Mercurial > cpython-lru_cache-weakref

diff Tools/unicode/makeunicodedata.py @ 47611:da47e7e135ae

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
#2630: Implement PEP 3138. The repr() of a string now contains printable Unicode characters unescaped. The new ascii() builtin can be used to get a repr() with only ASCII characters in it. PEP and patch were written by Atsuo Ishimoto.
author Georg Brandl <georg@python.org>
date Wed, 11 Jun 2008 18:37:52 +0000
parents d0f783ba7669
children b5e02775fffc
line wrap: on
line diff
--- a/Tools/unicode/makeunicodedata.py	Wed Jun 11 18:35:23 2008 +0000
+++ b/Tools/unicode/makeunicodedata.py	Wed Jun 11 18:37:52 2008 +0000
@@ -20,6 +20,7 @@
 # 2002-11-25 mvl  add UNIDATA_VERSION
 # 2004-05-29 perky add east asian width information
 # 2006-03-10 mvl  update to Unicode 4.1; add UCD 3.2 delta
+# 2008-06-11 gb   add NONPRINTABLE_MASK for Atsuo Ishimoto's ascii() patch
 #
 # written by Fredrik Lundh (fredrik@pythonware.com)
 #
@@ -60,6 +61,7 @@
 UPPER_MASK = 0x80
 XID_START_MASK = 0x100
 XID_CONTINUE_MASK = 0x200
+NONPRINTABLE_MASK = 0x400
 
 def maketables(trace=0):
 
@@ -71,7 +73,7 @@
                           EASTASIAN_WIDTH % version,
                           DERIVED_CORE_PROPERTIES % version)
 
-    print(len(filter(None, unicode.table)), "characters")
+    print(len(list(filter(None, unicode.table))), "characters")
 
     for version in old_versions:
         print("--- Reading", UNICODE_DATA % ("-"+version), "...")
@@ -79,7 +81,7 @@
                                   COMPOSITION_EXCLUSIONS % ("-"+version),
                                   EASTASIAN_WIDTH % ("-"+version),
                                   DERIVED_CORE_PROPERTIES % ("-"+version))
-        print(len(filter(None, old_unicode.table)), "characters")
+        print(len(list(filter(None, old_unicode.table))), "characters")
         merge_old_version(version, unicode, old_unicode)
 
     makeunicodename(unicode, trace)
@@ -371,6 +373,10 @@
                 flags |= TITLE_MASK
             if category == "Lu":
                 flags |= UPPER_MASK
+            if category[0] == "C":
+                flags |= NONPRINTABLE_MASK
+            if category[0] == "Z" and char != " ":
+                flags |= NONPRINTABLE_MASK
             if "XID_Start" in properties:
                 flags |= XID_START_MASK
             if "XID_Continue" in properties:
@@ -465,7 +471,7 @@
             if name and name[0] != "<":
                 names[char] = name + chr(0)
 
-    print(len(n for n in names if n is not None), "distinct names")
+    print(len(list(n for n in names if n is not None)), "distinct names")
 
     # collect unique words from names (note that we differ between
     # words inside a sentence, and words ending a sentence.  the