- }
-
- String text = textBuilder.toString();
- String translingual = "";
-
- while (text.length() > 0) {
- // Find start.
- final Matcher startMatcher = headingStart.matcher(text);
- if (!startMatcher.find()) {
- return;
- }
- text = text.substring(startMatcher.end());
-
- final String heading = startMatcher.group();
- for (final Selector selector : currentSelectors) {
- if (heading.indexOf("Translingual") != -1) {
- // Find end.
- final int depth = startMatcher.group(1).length();
- final Pattern endPattern = Pattern.compile(String.format("^={1,%d}[^=].*$", depth), Pattern.MULTILINE);
-
- final Matcher endMatcher = endPattern.matcher(text);
- if (endMatcher.find()) {
- int end = endMatcher.start();
- translingual = text.substring(0, endMatcher.start());
- text = text.substring(end);
- break;
- }
+ if (title.startsWith("Wiktionary:") ||
+ title.startsWith("Appendix:") ||
+ title.startsWith("Help:") ||
+ title.startsWith("Index:") ||
+ title.startsWith("MediaWiki:") ||
+ title.startsWith("Citations:") ||
+ title.startsWith("Concordance:") ||
+ title.startsWith("Glossary:") ||
+ title.startsWith("Rhymes:") ||
+ title.startsWith("Category:") ||
+ title.startsWith("Wikisaurus:") ||
+ title.startsWith("Unsupported titles/") ||
+ title.startsWith("Transwiki:") ||
+ title.startsWith("File:") ||
+ title.startsWith("Thread:") ||
+ title.startsWith("Template:") ||
+ title.startsWith("Summary:") ||
+ title.startsWith("Module:") ||
+ // DE
+ title.startsWith("Datei:") ||
+ title.startsWith("Verzeichnis:") ||
+ title.startsWith("Vorlage:") ||
+ title.startsWith("Thesaurus:") ||
+ title.startsWith("Kategorie:") ||
+ title.startsWith("Hilfe:") ||
+ title.startsWith("Reim:") ||
+ // FR:
+ title.startsWith("Annexe:") ||
+ title.startsWith("Catégori:") ||
+ title.startsWith("Modèle:") ||
+ title.startsWith("Thésaurus:") ||
+ title.startsWith("Projet:") ||
+ title.startsWith("Aide:") ||
+ title.startsWith("Fichier:") ||
+ title.startsWith("Wiktionnaire:") ||
+ title.startsWith("Catégorie:") ||
+ title.startsWith("Portail:") ||
+ title.startsWith("utiliusateur:") ||
+ title.startsWith("Kategorio:") ||
+ // IT
+ title.startsWith("Wikizionario:") ||
+ title.startsWith("Appendice:") ||
+ title.startsWith("Categoria:") ||
+ title.startsWith("Aiuto:") ||
+ title.startsWith("Portail:") ||
+ // ES
+ title.startsWith("Apéndice:") ||
+ title.startsWith("Archivo:") ||
+ title.startsWith("Ayuda:") ||
+ title.startsWith("Categoría:") ||
+ title.startsWith("Plantilla:") ||
+ title.startsWith("Wikcionario:") ||
+
+ // sentinel
+ false
+ ) {
+ return;
+ }
+ if (title.contains(":")) {
+ if (!title.startsWith("Sign gloss:")) {
+ System.err.println("title with colon: " + title);
+ }