Fix RegexTagger not picking up XML-configured "fieldMatcher".

Norconex · Mar 3, 2023 · 2fbdc6a · 2fbdc6a
1 parent 0d09886
commit 2fbdc6a
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 5 deletions.
diff --git a/CHANGES.xml b/CHANGES.xml
@@ -7,18 +7,18 @@
   </properties>
   <body>
 
-    <release version="3.0.1-SNAPSHOT" date="2022-??-??">
-
+    <release version="3.0.1-SNAPSHOT" date="2023-??-??">
       <action dev="essiembre" type="add" issue="76">
         New DOMPreserveTransformer.
       </action>
       <action dev="essiembre" type="update">
         Maven dependency updates: norconex-commons-maven-parent 1.0.2-SNAPSHOT.
       </action>
-
+      <action dev="essiembre" type="fix">
+        Fix RegexTagger not picking up XML-configured "fieldMatcher". 
+      </action>
     </release>
 
-
     <release version="3.0.0" date="2022-01-02" 
             description="Major release. NOT a drop-in replacement for 2.x.">
 

diff --git a/src/main/java/com/norconex/importer/handler/tagger/impl/RegexTagger.java b/src/main/java/com/norconex/importer/handler/tagger/impl/RegexTagger.java
@@ -198,6 +198,7 @@ public void setFieldMatcher(TextMatcher fieldMatcher) {
 
     @Override
     protected void loadStringTaggerFromXML(XML xml) {
+        fieldMatcher.loadFromXML(xml.getXML("fieldMatcher"));
         List<XML> nodes = xml.getXMLList("pattern");
         for (XML node : nodes) {
             node.checkDeprecated("@caseSensitive", "ignoreCase", true);
@@ -209,6 +210,7 @@ protected void loadStringTaggerFromXML(XML xml) {
 
     @Override
     protected void saveStringTaggerToXML(XML xml) {
+        xml.addElement("fieldMatcher", fieldMatcher);
         for (RegexFieldValueExtractor rfe : patterns) {
             rfe.saveToXML(xml.addElement("pattern"));
         }

diff --git a/src/test/java/com/norconex/importer/handler/tagger/impl/RegexTaggerTest.java b/src/test/java/com/norconex/importer/handler/tagger/impl/RegexTaggerTest.java
@@ -89,8 +89,9 @@ public void testExtractFirst100ContentChars()
     }
 
     @Test
-        public void testWriteRead() {
+    public void testWriteRead() {
         RegexTagger tagger = new RegexTagger();
+        tagger.getFieldMatcher().setPattern("(.*)(crawler)").partial();
         tagger.addPattern("field1", "123.*890");
         tagger.addPattern("field2", "abc.*xyz", 3);
         tagger.addPattern(new RegexFieldValueExtractor("blah")