Author: srowen
Date: Mon Nov 28 10:45:08 2011
New Revision: 1207060
URL: http://svn.apache.org/viewvc?rev=1207060&view=rev
Log:
MAHOUT-895 Match Wikipedia start/close tags as-is without preprocessing
Modified:
mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorDriver.java
mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java
Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorDriver.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorDriver.java?rev=1207060&r1=1207059&r2=1207060&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorDriver.java
(original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorDriver.java
Mon Nov 28 10:45:08 2011
@@ -144,8 +144,8 @@ public final class WikipediaDatasetCreat
throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
conf.set("key.value.separator.in.input.line", " ");
- conf.set("xmlinput.start", "<text xml:space=\"preserve\">");
- conf.set("xmlinput.end", "</text>");
+ conf.set("xmlinput.start", "<page>");
+ conf.set("xmlinput.end", "</page>");
conf.setBoolean("exact.match.only", exactMatchOnly);
conf.set("analyzer.class", analyzerClass.getName());
conf.set("io.serializations",
Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java?rev=1207060&r1=1207059&r2=1207060&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java
(original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorMapper.java
Mon Nov 28 10:45:08 2011
@@ -63,11 +63,11 @@ public class WikipediaDatasetCreatorMapp
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
{
String document = value.toString();
+ document = StringEscapeUtils.unescapeHtml(CLOSE_TEXT_TAG_PATTERN.matcher(
+ OPEN_TEXT_TAG_PATTERN.matcher(document).replaceFirst("")).replaceAll(""));
String catMatch = findMatchingCategory(document);
if (!"Unknown".equals(catMatch)) {
StringBuilder contents = new StringBuilder(1000);
- document = StringEscapeUtils.unescapeHtml(CLOSE_TEXT_TAG_PATTERN.matcher(
- OPEN_TEXT_TAG_PATTERN.matcher(document).replaceFirst("")).replaceAll(""));
TokenStream stream = analyzer.reusableTokenStream(catMatch, new StringReader(document));
CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
stream.reset();
|