Apache/nifi
1
0
Fork 0
mirror of https://github.com/apache/nifi.git synced 2025-02-21 18:05:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

NIFI-911:

Browse Source 
- Updating default value for Regex so it matches once (?s:^.*$) instead of twice (.*). Matching on .* results in matching for every character and then again for 0 characters.
This commit is contained in:
Matt Gilman 2015-08-31 14:58:38 -04:00
parent 2bb7853001
commit cd2e1424cb
2 changed files with 43 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/ReplaceText.java
View File

@ -71,6 +71,9 @@ public class ReplaceText extends AbstractProcessor {
public static final String ENTIRE_TEXT = "Entire text";
private final Pattern backReferencePattern = Pattern.compile("\\$(\\d+)");
private static final byte[] ZERO_BYTE_BUFFER = new byte[0];
private static final String DEFAULT_REGEX = "(?s:^.*$)";
private static final String DEFAULT_REPLACEMENT_VALUE = "$1";
// Properties
public static final PropertyDescriptor REGEX = new PropertyDescriptor.Builder()
.name("Regular Expression")
@ -78,14 +81,14 @@ public class ReplaceText extends AbstractProcessor {
.required(true)
.addValidator(StandardValidators.createRegexValidator(0, Integer.MAX_VALUE, true))
.expressionLanguageSupported(true)
.defaultValue("(.*)")
.defaultValue(DEFAULT_REGEX)
.build();
public static final PropertyDescriptor REPLACEMENT_VALUE = new PropertyDescriptor.Builder()
.name("Replacement Value")
.description("The value to replace the regular expression with. Back-references to Regular Expression capturing groups are supported, but "
+ "back-references that reference capturing groups that do not exist in the regular expression will be treated as literal value.")
.required(true)
.defaultValue("$1")
.defaultValue(DEFAULT_REPLACEMENT_VALUE)
.addValidator(Validator.VALID)
.expressionLanguageSupported(true)
.build();
@ -166,7 +169,7 @@ public class ReplaceText extends AbstractProcessor {
final ProcessorLog logger = getLogger();
final String unsubstitutedRegex = context.getProperty(REGEX).getValue();
String unsubstitutedReplacement = context.getProperty(REPLACEMENT_VALUE).getValue();
if (unsubstitutedRegex.equals("(.*)") && unsubstitutedReplacement.equals("$1")) {
if (unsubstitutedRegex.equals(DEFAULT_REGEX) && unsubstitutedReplacement.equals(DEFAULT_REPLACEMENT_VALUE)) {
// This pattern says replace content with itself. We can highly optimize this process by simply transferring
// all FlowFiles to the 'success' relationship
session.transfer(flowFiles, REL_SUCCESS);

38
nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/test/java/org/apache/nifi/processors/standard/TestReplaceText.java
View File

@ -16,7 +16,6 @@
*/
package org.apache.nifi.processors.standard;
import org.apache.nifi.processors.standard.ReplaceText;
import org.apache.nifi.util.MockFlowFile;
import org.apache.nifi.util.TestRunner;
import org.apache.nifi.util.TestRunners;
@ -386,4 +385,41 @@ public class TestReplaceText {
out.assertContentEquals("{ abc.txt }");
}
@Test
public void testDefaultReplacement() throws Exception {
final String defaultValue = "default-replacement-value";
// leave the default regex settings
final TestRunner runner = TestRunners.newTestRunner(new ReplaceText());
runner.setValidateExpressionUsage(false);
runner.setProperty(ReplaceText.REPLACEMENT_VALUE, defaultValue);
final Map<String, String> attributes = new HashMap<>();
runner.enqueue("original-text".getBytes(StandardCharsets.UTF_8), attributes);
runner.run();
runner.assertAllFlowFilesTransferred(ReplaceText.REL_SUCCESS, 1);
final MockFlowFile out = runner.getFlowFilesForRelationship(ReplaceText.REL_SUCCESS).get(0);
out.assertContentEquals(defaultValue);
}
@Test
public void testDefaultMultilineReplacement() throws Exception {
final String defaultValue = "default-replacement-value";
// leave the default regex settings
final TestRunner runner = TestRunners.newTestRunner(new ReplaceText());
runner.setValidateExpressionUsage(false);
runner.setProperty(ReplaceText.REPLACEMENT_VALUE, defaultValue);
final Map<String, String> attributes = new HashMap<>();
runner.enqueue(("original-text-line-1" + System.lineSeparator() + "original-text-line-2").getBytes(StandardCharsets.UTF_8), attributes);
runner.run();
runner.assertAllFlowFilesTransferred(ReplaceText.REL_SUCCESS, 1);
final MockFlowFile out = runner.getFlowFilesForRelationship(ReplaceText.REL_SUCCESS).get(0);
out.assertContentEquals(defaultValue);
}
}