FilesExpand file tree

 master

/

test_serializer.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

225 lines (171 loc) · 8.14 KB

 master

/

test_serializer.py

Copy path

Top

File metadata and controls

• Code
• Blame

225 lines (171 loc) · 8.14 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

from __future__ import absolute_import, division, unicode_literals

import os

import json

import pytest

from .support import get_data_files

from html5lib import constants

from html5lib.filters.lint import Filter as Lint

from html5lib.serializer import HTMLSerializer, serialize

from html5lib.treewalkers.base import TreeWalker

# pylint:disable=wrong-import-position

optionals_loaded = []

try:

from lxml import etree

optionals_loaded.append("lxml")

except ImportError:

pass

# pylint:enable=wrong-import-position

default_namespace = constants.namespaces["html"]

class JsonWalker(TreeWalker):

def __iter__(self):

for token in self.tree:

type = token[0]

if type == "StartTag":

if len(token) == 4:

namespace, name, attrib = token[1:4]

else:

namespace = default_namespace

name, attrib = token[1:3]

yield self.startTag(namespace, name, self._convertAttrib(attrib))

elif type == "EndTag":

if len(token) == 3:

namespace, name = token[1:3]

else:

namespace = default_namespace

name = token[1]

yield self.endTag(namespace, name)

elif type == "EmptyTag":

if len(token) == 4:

namespace, name, attrib = token[1:]

else:

namespace = default_namespace

name, attrib = token[1:]

for token in self.emptyTag(namespace, name, self._convertAttrib(attrib)):

yield token

elif type == "Comment":

yield self.comment(token[1])

elif type in ("Characters", "SpaceCharacters"):

for token in self.text(token[1]):

yield token

elif type == "Doctype":

if len(token) == 4:

yield self.doctype(token[1], token[2], token[3])

elif len(token) == 3:

yield self.doctype(token[1], token[2])

else:

yield self.doctype(token[1])

else:

raise ValueError("Unknown token type: " + type)

def _convertAttrib(self, attribs):

"""html5lib tree-walkers use a dict of (namespace, name): value for

attributes, but JSON cannot represent this. Convert from the format

in the serializer tests (a list of dicts with "namespace", "name",

and "value" as keys) to html5lib's tree-walker format."""

attrs = {}

for attrib in attribs:

name = (attrib["namespace"], attrib["name"])

assert(name not in attrs)

attrs[name] = attrib["value"]

return attrs

def serialize_html(input, options):

options = dict([(str(k), v) for k, v in options.items()])

encoding = options.get("encoding", None)

if "encoding" in options:

del options["encoding"]

stream = Lint(JsonWalker(input), False)

serializer = HTMLSerializer(alphabetical_attributes=True, **options)

return serializer.render(stream, encoding)

def runSerializerTest(input, expected, options):

encoding = options.get("encoding", None)

if encoding:

expected = list(map(lambda x: x.encode(encoding), expected))

result = serialize_html(input, options)

if len(expected) == 1:

assert expected[0] == result, "Expected:\n%s\nActual:\n%s\nOptions:\n%s" % (expected[0], result, str(options))

elif result not in expected:

assert False, "Expected: %s, Received: %s" % (expected, result)

def throwsWithLatin1(input):

with pytest.raises(UnicodeEncodeError):

serialize_html(input, {"encoding": "iso-8859-1"})

def testDoctypeName():

throwsWithLatin1([["Doctype", "\u0101"]])

def testDoctypePublicId():

throwsWithLatin1([["Doctype", "potato", "\u0101"]])

def testDoctypeSystemId():

throwsWithLatin1([["Doctype", "potato", "potato", "\u0101"]])

def testCdataCharacters():

runSerializerTest([["StartTag", "http://www.w3.org/1999/xhtml", "style", {}], ["Characters", "\u0101"]],

["<style>&amacr;"], {"encoding": "iso-8859-1"})

def testCharacters():

runSerializerTest([["Characters", "\u0101"]],

["&amacr;"], {"encoding": "iso-8859-1"})

def testStartTagName():

throwsWithLatin1([["StartTag", "http://www.w3.org/1999/xhtml", "\u0101", []]])

def testAttributeName():

throwsWithLatin1([["StartTag", "http://www.w3.org/1999/xhtml", "span", [{"namespace": None, "name": "\u0101", "value": "potato"}]]])

def testAttributeValue():

runSerializerTest([["StartTag", "http://www.w3.org/1999/xhtml", "span",

[{"namespace": None, "name": "potato", "value": "\u0101"}]]],

["<span potato=&amacr;>"], {"encoding": "iso-8859-1"})

def testEndTagName():

throwsWithLatin1([["EndTag", "http://www.w3.org/1999/xhtml", "\u0101"]])

def testComment():

throwsWithLatin1([["Comment", "\u0101"]])

def testThrowsUnknownOption():

with pytest.raises(TypeError):

HTMLSerializer(foobar=None)

@pytest.mark.parametrize("c", list("\t\n\u000C\x20\r\"'=<>`"))

def testSpecQuoteAttribute(c):

input_ = [["StartTag", "http://www.w3.org/1999/xhtml", "span",

[{"namespace": None, "name": "foo", "value": c}]]]

if c == '"':

output_ = ["<span foo='%s'>" % c]

else:

output_ = ['<span foo="%s">' % c]

options_ = {"quote_attr_values": "spec"}

runSerializerTest(input_, output_, options_)

@pytest.mark.parametrize("c", list("\t\n\u000C\x20\r\"'=<>`"

"\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n"

"\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15"

"\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"

"\x20\x2f\x60\xa0\u1680\u180e\u180f\u2000"

"\u2001\u2002\u2003\u2004\u2005\u2006\u2007"

"\u2008\u2009\u200a\u2028\u2029\u202f\u205f"

"\u3000"))

def testLegacyQuoteAttribute(c):

input_ = [["StartTag", "http://www.w3.org/1999/xhtml", "span",

[{"namespace": None, "name": "foo", "value": c}]]]

if c == '"':

output_ = ["<span foo='%s'>" % c]

else:

output_ = ['<span foo="%s">' % c]

options_ = {"quote_attr_values": "legacy"}

runSerializerTest(input_, output_, options_)

@pytest.fixture

def lxml_parser():

return etree.XMLParser(resolve_entities=False)

@pytest.mark.skipif("lxml" not in optionals_loaded, reason="lxml not importable")

def testEntityReplacement(lxml_parser):

doc = '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>'

tree = etree.fromstring(doc, parser=lxml_parser).getroottree()

result = serialize(tree, tree="lxml", omit_optional_tags=False)

assert result == '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>\u03B2</html>'

@pytest.mark.skipif("lxml" not in optionals_loaded, reason="lxml not importable")

def testEntityXML(lxml_parser):

doc = '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&gt;</html>'

tree = etree.fromstring(doc, parser=lxml_parser).getroottree()

result = serialize(tree, tree="lxml", omit_optional_tags=False)

assert result == '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&gt;</html>'

@pytest.mark.skipif("lxml" not in optionals_loaded, reason="lxml not importable")

def testEntityNoResolve(lxml_parser):

doc = '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>'

tree = etree.fromstring(doc, parser=lxml_parser).getroottree()

result = serialize(tree, tree="lxml", omit_optional_tags=False,

resolve_entities=False)

assert result == '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>'

def test_serializer():

for filename in get_data_files('serializer-testdata', '*.test', os.path.dirname(__file__)):

with open(filename) as fp:

tests = json.load(fp)

for test in tests['tests']:

yield runSerializerTest, test["input"], test["expected"], test.get("options", {})