from xml.etree.ElementTree import fromstring, tostring
import mcoll
from config import config
import os
import glob
import sys
import traceback

dir = config.get('dir', 'entry')
c = mcoll.Collection(dir)

SRC = "/home/jcgregorio/web/bitworking.org/data/"
#for filename in [os.path.join(SRC, name) for name in os.listdir(SRC) if not name.count("-")]:
#    f = file(filename, "r")
#    e = fromstring(f.read())
#    f.close()
#
#    d = {}
#    summary = e.find(u"{http://www.purl.org/RESTLog/}excerpt")
#    if summary != None:
#        d['summary'] = summary.text
#    desc = e.find("description")
#    d['content'] = desc.text
#    published = e.find("{http://purl.org/dc/elements/1.1/}date")
#    d['published'] = d['updated'] = published.text.rsplit("-", 1)[0]
#    title = e.find("title")
#    d['title'] = title.text
#    d['slug'] = u''
#    id = os.path.basename(filename)
#
#    c._put(id, d)
#    member = c.get(id)
#    content = member['content'].encode("utf-8")
#    summary = member['summary'].encode("utf-8")
#    s = "<?xml version='1.0' encoding='UTF-8'?> <div xmlns='http://www.w3.org/1999/xhtml'><div class='summary'>%s</div>%s</div>" % (summary, content)
#    try:
#        print id
#        fromstring(s)
#    except Exception, e:
#        print s
#        print e
#        sys.exit(1)
#
comments_dir = config.get('dir', 'comments')
for filename in [os.path.join(SRC, name) for name in os.listdir(SRC) if name.count("-")]:
    f = file(filename, "r")
    e = fromstring(f.read())
    f.close()
    (entry_id, comment_id) = os.path.basename(filename).rsplit('-', 1)


    c = mcoll.Collection(os.path.join(comments_dir, entry_id))

    d = {}
    author = e.find(u"{http://purl.org/dc/elements/1.1/}creator")
    if author != None:
        d['author'] = author.text
    summary = e.find(u"{http://www.purl.org/RESTLog/}excerpt")
    if summary != None:
        d['summary'] = summary.text
    desc = e.find("description")
    d['content'] = desc.text
    published = e.find("{http://purl.org/dc/elements/1.1/}date")
    d['published'] = d['updated'] = published.text.rsplit("-", 1)[0]
    title = e.find("title")
    d['title'] = title.text
    d['slug'] = u''

    c._put(comment_id, d)
    member = c.get(comment_id)
    content = member['content'].encode("utf-8")
    summary = member['summary'].encode("utf-8")
    s = "<?xml version='1.0' encoding='UTF-8'?> <div xmlns='http://www.w3.org/1999/xhtml'><div class='summary'>%s</div>%s</div>" % (summary, content)
    try:
        print entry_id, comment_id
        fromstring(s)
    except Exception, e:
        print s
        print e
        sys.exit(1)

    c.reindex()