summaryrefslogtreecommitdiffstats
path: root/contrib/python/wcwidth/py3/tests/test_textwrap.py
blob: 33da72a4fa98261ce1f2dfbb3976d52aa89204d3 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
"""Tests for sequence-aware text wrapping functions."""

# std imports
import sys
import platform
import textwrap

# 3rd party
import pytest

# local
from wcwidth import iter_sequences
from wcwidth.textwrap import SequenceTextWrapper, wrap


@pytest.fixture(autouse=True)
def mock_hyperlink_ids(monkeypatch):
    """Mock secrets.token_hex to return predictable IDs for testing."""
    counter = 0

    def fake_token_hex(n):
        nonlocal counter
        counter += 1
        return f'{counter:0{n * 2}x}'

    monkeypatch.setattr('secrets.token_hex', fake_token_hex)


SGR_RED = '\x1b[31m'
SGR_BOLD = '\x1b[1m'
SGR_RESET = '\x1b[0m'
ATTRS = ('\x1b[31m', '\x1b[34m', '\x1b[4m', '\x1b[7m', '\x1b[41m', '\x1b[37m', '\x1b[107m')

OSC_HYPERLINK = '\x1b]8;;https://example.com\x07link\x1b]8;;\x07'
CSI_CURSOR = '\x1b[5C'
CTRL_BEL = '\x07'

ZWJ = '\u200d'
WOMAN = '\U0001F469'
GIRL = '\U0001F467'
FAMILY_ZWJ = f'{WOMAN}{ZWJ}{WOMAN}{ZWJ}{GIRL}'
SMILEY_VS16 = '\u263a\ufe0f'
ZWJ_FAMILY = '\U0001F469\u200D\U0001F469\u200D\U0001F467\u200D\U0001F466'
CAFE_COMBINING = 'cafe\u0301'
HANGUL_GA = '\u1100\u1161'


def _strip(text):
    return ''.join(seg for seg, is_seq in iter_sequences(text) if not is_seq)


def _adjust_stdlib_result(expected, kwargs):
    """
    Adjust stdlib textwrap result for known bugs in older Python versions.

    CPython #140627: Older versions leave trailing whitespace and preceding all-whitespace lines
    when drop_whitespace=True. Fixed in 3.13.11+, 3.14.2+, and 3.15+. We always strip to normalize
    across versions.
    """
    if not expected:
        return expected
    if kwargs.get('drop_whitespace', True):
        # Strip trailing whitespace from each line (old Python bug)
        expected = [line.rstrip() for line in expected]
        # Remove leading all-whitespace lines (old Python bug)
        if expected and not expected[0].strip():
            expected = expected[1:]
            if expected and kwargs.get('subsequent_indent'):
                expected[0] = expected[0][len(kwargs['subsequent_indent']):]
    return expected


def _colorize(text):
    return ''.join(
        ATTRS[idx % len(ATTRS)] + char + SGR_RESET if char not in ' -\t' else char
        for idx, char in enumerate(text)
    )


@pytest.mark.parametrize('text,w,expected', [
    ('', 10, []),
    ('   ', 10, []),
    ('\u5973', 0, ['\u5973']),
    ('\u5973', 1, ['\u5973']),
    (ZWJ_FAMILY, 1, [ZWJ_FAMILY]),
    (HANGUL_GA, 1, [HANGUL_GA]),
])
def test_wrap_edge_cases(text, w, expected):
    assert wrap(text, w) == expected


def test_wrap_initial_indent():
    assert wrap('hello world', 10, initial_indent='> ') == ['> hello', 'world']


@pytest.mark.parametrize('text,w,break_long,expected', [
    ('abcdefghij', 3, True, ['abc', 'def', 'ghi', 'j']),
    ('abcdefghij', 3, False, ['abcdefghij']),
])
def test_wrap_long_words(text, w, break_long, expected):
    assert wrap(text, w, break_long_words=break_long) == expected


@pytest.mark.parametrize('text,w,break_hyphens,propagate,expected', [
    ('a-b-c-d', 3, True, True, ['a-', 'b-', 'c-d']),
    ('a-b-c-d', 3, False, True, ['a-b', '-c-', 'd']),
    ('---', 2, True, True, ['--', '-']),
    ('a---b', 2, True, True, ['a-', '--', 'b']),
    ('a-\x1b[31mb', 2, True, True, ['a-\x1b[31m\x1b[0m', '\x1b[31mb\x1b[0m']),
    ('a-\x1b[31mb', 2, True, False, ['a-\x1b[31m', 'b']),
])
def test_wrap_hyphen_long_words(text, w, break_hyphens, propagate, expected):
    assert wrap(text, w, break_on_hyphens=break_hyphens, propagate_sgr=propagate) == expected


# Comprehensive stdlib compatibility
TEXTWRAP_KWARGS = [
    {'break_long_words': False, 'drop_whitespace': False},
    {'break_long_words': False, 'drop_whitespace': True},
    {'break_long_words': True, 'drop_whitespace': False},
    {'break_long_words': True, 'drop_whitespace': True},
    {'break_long_words': True, 'drop_whitespace': False, 'subsequent_indent': ' '},
    {'break_long_words': True, 'drop_whitespace': True, 'subsequent_indent': ' '},
    {'break_long_words': True, 'drop_whitespace': True, 'break_on_hyphens': True},
    {'break_long_words': True, 'drop_whitespace': True, 'break_on_hyphens': False},
    {'break_long_words': True, 'drop_whitespace': False,
     'subsequent_indent': '', 'max_lines': 4, 'placeholder': '~'},
    {'break_long_words': True, 'drop_whitespace': True,
     'max_lines': 3, 'placeholder': '...'},
    {'break_long_words': True, 'drop_whitespace': True,
     'max_lines': 1, 'placeholder': '...'},
    {'expand_tabs': False, 'break_long_words': True, 'drop_whitespace': True},
    {'replace_whitespace': False, 'break_long_words': True,
     'drop_whitespace': True},
    {'fix_sentence_endings': True, 'break_long_words': True,
     'drop_whitespace': True},
]


@pytest.mark.parametrize('kwargs', TEXTWRAP_KWARGS)
@pytest.mark.parametrize('width', [3, 8, 20, 33])
def test_wrap_matches_stdlib(kwargs, width):
    pgraph = ' Z! a bc defghij klmnopqrstuvw<<>>xyz012345678900 ' * 2
    pgraph_colored = _colorize(pgraph)
    expected = _adjust_stdlib_result(
        textwrap.wrap(pgraph, width=width, **kwargs), kwargs
    )
    wrapper = SequenceTextWrapper(width=width, **kwargs)
    assert wrapper.wrap(pgraph) == expected
    # For colored text, strip sequences
    colored_result = [_strip(line) for line in wrapper.wrap(pgraph_colored)]
    if kwargs.get('drop_whitespace'):
        # normalize trailing whitespace, rstrip when drop_whitespace is True
        # matches CPython #140627 fix
        colored_result = [line.rstrip() for line in colored_result]
    assert colored_result == expected


@pytest.mark.parametrize('kwargs', TEXTWRAP_KWARGS)
@pytest.mark.parametrize('width', [8, 20, 37])
@pytest.mark.parametrize('tabsize', [4, 5, 8])
def test_wrap_tabsize_matches_stdlib(kwargs, width, tabsize):
    tabsize = min(tabsize, width)
    pgraph = ' Z! a bc\t defghij\t kl mnopqrs\ttuvw<<>>xyz012345678900 ' * 2
    expected = _adjust_stdlib_result(
        textwrap.wrap(pgraph, width=width, tabsize=tabsize, **kwargs), kwargs
    )
    wrapper = SequenceTextWrapper(width=width, tabsize=tabsize, **kwargs)
    assert wrapper.wrap(pgraph) == expected


def test_wrap_multiline_matches_stdlib():
    given = '\n' + 32 * 'A' + '\n' + 32 * 'B' + '\n' + 32 * 'C' + '\n\n'
    assert wrap(given, 30) == textwrap.wrap(given, 30)


@pytest.mark.parametrize('text,w,expected', [
    # CJK (2 cells each)
    ('\u4e2d\u6587\u5b57\u7b26', 4, ['\u4e2d\u6587', '\u5b57\u7b26']),
    ('\u4e2d\u6587\u5b57', 5, ['\u4e2d\u6587', '\u5b57']),
    # Combining characters
    (CAFE_COMBINING + '-latte', 4, ['cafe\u0301', '-lat', 'te']),
    # Emoji (ZWJ, VS16)
    (f'{FAMILY_ZWJ} ab', 4, [FAMILY_ZWJ, 'ab']),
    (f'{SMILEY_VS16} ab', 3, [SMILEY_VS16, 'ab']),
    ('\U0001F469\U0001F467\U0001F466', 4, ['\U0001F469\U0001F467', '\U0001F466']),
])
def test_wrap_unicode(benchmark, text, w, expected):
    kwargs = {'break_on_hyphens': False} if '-' in text else {}
    result = benchmark(wrap, text, w, **kwargs)
    assert result == expected


@pytest.mark.parametrize('text,w,expected', [
    # SGR sequences propagated across lines
    (f'{SGR_RED}red{SGR_RESET} blue', 4, [f'{SGR_RED}red{SGR_RESET}', 'blue']),
    # SGR at end of line propagates to next line
    (f'hello{SGR_RED} world', 6, [f'hello{SGR_RED}{SGR_RESET}', f'{SGR_RED}world{SGR_RESET}']),
    # Empty/adjacent sequences - sequences kept (no visible content)
    (f'{SGR_RED}{SGR_RESET}', 10, [f'{SGR_RED}{SGR_RESET}']),
    # Reset clears style, sequences kept with second line
    (f'hello {SGR_RED}{SGR_RESET}world', 6, ['hello', f'{SGR_RED}{SGR_RESET}world']),
    # OSC hyperlinks (with space separator) - not SGR, so preserved as-is
    (f'{OSC_HYPERLINK} text', 5, [OSC_HYPERLINK, 'text']),
    # CSI cursor sequences - not SGR, so preserved as-is
    (f'{CSI_CURSOR}text here', 10, [f'{CSI_CURSOR}text', 'here']),
    # Control characters
    (f'{CTRL_BEL}alert text', 6, [f'{CTRL_BEL}alert', 'text']),
    # Sequences in long word breaking - red starts after 'x', continues across lines
    ('x\x1b[31mabcdefghij\x1b[0m', 3,
     ['x\x1b[31mab\x1b[0m', '\x1b[31mcde\x1b[0m', '\x1b[31mfgh\x1b[0m', '\x1b[31mij\x1b[0m']),
    # Fs sequence (ESC d) - zero-width, stays with preceding text
    ('abc\x1bdefghij', 3, ['abc\x1bd', 'efg', 'hij']),
])
def test_wrap_sequences(benchmark, text, w, expected):
    """Escape sequence preservation (with propagate_sgr=True default)"""
    assert benchmark(wrap, text, w) == expected


@pytest.mark.parametrize('text,w,expected', [
    (f'hello{SGR_RED} world', 6, [f'hello{SGR_RED}', 'world']),
    ('x\x1b[31mabcdefghij\x1b[0m', 3, ['x\x1b[31mab', 'cde', 'fgh', 'ij\x1b[0m']),
]
)
def test_wrap_sequences_no_propagate(text, w, expected):
    result = wrap(text, w, propagate_sgr=False)
    assert result == expected


@pytest.mark.parametrize('text,w,expected', [
    (f'{SGR_RED}\u4e2d\u6587{SGR_RESET} ab', 5, [f'{SGR_RED}\u4e2d\u6587{SGR_RESET}', 'ab']),
    (f'{SGR_RED}{FAMILY_ZWJ}{SGR_RESET} ab', 4, [f'{SGR_RED}{FAMILY_ZWJ}{SGR_RESET}', 'ab']),
    (f'{SGR_BOLD}\u4e2d{SGR_RESET}y z', 4, [f'{SGR_BOLD}\u4e2d{SGR_RESET}y', 'z']),
])
def test_wrap_mixed(benchmark, text, w, expected):
    """Test mixed sequences + unicode."""
    result = benchmark(wrap, text, w)
    assert result == expected


@pytest.mark.parametrize('text,w,tabsize,expected', [
    # CJK (2 cells) + tab: tabsize=4, '\u4e2d' is 2 cols, tab expands to col 4
    ('\u4e2d\ta b', 6, 4, ['\u4e2d   a', 'b']),
    # CJK + tab with tabsize=8: '\u4e2d' is 2 cols, tab expands to col 8
    ('\u4e2d\ta b', 10, 8, ['\u4e2d       a', 'b']),
    # Emoji + tab (emoji width=2): similar column alignment
    (f'{SMILEY_VS16}\ta b', 6, 4, [f'{SMILEY_VS16}  a', 'b']),
    # Multiple CJK + tab: 4 cols, tab to 4 adds 0, but expand_tabs adds min 1
    ('\u4e2d\u6587\ta', 8, 4, ['\u4e2d\u6587  a']),
    # ASCII + tab + CJK: 'a' is 1 col, tab to 4 (3 spaces), CJK is 2 cols
    ('a\t\u4e2d b', 8, 4, ['a   \u4e2d b']),
])
@pytest.mark.skipif(
    platform.python_implementation() == 'PyPy' and sys.version_info < (3, 9),
    reason='PyPy 3.8 str.expandtabs() counts UTF-8 bytes instead of characters'
)
def test_wrap_tabsize_wide_chars(text, w, tabsize, expected):
    """Verify tabsize respects wide character column positions."""
    assert wrap(text, w, tabsize=tabsize) == expected


OSC_START_ST = '\x1b]8;;http://example.com\x1b\\'
OSC_END_ST = '\x1b]8;;\x1b\\'
OSC_START_BEL = '\x1b]8;;http://example.com\x07'
OSC_END_BEL = '\x1b]8;;\x07'


@pytest.mark.parametrize('text,w,expected', [
    (   # standard, ST-variant,
        f'{OSC_START_ST}link{OSC_END_ST}more',
        5,
        [f'{OSC_START_ST}link{OSC_END_ST}', 'more'],
    ),
    (   # BEL-variant,
        f'{OSC_START_BEL}link{OSC_END_BEL}more',
        5,
        [f'{OSC_START_BEL}link{OSC_END_BEL}', 'more'],
    ),
    (   # hyperlink breaks after word, 'prefix',
        f'prefix{OSC_START_ST}link{OSC_END_ST}',
        6,
        ['prefix', f'{OSC_START_ST}link{OSC_END_ST}'],
    ),
    (
        f'prefix{OSC_START_BEL}link{OSC_END_BEL}',
        6,
        ['prefix', f'{OSC_START_BEL}link{OSC_END_BEL}'],
    ),
    (   # hyperlink breaks before following, 'suffix',
        f'prefix{OSC_START_ST}link{OSC_END_ST}suffix',
        6,
        ['prefix', f'{OSC_START_ST}link{OSC_END_ST}', 'suffix'],
    ),
    (
        f'prefix{OSC_START_BEL}link{OSC_END_BEL}suffix',
        6,
        ['prefix', f'{OSC_START_BEL}link{OSC_END_BEL}', 'suffix'],
    ),
    (   # hyperlink *surrounded* by SGR attributes
        f'foo {SGR_RED}{OSC_START_ST}link{OSC_END_ST}{SGR_RESET} bar',
        6,
        ['foo', f'{SGR_RED}{OSC_START_ST}link{OSC_END_ST}{SGR_RESET}', 'bar'],
    ),
    (
        f'foo {SGR_RED}{OSC_START_BEL}link{OSC_END_BEL}{SGR_RESET} bar',
        6,
        ['foo', f'{SGR_RED}{OSC_START_BEL}link{OSC_END_BEL}{SGR_RESET}', 'bar'],
    ),
    (   # hyperlink *containing* SGR attributes
        f'foo {OSC_START_ST}{SGR_RED}link{SGR_RESET}{OSC_END_ST} bar',
        6,
        ['foo', f'{OSC_START_ST}{SGR_RED}link{SGR_RESET}{OSC_END_ST}', 'bar'],
    ),
    (
        f'foo {OSC_START_BEL}{SGR_RED}link{SGR_RESET}{OSC_END_BEL} bar',
        6,
        ['foo', f'{OSC_START_BEL}{SGR_RED}link{SGR_RESET}{OSC_END_BEL}', 'bar'],
    ),
    (   # hyperlink with internal space - breaks with id continuation (ST)
        f'Go {OSC_START_ST}Click here{OSC_END_ST} now',
        5,
        [
            'Go',
            '\x1b]8;id=00000001;http://example.com\x1b\\Click\x1b]8;;\x1b\\',
            '\x1b]8;id=00000001;http://example.com\x1b\\here\x1b]8;;\x1b\\',
            'now',
        ],
    ),
    (   # hyperlink with internal space - breaks with id continuation (BEL)
        f'Go {OSC_START_BEL}Click here{OSC_END_BEL} now',
        5,
        [
            'Go',
            '\x1b]8;id=00000001;http://example.com\x07Click\x1b]8;;\x07',
            '\x1b]8;id=00000001;http://example.com\x07here\x1b]8;;\x07',
            'now',
        ],
    ),
    (   # hyperlink with existing id= parameter is preserved
        '\x1b]8;id=my-link;http://example.com\x1b\\Click here\x1b]8;;\x1b\\',
        6,
        [
            '\x1b]8;id=my-link;http://example.com\x1b\\Click\x1b]8;;\x1b\\',
            '\x1b]8;id=my-link;http://example.com\x1b\\here\x1b]8;;\x1b\\',
        ],
    ),
    (   # hyperlink spanning 3+ lines
        f'{OSC_START_ST}one two three{OSC_END_ST}',
        5,
        [
            '\x1b]8;id=00000001;http://example.com\x1b\\one\x1b]8;;\x1b\\',
            '\x1b]8;id=00000001;http://example.com\x1b\\two\x1b]8;;\x1b\\',
            '\x1b]8;id=00000001;http://example.com\x1b\\three\x1b]8;;\x1b\\',
        ],
    ),
    (   # multiple hyperlinks in same text
        f'{OSC_START_ST}ab cd{OSC_END_ST} {OSC_START_BEL}ef gh{OSC_END_BEL}',
        4,
        [
            '\x1b]8;id=00000001;http://example.com\x1b\\ab\x1b]8;;\x1b\\',
            '\x1b]8;id=00000001;http://example.com\x1b\\cd\x1b]8;;\x1b\\',
            '\x1b]8;id=00000002;http://example.com\x07ef\x1b]8;;\x07',
            '\x1b]8;id=00000002;http://example.com\x07gh\x1b]8;;\x07',
        ],
    ),
    (   # long word inside hyperlink forces character-level breaking
        f'{OSC_START_ST}abcdefgh{OSC_END_ST}',
        3,
        [
            '\x1b]8;id=00000001;http://example.com\x1b\\abc\x1b]8;;\x1b\\',
            '\x1b]8;id=00000001;http://example.com\x1b\\def\x1b]8;;\x1b\\',
            '\x1b]8;id=00000001;http://example.com\x1b\\gh\x1b]8;;\x1b\\',
        ],
    ),
    (   # params with other keys but no id - id is prepended, other params preserved
        '\x1b]8;foo=bar;http://example.com\x1b\\Click here\x1b]8;;\x1b\\',
        6,
        [
            '\x1b]8;id=00000001:foo=bar;http://example.com\x1b\\Click\x1b]8;;\x1b\\',
            '\x1b]8;id=00000001:foo=bar;http://example.com\x1b\\here\x1b]8;;\x1b\\',
        ],
    ),
    (   # id not at start of params (junk:id=given) - full params preserved
        '\x1b]8;foo=bar:id=mylink;http://example.com\x1b\\Click here\x1b]8;;\x1b\\',
        6,
        [
            '\x1b]8;foo=bar:id=mylink;http://example.com\x1b\\Click\x1b]8;;\x1b\\',
            '\x1b]8;foo=bar:id=mylink;http://example.com\x1b\\here\x1b]8;;\x1b\\',
        ],
    ),])
def test_wrap_hyperlink_word_boundary(text, w, expected):
    """OSC hyperlink sequences should act as word boundaries."""
    result = wrap(text, w)
    assert result == expected


@pytest.mark.parametrize('text,kwargs', [
    ('The quick brown fox jumps over the lazy dog',
     {'width': 10, 'max_lines': 3, 'placeholder': '...'}),
    ('1234567890 1234567890 extra',
     {'width': 10, 'max_lines': 2, 'placeholder': '...'}),
    ('1234567890 1234567890',
     {'width': 10, 'max_lines': 1, 'placeholder': '...'}),
    ('short 1234567890 extra',
     {'width': 10, 'max_lines': 2, 'placeholder': '...'}),
    ('hello world',
     {'width': 10, 'max_lines': 5, 'placeholder': '...'}),
    ('hello world foo bar baz',
     {'width': 8, 'max_lines': 2, 'placeholder': ' [...]'}),
    ('a bb ccc',
     {'width': 3, 'max_lines': 2, 'placeholder': '.'}),
    ('a bb ccc dddd',
     {'width': 4, 'max_lines': 3, 'placeholder': '~'}),
    (' a ', {'width': 1, 'max_lines': 2, 'drop_whitespace': False, 'placeholder': '~'}),
    ('hello world', {'width': 20, 'max_lines': 5}),
    ('ab cd', {'width': 5, 'max_lines': 1}),
    ('aaa bbb ccc', {'width': 3, 'max_lines': 2, 'placeholder': '...'}),
    ('hello world foo bar',
     {'width': 10, 'subsequent_indent': '  ', 'max_lines': 2, 'placeholder': '...'}),
    ('hello world foo bar',
     {'width': 10, 'initial_indent': '> ', 'max_lines': 2, 'placeholder': '...'}),
])
def test_wrap_max_lines_matches_stdlib(text, kwargs):
    expected = _adjust_stdlib_result(textwrap.wrap(text, **kwargs), kwargs)
    assert wrap(text, **kwargs) == expected


def test_wrap_placeholder_too_large():
    with pytest.raises(ValueError, match="placeholder too large"):
        wrap('hello', width=3, max_lines=1, placeholder='.....')
    with pytest.raises(ValueError):
        textwrap.wrap('fox', width=1, max_lines=3, placeholder='...')


@pytest.mark.parametrize('text,w,ml,ph,expected', [
    (f'{SGR_RED}hello world foo bar{SGR_RESET}',
     8, 2, '...', [f'{SGR_RED}hello{SGR_RESET}', f'{SGR_RED}world...{SGR_RESET}']),
    (f'{SGR_RED}hello{SGR_RESET} world foo',
     8, 2, '...', [f'{SGR_RED}hello{SGR_RESET}', 'world...']),
    (f'{SGR_RED}hello{SGR_RESET} world',
     6, 1, '.', [f'{SGR_RED}hello{SGR_RESET}.']),
    ('\u4e2d\u6587 \u5b57\u7b26 hello', 5, 1, '~', ['\u4e2d\u6587~']),
    ('\u4e2d\u6587 \u5b57\u7b26 hello world', 5, 2, '~', ['\u4e2d\u6587', '\u5b57\u7b26~']),
    ('\u4e2d\u6587\u5b57\u7b26 hello', 12, 1, '...', ['\u4e2d\u6587\u5b57\u7b26...']),
])
def test_wrap_max_lines_sequences(text, w, ml, ph, expected):
    assert wrap(text, w, max_lines=ml, placeholder=ph) == expected


def test_wrap_max_lines_hyperlink_closed():
    """Truncation inside a hyperlink closes it before the placeholder."""
    text = f'{OSC_START_ST}Click here please{OSC_END_ST}'
    result = wrap(text, 10, max_lines=1, placeholder='...')
    assert len(result) == 1
    assert result[0].endswith(f'{OSC_END_ST}...')
    assert OSC_START_ST in result[0]


def test_wrap_max_lines_hyperlink_close_on_prev_line():
    """Fallback to previous line preserves hyperlink close sequence."""
    text = f'{OSC_START_ST}ab{OSC_END_ST} cccccccccc ddddd'
    result = wrap(text, 10, max_lines=2, placeholder='...')
    assert result == [f'{OSC_START_ST}ab{OSC_END_ST}...']


@pytest.mark.parametrize('text,kwargs', [
    ('hello\tworld', {'width': 20, 'expand_tabs': False, 'replace_whitespace': False}),
    ('hello\tworld foo\tbar baz', {'width': 12, 'expand_tabs': False, 'tabsize': 8}),
    ('hello\nworld', {'width': 20, 'replace_whitespace': False}),
    ('a\t b\n c', {'width': 20, 'replace_whitespace': False}),
    ('Hello world. This is a test.  More text.', {'width': 20, 'fix_sentence_endings': True}),
    ('Dr. Smith went to Washington. He left.', {'width': 20, 'fix_sentence_endings': True}),
])
def test_wrap_stdlib_params(text, kwargs):
    assert wrap(text, **kwargs) == textwrap.wrap(text, **kwargs)


def test_wrap_expand_tabs_false_with_sequences():
    text = f'{SGR_RED}a\tb{SGR_RESET}'
    result = wrap(text, 20, expand_tabs=False, replace_whitespace=False)
    assert '\t' in _strip(result[0])


def test_wrap_replace_whitespace_false_newlines_zero_width():
    """Newlines have zero display width, so more text fits per line than stdlib."""
    assert wrap('hello\nworld foo\nbar', 10, replace_whitespace=False) == [
        'hello\nworld', 'foo\nbar']


def test_wrap_bare_esc():
    """Bare ESC not part of a recognized sequence is treated as zero-width."""
    assert wrap('ab\x1bcd ef', 5) == ['ab\x1bcd', 'ef']
    assert wrap('ab\x1b\x00cdef', 3) == ['ab\x1b\x00c', 'def']