Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit8238648

Browse files
committed
Fix all the files outside of html5lib to flake8 cleanly
1 parent2c3b64b commit8238648

File tree

5 files changed

+80
-58
lines changed

5 files changed

+80
-58
lines changed

‎flake8-run.sh‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,5 +5,5 @@ if [[ ! -x $(which flake8) ]]; then
55
exit 1
66
fi
77

8-
flake8html5lib
8+
flake8`dirname$0`
99
exit$?

‎parse.py‎

Lines changed: 19 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,6 @@
55
"""
66

77
importsys
8-
importos
98
importtraceback
109
fromoptparseimportOptionParser
1110

@@ -15,17 +14,21 @@
1514
fromhtml5libimportconstants
1615
fromhtml5libimportutils
1716

17+
1818
defparse():
1919
optParser=getOptParser()
20-
opts,args=optParser.parse_args()
20+
opts,args=optParser.parse_args()
2121
encoding="utf8"
2222

2323
try:
2424
f=args[-1]
2525
# Try opening from the internet
2626
iff.startswith('http://'):
2727
try:
28-
importurllib.request,urllib.parse,urllib.error,cgi
28+
importurllib.request
29+
importurllib.parse
30+
importurllib.error
31+
importcgi
2932
f=urllib.request.urlopen(f)
3033
contentType=f.headers.get('content-type')
3134
ifcontentType:
@@ -41,7 +44,7 @@ def parse():
4144
try:
4245
# Try opening from file system
4346
f=open(f,"rb")
44-
exceptIOErrorase:
47+
exceptIOErrorase:
4548
sys.stderr.write("Unable to open file: %s\n"%e)
4649
sys.exit(1)
4750
exceptIndexError:
@@ -82,14 +85,15 @@ def parse():
8285
ifdocument:
8386
printOutput(p,document,opts)
8487
t2=time.time()
85-
sys.stderr.write("\n\nRun took: %fs (plus %fs to print the output)"%(t1-t0,t2-t1))
88+
sys.stderr.write("\n\nRun took: %fs (plus %fs to print the output)"%(t1-t0,t2-t1))
8689
else:
87-
sys.stderr.write("\n\nRun took: %fs"%(t1-t0))
90+
sys.stderr.write("\n\nRun took: %fs"%(t1-t0))
8891
else:
8992
document=run(parseMethod,f,encoding,opts.scripting)
9093
ifdocument:
9194
printOutput(p,document,opts)
9295

96+
9397
defrun(parseMethod,f,encoding,scripting):
9498
try:
9599
document=parseMethod(f,encoding=encoding,scripting=scripting)
@@ -98,6 +102,7 @@ def run(parseMethod, f, encoding, scripting):
98102
traceback.print_exc()
99103
returndocument
100104

105+
101106
defprintOutput(parser,document,opts):
102107
ifopts.encoding:
103108
print("Encoding:",parser.tokenizer.stream.charEncoding)
@@ -116,7 +121,7 @@ def printOutput(parser, document, opts):
116121
eliftb=="etree":
117122
sys.stdout.write(utils.default_etree.tostring(document))
118123
elifopts.tree:
119-
ifnothasattr(document,'__getitem__'):
124+
ifnothasattr(document,'__getitem__'):
120125
document= [document]
121126
forfragmentindocument:
122127
print(parser.tree.testSerializer(fragment))
@@ -126,7 +131,7 @@ def printOutput(parser, document, opts):
126131
kwargs= {}
127132
foroptinserializer.HTMLSerializer.options:
128133
try:
129-
kwargs[opt]=getattr(opts,opt)
134+
kwargs[opt]=getattr(opts,opt)
130135
except:
131136
pass
132137
ifnotkwargs['quote_char']:
@@ -142,12 +147,14 @@ def printOutput(parser, document, opts):
142147
encoding="utf-8"
143148
fortextinserializer.HTMLSerializer(**kwargs).serialize(tokens,encoding=encoding):
144149
sys.stdout.write(text)
145-
ifnottext.endswith('\n'):sys.stdout.write('\n')
150+
ifnottext.endswith('\n'):
151+
sys.stdout.write('\n')
146152
ifopts.error:
147-
errList=[]
153+
errList=[]
148154
forpos,errorcode,datavarsinparser.errors:
149-
errList.append("Line %i Col %i"%pos+" "+constants.E.get(errorcode,'Unknown error "%s"'%errorcode)%datavars)
150-
sys.stdout.write("\nParse errors:\n"+"\n".join(errList)+"\n")
155+
errList.append("Line %i Col %i"%pos+" "+constants.E.get(errorcode,'Unknown error "%s"'%errorcode)%datavars)
156+
sys.stdout.write("\nParse errors:\n"+"\n".join(errList)+"\n")
157+
151158

152159
defgetOptParser():
153160
parser=OptionParser(usage=__doc__)

‎setup.py‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
fromsetuptoolsimportsetup
66

77

8-
classifiers=[
8+
classifiers=[
99
'Development Status :: 5 - Production/Stable',
1010
'Intended Audience :: Developers',
1111
'License :: OSI Approved :: MIT License',
@@ -20,9 +20,9 @@
2020
'Programming Language :: Python :: 3.5',
2121
'Topic :: Software Development :: Libraries :: Python Modules',
2222
'Topic :: Text Processing :: Markup :: HTML'
23-
]
23+
]
2424

25-
packages= ['html5lib']+ ['html5lib.'+name
25+
packages= ['html5lib']+ ['html5lib.'+name
2626
fornameinos.listdir(os.path.join('html5lib'))
2727
ifos.path.isdir(os.path.join('html5lib',name))and
2828
notname.startswith('.')andname!='tests']
@@ -39,9 +39,9 @@
3939
assignments=filter(lambdax:isinstance(x,ast.Assign),t.body)
4040
forainassignments:
4141
if (len(a.targets)==1and
42-
isinstance(a.targets[0],ast.Name)and
43-
a.targets[0].id=="__version__"and
44-
isinstance(a.value,ast.Str)):
42+
isinstance(a.targets[0],ast.Name)and
43+
a.targets[0].id=="__version__"and
44+
isinstance(a.value,ast.Str)):
4545
version=a.value.s
4646

4747
setup(name='html5lib',

‎utils/entities.py‎

Lines changed: 31 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -2,57 +2,67 @@
22

33
importhtml5lib
44

5+
56
defparse(path="html5ents.xml"):
67
returnhtml5lib.parse(open(path),treebuilder="lxml")
78

9+
810
defentity_table(tree):
911
returndict((entity_name("".join(tr[0].xpath(".//text()"))),
1012
entity_characters(tr[1].text))
1113
fortrintree.xpath("//h:tbody/h:tr",
12-
namespaces={"h":"http://www.w3.org/1999/xhtml"}))
14+
namespaces={"h":"http://www.w3.org/1999/xhtml"}))
15+
1316

1417
defentity_name(inp):
1518
returninp.strip()
1619

20+
1721
defentity_characters(inp):
1822
return"".join(codepoint_to_character(item)
19-
foritemininp.split()
20-
ifitem)
23+
foritemininp.split()
24+
ifitem)
25+
2126

2227
defcodepoint_to_character(inp):
23-
return ("\U000"+inp[2:]).decode("unicode-escape")
28+
return ("\\U000"+inp[2:]).decode("unicode-escape")
29+
2430

2531
defmake_tests_json(entities):
2632
test_list=make_test_list(entities)
2733
tests_json= {"tests":
28-
[make_test(*item)foritemintest_list]
34+
[make_test(*item)foritemintest_list]
2935
}
3036
returntests_json
3137

38+
3239
defmake_test(name,characters,good):
3340
return {
34-
"description":test_description(name,good),
35-
"input":"&%s"%name,
36-
"output":test_expected(name,characters,good)
37-
}
41+
"description":test_description(name,good),
42+
"input":"&%s"%name,
43+
"output":test_expected(name,characters,good)
44+
}
45+
3846

3947
deftest_description(name,good):
4048
with_semicolon=name.endswith(";")
41-
semicolon_text= {True:"with a semi-colon",
42-
False:"without a semi-colon"}[with_semicolon]
49+
semicolon_text= {True:"with a semi-colon",
50+
False:"without a semi-colon"}[with_semicolon]
4351
ifgood:
44-
text="Named entity: %s %s"%(name,semicolon_text)
52+
text="Named entity: %s %s"%(name,semicolon_text)
4553
else:
46-
text="Bad named entity: %s %s"%(name,semicolon_text)
54+
text="Bad named entity: %s %s"%(name,semicolon_text)
4755
returntext
4856

57+
4958
deftest_expected(name,characters,good):
5059
rv= []
5160
ifnotgoodornotname.endswith(";"):
5261
rv.append("ParseError")
5362
rv.append(["Character",characters])
5463
returnrv
5564

65+
5666
defmake_test_list(entities):
5767
tests= []
5868
forentity_name,charactersinentities.items():
@@ -61,20 +71,23 @@ def make_test_list(entities):
6171
tests.append((entity_name,characters,True))
6272
returnsorted(tests)
6373

74+
6475
defsubentity_exists(entity_name,entities):
6576
foriinrange(1,len(entity_name)):
6677
ifentity_name[:-i]inentities:
6778
returnTrue
6879
returnFalse
6980

81+
7082
defmake_entities_code(entities):
71-
entities_text="\n".join("\"%s\": u\"%s\","%(
72-
name,entities[name].encode(
73-
"unicode-escape").replace("\"","\\\""))
74-
fornameinsorted(entities.keys()))
83+
entities_text="\n".join("\"%s\": u\"%s\","%(
84+
name,entities[name].encode(
85+
"unicode-escape").replace("\"","\\\""))
86+
fornameinsorted(entities.keys()))
7587
return"""entities = {
7688
%s
77-
}"""%entities_text
89+
}"""%entities_text
90+
7891

7992
defmain():
8093
entities=entity_table(parse())
@@ -85,4 +98,3 @@ def main():
8598

8699
if__name__=="__main__":
87100
main()
88-

‎utils/spider.py‎

Lines changed: 23 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,9 @@
77
s.spider("http://www.google.com", maxURLs=100)
88
"""
99

10-
importurllib.request,urllib.error,urllib.parse
10+
importurllib.request
11+
importurllib.error
12+
importurllib.parse
1113
importurllib.robotparser
1214
importmd5
1315

@@ -16,11 +18,13 @@
1618
importhtml5lib
1719
fromhtml5lib.treebuildersimportetree
1820

21+
1922
classSpider(object):
23+
2024
def__init__(self):
2125
self.unvisitedURLs=set()
2226
self.visitedURLs=set()
23-
self.buggyURLs=set()
27+
self.buggyURLs=set()
2428
self.robotParser=urllib.robotparser.RobotFileParser()
2529
self.contentDigest= {}
2630
self.http=httplib2.Http(".cache")
@@ -70,18 +74,18 @@ def updateURLs(self, tree):
7074
update the list of visited and unvisited URLs according to whether we
7175
have seen them before or not"""
7276
urls=set()
73-
#Remove all links we have already visited
77+
#Remove all links we have already visited
7478
forlinkintree.findall(".//a"):
75-
try:
76-
url=urllib.parse.urldefrag(link.attrib['href'])[0]
77-
if (urlandurlnotinself.unvisitedURLsandurl
79+
try:
80+
url=urllib.parse.urldefrag(link.attrib['href'])[0]
81+
if (urlandurlnotinself.unvisitedURLsandurl
7882
notinself.visitedURLs):
79-
urls.add(url)
80-
exceptKeyError:
81-
pass
83+
urls.add(url)
84+
exceptKeyError:
85+
pass
8286

83-
#Remove all non-http URLs and add a suitable base URL where that is
84-
#missing
87+
#Remove all non-http URLs and add a suitable base URL where that is
88+
#missing
8589
newUrls=set()
8690
forurlinurls:
8791
splitURL=list(urllib.parse.urlsplit(url))
@@ -93,23 +97,22 @@ def updateURLs(self, tree):
9397
urls=newUrls
9498

9599
responseHeaders= {}
96-
#Now we want to find the content types of the links we haven't visited
100+
#Now we want to find the content types of the links we haven't visited
97101
forurlinurls:
98102
try:
99103
resp,content=self.http.request(url,"HEAD")
100104
responseHeaders[url]=resp
101-
exceptAttributeErrorasKeyError:
102-
#Don't know why this happens
105+
exceptAttributeError:
106+
#Don't know why this happens
103107
pass
104108

105-
106-
#Remove links not of content-type html or pages not found
107-
#XXX - need to deal with other status codes?
109+
# Remove links not of content-type html or pages not found
110+
# XXX - need to deal with other status codes?
108111
toVisit=set([urlforurlinurlsifurlinresponseHeadersand
109-
"html"inresponseHeaders[url]['content-type']and
110-
responseHeaders[url]['status']=="200"])
112+
"html"inresponseHeaders[url]['content-type']and
113+
responseHeaders[url]['status']=="200"])
111114

112-
#Now check we are allowed to spider the page
115+
#Now check we are allowed to spider the page
113116
forurlintoVisit:
114117
robotURL=list(urllib.parse.urlsplit(url)[:2])
115118
robotURL.extend(["robots.txt","",""])

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp