#!/usr/bin/python

### THIS SCRIPT IS NOW DEAD TO ME.  I wrote it as a one-off to migrate my posts from bzero to wordpress.  It could easily be adapted to handle just about any content.  See the Post class's read() method as it is the only method that reads old content (in conjunction with the fullPath).

# scp extra/ to files/ under the weblog root

# configure the variables shown below

# run the script.  it will tell you what categories need to be created.   do so or remap as below.

RPCURL = 'http://www.friday.com/bbum/xmlrpc.php'
BASEURL = 'http://www.friday.com/bbum/'
FILEURL = '%s/files/' % BASEURL
USER = '<put your wordpress user name here -- most likely "admin">'
PASS = '<put your wordpress password here>'
BZEROCONTENT = '~/.bzero/bbum@mac.com'
BASEBADURL = 'http://www.pycs.net/bbum/'
ALTBADURL= 'http://bbum.pycs.net/'
rpcVerbose = 0

import os
import sys

BZEROCONTENTdata = os.path.expanduser(os.path.join(BZEROCONTENT, 'data'))
BZEROCONTENTextra = os.path.expanduser(os.path.join(BZEROCONTENT, 'extra'))

import xmlrpclib
import time

from pprint import pprint

server = xmlrpclib.ServerProxy(RPCURL, verbose=rpcVerbose)
baseContentDict = { 'mt_allow_comments' : 1, 'mt_allow_pings' : 1 }

categoryMap = {
    "Blogosphere" : "Weblogging",
    "Metalog" : "Weblogging",
    "CoreData" : "Core Data",
    "Creatures" : "Nature",
    "flickr" : "Flickr",
    "Hack" : "Hacks",
    "Design" : "Industrial Design",
    "Employment" : "Jobs",
    "OS X" : "Mac OS X",
    "Photo" : "Photography",
    "Photos" : "Photography",
    "Rant" : "Rants",
    "Weblogs" : "Weblogging",
    "Silliness" : "Humor",
    "life" : "Life",
    "reStructured Text" : None,
    "ReStructured Text" : None,
    "tcpflow" : None,
    "Address Book" : None,
    "Animation" : "Entertainment",
    "BitTorrent" : None,
    "CSS" : None,
    "Cayman" : None,
    "Coffee" : None,
    "DarwinPorts" : None,
    "Dashboard" : None,
    "Death" : "Life",
    "Desktop Software" : "Software",
    "Downloads" : "Software",
    "Electricity" : "Science",
    "Environment" : "Nature",
    "Facts of Life" : "Life",
    "Flickr" : None,
    "Cooking" : "Food",
    "Fun" : "Entertainment",
    "House" : None,
    "Intel" : None,
    "Java" : "Code",
    "Legos" : None,
    "Magnetism" : "Science",
    "Make" : "Hacks",
    "MarkDown" : None,
    "Microsoft Word" : None,
    "Network" : None,
    "Objective-C" : "Code",
    "P2P" : None,
    "PDF" : None,
    "Party" : "Entertainment",
    "Pathetic" : "Irritants",
    "Phone" : None,
    "Plants" : "Nature",
    "Politics" : "Government",
    "Privacy" : "Government",
    "Programming Languages" : "Code",
    "Python" : "Code",
    "Quartz Composer" : None,
    "RSS" : None,
    "Rants" : "Irritants",
    "ReSTedit" : "Software",
    "Screen Saver" : "Software",
    "Security" : None,
    "Starbucks" : None,
    "Storage" : None,
    "Stupidity" : "Irritants",
    "Subversion" : None,
    "Tides" : None,
    "Tiger" : "Mac OS X",
    "Unit Testing" : None,
    "Unix" : None,
    "Video Games" : "Entertainment",
    "WWDC" : None,
    "WebObjects" : None,
    "Wildlife" : "Nature",
    "World of Warcraft" : "Entertainment",
    "humor" : "Entertainment",
    "iMovie" : "Mac OS X",
    "iTunes" : "Mac OS X",
    "iTunes Music Store" : "Entertainment",
    "reStructuredText" : None
    }

def categoryFilter(aCategory):
    if not len(aCategory): return None
    if aCategory in categoryMap:
        return categoryMap[aCategory]
    else:
        return aCategory

class Post:
    categories = {}
    
    def __init__(self, fullPath):
        self.fullPath = fullPath
        self.ite = None
        self.topics = None
        self.title = None
        self.dateTuple = None
        self.body = ""
        self._read = False
        self.postResult = None
        self.rewritten = False

    def dump(self):
        print "### Post\n\t%s" % self.fullPath
        self.read()
        print "\tdate: %s" % (self.dateTuple,)
        print "\ttitle: %s" % (self.title)
        print "\tite: %s" % (self.ite)
        print "\ttopics: %s" % (self.topics)
        print "\tbody len: %d" % (len(self.body))

    def read(self):
        if self._read: return
        self._read = True
            
        f = file(self.fullPath, 'r')
        self.dateTuple = eval(f.readline()[5:])

        for l in f:
            if l[0] is not '%':
                break
            splitLine = l.split(' ', 1)
            head = splitLine[0][1:]
            if head in ['topics', 'ite']:
                data = splitLine[1].split(', ')
                data = ",".join(data)
                data = data.split(',')
                data = [categoryFilter(x.strip()) for x in data]
                data = filter(lambda x: x, data)
                setattr(self, head, data)
            else:
                setattr(self, head, splitLine[1].strip())

        self.body = ''.join([l for l in f])
        f.close()

        if self.topics:
            for aTopic in self.topics:
                Post.categories[aTopic] = 1

    def pubTitle(self):
        if not self.title:
            return '<<no title>>'
        else:
            return self.title

    def pubDate(self):
        if not self.dateTuple:
            self.dateTuple = time.localtime()
        return xmlrpclib.DateTime(self.dateTuple)
        
    def publish(self):
        self.read()
        contentDict = {}
        contentDict.update(baseContentDict)
        contentDict['title'] = self.pubTitle()
        contentDict['description'] = self.body
        contentDict['dateCreated'] = self.pubDate()

        print 'Posting: %s' % self.pubTitle()
        self.postResult = server.metaWeblog.newPost(0, USER, PASS, contentDict, 1)

        if self.topics:
            global serverCategories
            categories = []
            for aTopic in self.topics:
                newCat = serverCategories[aTopic]
                if newCat not in categories:
                    categories.append({'categoryId' : newCat})
            categories.sort()
            r = server.mt.setPostCategories(self.postResult, USER, PASS, categories)
            if not r:
                print "*** FAILED TO SET CATEGORIES *** {%s} %s" % (self.title, self.fullPath)

    def checkSanityWithURL(self, badURL):
        self.read()
        currentIndex = 0
        spewOpener = True
        while 1:
            problem = self.body.find(badURL, currentIndex)
            if problem == -1: break
            endProblem = self.body.find('"', problem)
            URL = self.body[problem:endProblem]
            path = URL[len(badURL):]
            path = path.replace("@20", " ")
            fullExtraPath = os.path.join(BZEROCONTENTextra, path)
            if os.path.isfile(fullExtraPath):
                bodyLen = len(self.body)
                path = path.replace(" ", "%20")
                self.body = self.body[:problem] + FILEURL + path + self.body[endProblem:]
                currentIndex = endProblem + (len(self.body) - bodyLen)
                self.rewritten = True
            else:
                if (endProblem - problem) > 50:
                    currentIndex = endProblem
                    print "BAD:\n%s" % self.fullPath
                    print ">>>>%s<<<<" % self.body[problem:endProblem]
                    continue
                bodyLen = len(self.body)
                self.body = self.body[:problem] + BASEURL + path.split('#')[0] + self.body[endProblem:]
                currentIndex = endProblem + (len(self.body) - bodyLen)
                self.rewritten = True

    def checkSanity(self):
        self.checkSanityWithURL(BASEBADURL)
        self.checkSanityWithURL(ALTBADURL)

def verifyCategories(categories):
    categories.sort()
    rawCategories = server.mt.getCategoryList(0, USER, PASS)
    serverCategories = {}
    for aCat in rawCategories:
        name = aCat['categoryName']
        id = aCat['categoryId']
        serverCategories[name] = id

    categoriesToCreate = []
    for aCat in categories:
        if not aCat in serverCategories:
            categoriesToCreate.append(aCat)

    if len(categoriesToCreate):
        print "Unfortunately, no API exists to create categories."
        print "The following categories will need to be created on the server:"
        for aCat in categoriesToCreate: print aCat
        sys.exit(0)

    return serverCategories

posts = [] 
def dataWalk(arg, dir, files):
    for f in files:
        if f[0] is '#':
            continue
        fullPath = os.path.join(dir, f)
        if os.path.isfile(fullPath) and fullPath[-1:] is not '~':
            posts.append(Post(fullPath))

os.path.walk(BZEROCONTENTdata, dataWalk, None)

for p in posts:
    p.checkSanity()

serverCategories = verifyCategories(Post.categories.keys())
pprint(serverCategories)

for p in posts:
    p.publish()