diff --git a/CHANGELOG.md b/CHANGELOG.md index 8921a6d..5f67f50 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,10 @@ All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/). It follows [some conventions](http://keepachangelog.com/). + ## [1.1.0] - 2017-09-20 + ### Added +- possibility to index EWTS text + ## [1.0.0] - 2017-04-14 ### Added - Maven packaging diff --git a/pom.xml b/pom.xml index 9351359..cd8b72f 100644 --- a/pom.xml +++ b/pom.xml @@ -4,7 +4,7 @@ io.bdrc.lucene lucene-bo jar - 1.0.0 + 1.1.0 lucene-bo Tibetan Lucene analyzer and components https://github.com/BuddhistDigitalResourceCenter/lucene-bo @@ -75,7 +75,7 @@ io.bdrc.ewtsconverter ewts-converter - 1.1.0 + 1.2.0 diff --git a/src/main/java/io/bdrc/lucene/bo/TibWordTokenizer.java b/src/main/java/io/bdrc/lucene/bo/TibWordTokenizer.java index cdcd2f5..9dbe5bc 100644 --- a/src/main/java/io/bdrc/lucene/bo/TibWordTokenizer.java +++ b/src/main/java/io/bdrc/lucene/bo/TibWordTokenizer.java @@ -66,9 +66,9 @@ public final class TibWordTokenizer extends Tokenizer { /** * Constructs a TibWordTokenizer using the file designed by filename - * @param filename - * @throws FileNotFoundException - * @throws IOException + * @param filename the path to the lexicon file + * @throws FileNotFoundException the file containing the lexicon cannot be found + * @throws IOException the file containing the lexicon cannot be read */ public TibWordTokenizer(String filename) throws FileNotFoundException, IOException { init(filename); @@ -76,8 +76,8 @@ public TibWordTokenizer(String filename) throws FileNotFoundException, IOExcepti /** * Constructs a TibWordTokenizer using a default lexicon file (here "resource/output/total_lexicon.txt") - * @throws FileNotFoundException - * @throws IOException + * @throws FileNotFoundException the file containing the lexicon cannot be found + * @throws IOException the file containing the lexicon cannot be read */ public TibWordTokenizer() throws FileNotFoundException, IOException { init("resource/output/total_lexicon.txt"); @@ -123,6 +123,9 @@ private void init(String filename) throws FileNotFoundException, IOException { * Called on each token character to normalize it before it is added to the * token. The default implementation does nothing. Subclasses may use this to, * e.g., lowercase tokens. + * + * @param c the character to normalize + * @return the normalized character */ protected int normalize(int c) { return c;