feat: initial py2 to 3 work

Author: JacobCoffee

code/planet-cache.py

@@ -1,5 +1,4 @@
-#!/usr/bin/env python
-# -*- coding: UTF-8 -*-
+#!/usr/bin/env python3
 """Planet cache tool.
 
 """
@@ -12,48 +11,48 @@
 import os
 import sys
 import time
-import dbhash
-import ConfigParser
+import dbm
+import configparser
 
 import planet
 
 
 def usage():
-    print "Usage: planet-cache [options] CACHEFILE [ITEMID]..."
-    print
-    print "Examine and modify information in the Planet cache."
-    print
-    print "Channel Commands:"
-    print " -C, --channel     Display known information on the channel"
-    print " -L, --list        List items in the channel"
-    print " -K, --keys        List all keys found in channel items"
-    print
-    print "Item Commands (need ITEMID):"
-    print " -I, --item        Display known information about the item(s)"
-    print " -H, --hide        Mark the item(s) as hidden"
-    print " -U, --unhide      Mark the item(s) as not hidden"
-    print
-    print "Other Options:"
-    print " -h, --help        Display this help message and exit"
+    print("Usage: planet-cache [options] CACHEFILE [ITEMID]...")
+    print()
+    print("Examine and modify information in the Planet cache.")
+    print()
+    print("Channel Commands:")
+    print(" -C, --channel     Display known information on the channel")
+    print(" -L, --list        List items in the channel")
+    print(" -K, --keys        List all keys found in channel items")
+    print()
+    print("Item Commands (need ITEMID):")
+    print(" -I, --item        Display known information about the item(s)")
+    print(" -H, --hide        Mark the item(s) as hidden")
+    print(" -U, --unhide      Mark the item(s) as not hidden")
+    print()
+    print("Other Options:")
+    print(" -h, --help        Display this help message and exit")
     sys.exit(0)
 
 def usage_error(msg, *args):
-    print >>sys.stderr, msg, " ".join(args)
-    print >>sys.stderr, "Perhaps you need --help ?"
+    print(msg, " ".join(args), file=sys.stderr)
+    print("Perhaps you need --help ?", file=sys.stderr)
     sys.exit(1)
 
 def print_keys(item, title):
     keys = item.keys()
     keys.sort()
     key_len = max([ len(k) for k in keys ])
 
-    print title + ":"
+    print(title + ":")
     for key in keys:
         if item.key_type(key) == item.DATE:
             value = time.strftime(planet.TIMEFMT_ISO, item[key])
         else:
             value = str(item[key])
-        print "    %-*s  %s" % (key_len, key, fit_str(value, 74 - key_len))
+        print("    %-*s  %s" % (key_len, key, fit_str(value, 74 - key_len)))
 
 def fit_str(string, length):
     if len(string) <= length:
@@ -116,24 +115,23 @@ def fit_str(string, length):
 
     # Open the cache file directly to get the URL it represents
     try:
-        db = dbhash.open(cache_file)
-        url = db["url"]
-        db.close()
-    except dbhash.bsddb._db.DBError, e:
-        print >>sys.stderr, cache_file + ":", e.args[1]
+        with dbm.open(cache_file, 'r') as db:
+            url = db[b"url"].decode('utf-8')
+    except dbm.error as e:
+        print(f"{cache_file}: {str(e)}", file=sys.stderr)
         sys.exit(1)
     except KeyError:
-        print >>sys.stderr, cache_file + ": Probably not a cache file"
+        print(f"{cache_file}: Probably not a cache file", file=sys.stderr)
         sys.exit(1)
 
     # Now do it the right way :-)
-    my_planet = planet.Planet(ConfigParser.ConfigParser())
+    my_planet = planet.Planet(configparser.ConfigParser())
     my_planet.cache_directory = os.path.dirname(cache_file)
     channel = planet.Channel(my_planet, url)
 
     for item_id in ids:
         if not channel.has_item(item_id):
-            print >>sys.stderr, item_id + ": Not in channel"
+            print(item_id + ": Not in channel", file=sys.stderr)
             sys.exit(1)
 
     # Do the user's bidding
@@ -146,49 +144,48 @@ def fit_str(string, length):
             print_keys(item, "Item Keys for %s" % item_id)
 
     elif command == "list":
-        print "Items in Channel:"
+        print("Items in Channel:")
         for item in channel.items(hidden=1, sorted=1):
-            print "    " + item.id
-            print "         " + time.strftime(planet.TIMEFMT_ISO, item.date)
+            print("    " + item.id)
+            print("         " + time.strftime(planet.TIMEFMT_ISO, item.date))
             if hasattr(item, "title"):
-                print "         " + fit_str(item.title, 70)
+                print("         " + fit_str(item.title, 70))
             if hasattr(item, "hidden"):
-                print "         (hidden)"
+                print("         (hidden)")
 
     elif command == "keys":
         keys = {}
         for item in channel.items():
             for key in item.keys():
                 keys[key] = 1
 
-        keys = keys.keys()
-        keys.sort()
+        keys = sorted(keys.keys())
 
-        print "Keys used in Channel:"
+        print("Keys used in Channel:")
         for key in keys:
-            print "    " + key
-        print
+            print("    " + key)
+        print()
 
-        print "Use --item to output values of particular items."
+        print("Use --item to output values of particular items.")
 
     elif command == "hide":
         for item_id in ids:
             item = channel.get_item(item_id)
             if hasattr(item, "hidden"):
-                print item_id + ": Already hidden."
+                print(item_id + ": Already hidden.")
             else:
                 item.hidden = "yes"
 
         channel.cache_write()
-        print "Done."
+        print("Done.")
 
     elif command == "unhide":
         for item_id in ids:
             item = channel.get_item(item_id)
             if hasattr(item, "hidden"):
-                del(item.hidden)
+                del item.hidden
             else:
-                print item_id + ": Not hidden."
+                print(item_id + ": Not hidden.")
 
         channel.cache_write()
-        print "Done."
+        print("Done.")

code/planet.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 """The Planet aggregator.
 
 A flexible and easy-to-use aggregator for generating websites.
@@ -16,14 +16,13 @@
 
 import os
 import sys
-import time
 import locale
 import socket
-import urlparse
+import configparser
+from urllib.parse import urljoin
 
 import planet
 
-from ConfigParser import ConfigParser
 
 # Default configuration file path
 CONFIG_FILE = "config.ini"
@@ -56,29 +55,29 @@ def main():
 
     for arg in sys.argv[1:]:
         if arg == "-h" or arg == "--help":
-            print "Usage: planet [options] [CONFIGFILE]"
-            print
-            print "Options:"
-            print " -v, --verbose       DEBUG level logging during update"
-            print " -o, --offline       Update the Planet from the cache only"
-            print " -h, --help          Display this help message and exit"
-            print
+            print("Usage: planet [options] [CONFIGFILE]")
+            print()
+            print("Options:")
+            print(" -v, --verbose       DEBUG level logging during update")
+            print(" -o, --offline       Update the Planet from the cache only")
+            print(" -h, --help          Display this help message and exit")
+            print()
             sys.exit(0)
         elif arg == "-v" or arg == "--verbose":
             verbose = 1
         elif arg == "-o" or arg == "--offline":
             offline = 1
         elif arg.startswith("-"):
-            print >>sys.stderr, "Unknown option:", arg
+            print("Unknown option:", arg, file=sys.stderr)
             sys.exit(1)
         else:
             config_file = arg
 
     # Read the configuration file
-    config = ConfigParser()
+    config = configparser()
     config.read(config_file)
     if not config.has_section("Planet"):
-        print >>sys.stderr, "Configuration missing [Planet] section."
+        print("Configuration missing [Planet] section.", file=sys.stderr)
         sys.exit(1)
 
     # Read the [Planet] config section
@@ -100,7 +99,7 @@ def main():
         for template_file in template_files:
             name = os.path.splitext(os.path.basename(template_file))[0]
             if name.find('atom')>=0 or name.find('rss')>=0:
-                planet_feed = urlparse.urljoin(planet_link, name)
+                planet_feed = urljoin(planet_link, name)
                 break
 
     # Define locale
@@ -118,7 +117,7 @@ def main():
                 locale_ok = True
                 break
         if not locale_ok:
-            print >>sys.stderr, "Unsupported locale setting."
+            print("Unsupported locale setting.", file=sys.stderr)
             sys.exit(1)
 
     # Activate logging

code/planet/__init__.py

@@ -1,5 +1,4 @@
-#!/usr/bin/env python
-# -*- coding: UTF-8 -*-
+#!/usr/bin/env python3
 """Planet aggregator library.
 
 This package is a library for developing web sites or software that
@@ -18,7 +17,6 @@
 import feedparser
 import sanitize
 import htmltmpl
-import sgmllib
 try:
     import logging
 except:
@@ -29,10 +27,11 @@
            "Planet", "Channel", "NewsItem")
 
 
+from html.parser import HTMLParser
 import os
-import md5
+from hashlib import md5
 import time
-import dbhash
+import dbm
 import re
 
 try: 
@@ -74,15 +73,18 @@ def escape(data):
 NEW_DATE_FORMAT = "%B %d, %Y"
 ACTIVITY_THRESHOLD = 0
 
-class stripHtml(sgmllib.SGMLParser):
+
+class stripHtml(HTMLParser):
     "remove all tags from the data"
-    def __init__(self, data):
-        sgmllib.SGMLParser.__init__(self)
-        self.result=''
-        self.feed(data)
-        self.close()
+    def __init__(self):
+        super().__init__()
+        self.result = []
+
     def handle_data(self, data):
-        if data: self.result+=data
+        self.result.append(data)
+
+    def get_data(self):
+        return "".join(self.result)
 
 def template_info(item, date_format):
     """Produce a dictionary of template information."""
@@ -504,7 +506,7 @@ def __init__(self, planet, url):
         if not os.path.isdir(planet.cache_directory):
             os.makedirs(planet.cache_directory)
         cache_filename = cache.filename(planet.cache_directory, url)
-        cache_file = dbhash.open(cache_filename, "c", 0666)
+        cache_file = dbm.open(cache_filename, "c", 0o666)
 
         cache.CachedInfo.__init__(self, cache_file, url, root=1)
 
@@ -695,7 +697,7 @@ def update_info(self, feed):
                     self.set_as_string(key + "_width", str(feed[key].width))
                 if feed[key].has_key("height"):
                     self.set_as_string(key + "_height", str(feed[key].height))
-            elif isinstance(feed[key], (str, unicode)):
+            elif isinstance(feed[key], str):
                 # String fields
                 try:
                     detail = key + '_detail'
@@ -890,7 +892,7 @@ def update(self, entry):
                         self.set_as_string(key + "_language", item.language)
                     value += cache.utf8(item.value)
                 self.set_as_string(key, value)
-            elif isinstance(entry[key], (str, unicode)):
+            elif isinstance(entry[key], str):
                 # String fields
                 try:
                     detail = key + '_detail'

code/planet/atomstyler.py

@@ -1,7 +1,7 @@
 from xml.dom import minidom, Node
-from urlparse import urlparse, urlunparse
+from urllib.parse import urlparse, urlunparse
 from xml.parsers.expat import ExpatError
-from htmlentitydefs import name2codepoint
+from html.entities import name2codepoint
 import re
 
 # select and apply an xml:base for this entry
@@ -75,20 +75,20 @@ def retype(parent):
         elif len(node.childNodes)==1:
 
           # replace html entity defs with utf-8
-          chunks=re.split('&(\w+);', node.childNodes[0].nodeValue)
+          chunks=re.split(r'&(\w+);', node.childNodes[0].nodeValue)
           for i in range(1,len(chunks),2):
              if chunks[i] in ['amp', 'lt', 'gt', 'apos', 'quot']:
                chunks[i] ='&' + chunks[i] +';'
              elif chunks[i] in name2codepoint:
-               chunks[i]=unichr(name2codepoint[chunks[i]])
+               chunks[i] = chr(name2codepoint[chunks[i]])
              else:
                chunks[i]='&' + chunks[i] + ';'
-          text = u"".join(chunks)
+          text = "".join(chunks)
 
           try:
             # see if the resulting text is a well-formed XML fragment
             div = '<div xmlns="http://www.w3.org/1999/xhtml">%s</div>'
-            data = minidom.parseString((div % text.encode('utf-8')))
+            data = minidom.parseString(div % text.encode('utf-8'))
 
             if text.find('<') < 0:
               # plain text