Merge lp:~stefanor/ibid/country-codes-533518 into lp:~ibid-core/ibid/old-release-0.1-1.6

[Stefano Rivera]

[Max Rabkin (max-rabkin)]

review: Approve

[Jonathan Hitchcock (vhata)]

review: Approve

[Michael Gorven (mgorven)]

 review approve

review: Approve

=== modified file 'ibid/plugins/conversions.py'
--- ibid/plugins/conversions.py	2010-02-20 21:58:38 +0000
+++ ibid/plugins/conversions.py	2010-03-07 10:12:33 +0000
@@ -10,8 +10,9 @@
 import ibid
 from ibid.plugins import Processor, handler, match
 from ibid.config import Option
-from ibid.utils import file_in_path, unicode_output, human_join
-from ibid.utils.html import get_country_codes, get_html_parse_tree
+from ibid.utils import file_in_path, get_country_codes, human_join, \
+                       unicode_output
+from ibid.utils.html import get_html_parse_tree
 
 features = {}
 log = logging.getLogger('plugins.conversions')
 
=== modified file 'ibid/plugins/network.py'
--- ibid/plugins/network.py	2010-02-24 12:42:45 +0000
+++ ibid/plugins/network.py	2010-03-07 10:12:33 +0000
@@ -21,9 +21,8 @@
 import ibid
 from ibid.plugins import Processor, match, authorise
 from ibid.config import Option, IntOption, FloatOption, DictOption
-from ibid.utils import file_in_path, unicode_output, human_join, \
-                       url_to_bytestring, get_process_output
-from ibid.utils.html import get_country_codes
+from ibid.utils import file_in_path, get_country_codes, get_process_output, \
+                       human_join, unicode_output, url_to_bytestring
 
 features = {}
 
@@ -430,27 +429,30 @@
         tld = tld.upper()
 
         if tld in self.country_codes:
-            event.addresponse(u'%(tld)s is the TLD for %(country)s', {
+            event.addresponse(u'%(tld)s is the ccTLD for %(country)s', {
                 'tld': tld,
                 'country': self.country_codes[tld],
             })
         else:
-            event.addresponse(u"ISO doesn't know about any such TLD")
+            event.addresponse(u"ISO doesn't know about any such ccTLD")
 
-    @match(r'^tld\s+for\s+(.+)$')
+    @match(r'^(?:cc)?tld\s+for\s+(.+)$')
     def country_to_tld(self, event, location):
         if not self.country_codes:
             self.country_codes = get_country_codes()
 
+        output = []
         for tld, country in self.country_codes.iteritems():
             if location.lower() in country.lower():
-                event.addresponse(u'%(tld)s is the TLD for %(country)s', {
+                output.append(u'%(tld)s is the ccTLD for %(country)s' % {
                     'tld': tld,
                     'country': country,
                 })
-                return
-
-        event.addresponse(u"ISO doesn't know about any TLD for %s", location)
+        if output:
+            event.addresponse(human_join(output))
+        else:
+            event.addresponse(u"ISO doesn't know about any TLD for %s",
+                              location)
 
 features['ports'] = {
     'description': u'Looks up port numbers for protocols',
 
=== modified file 'ibid/utils/__init__.py'
--- ibid/utils/__init__.py	2010-03-02 20:26:22 +0000
+++ ibid/utils/__init__.py	2010-03-07 10:12:33 +0000
@@ -1,6 +1,7 @@
 # Copyright (c) 2009-2010, Michael Gorven, Stefano Rivera
 # Released under terms of the MIT/X/Expat Licence. See COPYING for details.
 
+import codecs
 from gzip import GzipFile
 from htmlentitydefs import name2codepoint
 import logging
@@ -277,4 +278,35 @@
     code = process.wait()
     return output, error, code
 
+def get_country_codes():
+    filename = cacheable_download(
+            'http://www.iso.org/iso/list-en1-semic-3.txt',
+            'lookup/iso-3166-1_list_en.txt')
+
+    f = codecs.open(filename, 'r', 'ISO-8859-1')
+    countries = {
+        u'AC': u'Ascension Island',
+        u'UK': u'United Kingdom',
+        u'SU': u'Soviet Union',
+        u'EU': u'European Union',
+        u'TP': u'East Timor',
+        u'YU': u'Yugoslavia',
+    }
+
+    started = False
+    for line in f:
+        line = line.strip()
+        if started:
+            country, code = line.split(u';')
+            if u',' in country:
+                country = u' '.join(reversed(country.split(u',', 1)))
+            country = country.title()
+            countries[code] = country
+        elif line == u'':
+            started = True
+
+    f.close()
+
+    return countries
+
 # vi: set et sta sw=4 ts=4:
 
=== modified file 'ibid/utils/html.py'
--- ibid/utils/html.py	2010-02-21 10:12:10 +0000
+++ ibid/utils/html.py	2010-03-07 10:12:33 +0000
@@ -12,7 +12,7 @@
 from BeautifulSoup import BeautifulSoup
 
 from ibid.compat import ElementTree
-from ibid.utils import cacheable_download, url_to_bytestring
+from ibid.utils import url_to_bytestring
 
 class ContentTypeException(Exception):
     pass
@@ -62,25 +62,4 @@
 
     return parser.parse(data, encoding = encoding)
 
-def get_country_codes():
-    # The XML download doesn't include things like UK, so we consume this steaming pile of crud instead
-    filename = cacheable_download('http://www.iso.org/iso/country_codes/iso_3166_code_lists/iso-3166-1_decoding_table.htm', 'lookup/iso-3166-1_decoding_table.htm')
-    etree = get_html_parse_tree('file://' + filename, treetype='etree')
-    table = [x for x in etree.getiterator('table')][2]
-
-    countries = {}
-    for tr in table.getiterator('tr'):
-        abbr = [x.text for x in tr.getiterator('div')][0]
-        eng_name = [x.text for x in tr.getchildren()][1]
-
-        if eng_name and eng_name.strip():
-            # Cleanup:
-            if u',' in eng_name:
-                eng_name = u' '.join(reversed(eng_name.split(',', 1)))
-            eng_name = u' '.join(eng_name.split())
-
-            countries[abbr.upper()] = eng_name.title()
-
-    return countries
-
 # vi: set et sta sw=4 ts=4: