[WIP] Government bill proposals date fix

.travis.yml

@@ -25,7 +25,7 @@ install:
   - pip install -r requirements.txt --timeout 30
 # command to run tests, e.g. python setup.py test
 script:
-  - ./manage.py test
+  - ./manage.py test -v3
   # for the browser tests we need a real db with full data - we rely on cached version to speed up tests
   - if [ ! -f devdb/dev.db ]; then wget http://oknesset-devdb.s3.amazonaws.com/dev.db.bz2; fi
   - if [ ! -f devdb/dev.db ]; then bunzip2 dev.db.bz2 && cp dev.db devdb/dev.db; else cp devdb/dev.db dev.db; fi

laws/models/bill.py

@@ -325,7 +325,7 @@ def update_stage(self, force_update=False):
             self.save()
             return
         for cm in self.second_committee_meetings.all():
-            if not (self.stage_date) or self.stage_date < cm.date:
+            if not self.stage_date or self.stage_date < cm.date:
                 self.stage = BillStages.COMMITTEE_CORRECTIONS
                 self.stage_date = cm.date
         if self.stage == BillStages.COMMITTEE_CORRECTIONS:

simple/government_bills/tests/test_government_bill_proposal.py

@@ -0,0 +1,21 @@
+import datetime
+import os
+
+from django.test.testcases import SimpleTestCase
+
+from simple.government_bills.parse_government_bill_pdf import GovProposalParser
+
+
+class GovernmentBillProposalParserTestCase(SimpleTestCase):
+    def setUp(self):
+        super(GovernmentBillProposalParserTestCase, self).setUp()
+
+    def tearDown(self):
+        super(GovernmentBillProposalParserTestCase, self).setUp()
+
+    def test_date_parsing_returns_correct_date_from_gov_proposals(self):
+        filepath = os.path.dirname(__file__)
+        full_filepath = os.path.join(filepath, '1075.pdf')
+        parsed_page_date = GovProposalParser(full_filepath)
+        parsed_date = parsed_page_date.get_date()
+        self.assertEqual(parsed_date, datetime.date(2016, 8, 1))

simple/management/commands/syncdata.py

@@ -163,7 +163,7 @@ def parse_laws_page(self, page):
         count = -1
         lines = page.split('\n')
         for line in lines:
-
+            link = None
             r = re.search("""Href=\"(.*?)\">""", line)
             if r is not None:
                 link = 'http://www.knesset.gov.il/privatelaw/' + r.group(1)
@@ -172,7 +172,8 @@ def parse_laws_page(self, page):
                 name = r.group(1).replace("</td>", "").strip()
                 if len(name) > 1 and name.find('span') < 0:
                     names.append(name)
-                    links.append(link)
+                    if link:
+                        links.append(link)
                     exps.append('')
                     count += 1
             if re.search("""arrResume\[\d*\]""", line) is not None: