BATCH-1874: add RegexTokenizer

adding the simple array field set mapper

spring-batch-infrastructure/src/main/java/org/springframework/batch/item/file/mapping/ArrayFieldSetMapper.java

@@ -0,0 +1,33 @@
+/*
+ * Copyright 2011-2012 the original author or authors.
+ * 
+ * Licensed 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.springframework.batch.item.file.mapping;
+
+import org.springframework.batch.item.file.transform.FieldSet;
+import org.springframework.validation.BindException;
+
+/**
+ * A basic array mapper, returning the values backing a fieldset.
+ * Useful for reading the Strings resulting from the line tokenizer without having to
+ * deal with a {@link FieldSet} object.  
+ * 
+ * @author Costin Leau
+ */
+public class ArrayFieldSetMapper implements FieldSetMapper<String[]> {
+
+	public String[] mapFieldSet(FieldSet fieldSet) throws BindException {
+		return fieldSet.getValues();
+	}
+}

spring-batch-infrastructure/src/main/java/org/springframework/batch/item/file/transform/RegexLineTokenizer.java

@@ -0,0 +1,89 @@
+/*
+ * Copyright 2006-2012 the original author or authors.
+ * 
+ * Licensed 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.springframework.batch.item.file.transform;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import org.springframework.util.Assert;
+
+/**
+ * Line-tokenizer using a regular expression to filter out data (by using matching and non-matching groups).
+ * Consider the following regex which picks only the first and last name (notice the non-matching group in the middle):
+ * <pre>
+ * (.*?)(?: .*)* (.*) 
+ * </pre>
+ * For the names:
+ * <ul>  
+ *  <li>"Graham James Edward Miller"</li>
+ *  <li>"Andrew Gregory Macintyre"</li>
+ *  <li>"No MiddleName"</li>
+ * </ul> 
+ * 
+ * the output will be:
+ * <ul>
+ * <li>"Miller", "Graham"</li>
+ * <li>"Macintyre", "Andrew"</li>
+ * <li>"MiddleName", "No"</li>
+ * </ul>
+ * 
+ * An empty list is returned, in case of a non-match.
+ * 
+ * @see Matcher#group(int)
+ * @author Costin Leau
+ */
+public class RegexLineTokenizer extends AbstractLineTokenizer {
+
+	private Pattern pattern;
+
+	@Override
+	protected List<String> doTokenize(String line) {
+		Matcher matcher = pattern.matcher(line);
+		boolean matchFound = matcher.find();
+
+		if (matchFound) {
+			List<String> tokens = new ArrayList<String>(matcher.groupCount());
+			for (int i = 1; i <= matcher.groupCount(); i++) {
+				tokens.add(matcher.group(i));
+			}
+			return tokens;
+		}
+		return Collections.emptyList();
+	}
+
+	/**
+	 * Sets the regex pattern to use.
+	 * 
+	 * @param pattern Regular Expression pattern
+	 */
+	public void setPattern(Pattern pattern) {
+		Assert.notNull(pattern, "a non-null pattern is required");
+		this.pattern = pattern;
+	}
+
+	/**
+	 * Sets the regular expression to use. 
+	 * 
+	 * @param regex regular expression (as a String)
+	 */
+	public void setRegex(String regex) {
+		Assert.hasText(regex, "a valid regex is required");
+		this.pattern = Pattern.compile(regex);
+	}
+}

spring-batch-infrastructure/src/test/java/org/springframework/batch/item/file/transform/RegexLineTokenizerTests.java

@@ -0,0 +1,54 @@
+/*
+ * Copyright 2006-2012 the original author or authors.
+ * 
+ * Licensed 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.springframework.batch.item.file.transform;
+
+import java.util.List;
+
+import org.junit.Test;
+
+import static org.junit.Assert.*;
+
+public class RegexLineTokenizerTests {
+
+	private RegexLineTokenizer tokenizer = new RegexLineTokenizer();
+
+	@Test
+	public void testCapturingGroups() {
+		String line = "Liverpool, England: 53d 25m 0s N 3d 0m 0s";
+		tokenizer.setRegex("([a-zA-Z]+), ([a-zA-Z]+): ([0-9]+). ([0-9]+). ([0-9]+). ([A-Z]) ([0-9]+). ([0-9]+). ([0-9]+).");
+		List<String> tokens = tokenizer.doTokenize(line);
+		assertEquals(9, tokens.size());
+		assertEquals("England", tokens.get(1));
+		assertEquals("3", tokens.get(6));
+	}
+
+	@Test
+	public void testNonCapturingGroups() {
+		String line = "Graham James Edward Miller";
+		tokenizer.setRegex("(.*?)(?: .*)* (.*)");
+		List<String> tokens = tokenizer.doTokenize(line);
+		assertEquals(2, tokens.size());
+		assertEquals("Graham", tokens.get(0));
+		assertEquals("Miller", tokens.get(1));
+	}
+
+	@Test
+	public void testNoMatch() {
+		tokenizer.setRegex("([0-9]+).");
+		List<String> tokens = tokenizer.doTokenize("noNumber");
+		assertEquals(0, tokens.size());
+	}
+}