diff options
| author | Georg Brandl <georg@python.org> | 2008-06-11 18:37:52 (GMT) |
|---|---|---|
| committer | Georg Brandl <georg@python.org> | 2008-06-11 18:37:52 (GMT) |
| commit | 559e5d7f4d1155e95fb6f925c927a263f9196935 (patch) | |
| tree | 4688423e81e9ffed7a5b2c87c50b55419e8e885a /Tools/unicode | |
| parent | ea6d58d9d3033436b52e84960b9571525a4f5412 (diff) | |
| download | cpython-559e5d7f4d1155e95fb6f925c927a263f9196935.zip cpython-559e5d7f4d1155e95fb6f925c927a263f9196935.tar.gz cpython-559e5d7f4d1155e95fb6f925c927a263f9196935.tar.bz2 | |
#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.
Diffstat (limited to 'Tools/unicode')
| -rw-r--r-- | Tools/unicode/makeunicodedata.py | 12 |
1 files changed, 9 insertions, 3 deletions
diff --git a/Tools/unicode/makeunicodedata.py b/Tools/unicode/makeunicodedata.py index 885e559..7b82f5c 100644 --- a/Tools/unicode/makeunicodedata.py +++ b/Tools/unicode/makeunicodedata.py @@ -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 @@ TITLE_MASK = 0x40 UPPER_MASK = 0x80 XID_START_MASK = 0x100 XID_CONTINUE_MASK = 0x200 +NONPRINTABLE_MASK = 0x400 def maketables(trace=0): @@ -71,7 +73,7 @@ def maketables(trace=0): 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 @@ def maketables(trace=0): 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 @@ def makeunicodetype(unicode, trace): 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 @@ def makeunicodename(unicode, trace): 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 |