X-Git-Url: https://wagner.pp.ru/gitweb/?a=blobdiff_plain;ds=sidebyside;f=convertdump.py;h=f098a58f2a2e0b29fd0fbaca86ceb3a5a7e75509;hb=f780b9810d06ddd539df4e91b3a4a8a8a2a0784c;hp=106b274d796e8d918882249d95f4b2ea2de18686;hpb=2d9c66385fe5cc6c928ffdd1b8e21c006b3db546;p=oss%2Fljdump.git diff --git a/convertdump.py b/convertdump.py index 106b274..f098a58 100755 --- a/convertdump.py +++ b/convertdump.py @@ -1,9 +1,35 @@ #!/usr/bin/python +# Copyright 2009, Sean M. Graham (www.sean-graham.com) +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions are +# met: +# +# - Redistributions of source code must retain the above copyright notice, +# this list of conditions and the following disclaimer. +# +# - Redistributions in binary form must reproduce the above copyright notice, +# this list of conditions and the following disclaimer in the documentation +# and/or other materials provided with the distribution. +# +# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED +# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO +# EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, +# INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, +# OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, +# EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + import xml.dom.minidom import os import codecs import sys +import getopt from time import strptime, strftime @@ -40,13 +66,12 @@ def appendTextNode(doc, parent, nodename, value): parent.appendChild(element) -def addEntryForId(outDoc, element, username, id): +def addEntryForId(outDoc, element, username, id, includeSecure): entryFile = open("%s/L-%s" % (username,id), "r") inDoc = xml.dom.minidom.parse(entryFile) # Create an entry element entry = outDoc.createElement("entry") - element.appendChild(entry) # Create an itemid element appendTextNode(outDoc, entry, "itemid", getNodeText(inDoc,"itemid")) @@ -62,15 +87,28 @@ def addEntryForId(outDoc, element, username, id): event = inDoc.getElementsByTagName("event")[0] appendTextNode(outDoc, entry, "event", getNodeText(event, "event")) - # Create an allowmask element (doesn't exist in pydump output if public) - maskText = getNodeText(inDoc, "allowmask") + security = getNodeText(inDoc, "security") + + if(security != ""): + # don't append this entry unless the user provided the argument + if(includeSecure == False): + print("omitting secure entry: L-%s" % id) + return + else: + if(security == "usemask"): + print("including allowmask entry: L-%s" % id) + + # Create an allowmask element + maskText = getNodeText(inDoc, "allowmask") - # XXXSMG: consult L-1411 and L-976 for examples of security and - # allowmask use - if(maskText != ""): - appendTextNode(outDoc, entry, "allowmask", maskText) - else: - appendTextNode(outDoc, entry, "allowmask", "0") + if(maskText != ""): + appendTextNode(outDoc, entry, "allowmask", maskText) + else: + appendTextNode(outDoc, entry, "allowmask", "0") + else: + print("including private entry: L-%s" % id) + + appendTextNode(outDoc, entry, "security", security) # Create a taglist element appendTextNode(outDoc, entry, "taglist", getNodeText(inDoc, "taglist")) @@ -79,6 +117,8 @@ def addEntryForId(outDoc, element, username, id): # with it addCommentsForId(outDoc, entry, username, id) + element.appendChild(entry) + def addCommentsForId(outDoc, entry, username, id): try: commentFile = open("%s/C-%s" % (username,id), "r") @@ -132,17 +172,59 @@ def addCommentsForId(outDoc, entry, username, id): if(parentId != ""): appendTextNode(outDoc, outComment, "parent_itemid", parentId) +def usage(): + print( "Usage: convertdump.py [arguments]" ) + print( """ +This will convert a pydump archive into something compatible with the +WordPress LiveJournal importer. This is the same format used by the Windows +ljArchive exporter. + +Arguments: + -u --user username of archive to process [required] + -l --limit limit the number of entries in each xml file (default 250) + -i --insecure include private and protected entries in the output + -h --help show this help page + +Example: + ./convertdump.py --user stevemartin --limit 200 --insecure +""") + + def main(argv): username = "" entryLimit = 250 - + includeSecure = False; - if( len(argv) != 2 ): - print( "Usage: convertdump.py " ) - return - else: - username = argv[0] - entryLimit = int(argv[1]) + if( len(argv) == 0 ): + usage() + sys.exit(2) + + try: + opts, args = getopt.getopt(sys.argv[1:], "hu:l:i", ["help", + "user=", + "limit=", + "insecure"]) + except getopt.GetoptError, err: + # print help information and exit: + print str(err) # will print something like "option -a not recognized" + usage() + sys.exit(2) + + for o, a in opts: + if o == "-v": + verbose = True + elif o in ("-u", "--user"): + username = a + elif o in ("-l", "--limit"): + entryLimit = int(a) + elif o in ("-i", "--insecure"): + print( "Warning: Including secure entries in XML output" ) + includeSecure = True + elif o in ("-h", "--help"): + usage() + sys.exit() + else: + assert False, "unhandled option" userDir = os.listdir(username) @@ -161,7 +243,6 @@ def main(argv): entryArray.sort() - # Create the minidom document outDoc = xml.dom.minidom.Document() @@ -169,16 +250,15 @@ def main(argv): ljElement = outDoc.createElement("livejournal") outDoc.appendChild(ljElement) - entryLimit = 250 currentFileEntry = 0 # start processing entries for entry in entryArray: - addEntryForId(outDoc, ljElement, username, entry) + addEntryForId(outDoc, ljElement, username, entry, includeSecure) currentFileEntry += 1 - if( currentFileEntry == entryLimit ): + if( currentFileEntry == entryLimit or entry == entryArray[-1] ): f = open("%s - %s.xml" % (username, entry), "w") tempXML = outDoc.toxml("UTF-8")