/usr/lib/python2.7/dist-packages/openpyxl/formula/tests/test_tokenizer.py is in python-openpyxl 2.3.0-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | from __future__ import absolute_import
import pytest
@pytest.fixture
def tokenizer():
from .. import tokenizer
return tokenizer
# Constants from tokenizer.Token:
LITERAL = "LITERAL"
OPERAND = "OPERAND"
FUNC = "FUNC"
ARRAY = "ARRAY"
PAREN = "PAREN"
SEP = "SEP"
OP_PRE = "OPERATOR-PREFIX"
OP_IN = "OPERATOR-INFIX"
OP_POST = "OPERATOR-POSTFIX"
WSPACE = "WHITE-SPACE"
TEXT = 'TEXT'
NUMBER = 'NUMBER'
LOGICAL = 'LOGICAL'
ERROR = 'ERROR'
RANGE = 'RANGE'
OPEN = "OPEN"
CLOSE = "CLOSE"
ARG = "ARG"
ROW = "ROW"
class TestTokenizerRegexes(object):
@pytest.mark.parametrize("string, success", [
('1.0E', True),
('1.53321E', True),
('9.999E', True),
('3E', True),
('12E', False),
('0.1E', False),
('0E', False),
('', False),
('E', False),
])
def test_scientific_re(self, tokenizer, string, success):
regex = tokenizer.Tokenizer.SN_RE
assert bool(regex.match(string)) is success
@pytest.mark.parametrize('string, expected', [
(' ', ' '),
(' *', ' '),
(' ', ' '),
(' a', ' '),
(' ', ' '),
(' +', ' '),
('', None),
('*', None),
])
def test_whitespace_re(self, tokenizer, string, expected):
if expected is None:
assert not tokenizer.Tokenizer.WSPACE_RE.match(string)
else:
assert tokenizer.Tokenizer.WSPACE_RE.match(string)
assert tokenizer.Tokenizer.WSPACE_RE.match(string).group(0) == expected
@pytest.mark.parametrize('string, expected', [
('"spamspamspam"', '"spamspamspam"'),
('"this is "" a test "" "', '"this is "" a test "" "'),
('""', '""'),
('"spam and ""cheese"""+"ignore"', ('"spam and ""cheese"""')),
('\'"spam and ""cheese"""+"ignore"', None),
('"oops ""', None),
])
def test_string_re(self, tokenizer, string, expected):
regex = tokenizer.Tokenizer.STRING_REGEXES['"']
if expected is None:
assert not regex.match(string)
else:
assert regex.match(string)
assert regex.match(string).group(0) == expected
@pytest.mark.parametrize('string, expected', [
("'spam and ham'", "'spam and ham'"),
("'double'' triple''' quadruple ''''", "'double'' triple'''"),
("'sextuple '''''' and septuple''''''' and more",
"'sextuple '''''' and septuple'''''''",),
("''", "''"),
("'oops ''", None),
("gunk'hello world'", None),
])
def test_link_re(self, tokenizer, string, expected):
regex = tokenizer.Tokenizer.STRING_REGEXES["'"]
if expected is None:
assert not regex.match(string)
else:
assert regex.match(string)
assert regex.match(string).group(0) == expected
class TestTokenizer(object):
def test_init(self, tokenizer):
tok = tokenizer.Tokenizer("abcdefg")
assert tok.offset == 0
tok = tokenizer.Tokenizer("=abcdefg")
assert tok.offset == 0
@pytest.mark.parametrize('formula, tokens', [
('=IF(A$3<40%,"",INDEX(Pipeline!B$4:B$138,#REF!))',
[('IF(', FUNC, OPEN),
('A$3', OPERAND, RANGE),
('<', OP_IN, ""),
('40', OPERAND, NUMBER),
('%', OP_POST, ""),
(',', SEP, ARG),
('""', OPERAND, TEXT),
(',', SEP, ARG),
('INDEX(', FUNC, OPEN),
('Pipeline!B$4:B$138', OPERAND, RANGE),
(',', SEP, ARG),
('#REF!', OPERAND, ERROR),
(')', FUNC, CLOSE),
(')', FUNC, CLOSE)]),
("='Summary slices'!$C$3",
[("'Summary slices'!$C$3", OPERAND, RANGE)]),
('=-MAX(Pipeline!AA4:AA138)',
[("-", OP_PRE, ""),
('MAX(', FUNC, OPEN),
('Pipeline!AA4:AA138', OPERAND, RANGE),
(')', FUNC, CLOSE)]),
('=TEXT(-S7/1000,"$#,##0""M""")',
[('TEXT(', FUNC, OPEN),
('-', OP_PRE, ""),
('S7', OPERAND, RANGE),
('/', OP_IN, ""),
('1000', OPERAND, NUMBER),
(',', SEP, ARG),
('"$#,##0""M"""', OPERAND, TEXT),
(')', FUNC, CLOSE)]),
("=IF(A$3<1.3E-8,\"\",IF(ISNA('External Ref'!K7)," +
'"N/A",TEXT(K7*1E+12,"0")&"bp"',
[('IF(', FUNC, OPEN),
('A$3', OPERAND, RANGE),
('<', OP_IN, ""),
('1.3E-8', OPERAND, NUMBER),
(',', SEP, ARG),
('""', OPERAND, TEXT),
(',', SEP, ARG),
('IF(', FUNC, OPEN),
('ISNA(', FUNC, OPEN),
("'External Ref'!K7", OPERAND, RANGE),
(')', FUNC, CLOSE),
(',', SEP, ARG),
('"N/A"', OPERAND, TEXT),
(',', SEP, ARG),
('TEXT(', FUNC, OPEN),
('K7', OPERAND, RANGE),
('*', OP_IN, ""),
('1E+12', OPERAND, NUMBER),
(',', SEP, ARG),
('"0"', OPERAND, TEXT),
(')', FUNC, CLOSE),
('&', OP_IN, ""),
('"bp"', OPERAND, TEXT)]),
('=+IF(A$3<>$B7,"",(MIN(IF({TRUE, FALSE;1,2},A6:B6,$S7))>=' +
'LOWER_BOUND)*($BR6>$S72123))',
[("+", OP_PRE, ""),
('IF(', FUNC, OPEN),
('A$3', OPERAND, RANGE),
('<>', OP_IN, ""),
('$B7', OPERAND, RANGE),
(',', SEP, ARG),
('""', OPERAND, TEXT),
(',', SEP, ARG),
('(', PAREN, OPEN),
('MIN(', FUNC, OPEN),
('IF(', FUNC, OPEN),
('{', ARRAY, OPEN),
('TRUE', OPERAND, LOGICAL),
(',', SEP, ARG),
(' ', WSPACE, ''),
('FALSE', OPERAND, LOGICAL),
(';', SEP, ROW),
('1', OPERAND, NUMBER),
(',', SEP, ARG),
('2', OPERAND, NUMBER),
('}', ARRAY, CLOSE),
(',', SEP, ARG),
('A6:B6', OPERAND, RANGE),
(',', SEP, ARG),
('$S7', OPERAND, RANGE ),
(')', FUNC, CLOSE),
(')', FUNC, CLOSE),
('>=', OP_IN, ''),
('LOWER_BOUND', OPERAND, RANGE),
(')', PAREN, CLOSE),
('*', OP_IN, ''),
('(', PAREN, OPEN),
('$BR6', OPERAND, RANGE),
('>', OP_IN, ''),
('$S72123', OPERAND, RANGE),
(')', PAREN, CLOSE),
(')', FUNC, CLOSE)]),
('=(AW$4=$D7)+0%',
[('(', PAREN, OPEN),
('AW$4', OPERAND, RANGE),
('=', OP_IN, ''),
('$D7', OPERAND, RANGE),
(')', PAREN, CLOSE),
('+', OP_IN, ''),
('0', OPERAND, NUMBER),
('%', OP_POST, '')]),
('=$A:$A,$C:$C',
[('$A:$A', OPERAND, RANGE),
(',', OP_IN, ""),
('$C:$C', OPERAND, RANGE)]),
("Just text", [("Just text", LITERAL, "")]),
("123.456", [("123.456", LITERAL, "")]),
("31/12/1999", [("31/12/1999", LITERAL, "")]),
("", []),
])
def test_parse(self, tokenizer, formula, tokens):
tok = tokenizer.Tokenizer(formula)
tok.parse()
result = [(token.value, token.type, token.subtype)
for token in tok.items]
assert result == tokens
@pytest.mark.parametrize('formula, offset, result', [
('"spamspamspam"spam', 0, '"spamspamspam"'),
('"this is "" a test "" "test', 0, '"this is "" a test "" "'),
('""', 0, '""'),
('a"bcd""efg"hijk', 1, '"bcd""efg"'),
('"oops ""', 0, None),
("'spam and ham'", 0, "'spam and ham'"),
("'double'' triple''' quad ''''", 0, "'double'' triple'''"),
("123'sextuple '''''' and septuple''''''' and more", 3,
"'sextuple '''''' and septuple'''''''"),
("''", 0, "''"),
("'oops ''", 0, None),
])
def test_parse_string(self, tokenizer, formula, offset, result):
tok = tokenizer.Tokenizer(formula)
tok.offset = offset
if result is None:
with pytest.raises(tokenizer.TokenizerError):
tok.parse_string()
return
assert tok.parse_string() == len(result)
if formula[offset] == '"':
token = tok.items[0]
assert token.value == result
assert token.type == OPERAND
assert token.subtype == TEXT
assert not tok.token
else:
assert not tok.items
assert tok.token[0] == result
assert len(tok.token) == 1
@pytest.mark.parametrize('formula, offset, result', [
('[abc]def', 0, '[abc]'),
('[]abcdef', 0, '[]'),
('[abcdef]', 0, '[abcdef]'),
('a[bcd]ef', 1, '[bcd]'),
('ab[cde]f', 2, '[cde]'),
])
def test_parse_brackets(self, tokenizer, formula, offset, result):
tok = tokenizer.Tokenizer(formula)
tok.offset = offset
assert tok.parse_brackets() == len(result)
assert not tok.items
assert tok.token[0] == result
assert len(tok.token) == 1
def test_parse_brackets_error(self, tokenizer):
tok = tokenizer.Tokenizer('[unfinished business')
with pytest.raises(tokenizer.TokenizerError):
tok.parse_brackets()
@pytest.mark.parametrize('error', [
"#NULL!",
"#DIV/0!",
"#VALUE!",
"#REF!",
"#NAME?",
"#NUM!",
"#N/A"
])
def test_parse_error(self, tokenizer, error):
tok = tokenizer.Tokenizer(error)
assert tok.parse_error() == len(error)
assert len(tok.items) == 1
assert not tok.token
token = tok.items[0]
assert token.value == error
assert token.type == OPERAND
assert token.subtype == ERROR
def test_parse_error_error(self, tokenizer):
tok = tokenizer.Tokenizer("#NotAnError")
with pytest.raises(tokenizer.TokenizerError):
tok.parse_error()
@pytest.mark.parametrize('formula', [' ' * i for i in range(1, 10)])
def test_parse_whitespace(self, tokenizer, formula):
tok = tokenizer.Tokenizer(formula)
assert tok.parse_whitespace() == len(formula)
assert len(tok.items) == 1
token = tok.items[0]
assert token.value == " "
assert token.type == WSPACE
assert token.subtype == ""
assert not tok.token
@pytest.mark.parametrize('formula, result, type_', [
('>=', '>=', OP_IN),
('<=', '<=', OP_IN),
('<>', '<>', OP_IN),
('%', '%', OP_POST),
('*', '*', OP_IN),
('/', '/', OP_IN),
('^', '^', OP_IN),
('&', '&', OP_IN),
('=', '=', OP_IN),
('>', '>', OP_IN),
('<', '<', OP_IN),
('+', '+', OP_PRE),
('-', '-', OP_PRE),
('=<', '=', OP_IN),
('><', '>', OP_IN),
('<<', '<', OP_IN),
('>>', '>', OP_IN),
])
def test_parse_operator(self, tokenizer, formula, result, type_):
tok = tokenizer.Tokenizer(formula)
assert tok.parse_operator() == len(result)
assert len(tok.items) == 1
assert not tok.token
token = tok.items[0]
assert token.value == result
assert token.type == type_
assert token.subtype == ''
@pytest.mark.parametrize('prefix, char, type_', [
('name', '(', FUNC),
('', '(', PAREN),
('', '{', ARRAY),
])
def test_parse_opener(self, tokenizer, prefix, char, type_):
tok = tokenizer.Tokenizer(prefix + char)
tok.offset = len(prefix)
if prefix:
tok.token.append(prefix)
assert tok.parse_opener() == 1
assert not tok.token
assert len(tok.items) == 1
token = tok.items[0]
assert token.value == prefix + char
assert token.type == type_
assert token.subtype == OPEN
assert len(tok.token_stack) == 1
assert tok.token_stack[0] is token
def test_parse_opener_error(self, tokenizer):
tok = tokenizer.Tokenizer('name{')
tok.offset = 4
tok.token.append('name')
with pytest.raises(tokenizer.TokenizerError):
tok.parse_opener()
@pytest.mark.parametrize('formula, offset, opener', [
('func(a)', 6, ('func(', FUNC, OPEN)),
('(a)', 2, ('(', PAREN, OPEN)),
('{a,b,c}', 6, ('{', ARRAY, OPEN)),
])
def test_parse_closer(self, tokenizer, formula, offset, opener):
tok = tokenizer.Tokenizer(formula)
tok.offset = offset
tok.token_stack.append(tokenizer.Token(*opener))
assert tok.parse_closer() == 1
assert len(tok.items) == 1
token = tok.items[0]
assert token.value == formula[offset]
assert token.type == opener[1]
assert token.subtype == CLOSE
@pytest.mark.parametrize('formula, offset, opener', [
('func(a}', 6, ('func(', FUNC, OPEN)),
('(a}', 2, ('(', PAREN, OPEN)),
('{a,b,c)', 6, ('{', ARRAY, OPEN)),
])
def test_parse_closer_error(self, tokenizer, formula, offset, opener):
tok = tokenizer.Tokenizer(formula)
tok.offset = offset
tok.token_stack.append(tokenizer.Token(*opener))
with pytest.raises(tokenizer.TokenizerError):
tok.parse_closer()
@pytest.mark.parametrize('formula, offset, opener, type_, subtype', [
("{a;b}", 2, ('{', ARRAY, OPEN), SEP, ROW),
("{a,b}", 2, ('{', ARRAY, OPEN), SEP, ARG),
("(a,b)", 2, ('(', PAREN, OPEN), OP_IN, ''),
("FUNC(a,b)", 6, ('FUNC(', FUNC, OPEN), SEP, ARG),
("$A$15:$B$20,$A$1:$B$5", 11, None, OP_IN, "")
])
def test_parse_separator(self, tokenizer, formula, offset, opener, type_, subtype):
tok = tokenizer.Tokenizer(formula)
tok.offset = offset
if opener:
tok.token_stack.append(tokenizer.Token(*opener))
assert tok.parse_separator() == 1
assert len(tok.items) == 1
token = tok.items[0]
assert token.value == formula[offset]
assert token.type == type_
assert token.subtype == subtype
@pytest.mark.parametrize('formula, offset, token, ret', [
('1.0E-5', 4, ['1', '.', '0', 'E'], True),
('1.53321E+3', 8, ['1.53321', 'E'], True),
('9.9E+12', 4, ['9.', '9E'], True),
('3E+155', 2, ['9.', '9', 'E'], True),
('12E+15', 3, ['12', 'E'], False),
('0.1E-5', 4, ['0', '.1', 'E'], False),
('0E+7', 2, ['0', 'E'], False),
('12+', 2, ['1', '2'], False),
('13-E+', 4, ['E'], False),
('+', 0, [], False),
])
def test_check_scientific_notation(self, tokenizer, formula, offset, token, ret):
tok = tokenizer.Tokenizer(formula)
tok.offset = offset
tok.token[:] = token
assert ret is tok.check_scientific_notation()
if ret:
assert offset + 1 == tok.offset
assert token == tok.token[:-1]
assert tok.token[-1] == formula[offset]
else:
assert offset == tok.offset
assert token == tok.token
def test_assert_empty_token(self, tokenizer):
tok = tokenizer.Tokenizer("")
try:
tok.assert_empty_token()
except tokenizer.TokenizerError:
pytest.fail(
"assert_empty_token raised TokenizerError incorrectly")
tok.token.append("test")
with pytest.raises(tokenizer.TokenizerError):
tok.assert_empty_token()
def test_save_token(self, tokenizer):
tok = tokenizer.Tokenizer("")
tok.save_token()
assert not tok.items
tok.token.append("test")
tok.save_token()
assert len(tok.items) == 1
token = tok.items[0]
assert token.value == "test"
assert token.type == OPERAND
@pytest.mark.parametrize('formula', [
'=IF(A$3<40%,"",INDEX(Pipeline!B$4:B$138,#REF!))',
"='Summary slices'!$C$3",
'=-MAX(Pipeline!AA4:AA138)',
'=TEXT(-S7/1000,"$#,##0""M""")',
("=IF(A$3<1.3E-8,\"\",IF(ISNA('External Ref'!K7),"
'"N/A",TEXT(K7*1E+12,"0")&"bp"'),
('=+IF(A$3<>$B7,"",(MIN(IF({TRUE, FALSE;1,2},A6:B6,$S7))>=' +
'LOWER_BOUND)*($BR6>$S72123))'),
'=(AW$4=$D7)+0%',
"Just text",
"123.456",
"31/12/1999",
"",
])
def test_render(self, tokenizer, formula):
tok = tokenizer.Tokenizer(formula)
tok.parse()
assert tok.render() == formula
class TestToken(object):
def test_init(self, tokenizer):
tokenizer.Token('val', 'type', 'subtype')
@pytest.mark.parametrize('value, subtype', [
('"text"', TEXT),
('#REF!', ERROR),
('123', NUMBER),
('0', NUMBER),
('0.123', NUMBER),
('.123', NUMBER),
('1.234E5', NUMBER),
('1E+5', NUMBER),
('1.13E-55', NUMBER),
('TRUE', LOGICAL),
('FALSE', LOGICAL),
('A1', RANGE),
('ABCD12345', RANGE),
("'Hello world'!R123C[-12]", RANGE),
("[outside-workbook.xlsx]'A sheet name'!$AB$122", RANGE),
])
def test_make_operand(self, tokenizer, value, subtype):
tok = tokenizer.Token.make_operand(value)
assert tok.value == value
assert tok.type == OPERAND
assert tok.subtype == subtype
@pytest.mark.parametrize('value, type_, subtype', [
('{', ARRAY, OPEN),
('}', ARRAY, CLOSE),
('(', PAREN, OPEN),
(')', PAREN, CLOSE),
('FUNC(', FUNC, OPEN),
])
def test_make_subexp(self, tokenizer, value, type_, subtype):
tok = tokenizer.Token.make_subexp(value)
assert tok.value == value
assert tok.type == type_
assert tok.subtype == subtype
def test_make_subexp_func(self, tokenizer):
tok = tokenizer.Token.make_subexp(')', True)
assert tok.value == ')'
assert tok.type == FUNC
assert tok.subtype == CLOSE
tok = tokenizer.Token.make_subexp('TEST(', True)
assert tok.value == 'TEST('
assert tok.type == FUNC
assert tok.subtype == OPEN
@pytest.mark.parametrize('token, close_val', [
(('(', PAREN, OPEN), ')'),
(('{', ARRAY, OPEN), '}'),
(('FUNC(', FUNC, OPEN), ')'),
])
def test_get_closer(self, tokenizer, token, close_val):
closer = tokenizer.Token(*token).get_closer()
assert closer.value == close_val
assert closer.type == token[1]
assert closer.subtype == CLOSE
def test_make_separator(self, tokenizer):
token = tokenizer.Token.make_separator(',')
assert token.value == ','
assert token.type == SEP
assert token.subtype == ARG
token = tokenizer.Token.make_separator(';')
assert token.value == ';'
assert token.type == SEP
assert token.subtype == ROW
|