This is an automated email from the ASF dual-hosted git repository. lewismc pushed a commit to branch NUTCH-3197-codespell in repository https://gitbox.apache.org/repos/asf/nutch.git
commit 239c73dd5c36e8453b46a7a6c771eaadb78b358f Author: lewismc <[email protected]> AuthorDate: Sun Aug 16 14:08:16 2026 -0700 [NUTCH-3197] Yetus: fix product codespell typos flagged by precommit Linked follow-up to Child B shell/Docker/shelldocs PR. Correct misspellings in javadoc, comments, and nutch-default.xml descriptions; extend .codespellrc skip for ISO language codes (langmappings.properties), naivebayes models, and plugin sample fixtures. --- .codespellrc | 5 +++-- conf/nutch-default.xml | 8 ++++---- src/java/org/apache/nutch/crawl/CrawlDatum.java | 2 +- src/java/org/apache/nutch/crawl/CrawlDbReader.java | 2 +- src/java/org/apache/nutch/crawl/LinkDbReader.java | 2 +- src/java/org/apache/nutch/hostdb/ResolverThread.java | 2 +- src/java/org/apache/nutch/parse/Outlink.java | 2 +- src/java/org/apache/nutch/parse/OutlinkExtractor.java | 4 ++-- src/java/org/apache/nutch/parse/ParsePluginList.java | 2 +- src/java/org/apache/nutch/parse/ParseResult.java | 2 +- src/java/org/apache/nutch/plugin/Extension.java | 4 ++-- src/java/org/apache/nutch/plugin/ExtensionPoint.java | 2 +- src/java/org/apache/nutch/plugin/Plugin.java | 2 +- src/java/org/apache/nutch/plugin/PluginDescriptor.java | 2 +- src/java/org/apache/nutch/plugin/PluginRepository.java | 2 +- src/java/org/apache/nutch/scoring/webgraph/LinkRank.java | 6 +++--- src/java/org/apache/nutch/scoring/webgraph/ScoreUpdater.java | 2 +- src/java/org/apache/nutch/tools/ResolveUrls.java | 2 +- src/java/org/apache/nutch/tools/arc/ArcSegmentCreator.java | 2 +- src/java/org/apache/nutch/util/TrieStringMatcher.java | 2 +- .../src/java/org/creativecommons/nutch/CCParseFilter.java | 2 +- src/plugin/index-geoip/ivy.xml | 2 +- src/plugin/index-replace/README.txt | 2 +- .../java/org/apache/nutch/indexwriter/kafka/KafkaIndexWriter.java | 2 +- src/plugin/indexer-opensearch-1x/howto_upgrade_opensearch.md | 2 +- src/plugin/indexer-solr/howto_upgrade_solr.md | 2 +- .../org/apache/nutch/analysis/lang/LanguageIndexingFilter.java | 2 +- .../org/apache/nutch/protocol/htmlunit/HtmlUnitWebDriver.java | 2 +- .../java/org/apache/nutch/microformats/reltag/RelTagParser.java | 2 +- .../src/java/org/apache/nutch/parse/html/DOMBuilder.java | 4 ++-- .../src/java/org/apache/nutch/parse/html/DOMContentUtils.java | 2 +- .../src/java/org/apache/nutch/parse/html/HTMLMetaProcessor.java | 4 ++-- .../src/java/org/apache/nutch/parse/tika/DOMBuilder.java | 4 ++-- .../src/java/org/apache/nutch/parse/tika/DOMContentUtils.java | 2 +- .../src/java/org/apache/nutch/parse/tika/HTMLMetaProcessor.java | 4 ++-- .../parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java | 2 +- .../nutch/parsefilter/naivebayes/NaiveBayesParseFilter.java | 4 ++-- .../org/apache/nutch/parsefilter/naivebayes/package-info.java | 2 +- src/plugin/plugin.dtd | 2 +- .../src/java/org/apache/nutch/protocol/ftp/Client.java | 4 ++-- .../src/java/org/apache/nutch/protocol/ftp/FtpResponse.java | 2 +- src/plugin/protocol-selenium/README.md | 8 ++++---- .../apache/nutch/publisher/rabbitmq/RabbitMQPublisherImpl.java | 2 +- .../org/apache/nutch/scoring/metadata/MetadataScoringFilter.java | 2 +- .../src/java/org/apache/nutch/collection/CollectionManager.java | 6 +++--- .../src/java/org/apache/nutch/collection/Subcollection.java | 2 +- .../nutch/indexer/subcollection/SubcollectionIndexingFilter.java | 2 +- .../org/apache/nutch/scoring/urlmeta/URLMetaScoringFilter.java | 2 +- .../org/apache/nutch/net/urlnormalizer/protocol/package-info.java | 2 +- .../apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java | 2 +- 50 files changed, 70 insertions(+), 69 deletions(-) diff --git a/.codespellrc b/.codespellrc index dedef4624..9c76c2d71 100644 --- a/.codespellrc +++ b/.codespellrc @@ -3,9 +3,10 @@ # Loction: intentional misspelling in protocol-http/okhttp TestResponse fixtures # used to exercise SpellCheckedMetadata error-tolerant Location header matching. # uery: intentional query-string token in urlnormalizer-protocol TestProtocolURLNormalizer. -ignore-words-list = AfterAll,BeforeAll,Loction,uery +# fo: intentional trie matcher test prefix in PrefixStringMatcher/SuffixStringMatcher demo mains. +ignore-words-list = AfterAll,BeforeAll,Loction,uery,fo # CHANGES.md is a historical changelog not maintained by this branch. # Language-identifier corpora, binary license trees, and naivebayes training # sample are also listed in .yetus/excludes.txt for full-tree Yetus runs; skip # them here so local codespell matches CI. -skip = CHANGES.md,src/plugin/language-identifier/src/test,LICENSE-binary,NOTICE-binary,licenses-binary,conf/naivebayes-train.txt.template +skip = CHANGES.md,src/plugin/language-identifier/src/test,LICENSE-binary,NOTICE-binary,licenses-binary,conf/naivebayes-train.txt.template,src/plugin/language-identifier/src/java/org/apache/nutch/analysis/lang/langmappings.properties,**/naivebayes-model,**/sample/** diff --git a/conf/nutch-default.xml b/conf/nutch-default.xml index 949716dac..178fdbd2c 100644 --- a/conf/nutch-default.xml +++ b/conf/nutch-default.xml @@ -62,7 +62,7 @@ <description>If true, no file content will be saved during fetch. And it is probably what we want to set most of time, since file:// URLs are meant to be local and we can always use them directly at parsing - and indexing stages. Otherwise file contents will be saved. + and indexing stags. Otherwise file contents will be saved. !! NOT IMPLEMENTED YET !! </description> </property> @@ -1361,7 +1361,7 @@ <value>-1</value> <description> The maximum time in seconds fetcher will cache redirects for - deduplication. If the same redirect URL is seen again withing + deduplication. If the same redirect URL is seen again within this time it is skipped. This allows to avoid pathological cases where many or most of the URLs of a host are redirected to the same URL, eg. a page to login, accept cookies, indicating an @@ -1453,7 +1453,7 @@ <property> <name>indexer.score.power</name> <value>0.5</value> - <description>Determines the power of link analyis scores. The boost + <description>Determines the power of link analysis scores. The boost of each page is set to <i>score<sup>scorePower</sup></i> where <i>score</i> is its link analysis score and <i>scorePower</i> is the value of this parameter. This is compiled into indexes, so, when @@ -1745,7 +1745,7 @@ <name>parser.html.line.separators</name> <value>article,aside,blockquote,canvas,dd,div,dl,dt,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hr,li,main,nav,noscript,ol,output,p,pre,section,table,tfoot,ul,video</value> <description>Comma separated list of HTML tags. Newline will be added to the - parsed text after these tages. + parsed text after these tags. The default list above are the block-level HTML elements. Tags must be in lower case. To disable this feature, leave the list empty.</description> diff --git a/src/java/org/apache/nutch/crawl/CrawlDatum.java b/src/java/org/apache/nutch/crawl/CrawlDatum.java index 14f134089..c8f798ffe 100644 --- a/src/java/org/apache/nutch/crawl/CrawlDatum.java +++ b/src/java/org/apache/nutch/crawl/CrawlDatum.java @@ -419,7 +419,7 @@ public class CrawlDatum implements WritableComparable<CrawlDatum>, Cloneable { * @param that an existing {@link CrawlDatum} * @return 1 if any one field (score, status, fetchTime, retries, * fetchInterval or modifiedTime) of the new {@link CrawlDatum} - * minus the correspoinding field of the existing {@link CrawlDatum} + * minus the corresponding field of the existing {@link CrawlDatum} * is greater than 0, otherwise return -1. */ @Override diff --git a/src/java/org/apache/nutch/crawl/CrawlDbReader.java b/src/java/org/apache/nutch/crawl/CrawlDbReader.java index 266c819b8..66da1e6c9 100644 --- a/src/java/org/apache/nutch/crawl/CrawlDbReader.java +++ b/src/java/org/apache/nutch/crawl/CrawlDbReader.java @@ -115,7 +115,7 @@ public class CrawlDbReader extends AbstractChecker implements Closeable { synchronized (this) { if (readers != null) { if (this.lastModified == lastModified) { - // CrawlDB not modified, re-use readers + // CrawlDB not modified, reuse readers return; } else { // CrawlDB modified, close and re-open readers diff --git a/src/java/org/apache/nutch/crawl/LinkDbReader.java b/src/java/org/apache/nutch/crawl/LinkDbReader.java index 976e1a2a7..897aa1aca 100644 --- a/src/java/org/apache/nutch/crawl/LinkDbReader.java +++ b/src/java/org/apache/nutch/crawl/LinkDbReader.java @@ -87,7 +87,7 @@ public class LinkDbReader extends AbstractChecker implements Closeable { synchronized (this) { if (readers != null) { if (this.lastModified == lastModified) { - // CrawlDB not modified, re-use readers + // CrawlDB not modified, reuse readers return; } else { // CrawlDB modified, close and re-open readers diff --git a/src/java/org/apache/nutch/hostdb/ResolverThread.java b/src/java/org/apache/nutch/hostdb/ResolverThread.java index 05e4a940c..e730992c5 100644 --- a/src/java/org/apache/nutch/hostdb/ResolverThread.java +++ b/src/java/org/apache/nutch/hostdb/ResolverThread.java @@ -107,7 +107,7 @@ public class ResolverThread implements Runnable { */ @Override public void run() { - // Resolve the host and act appropriatly + // Resolve the host and act appropriately try { // Throws an exception if host is not found @SuppressWarnings("unused") diff --git a/src/java/org/apache/nutch/parse/Outlink.java b/src/java/org/apache/nutch/parse/Outlink.java index 0db7cdce2..2e3a03505 100644 --- a/src/java/org/apache/nutch/parse/Outlink.java +++ b/src/java/org/apache/nutch/parse/Outlink.java @@ -59,7 +59,7 @@ public class Outlink implements Writable { /** * Skips over one Outlink in the input. * @param in the {@link DataInput} tuple stream holding the - * toUrl and archor pair. + * toUrl and anchor pair. * @throws IOException if there is an error processing the {@link DataInput} */ public static void skip(DataInput in) throws IOException { diff --git a/src/java/org/apache/nutch/parse/OutlinkExtractor.java b/src/java/org/apache/nutch/parse/OutlinkExtractor.java index 1f90948af..83931965b 100644 --- a/src/java/org/apache/nutch/parse/OutlinkExtractor.java +++ b/src/java/org/apache/nutch/parse/OutlinkExtractor.java @@ -61,7 +61,7 @@ public class OutlinkExtractor { * cases (postscript is a known example). * * @param plainText - * the plain text from wich URLs should be extracted. + * the plain text from which URLs should be extracted. * @param conf a populated {@link Configuration} * @return Array of <code>Outlink</code>s within found in plainText */ @@ -75,7 +75,7 @@ public class OutlinkExtractor { * extracted <code>Outlink</code>s * * @param plainText - * the plain text from wich URLs should be extracted. + * the plain text from which URLs should be extracted. * @param anchor * the anchor of the url * @param conf a populated {@link Configuration} diff --git a/src/java/org/apache/nutch/parse/ParsePluginList.java b/src/java/org/apache/nutch/parse/ParsePluginList.java index 510c92bee..5bb5516cb 100644 --- a/src/java/org/apache/nutch/parse/ParsePluginList.java +++ b/src/java/org/apache/nutch/parse/ParsePluginList.java @@ -24,7 +24,7 @@ import java.util.Map; /** * This class represents a natural ordering for which parsing plugin should get * called for a particular mimeType. It provides methods to store the - * parse-plugins.xml data, and methods to retreive the name of the appropriate + * parse-plugins.xml data, and methods to retrieve the name of the appropriate * parsing plugin for a contentType. * * @author mattmann diff --git a/src/java/org/apache/nutch/parse/ParseResult.java b/src/java/org/apache/nutch/parse/ParseResult.java index 4a4dbf362..23a64dfc6 100644 --- a/src/java/org/apache/nutch/parse/ParseResult.java +++ b/src/java/org/apache/nutch/parse/ParseResult.java @@ -183,7 +183,7 @@ public class ParseResult implements Iterable<Map.Entry<Text, Parse>> { /** * A convenience method which returns true if at least one of the parses is * successful. Parse success is determined by {@link ParseStatus#isSuccess()}. - * @return true if atleast one result is a success, false otherwise + * @return true if at least one result is a success, false otherwise */ public boolean isAnySuccess() { for (Iterator<Entry<Text, Parse>> i = iterator(); i.hasNext();) { diff --git a/src/java/org/apache/nutch/plugin/Extension.java b/src/java/org/apache/nutch/plugin/Extension.java index cdc8533c0..a055b73f3 100644 --- a/src/java/org/apache/nutch/plugin/Extension.java +++ b/src/java/org/apache/nutch/plugin/Extension.java @@ -67,7 +67,7 @@ public class Extension { /** * Returns a attribute value, that is setuped in the manifest file and is - * definied by the extension point xml schema. + * defined by the extension point xml schema. * * @param pKey * a key @@ -109,7 +109,7 @@ public class Extension { } /** - * Sets the Class that implement the concret extension and is only used until + * Sets the Class that implement the concrete extension and is only used until * model creation at system start up. * * @param extensionClazz diff --git a/src/java/org/apache/nutch/plugin/ExtensionPoint.java b/src/java/org/apache/nutch/plugin/ExtensionPoint.java index 92ddfd815..b0243d927 100644 --- a/src/java/org/apache/nutch/plugin/ExtensionPoint.java +++ b/src/java/org/apache/nutch/plugin/ExtensionPoint.java @@ -103,7 +103,7 @@ public class ExtensionPoint { } /** - * Install a coresponding extension to this extension point. + * Install a corresponding extension to this extension point. * * @param extension the new {@link org.apache.nutch.plugin.Extension} * to install diff --git a/src/java/org/apache/nutch/plugin/Plugin.java b/src/java/org/apache/nutch/plugin/Plugin.java index 3a0fb2e91..2b641322f 100644 --- a/src/java/org/apache/nutch/plugin/Plugin.java +++ b/src/java/org/apache/nutch/plugin/Plugin.java @@ -58,7 +58,7 @@ public class Plugin { * used. * * @throws PluginRuntimeException - * If the startup was without successs. + * If the startup was without success. */ public void startUp() throws PluginRuntimeException { } diff --git a/src/java/org/apache/nutch/plugin/PluginDescriptor.java b/src/java/org/apache/nutch/plugin/PluginDescriptor.java index 7a93c863e..3449e1cc0 100644 --- a/src/java/org/apache/nutch/plugin/PluginDescriptor.java +++ b/src/java/org/apache/nutch/plugin/PluginDescriptor.java @@ -285,7 +285,7 @@ public class PluginDescriptor { /** * Returns a cached classloader for a plugin. Until classloader creation all * needed libraries are collected. A classloader use as first the plugins own - * libraries and add then all exported libraries of dependend plugins. + * libraries and add then all exported libraries of dependent plugins. * * @return PluginClassLoader the classloader for the plugin */ diff --git a/src/java/org/apache/nutch/plugin/PluginRepository.java b/src/java/org/apache/nutch/plugin/PluginRepository.java index bec062521..5d79aef0c 100644 --- a/src/java/org/apache/nutch/plugin/PluginRepository.java +++ b/src/java/org/apache/nutch/plugin/PluginRepository.java @@ -231,7 +231,7 @@ public class PluginRepository implements URLStreamHandlerFactory { } /** - * Returns all registed plugin descriptors. + * Returns all registered plugin descriptors. * * @return PluginDescriptor[] */ diff --git a/src/java/org/apache/nutch/scoring/webgraph/LinkRank.java b/src/java/org/apache/nutch/scoring/webgraph/LinkRank.java index de15e3d66..2eeed4456 100644 --- a/src/java/org/apache/nutch/scoring/webgraph/LinkRank.java +++ b/src/java/org/apache/nutch/scoring/webgraph/LinkRank.java @@ -632,7 +632,7 @@ public class LinkRank extends Configured implements Tool { } /** - * Runs the complete link analysis job. The complete job determins rank one + * Runs the complete link analysis job. The complete job determines rank one * score. Then runs through a given number of invert and analyze iterations, * by default 10. And finally replaces the NodeDb in the WebGraph with the * link rank output. @@ -654,7 +654,7 @@ public class LinkRank extends Configured implements Tool { LOG.info("LinkRank Analysis: starting"); // store the link rank under the webgraphdb temporarily, final scores get - // upddated into the nodedb + // updated into the nodedb Path linkRank = new Path(webGraphDb, "linkrank"); Configuration conf = getConf(); FileSystem fs = linkRank.getFileSystem(conf); @@ -670,7 +670,7 @@ public class LinkRank extends Configured implements Tool { Path nodeDb = new Path(linkRank, WebGraph.NODE_DIR); // get the number of total nodes in the webgraph, used for rank one, then - // initialze all urls with a default score + // initialize all urls with a default score int numLinks = runCounter(fs, webGraphDb); runInitializer(wgNodeDb, nodeDb); float rankOneScore = (1f / numLinks); diff --git a/src/java/org/apache/nutch/scoring/webgraph/ScoreUpdater.java b/src/java/org/apache/nutch/scoring/webgraph/ScoreUpdater.java index a595d4bf3..7460dbd0d 100644 --- a/src/java/org/apache/nutch/scoring/webgraph/ScoreUpdater.java +++ b/src/java/org/apache/nutch/scoring/webgraph/ScoreUpdater.java @@ -139,7 +139,7 @@ public class ScoreUpdater extends Configured implements Tool{ /** - * Updates the inlink score in the web graph node databsae into the crawl + * Updates the inlink score in the web graph node database into the crawl * database. * * @param crawlDb diff --git a/src/java/org/apache/nutch/tools/ResolveUrls.java b/src/java/org/apache/nutch/tools/ResolveUrls.java index ddfa6cf21..1b3f66572 100644 --- a/src/java/org/apache/nutch/tools/ResolveUrls.java +++ b/src/java/org/apache/nutch/tools/ResolveUrls.java @@ -130,7 +130,7 @@ public class ResolveUrls { // shutdown the thread pool and log totals pool.shutdown(); - LOG.info("Total: {}, Resovled: {}, Errored: {}, Average Time: {}", + LOG.info("Total: {}, Resolved: {}, Errored: {}, Average Time: {}", numTotal.get(), numResolved.get(), numErrored.get(), totalTime.get() / numTotal.get()); } diff --git a/src/java/org/apache/nutch/tools/arc/ArcSegmentCreator.java b/src/java/org/apache/nutch/tools/arc/ArcSegmentCreator.java index 722339c33..a9932ef4d 100644 --- a/src/java/org/apache/nutch/tools/arc/ArcSegmentCreator.java +++ b/src/java/org/apache/nutch/tools/arc/ArcSegmentCreator.java @@ -116,7 +116,7 @@ public class ArcSegmentCreator extends Configured implements Tool { * @param url * The url we are parsing. * @param t - * The error that occured. + * The error that occurred. */ private static void logError(Text url, Throwable t) { LOG.info("Conversion of {} failed with: {}", url, StringUtils.stringifyException(t)); diff --git a/src/java/org/apache/nutch/util/TrieStringMatcher.java b/src/java/org/apache/nutch/util/TrieStringMatcher.java index 0c8602575..0f615838d 100644 --- a/src/java/org/apache/nutch/util/TrieStringMatcher.java +++ b/src/java/org/apache/nutch/util/TrieStringMatcher.java @@ -202,7 +202,7 @@ public abstract class TrieStringMatcher { * Returns true if the given <code>String</code> is matched by a pattern in * the trie * @param input A String to be matched by a pattern - * @return true if there is a match, flase otherwise + * @return true if there is a match, false otherwise */ public abstract boolean matches(String input); diff --git a/src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCParseFilter.java b/src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCParseFilter.java index ee4e22ec2..a092d5a2c 100644 --- a/src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCParseFilter.java +++ b/src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCParseFilter.java @@ -134,7 +134,7 @@ public class CCParseFilter implements HtmlParseFilter { } /** - * Extract license url from element, if any. Thse are the href attribute of + * Extract license url from element, if any. These are the href attribute of * anchor elements with rel="license". These must also point to * http://creativecommons.org/licenses/. */ diff --git a/src/plugin/index-geoip/ivy.xml b/src/plugin/index-geoip/ivy.xml index ce2defbba..db8f508dd 100644 --- a/src/plugin/index-geoip/ivy.xml +++ b/src/plugin/index-geoip/ivy.xml @@ -38,7 +38,7 @@ <dependencies> <dependency org="com.maxmind.geoip2" name="geoip2" rev="5.0.2"> - <!-- Exlude libs provided in Nutch core --> + <!-- Exclude libs provided in Nutch core --> <exclude org="com.fasterxml.jackson.core" name="jackson-annotations" /> <exclude org="com.fasterxml.jackson.core" name="jackson-databind" /> <exclude org="com.fasterxml.jackson.core" name="jackson-core" /> diff --git a/src/plugin/index-replace/README.txt b/src/plugin/index-replace/README.txt index e136d4712..563c7fbca 100644 --- a/src/plugin/index-replace/README.txt +++ b/src/plugin/index-replace/README.txt @@ -86,7 +86,7 @@ Testing your match patterns bin/nutch parse crawl/segments/[segment] bin/nutch invertlinks crawl/linkdb -dir crawl/segments ...index your document, for example with SOLR... - bin/nutch solrindex http://localhost:8983/solr crawl/crawldb/ -linkdb crawl/linkdb/ crawl/segement[segment] -filter -normalize + bin/nutch solrindex http://localhost:8983/solr crawl/crawldb/ -linkdb crawl/linkdb/ crawl/segment[segment] -filter -normalize Inspect hadoop.log for info about pattern parsing and compilation.. grep replace logs/hadoop.log diff --git a/src/plugin/indexer-kafka/src/java/org/apache/nutch/indexwriter/kafka/KafkaIndexWriter.java b/src/plugin/indexer-kafka/src/java/org/apache/nutch/indexwriter/kafka/KafkaIndexWriter.java index 2fcf6de87..d071de1a0 100644 --- a/src/plugin/indexer-kafka/src/java/org/apache/nutch/indexwriter/kafka/KafkaIndexWriter.java +++ b/src/plugin/indexer-kafka/src/java/org/apache/nutch/indexwriter/kafka/KafkaIndexWriter.java @@ -156,7 +156,7 @@ public class KafkaIndexWriter implements IndexWriter { } inputDocs.clear(); } catch (NullPointerException e) { - LOG.info("All records have been sent to Kakfa on topic {}", topic); + LOG.info("All records have been sent to Kafka on topic {}", topic); } } diff --git a/src/plugin/indexer-opensearch-1x/howto_upgrade_opensearch.md b/src/plugin/indexer-opensearch-1x/howto_upgrade_opensearch.md index c9b723ffc..4bf4c5c60 100644 --- a/src/plugin/indexer-opensearch-1x/howto_upgrade_opensearch.md +++ b/src/plugin/indexer-opensearch-1x/howto_upgrade_opensearch.md @@ -37,7 +37,7 @@ (eventually with different versions) - duplicated libs can be added to the exclusions of transitive dependencies in build/plugins/indexer-opensearch-1x/ivy.xml - - but it should be made sure that the library versions in ivy/ivy.xml correspend to + - but it should be made sure that the library versions in ivy/ivy.xml correspond to those required by Tika 5. Remove the locally "installed" dependencies in src/plugin/indexer-opensearch-1x/lib/: diff --git a/src/plugin/indexer-solr/howto_upgrade_solr.md b/src/plugin/indexer-solr/howto_upgrade_solr.md index 905fb84a9..c7bdba5f3 100644 --- a/src/plugin/indexer-solr/howto_upgrade_solr.md +++ b/src/plugin/indexer-solr/howto_upgrade_solr.md @@ -37,7 +37,7 @@ (eventually with different versions) - duplicated libs can be added to the exclusions of transitive dependencies in build/plugins/indexer-solr/ivy.xml - - but it should be made sure that the library versions in ivy/ivy.xml correspend to + - but it should be made sure that the library versions in ivy/ivy.xml correspond to those required by Tika 5. Remove the locally "installed" dependencies in src/plugin/indexer-solr/lib/: diff --git a/src/plugin/language-identifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java b/src/plugin/language-identifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java index ed9362e20..2335a1f4e 100644 --- a/src/plugin/language-identifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java +++ b/src/plugin/language-identifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java @@ -41,7 +41,7 @@ import org.apache.hadoop.conf.Configuration; * information</li> * <li>Then, checking if a <code>Content-Language</code> HTTP header can be * found</li> - * <li>Finaly by analyzing the document content</li> + * <li>Finally by analyzing the document content</li> * </ul> * * @author Sami Siren diff --git a/src/plugin/lib-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HtmlUnitWebDriver.java b/src/plugin/lib-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HtmlUnitWebDriver.java index b99bb9603..1b16c3b93 100644 --- a/src/plugin/lib-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HtmlUnitWebDriver.java +++ b/src/plugin/lib-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HtmlUnitWebDriver.java @@ -171,7 +171,7 @@ public class HtmlUnitWebDriver extends HtmlUnitDriver { IOUtils.copyBytes(is, os, conf); LOG.debug("Screenshot for {} successfully saved to: {} {}", url, screenshotPath, srcFile.getName()); } else { - LOG.warn("Screenshot for {} not saved to HDFS (subsequently disgarded) as value for " + LOG.warn("Screenshot for {} not saved to HDFS (subsequently discarded) as value for " + "'screenshot.location' is absent from nutch-site.xml.", url); } } catch (Exception e) { diff --git a/src/plugin/microformats-reltag/src/java/org/apache/nutch/microformats/reltag/RelTagParser.java b/src/plugin/microformats-reltag/src/java/org/apache/nutch/microformats/reltag/RelTagParser.java index 9a55228a0..5b557c5cd 100644 --- a/src/plugin/microformats-reltag/src/java/org/apache/nutch/microformats/reltag/RelTagParser.java +++ b/src/plugin/microformats-reltag/src/java/org/apache/nutch/microformats/reltag/RelTagParser.java @@ -99,7 +99,7 @@ public class RelTagParser implements HtmlParseFilter { Node relNode = attrs.getNamedItem("rel"); // Checks that it contains a rel attribute too if (relNode != null) { - // Finaly checks that rel=tag + // Finally checks that rel=tag if ("tag".equalsIgnoreCase(relNode.getNodeValue())) { String tag = parseTag(hrefNode.getNodeValue()); if (!StringUtil.isEmpty(tag)) { diff --git a/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java b/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java index 6b98edf35..b80356130 100644 --- a/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java +++ b/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java @@ -361,7 +361,7 @@ 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. } /** @@ -648,7 +648,7 @@ public class DOMBuilder implements ContentHandler, LexicalHandler { String s = new String(ch, start, length); - // XXX [email protected]: modified from the original, to accomodate TagSoup. + // XXX [email protected]: modified from the original, to accommodate TagSoup. Node n = m_currentNode.getLastChild(); if (n instanceof CDATASection) ((CDATASection) n).appendData(s); diff --git a/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMContentUtils.java b/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMContentUtils.java index 0d9fa928a..2515a8f6c 100644 --- a/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMContentUtils.java +++ b/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMContentUtils.java @@ -139,7 +139,7 @@ public class DOMContentUtils { } /** - * This is a convinience method, equivalent to + * This is a convenience method, equivalent to * {@link #getText(StringBuffer,Node,boolean) getText(sb, node, false)}. * @param sb a {@link StringBuffer} used to store content text * found beneath the DOM node... if any exists diff --git a/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HTMLMetaProcessor.java b/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HTMLMetaProcessor.java index b3b7b921f..bcd094797 100644 --- a/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HTMLMetaProcessor.java +++ b/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HTMLMetaProcessor.java @@ -44,7 +44,7 @@ public class HTMLMetaProcessor { * @param metaTags a {@link HTMLMetaTags} to populate with tags discovered in the * given Node * @param node a DOM {@link Node} to process and extract metadata from - * @param currURL the cononical URL associated with the metatags and Node + * @param currURL the canonical URL associated with the metatags and Node */ public static final void getMetaTags(HTMLMetaTags metaTags, Node node, URL currURL) { @@ -68,7 +68,7 @@ public class HTMLMetaProcessor { Node nameNode = null; Node equivNode = null; Node contentNode = null; - // Retrieves name, http-equiv and content attribues + // Retrieves name, http-equiv and content attributes for (int i = 0; i < attrs.getLength(); i++) { Node attr = attrs.item(i); String attrName = attr.getNodeName().toLowerCase(Locale.ROOT); diff --git a/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMBuilder.java b/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMBuilder.java index ef22df6b9..7b4bced69 100644 --- a/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMBuilder.java +++ b/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMBuilder.java @@ -376,7 +376,7 @@ 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. } /** @@ -663,7 +663,7 @@ class DOMBuilder implements ContentHandler, LexicalHandler { String s = new String(ch, start, length); - // XXX [email protected]: modified from the original, to accomodate TagSoup. + // XXX [email protected]: modified from the original, to accommodate TagSoup. Node n = m_currentNode.getLastChild(); if (n instanceof CDATASection) ((CDATASection) n).appendData(s); diff --git a/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMContentUtils.java b/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMContentUtils.java index fbbc0f4eb..5ec232ac9 100644 --- a/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMContentUtils.java +++ b/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMContentUtils.java @@ -139,7 +139,7 @@ public class DOMContentUtils { } /** - * This is a convinience method, equivalent to + * This is a convenience method, equivalent to * {@link #getText(StringBuffer,Node,boolean) getText(sb, node, false)}. * @param sb a {@link StringBuffer} used to store content text * found beneath the DOM node... if any exists diff --git a/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/HTMLMetaProcessor.java b/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/HTMLMetaProcessor.java index c9550d828..1ca61e0a1 100644 --- a/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/HTMLMetaProcessor.java +++ b/src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/HTMLMetaProcessor.java @@ -45,7 +45,7 @@ public class HTMLMetaProcessor { * @param metaTags a {@link HTMLMetaTags} to populate with tags discovered in the * given Node * @param node a DOM {@link Node} to process and extract metadata from - * @param currURL the cononical URL associated with the metatags and Node + * @param currURL the canonical URL associated with the metatags and Node */ public static final void getMetaTags(HTMLMetaTags metaTags, Node node, URL currURL) { @@ -69,7 +69,7 @@ public class HTMLMetaProcessor { Node nameNode = null; Node equivNode = null; Node contentNode = null; - // Retrieves name, http-equiv and content attribues + // Retrieves name, http-equiv and content attributes for (int i = 0; i < attrs.getLength(); i++) { Node attr = attrs.item(i); String attrName = attr.getNodeName().toLowerCase(Locale.ROOT); diff --git a/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java b/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java index 7dc08fd7b..c048a4019 100644 --- a/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java +++ b/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java @@ -101,7 +101,7 @@ public class ZipParser implements Parser { final ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, resultTitle, outlinks, content.getMetadata()); - LOG.trace("Zip file parsed sucessfully."); + LOG.trace("Zip file parsed successfully."); return ParseResult.createParseResult(content.getUrl(), new ParseImpl( resultText, parseData)); diff --git a/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/NaiveBayesParseFilter.java b/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/NaiveBayesParseFilter.java index 2d222a7dc..49552ff03 100644 --- a/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/NaiveBayesParseFilter.java +++ b/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/NaiveBayesParseFilter.java @@ -63,7 +63,7 @@ public class NaiveBayesParseFilter implements HtmlParseFilter { try { return classify(text); } catch (IOException e) { - LOG.error("Error occured while classifying:: {} ::", text, e); + LOG.error("Error occurred while classifying:: {} ::", text, e); } return false; @@ -139,7 +139,7 @@ public class NaiveBayesParseFilter implements HtmlParseFilter { train(); } catch (Exception e) { - LOG.error("Error occured while training::", e); + LOG.error("Error occurred while training::", e); } diff --git a/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/package-info.java b/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/package-info.java index 354396995..c8305388d 100644 --- a/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/package-info.java +++ b/src/plugin/parsefilter-naivebayes/src/java/org/apache/nutch/parsefilter/naivebayes/package-info.java @@ -19,7 +19,7 @@ * Html Parse filter that classifies the outlinks from the parseresult as * relevant or irrelevant based on the parseText's relevancy (using a training * file where you can give positive and negative example texts see the - * description of parsefilter.naivebayes.trainfile) and if found irrelevent + * description of parsefilter.naivebayes.trainfile) and if found irrelevant * it gives the link a second chance if it contains any of the words from the * list given in parsefilter.naivebayes.wordlist. CAUTION: Set the * parser.timeout to -1 or a bigger value than 30, when using this classifier. diff --git a/src/plugin/plugin.dtd b/src/plugin/plugin.dtd index 9b67da74b..41b3fbb06 100644 --- a/src/plugin/plugin.dtd +++ b/src/plugin/plugin.dtd @@ -22,7 +22,7 @@ ! Author : Chris Mattmann, Jerome Charron ! Description: Nutch plug-in manifest DTD ! - ! PUBLIC ID : -//Apache Software Fundation//DTD Nutch Plugin Manifest 1.0//EN + ! PUBLIC ID : -//Apache Software Foundation//DTD Nutch Plugin Manifest 1.0//EN ! SYSTEM ID : http://lucene.apache.org/nutch/plugin.dtd --> diff --git a/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/Client.java b/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/Client.java index f83b805de..d2d5480e6 100644 --- a/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/Client.java +++ b/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/Client.java @@ -228,7 +228,7 @@ public class Client extends FTP { __initDefaults(); super.disconnect(); // no worry for data connection, since we always close it - // in every ftp command that invloves data connection + // in every ftp command that involves data connection } /*** @@ -517,7 +517,7 @@ public class Client extends FTP { * <p> * * @param fileType - * The <code> _FILE_TYPE </code> constant indcating the type of file. + * The <code> _FILE_TYPE </code> constant indicating the type of file. * @return True if successfully completed, false if not. * @exception FTPConnectionClosedException * If the FTP server prematurely closes the connection as a diff --git a/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/FtpResponse.java b/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/FtpResponse.java index 083963e67..70e564c56 100644 --- a/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/FtpResponse.java +++ b/src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/FtpResponse.java @@ -350,7 +350,7 @@ public class FtpResponse { // in case this FtpExceptionControlClosedByForcedDataClose is // thrown by retrieveList() (not retrieveFile()) above, if (os == null) { // indicating throwing by retrieveList() - // throw new FtpException("fail to get attibutes: "+path); + // throw new FtpException("fail to get attributes: "+path); Ftp.LOG.warn( "Please try larger maxContentLength for ftp.client.retrieveList(). ", e); diff --git a/src/plugin/protocol-selenium/README.md b/src/plugin/protocol-selenium/README.md index 265ea7316..0620fd43f 100644 --- a/src/plugin/protocol-selenium/README.md +++ b/src/plugin/protocol-selenium/README.md @@ -42,7 +42,7 @@ sudo apt-get install firefox * Install Xvfb and its associates -This step is not necessary for the PhantomJs broswer and may not be needed for all browsers. +This step is not necessary for the PhantomJs browser and may not be needed for all browsers. ``` sudo apt-get install xorg synaptic xvfb gtk2-engines-pixbuf xfonts-cyrillic xfonts-100dpi \ @@ -58,7 +58,7 @@ sudo export DISPLAY=:11 ``` ### B) Setting up a Selenium Grid -Using the Selenium Grid will allow you to parallelize the job by facilitating access of several instances of browsers whether on one machine or on several machines. Note that grid facilitates heterogeneity with regards to browser types used. However, these steps have been tested using a homogenous Selenium Grid with Firefox and PhantomJS browsers. +Using the Selenium Grid will allow you to parallelize the job by facilitating access of several instances of browsers whether on one machine or on several machines. Note that grid facilitates heterogeneity with regards to browser types used. However, these steps have been tested using a homogeneous Selenium Grid with Firefox and PhantomJS browsers. * Download the [Selenium Standalone Server](https://selenium.dev/downloads/) and follow the installation instructions. @@ -143,7 +143,7 @@ Using the Selenium Grid will allow you to parallelize the job by facilitating ac <value></value> <description> The location on disk where a URL screenshot should be saved - to if the 'selenium.take.screenshot' proerty is set to true. + to if the 'selenium.take.screenshot' property is set to true. By default this is null, in this case screenshots held in memory are simply discarded. </description> @@ -215,7 +215,7 @@ ant runtime * Be sure your browser version and selenium version are compatible (See list in 'Tested configurations' section below) * Be sure to start the Xvfb window then start selenium (not a necessary step for PhantomJS) * Disconnecting and reconnect nodes after a hub config change has proven useful in our tests. -* Be sure that each browser session deallocates its webdriver resource independently of any other tests running on other broswers (check out driver.quit() and driver.close()). +* Be sure that each browser session deallocates its webdriver resource independently of any other tests running on other browsers (check out driver.quit() and driver.close()). ### Tested configurations diff --git a/src/plugin/publish-rabbitmq/src/java/org/apache/nutch/publisher/rabbitmq/RabbitMQPublisherImpl.java b/src/plugin/publish-rabbitmq/src/java/org/apache/nutch/publisher/rabbitmq/RabbitMQPublisherImpl.java index c2ca626c8..4df6482fe 100644 --- a/src/plugin/publish-rabbitmq/src/java/org/apache/nutch/publisher/rabbitmq/RabbitMQPublisherImpl.java +++ b/src/plugin/publish-rabbitmq/src/java/org/apache/nutch/publisher/rabbitmq/RabbitMQPublisherImpl.java @@ -85,7 +85,7 @@ public class RabbitMQPublisherImpl implements NutchPublisher { message.setHeaders(headersStatic); client.publish(exchange, routingKey, message); } catch (Exception e) { - LOG.error("Error occured while publishing - {}", + LOG.error("Error occurred while publishing - {}", StringUtils.stringifyException(e)); } } diff --git a/src/plugin/scoring-metadata/src/java/org/apache/nutch/scoring/metadata/MetadataScoringFilter.java b/src/plugin/scoring-metadata/src/java/org/apache/nutch/scoring/metadata/MetadataScoringFilter.java index 26cbaa4c3..b984492c3 100644 --- a/src/plugin/scoring-metadata/src/java/org/apache/nutch/scoring/metadata/MetadataScoringFilter.java +++ b/src/plugin/scoring-metadata/src/java/org/apache/nutch/scoring/metadata/MetadataScoringFilter.java @@ -80,7 +80,7 @@ public class MetadataScoringFilter extends AbstractScoringFilter { /** * Takes the metadata, specified in your "scoring.db.md" property, from the - * datum object and injects it into the content. This is transfered to the + * datum object and injects it into the content. This is transferred to the * parseData object. * * @see ScoringFilter#passScoreBeforeParsing diff --git a/src/plugin/subcollection/src/java/org/apache/nutch/collection/CollectionManager.java b/src/plugin/subcollection/src/java/org/apache/nutch/collection/CollectionManager.java index 4be4eca61..3dc9f8c27 100644 --- a/src/plugin/subcollection/src/java/org/apache/nutch/collection/CollectionManager.java +++ b/src/plugin/subcollection/src/java/org/apache/nutch/collection/CollectionManager.java @@ -78,7 +78,7 @@ public class CollectionManager extends Configured { getConf().get("subcollections.config", DEFAULT_FILE_NAME)); parse(input); } catch (Exception e) { - LOG.warn("Error occured:", e); + LOG.warn("Error occurred:", e); } } @@ -121,7 +121,7 @@ public class CollectionManager extends Configured { /** * Get the named subcollection * - * @param id the id of a subcollection ot retrieve + * @param id the id of a subcollection to retrieve * @return Named SubCollection (or null if not existing) */ public Subcollection getSubColection(final String id) { @@ -150,7 +150,7 @@ public class CollectionManager extends Configured { * Id of SubCollection to create * @param name * Name of SubCollection to create - * @return Created SubCollection or null if allready existed + * @return Created SubCollection or null if already existed */ public Subcollection createSubCollection(final String id, final String name) { Subcollection subCol = null; diff --git a/src/plugin/subcollection/src/java/org/apache/nutch/collection/Subcollection.java b/src/plugin/subcollection/src/java/org/apache/nutch/collection/Subcollection.java index b82ffd627..869fb1032 100644 --- a/src/plugin/subcollection/src/java/org/apache/nutch/collection/Subcollection.java +++ b/src/plugin/subcollection/src/java/org/apache/nutch/collection/Subcollection.java @@ -235,7 +235,7 @@ public class Subcollection extends Configured implements URLFilter { * with a newline * * @param list An initialized {@link List} to insert String patterns. - * @param text A chunkl fo text (hopefully) containing patterns. + * @param text A chunk of text (hopefully) containing patterns. */ protected void parseList(List<String> list, String text) { list.clear(); diff --git a/src/plugin/subcollection/src/java/org/apache/nutch/indexer/subcollection/SubcollectionIndexingFilter.java b/src/plugin/subcollection/src/java/org/apache/nutch/indexer/subcollection/SubcollectionIndexingFilter.java index 8c11d0225..0dc4a1bfa 100644 --- a/src/plugin/subcollection/src/java/org/apache/nutch/indexer/subcollection/SubcollectionIndexingFilter.java +++ b/src/plugin/subcollection/src/java/org/apache/nutch/indexer/subcollection/SubcollectionIndexingFilter.java @@ -95,7 +95,7 @@ public class SubcollectionIndexingFilter extends Configured implements @Override public NutchDocument filter(NutchDocument doc, Parse parse, Text url, CrawlDatum datum, Inlinks inlinks) throws IndexingException { - // Check for subcollection overrride in HTML metadata + // Check for subcollection override in HTML metadata String subcollection = parse.getData().getMeta(metadataSource); if (subcollection != null) { subcollection = subcollection.trim(); diff --git a/src/plugin/urlmeta/src/java/org/apache/nutch/scoring/urlmeta/URLMetaScoringFilter.java b/src/plugin/urlmeta/src/java/org/apache/nutch/scoring/urlmeta/URLMetaScoringFilter.java index cb7e1b024..0b70a0d5f 100644 --- a/src/plugin/urlmeta/src/java/org/apache/nutch/scoring/urlmeta/URLMetaScoringFilter.java +++ b/src/plugin/urlmeta/src/java/org/apache/nutch/scoring/urlmeta/URLMetaScoringFilter.java @@ -75,7 +75,7 @@ public class URLMetaScoringFilter extends AbstractScoringFilter { /** * Takes the metadata, specified in your "urlmeta.tags" property, from the - * datum object and injects it into the content. This is transfered to the + * datum object and injects it into the content. This is transferred to the * parseData object. * * @see ScoringFilter#passScoreBeforeParsing diff --git a/src/plugin/urlnormalizer-protocol/src/java/org/apache/nutch/net/urlnormalizer/protocol/package-info.java b/src/plugin/urlnormalizer-protocol/src/java/org/apache/nutch/net/urlnormalizer/protocol/package-info.java index 04f125594..57120f90a 100644 --- a/src/plugin/urlnormalizer-protocol/src/java/org/apache/nutch/net/urlnormalizer/protocol/package-info.java +++ b/src/plugin/urlnormalizer-protocol/src/java/org/apache/nutch/net/urlnormalizer/protocol/package-info.java @@ -27,7 +27,7 @@ * The configuration of rules follows the schema: * * <pre> - * <host> \t <protcol> + * <host> \t <protocol> * </pre> * * for example diff --git a/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java b/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java index 2714e3e19..ed7cf2a8e 100644 --- a/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java +++ b/src/plugin/urlnormalizer-regex/src/java/org/apache/nutch/net/urlnormalizer/regex/RegexURLNormalizer.java @@ -67,7 +67,7 @@ public class RegexURLNormalizer extends Configured implements URLNormalizer { .getLogger(MethodHandles.lookup().lookupClass()); /** - * Class which holds a compiled pattern and its corresponding substition + * Class which holds a compiled pattern and its corresponding substitution * string. */ private static class Rule {
