You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@stormcrawler.apache.org by rz...@apache.org on 2024/05/21 10:33:04 UTC
(incubator-stormcrawler) 01/01: #1236 - Fix Typos in StormCrawler
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a commit to branch fix-typos
in repository https://gitbox.apache.org/repos/asf/incubator-stormcrawler.git
commit 63fabf5fa0d447896d5cc99083bb64b885433a44
Author: Richard Zowalla <rz...@apache.org>
AuthorDate: Tue May 21 12:29:26 2024 +0200
#1236 - Fix Typos in StormCrawler
---
THIRD-PARTY.txt | 13 ++++++++-----
.../archetype-resources/src/main/resources/urlfilters.json | 2 +-
.../main/java/org/apache/stormcrawler/bolt/FetcherBolt.java | 2 +-
.../org/apache/stormcrawler/bolt/SimpleFetcherBolt.java | 4 ++--
.../apache/stormcrawler/filtering/basic/BasicURLFilter.java | 10 +++++-----
.../stormcrawler/filtering/basic/BasicURLNormalizer.java | 8 ++++----
.../java/org/apache/stormcrawler/persistence/Scheduler.java | 2 +-
.../stormcrawler/persistence/urlbuffer/URLBuffer.java | 2 +-
.../main/java/org/apache/stormcrawler/spout/FileSpout.java | 2 +-
.../org/apache/stormcrawler/util/InitialisationUtil.java | 4 ++--
.../java/org/apache/stormcrawler/util/MetadataTransfer.java | 2 +-
.../src/main/java/org/apache/stormcrawler/util/URLUtil.java | 8 ++++----
core/src/main/resources/crawler-default.yaml | 2 +-
.../apache/stormcrawler/filtering/BasicURLFilterTest.java | 4 ++--
.../stormcrawler/filtering/BasicURLNormalizerTest.java | 4 ++--
...ce.java => ClassInheritingFromAbstractAndInterface.java} | 2 +-
.../stormcrawler/parse/filter/SubDocumentsParseFilter.java | 6 +++---
.../apache/stormcrawler/util/InitialisationUtilTest.java | 6 +++---
external/aws/README.md | 2 +-
.../main/resources/archetype-resources/opensearch-conf.yaml | 2 +-
.../archetype-resources/src/main/resources/urlfilters.json | 2 +-
external/opensearch/opensearch-conf.yaml | 2 +-
.../main/java/org/apache/stormcrawler/tika/DOMBuilder.java | 4 ++--
23 files changed, 49 insertions(+), 46 deletions(-)
diff --git a/THIRD-PARTY.txt b/THIRD-PARTY.txt
index e23eb21f..18b251b4 100644
--- a/THIRD-PARTY.txt
+++ b/THIRD-PARTY.txt
@@ -136,11 +136,12 @@ List of third-party dependencies grouped by their license type.
* FindBugs-jsr305 (com.google.code.findbugs:jsr305:3.0.2 - http://findbugs.sourceforge.net/)
* Google Android Annotations Library (com.google.android:annotations:4.1.1.4 - http://source.android.com/)
* Graphite Integration for Metrics (io.dropwizard.metrics:metrics-graphite:3.2.6 - http://metrics.dropwizard.io/metrics-graphite/)
- * Gson (com.google.code.gson:gson:2.8.9 - https://github.com/google/gson/gson)
+ * Gson (com.google.code.gson:gson:2.10.1 - https://github.com/google/gson/gson)
* Gson (com.google.code.gson:gson:2.9.0 - https://github.com/google/gson/gson)
* Guava: Google Core Libraries for Java (com.google.guava:guava:18.0 - http://code.google.com/p/guava-libraries/guava)
* Guava: Google Core Libraries for Java (com.google.guava:guava:31.1-android - https://github.com/google/guava)
* Guava: Google Core Libraries for Java (com.google.guava:guava:33.0.0-jre - https://github.com/google/guava)
+ * Guava: Google Core Libraries for Java (com.google.guava:guava:33.1.0-jre - https://github.com/google/guava)
* Guava InternalFutureFailureAccess and InternalFutures (com.google.guava:failureaccess:1.0.1 - https://github.com/google/guava/failureaccess)
* Guava InternalFutureFailureAccess and InternalFutures (com.google.guava:failureaccess:1.0.2 - https://github.com/google/guava/failureaccess)
* Guava ListenableFuture only (com.google.guava:listenablefuture:9999.0-empty-to-avoid-conflict-with-guava - https://github.com/google/guava/listenablefuture)
@@ -154,11 +155,13 @@ List of third-party dependencies grouped by their license type.
* io.grpc:grpc-stub (io.grpc:grpc-stub:1.50.2 - https://github.com/grpc/grpc-java)
* J2ObjC Annotations (com.google.j2objc:j2objc-annotations:1.3 - https://github.com/google/j2objc/)
* J2ObjC Annotations (com.google.j2objc:j2objc-annotations:2.8 - https://github.com/google/j2objc/)
+ * J2ObjC Annotations (com.google.j2objc:j2objc-annotations:3.0.0 - https://github.com/google/j2objc/)
* Jackcess (com.healthmarketscience.jackcess:jackcess:4.0.5 - https://jackcess.sourceforge.io)
* Jackcess Encrypt (com.healthmarketscience.jackcess:jackcess-encrypt:4.0.2 - http://jackcessencrypt.sf.net)
* Jackson-annotations (com.fasterxml.jackson.core:jackson-annotations:2.15.2 - https://github.com/FasterXML/jackson)
* Jackson-core (com.fasterxml.jackson.core:jackson-core:2.15.2 - https://github.com/FasterXML/jackson-core)
* Jackson-core (com.fasterxml.jackson.core:jackson-core:2.16.1 - https://github.com/FasterXML/jackson-core)
+ * Jackson-core (com.fasterxml.jackson.core:jackson-core:2.17.0 - https://github.com/FasterXML/jackson-core)
* jackson-databind (com.fasterxml.jackson.core:jackson-databind:2.15.2 - https://github.com/FasterXML/jackson)
* Jackson dataformat: CBOR (com.fasterxml.jackson.dataformat:jackson-dataformat-cbor:2.12.6 - http://github.com/FasterXML/jackson-dataformats-binary)
* Jackson dataformat: CBOR (com.fasterxml.jackson.dataformat:jackson-dataformat-cbor:2.16.1 - https://github.com/FasterXML/jackson-dataformats-binary)
@@ -235,7 +238,7 @@ List of third-party dependencies grouped by their license type.
* OpenTelemetry Java (io.opentelemetry:opentelemetry-sdk-trace:1.35.0 - https://github.com/open-telemetry/opentelemetry-java)
* OpenTelemetry Java (io.opentelemetry:opentelemetry-semconv:1.15.0-alpha - https://github.com/open-telemetry/opentelemetry-java)
* OpenTelemetry Semantic Conventions Java (io.opentelemetry.semconv:opentelemetry-semconv:1.23.1-alpha - https://github.com/open-telemetry/semantic-conventions-java)
- * org.opentest4j:opentest4j (org.opentest4j:opentest4j:1.2.0 - https://github.com/ota4j-team/opentest4j)
+ * org.opentest4j:opentest4j (org.opentest4j:opentest4j:1.3.0 - https://github.com/ota4j-team/opentest4j)
* org.seleniumhq.selenium:selenium-api (org.seleniumhq.selenium:selenium-api:4.18.1 - https://selenium.dev/)
* org.seleniumhq.selenium:selenium-http (org.seleniumhq.selenium:selenium-http:4.18.1 - https://selenium.dev/)
* org.seleniumhq.selenium:selenium-json (org.seleniumhq.selenium:selenium-json:4.18.1 - https://selenium.dev/)
@@ -247,9 +250,9 @@ List of third-party dependencies grouped by their license type.
* parso (com.epam:parso:2.0.14 - https://github.com/epam/parso)
* PDFBox JBIG2 ImageIO plugin (org.apache.pdfbox:jbig2-imageio:3.0.4 - https://www.apache.org/jbig2-imageio/)
* perfmark:perfmark-api (io.perfmark:perfmark-api:0.25.0 - https://github.com/perfmark/perfmark)
- * Playwright - Driver (com.microsoft.playwright:driver:1.41.2 - https://github.com/microsoft/playwright-java/driver)
- * Playwright - Drivers For All Platforms (com.microsoft.playwright:driver-bundle:1.41.2 - https://github.com/microsoft/playwright-java/driver-bundle)
- * Playwright - Main Library (com.microsoft.playwright:playwright:1.41.2 - https://github.com/microsoft/playwright-java/playwright)
+ * Playwright - Driver (com.microsoft.playwright:driver:1.43.0 - https://github.com/microsoft/playwright-java/driver)
+ * Playwright - Drivers For All Platforms (com.microsoft.playwright:driver-bundle:1.43.0 - https://github.com/microsoft/playwright-java/driver-bundle)
+ * Playwright - Main Library (com.microsoft.playwright:playwright:1.43.0 - https://github.com/microsoft/playwright-java/playwright)
* proto-google-common-protos (com.google.api.grpc:proto-google-common-protos:2.9.0 - https://github.com/googleapis/java-iam/proto-google-common-protos)
* rank-eval (org.opensearch.plugin:rank-eval-client:2.12.0 - https://github.com/opensearch-project/OpenSearch.git)
* rest (org.opensearch.client:opensearch-rest-client:2.12.0 - https://github.com/opensearch-project/OpenSearch.git)
diff --git a/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json b/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json
index 6098631b..a85ec7b5 100644
--- a/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json
+++ b/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json
@@ -23,7 +23,7 @@
"unmangleQueryString": true,
"checkValidURI": true,
"removeHashes": true,
- "hostIDNtoASCII": true
+ "hostIDNotASCII": true
}
},
{
diff --git a/core/src/main/java/org/apache/stormcrawler/bolt/FetcherBolt.java b/core/src/main/java/org/apache/stormcrawler/bolt/FetcherBolt.java
index 1c022640..b4da630a 100644
--- a/core/src/main/java/org/apache/stormcrawler/bolt/FetcherBolt.java
+++ b/core/src/main/java/org/apache/stormcrawler/bolt/FetcherBolt.java
@@ -535,7 +535,7 @@ public class FetcherBolt extends StatusEmitterBolt {
// autodiscovery of sitemaps
// the sitemaps will be sent down the topology
// if the robot file did not come from the cache
- // to avoid sending them unecessarily
+ // to avoid sending them unnecessarily
// check in the metadata if discovery setting has been
// overridden
diff --git a/core/src/main/java/org/apache/stormcrawler/bolt/SimpleFetcherBolt.java b/core/src/main/java/org/apache/stormcrawler/bolt/SimpleFetcherBolt.java
index 365aa658..7c5ccfcc 100644
--- a/core/src/main/java/org/apache/stormcrawler/bolt/SimpleFetcherBolt.java
+++ b/core/src/main/java/org/apache/stormcrawler/bolt/SimpleFetcherBolt.java
@@ -111,7 +111,7 @@ public class SimpleFetcherBolt extends StatusEmitterBolt {
private final AtomicInteger activeThreads = new AtomicInteger(0);
/**
- * Amount of time the bolt will sleep to enfore politeness, if the time needed to wait is above
+ * Amount of time the bolt will sleep to enforce politeness, if the time needed to wait is above
* it, the tuple is sent back to the Storm internal queue. Deactivate by default i.e. nothing is
* sent back to the bolt via the throttle stream.
*/
@@ -296,7 +296,7 @@ public class SimpleFetcherBolt extends StatusEmitterBolt {
// autodiscovery of sitemaps
// the sitemaps will be sent down the topology
// if the robot file did not come from the cache
- // to avoid sending them unecessarily
+ // to avoid sending them unnecessarily
// check in the metadata if discovery setting has been
// overridden
diff --git a/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLFilter.java b/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLFilter.java
index c3a97479..d7acf0a2 100644
--- a/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLFilter.java
+++ b/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLFilter.java
@@ -40,12 +40,12 @@ public class BasicURLFilter extends URLFilter {
return null;
}
if (maxPathRepetition > 1) {
- urlToFilter = filterPathRepet(urlToFilter);
+ urlToFilter = filterPathRepeat(urlToFilter);
}
return urlToFilter;
}
- public final String filterPathRepet(String urlToFilter) {
+ public final String filterPathRepeat(String urlToFilter) {
// check whether a path element is repeated N times
String[] paths = urlToFilter.split("/");
if (paths.length <= 4) return urlToFilter;
@@ -72,9 +72,9 @@ public class BasicURLFilter extends URLFilter {
@Override
public void configure(@NotNull Map<String, Object> stormConf, @NotNull JsonNode filterParams) {
- JsonNode repet = filterParams.get("maxPathRepetition");
- if (repet != null) {
- maxPathRepetition = repet.asInt(3);
+ JsonNode repeat = filterParams.get("maxPathRepetition");
+ if (repeat != null) {
+ maxPathRepetition = repeat.asInt(3);
}
JsonNode length = filterParams.get("maxLength");
diff --git a/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLNormalizer.java b/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLNormalizer.java
index 7550327c..32a42830 100644
--- a/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLNormalizer.java
+++ b/core/src/main/java/org/apache/stormcrawler/filtering/basic/BasicURLNormalizer.java
@@ -86,7 +86,7 @@ public class BasicURLNormalizer extends URLFilter {
boolean unmangleQueryString = true;
boolean checkValidURI = true;
boolean removeHashes = false;
- private boolean hostIDNtoASCII = false;
+ private boolean hostIDNotASCII = false;
final Set<String> queryElementsToRemove = new TreeSet<>();
@Override
@@ -125,7 +125,7 @@ public class BasicURLNormalizer extends URLFilter {
if (host != null) {
String newHost = host.toLowerCase(Locale.ROOT);
- if (hostIDNtoASCII && !isAscii(newHost)) {
+ if (hostIDNotASCII && !isAscii(newHost)) {
try {
newHost = IDN.toASCII(newHost);
} catch (IllegalArgumentException ex) {
@@ -204,9 +204,9 @@ public class BasicURLNormalizer extends URLFilter {
removeHashes = node.booleanValue();
}
- node = paramNode.get("hostIDNtoASCII");
+ node = paramNode.get("hostIDNotASCII");
if (node != null) {
- hostIDNtoASCII = node.booleanValue();
+ hostIDNotASCII = node.booleanValue();
}
}
diff --git a/core/src/main/java/org/apache/stormcrawler/persistence/Scheduler.java b/core/src/main/java/org/apache/stormcrawler/persistence/Scheduler.java
index 015ccd33..94f11a70 100644
--- a/core/src/main/java/org/apache/stormcrawler/persistence/Scheduler.java
+++ b/core/src/main/java/org/apache/stormcrawler/persistence/Scheduler.java
@@ -48,7 +48,7 @@ public abstract class Scheduler {
try {
scheduler = InitialisationUtil.initializeFromQualifiedName(className, Scheduler.class);
} catch (Exception e) {
- throw new RuntimeException("Can't instanciate " + className, e);
+ throw new RuntimeException("Can't instantiate " + className, e);
}
scheduler.init(stormConf);
diff --git a/core/src/main/java/org/apache/stormcrawler/persistence/urlbuffer/URLBuffer.java b/core/src/main/java/org/apache/stormcrawler/persistence/urlbuffer/URLBuffer.java
index 4b518e79..d89f9d55 100644
--- a/core/src/main/java/org/apache/stormcrawler/persistence/urlbuffer/URLBuffer.java
+++ b/core/src/main/java/org/apache/stormcrawler/persistence/urlbuffer/URLBuffer.java
@@ -55,7 +55,7 @@ public interface URLBuffer {
buffer = InitialisationUtil.initializeFromQualifiedName(className, URLBuffer.class);
buffer.configure(stormConf);
} catch (Exception e) {
- throw new RuntimeException("Can't instanciate " + className, e);
+ throw new RuntimeException("Can't instantiate " + className, e);
}
return buffer;
diff --git a/core/src/main/java/org/apache/stormcrawler/spout/FileSpout.java b/core/src/main/java/org/apache/stormcrawler/spout/FileSpout.java
index 773b90a2..508e2b76 100644
--- a/core/src/main/java/org/apache/stormcrawler/spout/FileSpout.java
+++ b/core/src/main/java/org/apache/stormcrawler/spout/FileSpout.java
@@ -145,7 +145,7 @@ public class FileSpout extends BaseRichSpout {
if (line.startsWith("#")) continue;
// check whether this entry should be skipped?
// totalTasks could be at 0 if a subclass forgot to
- // call this classe's open()
+ // call this classes open()
if (totalTasks == 0 || linesRead % totalTasks == taskIndex) {
LOG.debug(
"Adding to buffer for spout {} -> line ({}) {}",
diff --git a/core/src/main/java/org/apache/stormcrawler/util/InitialisationUtil.java b/core/src/main/java/org/apache/stormcrawler/util/InitialisationUtil.java
index fcc91e02..a320b07b 100644
--- a/core/src/main/java/org/apache/stormcrawler/util/InitialisationUtil.java
+++ b/core/src/main/java/org/apache/stormcrawler/util/InitialisationUtil.java
@@ -87,8 +87,8 @@ public final class InitialisationUtil {
/**
* Retrieves a class-instance for {@code qualifiedClassName} extending {@code T}. {@code T} is
- * supplied by contraining the type of {@code qualifiedClassName} to {@code superClass}. Further
- * constrains for implemented classes and interfaces are possible via {@code
+ * supplied by constraining the type of {@code qualifiedClassName} to {@code superClass}.
+ * Further constrains for implemented classes and interfaces are possible via {@code
* furtherSuperClasses}.
*
* <p>Requirements:
diff --git a/core/src/main/java/org/apache/stormcrawler/util/MetadataTransfer.java b/core/src/main/java/org/apache/stormcrawler/util/MetadataTransfer.java
index f07038e8..f9522303 100644
--- a/core/src/main/java/org/apache/stormcrawler/util/MetadataTransfer.java
+++ b/core/src/main/java/org/apache/stormcrawler/util/MetadataTransfer.java
@@ -30,7 +30,7 @@ import org.apache.stormcrawler.Metadata;
public class MetadataTransfer {
/**
- * Class to use for transfering metadata to outlinks. Must extend the class MetadataTransfer.
+ * Class to use for transferring metadata to outlinks. Must extend the class MetadataTransfer.
*/
public static final String metadataTransferClassParamName = "metadata.transfer.class";
diff --git a/core/src/main/java/org/apache/stormcrawler/util/URLUtil.java b/core/src/main/java/org/apache/stormcrawler/util/URLUtil.java
index 37ad6568..9f943a63 100644
--- a/core/src/main/java/org/apache/stormcrawler/util/URLUtil.java
+++ b/core/src/main/java/org/apache/stormcrawler/util/URLUtil.java
@@ -62,10 +62,10 @@ public class URLUtil {
* Handles cases where the url param information is encoded into the base url as opposed to the
* target.
*
- * <p>If the taget contains params (i.e. ';xxxx') information then the target params information
- * is assumed to be correct and any base params information is ignored. If the base contains
- * params information but the tareget does not, then the params information is moved to the
- * target allowing it to be correctly determined by the java.net.URL class.
+ * <p>If the target contains params (i.e. ';xxxx') information then the target params
+ * information is assumed to be correct and any base params information is ignored. If the base
+ * contains params information but the tareget does not, then the params information is moved to
+ * the target allowing it to be correctly determined by the java.net.URL class.
*
* @param base The base URL.
* @param target The target path from the base URL.
diff --git a/core/src/main/resources/crawler-default.yaml b/core/src/main/resources/crawler-default.yaml
index a8725338..831f095b 100644
--- a/core/src/main/resources/crawler-default.yaml
+++ b/core/src/main/resources/crawler-default.yaml
@@ -206,7 +206,7 @@ config:
implicit: -1
# selenium.capabilities:
- # a brower name is required
+ # a browser name is required
# browserName:"chrome"
# illustrates the use of the variable for user agent
# phantomjs.page.settings.userAgent: "$userAgent"
diff --git a/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLFilterTest.java b/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLFilterTest.java
index 916ecd95..7dec3520 100644
--- a/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLFilterTest.java
+++ b/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLFilterTest.java
@@ -29,10 +29,10 @@ import org.junit.Test;
public class BasicURLFilterTest {
- private URLFilter createFilter(int length, int repet) {
+ private URLFilter createFilter(int length, int repeat) {
BasicURLFilter filter = new BasicURLFilter();
ObjectNode filterParams = new ObjectNode(JsonNodeFactory.instance);
- filterParams.put("maxPathRepetition", repet);
+ filterParams.put("maxPathRepetition", repeat);
filterParams.put("maxLength", length);
Map<String, Object> conf = new HashMap<>();
filter.configure(conf, filterParams);
diff --git a/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLNormalizerTest.java b/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLNormalizerTest.java
index e7620fc7..bc9d7ff0 100644
--- a/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLNormalizerTest.java
+++ b/core/src/test/java/org/apache/stormcrawler/filtering/BasicURLNormalizerTest.java
@@ -313,9 +313,9 @@ public class BasicURLNormalizerTest {
}
@Test
- public void testHostIDNtoASCII() throws MalformedURLException {
+ public void testHostIDNotASCII() throws MalformedURLException {
ObjectNode filterParams = new ObjectNode(JsonNodeFactory.instance);
- filterParams.put("hostIDNtoASCII", true);
+ filterParams.put("hostIDNotASCII", true);
URLFilter urlFilter = createFilter(filterParams);
URL testSourceUrl = new URL("http://www.example.com/");
diff --git a/core/src/test/java/org/apache/stormcrawler/helper/initialisation/ClassInheritingFomAbstractAndInterface.java b/core/src/test/java/org/apache/stormcrawler/helper/initialisation/ClassInheritingFromAbstractAndInterface.java
similarity index 93%
rename from core/src/test/java/org/apache/stormcrawler/helper/initialisation/ClassInheritingFomAbstractAndInterface.java
rename to core/src/test/java/org/apache/stormcrawler/helper/initialisation/ClassInheritingFromAbstractAndInterface.java
index 6bf378de..29110361 100644
--- a/core/src/test/java/org/apache/stormcrawler/helper/initialisation/ClassInheritingFomAbstractAndInterface.java
+++ b/core/src/test/java/org/apache/stormcrawler/helper/initialisation/ClassInheritingFromAbstractAndInterface.java
@@ -19,5 +19,5 @@ package org.apache.stormcrawler.helper.initialisation;
import org.apache.stormcrawler.helper.initialisation.base.AbstractClass;
import org.apache.stormcrawler.helper.initialisation.base.ITestInterface;
-public class ClassInheritingFomAbstractAndInterface extends AbstractClass
+public class ClassInheritingFromAbstractAndInterface extends AbstractClass
implements ITestInterface {}
diff --git a/core/src/test/java/org/apache/stormcrawler/parse/filter/SubDocumentsParseFilter.java b/core/src/test/java/org/apache/stormcrawler/parse/filter/SubDocumentsParseFilter.java
index 339b94af..332ba6e6 100644
--- a/core/src/test/java/org/apache/stormcrawler/parse/filter/SubDocumentsParseFilter.java
+++ b/core/src/test/java/org/apache/stormcrawler/parse/filter/SubDocumentsParseFilter.java
@@ -61,9 +61,9 @@ public class SubDocumentsParseFilter extends ParseFilter {
// create a subdocument for each url found in the sitemap
ParseData parseData = parse.get(child.getTextContent());
- NodeList childs = node.getChildNodes();
- for (int j = 0; j < childs.getLength(); j++) {
- Node n = childs.item(j);
+ NodeList children = node.getChildNodes();
+ for (int j = 0; j < children.getLength(); j++) {
+ Node n = children.item(j);
parseData.put(n.getNodeName(), n.getTextContent());
}
}
diff --git a/core/src/test/java/org/apache/stormcrawler/util/InitialisationUtilTest.java b/core/src/test/java/org/apache/stormcrawler/util/InitialisationUtilTest.java
index da6d4ac9..49f8076e 100644
--- a/core/src/test/java/org/apache/stormcrawler/util/InitialisationUtilTest.java
+++ b/core/src/test/java/org/apache/stormcrawler/util/InitialisationUtilTest.java
@@ -33,7 +33,7 @@ public class InitialisationUtilTest {
public void can_initialize_an_inherited_class_as_abstract() {
final AbstractClass abstractClass =
InitialisationUtil.initializeFromQualifiedName(
- ClassInheritingFomAbstractAndInterface.class.getName(),
+ ClassInheritingFromAbstractAndInterface.class.getName(),
AbstractClass.class);
}
@@ -41,7 +41,7 @@ public class InitialisationUtilTest {
public void can_initialize_an_inherited_class_as_interface() {
final ITestInterface testInterface =
InitialisationUtil.initializeFromQualifiedName(
- ClassInheritingFomAbstractAndInterface.class.getName(),
+ ClassInheritingFromAbstractAndInterface.class.getName(),
ITestInterface.class);
}
@@ -56,7 +56,7 @@ public class InitialisationUtilTest {
public void can_initialize_an_inherited_class_as_abstract_and_check_for_interface() {
final AbstractClass abstractClass =
InitialisationUtil.initializeFromQualifiedName(
- ClassInheritingFomAbstractAndInterface.class.getName(),
+ ClassInheritingFromAbstractAndInterface.class.getName(),
AbstractClass.class,
ITestInterface.class);
}
diff --git a/external/aws/README.md b/external/aws/README.md
index 49119e3d..0398b2d5 100644
--- a/external/aws/README.md
+++ b/external/aws/README.md
@@ -37,7 +37,7 @@ Note that the creation of the domain can take some time. Once it is complete, no
See file [aws-conf.yaml] for an example of configuration.
-You'll need to define `cloudsearch.endpoint` and `cloudsearch.region` , unless you set `cloudsearch.batch.dump` to `true` in which case the batch of documents to index in JSON format will be dumped on the default tmp directory. The files have the prefix "CloudSearch_" e.g. `/tmp/CloudSearch_4822180575734804454.json`. These temp filse can be used as templates when defining the fields in the domain creation (see above).
+You'll need to define `cloudsearch.endpoint` and `cloudsearch.region` , unless you set `cloudsearch.batch.dump` to `true` in which case the batch of documents to index in JSON format will be dumped on the default tmp directory. The files have the prefix "CloudSearch_" e.g. `/tmp/CloudSearch_4822180575734804454.json`. These temp files can be used as templates when defining the fields in the domain creation (see above).
There are two additional configurations for CloudSearch \:
diff --git a/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml b/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml
index f37b8d5a..d9ce2e2f 100644
--- a/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml
+++ b/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml
@@ -10,7 +10,7 @@ config:
opensearch.concurrentRequests: 2
# Indexer bolt
- # adresses can be specified as a full URL
+ # addresses can be specified as a full URL
# if not we assume that the protocol is http and the port 9200
opensearch.indexer.addresses: "localhost"
opensearch.indexer.index.name: "content"
diff --git a/external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json b/external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json
index 6098631b..a85ec7b5 100644
--- a/external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json
+++ b/external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json
@@ -23,7 +23,7 @@
"unmangleQueryString": true,
"checkValidURI": true,
"removeHashes": true,
- "hostIDNtoASCII": true
+ "hostIDNotASCII": true
}
},
{
diff --git a/external/opensearch/opensearch-conf.yaml b/external/opensearch/opensearch-conf.yaml
index 032ba06f..852e2f06 100644
--- a/external/opensearch/opensearch-conf.yaml
+++ b/external/opensearch/opensearch-conf.yaml
@@ -13,7 +13,7 @@ config:
# opensearch.disable.tls.validation: false
# Indexer bolt
- # adresses can be specified as a full URL
+ # addresses can be specified as a full URL
# if not we assume that the protocol is http and the port 9200
opensearch.indexer.addresses: "localhost"
opensearch.indexer.index.name: "content"
diff --git a/external/tika/src/main/java/org/apache/stormcrawler/tika/DOMBuilder.java b/external/tika/src/main/java/org/apache/stormcrawler/tika/DOMBuilder.java
index a49805ac..f7e48d36 100644
--- a/external/tika/src/main/java/org/apache/stormcrawler/tika/DOMBuilder.java
+++ b/external/tika/src/main/java/org/apache/stormcrawler/tika/DOMBuilder.java
@@ -321,7 +321,7 @@ public class DOMBuilder implements ContentHandler, LexicalHandler {
*/
public void setIDAttribute(String id, Element elem) {
- // Do nothing. This method is meant to be overiden.
+ // Do nothing. This method is meant to be overridden.
}
/**
@@ -551,7 +551,7 @@ public class DOMBuilder implements ContentHandler, LexicalHandler {
String s = new String(ch, start, length);
- // XXX ab@apache.org: modified from the original, to accomodate TagSoup.
+ // XXX ab@apache.org: modified from the original, to accommodate TagSoup.
Node n = m_currentNode.getLastChild();
if (n instanceof CDATASection) {
((CDATASection) n).appendData(s);