| 1 | #!/usr/bin/env python2
|
| 2 | from __future__ import print_function
|
| 3 |
|
| 4 | import unittest
|
| 5 |
|
| 6 | from lazylex import html # module under test log = html.log
|
| 7 |
|
| 8 | log = html.log
|
| 9 |
|
| 10 | with open('lazylex/testdata.html') as f:
|
| 11 | TEST_HTML = f.read()
|
| 12 |
|
| 13 |
|
| 14 | def _MakeTagLexer(s):
|
| 15 | lex = html.TagLexer(s)
|
| 16 | lex.Reset(0, len(s))
|
| 17 | return lex
|
| 18 |
|
| 19 |
|
| 20 | def _PrintTokens(lex):
|
| 21 | log('')
|
| 22 | log('tag = %r', lex.TagName())
|
| 23 | for tok, start, end in lex.Tokens():
|
| 24 | log('%s %r', tok, lex.s[start:end])
|
| 25 |
|
| 26 |
|
| 27 | class RegexTest(unittest.TestCase):
|
| 28 |
|
| 29 | def testDotAll(self):
|
| 30 | import re
|
| 31 |
|
| 32 | # Note that $ matches end of line, not end of string
|
| 33 | p1 = re.compile(r'.')
|
| 34 | print(p1.match('\n'))
|
| 35 |
|
| 36 | p2 = re.compile(r'.', re.DOTALL)
|
| 37 | print(p2.match('\n'))
|
| 38 |
|
| 39 | #p3 = re.compile(r'[.\n]', re.VERBOSE)
|
| 40 | p3 = re.compile(r'[.\n]')
|
| 41 | print(p3.match('\n'))
|
| 42 |
|
| 43 | print('Negation')
|
| 44 |
|
| 45 | p4 = re.compile(r'[^>]')
|
| 46 | print(p4.match('\n'))
|
| 47 |
|
| 48 |
|
| 49 | class TagLexerTest(unittest.TestCase):
|
| 50 |
|
| 51 | def testTagLexer(self):
|
| 52 | # Invalid!
|
| 53 | #lex = _MakeTagLexer('< >')
|
| 54 | #print(lex.Tag())
|
| 55 |
|
| 56 | lex = _MakeTagLexer('<a>')
|
| 57 | _PrintTokens(lex)
|
| 58 |
|
| 59 | lex = _MakeTagLexer('<a novalue>')
|
| 60 | _PrintTokens(lex)
|
| 61 |
|
| 62 | # Note: we could have a different HasAttr() method
|
| 63 | # <a novalue> means lex.Get('novalue') == None
|
| 64 | # https://developer.mozilla.org/en-US/docs/Web/API/Element/hasAttribute
|
| 65 | self.assertEqual(None, lex.GetAttrRaw('novalue'))
|
| 66 |
|
| 67 | lex = _MakeTagLexer('<a href="double quoted">')
|
| 68 | _PrintTokens(lex)
|
| 69 |
|
| 70 | self.assertEqual('double quoted', lex.GetAttrRaw('href'))
|
| 71 | self.assertEqual(None, lex.GetAttrRaw('oops'))
|
| 72 |
|
| 73 | lex = _MakeTagLexer('<a href=foo class="bar">')
|
| 74 | _PrintTokens(lex)
|
| 75 |
|
| 76 | lex = _MakeTagLexer('<a href=foo class="bar" />')
|
| 77 | _PrintTokens(lex)
|
| 78 |
|
| 79 | lex = _MakeTagLexer('<a href="?foo=1&bar=2" />')
|
| 80 | self.assertEqual('?foo=1&bar=2', lex.GetAttrRaw('href'))
|
| 81 |
|
| 82 | def testTagName(self):
|
| 83 | lex = _MakeTagLexer('<a href=foo class="bar" />')
|
| 84 | self.assertEqual('a', lex.TagName())
|
| 85 |
|
| 86 | def testAllAttrs(self):
|
| 87 | """
|
| 88 | [('key', 'value')] for all
|
| 89 | """
|
| 90 | # closed
|
| 91 | lex = _MakeTagLexer('<a href=foo class="bar" />')
|
| 92 | self.assertEqual([('href', 'foo'), ('class', 'bar')],
|
| 93 | lex.AllAttrsRaw())
|
| 94 |
|
| 95 | lex = _MakeTagLexer('<a href="?foo=1&bar=2" />')
|
| 96 | self.assertEqual([('href', '?foo=1&bar=2')], lex.AllAttrsRaw())
|
| 97 |
|
| 98 |
|
| 99 | class LexerTest(unittest.TestCase):
|
| 100 |
|
| 101 | # IndexLinker in devtools/make_help.py
|
| 102 | # <pre> sections in doc/html_help.py
|
| 103 | # TocExtractor in devtools/cmark.py
|
| 104 |
|
| 105 | def testPstrip(self):
|
| 106 | """Remove anything like this.
|
| 107 |
|
| 108 | <p><pstrip> </pstrip></p>
|
| 109 | """
|
| 110 | pass
|
| 111 |
|
| 112 | def testCommentParse(self):
|
| 113 | n = len(TEST_HTML)
|
| 114 | for tok_id, end_pos in html._Tokens(TEST_HTML, 0, n):
|
| 115 | if tok_id == html.Invalid:
|
| 116 | raise RuntimeError()
|
| 117 | print(tok_id)
|
| 118 |
|
| 119 | Tok = html.Tok
|
| 120 | h = '''
|
| 121 | hi <!-- line 1
|
| 122 | line 2 --><br/>'''
|
| 123 | print(repr(h))
|
| 124 | lex = html.ValidTokens(h)
|
| 125 |
|
| 126 | tok_id, pos = next(lex)
|
| 127 | self.assertEqual(12, pos)
|
| 128 | self.assertEqual(Tok.RawData, tok_id)
|
| 129 |
|
| 130 | tok_id, pos = next(lex)
|
| 131 | log('tok %r', html.TokenName(tok_id))
|
| 132 | self.assertEqual(50, pos)
|
| 133 | self.assertEqual(Tok.Comment, tok_id)
|
| 134 |
|
| 135 | tok_id, pos = next(lex)
|
| 136 | self.assertEqual(55, pos)
|
| 137 | self.assertEqual(Tok.StartEndTag, tok_id)
|
| 138 |
|
| 139 | tok_id, pos = next(lex)
|
| 140 | self.assertEqual(55, pos)
|
| 141 | self.assertEqual(Tok.EndOfStream, tok_id)
|
| 142 |
|
| 143 | def testValid(self):
|
| 144 | Tok = html.Tok
|
| 145 |
|
| 146 | lex = html.ValidTokens('<a>hi</a>')
|
| 147 |
|
| 148 | tok_id, pos = next(lex)
|
| 149 | self.assertEqual(3, pos)
|
| 150 | self.assertEqual(Tok.StartTag, tok_id)
|
| 151 |
|
| 152 | tok_id, pos = next(lex)
|
| 153 | self.assertEqual(5, pos)
|
| 154 | self.assertEqual(Tok.RawData, tok_id)
|
| 155 |
|
| 156 | tok_id, pos = next(lex)
|
| 157 | self.assertEqual(9, pos)
|
| 158 | self.assertEqual(Tok.EndTag, tok_id)
|
| 159 |
|
| 160 | tok_id, pos = next(lex)
|
| 161 | self.assertEqual(9, pos)
|
| 162 | self.assertEqual(Tok.EndOfStream, tok_id)
|
| 163 |
|
| 164 | lex = html.Lexer('<a>hi</a>')
|
| 165 | while True:
|
| 166 | tok_id, pos = lex.Read()
|
| 167 | print('%d %s' % (pos, html.TokenName(tok_id)))
|
| 168 | if tok_id == Tok.EndOfStream:
|
| 169 | break
|
| 170 |
|
| 171 | return
|
| 172 | tok_id, pos = next(lex)
|
| 173 | self.assertEqual(9, pos)
|
| 174 | self.assertEqual(Tok.EndOfStream, tok_id)
|
| 175 |
|
| 176 | while True:
|
| 177 | tok_id, pos = next(lex)
|
| 178 | print('%d %s' % (pos, html.TokenName(tok_id)))
|
| 179 |
|
| 180 | def testInvalid(self):
|
| 181 | Tok = html.Tok
|
| 182 |
|
| 183 | lex = html.ValidTokens('<a>&')
|
| 184 |
|
| 185 | tok_id, pos = next(lex)
|
| 186 | self.assertEqual(3, pos)
|
| 187 | self.assertEqual(Tok.StartTag, tok_id)
|
| 188 |
|
| 189 | try:
|
| 190 | tok_id, pos = next(lex)
|
| 191 | except html.LexError as e:
|
| 192 | print(e)
|
| 193 | else:
|
| 194 | self.fail('Expected LexError')
|
| 195 |
|
| 196 |
|
| 197 | if __name__ == '__main__':
|
| 198 | unittest.main()
|