Add ability to requote a repository

git-svn-id: http://svn.savannah.nongnu.org/svn/rdiff-backup@863 2b77aa54-bcbc-44c9-a7ec-4f6cf2b41109

trunk/rdiff-backup/CHANGELOG

 New in v1.1.15 (????/??/??)
 ---------------------------
 
+New feature: If quoting requirements change, rdiff-backup can requote the
+entire repository if user specifies the --force option. (Andrew Ferguson)
+
 Don't print the warning message about unsupported hard links if the user
 has specified the --no-hard-links option. (Suggested by Andreas Olsson)
 

trunk/rdiff-backup/rdiff_backup/FilenameMapping.py

@@ -29,7 +29,8 @@ handle that error.)
 
 """
 
-import re, types
+from __future__ import generators
+import os, re, types
 import Globals, log, rpath
 
 # If true, enable character quoting, and set characters making
@@ -71,7 +72,7 @@ def init_quoting_regexps():
 				 re.compile("[%s]|%s" % (chars_to_quote, quoting_char), re.S)
 		unquoting_regexp = re.compile("%s[0-9]{3}" % quoting_char, re.S)
 	except re.error:
-		log.Log.FatalError("Error '%s' when processing char quote list '%s'" %
+		log.Log.FatalError("Error '%s' when processing char quote list %r" %
 						   (re.error, chars_to_quote))
 
 def quote(path):
@@ -171,3 +172,84 @@ def get_quotedrpath(rp, separate_basename = 0):
 def get_quoted_sep_base(filename):
 	"""Get QuotedRPath from filename assuming last bit is quoted"""
 	return get_quotedrpath(rpath.RPath(Globals.local_connection, filename), 1)
+
+def update_quoting(rbdir):
+	"""Update the quoting of a repository by renaming any
+	files that should be quoted differently.
+	"""
+
+	def requote(name):
+		unquoted_name = unquote(name)
+		quoted_name = quote(unquoted_name)
+		if name != quoted_name:
+			return quoted_name
+		else:
+			return None
+	
+	def process(dirpath_rp, name, list):
+		new_name = requote(name)
+		if new_name:
+			if list:
+				list.remove(name)
+				list.append(new_name)
+			name_rp = dirpath_rp.append(name)
+			new_rp = dirpath_rp.append(new_name)
+			log.Log("Re-quoting %s to %s" % (name_rp.path, new_rp.path), 5)
+			rpath.move(name_rp, new_rp)
+
+	assert rbdir.conn is Globals.local_connection
+	mirror_rp = rbdir.get_parent_rp()
+	mirror = mirror_rp.path
+
+	log.Log("Re-quoting repository %s" % mirror_rp.path, 3)
+
+	try:
+		os_walk = os.walk
+	except AttributeError:
+		os_walk = walk
+
+	for dirpath, dirs, files in os_walk(mirror):
+		dirpath_rp = mirror_rp.newpath(dirpath)
+
+		for name in dirs: process(dirpath_rp, name, dirs)
+		for name in files: process(dirpath_rp, name, None)
+
+"""
+os.walk() copied directly from Python 2.5.1's os.py
+
+Backported here for Python 2.2 support. os.walk() was first added
+in Python 2.3.
+"""
+def walk(top, topdown=True, onerror=None):
+	from os import error, listdir
+	from os.path import join, isdir, islink
+	# We may not have read permission for top, in which case we can't
+	# get a list of the files the directory contains.  os.path.walk
+	# always suppressed the exception then, rather than blow up for a
+	# minor reason when (say) a thousand readable directories are still
+	# left to visit.  That logic is copied here.
+	try:
+		# Note that listdir and error are globals in this module due
+		# to earlier import-*.
+		names = listdir(top)
+	except error, err:
+		if onerror is not None:
+			onerror(err)
+		return
+
+	dirs, nondirs = [], []
+	for name in names:
+		if isdir(join(top, name)):
+			dirs.append(name)
+		else:
+			nondirs.append(name)
+
+	if topdown:
+		yield top, dirs, nondirs
+	for name in dirs:
+		path = join(top, name)
+		if not islink(path):
+			for x in walk(path, topdown, onerror):
+				yield x
+	if not topdown:
+		yield top, dirs, nondirs

trunk/rdiff-backup/rdiff_backup/Main.py

@@ -329,7 +329,7 @@ def Backup(rpin, rpout):
 	SetConnections.BackupInitConnections(rpin.conn, rpout.conn)
 	backup_check_dirs(rpin, rpout)
 	backup_set_rbdir(rpin, rpout)
-	rpout.conn.fs_abilities.backup_set_globals(rpin)
+	rpout.conn.fs_abilities.backup_set_globals(rpin, force)
 	if Globals.chars_to_quote: rpout = backup_quoted_rpaths(rpout)
 	init_user_group_mapping(rpout.conn)
 	backup_final_init(rpout)

trunk/rdiff-backup/rdiff_backup/fs_abilities.py

@@ -577,7 +577,7 @@ class BackupSetGlobals(SetGlobals):
 		log.Log("Backup: must_escape_dos_devices = %d" % \
 				(self.src_fsa.escape_dos_devices or local_edd), 4)
 
-	def set_chars_to_quote(self, rbdir):
+	def set_chars_to_quote(self, rbdir, force):
 		"""Set chars_to_quote setting for backup session
 
 		Unlike the other options, the chars_to_quote setting also
@@ -585,10 +585,12 @@ class BackupSetGlobals(SetGlobals):
 		directory, not just the current fs features.
 
 		"""
-		ctq = self.compare_ctq_file(rbdir, self.get_ctq_from_fsas())
+		(ctq, update) = self.compare_ctq_file(rbdir,
+				self.get_ctq_from_fsas(), force)
 
 		SetConnections.UpdateGlobal('chars_to_quote', ctq)
 		if Globals.chars_to_quote: FilenameMapping.set_init_quote_vals()
+		return update
 
 	def get_ctq_from_fsas(self):
 		"""Determine chars_to_quote just from filesystems, no ctq file"""
@@ -608,24 +610,32 @@ class BackupSetGlobals(SetGlobals):
 		if ctq: ctq.append(';') # Quote quoting char if quoting anything
 		return "".join(ctq)
 
-	def compare_ctq_file(self, rbdir, suggested_ctq):
+	def compare_ctq_file(self, rbdir, suggested_ctq, force):
 		"""Compare ctq file with suggested result, return actual ctq"""
 		ctq_rp = rbdir.append("chars_to_quote")
 		if not ctq_rp.lstat():
 			if Globals.chars_to_quote is None: actual_ctq = suggested_ctq
 			else: actual_ctq = Globals.chars_to_quote
 			ctq_rp.write_string(actual_ctq)
-			return actual_ctq
+			return (actual_ctq, None)
 
 		if Globals.chars_to_quote is None: actual_ctq = ctq_rp.get_data()
 		else: actual_ctq = Globals.chars_to_quote # Globals override
 
-		if actual_ctq == suggested_ctq: return actual_ctq
+		if actual_ctq == suggested_ctq: return (actual_ctq, None)
 		if suggested_ctq == "":
 			log.Log("Warning: File system no longer needs quoting, "
 					"but we will retain for backwards compatibility.", 2)
-			return actual_ctq
+			return (actual_ctq, None)
 		if Globals.chars_to_quote is None:
+			if force:
+				log.Log("Warning: migrating rdiff-backup repository from"
+						"old quoting chars %r to new quoting chars %r" %
+						(actual_ctq, suggested_ctq), 2)
+				ctq_rp.delete()
+				ctq_rp.write_string(suggested_ctq)
+				return  (suggested_ctq, 1)
+			else:
 				log.Log.FatalError("""New quoting requirements!
 
 The quoting chars this session needs %r do not match
@@ -637,7 +647,11 @@ This may be caused when you copy an rdiff-backup repository from a
 normal file system onto a windows one that cannot support the same
 characters, or if you backup a case-sensitive file system onto a
 case-insensitive one that previously only had case-insensitive ones
-backed up onto it.""" % (suggested_ctq, actual_ctq, ctq_rp.path))
+backed up onto it.
+
+By specificying the --force option, rdiff-backup will migrate the
+repository from the old quoting chars to the new ones.""" %
+			(suggested_ctq, actual_ctq, ctq_rp.path))
 
 
 class RestoreSetGlobals(SetGlobals):
@@ -719,7 +733,7 @@ class SingleSetGlobals(RestoreSetGlobals):
 			 ('carbonfile_active', 'carbonfile_write', 'carbonfile_conn'))
 
 
-def backup_set_globals(rpin):
+def backup_set_globals(rpin, force):
 	"""Given rps for source filesystem and repository, set fsa globals
 
 	This should be run on the destination connection, because we may
@@ -742,10 +756,14 @@ def backup_set_globals(rpin):
 	bsg.set_change_ownership()
 	bsg.set_high_perms()
 	bsg.set_symlink_perms()
-	bsg.set_chars_to_quote(Globals.rbdir)
+	update_quoting = bsg.set_chars_to_quote(Globals.rbdir, force)
 	bsg.set_escape_dos_devices()
 	bsg.set_must_escape_dos_devices(Globals.rbdir)
 
+	if update_quoting and force:
+		FilenameMapping.update_quoting(Globals.rbdir)
+
+
 def restore_set_globals(rpout):
 	"""Set fsa related globals for restore session, given in/out rps"""
 	assert rpout.conn is Globals.local_connection