summaryrefslogtreecommitdiffstats
path: root/linguistics/src/main/java/com/yahoo/language/opennlp/UrlCharSequenceNormalizer.java
diff options
context:
space:
mode:
Diffstat (limited to 'linguistics/src/main/java/com/yahoo/language/opennlp/UrlCharSequenceNormalizer.java')
-rw-r--r--linguistics/src/main/java/com/yahoo/language/opennlp/UrlCharSequenceNormalizer.java31
1 files changed, 0 insertions, 31 deletions
diff --git a/linguistics/src/main/java/com/yahoo/language/opennlp/UrlCharSequenceNormalizer.java b/linguistics/src/main/java/com/yahoo/language/opennlp/UrlCharSequenceNormalizer.java
deleted file mode 100644
index 883319e2f8b..00000000000
--- a/linguistics/src/main/java/com/yahoo/language/opennlp/UrlCharSequenceNormalizer.java
+++ /dev/null
@@ -1,31 +0,0 @@
-// Copyright Yahoo. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
-package com.yahoo.language.opennlp;
-
-import opennlp.tools.util.normalizer.CharSequenceNormalizer;
-
-import java.util.regex.Pattern;
-
-/**
- * Modifies {@link opennlp.tools.util.normalizer.UrlCharSequenceNormalizer} to avoid the bad email regex.
- *
- * @author jonmv
- */
-public class UrlCharSequenceNormalizer implements CharSequenceNormalizer {
-
- private static final Pattern URL_REGEX =
- Pattern.compile("https?://[-_.?&~;+=/#0-9A-Za-z]+");
- private static final Pattern MAIL_REGEX =
- Pattern.compile("(?<![-+_.0-9A-Za-z])[-+_.0-9A-Za-z]+@[-0-9A-Za-z]+[-.0-9A-Za-z]+");
-
- private static final UrlCharSequenceNormalizer INSTANCE = new UrlCharSequenceNormalizer();
-
- public static UrlCharSequenceNormalizer getInstance() {
- return INSTANCE;
- }
-
- public CharSequence normalize(CharSequence text) {
- String modified = URL_REGEX.matcher(text).replaceAll(" ");
- return MAIL_REGEX.matcher(modified).replaceAll(" ");
- }
-
-}