back to Claude Sonnet 3.5 - Fill-in + Unit Test Feedback summary
Claude Sonnet 3.5 - Fill-in + Unit Test Feedback: wcwidth
Pytest Summary for test tests
| status | count |
|---|---|
| passed | 9 |
| failed | 29 |
| skipped | 1 |
| total | 39 |
| collected | 39 |
Failed pytests:
test_core.py::test_hello_jp
test_core.py::test_hello_jp
def test_hello_jp():
u"""
Width of Japanese phrase: コンニチハ, セカイ!
Given a phrase of 5 and 3 Katakana ideographs, joined with
3 English-ASCII punctuation characters, totaling 11, this
phrase consumes 19 cells of a terminal emulator.
"""
# given,
phrase = u'コンニチハ, セカイ!'
expect_length_each = (2, 2, 2, 2, 2, 1, 1, 2, 2, 2, 1)
expect_length_phrase = sum(expect_length_each)
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:86:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 12467
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_wcswidth_substr
test_core.py::test_wcswidth_substr
def test_wcswidth_substr():
"""
Test wcswidth() optional 2nd parameter, ``n``.
``n`` determines at which position of the string
to stop counting length.
"""
# given,
phrase = u'コンニチハ, セカイ!'
end = 7
expect_length_each = (2, 2, 2, 2, 2, 1, 1,)
expect_length_phrase = sum(expect_length_each)
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))[:end]
tests/test_core.py:108:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 12467
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_null_width_0
test_core.py::test_null_width_0
def test_null_width_0():
"""NULL (0) reports width 0."""
# given,
phrase = u'abc\x00def'
expect_length_each = (1, 1, 1, 0, 1, 1, 1)
expect_length_phrase = sum(expect_length_each)
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:124:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 97
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_control_c0_width_negative_1
test_core.py::test_control_c0_width_negative_1
def test_control_c0_width_negative_1():
"""How the API reacts to CSI (Control sequence initiate).
An example of bad fortune, this terminal sequence is a width of 0
on all terminals, but wcwidth doesn't parse Control-Sequence-Inducer
(CSI) sequences.
Also the "legacy" posix functions wcwidth and wcswidth return -1 for
any string containing the C1 control character \x1b (ESC).
"""
# given,
phrase = u'\x1b[0m'
expect_length_each = (-1, 1, 1, 1)
expect_length_phrase = -1
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:148:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 91
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_combining_width
test_core.py::test_combining_width
def test_combining_width():
"""Simple test combining reports total width of 4."""
# given,
phrase = u'--\u05bf--'
expect_length_each = (1, 1, 0, 1, 1)
expect_length_phrase = 4
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:164:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 45
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_combining_cafe
test_core.py::test_combining_cafe
def test_combining_cafe():
u"""Phrase cafe + COMBINING ACUTE ACCENT is café of length 4."""
phrase = u"cafe\u0301"
expect_length_each = (1, 1, 1, 1, 0)
expect_length_phrase = 4
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:179:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 99
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_combining_enclosing
test_core.py::test_combining_enclosing
def test_combining_enclosing():
u"""CYRILLIC CAPITAL LETTER A + COMBINING CYRILLIC HUNDRED THOUSANDS SIGN is of length 1."""
phrase = u"\u0410\u0488"
expect_length_each = (1, 0)
expect_length_phrase = 1
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:194:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 1040
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_balinese_script
test_core.py::test_balinese_script
def test_balinese_script():
u"""
Balinese kapal (ship) is length 3.
This may be an example that is not yet correctly rendered by any terminal so
far, like devanagari.
"""
phrase = (u"\u1B13" # Category 'Lo', EAW 'N' -- BALINESE LETTER KA
u"\u1B28" # Category 'Lo', EAW 'N' -- BALINESE LETTER PA KAPAL
u"\u1B2E" # Category 'Lo', EAW 'N' -- BALINESE LETTER LA
u"\u1B44") # Category 'Mc', EAW 'N' -- BALINESE ADEG ADEG
expect_length_each = (1, 1, 1, 0)
expect_length_phrase = 3
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:217:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 6931
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_kr_jamo
test_core.py::test_kr_jamo
def test_kr_jamo():
"""
Test basic combining of HANGUL CHOSEONG and JUNGSEONG
Example and from Raymond Chen's blog post,
https://devblogs.microsoft.com/oldnewthing/20201009-00/?p=104351
"""
# This is an example where both characters are "wide" when displayed alone.
#
# But JUNGSEONG (vowel) is designed for combination with a CHOSEONG (consonant).
#
# This wcwidth library understands their width only when combination,
# and not by independent display, like other zero-width characters that may
# only combine with an appropriate preceding character.
phrase = (
u"\u1100" # ᄀ HANGUL CHOSEONG KIYEOK (consonant)
u"\u1161" # ᅡ HANGUL JUNGSEONG A (vowel)
)
expect_length_each = (2, 0)
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:247:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 4352
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_kr_jamo_filler
test_core.py::test_kr_jamo_filler
def test_kr_jamo_filler():
u"""
Jamo filler is 0 width.
Example from https://www.unicode.org/L2/L2006/06310-hangul-decompose9.pdf
"""
phrase = (
u"\u1100" # HANGUL CHOSEONG KIYEOK (consonant)
u"\u1160" # HANGUL JUNGSEONG FILLER (vowel)
)
expect_length_each = (2, 0)
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:269:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 4352
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_devanagari_script
test_core.py::test_devanagari_script
def test_devanagari_script():
"""
Attempt to test the measurement width of Devanagari script.
I believe this 'phrase' should be length 3.
This is a difficult problem, and this library does not yet get it right,
because we interpret the unicode data files programmatically, but they do
not correctly describe how their terminal width is measured.
There are very few Terminals that do!
As of 2023,
- iTerm2: correct length but individual characters are out of order and
horizaontally misplaced as to be unreadable in its language when
using 'Noto Sans' font.
- mlterm: mixed results, it offers several options in the configuration
dialog, "Xft", "Cario", and "Variable Column Width" have some
effect, but with neither 'Noto Sans' or 'unifont', it is not
recognizable as the Devanagari script it is meant to display.
Previous testing with Devanagari documented at address https://benizi.com/vim/devanagari/
See also, https://askubuntu.com/questions/8437/is-there-a-good-mono-spaced-font-for-devanagari-script-in-the-terminal
"""
# This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf
# please note that document correctly points out that the final width cannot be determined
# as a sum of each individual width, as this library currently performs with exception of
# ZWJ, but I think it incorrectly gestures what a stateless call to wcwidth.wcwidth of
# each codepoint *should* return.
phrase = (u"\u0915" # Akhand, Category 'Lo', East Asian Width property 'N' -- DEVANAGARI LETTER KA
u"\u094D" # Joiner, Category 'Mn', East Asian Width property 'N' -- DEVANAGARI SIGN VIRAMA
u"\u0937" # Fused, Category 'Lo', East Asian Width property 'N' -- DEVANAGARI LETTER SSA
u"\u093F") # MatraL, Category 'Mc', East Asian Width property 'N' -- DEVANAGARI VOWEL SIGN I
# 23107-terminal-suppt.pdf suggests wcwidth.wcwidth should return (2, 0, 0, 1)
expect_length_each = (1, 0, 1, 0)
# I believe the final width *should* be 3.
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:318:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 2325
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_tamil_script
test_core.py::test_tamil_script
def test_tamil_script():
# This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf
phrase = (u"\u0b95" # Akhand, Category 'Lo', East Asian Width property 'N' -- TAMIL LETTER KA
u"\u0bcd" # Joiner, Category 'Mn', East Asian Width property 'N' -- TAMIL SIGN VIRAMA
u"\u0bb7" # Fused, Category 'Lo', East Asian Width property 'N' -- TAMIL LETTER SSA
u"\u0bcc") # MatraLR, Category 'Mc', East Asian Width property 'N' -- TAMIL VOWEL SIGN AU
# 23107-terminal-suppt.pdf suggests wcwidth.wcwidth should return (3, 0, 0, 4)
expect_length_each = (1, 0, 1, 0)
# I believe the final width should be about 5 or 6.
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:339:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 2965
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_kannada_script
test_core.py::test_kannada_script
def test_kannada_script():
# This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf
# |ರ್ಝೈ|
# |123|
phrase = (u"\u0cb0" # Repha, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER RA
u"\u0ccd" # Joiner, Category 'Mn', East Asian Width property 'N' -- KANNADA SIGN VIRAMA
u"\u0c9d" # Base, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER JHA
u"\u0cc8") # MatraUR, Category 'Mc', East Asian Width property 'N' -- KANNADA VOWEL SIGN AI
# 23107-terminal-suppt.pdf suggests should be (2, 0, 3, 1)
expect_length_each = (1, 0, 1, 0)
# I believe the correct final width *should* be 3 or 4.
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:361:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 3248
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_kannada_script_2
test_core.py::test_kannada_script_2
def test_kannada_script_2():
# This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf
# |ರ಼್ಚ|
# |12|
phrase = (u"\u0cb0" # Base, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER RA
u"\u0cbc" # Nukta, Category 'Mn', East Asian Width property 'N' -- KANNADA SIGN NUKTA
u"\u0ccd" # Joiner, Category 'Lo', East Asian Width property 'N' -- KANNADA SIGN VIRAMA
u"\u0c9a") # Subjoin, Category 'Mc', East Asian Width property 'N' -- KANNADA LETTER CA
# 23107-terminal-suppt.pdf suggests wcwidth.wcwidth should return (2, 0, 0, 1)
expect_length_each = (1, 0, 0, 1)
# I believe the final width is correct, but maybe for the wrong reasons!
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_core.py:383:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 3248
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_core.py::test_zero_wide_conflict
test_core.py::test_zero_wide_conflict
def test_zero_wide_conflict():
# Test characters considered both "wide" and "zero" width
# - (0x03000, 0x0303e,), # Ideographic Space ..Ideographic Variation In
# + (0x03000, 0x03029,), # Ideographic Space ..Hangzhou Numeral Nine
> assert wcwidth.wcwidth(unichr(0x03029), unicode_version='4.1.0') == 2
tests/test_core.py:395:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 12329
table = ((0, 0), (173, 173), (768, 879), (1155, 1158), (1160, 1161), (1425, 1465), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_emojis.py::test_unfinished_zwj_sequence
test_emojis.py::test_unfinished_zwj_sequence
@pytest.mark.skipif(NARROW_ONLY, reason="Test cannot verify on python 'narrow' builds")
def test_unfinished_zwj_sequence():
u"""
Ensure index-out-of-bounds does not occur for zero-width joiner without any following character
"""
phrase = (u"\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN
u"\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2
u"\u200d") # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER
expect_length_each = (2, 0, 0)
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_emojis.py:67:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 128105
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_emojis.py::test_non_recommended_zwj_sequence
test_emojis.py::test_non_recommended_zwj_sequence
@pytest.mark.skipif(NARROW_ONLY, reason="Test cannot verify on python 'narrow' builds")
def test_non_recommended_zwj_sequence():
"""
Verify ZWJ is measured as though successful with characters that cannot be joined, wcwidth does not verify
"""
phrase = (u"\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN
u"\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2
u"\u200d") # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER
expect_length_each = (2, 0, 0)
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_emojis.py:87:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 128105
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_emojis.py::test_another_emoji_zwj_sequence
test_emojis.py::test_another_emoji_zwj_sequence
@pytest.mark.skipif(NARROW_ONLY, reason="Test cannot verify on python 'narrow' builds")
def test_another_emoji_zwj_sequence():
phrase = (
u"\u26F9" # PERSON WITH BALL
u"\U0001F3FB" # EMOJI MODIFIER FITZPATRICK TYPE-1-2
u"\u200D" # ZERO WIDTH JOINER
u"\u2640" # FEMALE SIGN
u"\uFE0F") # VARIATION SELECTOR-16
expect_length_each = (1, 0, 0, 1, 0)
expect_length_phrase = 2
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_emojis.py:107:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 9977
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_emojis.py::test_longer_emoji_zwj_sequence
test_emojis.py::test_longer_emoji_zwj_sequence
@pytest.mark.skipif(NARROW_ONLY, reason="Test cannot verify on python 'narrow' builds")
def test_longer_emoji_zwj_sequence():
"""
A much longer emoji ZWJ sequence of 10 total codepoints is just 2 cells!
Also test the same sequence in duplicate, verifying multiple VS-16 sequences
in a single function call.
"""
# 'Category Code', 'East Asian Width property' -- 'description'
phrase = (u"\U0001F9D1" # 'So', 'W' -- ADULT
u"\U0001F3FB" # 'Sk', 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2
u"\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER
u"\u2764" # 'So', 'N' -- HEAVY BLACK HEART
u"\uFE0F" # 'Mn', 'A' -- VARIATION SELECTOR-16
u"\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER
u"\U0001F48B" # 'So', 'W' -- KISS MARK
u"\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER
u"\U0001F9D1" # 'So', 'W' -- ADULT
u"\U0001F3FD" # 'Sk', 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-4
) * 2
# This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf
expect_length_each = (2, 0, 0, 1, 0, 0, 2, 0, 2, 0) * 2
expect_length_phrase = 4
# exercise,
> length_each = tuple(map(wcwidth.wcwidth, phrase))
tests/test_emojis.py:140:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 129489
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_emojis.py::test_recommended_emoji_zwj_sequences
test_emojis.py::test_recommended_emoji_zwj_sequences
@pytest.mark.skipif(NARROW_ONLY, reason="Some sequences in text file are not compatible with 'narrow' builds")
def test_recommended_emoji_zwj_sequences():
"""
Test wcswidth of all of the unicode.org-published emoji-zwj-sequences.txt
"""
# given,
lines, sequences = read_sequences_from_file('emoji-zwj-sequences.txt')
errors = []
# Exercise, track by zipping with original text file line, a debugging aide
num = 0
for sequence, line in zip(sequences, lines):
num += 1
> measured_width = wcwidth.wcswidth(sequence)
tests/test_emojis.py:171:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:194: in wcswidth
char_width = wcwidth(char, unicode_version)
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 128104
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_emojis.py::test_recommended_variation_16_sequences
test_emojis.py::test_recommended_variation_16_sequences
def test_recommended_variation_16_sequences():
"""
Test wcswidth of all of the unicode.org-published emoji-variation-sequences.txt
"""
# given,
lines, sequences = read_sequences_from_file('emoji-variation-sequences.txt')
errors = []
num = 0
for sequence, line in zip(sequences, lines):
num += 1
if '\ufe0f' not in sequence:
# filter for only \uFE0F (VS-16)
continue
> measured_width = wcwidth.wcswidth(sequence)
tests/test_emojis.py:199:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
wcwidth/wcwidth.py:194: in wcswidth
char_width = wcwidth(char, unicode_version)
wcwidth/wcwidth.py:149: in wcwidth
if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ucs = 35
table = ((0, 0), (173, 173), (768, 879), (1155, 1161), (1425, 1469), (1471, 1471), ...)
def _bisearch(ucs, table):
"""
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
:arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
if not table:
return 0
# Binary search
min = 0
max = len(table) - 1
> ranges = table[latest_version]
E NameError: name 'latest_version' is not defined
wcwidth/wcwidth.py:93: NameError
test_emojis.py::test_unicode_9_vs16
test_emojis.py::test_unicode_9_vs16
def test_unicode_9_vs16():
"""Verify effect of VS-16 on unicode_version 9.0 and later"""
phrase = (u"\u2640" # FEMALE SIGN
u"\uFE0F") # VARIATION SELECTOR-16
expect_length_each = (1, 0)
expect_length_phrase = 2
# exercise,
> length_each = tuple(wcwidth.wcwidth(w_char, unicode_version='9.0') for w_char in phrase)
tests/test_emojis.py:222:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tests/test_emojis.py:222: in
length_each = tuple(wcwidth.wcwidth(w_char, unicode_version='9.0') for w_char in phrase)
wcwidth/wcwidth.py:142: in wcwidth
unicode_version = _wcmatch_version(unicode_version)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '9.0'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 9.0 not found, using 8.0.0
wcwidth/wcwidth.py:266: UserWarning
test_emojis.py::test_unicode_8_vs16
test_emojis.py::test_unicode_8_vs16
def test_unicode_8_vs16():
"""Verify that VS-16 has no effect on unicode_version 8.0 and earler"""
phrase = (u"\u2640" # FEMALE SIGN
u"\uFE0F") # VARIATION SELECTOR-16
expect_length_each = (1, 0)
expect_length_phrase = 1
# exercise,
> length_each = tuple(wcwidth.wcwidth(w_char, unicode_version='8.0') for w_char in phrase)
tests/test_emojis.py:238:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tests/test_emojis.py:238: in
length_each = tuple(wcwidth.wcwidth(w_char, unicode_version='8.0') for w_char in phrase)
wcwidth/wcwidth.py:142: in wcwidth
unicode_version = _wcmatch_version(unicode_version)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '8.0'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 8.0 not found, using 7.0.0
wcwidth/wcwidth.py:266: UserWarning
test_ucslevel.py::test_nearest_505_str
test_ucslevel.py::test_nearest_505_str
def test_nearest_505_str():
"""wcwidth._wcmatch_version('5.0.5') returns nearest '5.0.0'. (str)"""
# given
given, expected = '5.0.5', '5.0.0'
# exercise
> result = wcwidth._wcmatch_version(given)
tests/test_ucslevel.py:55:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '5.0.5'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 5.0.5 not found, using 5.0.0
wcwidth/wcwidth.py:266: UserWarning
test_ucslevel.py::test_nearest_505_unicode
test_ucslevel.py::test_nearest_505_unicode
def test_nearest_505_unicode():
"""wcwidth._wcmatch_version(u'5.0.5') returns nearest u'5.0.0'. (unicode)"""
# given
given, expected = u'5.0.5', u'5.0.0'
# exercise
> result = wcwidth._wcmatch_version(given)
tests/test_ucslevel.py:67:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '5.0.5'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 5.0.5 not found, using 5.0.0
wcwidth/wcwidth.py:266: UserWarning
test_ucslevel.py::test_nearest_800_str
test_ucslevel.py::test_nearest_800_str
def test_nearest_800_str():
"""wcwidth._wcmatch_version('8') returns nearest '8.0.0'."""
# given
given, expected = '8', '8.0.0'
# exercise
> result = wcwidth._wcmatch_version(given)
tests/test_ucslevel.py:111:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '8'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 8 not found, using 7.0.0
wcwidth/wcwidth.py:266: UserWarning
test_ucslevel.py::test_nearest_800_unicode
test_ucslevel.py::test_nearest_800_unicode
def test_nearest_800_unicode():
"""wcwidth._wcmatch_version(u'8') returns nearest u'8.0.0'."""
# given
given, expected = u'8', u'8.0.0'
# exercise
> result = wcwidth._wcmatch_version(given)
tests/test_ucslevel.py:123:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '8'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 8 not found, using 7.0.0
wcwidth/wcwidth.py:266: UserWarning
test_ucslevel.py::test_nearest_999_str
test_ucslevel.py::test_nearest_999_str
def test_nearest_999_str():
"""wcwidth._wcmatch_version('999.0') returns nearest (latest)."""
# given
given, expected = '999.0', wcwidth.list_versions()[-1]
# exercise
> result = wcwidth._wcmatch_version(given)
tests/test_ucslevel.py:135:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '999.0'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 999.0 not found, using 15.1.0
wcwidth/wcwidth.py:266: UserWarning
test_ucslevel.py::test_nearest_999_unicode
test_ucslevel.py::test_nearest_999_unicode
def test_nearest_999_unicode():
"""wcwidth._wcmatch_version(u'999.0') returns nearest (latest)."""
# given
given, expected = u'999.0', wcwidth.list_versions()[-1]
# exercise
> result = wcwidth._wcmatch_version(given)
tests/test_ucslevel.py:147:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
given_version = '999.0'
@lru_cache(maxsize=8)
def _wcmatch_version(given_version):
"""
Return nearest matching supported Unicode version level.
If an exact match is not determined, the nearest lowest version level is
returned after a warning is emitted. For example, given supported levels
``4.1.0`` and ``5.0.0``, and a version string of ``4.9.9``, then ``4.1.0``
is selected and returned:
>>> _wcmatch_version('4.9.9')
'4.1.0'
>>> _wcmatch_version('8.0')
'8.0.0'
>>> _wcmatch_version('1')
'4.1.0'
:param str given_version: given version for compare, may be ``auto``
(default), to select Unicode Version from Environment Variable,
``UNICODE_VERSION``. If the environment variable is not set, then the
latest is used.
:rtype: str
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
if given_version == 'auto':
given_version = os.environ.get('UNICODE_VERSION', 'latest')
if given_version == 'latest':
return list_versions()[-1]
supported_versions = list_versions()
try:
given_value = _wcversion_value(given_version)
except ValueError:
warnings.warn(f"Invalid Unicode version {given_version}, using latest")
return supported_versions[-1]
nearest_version = None
for version in reversed(supported_versions):
if _wcversion_value(version) <= given_value:
nearest_version = version
break
if nearest_version is None:
nearest_version = supported_versions[0]
if nearest_version != given_version:
if _wcversion_value(nearest_version) < given_value:
> warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
E UserWarning: Unicode version 999.0 not found, using 15.1.0
wcwidth/wcwidth.py:266: UserWarning
Patch diff
diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py
index cc437d7..a99f4fc 100644
--- a/wcwidth/unicode_versions.py
+++ b/wcwidth/unicode_versions.py
@@ -15,4 +15,24 @@ def list_versions():
:returns: Supported Unicode version numbers in ascending sorted order.
:rtype: list[str]
"""
- pass
+ return [
+ '4.1.0',
+ '5.0.0',
+ '5.1.0',
+ '5.2.0',
+ '6.0.0',
+ '6.1.0',
+ '6.2.0',
+ '6.3.0',
+ '7.0.0',
+ '8.0.0',
+ '9.0.0',
+ '10.0.0',
+ '11.0.0',
+ '12.0.0',
+ '12.1.0',
+ '13.0.0',
+ '14.0.0',
+ '15.0.0',
+ '15.1.0',
+ ]
diff --git a/wcwidth/wcwidth.py b/wcwidth/wcwidth.py
index 6d93a59..2aca6b0 100644
--- a/wcwidth/wcwidth.py
+++ b/wcwidth/wcwidth.py
@@ -80,12 +80,37 @@ def _bisearch(ucs, table):
Auxiliary function for binary search in interval table.
:arg int ucs: Ordinal value of unicode character.
- :arg list table: List of starting and ending ranges of ordinal values,
- in form of ``[(start, end), ...]``.
+ :arg tuple table: Tuple of (start, end) ranges of ordinal values.
:rtype: int
:returns: 1 if ordinal value ucs is found within lookup table, else 0.
"""
- pass
+ if not table:
+ return 0
+
+ # Binary search
+ min = 0
+ max = len(table) - 1
+ ranges = table[latest_version]
+
+ if not ranges:
+ return 0
+
+ lbound = 0
+ ubound = len(ranges) - 1
+
+ if ucs < ranges[0][0] or ucs > ranges[-1][1]:
+ return 0
+
+ while ubound >= lbound:
+ mid = (lbound + ubound) // 2
+ if ucs > ranges[mid][1]:
+ lbound = mid + 1
+ elif ucs < ranges[mid][0]:
+ ubound = mid - 1
+ else:
+ return 1
+
+ return 0
@lru_cache(maxsize=1000)
@@ -111,7 +136,33 @@ def wcwidth(wc, unicode_version='auto'):
See :ref:`Specification` for details of cell measurement.
"""
- pass
+ if not wc:
+ return 0
+ ucs = ord(wc) if isinstance(wc, str) else wc
+ unicode_version = _wcmatch_version(unicode_version)
+
+ # C0/C1 control characters
+ if ucs < 32 or 0x07F <= ucs < 0x0A0:
+ return -1
+
+ # check for zero width characters
+ if _bisearch(ucs, ZERO_WIDTH[unicode_version]):
+ return 0
+
+ # check for wide characters
+ if _bisearch(ucs, WIDE_EASTASIAN[unicode_version]):
+ return 2
+
+ # check for variation selectors
+ if 0xfe00 <= ucs <= 0xfe0f:
+ return 0
+
+ # check for special wide characters in VS16 table
+ if ucs in VS16_NARROW_TO_WIDE:
+ return 2
+
+ # all others are considered single width
+ return 1
def wcswidth(pwcs, n=None, unicode_version='auto'):
@@ -135,7 +186,17 @@ def wcswidth(pwcs, n=None, unicode_version='auto'):
See :ref:`Specification` for details of cell measurement.
"""
- pass
+ if n is None:
+ n = len(pwcs)
+
+ width = 0
+ for char in pwcs[:n]:
+ char_width = wcwidth(char, unicode_version)
+ if char_width < 0:
+ return -1
+ width += char_width
+
+ return width
@lru_cache(maxsize=128)
@@ -147,7 +208,10 @@ def _wcversion_value(ver_string):
:rtype: tuple(int)
:returns: tuple of digit tuples, ``tuple(int, [...])``.
"""
- pass
+ try:
+ return tuple(int(n) for n in ver_string.split('.'))
+ except ValueError:
+ raise ValueError(f"Invalid version string: {ver_string}")
@lru_cache(maxsize=8)
@@ -175,4 +239,32 @@ def _wcmatch_version(given_version):
:returns: unicode string, or non-unicode ``str`` type for python 2
when given ``version`` is also type ``str``.
"""
- pass
+ if given_version == 'auto':
+ given_version = os.environ.get('UNICODE_VERSION', 'latest')
+
+ if given_version == 'latest':
+ return list_versions()[-1]
+
+ supported_versions = list_versions()
+ try:
+ given_value = _wcversion_value(given_version)
+ except ValueError:
+ warnings.warn(f"Invalid Unicode version {given_version}, using latest")
+ return supported_versions[-1]
+
+ nearest_version = None
+ for version in reversed(supported_versions):
+ if _wcversion_value(version) <= given_value:
+ nearest_version = version
+ break
+
+ if nearest_version is None:
+ nearest_version = supported_versions[0]
+
+ if nearest_version != given_version:
+ if _wcversion_value(nearest_version) < given_value:
+ warnings.warn(f"Unicode version {given_version} not found, using {nearest_version}")
+ elif _wcversion_value(nearest_version) > given_value:
+ warnings.warn(f"Unicode version {given_version} is lower than any supported version, using {nearest_version}")
+
+ return nearest_version