summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
authorS129778 <S129778@S129778.campus.tue.nl>2014-05-15 15:01:29 +0200
committerS129778 <S129778@S129778.campus.tue.nl>2014-05-15 15:11:59 +0200
commitd8162eb3e3d5b6008314cfdafd714c90632e0354 (patch)
tree8952961d38f363d69b900586cc420cb94e4fc393 /src
parent627b3dd7aa3597eb049f9996492198686dc138d2 (diff)
downloadGoldfarmer-d8162eb3e3d5b6008314cfdafd714c90632e0354.tar.gz
punctuation in text
Diffstat (limited to 'src')
-rw-r--r--src/main/Analyzor.java8
1 files changed, 8 insertions, 0 deletions
diff --git a/src/main/Analyzor.java b/src/main/Analyzor.java
index e893529..4b30134 100644
--- a/src/main/Analyzor.java
+++ b/src/main/Analyzor.java
@@ -129,4 +129,12 @@ public class Analyzor {
data.beforeFirst();
}
+
+ private String replacePunct(String text) {
+ text = text.replaceAll("https?://\\S*", "");
+ text = text.replaceAll("[!?):;\"']", " $0");
+ text = text.replaceAll("[.,-](\\s|$)", " $0");
+ text = text.replaceAll("\\s[(\"']", "$0 ");
+ return text;
+ }
}