Merge pull request #152 from ninniuz/151_server_extraction_ampersand

jimkont · jimkont · commit 9330afdf2d5f · 2014-01-19T21:02:53.000-08:00
Issue #151: URL encode wikititle in sample page extraction
diff --git a/core/src/main/scala/org/dbpedia/extraction/util/WikiApi.scala b/core/src/main/scala/org/dbpedia/extraction/util/WikiApi.scala
@@ -119,7 +119,7 @@ class WikiApi(url: URL, language: Language)
         {
             for(titleGroup <- titles.grouped(pageDownloadLimit))
             {
-                val response = query("?action=query&format=xml&prop=revisions&titles=" + titleGroup.map(_.encodedWithNamespace).mkString("|") + "&rvprop=ids|content|timestamp|user|userid")
+                val response = query("?action=query&format=xml&prop=revisions&titles=" + titleGroup.map(t => URLEncoder.encode(t.encodedWithNamespace, "UTF-8")).mkString("|") + "&rvprop=ids|content|timestamp|user|userid")
                 processPages(response, proc)
             }
         }

Original file line number	Diff line number	Diff line change
`@@ -119,7 +119,7 @@ class WikiApi(url: URL, language: Language)`
`119`	`119`	`{`
`120`	`120`	`for(titleGroup <- titles.grouped(pageDownloadLimit))`
`121`	`121`	`{`
`122`		`- val response = query("?action=query&format=xml&prop=revisions&titles=" + titleGroup.map(_.encodedWithNamespace).mkString("\|") + "&rvprop=ids\|content\|timestamp\|user\|userid")`
	`122`	`+ val response = query("?action=query&format=xml&prop=revisions&titles=" + titleGroup.map(t => URLEncoder.encode(t.encodedWithNamespace, "UTF-8")).mkString("\|") + "&rvprop=ids\|content\|timestamp\|user\|userid")`
`123`	`123`	`processPages(response, proc)`
`124`	`124`	`}`
`125`	`125`	`}`