Hopiu/linkchecker
1
0
Fork 0
mirror of https://github.com/Hopiu/linkchecker.git synced 2026-04-23 23:54:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

release 1.2.13

Browse source 
git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@222 e7d03fd6-7b0d-0410-9947-9c21f3af8025
This commit is contained in:
calvin 2001-01-07 13:28:38 +00:00
parent d82d4c4d97
commit 7f226fc478
12 changed files with 210 additions and 149 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
Makefile
View file

@ -45,7 +45,7 @@ package:
cd dist && dpkg-scanpackages . ../override.txt | gzip --best > Packages.gz
files: locale
./$(PACKAGE) $(LCOPTS) -i$(HOST) http://$(HOST)/~calvin/
env http_proxy="" ./$(PACKAGE) $(LCOPTS) -i$(HOST) http://$(HOST)/~calvin/
VERSION:
echo $(VERSION) > VERSION

1
create.sql
View file

@ -14,5 +14,6 @@ create table linksdb (
valid int,
url varchar(50),
line int,
name varchar(50),
cached int
);

8
debian/changelog vendored
View file

@ -11,8 +11,14 @@ linkchecker (1.2.13) unstable; urgency=low
- two licenses: GPL and Python 2.0
* linkcheck/__init__.py: user friendly warning for keyboard interrupts
* debian/control: standards version 3.2.1
* support Mozilla-specific find: links
* print link names for:
- <a href> links (<a href="..">link name</a>)
- <img> links (the alt= attribute)
this makes it easier for bookmarks.html files to find the link
WARNING: this changed the output format!
-- Bastian Kleineidam <calvin@users.sourceforge.net> Sat, 6 Jan 2001 18:57:43 +0100
-- Bastian Kleineidam <calvin@users.sourceforge.net> Sun, 7 Jan 2001 12:51:19 +0100
linkchecker (1.2.12) unstable; urgency=low

1
linkcheck/Config.py
View file

@ -124,6 +124,7 @@ class Configuration(UserDict.UserDict):
"filename": "linkchecker-out.ansi",
'colorparent': ESC+"[37m", # white
'colorurl': ESC+"[0m", # standard
'colorname': ESC+"[0m", # standard
'colorreal': ESC+"[36m", # cyan
'colorbase': ESC+"[35m", # magenty
'colorvalid': ESC+"[1;32m", # green

4
linkcheck/FileUrlData.py
View file

@ -29,12 +29,12 @@ class FileUrlData(UrlData):
urlName,
recursionLevel,
parentName = None,
baseRef = None, line=0):
baseRef = None, line=0, name=""):
UrlData.__init__(self,
urlName,
recursionLevel,
parentName=parentName,
baseRef=baseRef, line=line)
baseRef=baseRef, line=line, name=name)
if not parentName and not baseRef and \
not re.compile("^file:").search(self.urlName):
self.urlName = os.path.expanduser(self.urlName)

10
linkcheck/HostCheckingUrlData.py
View file

@ -23,13 +23,11 @@ from linkcheck import _
class HostCheckingUrlData(UrlData):
"Url link for which we have to connect to a specific host"
def __init__(self,
urlName,
recursionLevel,
parentName = None,
baseRef = None, line=0):
def __init__(self, urlName, recursionLevel, parentName = None,
baseRef = None, line=0, name=""):
UrlData.__init__(self, urlName, recursionLevel,
parentName=parentName, baseRef=baseRef, line=line)
parentName=parentName, baseRef=baseRef, line=line,
name=name)
self.host = None
self.url = urlName

99
linkcheck/Logging.py
View file

@ -41,13 +41,11 @@ import Config, StringUtil
import linkcheck
_ = linkcheck._
# HTML shortcuts
RowEnd="</td></tr>\n"
# keywords
KeyWords = ["Real URL",
"Result",
"Base",
"Name",
"Parent URL",
"Info",
"Warning",
@ -109,44 +107,46 @@ class StandardLogger:
self.fd.flush()
def newUrl(self, urldata):
self.fd.write("\n"+_("URL")+Spaces["URL"]+urldata.urlName)
if urldata.cached:
def newUrl(self, urlData):
self.fd.write("\n"+_("URL")+Spaces["URL"]+urlData.urlName)
if urlData.cached:
self.fd.write(_(" (cached)\n"))
else:
self.fd.write("\n")
if urldata.parentName:
if urlData.name:
self.fd.write(_("Name")+Spaces["Name"]+urlData.name+"\n")
if urlData.parentName:
self.fd.write(_("Parent URL")+Spaces["Parent URL"]+
urldata.parentName+_(", line ")+
str(urldata.line)+"\n")
if urldata.baseRef:
self.fd.write(_("Base")+Spaces["Base"]+urldata.baseRef+"\n")
if urldata.url:
self.fd.write(_("Real URL")+Spaces["Real URL"]+urldata.url+"\n")
if urldata.downloadtime:
urlData.parentName+_(", line ")+
str(urlData.line)+"\n")
if urlData.baseRef:
self.fd.write(_("Base")+Spaces["Base"]+urlData.baseRef+"\n")
if urlData.url:
self.fd.write(_("Real URL")+Spaces["Real URL"]+urlData.url+"\n")
if urlData.downloadtime:
self.fd.write(_("D/L Time")+Spaces["D/L Time"]+
_("%.3f seconds\n") % urldata.downloadtime)
if urldata.checktime:
_("%.3f seconds\n") % urlData.downloadtime)
if urlData.checktime:
self.fd.write(_("Check Time")+Spaces["Check Time"]+
_("%.3f seconds\n") % urldata.checktime)
if urldata.infoString:
_("%.3f seconds\n") % urlData.checktime)
if urlData.infoString:
self.fd.write(_("Info")+Spaces["Info"]+
StringUtil.indent(
StringUtil.blocktext(urldata.infoString, 65),
StringUtil.blocktext(urlData.infoString, 65),
MaxIndent)+"\n")
if urldata.warningString:
if urlData.warningString:
self.warnings = self.warnings+1
self.fd.write(_("Warning")+Spaces["Warning"]+
StringUtil.indent(
StringUtil.blocktext(urldata.warningString, 65),
StringUtil.blocktext(urlData.warningString, 65),
MaxIndent)+"\n")
self.fd.write(_("Result")+Spaces["Result"])
if urldata.valid:
self.fd.write(urldata.validString+"\n")
if urlData.valid:
self.fd.write(urlData.validString+"\n")
else:
self.errors = self.errors+1
self.fd.write(urldata.errorString+"\n")
self.fd.write(urlData.errorString+"\n")
self.fd.flush()
@ -207,7 +207,7 @@ class HtmlLogger(StandardLogger):
"body { font-family: Arial,sans-serif; font-size: 11pt }\n"
"td { font-family: Arial,sans-serif; font-size: 11pt }\n"
"code { font-family: Courier }\n"
"a:hover { color: #34a4ef }\n"
"a:hover { color: #34a4ef }\n"
"//-->\n</style>\n</head>\n"+
"<body bgcolor="+self.colorbackground+" link="+self.colorlink+
" vlink="+self.colorlink+" alink="+self.colorlink+">"+
@ -224,47 +224,53 @@ class HtmlLogger(StandardLogger):
'><tr><td><table align="left" border="0" cellspacing="0"'
' cellpadding="3" summary="checked link" bgcolor='+
self.colorbackground+
"><tr><td bgcolor="+self.colorurl+">"+
"URL</td><td bgcolor="+self.colorurl+">"+urlData.urlName)
"><tr><td bgcolor="+self.colorurl+">"+_("URL")+
"</td><td bgcolor="+self.colorurl+">"+urlData.urlName)
if urlData.cached:
self.fd.write(_(" (cached)\n"))
self.fd.write(RowEnd)
self.fd.write("</td></tr>\n")
if urlData.name:
self.fd.write("<tr><td>"+_("Name")+"</td><td>"+
urlData.name+"</td></tr>\n")
if urlData.parentName:
self.fd.write("<tr><td>"+_("Parent URL")+"</td><td>"+
'<a href="'+urlData.parentName+'">'+
urlData.parentName+"</a> line "+str(urlData.line)+
RowEnd)
"</td></tr>\n")
if urlData.baseRef:
self.fd.write("<tr><td>"+_("Base")+"</td><td>"+
urlData.baseRef+RowEnd)
urlData.baseRef+"</td></tr>\n")
if urlData.url:
self.fd.write("<tr><td>"+_("Real URL")+"</td><td>"+
"<a href=\""+urlData.url+
'">'+urlData.url+"</a>"+RowEnd)
'">'+urlData.url+"</a></td></tr>\n")
if urlData.downloadtime:
self.fd.write("<tr><td>"+_("D/L Time")+"</td><td>"+
(_("%.3f seconds") % urlData.downloadtime)+RowEnd)
(_("%.3f seconds") % urlData.downloadtime)+
"</td></tr>\n")
if urlData.checktime:
self.fd.write("<tr><td>"+_("Check Time")+
"</td><td>"+
(_("%.3f seconds") % urlData.checktime)+RowEnd)
(_("%.3f seconds") % urlData.checktime)+
"</td></tr>\n")
if urlData.infoString:
self.fd.write("<tr><td>"+_("Info")+"</td><td>"+
StringUtil.htmlify(urlData.infoString)+RowEnd)
StringUtil.htmlify(urlData.infoString)+
"</td></tr>\n")
if urlData.warningString:
self.warnings = self.warnings+1
self.fd.write("<tr>"+self.tablewarning+_("Warning")+
"</td>"+self.tablewarning+
urlData.warningString+RowEnd)
string.replace(urlData.warningString,"\n", "<br>")+
"</td></tr>\n")
if urlData.valid:
self.fd.write("<tr>"+self.tableok+_("Result")+"</td>"+
self.tableok+urlData.validString+RowEnd)
self.tableok+urlData.validString+"</td></tr>\n")
else:
self.errors = self.errors+1
self.fd.write("<tr>"+self.tableerror+_("Result")+
"</td>"+self.tableerror+
urlData.errorString++RowEnd)
urlData.errorString+"</td></tr>\n")
self.fd.write("</table></td></tr></table><br clear=all><br>")
self.fd.flush()
@ -316,6 +322,7 @@ class ColoredLogger(StandardLogger):
apply(StandardLogger.__init__, (self,), args)
self.colorparent = args['colorparent']
self.colorurl = args['colorurl']
self.colorname = args['colorname']
self.colorreal = args['colorreal']
self.colorbase = args['colorbase']
self.colorvalid = args['colorvalid']
@ -354,7 +361,12 @@ class ColoredLogger(StandardLogger):
self.fd.write(_(" (cached)\n"))
else:
self.fd.write("\n")
if urlData.name:
if self.prefix:
self.fd.write("| ")
self.fd.write(_("Name")+Spaces["Name"]+self.colorname+
urlData.name+self.colorreset+"\n")
if urlData.baseRef:
if self.prefix:
self.fd.write("| ")
@ -590,8 +602,8 @@ class SQLLogger(StandardLogger):
def newUrl(self, urlData):
self.fd.write("insert into %s(urlname,recursionlevel,parentname,"
"baseref,errorstring,validstring,warningstring,infoString,"
"valid,url,line,checktime,downloadtime,cached) values "
"(%s,%d,%s,%s,%s,%s,%s,%s,%d,%s,%d,%d,%d,%d)%s\n" % \
"valid,url,line,name,checktime,downloadtime,cached) values "
"(%s,%d,%s,%s,%s,%s,%s,%s,%d,%s,%d,%s,%d,%d,%d)%s\n" % \
(self.dbname,
StringUtil.sqlify(urlData.urlName),
urlData.recursionLevel,
@ -604,6 +616,7 @@ class SQLLogger(StandardLogger):
urlData.valid,
StringUtil.sqlify(urlData.url),
urlData.line,
StringUtil.sqlify(urlData.name),
urlData.checktime,
urlData.downloadtime,
urlData.cached,
@ -682,6 +695,7 @@ class CSVLogger(StandardLogger):
"# valid;\n"
"# url;\n"
"# line;\n"
"# name;\n"
"# downloadtime;\n"
"# checktime;\n"
"# cached;\n")
@ -689,7 +703,7 @@ class CSVLogger(StandardLogger):
def newUrl(self, urlData):
self.fd.write(
"%s%s%d%s%s%s%s%s%s%s%s%s%s%s%s%s%d%s%s%s%d%s%d%s%d%s%d\n" % (
"%s%s%d%s%s%s%s%s%s%s%s%s%s%s%s%s%d%s%s%s%d%s%s%s%d%s%d%s%d\n" % (
urlData.urlName, self.separator,
urlData.recursionLevel, self.separator,
urlData.parentName, self.separator,
@ -701,6 +715,7 @@ class CSVLogger(StandardLogger):
urlData.valid, self.separator,
urlData.url, self.separator,
urlData.line, self.separator,
urlData.name, self.separator,
urlData.downloadtime, self.separator,
urlData.checktime, self.separator,
urlData.cached))

33
linkcheck/StringUtil.py
View file

@ -15,24 +15,17 @@
along with this program; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
"""
import string,re,sys
import string,re,sys,htmlentitydefs
HtmlTable = [
("ä","&auml;"),
("ö","&ouml;"),
("ü","&uuml;"),
("Ä","&Auml;"),
("Ö","&Ouml;"),
("Ü","&Uuml;"),
("ß","&szlig;"),
("&","&amp;"),
("<","&lt;"),
(">","&gt;"),
("é","&eacute;"),
("è","&egrave;"),
("à","&agrave;"),
("ç","&ccedil;"),
]
HtmlTable = []
UnHtmlTable = []
for ent,ch in htmlentitydefs.entitydefs.items():
HtmlTable.append((ch, "&"+ent+";"))
UnHtmlTable.append(("&"+ent+";", ch))
# order matters!
HtmlTable.sort()
UnHtmlTable.sort()
UnHtmlTable.reverse()
SQLTable = [
("'","''")
@ -160,6 +153,8 @@ def htmlify(str):
"Escape special HTML chars and strings"
return applyTable(HtmlTable, str)
def unhtmlify(str):
return applyTable(UnHtmlTable, str)
def getLineNumber(str, index):
"return the line number of str[index]"
@ -184,3 +179,7 @@ def paginate(text, lines=22):
print "press return to continue..."
sys.stdin.read(1)
if __name__=='__main__':
print htmlify("äöü")
print unhtmlify("&auml;&nbsp;&auml;&amp;auml;")

155
linkcheck/UrlData.py
View file

@ -52,19 +52,25 @@ _linkMatcher = r"""
> # close tag
"""
LinkPatterns = (
re.compile(_linkMatcher % ("a", "href"), re.VERBOSE),
re.compile(_linkMatcher % ("img", "src"), re.VERBOSE),
re.compile(_linkMatcher % ("form", "action"), re.VERBOSE),
re.compile(_linkMatcher % ("body", "background"), re.VERBOSE),
re.compile(_linkMatcher % ("frame", "src"), re.VERBOSE),
re.compile(_linkMatcher % ("link", "href"), re.VERBOSE),
# <meta http-equiv="refresh" content="x; url=...">
re.compile(_linkMatcher % ("meta", "url"), re.VERBOSE),
re.compile(_linkMatcher % ("area", "href"), re.VERBOSE),
re.compile(_linkMatcher % ("script", "src"), re.VERBOSE),
LinkTags = (
("a", "href"),
("img", "src"),
("form", "action"),
("body", "background"),
("frame", "src"),
("link", "href"),
("meta", "url"), # <meta http-equiv="refresh" content="x; url=...">
("area", "href"),
("script", "src"),
)
LinkPatterns = []
for tag,attr in LinkTags:
pattern = re.compile(_linkMatcher % (tag, attr), re.VERBOSE)
pattern.tag = tag
pattern.attr = attr
LinkPatterns.append(pattern)
class UrlData:
"Representing a URL with additional information like validity etc"
@ -73,7 +79,8 @@ class UrlData:
recursionLevel,
parentName = None,
baseRef = None,
line = 0):
line = 0,
name = ""):
self.urlName = urlName
self.recursionLevel = recursionLevel
self.parentName = parentName
@ -85,6 +92,7 @@ class UrlData:
self.valid = 1
self.url = None
self.line = line
self.name = name
self.downloadtime = 0
self.checktime = 0
self.cached = 0
@ -252,8 +260,10 @@ class UrlData:
if not (anchor!="" and self.isHtml() and self.valid):
return
self.getContent()
for cur_anchor,line in self.searchInForTag(
re.compile(_linkMatcher % ("a", "name"), re.VERBOSE)):
pattern = re.compile(_linkMatcher % ("a", "name"), re.VERBOSE)
pattern.tag = "a"
pattern.attr = "name"
for cur_anchor,line in self.searchInForTag(pattern):
if cur_anchor == anchor:
return
self.setWarning("anchor #"+anchor+" not found")
@ -321,8 +331,11 @@ class UrlData:
debug(Config.DebugDelim+"Parsing recursively into\n"+\
str(self)+"\n"+Config.DebugDelim)
# search for a possible base reference
bases = self.searchInForTag(re.compile(_linkMatcher % ("base",
"href"), re.VERBOSE))
pattern = re.compile(_linkMatcher % ("base", "href"), re.VERBOSE)
pattern.tag = "base"
pattern.attr = "href"
bases = self.searchInForTag(pattern)
baseRef = None
if len(bases)>=1:
baseRef = bases[0][0]
@ -332,12 +345,14 @@ class UrlData:
# search for tags and add found tags to URL queue
for pattern in LinkPatterns:
urls = self.searchInForTag(pattern)
for url,line in urls:
for url,line,name in urls:
config.appendUrl(GetUrlDataFrom(url,
self.recursionLevel+1, self.url, baseRef, line))
self.recursionLevel+1, self.url, baseRef, line, name))
def searchInForTag(self, pattern):
debug("Searching for tag %s, attribute %s" \
% (pattern.tag, pattern.attr))
urls = []
index = 0
while 1:
@ -346,26 +361,46 @@ class UrlData:
index = match.end()
if self._isInComment(match.start()): continue
# need to strip optional ending quotes for the meta tag
urls.append((string.strip(StringUtil.stripQuotes(match.group('value'))),
StringUtil.getLineNumber(self.getContent(),
match.start())))
url = string.strip(StringUtil.stripQuotes(match.group('value')))
lineno=StringUtil.getLineNumber(self.getContent(), match.start())
# extra feature: get optional name for this bookmark
name = self.searchInForName(pattern.tag, pattern.attr,
match.start(), match.end())
urls.append((url, lineno, name))
return urls
def searchInForName(self, tag, attr, start, end):
name=""
if tag=='img':
all = self.getContent()[start:end]
mo = re.search("(?i)\s+alt\s*=\s*(?P<name>(\".+?\"|[^\s>]+))", all)
if mo:
name = StringUtil.stripQuotes(mo.group('name'))
name = StringUtil.unhtmlify(name)
elif tag=='a' and attr=='href':
all = self.getContent()[end:]
mo = re.search("(?i)(?P<name>.*?)</a\s*>", all)
if mo:
name = mo.group('name')
return name
def get_scheme(self):
return "no"
return "none"
def __str__(self):
return """%s link
urlname=%s
parentName=%s
baseRef=%s
cached=%s
recursionLevel=%s
urlConnection=%s
line=%s""" % \
(self.get_scheme(), self.urlName, self.parentName, self.baseRef,
self.cached, self.recursionLevel, self.urlConnection, self.line)
return ("%s link\n"
"urlname=%s\n"
"parentName=%s\n"
"baseRef=%s\n"
"cached=%s\n"
"recursionLevel=%s\n"
"urlConnection=%s\n"
"line=%s\n"
"name=%s" % \
(self.get_scheme(), self.urlName, self.parentName, self.baseRef,
self.cached, self.recursionLevel, self.urlConnection, self.line,
self.name))
def _getUserPassword(self, config):
@ -376,6 +411,7 @@ line=%s""" % \
from FileUrlData import FileUrlData
from FindUrlData import FindUrlData
from FtpUrlData import FtpUrlData
from GopherUrlData import GopherUrlData
from HttpUrlData import HttpUrlData
@ -385,37 +421,38 @@ from MailtoUrlData import MailtoUrlData
from TelnetUrlData import TelnetUrlData
from NntpUrlData import NntpUrlData
def GetUrlDataFrom(urlName,
recursionLevel,
parentName = None,
baseRef = None, line = 0):
def GetUrlDataFrom(urlName, recursionLevel, parentName = None,
baseRef = None, line = 0, name = None):
# search for the absolute url
name=""
url=""
if urlName and ":" in urlName:
name = string.lower(urlName)
url = string.lower(urlName)
elif baseRef and ":" in baseRef:
name = string.lower(baseRef)
url = string.lower(baseRef)
elif parentName and ":" in parentName:
name = string.lower(parentName)
url = string.lower(parentName)
# test scheme
if re.search("^http:", name):
return HttpUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^ftp:", name):
return FtpUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^file:", name):
return FileUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^telnet:", name):
return TelnetUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^mailto:", name):
return MailtoUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^gopher:", name):
return GopherUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^javascript:", name):
return JavascriptUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^https:", name):
return HttpsUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^(s?news|nntp):", name):
return NntpUrlData(urlName, recursionLevel, parentName, baseRef, line)
if re.search("^http:", url):
return HttpUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^ftp:", url):
return FtpUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^file:", url):
return FileUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^telnet:", url):
return TelnetUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^mailto:", url):
return MailtoUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^gopher:", url):
return GopherUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^javascript:", url):
return JavascriptUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^https:", url):
return HttpsUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
if re.search("^(s?news|nntp):", url):
return NntpUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
# Mozillas Technology links start with "find:"
if re.search("^find:", url):
return FindUrlData(urlName, recursionLevel, parentName, baseRef, line, name)
# assume local file
return FileUrlData(urlName, recursionLevel, parentName, baseRef, line)
return FileUrlData(urlName, recursionLevel, parentName, baseRef, line, name)

3
po/de.po
View file

@ -130,6 +130,9 @@ msgstr "Sekunden"
msgid "URL"
msgstr "URL"
msgid "Name"
msgstr ""
msgid "URL is null or empty"
msgstr "URL ist Null oder leer"

3
po/fr.po
View file

@ -122,6 +122,9 @@ msgstr "secondes"
msgid "URL"
msgstr ""
msgid "Name"
msgstr ""
msgid "URL is null or empty"
msgstr "L'URL est nulle ou vide"

40
test/test1.html
View file

@ -1,25 +1,23 @@
Just some HTTP links
<a href="http://www.garantiertnixgutt.bla"> <!-- bad url -->
<a href="http://www.heise.de"> <!-- ok -->
<a href="http:/www.heise.de"> <!-- one slash -->
<a href="http:www.heise.de"> <!-- no slash -->
<a href="http://"> <!-- no url -->
<a href="http:/"> <!-- no url, one slash -->
<a href="http:"> <!-- no url, no slash -->
<a href="http://www.blubb.de/stalter&sohn"> <!-- unquoted ampersand -->
<a name="iswas"> <!-- anchor for test2.html -->
<a href=http://slashdot.org/> <!-- unquoted -->
<!-- invalid anchor -->
<a href="http://treasure.calvinsplayground.de/~calvin/software/#isnix">
<!-- authorization (user=calvin, pass=calvin) -->
<a href="http://treasure.calvinsplayground.de/~calvin/isnich/">
<a href="https://www.heise.de"> <!-- https -->
<a href="HtTP://WWW.hEIsE.DE"> <!-- should be cached -->
<a href="HTTP://WWW.HEISE.DE"> <!-- should be cached -->
<a href="http://www.garantiertnixgutt.bla">bad url</a>
<a href="http://www.heise.de">ok</a>
<a href="http:/www.heise.de">one slash</a>
<a href="http:www.heise.de">no slash</a>
<a href="http://">no url</a>
<a href="http:/">no url, one slash</a>
<a href="http:">no url, no slash</a>
<a href="http://www.blubb.de/stalter&sohn">unquoted ampersand</a>
<a name="iswas">anchor for test2.html</a>
<a href=http://slashdot.org/>unquoted</a>
<a href="http://treasure.calvinsplayground.de/~calvin/software/#isnix"
>invalid anchor</a>
<a href="http://treasure.calvinsplayground.de/~calvin/isnich/"
>authorization (user=calvin, pass=calvin)</a>
<a href="https://www.heise.de">https</a>
<a href="HtTP://WWW.hEIsE.DE">should be cached</a>
<a href="HTTP://WWW.HEISE.DE">should be cached</a>
<!-- <a href=http://nocheckin> no check because of comment -->
<!-- no beginning quote -->
<a href=illegalquote1">
<!-- no ending quote -->
<a href="illegalquote2>
<a href=illegalquote1">no beginning quote</a>
<a href="illegalquote2>no ending quote</a>
<!-- check the parser at end of file -->
<a href="g