From aa705bef2eb8fbbb9aeb56995e713a7b6ba0ed00 Mon Sep 17 00:00:00 2001 From: Edward Betts Date: Sun, 4 Nov 2018 12:14:07 +0200 Subject: [PATCH] Correct spelling mistakes. --- commons/src/main/java/org/archive/bdb/BdbModule.java | 2 +- commons/src/main/java/org/archive/io/Warc2Arc.java | 2 +- commons/src/main/java/org/archive/spring/Sheet.java | 4 ++-- .../src/main/java/org/archive/util/Histotable.java | 4 ++-- .../org/archive/util/IdentityCacheableWrapper.java | 2 +- .../org/archive/util/fingerprint/MemLongFPSet.java | 2 +- .../src/main/java/org/archive/util/ms/package.html | 2 +- .../src/test/java/org/archive/io/ArchiveTest.java | 2 +- .../archive/crawler/framework/CrawlController.java | 2 +- .../java/org/archive/crawler/framework/CrawlJob.java | 2 +- .../org/archive/crawler/framework/CrawlStatus.java | 8 ++++---- .../java/org/archive/crawler/framework/Frontier.java | 12 ++++++------ .../org/archive/crawler/framework/ToeThread.java | 4 ++-- .../frontier/AntiCalendarCostAssignmentPolicy.java | 2 +- .../crawler/frontier/BdbMultipleWorkQueues.java | 4 ++-- .../src/main/java/org/archive/crawler/package.html | 6 +++--- .../crawler/postprocessor/LowDiskPauseProcessor.java | 2 +- .../archive/crawler/prefetch/FrontierPreparer.java | 4 ++-- .../crawler/prefetch/PreconditionEnforcer.java | 2 +- .../org/archive/crawler/prefetch/Preselector.java | 2 +- .../archive/crawler/reporting/StatisticsTracker.java | 2 +- .../archive/crawler/restlet/EditRepresentation.java | 2 +- .../archive/crawler/restlet/EngineApplication.java | 2 +- .../org/archive/crawler/restlet/EnhDirectory.java | 2 +- .../org/archive/crawler/util/BdbUriUniqFilter.java | 2 +- .../org/archive/crawler/util/CheckpointUtils.java | 2 +- .../java/org/archive/crawler/util/LogReader.java | 6 +++--- .../org/archive/crawler/util/RecoveryLogMapper.java | 2 +- .../extras/adaptive/AdaptiveRevisitFrontier_en.utf8 | 4 ++-- .../crawler/extras/adaptive/WaitEvaluator_en.utf8 | 6 +++--- .../org/archive/crawler/prefetch/Preselector_en.utf8 | 2 +- .../crawler/prefetch/RuntimeLimitEnforcer_en.utf8 | 2 +- .../crawler/restlet/codemirror/mode/xmlpure.js | 2 +- .../org/archive/crawler/restlet/css/foundation.css | 4 ++-- .../restlet/js/foundation/foundation.forms.js | 2 +- .../restlet/js/foundation/foundation.joyride.js | 2 +- .../restlet/js/foundation/foundation.magellan.js | 2 +- .../org/archive/crawler/restlet/js/vendor/jquery.js | 8 ++++---- .../org/archive/crawler/restlet/js/vendor/zepto.js | 12 ++++++------ .../java/org/archive/crawler/selftest/package.html | 2 +- engine/src/webapps/selftest/Auth/basic/index.html | 2 +- .../webapps/selftest/BadURIsStopPageParsing/two.html | 2 +- engine/src/webapps/selftest/MaxLinkHops/index.html | 2 +- engine/src/xsd/arc/1.0/arc.html | 2 +- engine/src/xsd/arc/1.0/arc.xsd | 2 +- .../BadURIsStopPageParsingSelfTest/htdocs/two.html | 2 +- 46 files changed, 75 insertions(+), 75 deletions(-) diff --git a/commons/src/main/java/org/archive/bdb/BdbModule.java b/commons/src/main/java/org/archive/bdb/BdbModule.java index 8e082faa..d5ee2eb9 100644 --- a/commons/src/main/java/org/archive/bdb/BdbModule.java +++ b/commons/src/main/java/org/archive/bdb/BdbModule.java @@ -451,7 +451,7 @@ public class BdbModule implements Lifecycle, Checkpointable, Closeable, Disposab dbc.database.sync(); } - // Do a force checkpoint. Thats what a sync does (i.e. doSync). + // Do a force checkpoint. That's what a sync does (i.e. doSync). CheckpointConfig chkptConfig = new CheckpointConfig(); chkptConfig.setForce(true); diff --git a/commons/src/main/java/org/archive/io/Warc2Arc.java b/commons/src/main/java/org/archive/io/Warc2Arc.java index 3cd1142f..30c9ff20 100644 --- a/commons/src/main/java/org/archive/io/Warc2Arc.java +++ b/commons/src/main/java/org/archive/io/Warc2Arc.java @@ -128,7 +128,7 @@ public class Warc2Arc { int offset = r.getHeader().getContentBegin(); // This mimetype is not exactly what you'd expect to find in // an ARC though technically its 'correct'. To get right one, - // need to parse the HTTP Headers. Thats messy. Not doing for + // need to parse the HTTP Headers. That's messy. Not doing for // now. String mimetype = r.getHeader().getMimetype(); // Clean out ISO time string '-', 'T', ':', and 'Z' characters. diff --git a/commons/src/main/java/org/archive/spring/Sheet.java b/commons/src/main/java/org/archive/spring/Sheet.java index c2e7dd14..630275fb 100644 --- a/commons/src/main/java/org/archive/spring/Sheet.java +++ b/commons/src/main/java/org/archive/spring/Sheet.java @@ -98,7 +98,7 @@ public class Sheet implements BeanFactoryAware, BeanNameAware { } /** - * Ensure any properties targetted by this Sheet know to + * Ensure any properties targeted by this Sheet know to * check the right property paths for overrides at lookup time, * and that the override values are compatible types for their * destination properties. @@ -130,7 +130,7 @@ public class Sheet implements BeanFactoryAware, BeanNameAware { try { hkp = (HasKeyedProperties) bean; } catch (ClassCastException cce) { - // targetted bean has no overridable properties + // targeted bean has no overridable properties throw new TypeMismatchException(bean,HasKeyedProperties.class,cce); } // install knowledge of this path diff --git a/commons/src/main/java/org/archive/util/Histotable.java b/commons/src/main/java/org/archive/util/Histotable.java index be5fe4de..541af020 100644 --- a/commons/src/main/java/org/archive/util/Histotable.java +++ b/commons/src/main/java/org/archive/util/Histotable.java @@ -43,7 +43,7 @@ public class Histotable extends TreeMap { private static final long serialVersionUID = 310306238032568623L; /** - * Record one more occurence of the given object key. + * Record one more occurrence of the given object key. * * @param key Object key. */ @@ -52,7 +52,7 @@ public class Histotable extends TreeMap { } /** - * Record count more occurence(s) of the given object key. + * Record count more occurrence(s) of the given object key. * * @param key Object key. */ diff --git a/commons/src/main/java/org/archive/util/IdentityCacheableWrapper.java b/commons/src/main/java/org/archive/util/IdentityCacheableWrapper.java index f743d38a..60b0e4e7 100644 --- a/commons/src/main/java/org/archive/util/IdentityCacheableWrapper.java +++ b/commons/src/main/java/org/archive/util/IdentityCacheableWrapper.java @@ -62,7 +62,7 @@ public class IdentityCacheableWrapper implements IdentityCacheable { } // - // AutoKryo suppport + // AutoKryo support // public static void autoregisterTo(AutoKryo kryo) { kryo.register(IdentityCacheableWrapper.class); diff --git a/commons/src/main/java/org/archive/util/fingerprint/MemLongFPSet.java b/commons/src/main/java/org/archive/util/fingerprint/MemLongFPSet.java index 35aa4bc4..8556edc3 100644 --- a/commons/src/main/java/org/archive/util/fingerprint/MemLongFPSet.java +++ b/commons/src/main/java/org/archive/util/fingerprint/MemLongFPSet.java @@ -76,7 +76,7 @@ implements LongFPSet, Serializable { } private void grow() { - // Catastrophic event. Log its occurance. + // Catastrophic event. Log its occurrence. logger.info("Doubling fingerprinting slots to " + (1 << this.capacityPowerOfTwo)); long[] oldValues = values; diff --git a/commons/src/main/java/org/archive/util/ms/package.html b/commons/src/main/java/org/archive/util/ms/package.html index 82b3bb38..2ae9b949 100644 --- a/commons/src/main/java/org/archive/util/ms/package.html +++ b/commons/src/main/java/org/archive/util/ms/package.html @@ -79,7 +79,7 @@ of this is that every .doc file has a piece table, even those that were not "fast-saved".

The reader returned by -{@link org.achive.util.ms.Doc#getText(SeekInputStream)} consults the piece +{@link org.archive.util.ms.Doc#getText(SeekInputStream)} consults the piece table to determine where in the WordDocument subfile the next piece of text is located. It also uses the piece table to determine how bytes should be converted to Unicode characters. diff --git a/commons/src/test/java/org/archive/io/ArchiveTest.java b/commons/src/test/java/org/archive/io/ArchiveTest.java index 847c0830..c6bb460d 100644 --- a/commons/src/test/java/org/archive/io/ArchiveTest.java +++ b/commons/src/test/java/org/archive/io/ArchiveTest.java @@ -362,7 +362,7 @@ public class ArchiveTest /** * wayback-like replay of ARC record at offset - * @param arcReader an ARCReader intance + * @param arcReader an ARCReader instance * @throws IOException */ private void replayRecord(ARCReader arcReader) throws IOException { diff --git a/engine/src/main/java/org/archive/crawler/framework/CrawlController.java b/engine/src/main/java/org/archive/crawler/framework/CrawlController.java index ba63ceb7..0c32cc3a 100644 --- a/engine/src/main/java/org/archive/crawler/framework/CrawlController.java +++ b/engine/src/main/java/org/archive/crawler/framework/CrawlController.java @@ -471,7 +471,7 @@ implements Serializable, } /** - * Stop the crawl temporarly. + * Stop the crawl temporarily. */ public synchronized void requestCrawlPause() { if (state == State.PAUSING || state == State.PAUSED) { diff --git a/engine/src/main/java/org/archive/crawler/framework/CrawlJob.java b/engine/src/main/java/org/archive/crawler/framework/CrawlJob.java index d621c9b2..0718c292 100644 --- a/engine/src/main/java/org/archive/crawler/framework/CrawlJob.java +++ b/engine/src/main/java/org/archive/crawler/framework/CrawlJob.java @@ -637,7 +637,7 @@ public class CrawlJob implements Comparable, ApplicationListenerThat is to say that there are no more URIs either currently availible + *

That is to say that there are no more URIs either currently available * (ready to be emitted), URIs belonging to deferred hosts or pending URIs * in the Frontier. Thus this method may return false even if there is no - * currently availible URI. + * currently available URI. * * @return true if the frontier contains no more URIs to crawl. */ @@ -235,7 +235,7 @@ public interface Frontier extends Lifecycle, Reporter { * the processing chain. Can include failure to acquire prerequisites, to * establish a connection with the host and any number of other problems. * Does not count those that will be retried, only those that have - * permenantly failed. + * permanently failed. * * @return Number of URIs that failed to process. */ @@ -336,7 +336,7 @@ public interface Frontier extends Lifecycle, Reporter { * that are stored in cache (usually this means in memory * rather then on disk, but that is an implementation * detail) will be considered. Others will be entierly - * ignored, as if they dont exist. This is usefull for quick + * ignored, as if they don't exist. This is useful for quick * peeks at the top of the URI list. * @return A URIFrontierMarker that is set for the 'start' of the frontier's * URI list. @@ -370,7 +370,7 @@ public interface Frontier extends Lifecycle, Reporter { * invoking it. * * @param marker - * A marker specifing from what position in the Frontier the + * A marker specifying from what position in the Frontier the * list should begin. * @param numberOfMatches * how many URIs to add at most to the list before returning it diff --git a/engine/src/main/java/org/archive/crawler/framework/ToeThread.java b/engine/src/main/java/org/archive/crawler/framework/ToeThread.java index 8a13e2a5..4e9c4791 100644 --- a/engine/src/main/java/org/archive/crawler/framework/ToeThread.java +++ b/engine/src/main/java/org/archive/crawler/framework/ToeThread.java @@ -287,7 +287,7 @@ implements Reporter, ProgressStatisticsReporter, currentCuri.setFetchStatus(S_SERIOUS_ERROR); context = currentCuri.shortReportLine() + " in " + currentProcessorName; } - String message = "Serious error occured trying " + + String message = "Serious error occurred trying " + "to process '" + context + "'\n" + extraInfo; logger.log(Level.SEVERE, message.toString(), err); setPriority(DEFAULT_PRIORITY); @@ -307,7 +307,7 @@ implements Reporter, ProgressStatisticsReporter, currentCuri.getAnnotations().add("err="+e.getClass().getName()); currentCuri.getData().put(A_RUNTIME_EXCEPTION, e); String message = "Problem " + e + - " occured when trying to process '" + " occurred when trying to process '" + currentCuri.toString() + "' at step " + previousStep + " in " + currentProcessorName +"\n"; diff --git a/engine/src/main/java/org/archive/crawler/frontier/AntiCalendarCostAssignmentPolicy.java b/engine/src/main/java/org/archive/crawler/frontier/AntiCalendarCostAssignmentPolicy.java index 1d455f98..4237acd4 100644 --- a/engine/src/main/java/org/archive/crawler/frontier/AntiCalendarCostAssignmentPolicy.java +++ b/engine/src/main/java/org/archive/crawler/frontier/AntiCalendarCostAssignmentPolicy.java @@ -51,7 +51,7 @@ public class AntiCalendarCostAssignmentPolicy extends UnitCostAssignmentPolicy { Matcher m = TextUtils.getMatcher(CALENDARISH, curi.toString()); if (m.find()) { cost++; - // TODO: consider if multiple occurences should cost more + // TODO: consider if multiple occurrences should cost more } TextUtils.recycleMatcher(m); return cost; diff --git a/engine/src/main/java/org/archive/crawler/frontier/BdbMultipleWorkQueues.java b/engine/src/main/java/org/archive/crawler/frontier/BdbMultipleWorkQueues.java index c1503252..1f480c71 100644 --- a/engine/src/main/java/org/archive/crawler/frontier/BdbMultipleWorkQueues.java +++ b/engine/src/main/java/org/archive/crawler/frontier/BdbMultipleWorkQueues.java @@ -492,9 +492,9 @@ public class BdbMultipleWorkQueues { /** * Method used by BdbFrontier during checkpointing. *

The backing bdbje database has been marked deferred write so we save - * on writes to disk. Means no guarantees disk will have whats in memory + * on writes to disk. Means no guarantees disk will have what's in memory * unless a sync is called (Calling sync on the bdbje Environment is not - * sufficent). + * sufficient). *

Package access only because only Frontiers of this package would ever * need access. * @see Deferred Write Databases diff --git a/engine/src/main/java/org/archive/crawler/package.html b/engine/src/main/java/org/archive/crawler/package.html index 71b1a21a..055311fd 100644 --- a/engine/src/main/java/org/archive/crawler/package.html +++ b/engine/src/main/java/org/archive/crawler/package.html @@ -31,7 +31,7 @@

  1. Core classes - these can often be configured but not replaced. -
  2. Pluggable classes - these must implment a given interface +
  3. Pluggable classes - these must implement a given interface or extend a specific class but 3rd parties can introduce their own implementations.
@@ -86,7 +86,7 @@ When a URI is crawled, a {@link org.archive.crawler.framework.ToeThread ToeThread} will execute a series of processors on it.

- The processors are split into 5 distinct chains that are exectued in sequence: + The processors are split into 5 distinct chains that are executed in sequence:

  1. Pre-fetch processing chain @@ -129,7 +129,7 @@ implementations can be made of these to define any arbitrary scope. It should be noted though that usually any type of limitations to the scope of a crawl can be more easily achived using one of the existing scopes and - modifing it with appropriate filters. + modifying it with appropriate filters.

    {@link org.archive.crawler.framework.CrawlScope CrawlScope} - Base class for scopes.
    diff --git a/engine/src/main/java/org/archive/crawler/postprocessor/LowDiskPauseProcessor.java b/engine/src/main/java/org/archive/crawler/postprocessor/LowDiskPauseProcessor.java index f94b2979..f991845f 100644 --- a/engine/src/main/java/org/archive/crawler/postprocessor/LowDiskPauseProcessor.java +++ b/engine/src/main/java/org/archive/crawler/postprocessor/LowDiskPauseProcessor.java @@ -39,7 +39,7 @@ import org.springframework.beans.factory.annotation.Autowired; * disk space and pause the crawl if free space on monitored * filesystems falls below certain thresholds. * - * @deprecated Is highly system dependant. + * @deprecated Is highly system dependent. * Use {@link org.archive.crawler.monitor.DiskSpaceMonitor} instead. */ @Deprecated diff --git a/engine/src/main/java/org/archive/crawler/prefetch/FrontierPreparer.java b/engine/src/main/java/org/archive/crawler/prefetch/FrontierPreparer.java index 4eae6e6a..6736a920 100644 --- a/engine/src/main/java/org/archive/crawler/prefetch/FrontierPreparer.java +++ b/engine/src/main/java/org/archive/crawler/prefetch/FrontierPreparer.java @@ -38,7 +38,7 @@ import org.springframework.beans.factory.annotation.Autowired; /** * Processor to preload URI with as much precalculated policy-based - * info as possible before it reaches frontier criticial sections. + * info as possible before it reaches frontier critical sections. * * Frontiers also maintain a direct reference to this class, in case * they need to perform remedial preparation for URIs that do not @@ -195,7 +195,7 @@ public class FrontierPreparer extends Scoper { if (getPreferenceDepthHops() == 0) { return HIGH; // this implies seed redirects are treated as path - // length 1, which I belive is standard. + // length 1, which I believe is standard. // curi.getPathFromSeed() can never be null here, because // we're processing a link extracted from curi } else if (getPreferenceDepthHops() > 0 && diff --git a/engine/src/main/java/org/archive/crawler/prefetch/PreconditionEnforcer.java b/engine/src/main/java/org/archive/crawler/prefetch/PreconditionEnforcer.java index 258f9bfa..f3dcfa7e 100644 --- a/engine/src/main/java/org/archive/crawler/prefetch/PreconditionEnforcer.java +++ b/engine/src/main/java/org/archive/crawler/prefetch/PreconditionEnforcer.java @@ -368,7 +368,7 @@ public class PreconditionEnforcer extends Processor { * *

    * One day, do optimization and avoid running the bulk of the code below. - * Argument for running the code everytime is that overrides and refinements + * Argument for running the code every time is that overrides and refinements * may change what comes back from credential store. * * @param curi CrawlURI we're checking for any required preconditions. diff --git a/engine/src/main/java/org/archive/crawler/prefetch/Preselector.java b/engine/src/main/java/org/archive/crawler/prefetch/Preselector.java index d159d6c6..9c1e17f5 100644 --- a/engine/src/main/java/org/archive/crawler/prefetch/Preselector.java +++ b/engine/src/main/java/org/archive/crawler/prefetch/Preselector.java @@ -47,7 +47,7 @@ public class Preselector extends Scoper { * Recheck if uri is in scope. This is meaningful if the scope is altered * during a crawl. URIs are checked against the scope when they are added to * queues. Setting this value to true forces the URI to be checked against - * the scope when it is comming out of the queue, possibly after the scope + * the scope when it is coming out of the queue, possibly after the scope * is altered. */ { diff --git a/engine/src/main/java/org/archive/crawler/reporting/StatisticsTracker.java b/engine/src/main/java/org/archive/crawler/reporting/StatisticsTracker.java index 37b91c5e..8c83d78f 100644 --- a/engine/src/main/java/org/archive/crawler/reporting/StatisticsTracker.java +++ b/engine/src/main/java/org/archive/crawler/reporting/StatisticsTracker.java @@ -252,7 +252,7 @@ public class StatisticsTracker protected long crawlStartTime; /** wall-clock time the crawl ended */ protected long crawlEndTime = -1; // Until crawl ends, this value is -1. - /** wall-clock time of last pause, while pause in progres */ + /** wall-clock time of last pause, while pause in progress */ protected long crawlPauseStarted = 0; /** duration tally of all time spent in paused state */ protected long crawlTotalPausedTime = 0; diff --git a/engine/src/main/java/org/archive/crawler/restlet/EditRepresentation.java b/engine/src/main/java/org/archive/crawler/restlet/EditRepresentation.java index a06fbc12..a4ea7996 100644 --- a/engine/src/main/java/org/archive/crawler/restlet/EditRepresentation.java +++ b/engine/src/main/java/org/archive/crawler/restlet/EditRepresentation.java @@ -35,7 +35,7 @@ import org.restlet.resource.FileRepresentation; /** * Representation wrapping a FileRepresentation, displaying its contents - * in a TextArea for editting. + * in a TextArea for editing. * * @author gojomo */ diff --git a/engine/src/main/java/org/archive/crawler/restlet/EngineApplication.java b/engine/src/main/java/org/archive/crawler/restlet/EngineApplication.java index 94dc19c2..6c7793f7 100644 --- a/engine/src/main/java/org/archive/crawler/restlet/EngineApplication.java +++ b/engine/src/main/java/org/archive/crawler/restlet/EngineApplication.java @@ -139,7 +139,7 @@ public class EngineApplication extends Application { "back.\n"); } else{ - pw.append("

    An error occured

    \n"); + pw.append("

    An error occurred

    \n"); pw.append( "You may be able to recover and try something " + "else by going " + diff --git a/engine/src/main/java/org/archive/crawler/restlet/EnhDirectory.java b/engine/src/main/java/org/archive/crawler/restlet/EnhDirectory.java index d6c12297..ea7bb79d 100644 --- a/engine/src/main/java/org/archive/crawler/restlet/EnhDirectory.java +++ b/engine/src/main/java/org/archive/crawler/restlet/EnhDirectory.java @@ -35,7 +35,7 @@ import org.restlet.data.Response; * Enhanced version of Restlet Directory, which allows the local * filesystem directory to be determined dynamically based on the * request details. Also, via use of an EnhDirectoryResource, adds - * other capabilities (editting, etc.). + * other capabilities (editing, etc.). * * @author gojomo */ diff --git a/engine/src/main/java/org/archive/crawler/util/BdbUriUniqFilter.java b/engine/src/main/java/org/archive/crawler/util/BdbUriUniqFilter.java index 2a910f28..129db839 100644 --- a/engine/src/main/java/org/archive/crawler/util/BdbUriUniqFilter.java +++ b/engine/src/main/java/org/archive/crawler/util/BdbUriUniqFilter.java @@ -243,7 +243,7 @@ implements Lifecycle, Checkpointable, BeanNameAware, DisposableBean { } if (env != null) { try { - // This sync flushes whats in RAM. Its expensive operation. + // This sync flushes what's in RAM. Its expensive operation. // Without, data can be lost. Not for transactional operation. env.sync(); } catch (DatabaseException e) { diff --git a/engine/src/main/java/org/archive/crawler/util/CheckpointUtils.java b/engine/src/main/java/org/archive/crawler/util/CheckpointUtils.java index 7c4a9bc4..b1554039 100644 --- a/engine/src/main/java/org/archive/crawler/util/CheckpointUtils.java +++ b/engine/src/main/java/org/archive/crawler/util/CheckpointUtils.java @@ -64,7 +64,7 @@ public class CheckpointUtils { * Utility function to serialize an object to a file in current checkpoint * dir. Facilities * to store related files alongside the serialized object in a directory - * named with a .auxillary suffix. + * named with a .auxiliary suffix. * * @param o Object to serialize. * @param dir Directory to serialize into. diff --git a/engine/src/main/java/org/archive/crawler/util/LogReader.java b/engine/src/main/java/org/archive/crawler/util/LogReader.java index a88f768c..40d6b10d 100644 --- a/engine/src/main/java/org/archive/crawler/util/LogReader.java +++ b/engine/src/main/java/org/archive/crawler/util/LogReader.java @@ -801,7 +801,7 @@ public class LogReader pos = lastPos - BUFFERSIZE; } raf.seek(pos); - // If less then BUFFERSIZE avaliable read the remaining bytes + // If less then BUFFERSIZE available read the remaining bytes if ((lastPos - pos) < BUFFERSIZE) { int remainer = (int) (lastPos - pos); buffer = new byte[remainer]; @@ -818,11 +818,11 @@ public class LogReader } } } - // reset last postion + // reset last position lastPos = pos; } while ((numOfLines <= n) && (pos != 0)); - // print last n line starting from last postion + // print last n line starting from last position for (pos = lastPos; pos < endPos; pos += buffer.length) { raf.seek(pos); if ((endPos - pos) < BUFFERSIZE) { diff --git a/engine/src/main/java/org/archive/crawler/util/RecoveryLogMapper.java b/engine/src/main/java/org/archive/crawler/util/RecoveryLogMapper.java index 2d9b0de9..af7667f0 100644 --- a/engine/src/main/java/org/archive/crawler/util/RecoveryLogMapper.java +++ b/engine/src/main/java/org/archive/crawler/util/RecoveryLogMapper.java @@ -85,7 +85,7 @@ public class RecoveryLogMapper { * recoverLogFileName, will throw throw SeedUrlNotFoundException. Use * {@link #RecoveryLogMapper(String)} if you want to just log such cases and * keep going. (Those should not happen if the recover log is written - * correctly, but we see them in pratice.) + * correctly, but we see them in practice.) * * @param recoverLogFileName * @throws java.io.FileNotFoundException diff --git a/engine/src/main/resources/org/archive/crawler/extras/adaptive/AdaptiveRevisitFrontier_en.utf8 b/engine/src/main/resources/org/archive/crawler/extras/adaptive/AdaptiveRevisitFrontier_en.utf8 index e154c822..25819ba8 100644 --- a/engine/src/main/resources/org/archive/crawler/extras/adaptive/AdaptiveRevisitFrontier_en.utf8 +++ b/engine/src/main/resources/org/archive/crawler/extras/adaptive/AdaptiveRevisitFrontier_en.utf8 @@ -1,7 +1,7 @@ description: AdaptiveRevisitFrontier. EXPERIMENTAL Frontier that will repeatedly visit all encountered URIs. Wait time between visits is configurable and is determined -by seperate Processor(s). See WaitEvaluators. See documentation for ARFrontier +by separate Processor(s). See WaitEvaluators. See documentation for ARFrontier limitations. @@ -63,7 +63,7 @@ For retryable problems, seconds to wait before a retry use-uri-uniq-filter-description: -Should the Frontier use a seperate 'already included' datastructure +Should the Frontier use a separate 'already included' datastructure or rely on the queues'. diff --git a/engine/src/main/resources/org/archive/crawler/extras/adaptive/WaitEvaluator_en.utf8 b/engine/src/main/resources/org/archive/crawler/extras/adaptive/WaitEvaluator_en.utf8 index 6dadb020..7410ec0f 100644 --- a/engine/src/main/resources/org/archive/crawler/extras/adaptive/WaitEvaluator_en.utf8 +++ b/engine/src/main/resources/org/archive/crawler/extras/adaptive/WaitEvaluator_en.utf8 @@ -16,7 +16,7 @@ whose content change detection is not available. initial-wait-interval-seconds-description: The initial wait time between revisits. Will then be updated according to -crawler experiance. I.e. shorter wait, visit more often, if document has +crawler experience. I.e. shorter wait, visit more often, if document has changed between visits, and vica versa. @@ -30,8 +30,8 @@ completed. min-wait-interval-seconds-description: -The minum settable wait time between revisits. Once a URIs wait time -reaches this value, it will not be shortened further, regardlesss of +The minimum settable wait time between revisits. Once a URIs wait time +reaches this value, it will not be shortened further, regardless of subsequent visits that discover changes. diff --git a/engine/src/main/resources/org/archive/crawler/prefetch/Preselector_en.utf8 b/engine/src/main/resources/org/archive/crawler/prefetch/Preselector_en.utf8 index ff040384..2c1401d3 100644 --- a/engine/src/main/resources/org/archive/crawler/prefetch/Preselector_en.utf8 +++ b/engine/src/main/resources/org/archive/crawler/prefetch/Preselector_en.utf8 @@ -19,7 +19,7 @@ recheck-scope-description: Recheck if uri is in scope. This is meaningful if the scope is altered during a crawl. URIs are checked against the scope when they are added to queues. Setting this value to true forces the URI to be checked against -the scope when it is comming out of the queue, possibly after the scope +the scope when it is coming out of the queue, possibly after the scope is altered. diff --git a/engine/src/main/resources/org/archive/crawler/prefetch/RuntimeLimitEnforcer_en.utf8 b/engine/src/main/resources/org/archive/crawler/prefetch/RuntimeLimitEnforcer_en.utf8 index 37afa3f6..1f6546d3 100644 --- a/engine/src/main/resources/org/archive/crawler/prefetch/RuntimeLimitEnforcer_en.utf8 +++ b/engine/src/main/resources/org/archive/crawler/prefetch/RuntimeLimitEnforcer_en.utf8 @@ -3,7 +3,7 @@ A processor that halts further progress once a fixed amount of time has elapsed since the start of a crawl. It is possible to configure this processor per host, but it should be noted that Heritrix does not track runtime -per host seperately. Especially when using facilities +per host separately. Especially when using facilities like the BdbFrontier's hold-queues, the actual amount of time spent crawling a host may have little relevance to total elapsed time. Note however that using overrides diff --git a/engine/src/main/resources/org/archive/crawler/restlet/codemirror/mode/xmlpure.js b/engine/src/main/resources/org/archive/crawler/restlet/codemirror/mode/xmlpure.js index 18d710cf..37ad9e02 100644 --- a/engine/src/main/resources/org/archive/crawler/restlet/codemirror/mode/xmlpure.js +++ b/engine/src/main/resources/org/archive/crawler/restlet/codemirror/mode/xmlpure.js @@ -83,7 +83,7 @@ CodeMirror.defineMode("xmlpure", function(config, parserConfig) { return null; } - // return true if the current token is seperated from the tokens before it + // return true if the current token is separated from the tokens before it // which means either this is the start of the line, or there is at least // one space or tab character behind the token // otherwise returns false diff --git a/engine/src/main/resources/org/archive/crawler/restlet/css/foundation.css b/engine/src/main/resources/org/archive/crawler/restlet/css/foundation.css index 519efd85..e66bd7d7 100644 --- a/engine/src/main/resources/org/archive/crawler/restlet/css/foundation.css +++ b/engine/src/main/resources/org/archive/crawler/restlet/css/foundation.css @@ -237,7 +237,7 @@ select { margin-left: auto; margin-right: auto; float: none !important; } } -/* Styles for screens that are atleast 768px; */ +/* Styles for screens that are at least 768px; */ @media only screen and (min-width: 48em) { .row .large-1 { position: relative; @@ -2927,7 +2927,7 @@ form.custom { top: 0px; left: 0px; } -/* Styles for screens that are atleast 768px; */ +/* Styles for screens that are at least 768px; */ @media only screen and (min-width: 48em) { .joyride-tip-guide { width: 300px; diff --git a/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.forms.js b/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.forms.js index d6eaf08b..73dcad6d 100644 --- a/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.forms.js +++ b/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.forms.js @@ -352,7 +352,7 @@ hidden_fix : { /** - * Sets all hidden parent elements and self to visibile. + * Sets all hidden parent elements and self to visible. * * @method adjust * @param {jQuery Object} $child diff --git a/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.joyride.js b/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.joyride.js index a2bc0674..1900061e 100644 --- a/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.joyride.js +++ b/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.joyride.js @@ -122,7 +122,7 @@ if (!this.settings.init) this.init(); - // non configureable settings + // non configurable settings this.settings.$content_el = $this; this.settings.$body = $(this.settings.tipContainer); this.settings.body_offset = $(this.settings.tipContainer).position(); diff --git a/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.magellan.js b/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.magellan.js index 3cdef5b6..cea51bc5 100644 --- a/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.magellan.js +++ b/engine/src/main/resources/org/archive/crawler/restlet/js/foundation/foundation.magellan.js @@ -105,7 +105,7 @@ if (topOffset <= self.settings.threshold) { $("[data-magellan-arrival='" + destination_name + "']").trigger('arrival'); } - // In large screens we may hit the bottom of the page and dont reach the top of the last magellan-destination, so lets force it + // In large screens we may hit the bottom of the page and don't reach the top of the last magellan-destination, so lets force it if (scrolltopPlusHeight >= $(self.scope).height() && lastDestinationTop > windowScrollTop && lastDestinationTop < scrolltopPlusHeight) { $('[data-magellan-arrival]').last().trigger('arrival'); } diff --git a/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/jquery.js b/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/jquery.js index 6362d0f3..be5e490c 100644 --- a/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/jquery.js +++ b/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/jquery.js @@ -4186,7 +4186,7 @@ setDocument = Sizzle.setDocument = function( node ) { // Regex strategy adopted from Diego Perini assert(function( div ) { // Select is set to empty string on purpose - // This is to test IE's treatment of not explictly + // This is to test IE's treatment of not explicitly // setting a boolean content attribute, // since its presence should be enough // http://bugs.jquery.com/ticket/12359 @@ -6164,7 +6164,7 @@ jQuery.fn.extend({ if ( hasScripts ) { doc = scripts[ scripts.length - 1 ].ownerDocument; - // Reenable scripts + // Re-enable scripts jQuery.map( scripts, restoreScript ); // Evaluate executable scripts on first document insertion @@ -6836,7 +6836,7 @@ jQuery.extend({ value += "px"; } - // Fixes #8908, it can be done more correctly by specifing setters in cssHooks, + // Fixes #8908, it can be done more correctly by specifying setters in cssHooks, // but it would mean to define eight (for every problematic property) identical functions if ( !jQuery.support.clearCloneStyle && value === "" && name.indexOf("background") === 0 ) { style[ name ] = "inherit"; @@ -8830,7 +8830,7 @@ function propFilter( props, specialEasing ) { value = hooks.expand( value ); delete props[ name ]; - // not quite $.extend, this wont overwrite keys already present. + // not quite $.extend, this won't overwrite keys already present. // also - reusing 'index' from above because we have the correct "name" for ( index in value ) { if ( !( index in props ) ) { diff --git a/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/zepto.js b/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/zepto.js index 5e453a21..615b90ba 100644 --- a/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/zepto.js +++ b/engine/src/main/resources/org/archive/crawler/restlet/js/vendor/zepto.js @@ -137,7 +137,7 @@ var Zepto = (function() { // `$.zepto.fragment` takes a html string and an optional tag name // to generate DOM nodes nodes from the given html string. // The generated DOM nodes are returned as an array. - // This function can be overriden in plugins for example to make + // This function can be overridden in plugins for example to make // it compatible with browsers that don't support the DOM fully. zepto.fragment = function(html, name, properties) { if (html.replace) html = html.replace(tagExpanderRE, "<$1>") @@ -162,7 +162,7 @@ var Zepto = (function() { // `$.zepto.Z` swaps out the prototype of the given `dom` array // of nodes with `$.fn` and thus supplying all the Zepto functions // to the array. Note that `__proto__` is not supported on Internet - // Explorer. This method can be overriden in plugins. + // Explorer. This method can be overridden in plugins. zepto.Z = function(dom, selector) { dom = dom || [] dom.__proto__ = $.fn @@ -171,7 +171,7 @@ var Zepto = (function() { } // `$.zepto.isZ` should return `true` if the given object is a Zepto - // collection. This method can be overriden in plugins. + // collection. This method can be overridden in plugins. zepto.isZ = function(object) { return object instanceof zepto.Z } @@ -179,7 +179,7 @@ var Zepto = (function() { // `$.zepto.init` is Zepto's counterpart to jQuery's `$.fn.init` and // takes a CSS selector and an optional context (and handles various // special cases). - // This method can be overriden in plugins. + // This method can be overridden in plugins. zepto.init = function(selector, context) { // If nothing given, return an empty Zepto collection if (!selector) return zepto.Z() @@ -241,7 +241,7 @@ var Zepto = (function() { // `$.zepto.qsa` is Zepto's CSS selector implementation which // uses `document.querySelectorAll` and optimizes for some special cases, like `#id`. - // This method can be overriden in plugins. + // This method can be overridden in plugins. zepto.qsa = function(element, selector){ var found return (isDocument(element) && idSelectorRE.test(selector)) ? @@ -838,7 +838,7 @@ window.Zepto = Zepto chrome = ua.match(/Chrome\/([\d.]+)/) || ua.match(/CriOS\/([\d.]+)/), firefox = ua.match(/Firefox\/([\d.]+)/) - // Todo: clean this up with a better OS/browser seperation: + // Todo: clean this up with a better OS/browser separation: // - discern (more) between multiple browsers on android // - decide if kindle fire in silk mode is android or not // - Firefox on Android doesn't specify the Android version diff --git a/engine/src/test/java/org/archive/crawler/selftest/package.html b/engine/src/test/java/org/archive/crawler/selftest/package.html index db8534ca..63627870 100644 --- a/engine/src/test/java/org/archive/crawler/selftest/package.html +++ b/engine/src/test/java/org/archive/crawler/selftest/package.html @@ -5,7 +5,7 @@ Provides the client-side aspect of the heritrix integration self test.

    The selftest webapp is the repository for the serverside of the - intergration test.

    The integration self test is run from the command + integration test.

    The integration self test is run from the command line. Invocation makes the crawler go up against itself trawling the selftest webapp. When done, the product -- arc and log files -- are analyzed by code herein to verify test pass or fail.

    The integration diff --git a/engine/src/webapps/selftest/Auth/basic/index.html b/engine/src/webapps/selftest/Auth/basic/index.html index 178ed120..d05285a1 100644 --- a/engine/src/webapps/selftest/Auth/basic/index.html +++ b/engine/src/webapps/selftest/Auth/basic/index.html @@ -16,7 +16,7 @@ in org.archive.crawler.Heritrix#selftest and by directives set in the selftest web.xml file.

    -

    Link to a file thats only accessible if we've successfully +

    Link to a file that's only accessible if we've successfully logged in: basic-loggedin.html page.

    diff --git a/engine/src/webapps/selftest/BadURIsStopPageParsing/two.html b/engine/src/webapps/selftest/BadURIsStopPageParsing/two.html index 7ae7b9be..a591c4c1 100644 --- a/engine/src/webapps/selftest/BadURIsStopPageParsing/two.html +++ b/engine/src/webapps/selftest/BadURIsStopPageParsing/two.html @@ -11,6 +11,6 @@

    Pointer to a document that should be found in spite of bad BASE: Good #2 ONLY, in selftest, using above base, this document will be outside of selftest -scope. Thats OK.

    +scope. That's OK.

    diff --git a/engine/src/webapps/selftest/MaxLinkHops/index.html b/engine/src/webapps/selftest/MaxLinkHops/index.html index 8dcfe5ae..adcd9835 100644 --- a/engine/src/webapps/selftest/MaxLinkHops/index.html +++ b/engine/src/webapps/selftest/MaxLinkHops/index.html @@ -8,7 +8,7 @@

    Hop #2

    -

    The selftest home page links to this index.html. Thats one hop. +

    The selftest home page links to this index.html. That's one hop. Going to next page is second hop.

    diff --git a/engine/src/xsd/arc/1.0/arc.html b/engine/src/xsd/arc/1.0/arc.html index bb0484e3..491f0f11 100644 --- a/engine/src/xsd/arc/1.0/arc.html +++ b/engine/src/xsd/arc/1.0/arc.html @@ -701,7 +701,7 @@ function viewDocumentation(compDesc, compName, docTextArray) { XML Schema for http://archive.org/arc/1.0/ namespace. This schema adds Dublin Core element refinements for Internet - Achive ARC file metadata. It also adds new elements + Archive ARC file metadata. It also adds new elements that subclass the 'dc:any' type and the 'dc:metadata' element container. diff --git a/engine/src/xsd/arc/1.0/arc.xsd b/engine/src/xsd/arc/1.0/arc.xsd index 60a25991..510beffa 100644 --- a/engine/src/xsd/arc/1.0/arc.xsd +++ b/engine/src/xsd/arc/1.0/arc.xsd @@ -12,7 +12,7 @@ XML Schema for http://archive.org/arc/1.0/ namespace. This schema adds Dublin Core element refinements for Internet - Achive ARC file metadata. It also adds new elements + Archive ARC file metadata. It also adds new elements that subclass the 'dc:any' type and the 'dc:metadata' element container. diff --git a/engine/testdata/selftest/BadURIsStopPageParsingSelfTest/htdocs/two.html b/engine/testdata/selftest/BadURIsStopPageParsingSelfTest/htdocs/two.html index 7ae7b9be..a591c4c1 100644 --- a/engine/testdata/selftest/BadURIsStopPageParsingSelfTest/htdocs/two.html +++ b/engine/testdata/selftest/BadURIsStopPageParsingSelfTest/htdocs/two.html @@ -11,6 +11,6 @@

    Pointer to a document that should be found in spite of bad BASE: Good #2 ONLY, in selftest, using above base, this document will be outside of selftest -scope. Thats OK.

    +scope. That's OK.