Merge pull request #556 from marwoodandrew/sd-5402

[SD-5402] Category mapping for PA ingest

superdesk/io/feed_parsers/__init__.py

@@ -145,3 +145,4 @@ class EmailFeedParser(FeedParser, metaclass=ABCMeta):
 import superdesk.io.feed_parsers.afp_newsml_1_2  # NOQA
 import superdesk.io.feed_parsers.scoop_newsml_2_0  # NOQA
 import superdesk.io.feed_parsers.ap_anpa  # NOQA
+import superdesk.io.feed_parsers.pa_nitf  # NOQA

superdesk/io/feed_parsers/pa_nitf.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python
+# -*- coding: utf-8; -*-
+#
+# This file is part of Superdesk.
+#
+# Copyright 2013, 2014, 2015 Sourcefabric z.u. and contributors.
+#
+# For the full copyright and license information, please see the
+# AUTHORS and LICENSE files distributed with this source code, or
+# at https://www.sourcefabric.org/superdesk/license
+
+from superdesk.io.feed_parsers.nitf import NITFFeedParser
+from superdesk.io import register_feed_parser
+
+
+class PAFeedParser(NITFFeedParser):
+    """
+    NITF Parser extension for Press Association, it maps the category meta tag to an anpa category
+    """
+    NAME = 'pa_nitf'
+
+    def _category_mapping(self, elem):
+        """
+        Map the category supplied by PA to a best guess anpa_category in the system
+        :param elem:
+        :return: anpa category list qcode
+        """
+        if elem.get('content') is not None:
+            category = elem.get('content')[:1].upper()
+            if category in {'S', 'R', 'F'}:
+                return [{'qcode': 'S'}]
+            if category == 'Z':
+                return [{'qcode': 'V'}]
+        return [{'qcode': 'I'}]
+
+    def __init__(self):
+        self.MAPPING = {'anpa_category': {'xpath': "head/meta/[@name='category']", 'filter': self._category_mapping}}
+        super().__init__()
+
+register_feed_parser(PAFeedParser.NAME, PAFeedParser())

tests/io/feed_parsers/pa_nitf_test.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python
+# -*- coding: utf-8; -*-
+#
+# This file is part of Superdesk.
+#
+# Copyright 2013, 2014, 2015 Sourcefabric z.u. and contributors.
+#
+# For the full copyright and license information, please see the
+# AUTHORS and LICENSE files distributed with this source code, or
+# at https://www.sourcefabric.org/superdesk/license
+
+import os
+from test_factory import SuperdeskTestCase
+from superdesk.io.feed_parsers.pa_nitf import PAFeedParser
+from superdesk.etree import etree
+
+
+class PANITFFileTestCase(SuperdeskTestCase):
+
+    vocab = [{'_id': 'genre', 'items': [{'name': 'Current'}]}]
+
+    def setUp(self):
+        super().setUp()
+        with self.app.app_context():
+            self.app.data.insert('vocabularies', self.vocab)
+        dirname = os.path.dirname(os.path.realpath(__file__))
+        fixture = os.path.normpath(os.path.join(dirname, '../fixtures', self.filename))
+        provider = {'name': 'Test'}
+        with open(fixture) as f:
+            self.nitf = f.read()
+            self.item = PAFeedParser().parse(etree.fromstring(self.nitf), provider)
+
+
+class PAFileWithNoSubjects(PANITFFileTestCase):
+
+    filename = 'pa2.xml'
+
+    def test_headline(self):
+        self.assertEqual(self.item.get('headline'), '1 SOCCER INT-Teams')
+
+    def test_anpa_category(self):
+        self.assertEqual(self.item.get('anpa_category'), [{'qcode': 'S'}])