jayvdb added a comment.

To verify the API is currently emitting NFC normalised langlink titles, I put 
the following into User:John_Vandenberg/test 
<https://en.wikipedia.org/w/index.php?title=User:John_Vandenberg/test&oldid=672324473>

  [[fa:&#x2126;]]
  
  [[fi:&#937;]]

https://en.wikipedia.org/w/api.php?action=query&prop=langlinks&titles=User:John_Vandenberg/test
 returns

  {
      "query": {
          "pages": {
              "40071800": {
                  "pageid": 40071800,
                  "ns": 2,
                  "title": "User:John Vandenberg/test",
                  "langlinks": [
                      {
                          "lang": "fa",
                          "*": "\u03a9"
                      },
                      {
                          "lang": "fi",
                          "*": "\u03a9"
                      }
                  ]
              }
          }
      }
  }

(also tested other formats, such as dbg, and all return actual unicode.)

The only way to get unnormalised html references out is to use `export`, like 
https://en.wikipedia.org/w/api.php?action=query&prop=langlinks&titles=User:John_Vandenberg/test&export=1
 :

  {
      "batchcomplete": "",
      "query": {
          "normalized": [
              {
                  "from": "User:John_Vandenberg/test",
                  "to": "User:John Vandenberg/test"
              }
          ],
          "pages": {
              "40071800": {
                  "pageid": 40071800,
                  "ns": 2,
                  "title": "User:John Vandenberg/test",
                  "langlinks": [
                      {
                          "lang": "fa",
                          "*": "\u03a9"
                      },
                      {
                          "lang": "fi",
                          "*": "\u03a9"
                      }
                  ]
              }
          },
          "export": {
              "*": "<mediawiki 
xmlns=\"http://www.mediawiki.org/xml/export-0.10/\"; 
xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"; 
xsi:schemaLocation=\"http://www.mediawiki.org/xml/export-0.10/ 
http://www.mediawiki.org/xml/export-0.10.xsd\"; version=\"0.10\" 
xml:lang=\"en\">\n  <siteinfo>\n    <sitename>Wikipedia</sitename>\n    
<dbname>enwiki</dbname>\n    
<base>https://en.wikipedia.org/wiki/Main_Page</base>\n    <generator>MediaWiki 
1.26wmf14</generator>\n    <case>first-letter</case>\n    <namespaces>\n      
<namespace key=\"-2\" case=\"first-letter\">Media</namespace>\n      <namespace 
key=\"-1\" case=\"first-letter\">Special</namespace>\n      <namespace 
key=\"0\" case=\"first-letter\" />\n      <namespace key=\"1\" 
case=\"first-letter\">Talk</namespace>\n      <namespace key=\"2\" 
case=\"first-letter\">User</namespace>\n      <namespace key=\"3\" 
case=\"first-letter\">User talk</namespace>\n      <namespace key=\"4\" 
case=\"first-letter\">Wikipedia</namespace>\n     
<namespace key=\"5\" case=\"first-letter\">Wikipedia talk</namespace>\n      
<namespace key=\"6\" case=\"first-letter\">File</namespace>\n      <namespace 
key=\"7\" case=\"first-letter\">File talk</namespace>\n      <namespace 
key=\"8\" case=\"first-letter\">MediaWiki</namespace>\n      <namespace 
key=\"9\" case=\"first-letter\">MediaWiki talk</namespace>\n      <namespace 
key=\"10\" case=\"first-letter\">Template</namespace>\n      <namespace 
key=\"11\" case=\"first-letter\">Template talk</namespace>\n      <namespace 
key=\"12\" case=\"first-letter\">Help</namespace>\n      <namespace key=\"13\" 
case=\"first-letter\">Help talk</namespace>\n      <namespace key=\"14\" 
case=\"first-letter\">Category</namespace>\n      <namespace key=\"15\" 
case=\"first-letter\">Category talk</namespace>\n      <namespace key=\"100\" 
case=\"first-letter\">Portal</namespace>\n      <namespace key=\"101\" 
case=\"first-letter\">Portal talk</namespace>\n      <namespace key=\"108\"
case=\"first-letter\">Book</namespace>\n      <namespace key=\"109\" 
case=\"first-letter\">Book talk</namespace>\n      <namespace key=\"118\" 
case=\"first-letter\">Draft</namespace>\n      <namespace key=\"119\" 
case=\"first-letter\">Draft talk</namespace>\n      <namespace key=\"446\" 
case=\"first-letter\">Education Program</namespace>\n      <namespace 
key=\"447\" case=\"first-letter\">Education Program talk</namespace>\n      
<namespace key=\"710\" case=\"first-letter\">TimedText</namespace>\n      
<namespace key=\"711\" case=\"first-letter\">TimedText talk</namespace>\n      
<namespace key=\"828\" case=\"first-letter\">Module</namespace>\n      
<namespace key=\"829\" case=\"first-letter\">Module talk</namespace>\n      
<namespace key=\"2600\" case=\"first-letter\">Topic</namespace>\n    
</namespaces>\n  </siteinfo>\n  <page>\n    <title>User:John 
Vandenberg/test</title>\n    <ns>2</ns>\n    <id>40071800</id>\n    
<revision>\n      <id>672324473</id>\n     
<parentid>671175129</parentid>\n      
<timestamp>2015-07-20T20:42:08Z</timestamp>\n      <contributor>\n        
<username>John Vandenberg</username>\n        <id>101140</id>\n      
</contributor>\n      <comment>[[WP:AES|\u2190]]Replaced content with 
'[[fa:&amp;#x2126;]]  [[fi:&amp;#937;]]'</comment>\n      
<model>wikitext</model>\n      <format>text/x-wiki</format>\n      <text 
xml:space=\"preserve\" 
bytes=\"30\">[[fa:&amp;#x2126;]]\n\n[[fi:&amp;#937;]]</text>\n      
<sha1>qmuv4xpjkjen1lug58vlwifs20xuk81</sha1>\n    </revision>\n  
</page>\n</mediawiki>\n"
          }
      }
  }


TASK DETAIL
  https://phabricator.wikimedia.org/T102461

EMAIL PREFERENCES
  https://phabricator.wikimedia.org/settings/panel/emailpreferences/

To: jayvdb
Cc: Ricordisamoa, gerritbot, Aklapper, jayvdb, pywikibot-bugs-list, Anshoe, 
Malyacko, P.Copp



_______________________________________________
pywikibot-bugs mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/pywikibot-bugs

Reply via email to