| 1 | #!/usr/bin/env python2
|
| 2 | from __future__ import print_function
|
| 3 |
|
| 4 | from _devbuild.gen.htm8_asdl import (h8_id, h8_id_t, h8_id_str, attr_name,
|
| 5 | attr_value_e, attr_value_str)
|
| 6 |
|
| 7 | import unittest
|
| 8 | import re
|
| 9 |
|
| 10 | from typing import List, Tuple
|
| 11 |
|
| 12 | from data_lang import htm8
|
| 13 | from doctools.util import log
|
| 14 |
|
| 15 | with open('data_lang/testdata/hello.htm8') as f:
|
| 16 | TEST_HTML = f.read()
|
| 17 |
|
| 18 |
|
| 19 | class RegexTest(unittest.TestCase):
|
| 20 |
|
| 21 | def testDotAll(self):
|
| 22 | # type: () -> None
|
| 23 |
|
| 24 | # Note that $ matches end of line, not end of string
|
| 25 | p1 = re.compile(r'.')
|
| 26 | print(p1.match('\n'))
|
| 27 |
|
| 28 | p2 = re.compile(r'.', re.DOTALL)
|
| 29 | print(p2.match('\n'))
|
| 30 |
|
| 31 | #p3 = re.compile(r'[.\n]', re.VERBOSE)
|
| 32 | p3 = re.compile(r'[.\n]')
|
| 33 | print(p3.match('\n'))
|
| 34 |
|
| 35 | print('Negation')
|
| 36 |
|
| 37 | p4 = re.compile(r'[^>]')
|
| 38 | print(p4.match('\n'))
|
| 39 |
|
| 40 | def testAttrRe(self):
|
| 41 | # type: () -> None
|
| 42 | _ATTR_RE = htm8._ATTR_RE
|
| 43 | m = _ATTR_RE.match(' empty= val')
|
| 44 | print(m.groups())
|
| 45 |
|
| 46 |
|
| 47 | class FunctionsTest(unittest.TestCase):
|
| 48 |
|
| 49 | def testFindLineNum(self):
|
| 50 | # type: () -> None
|
| 51 | s = 'foo\n' * 3
|
| 52 | for pos in [1, 5, 10, 50]: # out of bounds
|
| 53 | line_num = htm8._FindLineNum(s, pos)
|
| 54 | print(line_num)
|
| 55 |
|
| 56 |
|
| 57 | class AttrLexerTest(unittest.TestCase):
|
| 58 |
|
| 59 | def testNoAttrs(self):
|
| 60 | # type: () -> None
|
| 61 |
|
| 62 | # TODO: h8_id.StartTag and EndTag will expose the tag_name_pos - the
|
| 63 | # end of the tag name
|
| 64 |
|
| 65 | h = 'x <a>'
|
| 66 | lx = htm8.Lexer(h)
|
| 67 |
|
| 68 | # Skip raw data
|
| 69 | tok_id, end_pos = lx.Read()
|
| 70 | self.assertEqual(h8_id.RawData, tok_id)
|
| 71 |
|
| 72 | tok_id, end_pos = lx.Read()
|
| 73 | self.assertEqual(h8_id.StartTag, tok_id)
|
| 74 |
|
| 75 | attr_lx = htm8.AttrLexer(h)
|
| 76 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 77 |
|
| 78 | # There is no tag
|
| 79 | n, name_start, name_end = attr_lx.ReadName()
|
| 80 | self.assertEqual(n, attr_name.Done)
|
| 81 | self.assertEqual(-1, name_start)
|
| 82 | self.assertEqual(-1, name_end)
|
| 83 |
|
| 84 | try:
|
| 85 | result = attr_lx.ReadRawValue()
|
| 86 | except AssertionError as e:
|
| 87 | print(e)
|
| 88 | else:
|
| 89 | self.fail('should have failed')
|
| 90 |
|
| 91 | def testInvalid(self):
|
| 92 | h = '<a !>'
|
| 93 | lx = htm8.Lexer(h)
|
| 94 |
|
| 95 | tok_id, end_pos = lx.Read()
|
| 96 | self.assertEqual(h8_id.StartTag, tok_id)
|
| 97 |
|
| 98 | attr_lx = htm8.AttrLexer(h)
|
| 99 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 100 |
|
| 101 | n, name_start, name_end = attr_lx.ReadName()
|
| 102 | self.assertEqual(n, attr_name.Invalid)
|
| 103 | self.assertEqual(-1, name_start)
|
| 104 | self.assertEqual(-1, name_end)
|
| 105 |
|
| 106 | try:
|
| 107 | result = attr_lx.ReadRawValue()
|
| 108 | except AssertionError as e:
|
| 109 | print(e)
|
| 110 | else:
|
| 111 | self.fail('should have failed')
|
| 112 |
|
| 113 | def testEmpty(self):
|
| 114 | h = '<img src=/>'
|
| 115 | lx = htm8.Lexer(h)
|
| 116 |
|
| 117 | tok_id, end_pos = lx.Read()
|
| 118 | self.assertEqual(h8_id.StartEndTag, tok_id)
|
| 119 |
|
| 120 | attr_lx = htm8.AttrLexer(h)
|
| 121 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 122 |
|
| 123 | n, name_start, name_end = attr_lx.ReadName()
|
| 124 | self.assertEqual(n, attr_name.Ok)
|
| 125 | self.assertEqual(5, name_start)
|
| 126 | self.assertEqual(8, name_end)
|
| 127 | self.assertEqual(False, attr_lx.next_value_is_missing)
|
| 128 |
|
| 129 | self.assertEqual(True, attr_lx.AttrNameEquals('src'))
|
| 130 | self.assertEqual(False, attr_lx.AttrNameEquals('srcz'))
|
| 131 |
|
| 132 | v, attr_start, attr_end = attr_lx.ReadRawValue()
|
| 133 | log('v = %s', attr_value_str(v))
|
| 134 | self.assertEqual(attr_value_e.Empty, v)
|
| 135 | self.assertEqual(-1, attr_start)
|
| 136 | self.assertEqual(-1, attr_end)
|
| 137 |
|
| 138 | def testMissing(self):
|
| 139 | h = '<img SRC/>'
|
| 140 | lx = htm8.Lexer(h)
|
| 141 |
|
| 142 | tok_id, end_pos = lx.Read()
|
| 143 | self.assertEqual(h8_id.StartEndTag, tok_id)
|
| 144 |
|
| 145 | attr_lx = htm8.AttrLexer(h)
|
| 146 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 147 |
|
| 148 | n, name_start, name_end = attr_lx.ReadName()
|
| 149 | self.assertEqual(n, attr_name.Ok)
|
| 150 | self.assertEqual(5, name_start)
|
| 151 | self.assertEqual(8, name_end)
|
| 152 | self.assertEqual(True, attr_lx.next_value_is_missing)
|
| 153 |
|
| 154 | self.assertEqual(True, attr_lx.AttrNameEquals('src'))
|
| 155 | self.assertEqual(False, attr_lx.AttrNameEquals('srcz'))
|
| 156 |
|
| 157 | v, attr_start, attr_end = attr_lx.ReadRawValue()
|
| 158 | self.assertEqual(attr_value_e.Missing, v)
|
| 159 | self.assertEqual(-1, attr_start)
|
| 160 | self.assertEqual(-1, attr_end)
|
| 161 |
|
| 162 | def testUnquoted(self):
|
| 163 | # CAREFUL: /> is a StartEndTag, and / is not part of unquoted value
|
| 164 | h = '<a x=foo/>'
|
| 165 | lx = htm8.Lexer(h)
|
| 166 |
|
| 167 | tok_id, end_pos = lx.Read()
|
| 168 | self.assertEqual(h8_id.StartEndTag, tok_id)
|
| 169 |
|
| 170 | attr_lx = htm8.AttrLexer(h)
|
| 171 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 172 | n, name_start, name_end = attr_lx.ReadName()
|
| 173 | self.assertEqual(n, attr_name.Ok)
|
| 174 | self.assertEqual(3, name_start)
|
| 175 | self.assertEqual(4, name_end)
|
| 176 |
|
| 177 | v, attr_start, attr_end = attr_lx.ReadRawValue()
|
| 178 |
|
| 179 | log('v = %s', attr_value_str(v))
|
| 180 | log('unquoted val %r', h[attr_start:attr_end])
|
| 181 |
|
| 182 | self.assertEqual(attr_value_e.Unquoted, v)
|
| 183 | self.assertEqual(5, attr_start)
|
| 184 | self.assertEqual(8, attr_end)
|
| 185 |
|
| 186 | def testDoubleQuoted(self):
|
| 187 | h = '<a x="f&">'
|
| 188 | lx = htm8.Lexer(h)
|
| 189 |
|
| 190 | tok_id, end_pos = lx.Read()
|
| 191 | self.assertEqual(h8_id.StartTag, tok_id)
|
| 192 |
|
| 193 | attr_lx = htm8.AttrLexer(h)
|
| 194 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 195 | n, name_start, name_end = attr_lx.ReadName()
|
| 196 | self.assertEqual(n, attr_name.Ok)
|
| 197 | self.assertEqual(3, name_start)
|
| 198 | self.assertEqual(4, name_end)
|
| 199 |
|
| 200 | v, attr_start, attr_end = attr_lx.ReadRawValue()
|
| 201 |
|
| 202 | log('v = %s', attr_value_str(v))
|
| 203 | log('val %r', h[attr_start:attr_end])
|
| 204 |
|
| 205 | self.assertEqual(attr_value_e.DoubleQuoted, v)
|
| 206 | self.assertEqual(6, attr_start)
|
| 207 | self.assertEqual(8, attr_end)
|
| 208 |
|
| 209 | def testSingleQuoted(self):
|
| 210 | h = "<a x='&f'>"
|
| 211 | lx = htm8.Lexer(h)
|
| 212 |
|
| 213 | tok_id, end_pos = lx.Read()
|
| 214 | self.assertEqual(h8_id.StartTag, tok_id)
|
| 215 |
|
| 216 | attr_lx = htm8.AttrLexer(h)
|
| 217 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 218 | n, name_start, name_end = attr_lx.ReadName()
|
| 219 | self.assertEqual(n, attr_name.Ok)
|
| 220 | self.assertEqual(3, name_start)
|
| 221 | self.assertEqual(4, name_end)
|
| 222 |
|
| 223 | v, attr_start, attr_end = attr_lx.ReadRawValue()
|
| 224 |
|
| 225 | log('v = %s', attr_value_str(v))
|
| 226 | log('unquoted val %r', h[attr_start:attr_end])
|
| 227 |
|
| 228 | self.assertEqual(attr_value_e.SingleQuoted, v)
|
| 229 | self.assertEqual(6, attr_start)
|
| 230 | self.assertEqual(8, attr_end)
|
| 231 |
|
| 232 | def testDoubleQuoted_Bad(self):
|
| 233 | h = '<a x="foo>'
|
| 234 | lx = htm8.Lexer(h)
|
| 235 |
|
| 236 | tok_id, end_pos = lx.Read()
|
| 237 | self.assertEqual(h8_id.StartTag, tok_id)
|
| 238 |
|
| 239 | attr_lx = htm8.AttrLexer(h)
|
| 240 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 241 | n, name_start, name_end = attr_lx.ReadName()
|
| 242 | self.assertEqual(n, attr_name.Ok)
|
| 243 | self.assertEqual(3, name_start)
|
| 244 | self.assertEqual(4, name_end)
|
| 245 |
|
| 246 | try:
|
| 247 | v, attr_start, attr_end = attr_lx.ReadRawValue()
|
| 248 | except htm8.LexError as e:
|
| 249 | print(e)
|
| 250 | else:
|
| 251 | self.fail('Expected LexError')
|
| 252 |
|
| 253 | def testSingleQuoted_Bad(self):
|
| 254 | h = "<a x='foo>"
|
| 255 | lx = htm8.Lexer(h)
|
| 256 |
|
| 257 | tok_id, end_pos = lx.Read()
|
| 258 | self.assertEqual(h8_id.StartTag, tok_id)
|
| 259 |
|
| 260 | attr_lx = htm8.AttrLexer(h)
|
| 261 | attr_lx.Init(lx.TagNamePos(), end_pos)
|
| 262 | n, name_start, name_end = attr_lx.ReadName()
|
| 263 | self.assertEqual(n, attr_name.Ok)
|
| 264 | self.assertEqual(3, name_start)
|
| 265 | self.assertEqual(4, name_end)
|
| 266 |
|
| 267 | try:
|
| 268 | v, attr_start, attr_end = attr_lx.ReadRawValue()
|
| 269 | except htm8.LexError as e:
|
| 270 | print(e)
|
| 271 | else:
|
| 272 | self.fail('Expected LexError')
|
| 273 |
|
| 274 |
|
| 275 | def ValidTokenList(s, no_special_tags=False):
|
| 276 | # type: (str, bool) -> List[Tuple[h8_id_t, int]]
|
| 277 | """A wrapper that can be more easily translated to C++. Doesn't use iterators."""
|
| 278 |
|
| 279 | start_pos = 0
|
| 280 | tokens = []
|
| 281 | lx = htm8.Lexer(s, no_special_tags=no_special_tags)
|
| 282 | while True:
|
| 283 | tok_id, end_pos = lx.Read()
|
| 284 | tokens.append((tok_id, end_pos))
|
| 285 | if tok_id == h8_id.EndOfStream:
|
| 286 | break
|
| 287 | if tok_id == h8_id.Invalid:
|
| 288 | raise htm8.LexError(s, start_pos)
|
| 289 | start_pos = end_pos
|
| 290 | return tokens
|
| 291 |
|
| 292 |
|
| 293 | def Lex(h, no_special_tags=False):
|
| 294 | # type: (str, bool) -> List[Tuple[int, int]]
|
| 295 | print(repr(h))
|
| 296 | tokens = ValidTokenList(h, no_special_tags=no_special_tags)
|
| 297 | start_pos = 0
|
| 298 | for tok_id, end_pos in tokens:
|
| 299 | frag = h[start_pos:end_pos]
|
| 300 | log('%d %s %r', end_pos, h8_id_str(tok_id), frag)
|
| 301 | start_pos = end_pos
|
| 302 | return tokens
|
| 303 |
|
| 304 |
|
| 305 | class LexerTest(unittest.TestCase):
|
| 306 |
|
| 307 | # IndexLinker in devtools/make_help.py
|
| 308 | # <pre> sections in doc/html_help.py
|
| 309 | # TocExtractor in devtools/cmark.py
|
| 310 |
|
| 311 | def testPstrip(self):
|
| 312 | # type: () -> None
|
| 313 | """Remove anything like this.
|
| 314 |
|
| 315 | <p><pstrip> </pstrip></p>
|
| 316 | """
|
| 317 | pass
|
| 318 |
|
| 319 | def testCommentParse(self):
|
| 320 | # type: () -> None
|
| 321 | n = len(TEST_HTML)
|
| 322 | tokens = Lex(TEST_HTML)
|
| 323 |
|
| 324 | def testCommentParse2(self):
|
| 325 | # type: () -> None
|
| 326 | h = '''
|
| 327 | hi <!-- line 1
|
| 328 | line 2 --><br/>'''
|
| 329 | tokens = Lex(h)
|
| 330 |
|
| 331 | self.assertEqual(
|
| 332 | [
|
| 333 | (h8_id.RawData, 12),
|
| 334 | (h8_id.Comment, 50), # <? err ?>
|
| 335 | (h8_id.StartEndTag, 55),
|
| 336 | (h8_id.EndOfStream, 55),
|
| 337 | ],
|
| 338 | tokens)
|
| 339 |
|
| 340 | def testProcessingInstruction(self):
|
| 341 | # type: () -> None
|
| 342 | # <?xml ?> header
|
| 343 | h = 'hi <? err ?>'
|
| 344 | tokens = Lex(h)
|
| 345 |
|
| 346 | self.assertEqual(
|
| 347 | [
|
| 348 | (h8_id.RawData, 3),
|
| 349 | (h8_id.Processing, 12), # <? err ?>
|
| 350 | (h8_id.EndOfStream, 12),
|
| 351 | ],
|
| 352 | tokens)
|
| 353 |
|
| 354 | def testScriptStyle(self):
|
| 355 | # type: () -> None
|
| 356 | h = '''
|
| 357 | hi <script src=""> if (x < 1 && y > 2 ) { console.log(""); }
|
| 358 | </script>
|
| 359 | '''
|
| 360 | tokens = Lex(h)
|
| 361 |
|
| 362 | expected = [
|
| 363 | (h8_id.RawData, 12),
|
| 364 | (h8_id.StartTag, 27), # <script>
|
| 365 | (h8_id.HtmlCData, 78), # JavaScript code is HTML CData
|
| 366 | (h8_id.EndTag, 87), # </script>
|
| 367 | (h8_id.RawData, 96), # \n
|
| 368 | (h8_id.EndOfStream, 96), # \n
|
| 369 | ]
|
| 370 | self.assertEqual(expected, tokens)
|
| 371 |
|
| 372 | # Test case matching
|
| 373 | tokens = Lex(h.replace('script', 'scrIPT'))
|
| 374 | self.assertEqual(expected, tokens)
|
| 375 |
|
| 376 | def testScriptStyleXml(self):
|
| 377 | # type: () -> None
|
| 378 | h = 'hi <script src=""> < </script>'
|
| 379 | # XML mode
|
| 380 | tokens = Lex(h, no_special_tags=True)
|
| 381 |
|
| 382 | self.assertEqual(
|
| 383 | [
|
| 384 | (h8_id.RawData, 3),
|
| 385 | (h8_id.StartTag, 18), # <script>
|
| 386 | (h8_id.RawData, 19), # space
|
| 387 | (h8_id.CharEntity, 23), # </script>
|
| 388 | (h8_id.RawData, 24), # \n
|
| 389 | (h8_id.EndTag, 33), # \n
|
| 390 | (h8_id.EndOfStream, 33), # \n
|
| 391 | ],
|
| 392 | tokens)
|
| 393 |
|
| 394 | def testCData(self):
|
| 395 | # type: () -> None
|
| 396 |
|
| 397 | # from
|
| 398 | # /home/andy/src/languages/Python-3.11.5/Lib/test/xmltestdata/c14n-20/inC14N4.xml
|
| 399 | h = '<compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>'
|
| 400 | tokens = Lex(h)
|
| 401 |
|
| 402 | self.assertEqual([
|
| 403 | (h8_id.StartTag, 9),
|
| 404 | (h8_id.CData, 61),
|
| 405 | (h8_id.EndTag, 71),
|
| 406 | (h8_id.EndOfStream, 71),
|
| 407 | ], tokens)
|
| 408 |
|
| 409 | def testEntity(self):
|
| 410 | # type: () -> None
|
| 411 |
|
| 412 | # from
|
| 413 | # /home/andy/src/Python-3.12.4/Lib/test/xmltestdata/c14n-20/inC14N5.xml
|
| 414 | h = '&ent1;, &ent2;!'
|
| 415 |
|
| 416 | tokens = Lex(h)
|
| 417 |
|
| 418 | self.assertEqual([
|
| 419 | (h8_id.CharEntity, 6),
|
| 420 | (h8_id.RawData, 8),
|
| 421 | (h8_id.CharEntity, 14),
|
| 422 | (h8_id.RawData, 15),
|
| 423 | (h8_id.EndOfStream, 15),
|
| 424 | ], tokens)
|
| 425 |
|
| 426 | def testStartTag(self):
|
| 427 | # type: () -> None
|
| 428 |
|
| 429 | h = '<a>hi</a>'
|
| 430 | tokens = Lex(h)
|
| 431 |
|
| 432 | self.assertEqual([
|
| 433 | (h8_id.StartTag, 3),
|
| 434 | (h8_id.RawData, 5),
|
| 435 | (h8_id.EndTag, 9),
|
| 436 | (h8_id.EndOfStream, 9),
|
| 437 | ], tokens)
|
| 438 |
|
| 439 | # Make sure we don't consume too much
|
| 440 | h = '<a><source>1.7</source></a>'
|
| 441 |
|
| 442 | tokens = Lex(h)
|
| 443 |
|
| 444 | self.assertEqual([
|
| 445 | (h8_id.StartTag, 3),
|
| 446 | (h8_id.StartTag, 11),
|
| 447 | (h8_id.RawData, 14),
|
| 448 | (h8_id.EndTag, 23),
|
| 449 | (h8_id.EndTag, 27),
|
| 450 | (h8_id.EndOfStream, 27),
|
| 451 | ], tokens)
|
| 452 |
|
| 453 | return
|
| 454 |
|
| 455 | h = '''
|
| 456 | <configuration>
|
| 457 | <source>1.7</source>
|
| 458 | </configuration>'''
|
| 459 |
|
| 460 | tokens = Lex(h)
|
| 461 |
|
| 462 | self.assertEqual([
|
| 463 | (h8_id.RawData, 9),
|
| 464 | (h8_id.StartTag, 24),
|
| 465 | (h8_id.RawData, 9),
|
| 466 | (h8_id.EndOfStream, 9),
|
| 467 | ], tokens)
|
| 468 |
|
| 469 | def testBad(self):
|
| 470 | # type: () -> None
|
| 471 | h = '&'
|
| 472 | tokens = Lex(h)
|
| 473 |
|
| 474 | self.assertEqual([
|
| 475 | (h8_id.BadAmpersand, 1),
|
| 476 | (h8_id.EndOfStream, 1),
|
| 477 | ], tokens)
|
| 478 |
|
| 479 | h = '>'
|
| 480 | tokens = Lex(h)
|
| 481 |
|
| 482 | self.assertEqual([
|
| 483 | (h8_id.BadGreaterThan, 1),
|
| 484 | (h8_id.EndOfStream, 1),
|
| 485 | ], tokens)
|
| 486 |
|
| 487 | def testEndOfStream(self):
|
| 488 | # type: () -> None
|
| 489 |
|
| 490 | # NUL is end
|
| 491 | h = 'a\0b'
|
| 492 | tokens = Lex(h)
|
| 493 |
|
| 494 | self.assertEqual([
|
| 495 | (h8_id.RawData, 1),
|
| 496 | (h8_id.EndOfStream, 2),
|
| 497 | ], tokens)
|
| 498 |
|
| 499 |
|
| 500 | if __name__ == '__main__':
|
| 501 | unittest.main()
|