Skip to content

Commit 2f3cc1a

Browse files
committed
Use more-readable-anchors-new instead of lessreadableanchors(old) ; minor fixes in abstract description and bzip2 footnote
1 parent 8f11bac commit 2f3cc1a

File tree

1 file changed

+6
-4
lines changed

1 file changed

+6
-4
lines changed

scripts/src/main/scala/org/dbpedia/extraction/scripts/CreateDownloadPage.scala

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,7 @@ package org.dbpedia.extraction.scripts
33
import java.util.Locale
44
import java.io.File
55
import org.dbpedia.extraction.util.RichFile.wrapFile
6+
import org.dbpedia.extraction.util.RichString.wrapString
67
import org.dbpedia.extraction.util.StringPlusser
78
import org.dbpedia.extraction.scripts.IOUtils.readLines
89
import scala.collection.mutable.{Map,HashMap}
@@ -90,7 +91,7 @@ abstract class Fileset(
9091

9192
protected def path(language: String, modifier: String, format: String): String
9293

93-
val anchor = name.replace(" ", "").toLowerCase(Locale.ENGLISH)
94+
val anchor = name.replaceChars(" ()", "-").toLowerCase(Locale.ENGLISH)
9495
}
9596

9697
class Ontology(name: String, file: String, text: String)
@@ -139,8 +140,8 @@ val datasets = List(
139140
),
140141
List(
141142
new Dataset("Titles", "labels", "//Titles of all Wikipedia Articles in the corresponding language.//"),
142-
new Dataset("Short Abstracts", "short_abstracts", "//Short Abstracts (max. 500 chars long) of Wikipedia articles//"),
143-
new Dataset("Extended Abstracts", "long_abstracts", "//Additional, extended English abstracts.//"),
143+
new Dataset("Short Abstracts", "short_abstracts", "//Short Abstracts (max. 500 characters long) of Wikipedia articles.//"),
144+
new Dataset("Extended Abstracts", "long_abstracts", "//Full abstracts of Wikipedia articles, usually the first section.//"),
144145
new Dataset("Images", "images", "//Main image and corresponding thumbnail from Wikipedia article.//")
145146
),
146147
List(
@@ -262,7 +263,8 @@ def generate: Unit = {
262263
"\n" +
263264
"[[#1]] Most files were packed with ((http://compression.ca/pbzip2/ pbzip2)), which generates concatenated streams. " +
264265
"Some older bzip2 decompressors, for example ((https://issues.apache.org/jira/browse/COMPRESS-162 Apache Commons Compress before version 1.4)), " +
265-
"cannot handle this format. Please make sure that you use the latest version and let us know if you experience any problems.\n"+
266+
"cannot handle this format. Please make sure that you use the latest version. " +
267+
"((https://lists.sourceforge.net/lists/listinfo/dbpedia-discussion/ Let us know)) if you experience any problems.\n"+
266268
"\n" +
267269
mark("")
268270

0 commit comments

Comments
 (0)