You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by br...@apache.org on 2022/11/14 12:27:11 UTC
[cassandra] branch trunk updated: replace local wcwidth.py with pypi module 'wcwidth'
This is an automated email from the ASF dual-hosted git repository.
brandonwilliams pushed a commit to branch trunk
in repository https://gitbox.apache.org/repos/asf/cassandra.git
The following commit(s) were added to refs/heads/trunk by this push:
new 8a5bdf61db replace local wcwidth.py with pypi module 'wcwidth'
8a5bdf61db is described below
commit 8a5bdf61db8dfe1d83d03f41753a46087082b2ee
Author: Brad Schoening <57...@users.noreply.github.com>
AuthorDate: Thu Nov 10 22:24:28 2022 -0500
replace local wcwidth.py with pypi module 'wcwidth'
Patch by Brad Schoening; reviewed by brandonwilliams and smiklosovic for
CASSANDRA-17287
---
.build/build-resolver.xml | 4 +-
CHANGES.txt | 1 +
bin/cqlsh.py | 2 +-
pylib/cqlshlib/formatting.py | 2 +-
pylib/cqlshlib/wcwidth.py | 379 -------------------------------------------
pylib/requirements.txt | 1 +
6 files changed, 7 insertions(+), 382 deletions(-)
diff --git a/.build/build-resolver.xml b/.build/build-resolver.xml
index e7bcc038dc..60122b854f 100644
--- a/.build/build-resolver.xml
+++ b/.build/build-resolver.xml
@@ -199,10 +199,11 @@
<mkdir dir="${local.repository}/org/apache/cassandra/deps/sigar-bin"/>
<mkdir dir="${build.lib}/sigar-bin"/>
- <!-- files.pythonhosted.org -->
+ <!-- files.pythonhosted.org/packages -->
<get src="${artifact.python.pypi}/59/a0/cf4cd997e1750f0c2d91c6ea5abea218251c43c3581bcc2f118b00baf5cf/futures-2.1.6-py2.py3-none-any.whl" dest="${local.repository}/org/apache/cassandra/deps/futures-2.1.6-py2.py3-none-any.zip" usetimestamp="true" quiet="true" skipexisting="true"/>
<get src="${artifact.python.pypi}/73/fb/00a976f728d0d1fecfe898238ce23f502a721c0ac0ecfedb80e0d88c64e9/six-1.12.0-py2.py3-none-any.whl" dest="${local.repository}/org/apache/cassandra/deps/six-1.12.0-py2.py3-none-any.zip" usetimestamp="true" quiet="true" skipexisting="true"/>
<get src="${artifact.python.pypi}/37/b2/ef1124540ee2c0b417be8d0f74667957e6aa084a3f26621aa67e2e77f3fb/pure_sasl-0.6.2-py2-none-any.whl" dest="${local.repository}/org/apache/cassandra/deps/pure_sasl-0.6.2-py2-none-any.zip" usetimestamp="true" quiet="true" skipexisting="true"/>
+ <get src="${artifact.python.pypi}/59/7c/e39aca596badaf1b78e8f547c807b04dae603a433d3e7a7e04d67f2ef3e5/wcwidth-0.2.5-py2.py3-none-any.whl" dest="${local.repository}/org/apache/cassandra/deps/wcwidth-0.2.5-py2.py3-none-any.zip" usetimestamp="true" quiet="true" skipexisting="true"/>
<!-- apache/cassandra/lib -->
<get src="${lib.download.base.url}/lib/geomet-0.1.0.zip" dest="${local.repository}/org/apache/cassandra/deps/geomet-0.1.0.zip" usetimestamp="true" quiet="true" skipexisting="true"/>
@@ -234,6 +235,7 @@
<file file="${local.repository}/org/apache/cassandra/deps/six-1.12.0-py2.py3-none-any.zip"/>
<file file="${local.repository}/org/apache/cassandra/deps/geomet-0.1.0.zip"/>
<file file="${local.repository}/org/apache/cassandra/deps/pure_sasl-0.6.2-py2-none-any.zip"/>
+ <file file="${local.repository}/org/apache/cassandra/deps/wcwidth-0.2.5-py2.py3-none-any.zip"/>
</copy>
<copy todir="${build.lib}/sigar-bin/" quiet="true">
<file file="${local.repository}/org/apache/cassandra/deps/sigar-bin/libsigar-amd64-freebsd-6.so"/>
diff --git a/CHANGES.txt b/CHANGES.txt
index fdf85df69b..ec6b151248 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,4 +1,5 @@
4.2
+ * Replace 'wcwidth.py' with pypi module (CASSANDRA-17287)
* Add nodetool forcecompact to remove tombstoned or ttl'd data ignoring GC grace for given table and partition keys (CASSANDRA-17711)
* Offer IF (NOT) EXISTS in cqlsh completion for CREATE TYPE, DROP TYPE, CREATE ROLE and DROP ROLE (CASSANDRA-16640)
* Nodetool bootstrap resume will now return an error if the operation fails (CASSANDRA-16491)
diff --git a/bin/cqlsh.py b/bin/cqlsh.py
index 7e6db9bdb8..2d079c0fe1 100755
--- a/bin/cqlsh.py
+++ b/bin/cqlsh.py
@@ -56,7 +56,7 @@ if cql_zip:
sys.path.insert(0, os.path.join(cql_zip, 'cassandra-driver-' + ver))
# the driver needs dependencies
-third_parties = ('six-', 'pure_sasl-')
+third_parties = ('six-', 'pure_sasl-', 'wcwidth-')
for lib in third_parties:
lib_zip = find_zip(lib)
diff --git a/pylib/cqlshlib/formatting.py b/pylib/cqlshlib/formatting.py
index 39bc060485..d463e4e902 100644
--- a/pylib/cqlshlib/formatting.py
+++ b/pylib/cqlshlib/formatting.py
@@ -20,12 +20,12 @@ import math
import os
import re
import sys
+import wcwidth
from collections import defaultdict
from cassandra.cqltypes import EMPTY
from cassandra.util import datetime_from_timestamp
-from . import wcwidth
from .displaying import colorme, get_str, FormattedValue, DEFAULT_VALUE_COLORS, NO_COLOR_MAP
from .util import UTC
diff --git a/pylib/cqlshlib/wcwidth.py b/pylib/cqlshlib/wcwidth.py
deleted file mode 100644
index 0be3af215b..0000000000
--- a/pylib/cqlshlib/wcwidth.py
+++ /dev/null
@@ -1,379 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# adapted from http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
-# -thepaul
-
-# This is an implementation of wcwidth() and wcswidth() (defined in
-# IEEE Std 1002.1-2001) for Unicode.
-#
-# http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
-# http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
-#
-# In fixed-width output devices, Latin characters all occupy a single
-# "cell" position of equal width, whereas ideographic CJK characters
-# occupy two such cells. Interoperability between terminal-line
-# applications and (teletype-style) character terminals using the
-# UTF-8 encoding requires agreement on which character should advance
-# the cursor by how many cell positions. No established formal
-# standards exist at present on which Unicode character shall occupy
-# how many cell positions on character terminals. These routines are
-# a first attempt of defining such behavior based on simple rules
-# applied to data provided by the Unicode Consortium.
-#
-# For some graphical characters, the Unicode standard explicitly
-# defines a character-cell width via the definition of the East Asian
-# FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
-# In all these cases, there is no ambiguity about which width a
-# terminal shall use. For characters in the East Asian Ambiguous (A)
-# class, the width choice depends purely on a preference of backward
-# compatibility with either historic CJK or Western practice.
-# Choosing single-width for these characters is easy to justify as
-# the appropriate long-term solution, as the CJK practice of
-# displaying these characters as double-width comes from historic
-# implementation simplicity (8-bit encoded characters were displayed
-# single-width and 16-bit ones double-width, even for Greek,
-# Cyrillic, etc.) and not any typographic considerations.
-#
-# Much less clear is the choice of width for the Not East Asian
-# (Neutral) class. Existing practice does not dictate a width for any
-# of these characters. It would nevertheless make sense
-# typographically to allocate two character cells to characters such
-# as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
-# represented adequately with a single-width glyph. The following
-# routines at present merely assign a single-cell width to all
-# neutral characters, in the interest of simplicity. This is not
-# entirely satisfactory and should be reconsidered before
-# establishing a formal standard in this area. At the moment, the
-# decision which Not East Asian (Neutral) characters should be
-# represented by double-width glyphs cannot yet be answered by
-# applying a simple rule from the Unicode database content. Setting
-# up a proper standard for the behavior of UTF-8 character terminals
-# will require a careful analysis not only of each Unicode character,
-# but also of each presentation form, something the author of these
-# routines has avoided to do so far.
-#
-# http://www.unicode.org/unicode/reports/tr11/
-#
-# Markus Kuhn -- 2007-05-26 (Unicode 5.0)
-#
-# Permission to use, copy, modify, and distribute this software
-# for any purpose and without fee is hereby granted. The author
-# disclaims all warranties with regard to this software.
-#
-# Latest C version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
-
-# auxiliary function for binary search in interval table
-
-
-def bisearch(ucs, table):
- min = 0
- max = len(table) - 1
- if ucs < table[0][0] or ucs > table[max][1]:
- return 0
- while max >= min:
- mid = int((min + max) / 2)
- if ucs > table[mid][1]:
- min = mid + 1
- elif ucs < table[mid][0]:
- max = mid - 1
- else:
- return 1
- return 0
-
-
-# The following two functions define the column width of an ISO 10646
-# character as follows:
-#
-# - The null character (U+0000) has a column width of 0.
-#
-# - Other C0/C1 control characters and DEL will lead to a return
-# value of -1.
-#
-# - Non-spacing and enclosing combining characters (general
-# category code Mn or Me in the Unicode database) have a
-# column width of 0.
-#
-# - SOFT HYPHEN (U+00AD) has a column width of 1.
-#
-# - Other format characters (general category code Cf in the Unicode
-# database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
-#
-# - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
-# have a column width of 0.
-#
-# - Spacing characters in the East Asian Wide (W) or East Asian
-# Full-width (F) category as defined in Unicode Technical
-# Report #11 have a column width of 2.
-#
-# - All remaining characters (including all printable
-# ISO 8859-1 and WGL4 characters, Unicode control characters,
-# etc.) have a column width of 1.
-#
-# This implementation assumes that wchar_t characters are encoded
-# in ISO 10646.
-
-# sorted list of non-overlapping intervals of non-spacing characters
-# generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c"
-combining = (
- (0x0300, 0x036F), (0x0483, 0x0486), (0x0488, 0x0489),
- (0x0591, 0x05BD), (0x05BF, 0x05BF), (0x05C1, 0x05C2),
- (0x05C4, 0x05C5), (0x05C7, 0x05C7), (0x0600, 0x0603),
- (0x0610, 0x0615), (0x064B, 0x065E), (0x0670, 0x0670),
- (0x06D6, 0x06E4), (0x06E7, 0x06E8), (0x06EA, 0x06ED),
- (0x070F, 0x070F), (0x0711, 0x0711), (0x0730, 0x074A),
- (0x07A6, 0x07B0), (0x07EB, 0x07F3), (0x0901, 0x0902),
- (0x093C, 0x093C), (0x0941, 0x0948), (0x094D, 0x094D),
- (0x0951, 0x0954), (0x0962, 0x0963), (0x0981, 0x0981),
- (0x09BC, 0x09BC), (0x09C1, 0x09C4), (0x09CD, 0x09CD),
- (0x09E2, 0x09E3), (0x0A01, 0x0A02), (0x0A3C, 0x0A3C),
- (0x0A41, 0x0A42), (0x0A47, 0x0A48), (0x0A4B, 0x0A4D),
- (0x0A70, 0x0A71), (0x0A81, 0x0A82), (0x0ABC, 0x0ABC),
- (0x0AC1, 0x0AC5), (0x0AC7, 0x0AC8), (0x0ACD, 0x0ACD),
- (0x0AE2, 0x0AE3), (0x0B01, 0x0B01), (0x0B3C, 0x0B3C),
- (0x0B3F, 0x0B3F), (0x0B41, 0x0B43), (0x0B4D, 0x0B4D),
- (0x0B56, 0x0B56), (0x0B82, 0x0B82), (0x0BC0, 0x0BC0),
- (0x0BCD, 0x0BCD), (0x0C3E, 0x0C40), (0x0C46, 0x0C48),
- (0x0C4A, 0x0C4D), (0x0C55, 0x0C56), (0x0CBC, 0x0CBC),
- (0x0CBF, 0x0CBF), (0x0CC6, 0x0CC6), (0x0CCC, 0x0CCD),
- (0x0CE2, 0x0CE3), (0x0D41, 0x0D43), (0x0D4D, 0x0D4D),
- (0x0DCA, 0x0DCA), (0x0DD2, 0x0DD4), (0x0DD6, 0x0DD6),
- (0x0E31, 0x0E31), (0x0E34, 0x0E3A), (0x0E47, 0x0E4E),
- (0x0EB1, 0x0EB1), (0x0EB4, 0x0EB9), (0x0EBB, 0x0EBC),
- (0x0EC8, 0x0ECD), (0x0F18, 0x0F19), (0x0F35, 0x0F35),
- (0x0F37, 0x0F37), (0x0F39, 0x0F39), (0x0F71, 0x0F7E),
- (0x0F80, 0x0F84), (0x0F86, 0x0F87), (0x0F90, 0x0F97),
- (0x0F99, 0x0FBC), (0x0FC6, 0x0FC6), (0x102D, 0x1030),
- (0x1032, 0x1032), (0x1036, 0x1037), (0x1039, 0x1039),
- (0x1058, 0x1059), (0x1160, 0x11FF), (0x135F, 0x135F),
- (0x1712, 0x1714), (0x1732, 0x1734), (0x1752, 0x1753),
- (0x1772, 0x1773), (0x17B4, 0x17B5), (0x17B7, 0x17BD),
- (0x17C6, 0x17C6), (0x17C9, 0x17D3), (0x17DD, 0x17DD),
- (0x180B, 0x180D), (0x18A9, 0x18A9), (0x1920, 0x1922),
- (0x1927, 0x1928), (0x1932, 0x1932), (0x1939, 0x193B),
- (0x1A17, 0x1A18), (0x1B00, 0x1B03), (0x1B34, 0x1B34),
- (0x1B36, 0x1B3A), (0x1B3C, 0x1B3C), (0x1B42, 0x1B42),
- (0x1B6B, 0x1B73), (0x1DC0, 0x1DCA), (0x1DFE, 0x1DFF),
- (0x200B, 0x200F), (0x202A, 0x202E), (0x2060, 0x2063),
- (0x206A, 0x206F), (0x20D0, 0x20EF), (0x302A, 0x302F),
- (0x3099, 0x309A), (0xA806, 0xA806), (0xA80B, 0xA80B),
- (0xA825, 0xA826), (0xFB1E, 0xFB1E), (0xFE00, 0xFE0F),
- (0xFE20, 0xFE23), (0xFEFF, 0xFEFF), (0xFFF9, 0xFFFB),
- (0x10A01, 0x10A03), (0x10A05, 0x10A06), (0x10A0C, 0x10A0F),
- (0x10A38, 0x10A3A), (0x10A3F, 0x10A3F), (0x1D167, 0x1D169),
- (0x1D173, 0x1D182), (0x1D185, 0x1D18B), (0x1D1AA, 0x1D1AD),
- (0x1D242, 0x1D244), (0xE0001, 0xE0001), (0xE0020, 0xE007F),
- (0xE0100, 0xE01EF)
-)
-
-
-# sorted list of non-overlapping intervals of East Asian Ambiguous
-# characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c"
-ambiguous = (
- (0x00A1, 0x00A1), (0x00A4, 0x00A4), (0x00A7, 0x00A8),
- (0x00AA, 0x00AA), (0x00AE, 0x00AE), (0x00B0, 0x00B4),
- (0x00B6, 0x00BA), (0x00BC, 0x00BF), (0x00C6, 0x00C6),
- (0x00D0, 0x00D0), (0x00D7, 0x00D8), (0x00DE, 0x00E1),
- (0x00E6, 0x00E6), (0x00E8, 0x00EA), (0x00EC, 0x00ED),
- (0x00F0, 0x00F0), (0x00F2, 0x00F3), (0x00F7, 0x00FA),
- (0x00FC, 0x00FC), (0x00FE, 0x00FE), (0x0101, 0x0101),
- (0x0111, 0x0111), (0x0113, 0x0113), (0x011B, 0x011B),
- (0x0126, 0x0127), (0x012B, 0x012B), (0x0131, 0x0133),
- (0x0138, 0x0138), (0x013F, 0x0142), (0x0144, 0x0144),
- (0x0148, 0x014B), (0x014D, 0x014D), (0x0152, 0x0153),
- (0x0166, 0x0167), (0x016B, 0x016B), (0x01CE, 0x01CE),
- (0x01D0, 0x01D0), (0x01D2, 0x01D2), (0x01D4, 0x01D4),
- (0x01D6, 0x01D6), (0x01D8, 0x01D8), (0x01DA, 0x01DA),
- (0x01DC, 0x01DC), (0x0251, 0x0251), (0x0261, 0x0261),
- (0x02C4, 0x02C4), (0x02C7, 0x02C7), (0x02C9, 0x02CB),
- (0x02CD, 0x02CD), (0x02D0, 0x02D0), (0x02D8, 0x02DB),
- (0x02DD, 0x02DD), (0x02DF, 0x02DF), (0x0391, 0x03A1),
- (0x03A3, 0x03A9), (0x03B1, 0x03C1), (0x03C3, 0x03C9),
- (0x0401, 0x0401), (0x0410, 0x044F), (0x0451, 0x0451),
- (0x2010, 0x2010), (0x2013, 0x2016), (0x2018, 0x2019),
- (0x201C, 0x201D), (0x2020, 0x2022), (0x2024, 0x2027),
- (0x2030, 0x2030), (0x2032, 0x2033), (0x2035, 0x2035),
- (0x203B, 0x203B), (0x203E, 0x203E), (0x2074, 0x2074),
- (0x207F, 0x207F), (0x2081, 0x2084), (0x20AC, 0x20AC),
- (0x2103, 0x2103), (0x2105, 0x2105), (0x2109, 0x2109),
- (0x2113, 0x2113), (0x2116, 0x2116), (0x2121, 0x2122),
- (0x2126, 0x2126), (0x212B, 0x212B), (0x2153, 0x2154),
- (0x215B, 0x215E), (0x2160, 0x216B), (0x2170, 0x2179),
- (0x2190, 0x2199), (0x21B8, 0x21B9), (0x21D2, 0x21D2),
- (0x21D4, 0x21D4), (0x21E7, 0x21E7), (0x2200, 0x2200),
- (0x2202, 0x2203), (0x2207, 0x2208), (0x220B, 0x220B),
- (0x220F, 0x220F), (0x2211, 0x2211), (0x2215, 0x2215),
- (0x221A, 0x221A), (0x221D, 0x2220), (0x2223, 0x2223),
- (0x2225, 0x2225), (0x2227, 0x222C), (0x222E, 0x222E),
- (0x2234, 0x2237), (0x223C, 0x223D), (0x2248, 0x2248),
- (0x224C, 0x224C), (0x2252, 0x2252), (0x2260, 0x2261),
- (0x2264, 0x2267), (0x226A, 0x226B), (0x226E, 0x226F),
- (0x2282, 0x2283), (0x2286, 0x2287), (0x2295, 0x2295),
- (0x2299, 0x2299), (0x22A5, 0x22A5), (0x22BF, 0x22BF),
- (0x2312, 0x2312), (0x2460, 0x24E9), (0x24EB, 0x254B),
- (0x2550, 0x2573), (0x2580, 0x258F), (0x2592, 0x2595),
- (0x25A0, 0x25A1), (0x25A3, 0x25A9), (0x25B2, 0x25B3),
- (0x25B6, 0x25B7), (0x25BC, 0x25BD), (0x25C0, 0x25C1),
- (0x25C6, 0x25C8), (0x25CB, 0x25CB), (0x25CE, 0x25D1),
- (0x25E2, 0x25E5), (0x25EF, 0x25EF), (0x2605, 0x2606),
- (0x2609, 0x2609), (0x260E, 0x260F), (0x2614, 0x2615),
- (0x261C, 0x261C), (0x261E, 0x261E), (0x2640, 0x2640),
- (0x2642, 0x2642), (0x2660, 0x2661), (0x2663, 0x2665),
- (0x2667, 0x266A), (0x266C, 0x266D), (0x266F, 0x266F),
- (0x273D, 0x273D), (0x2776, 0x277F), (0xE000, 0xF8FF),
- (0xFFFD, 0xFFFD), (0xF0000, 0xFFFFD), (0x100000, 0x10FFFD)
-)
-
-
-def mk_wcwidth(ucs):
- # test for 8-bit control characters
- if ucs == 0:
- return 0
- if ucs < 32 or (ucs >= 0x7f and ucs < 0xa0):
- return -1
-
- # binary search in table of non-spacing characters
- if bisearch(ucs, combining):
- return 0
-
- # if we arrive here, ucs is not a combining or C0/C1 control character
-
- return 1 + int(
- ucs >= 0x1100
- and (ucs <= 0x115f # Hangul Jamo init. consonants
- or ucs == 0x2329 or ucs == 0x232a
- or (ucs >= 0x2e80 and ucs <= 0xa4cf
- and ucs != 0x303f) # CJK ... Yi
- or (ucs >= 0xac00 and ucs <= 0xd7a3) # Hangul Syllables
- or (ucs >= 0xf900 and ucs <= 0xfaff) # CJK Compatibility Ideographs
- or (ucs >= 0xfe10 and ucs <= 0xfe19) # Vertical forms
- or (ucs >= 0xfe30 and ucs <= 0xfe6f) # CJK Compatibility Forms
- or (ucs >= 0xff00 and ucs <= 0xff60) # Fullwidth Forms
- or (ucs >= 0xffe0 and ucs <= 0xffe6)
- or (ucs >= 0x20000 and ucs <= 0x2fffd)
- or (ucs >= 0x30000 and ucs <= 0x3fffd))
- )
-
-
-def mk_wcswidth(pwcs):
- width = 0
- for c in pwcs:
- w = mk_wcwidth(c)
- if w < 0:
- return -1
- else:
- width += w
-
- return width
-
-
-# The following functions are the same as mk_wcwidth() and
-# mk_wcswidth(), except that spacing characters in the East Asian
-# Ambiguous (A) category as defined in Unicode Technical Report #11
-# have a column width of 2. This variant might be useful for users of
-# CJK legacy encodings who want to migrate to UCS without changing
-# the traditional terminal character-width behaviour. It is not
-# otherwise recommended for general use.
-def mk_wcwidth_cjk(ucs):
- # binary search in table of non-spacing characters
- if bisearch(ucs, ambiguous):
- return 2
-
- return mk_wcwidth(ucs)
-
-
-def mk_wcswidth_cjk(pwcs):
- width = 0
-
- for c in pwcs:
- w = mk_wcwidth_cjk(c)
- if w < 0:
- return -1
- width += w
-
- return width
-
-# python-y versions, dealing with unicode objects
-
-
-def wcwidth(c):
- return mk_wcwidth(ord(c))
-
-
-def wcswidth(s):
- return mk_wcswidth(list(map(ord, s)))
-
-
-def wcwidth_cjk(c):
- return mk_wcwidth_cjk(ord(c))
-
-
-def wcswidth_cjk(s):
- return mk_wcswidth_cjk(list(map(ord, s)))
-
-
-if __name__ == "__main__":
- samples = (
- ('MUSIC SHARP SIGN', 1),
- ('FULLWIDTH POUND SIGN', 2),
- ('FULLWIDTH LATIN CAPITAL LETTER P', 2),
- ('CJK RADICAL BOLT OF CLOTH', 2),
- ('LATIN SMALL LETTER A', 1),
- ('LATIN SMALL LETTER AE', 1),
- ('SPACE', 1),
- ('NO-BREAK SPACE', 1),
- ('CJK COMPATIBILITY IDEOGRAPH-F920', 2),
- ('MALAYALAM VOWEL SIGN UU', 0),
- ('ZERO WIDTH SPACE', 0),
- ('ZERO WIDTH NO-BREAK SPACE', 0),
- ('COMBINING PALATALIZED HOOK BELOW', 0),
- ('COMBINING GRAVE ACCENT', 0),
- )
- nonprinting = '\r\n\t\a\b\f\v\x7f'
-
- import unicodedata
-
- for name, printwidth in samples:
- uchr = unicodedata.lookup(name)
- calculatedwidth = wcwidth(uchr)
- assert calculatedwidth == printwidth, \
- 'width for %r should be %d, but is %d?' % (uchr, printwidth, calculatedwidth)
-
- for c in nonprinting:
- calculatedwidth = wcwidth(c)
- assert calculatedwidth < 0, \
- '%r is a control character, but wcwidth gives %d' % (c, calculatedwidth)
-
- assert wcwidth('\0') == 0 # special case
-
- # depending on how python is compiled, code points above U+FFFF may not be
- # treated as single characters, so ord() won't work. test a few of these
- # manually.
-
- assert mk_wcwidth(0xe01ef) == 0
- assert mk_wcwidth(0x10ffff) == 1
- assert mk_wcwidth(0x3fffd) == 2
-
- teststr = 'B\0ig br\u00f8wn moose\ub143\u200b'
- calculatedwidth = wcswidth(teststr)
- assert calculatedwidth == 17, 'expected 17, got %d' % calculatedwidth
-
- calculatedwidth = wcswidth_cjk(teststr)
- assert calculatedwidth == 18, 'expected 18, got %d' % calculatedwidth
-
- assert wcswidth('foobar\u200b\a') < 0
-
- print('tests pass.')
diff --git a/pylib/requirements.txt b/pylib/requirements.txt
index c030460b3f..379f6ae332 100644
--- a/pylib/requirements.txt
+++ b/pylib/requirements.txt
@@ -3,3 +3,4 @@
-e git+https://github.com/riptano/ccm.git@cassandra-test#egg=ccm
coverage
pytest
+wcwidth
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org