Minimize transient garbage creation identified by allocation profiling

* UURIFactory, canonicalize/**, PathologicalPathDecideRule, ExtractorHTML
    use recycled matchers via TextUtils
* CrawlURI, KeyedProperties, OverlayContext, SheetOverlaysManager
    use ArrayList and indexed access rather than LinkedList and iterator instances

commons/src/main/java/org/archive/net/UURIFactory.java

@@ -372,17 +372,20 @@ public class UURIFactory extends URI {
         // Test for the case of more than two slashes after the http(s) scheme.
         // Replace with two slashes as mozilla does if found.
         // See [ 788219 ] URI Syntax Errors stop page parsing.
-        Matcher matcher = HTTP_SCHEME_SLASHES.matcher(uri);
+//        Matcher matcher = HTTP_SCHEME_SLASHES.matcher(uri);
+        Matcher matcher = TextUtils.getMatcher(HTTP_SCHEME_SLASHES.pattern(), uri);
         if (matcher.matches()) {
             uri = matcher.group(1) + matcher.group(2);
         }
+        TextUtils.recycleMatcher(matcher); 
 
         // now, minimally escape any whitespace
         uri = escapeWhitespace(uri);
         
         // For further processing, get uri elements.  See the RFC2396REGEX
         // comment above for explanation of group indices used in the below.
-        matcher = RFC2396REGEX.matcher(uri);
+//        matcher = RFC2396REGEX.matcher(uri);
+        matcher = TextUtils.getMatcher(RFC2396REGEX.pattern(), uri);
         if (!matcher.matches()) {
             throw new URIException("Failed parse of " + uri);
         }
@@ -392,6 +395,7 @@ public class UURIFactory extends URI {
         String uriPath = checkUriElement(matcher.group(6));
         String uriQuery = checkUriElement(matcher.group(8));
         // UNUSED String uriFragment = checkUriElement(matcher.group(10));
+        TextUtils.recycleMatcher(matcher); matcher = null;
         
         // Test if relative URI. If so, need a base to resolve against.
         if (uriScheme == null || uriScheme.length() <= 0) {
@@ -701,7 +705,8 @@ public class UURIFactory extends URI {
      */
     private String checkPort(String uriAuthority)
     throws URIException {
-        Matcher m = PORTREGEX.matcher(uriAuthority);
+//        Matcher m = PORTREGEX.matcher(uriAuthority);
+        Matcher m = TextUtils.getMatcher(PORTREGEX.pattern(), uriAuthority);
         if (m.matches()) {
             String no = m.group(2);
             if (no != null && no.length() > 0) {
@@ -726,6 +731,7 @@ public class UURIFactory extends URI {
                 }
             }
         }
+        TextUtils.recycleMatcher(m); 
         return uriAuthority;
     }
 

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

@@ -21,7 +21,6 @@
 
 import java.util.ArrayList;
 import java.util.HashSet;
-import java.util.LinkedList;
 import java.util.List;
 import java.util.Map;
 import java.util.concurrent.ConcurrentHashMap;
@@ -56,19 +55,21 @@ public class KeyedProperties extends ConcurrentHashMap<String,Object> {
      * @return discovered override, or local value
      */
     public Object get(String key) {
-        if(!threadOverrides.get().isEmpty()) {
-            for(OverlayContext ocontext: threadOverrides.get()) {
-                for(String name: ocontext.getOverlayNames()) {
-                    Map<String,Object> m = ocontext.getOverlayMap(name);
-                    for(String ok : getOverrideKeys(key)) {
-                        Object val = m.get(ok);
-                        if(val!=null) {
-                            return val;
-                        }
+        ArrayList<OverlayContext> overlays = threadOverrides.get();
+        for(int i = overlays.size()-1; i>=0; i--) {
+            OverlayContext ocontext = overlays.get(i); 
+            for(int j = ocontext.getOverlayNames().size()-1; j>=0; j--) {
+                String name = ocontext.getOverlayNames().get(j);
+                Map<String,Object> m = ocontext.getOverlayMap(name);
+                for(String ok : getOverrideKeys(key)) {
+                    Object val = m.get(ok);
+                    if(val!=null) {
+                        return val;
                     }
                 }
             }
         }
+
         return super.get(key);
     }
 
@@ -95,10 +96,10 @@ public class KeyedProperties extends ConcurrentHashMap<String,Object> {
     /**
      * ThreadLocal (contextual) collection of pushed override maps
      */
-    static ThreadLocal<LinkedList<OverlayContext>> threadOverrides = 
-        new ThreadLocal<LinkedList<OverlayContext>>() {
-        protected LinkedList<OverlayContext> initialValue() {
-            return new LinkedList<OverlayContext>();
+    static ThreadLocal<ArrayList<OverlayContext>> threadOverrides = 
+        new ThreadLocal<ArrayList<OverlayContext>>() {
+        protected ArrayList<OverlayContext> initialValue() {
+            return new ArrayList<OverlayContext>();
         }
     };
     /**
@@ -106,7 +107,7 @@ public class KeyedProperties extends ConcurrentHashMap<String,Object> {
      * @param m Map to add
      */
     static public void pushOverrideContext(OverlayContext ocontext) {
-        threadOverrides.get().addFirst(ocontext);
+        threadOverrides.get().add(ocontext);
     }
     
     /**
@@ -115,7 +116,7 @@ public class KeyedProperties extends ConcurrentHashMap<String,Object> {
      */
     static public OverlayContext popOverridesContext() {
         // TODO maybe check that pop is as expected
-        return threadOverrides.get().removeFirst();
+        return threadOverrides.get().remove(threadOverrides.get().size()-1);
     }
     
     static public void clearAllOverrideContexts() {

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

@@ -19,7 +19,7 @@
  
  package org.archive.spring;
 
-import java.util.LinkedList;
+import java.util.ArrayList;
 import java.util.Map;
 
 /**
@@ -32,7 +32,7 @@ public interface OverlayContext {
      * (even if in fact no overlays were added) */
     public boolean haveOverlayNamesBeenSet();
     /** return a list of the names of overlay maps to consider */ 
-    LinkedList<String> getOverlayNames();
+    ArrayList<String> getOverlayNames();
     /** get the map corresponding to the overlay name */ 
     Map<String,Object> getOverlayMap(String name);
 }