> iterator = headers.entrySet().iterator();
+ while (iterator.hasNext() && !headerFound) {
+ startHeader = endHeader;
+ endHeader = iterator.next().getKey();
+ if (endHeader > matcher.start()) {
+ headerFound = true;
+ }
+ }
+
+ String header = headers.get(startHeader);
+ if (header != null && headers.get(startHeader).matches(REGEX_APPLICABLE_DOCUMENTS)) {
+ score += 0.25;
+ }
+
+ builder.setScore(score);
+
+ if (score >= threshold) {
+ standards.add(builder.build());
+ }
+ }
+
+ return standards;
+ }
+}
\ No newline at end of file
diff --git a/tika-example/src/main/java/org/apache/tika/example/StandardsExtractionExample.java b/tika-example/src/main/java/org/apache/tika/example/StandardsExtractionExample.java
new file mode 100644
index 000000000..aad5fd7bb
--- /dev/null
+++ b/tika-example/src/main/java/org/apache/tika/example/StandardsExtractionExample.java
@@ -0,0 +1,109 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.tika.sax;
+
+import java.io.BufferedInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.file.FileVisitResult;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.nio.file.SimpleFileVisitor;
+import java.nio.file.attribute.BasicFileAttributes;
+import java.util.Collections;
+import java.util.HashSet;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.AutoDetectParser;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+
+/**
+ * Class to demonstrate how to use the {@link StandardsExtractingContentHandler}
+ * to get a list of the standard references from every file in a directory.
+ *
+ *
+ * You can run this main method by running
+ *
+ * mvn exec:java -Dexec.mainClass="org.apache.tika.example.StandardsExtractionExample" -Dexec.args="/path/to/input"
+ *
+ * from the tika-example directory.
+ *
+ */
+public class StandardsExtractionExample {
+ private static HashSet standardReferences = new HashSet<>();
+ private static int failedFiles = 0;
+ private static int successfulFiles = 0;
+
+ public static void main(String[] args) {
+ if (args.length < 1) {
+ System.err.println("Usage: " + StandardsExtractionExample.class.getName() + " /path/to/input");
+ System.exit(1);
+ }
+ String pathname = args[0];
+
+ Path folder = Paths.get(pathname);
+ System.out.println("Searching " + folder.toAbsolutePath() + "...");
+ processFolder(folder);
+ System.out.println(standardReferences.toString());
+ System.out.println("Parsed " + successfulFiles + "/" + (successfulFiles + failedFiles));
+ }
+
+ public static void processFolder(Path folder) {
+ try {
+ Files.walkFileTree(folder, new SimpleFileVisitor() {
+ @Override
+ public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
+ try {
+ process(file);
+ successfulFiles++;
+ } catch (Exception e) {
+ failedFiles++;
+ // ignore this file
+ }
+ return FileVisitResult.CONTINUE;
+ }
+
+ @Override
+ public FileVisitResult visitFileFailed(Path file, IOException exc) throws IOException {
+ failedFiles++;
+ return FileVisitResult.CONTINUE;
+ }
+ });
+ } catch (IOException e) {
+ // ignore failure
+ }
+ }
+
+ public static void process(Path path) throws Exception {
+ Parser parser = new AutoDetectParser();
+ Metadata metadata = new Metadata();
+ // The StandardsExtractingContentHandler will examine any characters for
+ // standard references before passing them
+ // to the underlying Handler.
+ StandardsExtractingContentHandler handler = new StandardsExtractingContentHandler(new BodyContentHandler(-1),
+ metadata);
+ handler.setThreshold(1.0);
+ try (InputStream stream = new BufferedInputStream(Files.newInputStream(path))) {
+ parser.parse(stream, handler, metadata, new ParseContext());
+ }
+ String[] references = metadata.getValues(StandardsExtractingContentHandler.STANDARD_REFERENCES);
+ Collections.addAll(standardReferences, references);
+ }
+}
\ No newline at end of file
diff --git a/tika-parsers/src/test/java/org/apache/tika/sax/StandardsExtractingContentHandlerTest.java b/tika-parsers/src/test/java/org/apache/tika/sax/StandardsExtractingContentHandlerTest.java
new file mode 100644
index 000000000..ff31a97f4
--- /dev/null
+++ b/tika-parsers/src/test/java/org/apache/tika/sax/StandardsExtractingContentHandlerTest.java
@@ -0,0 +1,50 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.tika.sax;
+
+import static org.junit.Assert.*;
+
+import java.io.InputStream;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.AutoDetectParser;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+import org.junit.Test;
+
+/**
+ * Test class for the {@link StandardsExtractingContentHandler} class.
+ */
+public class StandardsExtractingContentHandlerTest {
+
+ @Test
+ public void testExtractStandards() throws Exception {
+ Parser parser = new AutoDetectParser();
+ Metadata metadata = new Metadata();
+
+ StandardsExtractingContentHandler handler = new StandardsExtractingContentHandler(new BodyContentHandler(-1), metadata);
+ handler.setThreshold(0.75);
+ InputStream inputStream = StandardsExtractingContentHandlerTest.class.getResourceAsStream("/test-documents/testStandardsExtractor.pdf");
+
+ parser.parse(inputStream, handler, metadata, new ParseContext());
+
+ String[] standardReferences = metadata.getValues(StandardsExtractingContentHandler.STANDARD_REFERENCES);
+ assertTrue(standardReferences[0].equals("ANSI/TIA 222-G"));
+ assertTrue(standardReferences[1].equals("TIA/ANSI 222-G-1"));
+ }
+}
\ No newline at end of file
diff --git a/tika-parsers/src/test/resources/test-documents/testStandardsExtractor.pdf b/tika-parsers/src/test/resources/test-documents/testStandardsExtractor.pdf
new file mode 100644
index 000000000..aad6d79d4
Binary files /dev/null and b/tika-parsers/src/test/resources/test-documents/testStandardsExtractor.pdf differ