User:Daniel Mietchen/Sandbox4URLshortening

This page is used in conjunction with m:Special:UrlShortener as a workaround to https://phabricator.wikimedia.org/T220703 . URL shortening can also be triggered via the MediaWiki API.

The following query uses these:

• Properties: KIT Linked Open Numbers ID (P5176)   , numeric value (P1181)   , title (P1476)   

  # Most common ngrams in titles of works that contain the string "bologna" 
  # where the work has not been tagged as being about anything that contains that string
  
  SELECT DISTINCT ?Ngram ?Count ?Length ?CountTimesLength ?N ?ExamplePub ?ExamplePubTitle
  
  WITH
  { # Generating a list of regexes to look for the NumericValue-th word in a string                                                              
    SELECT ?Regex1 ?Regex2 ?Regex3 ?Regex4 ?NumericValue 
      { 
        ?NumberItem wdt:P5176 []; wdt:P1181 ?NumericValue . 
        FILTER( ?NumericValue > 0 ) 
        FILTER( ?NumericValue < 51)
        BIND( CONCAT( "^([^ ]+ ){", STR( ?NumericValue - 1 ),"}([^ ]+) .*") AS ?Regex1)
        BIND( CONCAT( "^([^ ]+ ){", STR( ?NumericValue + 1 ),"}([^ ]+) .*") AS ?Regex2) 
        BIND( CONCAT( "^([^ ]+ ){", STR( ?NumericValue + 3 ),"}([^ ]+) .*") AS ?Regex3) 
        BIND( CONCAT( "^([^ ]+ ){", STR( ?NumericValue + 5 ),"}([^ ]+) .*") AS ?Regex4) 
      }
  } AS %regexes 
  WITH
  { # Generating a list of titles to be analyzed
    SELECT ?Title ?Publication ?Seeds ?ClearTitleLength
     { # Choosing the entities whose titles are to be analyzed
        {
            SELECT ?Title ?Publication  WHERE {  
             hint:Query hint:optimizer "None".
  
              {  SERVICE wikibase:mwapi {
                bd:serviceParam wikibase:api "Search";
                                wikibase:endpoint "www.wikidata.org";
                                mwapi:srsearch "virus and haswbstatement:P31=Q13442814".
                ?page_title wikibase:apiOutput mwapi:title.
              }
              }
              UNION
              {  SERVICE wikibase:mwapi {
                bd:serviceParam wikibase:api "Search";
                                wikibase:endpoint "www.wikidata.org";
                                mwapi:srsearch "virus -and haswbstatement:P31=Q13442814".
                ?page_title wikibase:apiOutput mwapi:title.
              }
              }
                                    
          BIND(IRI(CONCAT(STR(wd:), ?page_title)) AS ?Publication)
          ?Publication wdt:P1476 ?Title.
  
          FILTER (REGEX(LCASE(?Title), "(transmi
  

Try it!