+			
+			Operation IDs are all held within the OP_MASK. Only one Operation ID will 
+			be active per call.
+		:param cur_count: Current absolute count of items
+			
+		:param max_count:
+			The maximum count of items we expect. It may be None in case there is 
+			no maximum number of items or if it is (yet) unknown.
+		
+		:param message:
+			In case of the 'WRITING' operation, it contains the amount of bytes
+			transferred. It may possibly be used for other purposes as well.
+		
+		You may read the contents of the current line in self._cur_line"""
+		pass
+
+
 class Actor(object):
 	"""Actors hold information about a person acting on the repository. They 
 	can be committers and authors or anything with a name and an email as