Fix configuration schema checking

Fix some minor IDE warnings

MANIFEST.in

@@ -0,0 +1,2 @@
+include webarticlecurator/crawl_schema.yaml
+include webarticlecurator/site_schema.yaml

webarticlecurator/__main__.py

@@ -214,8 +214,9 @@ def main():
                         format(set(commands.keys())))
 
     command = parser.parse_args(sys.argv[1:2]).command  # Route ArgumentParser before reparsing the whole CLI
-    sub_args = commands[command][0](ArgumentParser())
-    commands[command][1](sub_args)
+    argparse_fun, main_fun = commands[command]
+    sub_args = argparse_fun(ArgumentParser())
+    main_fun(sub_args)
 
 
 if __name__ == '__main__':

webarticlecurator/news_crawler.py

@@ -40,14 +40,14 @@ def __init__(self, settings, existing_archive_filename, new_archive_filename, ar
 
         # Open files for writing gathered URLs on exit if needed
         self.good_urls = set()
-        self._new_good_archive_urls_fh = settings.get('new_good_archive_urls')
-        if self._new_good_archive_urls_fh is not None:
-            self._new_good_archive_urls_fh = open(self._new_good_archive_urls_fh, 'w', encoding='UTF-8')
+        new_good_archive_urls_fname = settings.get('new_good_archive_urls')
+        if new_good_archive_urls_fname is not None:
+            self._new_good_archive_urls_fh = open(new_good_archive_urls_fname, 'w', encoding='UTF-8')
 
         self.problematic_urls = set()
-        self._new_problematic_archive_urls_fh = settings.get('new_problematic_archive_urls')
-        if self._new_problematic_archive_urls_fh is not None:
-            self._new_problematic_archive_urls_fh = open(self._new_problematic_archive_urls_fh, 'w', encoding='UTF-8')
+        new_problematic_archive_urls_fname = settings.get('new_problematic_archive_urls')
+        if new_problematic_archive_urls_fname is not None:
+            self._new_problematic_archive_urls_fh = open(new_problematic_archive_urls_fname, 'w', encoding='UTF-8')
 
         # Setup the list of cached article URLs to stop archive crawling in time
         self.known_article_urls = set()
@@ -241,14 +241,14 @@ def __init__(self, settings, articles_existing_warc_filename, articles_new_warc_
 
         # Open files for writing gathered URLs on exit if needed
         self._new_urls = set()
-        self._new_good_urls_fh = settings.get('new_good_urls')
-        if self._new_good_urls_fh is not None:
-            self._new_good_urls_fh = open(self._new_good_urls_fh, 'a+', encoding='UTF-8')
+        new_good_urls_fname = settings.get('new_good_urls')
+        if new_good_urls_fname is not None:
+            self._new_good_urls_fh = open(new_good_urls_fname, 'a+', encoding='UTF-8')
 
         self.problematic_article_urls = set()
-        self._new_problematic_urls_fh = settings.get('new_problematic_urls')
-        if self._new_problematic_urls_fh is not None:
-            self._new_problematic_urls_fh = open(self._new_problematic_urls_fh, 'a+', encoding='UTF-8')
+        new_problematic_urls_fname = settings.get('new_problematic_urls')
+        if new_problematic_urls_fname is not None:
+            self._new_problematic_urls_fh = open(new_problematic_urls_fname, 'a+', encoding='UTF-8')
 
         # Store values at init-time
         self._filter_by_date = settings['FILTER_ARTICLES_BY_DATE']

webarticlecurator/utils.py

@@ -10,8 +10,8 @@
 
 import yamale
 
-site_schema = yamale.make_schema(os.path.join(os.path.dirname(os.path.abspath(__file__)), './site_schema.yaml'))
-crawl_schema = yamale.make_schema(os.path.join(os.path.dirname(os.path.abspath(__file__)), './crawl_schema.yaml'))
+site_schema = yamale.make_schema(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'site_schema.yaml'))
+crawl_schema = yamale.make_schema(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'crawl_schema.yaml'))
 
 
 def load_and_validate(schema, fname):

webarticlecurator/version.py

@@ -1,4 +1,4 @@
 #!/usr/bin/env pyhton3
 # -*- coding: utf-8, vim: expandtab:ts=4 -*-
 
-__version__ = '1.0.0'
+__version__ = '1.0.1'