8000 More support infrastructure · html5lib/html5lib-python@dfaa612 · GitHub
[go: up one dir, main page]
Skip to content

Commit dfaa612

Browse files
jgrahamjgraham
committed
More support infrastructure
--HG-- extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%40735
1 parent 9673c0c commit dfaa612

File tree

1 file changed

+94
-0
lines changed

1 file changed

+94
-0
lines changed

‎tests/support.py

Lines changed: 94 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,20 @@
66
os.chdir(os.path.split(os.path.abspath(__file__))[0])
77
sys.path.insert(0, os.path.abspath(os.path.join(os.pardir, "src")))
88

9+
#RELEASE remove
10+
import html5parser
11+
#Run tests over all treebuilders
12+
#XXX - it would be nice to automate finding all treebuilders or to allow running just one
13+
14+
import treebuilders
15+
#END RELEASE
16+
17+
#RELEASE add
18+
#import html5lib
19+
#from html5lib import html5parser
20+
#from html5lib.treebuilders import simpletree, etreefull, dom
21+
#END RELEASE
22+
923
try:
1024
import simplejson
1125
except:
@@ -17,5 +31,85 @@ def load(f):
1731
return eval(input.replace('\r',''))
1832
load = staticmethod(load)
1933

34+
#Build a dict of avaliable trees
35+
treeTypes = {"simpletree":treebuilders.getTreeBuilder("simpletree"),
36+
"DOM":treebuilders.getTreeBuilder("dom")}
37+
38+
#Try whatever etree implementations are avaliable from a list that are
39+
#"supposed" to work
40+
try:
41+
import xml.etree.ElementTree as ElementTree
42+
treeTypes['ElementTree'] = treebuilders.getTreeBuilder("etree", ElementTree, fullTree=True)
43+
except ImportError:
44+
try:
45+
import elementtree.ElementTree as ElementTree
46+
treeTypes['ElementTree'] = treebuilders.getTreeBuilder("etree", ElementTree, fullTree=True)
47+
except ImportError:
48+
pass
49+
50+
try:
51+
import xml.etree.cElementTree as cElementTree
52+
treeTypes['cElementTree'] = treebuilders.getTreeBuilder("etree", cElementTree, fullTree=True)
53+
except ImportError:
54+
try:
55+
import cElementTree
56+
treeTypes['cElementTree'] = treebuilders.getTreeBuilder("etree", cElementTree, fullTree=True)
57+
except ImportError:
58+
pass
59+
60+
try:
61+
import lxml.etree as lxml
62+
treeTypes['lxml'] = treebuilders.getTreeBuilder("etree", lxml, fullTree=True)
63+
except ImportError:
64+
pass
65+
66+
try:
67+
import BeautifulSoup
68+
treeTypes["beautifulsoup"] = treebuilders.getTreeBuilder("beautifulsoup", fullTree=True)
69+
except ImportError:
70+
pass
71+
2072
def html5lib_test_files(subdirectory, files='*.dat'):
2173
return glob.glob(os.path.join(os.path.pardir,os.path.pardir,'testdata',subdirectory,files))
74+
75+
class TestData(object):
76+
def __init__(self, filename, sections):
77+
self.f = open(filename)
78+
self.sections = sections
79+
80+
def __iter__(self):
81+
data = {}
82+
key=None
83+
for line in self.f:
84+
heading = self.isSectionHeading(line)
85+
if heading:
86+
if data and heading == self.sections[0]:
87+
#Remove trailing newline
88+
data[key] = data[key][:-1]
89+
yield self.normaliseOutput(data)
90+
data = {}
91+
key = heading
92+
data[key]=""
93+
elif key is not None:
94+
data[key] += line
95+
if data:
96+
yield self.normaliseOutput(data)
97+
98+
def isSectionHeading(self, line):
99+
"""If the current heading is a test section heading return the heading,
100+
otherwise return False"""
101+
line=line.strip()
102+
if line.startswith("#") and line[1:] in self.sections:
103+
return line[1:]
104+
else:
105+
return False
106+
107+
def normaliseOutput(self, data):
108+
#Remove trailing newlines
109+
for key,value in data.iteritems():
110+
if value.endswith("\n"):
111+
data[key] = value[:-1]
112+
for heading in self.sections:
113+
if heading not in data:
114+
data[heading] = None
115+
return data

0 commit comments

Comments
 (0)
0