/[pcre]/code/trunk/maint/MultiStage2.py
ViewVC logotype

Diff of /code/trunk/maint/MultiStage2.py

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 490 by ph10, Mon Aug 17 14:48:48 2009 UTC revision 491 by ph10, Mon Mar 1 17:45:08 2010 UTC
# Line 66  Line 66 
66  # individual character types such as ucp_Cc to the general types like ucp_C.  # individual character types such as ucp_Cc to the general types like ucp_C.
67  #  #
68  #  Philip Hazel, 03 July 2008  #  Philip Hazel, 03 July 2008
69    #
70    # 01-March-2010: Updated list of scripts for Unicode 5.2.0
71  ##############################################################################  ##############################################################################
72    
73    
# Line 102  def read_table(file_name, get_value, def Line 104  def read_table(file_name, get_value, def
104                  if len(chardata) <= 1:                  if len(chardata) <= 1:
105                          continue                          continue
106                  value = get_value(chardata)                  value = get_value(chardata)
   
107                  m = re.match(r'([0-9a-fA-F]+)(\.\.([0-9a-fA-F]+))?$', chardata[0])                  m = re.match(r'([0-9a-fA-F]+)(\.\.([0-9a-fA-F]+))?$', chardata[0])
108                  char = int(m.group(1), 16)                  char = int(m.group(1), 16)
109                  if m.group(3) is None:                  if m.group(3) is None:
# Line 246  script_names = ['Arabic', 'Armenian', 'B Line 247  script_names = ['Arabic', 'Armenian', 'B
247  # New for Unicode 5.0  # New for Unicode 5.0
248   'Balinese', 'Cuneiform', 'Nko', 'Phags_Pa', 'Phoenician', \   'Balinese', 'Cuneiform', 'Nko', 'Phags_Pa', 'Phoenician', \
249  # New for Unicode 5.1  # New for Unicode 5.1
250   'Carian', 'Cham', 'Kayah_Li', 'Lepcha', 'Lycian', 'Lydian', 'Ol_Chiki', 'Rejang', 'Saurashtra', 'Sundanese', 'Vai']   'Carian', 'Cham', 'Kayah_Li', 'Lepcha', 'Lycian', 'Lydian', 'Ol_Chiki', 'Rejang', 'Saurashtra', 'Sundanese', 'Vai', \
251    # New for Unicode 5.2
252     'Avestan', 'Bamum', 'Egyptian_Hieroglyphs', 'Imperial_Aramaic', \
253     'Inscriptional_Pahlavi', 'Inscriptional_Parthian', \
254     'Javanese', 'Kaithi', 'Lisu', 'Meetei_Mayek', \
255     'Old_South_Arabian', 'Old_Turkic', 'Samaritan', 'Tai_Tham', 'Tai_Viet'
256     ]
257    
258  category_names = ['Cc', 'Cf', 'Cn', 'Co', 'Cs', 'Ll', 'Lm', 'Lo', 'Lt', 'Lu',  category_names = ['Cc', 'Cf', 'Cn', 'Co', 'Cs', 'Ll', 'Lm', 'Lo', 'Lt', 'Lu',
259    'Mc', 'Me', 'Mn', 'Nd', 'Nl', 'No', 'Pc', 'Pd', 'Pe', 'Pf', 'Pi', 'Po', 'Ps',    'Mc', 'Me', 'Mn', 'Nd', 'Nl', 'No', 'Pc', 'Pd', 'Pe', 'Pf', 'Pi', 'Po', 'Ps',

Legend:
Removed from v.490  
changed lines
  Added in v.491

  ViewVC Help
Powered by ViewVC 1.1.5