From: Reimar Döffinger Date: Wed, 9 Jan 2019 20:43:52 +0000 (+0100) Subject: Improve wiktionary splitter for Spanish and Portuguese X-Git-Url: http://gitweb.fperrin.net/?p=DictionaryPC.git;a=commitdiff_plain;h=db867ac06ddeb858f5a70f682e71826346c31895 Improve wiktionary splitter for Spanish and Portuguese --- diff --git a/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java b/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java index 056fabe..435c3f2 100644 --- a/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java +++ b/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java @@ -187,6 +187,15 @@ public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler { title.startsWith("Plantilla:") || title.startsWith("Wikcionario:") || + // PT + title.startsWith("Ajuda:") || + title.startsWith("Apêndice:") || + title.startsWith("Citações:") || + title.startsWith("Portal:") || + title.startsWith("Predefinição:") || + title.startsWith("Vocabulário:") || + title.startsWith("Wikcionário:") || + // sentinel false ) return; @@ -196,6 +205,8 @@ public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler { } String text = textBuilder.toString(); + // Workaround for Spanish wiktionary {{ES}} pattern + text = text.replace("{{ES}}", "== {{lengua|es}} =="); String translingual = ""; int start = 0; final Matcher startMatcher = headingStart.matcher(text);