#!/usr/bin/env python
"""
A Python module which can parse ChangeLog formatetd document.
"""

# -*- coding: utf-8 -*-
import re

__author__ = 'mattn <mattn.jp@gmail.com>'
__url__ = 'http://mattn.kaoriya.net/'
__date__ = 'Tue, 24 Jun 2008'
__version__ = '0.1'

class Item:
  """
  ChangeLog item object. you can access attributes as title, content, tags.
  """
  def __init__(self, title, description="", content="", tags=None):
    """
    initialize item object. maybe, you wont this method.
    """
    self.title = title and title.strip() or ""
    self.content = content and content.strip() or ""
    self.tags = []
    if tags:
      if not isinstance(tags, list): tags = [tags]
      for tag in tags:
        self.tags.append(tag[1:-1])

class Entry:
  """
  ChangeLog entry object. you can access attributes as date, author, items.
  """
  def __init__(self, date, author):
    """
    initialize item object. maybe, you wont this method.
    """
    self.date = date or date.strip() or ""
    self.author = author or author.strip() or ""
    self.items = []

def parse(filename, encoding="utf-8"):
  """
  parse ChangeLog formated docment.
  """
  re_head = re.compile('^(\d{4}-\d{2}-\d{2}(?: \(.{3}\))?)\s*(.*)$')
  re_item = re.compile('^\t\*(.*?)(\[.*\])?:(.*)$')
  entries = []
  entry = None
  item = None
  for line in open(filename):
    line = line.decode("utf-8")
    rm = re_head.match(line)
    if rm:
      if entry:
        entry.items.append(item)
        entries.append(entry)
      entry = Entry(date = rm.group(1), author = rm.group(2))
      item = None
    elif entry:
      rm = re_item.match(line)
      if rm:
        if entry and item: entry.items.append(item)
        item = Item(title=rm.group(1), tags=rm.group(2), description=rm.group(3))
      else:
        if item:
          item.content += line[1:]
  if entry:
    entry.items.append(item)
    entries.append(entry)
  return entries

if __name__ == '__main__':
  entries = parse("ChangeLog")
  for entry in entries:
    print "date: %s" % entry.date
    print "author: %s" % entry.author
    for item in entry.items:
      print "  title: %s" % item.title
      print "  tags: %s" % ",".join(item.tags)
      print "  content: %3s..." % item.content.split()[0]