/stdhome

# walker.py

#

# Copyright (C) 2013 to 2014 Tim Marston <tim@edm.am>

#

# This file is part of stdhome (hereafter referred to as "this program").

# See http://ed.am/dev/stdhome for more information.

#

# This program is free software: you can redistribute it and/or modify

# it under the terms of the GNU General Public License as published by

# the Free Software Foundation, either version 3 of the License, or

# (at your option) any later version.

#

# This program is distributed in the hope that it will be useful,

# but WITHOUT ANY WARRANTY; without even the implied warranty of

# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

# GNU General Public License for more details.

#

# You should have received a copy of the GNU General Public License

# along with this program.  If not, see <http://www.gnu.org/licenses/>.

import os

class Walker:

	"""Classes which derive from the Walker class are intended to walk through

	(traverse) a single list of filenames in two locations.  They must provide

	the two locations (src_dir and dst_dir) and a list of relative filenames

	(walk_list).  For each files in the walk list, the process() method is

	called, allowing the deriving class to perform some kind of processing.  See

	process() for more information.

	"""

	def walk( self ):

		"""Iterates over self.walk_list, calling process() for each entry in turn.  For

		directory entries, where process() returns False, subsequent entries in

		walk_list that fall under the directory are skipped.

		"""

		skip = ''

		for rel_file in self.walk_list:

			# if we're skipping, skip entries in subdirectories, or turn off

			# skipping if it no longer matches

			if skip:

				if skip == rel_file[ : len( skip ) ]:

					continue

				else:

					skip = ''

			src = Walker.File( os.path.join( self.src_dir, rel_file ) )

			dst = Walker.File( os.path.join( self.dst_dir, rel_file ) )

			# process ths entry

			recurse = self.process( rel_file, src, dst )

			# Set up skipping, as required.  Note that we don't check to see if

			# we're dealing with a directory here.  We can't, because we've no

			# way of knowing what to check.  It could be src_type or dst_type

			# (if src_dir or dst_dir was used to generate the walk list) or it

			# could be neither (if the walk list came from somewhere else).  But

			# it shouldn't matter.  We adding an os.pathset to the end of the

			# filename, so it wuill only match files that are descendents of a

			# directory with the name of this file.

			if not recurse: skip = rel_file + os.sep

	class File:

		def __init__( self, full_file ):

			self.file = full_file

			if not os.path.exists( self.file ):

				self.type = '_'

			elif os.path.isfile( self.file ):

				self.type = 'f'

			elif os.path.isdir( self.file ):

				self.type = 'd'

			else:

				self.type = '?'

			if os.path.islink( self.file ):

				self.link_type = self.type

				self.type = 'l'

			else:

				self.link_type = False

		def get_type_name( self ):

			if self.type == 'l': return 'symlink'

			elif self.type == 'f': return 'file'

			elif self.type == 'd': return 'directory'

			elif self.type == '_': return 'missing'

			else: return 'unknown'

		def __str__( self ):

			type = self.type

			if( self.link_type ): type += '/' + self.link_type

			return 'File( %s (%s) )' % ( self.file, type )

	@staticmethod

	def generate_walk_list( full_dir, rel_file = '' ):

		"""Returns a list of files and directories in full_dir, specified as relative

		files (relative to full_dir), breadth first.

		"""

		# ignore some files

		if rel_file in { '.bzr', '.bzrignore', '.stdhome', '.stdhomerc' }:

			return list()

		full_file = os.path.join( full_dir, rel_file )

		# files and links are returned

		if os.path.isfile( full_file ) or os.path.islink( full_file ):

			return [ rel_file ]

		# directories are returned and recursed in to

		elif os.path.isdir( full_file ):

			ret = [ rel_file ] if rel_file != '' else []

			for file in os.listdir( full_file ):

				ret.extend( Walker.generate_walk_list(

					full_dir, os.path.join( rel_file, file ) ) )

			return sorted( ret )

		# other kinds are invalid

		else:

			raise RuntimeError(

				'unknown/exotic file: %s' % full_file )