test.py

# coding: utf-8
 
from __future__ import with_statement
import os, re
 
reName1 = re.compile(r'^\d+-\d+-\d+_[^\.]+\.markdown$')
reName1_1 = re.compile(r'^\d+-\d+-\d+_[^\.]+\.md$')
 
reName2 = re.compile(r'^\d+-\d+-\d+-[^\.]+\.markdown$')
reDate = re.compile(r'^date: ([\d\-]+) (\d+):(\d+)\n$', re.I)
def rename():
  for f in os.listdir('.'):
    if not os.path.isfile(f):
      continue
    m = reName1.match(f)
 
    if m == None:
      m = reName2.match(f)
 
    if m != None:
      with open(f) as ff:
        for line in ff:
          m2 = reDate.match(line)
          if m2 != None:
            newName = '%s_%s-%s.md' % (m2.group(1), m2.group(2), m2.group(3))
 
      print '%s -> %s' % (f, newName)
      os.rename(f, newName)
 
 
 
def rewrite():
  import codecs
  files = (f for f in os.listdir('.') if reName1_1.match(f) != None)
  fn = 0
  for f in tuple(files):#[40:]:
    # if f != '2012-06-03_14-55.md':
    #   continue
 
    lines = []
    with codecs.open(f, encoding='utf-8') as ff:
      ln = 0
      for l in ff:
        ln += 1
        if ln > 10:
          lines.append(l)
          continue
          # break
        ll = re.sub(ur'^-{3,}\r\n$', u'', l)
        if ll != l:
          continue
 
        ll = re.sub(ur'^layout: [\w\s]+$', u'', l)
        if ll != l:
          continue
 
        ll = re.sub(ur'^comments: [\w\s]+$', u'', l)
        if ll != l:
          continue
 
        if ll == l:
          ll = re.sub(ur'^title: "?([^"]+)"?([\r\n]+)$', ur'Title: \1\2', l)
          if ll != l:
            lines.append(ll)
 
        if ll == l:
          ll = re.sub(ur'^date: ([^\r\n]+)([\r\n]+)$', ur'Date: \1\2', l)
          if ll != l:
            lines.append(ll)
 
        if ll == l:
          ll = re.sub(ur'^published: ([^\r\n]+)([\r\n]+)$', ur'Published: \1\2', l)
          if ll != l:
            lines.append(ll)
 
        if ll == l:
          ll = re.sub(ur'^categories: ([^\r\n]*)([\r\n]+)$', ur'\1', l)
          if ll != l:
            ll = u'Tags: %s\r\n' % ', '.join(ll.lower().split(' ')).strip(u', ')
            lines.append(ll)
 
 
        if ll == l:
          lines.append(ll)
    # TODO write
    # print repr(lines)
#     print '''%s
# %s
# ''' % (f.encode('utf-8'), ''.join(lines).encode('utf-8'))
    with codecs.open('_' + f, 'w', encoding='utf-8') as ff:
      ff.writelines(lines)
 
   
 
if __name__ == '__main__':
  # rename()
  rewrite()