Github user takuti commented on a diff in the pull request:
https://github.com/apache/incubator-hivemall/pull/97#discussion_r126846652
--- Diff: nlp/src/main/java/hivemall/nlp/tokenizer/KuromojiUDF.java ---
@@ -44,47 +53,52 @@
import org.apache.lucene.analysis.ja.JapaneseAnalyzer;
import org.apache.lucene.analysis.ja.JapaneseTokenizer;
import org.apache.lucene.analysis.ja.JapaneseTokenizer.Mode;
+import org.apache.lucene.analysis.ja.dict.UserDictionary;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
@Description(
name = "tokenize_ja",
- value = "_FUNC_(String line [, const string mode = \"normal\",
const list<string> stopWords, const list<string> stopTags])"
+ value = "_FUNC_(String line [, const string mode = \"normal\",
const array<string> stopWords, const array<string> stopTags, const
array<string> userDict (or string userDictURL)])"
+ " - returns tokenized strings in array<string>")
@UDFType(deterministic = true, stateful = false)
public final class KuromojiUDF extends GenericUDF {
+ private static final int CONNECT_TIMEOUT_MS = 10000;
+ private static final int READ_TIMEOUT_MS = 30000;
+ private static final long MAX_INPUT_STREAM_SIZE = 1000000L; // ~1MB
--- End diff --
Sure
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
