add CommonPattern for multiple spaces

to eliminate empty split words on following spaces

htroot/ViewFile.java

@@ -449,7 +449,7 @@ public class ViewFile {
             words = words.substring(1, words.length() - 1);
         }
         words = UTF8.decodeURL(words);
-        if (words.indexOf(' ',0) >= 0) return CommonPattern.SPACE.split(words);
+        if (words.indexOf(' ',0) >= 0) return CommonPattern.SPACES.split(words);
         if (words.indexOf(',',0) >= 0) return CommonPattern.COMMA.split(words);
         if (words.indexOf('+',0) >= 0) return words.split("\\+");
         w = new String[1];

htroot/Vocabulary_p.java

@@ -164,7 +164,7 @@ public class Vocabulary_p {
                                 t = t.replaceAll("_", " ").replaceAll("\"", " ").replaceAll("'", " ").replaceAll(",", " ").replaceAll("  ", " ").trim();
                                 if (t.isEmpty()) continue;
                                 if (discoverFromTitleSplitted) {
-                                    String[] ts = CommonPattern.SPACE.split(t);
+                                    String[] ts = CommonPattern.SPACES.split(t);
                                     for (String s: ts) {
                                         if (s.isEmpty()) continue;
                                         if (s.endsWith(".jpg") || s.endsWith(".gif")) continue;

htroot/yacysearch_location.java

@@ -70,7 +70,7 @@ public class yacysearch_location {
             int placemarkCounter = 0;
             if (query.length() > 0 && search_query) {
                 final Set<GeoLocation> locations = LibraryProvider.geoLoc.find(query, true);
-                for (final String qp: CommonPattern.SPACE.split(query)) {
+                for (final String qp: CommonPattern.SPACES.split(query)) {
                     locations.addAll(LibraryProvider.geoLoc.find(qp, true));
                 }
                 String ip = sb.peers.mySeed().getIP();

pom.xml

@@ -34,7 +34,7 @@
         <maven.compiler.source>1.7</maven.compiler.source>
         <maven.compiler.target>1.7</maven.compiler.target>
         <!-- the Solr version used in dependency section for all related dependencies -->
-        <solr.version>4.10.3</solr.version> 
+        <solr.version>5.2.1</solr.version> 
         <!-- the Jetty version used in dependency section for all related dependencies -->
         <jetty.version>9.2.11.v20150529</jetty.version>
                 

source/net/yacy/cora/document/feed/RSSMessage.java

@@ -199,7 +199,7 @@ public class RSSMessage implements Hit, Comparable<RSSMessage>, Comparator<RSSMe
         final String subject = Token.subject.valueFrom(this.map, "");
         if (subject.indexOf(',') >= 0) return CommonPattern.COMMA.split(subject);
         if (subject.indexOf(';') >= 0) return CommonPattern.SEMICOLON.split(subject);
-        return CommonPattern.SPACE.split(subject);
+        return CommonPattern.SPACES.split(subject);
     }
 
     @Override

source/net/yacy/cora/document/id/MultiProtocolURL.java

@@ -985,7 +985,7 @@ public class MultiProtocolURL implements Serializable, Comparable<MultiProtocolU
         while ((p = t.indexOf("  ",0)) >= 0) t = t.substring(0, p) + t.substring(p + 1);
 
         // split the string into tokens and add all camel-case splitting
-        final String[] u = CommonPattern.SPACE.split(t);
+        final String[] u = CommonPattern.SPACES.split(t);
         final Set<String> token = new LinkedHashSet<String>();
         for (final String r: u) token.add(r);
         for (final String r: u) token.addAll(parseCamelCase(r));

source/net/yacy/cora/util/CommonPattern.java

@@ -39,6 +39,7 @@ import java.util.regex.Pattern;
 public class CommonPattern {
 
     public final static Pattern SPACE       = Pattern.compile(" ");
+    public final static Pattern SPACES      = Pattern.compile(" +"); // pattern for one or multiple spaces
     public final static Pattern COMMA       = Pattern.compile(",");
     public final static Pattern SEMICOLON   = Pattern.compile(";");
     public final static Pattern DOUBLEPOINT = Pattern.compile(":");

source/net/yacy/data/DidYouMean.java

@@ -305,7 +305,7 @@ public class DidYouMean {
                                 s = snippet + (afterSnippet.length() > 0 ? " " + afterSnippet : "");
                                 for (int i = 0; i < s.length(); i++) {char c = s.charAt(i); if (c < 'A') s = s.replace(c, ' ');} // remove funny symbols
                                 s = s.replaceAll("<b>", " ").replaceAll("</b>", " ").replaceAll("  ", " ").trim(); // wipe superfluous whitespace
-                                String[] sx = CommonPattern.SPACE.split(s);
+                                String[] sx = CommonPattern.SPACES.split(s);
                                 StringBuilder sb = new StringBuilder(s.length());
                                 for (String x: sx) if (x.length() > 1 && sb.length() < 28) sb.append(x).append(' '); else break;
                                 s = sb.toString().trim();

source/net/yacy/search/schema/CollectionConfiguration.java

@@ -284,7 +284,7 @@ public class CollectionConfiguration extends SchemaConfiguration implements Seri
             add(doc, CollectionSchema.title_chars_val, cv);
         }
         if (allAttr || contains(CollectionSchema.title_words_val)) {
-            Integer[] cv = new Integer[]{new Integer(CommonPattern.SPACE.split(title).length)};
+            Integer[] cv = new Integer[]{new Integer(CommonPattern.SPACES.split(title).length)};
             add(doc, CollectionSchema.title_words_val, cv);
         }
 
@@ -297,7 +297,7 @@ public class CollectionConfiguration extends SchemaConfiguration implements Seri
             add(doc, CollectionSchema.description_chars_val, description_exist ? new Integer[]{new Integer(description.length())} : new Integer[0]);
         }
         if (allAttr || contains(CollectionSchema.description_words_val)) {
-            add(doc, CollectionSchema.description_words_val, description_exist ? new Integer[]{new Integer(description.length() == 0 ? 0 : CommonPattern.SPACE.split(description).length)} : new Integer[0]);
+            add(doc, CollectionSchema.description_words_val, description_exist ? new Integer[]{new Integer(description.length() == 0 ? 0 : CommonPattern.SPACES.split(description).length)} : new Integer[0]);
         }
 
         String keywords = md.dc_subject();
@@ -460,7 +460,7 @@ public class CollectionConfiguration extends SchemaConfiguration implements Seri
         }
         if (allAttr || contains(CollectionSchema.title_words_val)) {
             ArrayList<Integer> cv = new ArrayList<Integer>(titles.size());
-            for (String s: titles) cv.add(new Integer(CommonPattern.SPACE.split(s).length));
+            for (String s: titles) cv.add(new Integer(CommonPattern.SPACES.split(s).length));
             add(doc, CollectionSchema.title_words_val, cv);
         }
 
@@ -479,7 +479,7 @@ public class CollectionConfiguration extends SchemaConfiguration implements Seri
         }
         if (allAttr || contains(CollectionSchema.description_words_val)) {
             ArrayList<Integer> cv = new ArrayList<Integer>(descriptions.length);
-            for (String s: descriptions) cv.add(new Integer(CommonPattern.SPACE.split(s).length));
+            for (String s: descriptions) cv.add(new Integer(CommonPattern.SPACES.split(s).length));
             add(doc, CollectionSchema.description_words_val, cv);
         }