Correct spelling mistakes.

commons/src/main/java/org/archive/bdb/BdbModule.java

@@ -451,7 +451,7 @@ public void doCheckpoint(final Checkpoint checkpointInProgress) throws IOExcepti
                 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);
 

commons/src/main/java/org/archive/io/Warc2Arc.java

@@ -128,7 +128,7 @@ protected void transform(final WARCReader reader, final ARCWriter writer)
                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.

commons/src/main/java/org/archive/spring/Sheet.java

@@ -98,7 +98,7 @@ public void setMap(Map<String, Object> m) {
     }
 
     /**
-     * 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 void prime() {
             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 

commons/src/main/java/org/archive/util/Histotable.java

@@ -43,7 +43,7 @@ public class Histotable<K> extends TreeMap<K,Long> {
     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 void tally(K key) {
     }
 
     /**
-     * Record <i>count</i> more occurence(s) of the given object key.
+     * Record <i>count</i> more occurrence(s) of the given object key.
      * 
      * @param key Object key.
      */

commons/src/main/java/org/archive/util/IdentityCacheableWrapper.java

@@ -62,7 +62,7 @@ public void setIdentityCache(ObjectIdentityCache<?> cache) {
     } 
 
     //
-    // AutoKryo suppport
+    // AutoKryo support
     //
     public static void autoregisterTo(AutoKryo kryo) {
         kryo.register(IdentityCacheableWrapper.class);

commons/src/main/java/org/archive/util/fingerprint/MemLongFPSet.java

@@ -76,7 +76,7 @@ protected void makeSpace() {
     }
 
     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;

commons/src/main/java/org/archive/util/ms/package.html

@@ -79,7 +79,7 @@ <h3>The Piece Table</h3>
 were not "fast-saved".
 
 <p>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.

commons/src/test/java/org/archive/io/ArchiveTest.java

@@ -362,7 +362,7 @@ private void dumpArchive(ArchiveReader reader) throws IOException {
 
 	/**
 	 * 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 {

engine/src/main/java/org/archive/crawler/framework/CrawlController.java

@@ -471,7 +471,7 @@ public void beginCrawlStop() {
     }
 
     /**
-     * Stop the crawl temporarly.
+     * Stop the crawl temporarily.
      */
     public synchronized void requestCrawlPause() {
         if (state == State.PAUSING || state == State.PAUSED) {

engine/src/main/java/org/archive/crawler/framework/CrawlJob.java

@@ -637,7 +637,7 @@ public List<File> getImportedConfigs(File xml) {
     }
 
     /**
-     * Return all known ConfigPaths, as an aid to viewing or editting. 
+     * Return all known ConfigPaths, as an aid to viewing or editing.
      * 
      * @return all ConfigPaths known to the ApplicationContext, in a 
      * map by name, or an empty map if no ApplicationContext

engine/src/main/java/org/archive/crawler/framework/CrawlStatus.java

@@ -2,7 +2,7 @@
 
 public enum CrawlStatus {
 
-    /** Inital value. May not be ready to run/incomplete. */    
+    /** Initial value. May not be ready to run/incomplete. */
     CREATED("Created"),
 
     /** Job has been successfully submitted to a CrawlJobHandler. */
@@ -28,7 +28,7 @@ public enum CrawlStatus {
 
 
     /**
-     * Job finished normally when the specifed amount of data (MB) had been
+     * Job finished normally when the specified amount of data (MB) had been
      * downloaded
      */
     FINISHED_DATA_LIMIT("Finished - Maximum amount of data limit hit"),
@@ -43,12 +43,12 @@ public enum CrawlStatus {
     FINISHED_WRITE_LIMIT("Finished - Maximum bytes written"),
 
     /**
-     * Job is going to be temporarly stopped after active threads are finished.
+     * Job is going to be temporarily stopped after active threads are finished.
      */
     WAITING_FOR_PAUSE("Pausing - Waiting for threads to finish"),
 
 
-    /** Job was temporarly stopped. State is kept so it can be resumed */
+    /** Job was temporarily stopped. State is kept so it can be resumed */
     PAUSED("Paused"),
 
 

engine/src/main/java/org/archive/crawler/framework/Frontier.java

@@ -93,7 +93,7 @@
 public interface Frontier extends Lifecycle, Reporter {
 
     /**
-     * Get the next URI that should be processed. If no URI becomes availible
+     * Get the next URI that should be processed. If no URI becomes available
      * during the time specified null will be returned.
      *
      * @return the next URI that should be processed.
@@ -104,10 +104,10 @@ public interface Frontier extends Lifecycle, Reporter {
     /**
      * Returns true if the frontier contains no more URIs to crawl.
      *
-     * <p>That is to say that there are no more URIs either currently availible
+     * <p>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 long importRecoverFormat(File source, boolean applyScope,
      *                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 long importRecoverFormat(File source, boolean applyScope,
      * 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

engine/src/main/java/org/archive/crawler/framework/ToeThread.java

@@ -287,7 +287,7 @@ private void seriousError(Error err) {
                         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 @@ private void recoverableProblem(Throwable e) {
         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";

engine/src/main/java/org/archive/crawler/frontier/AntiCalendarCostAssignmentPolicy.java

@@ -51,7 +51,7 @@ public int costOf(CrawlURI curi) {
         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;

engine/src/main/java/org/archive/crawler/frontier/BdbMultipleWorkQueues.java

@@ -492,9 +492,9 @@ public void delete(CrawlURI item) throws DatabaseException {
     /**
      * Method used by BdbFrontier during checkpointing.
      * <p>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).
      * <p>Package access only because only Frontiers of this package would ever
      * need access.
      * @see <a href="http://www.sleepycat.com/jedocs/GettingStartedGuide/DB.html">Deferred Write Databases</a>

engine/src/main/java/org/archive/crawler/package.html

@@ -31,7 +31,7 @@ <h3>framework</h3>
         <ol>
             <li> <em>Core classes</em> - these can often be configured but not 
                  replaced.
-            <li> <em>Pluggable classes</em> - these must implment a given interface 
+            <li> <em>Pluggable classes</em> - these must implement a given interface 
                  or extend a specific class but 3rd parties can introduce their own
                  implementations.
         </ol>
@@ -86,7 +86,7 @@ <h3>Processor</h3>
         When a URI is crawled, a {@link org.archive.crawler.framework.ToeThread
         ToeThread} will execute a series of <tt>processors</tt> on it.
     <p>
-        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:
 
                        <ol>
             <li>Pre-fetch processing chain
@@ -129,7 +129,7 @@ <h3>Scope</h3>
         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.
     <p>
         {@link org.archive.crawler.framework.CrawlScope CrawlScope} - Base class for
         scopes.<br>

engine/src/main/java/org/archive/crawler/postprocessor/LowDiskPauseProcessor.java

@@ -39,7 +39,7 @@
  * 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

engine/src/main/java/org/archive/crawler/prefetch/FrontierPreparer.java

@@ -38,7 +38,7 @@
 
 /**
  * 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 @@ protected int getSchedulingDirective(CrawlURI curi) {
         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 && 

engine/src/main/java/org/archive/crawler/prefetch/PreconditionEnforcer.java

@@ -368,7 +368,7 @@ public boolean isIpExpired(CrawlURI curi) {
     *
     * <p>
     * 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.

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.
      */
     {

engine/src/main/java/org/archive/crawler/reporting/StatisticsTracker.java

@@ -252,7 +252,7 @@ public void setCrawlController(CrawlController controller) {
     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;

engine/src/main/java/org/archive/crawler/restlet/EditRepresentation.java

@@ -35,7 +35,7 @@
 
 /**
  * Representation wrapping a FileRepresentation, displaying its contents
- * in a TextArea for editting. 
+ * in a TextArea for editing.
  * 
  * @author gojomo
  */

engine/src/main/java/org/archive/crawler/restlet/EngineApplication.java

@@ -139,7 +139,7 @@ public Representation getRepresentation(Status status, Request request, Response
                 "<a href='javascript:history.back();void(0);'>back</a>.\n");
             }
             else{
-                pw.append("<h1>An error occured</h1>\n");
+                pw.append("<h1>An error occurred</h1>\n");
                 pw.append(
                         "You may be able to recover and try something " +
                         "else by going " +

engine/src/main/java/org/archive/crawler/restlet/EnhDirectory.java

@@ -35,7 +35,7 @@
  * 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
  */

engine/src/main/java/org/archive/crawler/util/BdbUriUniqFilter.java

@@ -243,7 +243,7 @@ public synchronized void close() {
         }
         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) {

engine/src/main/java/org/archive/crawler/util/CheckpointUtils.java

@@ -64,7 +64,7 @@ public static String getClassCheckpointFilename(final Class<?> c,
      * 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 <code>.auxillary</code> suffix.
+     * named with a <code>.auxiliary</code> suffix.
      *
      * @param o Object to serialize.
      * @param dir Directory to serialize into.

engine/src/main/java/org/archive/crawler/util/LogReader.java

@@ -801,7 +801,7 @@ public static String[] tail(RandomAccessFile raf, int n) {
                     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 static String[] tail(RandomAccessFile raf, int n) {
                         }
                     }
                 }
-                // 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) {

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