still refactoring

.gitignore

@@ -0,0 +1,6 @@
+*~
+*.db
+*.pyc
+*.json
+*.gz
+*.py#

AUTHORS.rst

@@ -0,0 +1 @@
+Tyler Brown 

MANIFEST.in

@@ -0,0 +1,2 @@
+include AUTHORS.rst
+include README.rst

gathernews/__init__.py

@@ -4,8 +4,22 @@
 # - better organization of tables for large entries
 # - support for databases other than SQLite3
 
-import duplicates
+# Asynchronous stuff, twisted
+import async
+# Any functions that must be called to keep the versions compatible
+import bug_fixes
+# Module that lets you commit RSS feeds to a SQLite3 database
+import gRSS
+# Does anything related to reading or writing from file storage
 import io
-import new_tables
-import populate_tables
+# Anything related to Mongo IO
+import mongo_io
+# Filter out any garbage from Feedparser input
+import rm_garbage
+# Anything related to SQLite3 IO
+import sqlite3_io
+# Multithreading
 import threads
+
+
+

gathernews/bug_fixes.py

@@ -1,7 +1,15 @@
+from io import ReadFiles
+from sqlite3_io import Sqlite3IO
 
-class v1_bugs:
-    """ Any functions that must be called to keep the versions compatible"""
 
+class v1_bugs(object):
+    """ Any functions that must be called to keep the version 1 compatible"""
+
+    def __init__(self, path):
+        self.read_files = ReadFiles(path)
+        self.use_sqlite3 = Sqlite3IO(path)
+        self.path = path
+
     def fix_create_table_bug(self):
         """ Fix the create table bug
 
@@ -27,7 +35,7 @@ def fix_create_table_bug(self):
         """
 
         # get table names from the database
-        db_names = self.get_tablenames()
+        db_names = self.use_sqlite3.get_tablenames()
 
         # get table names from RSS feeds
         create_these_tables = {}

gathernews/gRSS.py

@@ -41,6 +41,19 @@
 import json
 import logging
 
+## custom modules
+
+# clean input
+from io import ReadFiles, WriteFiles
+from rm_garbage import FilterGarbage
+from bug_fixes import v1_bugs
+# play well with DBs
+from mongo_io import MongoIO
+from sqlite3_io import Sqlite3IO
+# handle requests quickly 
+#from async import *
+#from threads import *
+
 
 class CaptureFeeds(object):
     """ Commits RSS news feeds to a SQLite3 database  """

gathernews/io.py

@@ -1,5 +1,5 @@
-class io(object):
-    """ Does anything related to reading or writing from file storage """
+class ReadFiles(object):
+    """ Does anything related to reading from file storage """
 
     def __init__(self, path):
         self.path = path
@@ -41,7 +41,35 @@ def read_file(self, path, your_file_name):
         return clean_file
 
 
-     def update_feeds_json(self, path, create_these_tables,
+    def does_json_exist(self, path, your_file_name):
+        """ If a json object exists then return it
+
+        Args:
+            file_name: This is the name of your file.
+
+        Returns:
+            A json object from your specified path is returned.
+        """
+        try:
+            with open(path + your_file_name, 'r') as f:
+                return json.load(f)
+        # At some point you should create a method that checks to see if the
+        # file path given by the user is accurate. 
+        except:
+            return False
+
+
+    def get_RSS_link(self):
+        """RSS links used to pull feeds"""
+        return self.read_file(self.path, "feeds_list")
+
+
+class WriteFiles(ReadFiles):
+    """ Does anything related to writing from file storage """
+    # Not sure what this will inherit for a file_path from ReadFiles
+    # under which conditions, but hey, isn't learning fun
+
+    def update_feeds_json(self, path, create_these_tables,
                           previous_feeds_list, current_feeds_list):
         """ A JSON object of table_names in the database is updated.
 
@@ -73,26 +101,3 @@ def update_feeds_json(self, path, create_these_tables,
                return json.dump(previous_feeds_list, f)
         else:
             return False
-
-
-    def does_json_exist(self, path, your_file_name):
-        """ If a json object exists then return it
-
-        Args:
-            file_name: This is the name of your file.
-
-        Returns:
-            A json object from your specified path is returned.
-        """
-        try:
-            with open(path + your_file_name, 'r') as f:
-                return json.load(f)
-        # At some point you should create a method that checks to see if the
-        # file path given by the user is accurate. 
-        except:
-            return False
-
-
-    def get_RSS_link(self):
-        """RSS links used to pull feeds"""
-        return self.read_file(self.path, "feeds_list.txt")

gathernews/mongo_io.py

@@ -0,0 +1,5 @@
+
+
+class MongoIO(object):
+    """ Anything related to MongoDB io """
+    pass

gathernews/rm_garbage.py

@@ -1,3 +1,6 @@
+from io import ReadFiles
+
+
 
 class FilterGarbage:
     """ Filter out any garbage from Feedparser input """

gathernews/tests/__init__.py

@@ -1 +1,9 @@
-import test_gRSS
+import test_gRSS # this is more or less contains the main method
+import test_async
+import test_bug_fixes
+import test_io
+import test_mongo_io
+import test_rm_garbage
+import test_sqlite3_io
+import test_threads
+

gathernews/tests/bad_feeds_list.txt

@@ -0,0 +1,2 @@
+# these are bad rss links
+dontcha know...

gathernews/tests/feeds_list.txt

@@ -0,0 +1,10 @@
+http://feeds.reuters.com/reuters/businessNews
+http://feeds.reuters.com/reuters/entertainment
+http://feeds.reuters.com/reuters/topNews
+http://feeds.reuters.com/Reuters/worldNews
+http://rss.cnn.com/rss/money_latest.rss
+http://rss.cnn.com/rss/cnn_showbiz.rss
+http://rss.cnn.com/rss/cnn_topstories.rss
+http://rss.cnn.com/rss/cnn_world.rss
+
+