xpath sifter and category support

filters/xpath_sifter.py

@@ -0,0 +1,23 @@
+import sys, libxml2
+
+# parse options
+options = dict(zip(sys.argv[1::2],sys.argv[2::2]))
+
+# parse entry
+doc = libxml2.parseDoc(sys.stdin.read())
+ctxt = doc.xpathNewContext()
+ctxt.xpathRegisterNs('atom','http://www.w3.org/2005/Atom')
+ctxt.xpathRegisterNs('xhtml','http://www.w3.org/1999/xhtml')
+
+# process requirements
+if options.has_key('--require'):
+  for xpath in options['--require'].split('\n'):
+     if xpath and not ctxt.xpathEval(xpath): sys.exit(1)
+
+# process exclusions
+if options.has_key('--exclude'):
+  for xpath in options['--exclude'].split('\n'):
+     if xpath and ctxt.xpathEval(xpath): sys.exit(1)
+
+# if we get this far, the feed is to be included
+print doc

planet/reconstitute.py

@@ -110,6 +110,16 @@ def date(xentry, name, parsed):
     formatted = time.strftime(config.date_format(), parsed)
     xdate.setAttribute('planet:format', formatted)
 
+def category(xentry, tag):
+    xtag = xentry.ownerDocument.createElement('category')
+    if tag.has_key('term') and tag.term:
+        xtag.setAttribute('term', tag.get('term'))
+    if tag.has_key('scheme') and tag.scheme:
+        xtag.setAttribute('scheme', tag.get('scheme'))
+    if tag.has_key('label') and tag.label:
+        xtag.setAttribute('label', tag.get('label'))
+    xentry.appendChild(xtag)
+
 def author(xentry, name, detail):
     """ insert an author-like element into the entry """
     if not detail: return
@@ -160,6 +170,9 @@ def source(xsource, source, bozo):
     createTextElement(xsource, 'icon', source.get('icon', None))
     createTextElement(xsource, 'logo', source.get('logo', None))
 
+    for tag in source.get('tags',[]):
+        category(xsource, tag)
+
     author_detail = source.get('author_detail',{})
     if not author_detail.has_key('name') and source.has_key('planet_name'):
         author_detail['name'] = source['planet_name']
@@ -201,6 +214,9 @@ def reconstitute(feed, entry):
     date(xentry, 'updated', entry.get('updated_parsed',time.gmtime()))
     date(xentry, 'published', entry.get('published_parsed',None))
 
+    for tag in entry.get('tags',[]):
+        category(xentry, tag)
+
     author(xentry, 'author', entry.get('author_detail',None))
     for contributor in entry.get('contributors',[]):
         author(xentry, 'contributor', contributor)

tests/data/filter/category-one.xml

@@ -0,0 +1,3 @@
+<entry xmlns="http://www.w3.org/2005/Atom">
+  <category term="one"/>
+</entry>

tests/data/filter/category-two.xml

@@ -0,0 +1,3 @@
+<entry xmlns="http://www.w3.org/2005/Atom">
+  <category term="two"/>
+</entry>

tests/data/filter/coral_cdn.xml

@@ -1,4 +1,4 @@
-<entry xmlns="http://www.w3.org/2005/xhtml">
+<entry xmlns="http://www.w3.org/2005/Atom">
   <content>
      <div xmlns="http://www.w3.org/1999/xhtml">
        <img src="http://example.com/foo.png"/>

tests/data/filter/xpath-sifter.ini

@@ -0,0 +1,6 @@
+[Planet]
+filters = xpath_sifter.py
+
+[xpath_sifter.py]
+require:
+  //atom:category[@term='two']

tests/data/reconstitute/category_label.xml

@@ -0,0 +1,11 @@
+<!--
+Description:  category label
+Expect:       tags[0].label == 'Inbox'
+-->
+
+<feed xmlns="http://www.w3.org/2005/Atom">
+  <entry>
+    <category label="Inbox"/>
+  </entry>
+</feed>
+

tests/data/reconstitute/category_scheme.xml

@@ -0,0 +1,11 @@
+<!--
+Description:  category scheme
+Expect:       tags[0].scheme == 'http://example.com/categories'
+-->
+
+<feed xmlns="http://www.w3.org/2005/Atom">
+  <entry>
+    <category scheme="http://example.com/categories"/>
+  </entry>
+</feed>
+

tests/data/reconstitute/category_term.xml

@@ -0,0 +1,11 @@
+<!--
+Description:  category term
+Expect:       tags[0].term == 'inbox'
+-->
+
+<feed xmlns="http://www.w3.org/2005/Atom">
+  <entry>
+    <category term="inbox"/>
+  </entry>
+</feed>
+

tests/data/reconstitute/source_category.xml

@@ -0,0 +1,14 @@
+<!--
+Description:  source category
+Expect:       source.tags[0].term == 'inbox' and source.tags[0].scheme == 'http://example.com/categories' and source.tags[0].label == 'Inbox'
+-->
+
+<feed xmlns="http://www.w3.org/2005/Atom">
+  <entry>
+    <source>
+      <category term='inbox' label='Inbox'
+        scheme="http://example.com/categories"/>
+    </source>
+  </entry>
+</feed>
+

tests/test_filters.py

@@ -58,6 +58,24 @@ class FilterTests(unittest.TestCase):
         self.assertEqual(u'before--after',
             excerpt.firstChild.firstChild.nodeValue)
 
+    def test_xpath_filter(self):
+        config.load('tests/data/filter/xpath-sifter.ini')
+        testfile = 'tests/data/filter/category-one.xml'
+
+        output = open(testfile).read()
+        for filter in config.filters():
+            output = shell.run(filter, output, mode="filter")
+
+        self.assertEqual('', output)
+
+        testfile = 'tests/data/filter/category-two.xml'
+
+        output = open(testfile).read()
+        for filter in config.filters():
+            output = shell.run(filter, output, mode="filter")
+
+        self.assertNotEqual('', output)
+
 try:
     from subprocess import Popen, PIPE
     sed=Popen(['sed','--version'],stdout=PIPE,stderr=PIPE)