Loads rules from a source file

[frenchie/icalparse.git] / icalparse.py

diff --git a/icalparse.py b/icalparse.py
index 713e9f3..1ed6076 100755 (executable)
--- a/icalparse.py
+++ b/icalparse.py
@@ -24,17 +24,26 @@ import sys
 import urlparse
 import os
 
+
 class InvalidICS(Exception): pass
 class notJoined(Exception): pass
+class IncompleteICS(InvalidICS): pass
+
 
 def lineJoiner(oldcal):
        '''Takes a string containing a calendar and returns an array of its lines'''
 
+       if not oldcal[0:15] == 'BEGIN:VCALENDAR':
+               raise InvalidICS, "Does not appear to be a valid ICS file"
+
+       if not 'END:VCALENDAR' in oldcal[-15:-1]:
+               raise IncompleteICS, "File appears to be incomplete"
+
        if list(oldcal) == oldcal:
                oldcal = '\r\n'.join(oldcal)
 
-       oldcal.replace('\r\n ', '')
-       return oldcal.split('\r\n')
+       oldcal = oldcal.replace('\r\n ', '').replace('\r\n\t','')
+       return oldcal.strip().split('\r\n')
 
 
 def lineFolder(oldcal, length=75):
@@ -60,6 +69,20 @@ def lineFolder(oldcal, length=75):
 
        return cal
 
+
+def splitFields(cal):
+       '''Takes a list of lines in a calendar file and returns a list of key, value pairs'''
+
+       ical = [tuple(x.split(':',1)) for x in cal]
+
+       # Check that we got 2 items on every line
+       for line in ical:
+               if not len(line) == 2:
+                       raise InvalidICS, "Didn't find a content key on: %s"%(line)
+
+       return ical
+
+
 def getContent(url='',stdin=False):
        '''Generic content retriever, DO NOT use this function in a CGI script as
        it can read from the local disk (which you probably don't want it to).
@@ -87,7 +110,7 @@ def getContent(url='',stdin=False):
                res = urllib2.urlopen(url)
                content = res.read()
                res.close()
-       except (urllib2.URLError, ValueError), e:
+       except (urllib2.URLError, OSError), e:
                sys.stderr.write('%s\n'%e)
                sys.exit(1)
        return content
@@ -121,12 +144,24 @@ def getHTTPContent(url='',cache='.httplib2-cache'):
        try:
                content = urllib2.urlopen(url).read()
                return content
-       except urllib2.URLError, e:
+       except (urllib2.URLError, OSError), e:
                sys.stderr.write('%s\n'%e)
                sys.exit(1)
 
        return ''
 
+
+def generateRules():
+       '''Attempts to load a series of rules into a list'''
+       try:
+               import parserrules
+       except ImportError:
+               return []
+
+       rules = [getattr(parserrules, rule) for rule in dir(parserrules) if callable(getattr(parserrules, rule))]
+       return rules
+
+
 if __name__ == '__main__':
        from optparse import OptionParser
        # If the user passed us a 'stdin' argument, we'll go with that,
@@ -149,3 +184,7 @@ if __name__ == '__main__':
                url = ''
 
        content = getContent(url, options.stdin)
+       cal = lineJoiner(content)
+       ical = splitFields(cal)
+       rules = generateRules()
+       print rules