[Python-checkins] r86681 - in python/branches/py3k: Lib/test/test_ucn.py Misc/NEWS Modules/unicodedata.c Tools/unicode/makeunicodedata.py

[martin.v.loewis]

Author: martin.v.loewis
Date: Mon Nov 22 10:00:02 2010
New Revision: 86681

Log:
Issue #10459: Update CJK character names to Unicode 6.0.


Modified:
   python/branches/py3k/Lib/test/test_ucn.py
   python/branches/py3k/Misc/NEWS
   python/branches/py3k/Modules/unicodedata.c
   python/branches/py3k/Tools/unicode/makeunicodedata.py

Modified: python/branches/py3k/Lib/test/test_ucn.py
==============================================================================
--- python/branches/py3k/Lib/test/test_ucn.py	(original)
+++ python/branches/py3k/Lib/test/test_ucn.py	Mon Nov 22 10:00:02 2010
@@ -88,9 +88,13 @@
         self.checkletter("CJK UNIFIED IDEOGRAPH-3400", "\u3400")
         self.checkletter("CJK UNIFIED IDEOGRAPH-4DB5", "\u4db5")
         self.checkletter("CJK UNIFIED IDEOGRAPH-4E00", "\u4e00")
-        self.checkletter("CJK UNIFIED IDEOGRAPH-9FA5", "\u9fa5")
+        self.checkletter("CJK UNIFIED IDEOGRAPH-9FCB", "\u9fCB")
         self.checkletter("CJK UNIFIED IDEOGRAPH-20000", "\U00020000")
         self.checkletter("CJK UNIFIED IDEOGRAPH-2A6D6", "\U0002a6d6")
+        self.checkletter("CJK UNIFIED IDEOGRAPH-2A700", "\U0002A700")
+        self.checkletter("CJK UNIFIED IDEOGRAPH-2B734", "\U0002B734")
+        self.checkletter("CJK UNIFIED IDEOGRAPH-2B740", "\U0002B740")
+        self.checkletter("CJK UNIFIED IDEOGRAPH-2B81D", "\U0002B81D")
 
     def test_bmp_characters(self):
         import unicodedata

Modified: python/branches/py3k/Misc/NEWS
==============================================================================
--- python/branches/py3k/Misc/NEWS	(original)
+++ python/branches/py3k/Misc/NEWS	Mon Nov 22 10:00:02 2010
@@ -32,6 +32,8 @@
 Library
 -------
 
+- Issue #10459: Update CJK character names to Unicode 6.0.
+
 - Issue #4493: urllib.request adds '/' in front of path components which does not
   start with '/. Common behavior exhibited by browsers and other clients.
 

Modified: python/branches/py3k/Modules/unicodedata.c
==============================================================================
--- python/branches/py3k/Modules/unicodedata.c	(original)
+++ python/branches/py3k/Modules/unicodedata.c	Mon Nov 22 10:00:02 2010
@@ -866,13 +866,16 @@
     { 0,    0,     "H"  }
 };
 
+/* These ranges need to match makeunicodedata.py:cjk_ranges. */
 static int
 is_unified_ideograph(Py_UCS4 code)
 {
-    return (
-        (0x3400 <= code && code <= 0x4DB5) || /* CJK Ideograph Extension A */
-        (0x4E00 <= code && code <= 0x9FBB) || /* CJK Ideograph */
-        (0x20000 <= code && code <= 0x2A6D6));/* CJK Ideograph Extension B */
+    return
+        (0x3400 <= code && code <= 0x4DB5)   || /* CJK Ideograph Extension A */
+        (0x4E00 <= code && code <= 0x9FCB)   || /* CJK Ideograph */
+        (0x20000 <= code && code <= 0x2A6D6) || /* CJK Ideograph Extension B */
+        (0x2A700 <= code && code <= 0x2B734) || /* CJK Ideograph Extension C */
+        (0x2B740 <= code && code <= 0x2B81D);   /* CJK Ideograph Extension D */
 }
 
 static int

Modified: python/branches/py3k/Tools/unicode/makeunicodedata.py
==============================================================================
--- python/branches/py3k/Tools/unicode/makeunicodedata.py	(original)
+++ python/branches/py3k/Tools/unicode/makeunicodedata.py	Mon Nov 22 10:00:02 2010
@@ -70,6 +70,15 @@
 NODELTA_MASK = 0x800
 NUMERIC_MASK = 0x1000
 
+# these ranges need to match unicodedata.c:is_unified_ideograph
+cjk_ranges = [
+    ('3400', '4DB5'),
+    ('4E00', '9FCB'),
+    ('20000', '2A6D6'),
+    ('2A700', '2B734'),
+    ('2B740', '2B81D')
+]
+
 def maketables(trace=0):
 
     print("--- Reading", UNICODE_DATA % "", "...")
@@ -81,7 +90,7 @@
 
     for version in old_versions:
         print("--- Reading", UNICODE_DATA % ("-"+version), "...")
-        old_unicode = UnicodeData(version)
+        old_unicode = UnicodeData(version, cjk_check=False)
         print(len(list(filter(None, old_unicode.table))), "characters")
         merge_old_version(version, unicode, old_unicode)
 
@@ -804,7 +813,8 @@
 
     def __init__(self, version,
                  linebreakprops=False,
-                 expand=1):
+                 expand=1,
+                 cjk_check=True):
         self.changed = []
         file = open_data(UNICODE_DATA, version)
         table = [None] * 0x110000
@@ -816,6 +826,8 @@
             char = int(s[0], 16)
             table[char] = s
 
+        cjk_ranges_found = []
+
         # expand first-last ranges
         if expand:
             field = None
@@ -826,12 +838,17 @@
                         s[1] = ""
                         field = s
                     elif s[1][-5:] == "Last>":
+                        if s[1].startswith("<CJK Ideograph"):
+                            cjk_ranges_found.append((field[0],
+                                                     s[0]))
                         s[1] = ""
                         field = None
                 elif field:
                     f2 = field[:]
                     f2[0] = "%X" % i
                     table[i] = f2
+            if cjk_check and cjk_ranges != cjk_ranges_found:
+                raise ValueError("CJK ranges deviate: have %r" % cjk_ranges_found)
 
         # public attributes
         self.filename = UNICODE_DATA % ''