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 | def Lex(h):
|
100 | print(repr(h))
|
101 | lex = html.ValidTokens(h)
|
102 | tokens = list(lex)
|
103 | for tok_id, end_pos in tokens:
|
104 | log('%d %s', end_pos, html.TokenName(tok_id))
|
105 | return tokens
|
106 |
|
107 |
|
108 | class LexerTest(unittest.TestCase):
|
109 |
|
110 | # IndexLinker in devtools/make_help.py
|
111 | # <pre> sections in doc/html_help.py
|
112 | # TocExtractor in devtools/cmark.py
|
113 |
|
114 | def testPstrip(self):
|
115 | """Remove anything like this.
|
116 |
|
117 | <p><pstrip> </pstrip></p>
|
118 | """
|
119 | pass
|
120 |
|
121 | def testCommentParse(self):
|
122 | n = len(TEST_HTML)
|
123 | for tok_id, end_pos in html._Tokens(TEST_HTML, 0, n):
|
124 | if tok_id == html.Invalid:
|
125 | raise RuntimeError()
|
126 | print(tok_id)
|
127 |
|
128 | def testCommentParse2(self):
|
129 |
|
130 | Tok = html.Tok
|
131 | h = '''
|
132 | hi <!-- line 1
|
133 | line 2 --><br/>'''
|
134 | tokens = Lex(h)
|
135 |
|
136 | self.assertEqual(
|
137 | [
|
138 | (Tok.RawData, 12),
|
139 | (Tok.Comment, 50), # <? err ?>
|
140 | (Tok.StartEndTag, 55),
|
141 | (Tok.EndOfStream, 55),
|
142 | ],
|
143 | tokens)
|
144 |
|
145 | def testProcessingInstruction(self):
|
146 | # <?xml ?> header
|
147 | Tok = html.Tok
|
148 | h = 'hi <? err ?>'
|
149 | tokens = Lex(h)
|
150 |
|
151 | self.assertEqual(
|
152 | [
|
153 | (Tok.RawData, 3),
|
154 | (Tok.Processing, 12), # <? err ?>
|
155 | (Tok.EndOfStream, 12),
|
156 | ],
|
157 | tokens)
|
158 |
|
159 | def testScriptStyle(self):
|
160 | Tok = html.Tok
|
161 | h = '''
|
162 | hi <script src=""> if (x < 1 && y > 2 ) { console.log(""); }
|
163 | </script>
|
164 | '''
|
165 | tokens = Lex(h)
|
166 |
|
167 | self.assertEqual(
|
168 | [
|
169 | (Tok.RawData, 12),
|
170 | (Tok.StartTag, 27), # <script>
|
171 | (Tok.HtmlCData, 78), # JavaScript code is HTML CData
|
172 | (Tok.EndTag, 87), # </script>
|
173 | (Tok.RawData, 96), # \n
|
174 | (Tok.EndOfStream, 96), # \n
|
175 | ],
|
176 | tokens)
|
177 |
|
178 | def testCData(self):
|
179 | Tok = html.Tok
|
180 |
|
181 | # from
|
182 | # /home/andy/src/languages/Python-3.11.5/Lib/test/xmltestdata/c14n-20/inC14N4.xml
|
183 | h = '<compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>'
|
184 | tokens = Lex(h)
|
185 |
|
186 | self.assertEqual([
|
187 | (Tok.StartTag, 9),
|
188 | (Tok.CData, 61),
|
189 | (Tok.EndTag, 71),
|
190 | (Tok.EndOfStream, 71),
|
191 | ], tokens)
|
192 |
|
193 | def testEntity(self):
|
194 | Tok = html.Tok
|
195 |
|
196 | # from
|
197 | # /home/andy/src/Python-3.12.4/Lib/test/xmltestdata/c14n-20/inC14N5.xml
|
198 | h = '&ent1;, &ent2;!'
|
199 |
|
200 | tokens = Lex(h)
|
201 |
|
202 | self.assertEqual([
|
203 | (Tok.CharEntity, 6),
|
204 | (Tok.RawData, 8),
|
205 | (Tok.CharEntity, 14),
|
206 | (Tok.RawData, 15),
|
207 | (Tok.EndOfStream, 15),
|
208 | ], tokens)
|
209 |
|
210 | def testStartTag(self):
|
211 | Tok = html.Tok
|
212 |
|
213 | h = '<a>hi</a>'
|
214 | tokens = Lex(h)
|
215 |
|
216 | self.assertEqual([
|
217 | (Tok.StartTag, 3),
|
218 | (Tok.RawData, 5),
|
219 | (Tok.EndTag, 9),
|
220 | (Tok.EndOfStream, 9),
|
221 | ], tokens)
|
222 |
|
223 | def testInvalid(self):
|
224 | Tok = html.Tok
|
225 |
|
226 | INVALID = [
|
227 | # Should be &
|
228 | '<a>&',
|
229 | '&', # not finished
|
230 | '&#', # not finished
|
231 | # Hm > is allowed?
|
232 | #'a > b',
|
233 | 'a < b',
|
234 | '<!-- unfinished comment',
|
235 | '<? unfinished processing',
|
236 | '</div bad=attr> <a> <b>',
|
237 | ]
|
238 |
|
239 | for s in INVALID:
|
240 | lex = html.ValidTokens(s)
|
241 | try:
|
242 | for i in xrange(5):
|
243 | tok_id, pos = next(lex)
|
244 | except html.LexError as e:
|
245 | print(e)
|
246 | else:
|
247 | self.fail('Expected LexError')
|
248 |
|
249 |
|
250 | if __name__ == '__main__':
|
251 | unittest.main()
|