FOAF reading lists

examples/opml-top100.ini

@@ -28,12 +28,11 @@ items_per_page = 60
 
 activity_threshold = 90
 
-# Reading lists, one per line, indented
-reading_lists =
-  http://share.opml.org/opml/top100.opml
-
 filters = excerpt.py
 
 [excerpt.py]
 omit = img p br
 width = 500
+
+[http://share.opml.org/opml/top100.opml]
+content_type = opml

planet/config.py

@@ -103,12 +103,12 @@ def __init__():
     define_planet_list('template_directories')
     define_planet_list('filters')
     define_planet_list('filter_directories')
-    define_planet_list('reading_lists')
 
     # template options
     define_tmpl_int('days_per_page', 0)
     define_tmpl_int('items_per_page', 60)
     define_tmpl('encoding', 'utf-8')
+    define_tmpl('content_type', 'utf-8')
 
 def load(config_file):
     """ initialize and load a configuration"""
@@ -117,7 +117,7 @@ def load(config_file):
     parser.read(config_file)
 
     import config, planet
-    from planet import opml
+    from planet import opml, foaf
     log = planet.getLogger(config.log_level())
 
     # Theme support
@@ -173,7 +173,10 @@ def load(config_file):
                 # read once to verify
                 data=StringIO.StringIO(urllib.urlopen(list).read())
                 cached_config = ConfigParser()
-                opml.opml2config(data, cached_config)
+                if content_type(list).find('opml')>=0:
+                    opml.opml2config(data, cached_config)
+                elif content_type(list).find('foaf')>=0:
+                    foaf.foaf2config(data, cached_config)
                 if not cached_config.sections(): raise Exception
 
                 # write to cache
@@ -184,7 +187,7 @@ def load(config_file):
                 # re-parse and proceed
                 log.debug("Using %s readinglist", list) 
                 data.seek(0)
-                opml.opml2config(data, parser)
+                parser.read(cache_filename)
             except:
                 try:
                     parser.read(cache_filename)
@@ -226,7 +229,18 @@ def feedtype():
 def subscriptions():
     """ list the feed subscriptions """
     return filter(lambda feed: feed!='Planet' and 
-        feed not in template_files()+filters(), parser.sections())
+        feed not in template_files()+filters()+reading_lists(),
+        parser.sections())
+
+def reading_lists():
+    """ list of lists of feed subscriptions """
+    result = []
+    for section in parser.sections():
+        if parser.has_option(section, 'content_type'):
+            type = parser.get(section, 'content_type')
+            if type.find('opml')>=0 or type.find('foaf')>=0:
+                result.append(section)
+    return result
 
 def planet_options():
     """ dictionary of planet wide options"""

planet/foaf.py

@@ -0,0 +1,56 @@
+from ConfigParser import ConfigParser
+
+# input = foaf, output = ConfigParser
+def foaf2config(rdf, baseuri, config=None):
+
+    if not config:
+        config = ConfigParser()
+
+    try:
+        from RDF import Model, NS, Parser, Statement
+    except:
+        return config
+
+    if hasattr(rdf, 'read'):
+        rdf = rdf.read()
+
+    model = Model()
+    def handler(code, level, facility, message, line, column, byte, file, uri):
+        pass
+    Parser().parse_string_into_model(model,rdf,baseuri,handler)
+
+    dc   = NS('http://purl.org/dc/elements/1.1/')
+    foaf = NS('http://xmlns.com/foaf/0.1/')
+    rdfs = NS('http://www.w3.org/2000/01/rdf-schema#')
+
+    for statement in model.find_statements(Statement(None,foaf.weblog,None)):
+        feed = model.get_target(statement.object,rdfs.seeAlso)
+        if not feed: continue
+
+        title = model.get_target(statement.subject,foaf.name)
+        if not title: title = model.get_target(statement.object,dc.title)
+        if not title: continue
+
+        feed = str(feed.uri)
+        if not config.has_section(feed):
+            config.add_section(feed)
+            config.set(feed, 'name', str(title))
+
+    return config
+
+if __name__ == "__main__":
+    import sys, urllib
+    config = ConfigParser()
+
+    for uri in sys.argv[1:]:
+        foaf2config(urllib.urlopen(uri), uri, config)
+
+    config.write(sys.stdout)
+
+if __name__ == "__main__":
+    # small main program which converts FOAF into config.ini format
+    import sys, urllib
+    config = ConfigParser()
+    for foaf in sys.argv[1:]:
+        foaf2config(urllib.urlopen(foaf), config)
+    config.write(sys.stdout)

planet/opml.py

@@ -140,3 +140,11 @@ cp1252 = {
   unichr(156): unichr( 339), # latin small ligature oe
   unichr(158): unichr( 382), # latin small letter z with caron
   unichr(159): unichr( 376)} # latin capital letter y with diaeresis
+
+if __name__ == "__main__":
+    # small main program which converts OPML into config.ini format
+    import sys, urllib
+    config = ConfigParser()
+    for opml in sys.argv[1:]:
+        opml2config(urllib.urlopen(opml), config)
+    config.write(sys.stdout)

tests/data/config/rlist.ini

@@ -2,4 +2,6 @@
 name = Test Configuration
 output_theme = asf
 cache_directory = tests/work/config/cache
-reading_lists = tests/data/config/opml.xml
+
+[tests/data/config/opml.xml]
+content_type = opml

tests/test_foaf.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+
+import unittest
+from planet.foaf import foaf2config
+from ConfigParser import ConfigParser
+
+blogroll = 'http://journal.dajobe.org/journal/2003/07/semblogs/bloggers.rdf'
+testfeed = "http://dannyayers.com/feed/rdf"
+test_foaf_document = '''
+<rdf:RDF
+  xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+  xmlns:foaf="http://xmlns.com/foaf/0.1/"
+  xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#"
+  xmlns:rss="http://purl.org/rss/1.0/"
+  xmlns:dc="http://purl.org/dc/elements/1.1/">
+
+<foaf:Agent rdf:nodeID="id2245354"> 
+<foaf:name>Danny Ayers</foaf:name> 
+<rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Person"/> 
+<foaf:weblog> 
+<foaf:Document rdf:about="http://dannyayers.com/"> 
+<dc:title>Raw Blog by Danny Ayers</dc:title> 
+<rdfs:seeAlso> 
+<rss:channel rdf:about="http://dannyayers.com/feed/rdf"> 
+<foaf:maker rdf:nodeID="id2245354"/> 
+<foaf:topic rdf:resource="http://www.w3.org/2001/sw/"/> 
+<foaf:topic rdf:resource="http://www.w3.org/RDF/"/> 
+</rss:channel> 
+</rdfs:seeAlso> 
+</foaf:Document> 
+</foaf:weblog> 
+<foaf:interest rdf:resource="http://www.w3.org/2001/sw/"/> 
+<foaf:interest rdf:resource="http://www.w3.org/RDF/"/> 
+</foaf:Agent> 
+
+</rdf:RDF> 
+'''.strip()
+
+class FoafTest(unittest.TestCase):
+    """
+    Test the foaf2config function
+    """
+
+    def setUp(self):
+        self.config = ConfigParser()
+
+    #
+    # Tests
+    #
+
+    def test_foaf_document(self):
+        foaf2config(test_foaf_document, blogroll, self.config)
+        self.assertEqual('Danny Ayers', self.config.get(testfeed, 'name'))
+
+    def test_no_foaf_name(self):
+        test = test_foaf_document.replace('foaf:name','foaf:title')
+        foaf2config(test, blogroll, self.config)
+        self.assertEqual('Raw Blog by Danny Ayers',
+           self.config.get(testfeed, 'name'))
+
+    def test_no_weblog(self):
+        test = test_foaf_document.replace('rdfs:seeAlso','rdfs:seealso')
+        foaf2config(test, blogroll, self.config)
+        self.assertFalse(self.config.has_section(testfeed))
+
+    def test_invalid_xml_before(self):
+        test = '\n<?xml version="1.0" encoding="UTF-8"?>' + test_foaf_document
+        foaf2config(test, blogroll, self.config)
+        self.assertFalse(self.config.has_section(testfeed))
+
+    def test_invalid_xml_after(self):
+        test = test_foaf_document.strip()[:-1]
+        foaf2config(test, blogroll, self.config)
+        self.assertEqual('Danny Ayers', self.config.get(testfeed, 'name'))
+
+if __name__ == '__main__':
+    unittest.main()