#/usr/bin/python

from config import directory
import os, re, time

splitExcerpt=re.compile('(?:<div class="excerpt"(?: updated="([^"]*?)")?/?>(?:(.*?)</div>)?\s*)?(.*)',re.S)

class post:
  def __init__(self, entry, flavor="html"):
    self._entry = entry
    self._modified = None
    self._title = None
    self._flavor = flavor
    self._updated = None
    self._excerpt = None
    self._body = None

    if entry and entry.find('/')>=0 and not entry.isdigit(): 
      self._entry = self.find(entry)
    if entry.split('/')[-1].find('.')>=0:
      (self._entry,self._flavor)=entry.split('/')[-1].split('.',1)

  def find(self,entry):
    try:
      start=map(int,filter(lambda x:x.isdigit(), entry.split('/'))[0:3])
      finish=start[:]
      finish[len(start)-1] += 1
      start=time.mktime((start+[0]*9)[0:9])-3600
      finish=time.mktime((finish+[0]*9)[0:9])
      slug=entry.split('/')[-1].lower()
      for name in os.listdir(directory.data):
        if name.endswith(".txt"): 
          mtime=os.stat(directory.data+name).st_mtime
          if mtime>=start and mtime<finish:
            if post(name.split('.')[0]).slug().lower() == slug:
              return name.split('.')[0]
    except:
      pass

  def parse(self):
    if not self._entry: return
    file=open(self.filepath())
    self._title = file.readline().strip()
    (self._updated,self._excerpt,self._body)=\
      splitExcerpt.match(file.read()).groups()
    file.close()

  def body(self):
    if not self._entry: return
    if not self._body: self.parse()
    return self._body

  def id(self):
    return self._entry

  def filepath(self):
    if not self._entry: return
    if self._entry.find('-')>=0 and self._entry.split('-')[-1].isdigit():
      return directory.data + self._entry + ".cmt"
    return directory.data + self._entry + ".txt"

  def modified(self):
    if self._entry and not self._modified:
      self._modified = os.stat(self.filepath()).st_mtime
    return self._modified

  def slug(self):
    if not self._entry: return
    if not self.title() or not self._entry.isdigit():
      return self._entry.replace("_","-")
    title=re.sub('\&#?\w+;','',self._title.replace("'",""))
    title=re.sub('<.*?>','',title)
    alnum = lambda c: c.isalnum() and c or ' '
    return '-'.join(''.join([alnum(c) for c in title]).split())

  def title(self):
    if self._entry and not self._title:
      self._title=open(self.filepath()).readline().strip()
    return self._title

  def link(self):
    if not self._entry: return
    if not self._title: self.title()
    if self._flavor<>'html' or not self._title:
      return self._entry + "." + self._flavor
    path=time.strftime("%Y/%m/%d/",time.localtime(self.modified()))
    return path+self.slug()

if __name__ == '__main__':
  # assert post('2003/09/04/Nonce.rss').link() == '1585.rss'
  assert post('flamebait.html').slug() == 'flamebait'
  assert post('flamebait').slug() == 'flamebait'
  assert post('1585.html').slug() == 'Nonce'
  assert post('2003/09/04/Nonce').id() == '1585'
  assert post('2003/09/Nonce').id() == '1585'
  assert post('2003/Nonce').id() == '1585'
  assert post('2436.html').link() == '2006/11/10/Thats-Not-Write'

  import sys
  for name in sys.argv[1:]:
    p=post(name)
    print p.link()
    print p._entry
    print p.filepath()