mirror of
https://github.com/Hopiu/linkchecker.git
synced 2026-03-24 01:40:23 +00:00
9c1f09e451
git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@79 e7d03fd6-7b0d-0410-9947-9c21f3af8025
95 lines
3.3 KiB
Python
95 lines
3.3 KiB
Python
"""
|
|
Copyright (C) 2000 Bastian Kleineidam
|
|
|
|
This program is free software; you can redistribute it and/or modify
|
|
it under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; either version 2 of the License, or
|
|
(at your option) any later version.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
along with this program; if not, write to the Free Software
|
|
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
"""
|
|
import string,re
|
|
import UrlData
|
|
|
|
class ParseException(Exception):
|
|
pass
|
|
|
|
|
|
ws = re.compile("\s+")
|
|
regex_realUrl = re.compile("^Real URL.+")
|
|
regex_result = re.compile("^Result.+")
|
|
regex_base = re.compile("^Base.+")
|
|
regex_info = re.compile("^Info.+")
|
|
regex_warning = re.compile("^Warning.+")
|
|
regex_parentUrl = re.compile("^Parent URL.+")
|
|
regex_valid = re.compile("^Valid.*")
|
|
|
|
|
|
class OutputReader:
|
|
|
|
def resetState(self):
|
|
self.urlName = None
|
|
self.parentName = None
|
|
self.baseRef = None
|
|
self.info = None
|
|
self.warning = None
|
|
self.result = None
|
|
self.linenumber = 0
|
|
self.state = 0
|
|
|
|
def parse(self, file):
|
|
line = file.readline()
|
|
url = None
|
|
urls = []
|
|
self.resetState()
|
|
|
|
while line:
|
|
if ws.match(line):
|
|
if self.state>=2:
|
|
#append url
|
|
urldata = UrlData.GetUrlDataFrom(self.urlName, 0,
|
|
self.parentName, self.baseRef, self.linenumber)
|
|
if self.info:
|
|
urldata.setInfo(self.info)
|
|
if self.warning:
|
|
urldata.setWarning(self.info)
|
|
if OutputReader.regex_valid.match(self.result):
|
|
urldata.valid=1
|
|
urldata.validString = self.result
|
|
else:
|
|
urldata.valid=0
|
|
urldata.errorString = self.result
|
|
urls.append(urldata)
|
|
elif self.state:
|
|
raise ParseException, "No Real URL and Result keyword found"
|
|
self.resetState()
|
|
|
|
elif regex_realUrl.match(line):
|
|
self.state = self.state+1
|
|
self.urlName = string.strip(line[8:])
|
|
elif regex_result.match(line):
|
|
self.state = self.state+1
|
|
self.result = string.strip(line[6:])
|
|
elif regex_info.match(line):
|
|
self.info = string.strip(line[4:])
|
|
elif regex_base.match(line):
|
|
self.baseRef = string.strip(line[4:])
|
|
elif regex_warning.match(line):
|
|
self.warning = string.strip(line[7:])
|
|
elif regex_parentUrl.match(line):
|
|
self.parentName = string.strip(line[10:])
|
|
if ',' in self.parentName:
|
|
self.parentName,self.linenumber = string.split(self.parentName,",",1)
|
|
else:
|
|
pass
|
|
|
|
line = file.readline()
|
|
return urls
|
|
|