You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by ra...@apache.org on 2017/02/07 22:12:52 UTC
opennlp git commit: OPENNLP-904 change PR following comments
Repository: opennlp
Updated Branches:
refs/heads/904 0e7c49aeb -> 177a63f10
OPENNLP-904 change PR following comments
Project: http://git-wip-us.apache.org/repos/asf/opennlp/repo
Commit: http://git-wip-us.apache.org/repos/asf/opennlp/commit/177a63f1
Tree: http://git-wip-us.apache.org/repos/asf/opennlp/tree/177a63f1
Diff: http://git-wip-us.apache.org/repos/asf/opennlp/diff/177a63f1
Branch: refs/heads/904
Commit: 177a63f10db7d2686a69bf8b6e9a5dd96a3b3cbd
Parents: 0e7c49a
Author: Rodrigo Agerri <ra...@apache.org>
Authored: Tue Feb 7 23:12:35 2017 +0100
Committer: Rodrigo Agerri <ra...@apache.org>
Committed: Tue Feb 7 23:12:35 2017 +0100
----------------------------------------------------------------------
.../tools/lemmatizer/DictionaryLemmatizer.java | 16 +++++-----------
1 file changed, 5 insertions(+), 11 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/opennlp/blob/177a63f1/opennlp-tools/src/main/java/opennlp/tools/lemmatizer/DictionaryLemmatizer.java
----------------------------------------------------------------------
diff --git a/opennlp-tools/src/main/java/opennlp/tools/lemmatizer/DictionaryLemmatizer.java b/opennlp-tools/src/main/java/opennlp/tools/lemmatizer/DictionaryLemmatizer.java
index 260f98a..7d31119 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/lemmatizer/DictionaryLemmatizer.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/lemmatizer/DictionaryLemmatizer.java
@@ -18,7 +18,6 @@
package opennlp.tools.lemmatizer;
import java.io.BufferedReader;
-import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.ArrayList;
@@ -52,19 +51,14 @@ public class DictionaryLemmatizer implements Lemmatizer {
// 1. We could get every lemma for a word,pos pair in the key
// 2. We could get every pos,lemma for a word in the key
// Crucially, both keys and values need to be collections, probably lists
- public DictionaryLemmatizer(final InputStream dictionary) {
+ public DictionaryLemmatizer(final InputStream dictionary) throws java.io.IOException {
this.dictMap = new HashMap<>();
final BufferedReader breader = new BufferedReader(
new InputStreamReader(dictionary));
String line;
- try {
- while ((line = breader.readLine()) != null) {
- final String[] elems = line.split("\t");
- this.dictMap.put(Arrays.asList(elems[0], elems[1]),
- Arrays.asList(elems[2]));
- }
- } catch (final IOException e) {
- e.printStackTrace();
+ while ((line = breader.readLine()) != null) {
+ final String[] elems = line.split("\t");
+ this.dictMap.put(Arrays.asList(elems[0], elems[1]), Arrays.asList(elems[2]));
}
}
@@ -103,7 +97,7 @@ public class DictionaryLemmatizer implements Lemmatizer {
}
public List<List<String>> lemmatize(final List<String> tokens, final List<String> posTags) {
- List<List<String>> allLemmas = new ArrayList<List<String>>();
+ List<List<String>> allLemmas = new ArrayList<>();
for (int i = 0; i < tokens.size(); i++) {
allLemmas.add(this.getAllLemmas(tokens.get(i), posTags.get(i)));
}