src/inout/io.py

   1 import os,sys
   2
   3
   4 def create_dir_if_necessary(path):
   5     if len(path) > 0 and not os.path.exists(path):
   6         os.makedirs(path)
   7
   8 def safe_chdir(path):
   9     #try:
  10     #    path = os_encode(path_unicode)
  11     #except UnicodeError:
  12     #    #logger.log('Error decoding path %s'%repr(path_unicode))
  13     #    print 'Error decoding path %s'%repr(path_unicode)
  14     #    path = path_unicode
  15     create_dir_if_necessary(path)
  16     os.chdir(path)
  17
  18 def create_file(file_path):
  19     dir = os.path.dirname(os_encode(file_path))
  20     create_dir_if_necessary(dir)
  21     encoded_file_path = os_encode(file_path)
  22     file_name = os.path.join(dir,os.path.basename(encoded_file_path))
  23
  24     f = file(file_name,'w')
  25     return f
  26
  27
  28 def os_encode(s):
  29     return s.encode(sys.getfilesystemencoding())
  30
  31 def os_decode(s):
  32     if type(s) == unicode:
  33         return s
  34     else:
  35         return unicode(s,sys.getfilesystemencoding())
  36
  37 def write(file_path,content):
  38     f = create_file(file_path)
  39     f.write(os_encode(content))
  40     f.close()
  41     from log.logging import logger
  42     logger.log(u'Wrote %s to %s'%(content,os.path.abspath(file_path)))
  43
  44 def list_dir(root,recursive=False,filter=None):
  45     encoded_root = os_encode(root)
  46     if not os.path.exists(encoded_root):
  47         return []
  48     all_files_and_dirs = []
  49     for name in os.listdir(encoded_root):
  50         file_name = os_decode(os.path.join(encoded_root,name))
  51         if recursive and os.path.isdir(os_encode(file_name)):
  52             all_files_and_dirs.extend(list_dir(file_name, True,filter))
  53         if (not filter) or filter(file_name):
  54             all_files_and_dirs.append(file_name)
  55     return all_files_and_dirs
  56
  57 def guess_encoding(data):
  58     #from logging import logger
  59     encodings = ['ascii','utf-8','utf-16']
  60     successful_encoding = None
  61     if data[:3]=='\xEF\xBB\xBF':
  62         data = data[3:]
  63
  64     for enc in encodings:
  65         if not enc:
  66             continue
  67         try:
  68             decoded = unicode(data, enc)
  69             successful_encoding = enc
  70             break
  71         except (UnicodeError, LookupError):
  72             pass
  73     if successful_encoding is None:
  74         raise UnicodeError('Unable to decode input data %s. Tried the'
  75             ' following encodings: %s.' %(repr(data), ', '.join([repr(enc)
  76                 for enc in encodings if enc])))
  77     else:
  78         #logger.log('Decoded %s to %s'%(repr(data),repr(decoded)),6)
  79         return (decoded, successful_encoding)
  80
  81
  82 def read_text_from_file(unicode_file_name):
  83     from log.logging import logger
  84     file_name = os_encode(unicode_file_name)
  85 #    logger.log(u'Reading from %s'%os.path.abspath(file_name).decode('utf-8'))
  86     f=file(file_name,'r')
  87     raw=f.read()
  88     f.close()
  89     (text,encoding)=guess_encoding(raw)
  90
  91     return text
  92 def parse_file_to_line_list(unicode_complete_path):
  93     text = read_text_from_file(unicode_complete_path)
  94     lines = text.splitlines()
  95     return lines
  96 def is_dir(unicode_path):
  97     return os.path.isdir(os_encode(unicode_path))