Changeset 31215

Timestamp:

2016-12-12T17:12:56+13:00 (7 years ago)

Author:

davidb

Message:

Changed back to Guava 20 API, now mvn shading allows me to have this in the JAR file as well as the Guava 14 that Spark/Apache uses

File:

• other-projects/hathitrust/wcsa/extracted-features-solr/trunk/solr-ingest/src/main/java/org/hathitrust/extractedfeatures/WhitelistBloomFilter.java (modified) (6 diffs)

other-projects/hathitrust/wcsa/extracted-features-solr/trunk/solr-ingest/src/main/java/org/hathitrust/extractedfeatures/WhitelistBloomFilter.java

@@ -3 +3 @@
 import java.io.BufferedInputStream;
 import java.io.BufferedOutputStream;
-import java.io.DataInputStream;
-import java.io.DataOutputStream;
 import java.io.File;
 import java.io.FileInputStream;
@@ -11 +9 @@
 import java.io.IOException;
 import java.io.InputStream;
-import java.io.OutputStream;
 import java.io.Serializable;
 import java.nio.charset.Charset;
@@ -21 +18 @@
 import javax.annotation.Nullable;
 
-import static com.google.common.base.Preconditions.checkNotNull;
-
 import com.google.common.base.Preconditions;
 import com.google.common.hash.BloomFilter;
-//import com.google.common.hash.BloomFilterAdvanced;
-//import com.google.common.hash.BloomFilterStrategies.BitArray;
 import com.google.common.hash.Funnel;
 import com.google.common.hash.Funnels;
 import com.google.common.hash.PrimitiveSink;
-import com.google.common.primitives.SignedBytes;
-import com.google.common.primitives.UnsignedBytes;
 
 public class WhitelistBloomFilter {
@@ -83 +74 @@
                 num_lines = countLines(dictionary_filename);
                  
-                //Funnel<CharSequence> string_funnel = Funnels.stringFunnel(StandardCharsets.UTF_8);
-                Funnel<CharSequence> string_funnel = stringFunnel(StandardCharsets.UTF_8);
+                Funnel<CharSequence> string_funnel = Funnels.stringFunnel(StandardCharsets.UTF_8);
                 _bloomFilter = BloomFilter.create(string_funnel, num_lines,FALSE_POSITIVE_PERCENTAGE);
             } 
@@ -154 +144 @@
             BufferedInputStream bfis = new BufferedInputStream(fis);
 
-            //Funnel<CharSequence> string_funnel = Funnels.stringFunnel(StandardCharsets.UTF_8);
-            Funnel<CharSequence> string_funnel = stringFunnel(StandardCharsets.UTF_8);
+            Funnel<CharSequence> string_funnel = Funnels.stringFunnel(StandardCharsets.UTF_8);
             bloomFilter = BloomFilter.readFrom(bfis,string_funnel);
 
@@ -171 +160 @@
 
 
-    // Spark uses Guava 14.0, the following is future-ported from Guava 20.0
-    // Added in here, rather then Funnel, and StringCharsetFunnel -> MyStringCharsetFunnel
-    
-    public static Funnel<CharSequence> stringFunnel(Charset charset) {
 
-        return new MyStringCharsetFunnel(charset);
-
-      }
-    
-    private static class MyStringCharsetFunnel implements Funnel<CharSequence>, Serializable {
-
-        private static final long serialVersionUID = 1L;
-        
-        private final Charset charset;
-
-        MyStringCharsetFunnel(Charset charset) {
-          this.charset = Preconditions.checkNotNull(charset);
-        }
-
-        public void funnel(CharSequence from, PrimitiveSink into) {
-          into.putString(from, charset);
-        }
-
-        @Override
-        public String toString() {
-          return "Funnels.stringFunnel(" + charset.name() + ")";
-        }
-
-        @Override
-        public boolean equals(@Nullable Object o) {
-
-          if (o instanceof MyStringCharsetFunnel) {
-            MyStringCharsetFunnel funnel = (MyStringCharsetFunnel) o;
-            return this.charset.equals(funnel.charset);
-          }
-          return false;
-        }
-
-        @Override
-        public int hashCode() {
-          return MyStringCharsetFunnel.class.hashCode() ^ charset.hashCode();
-        }
-
-        Object writeReplace() {
-          return new SerializedForm(charset);
-        }
-
-        private static class SerializedForm implements Serializable {
-          private final String charsetCanonicalName;
-
-          SerializedForm(Charset charset) {
-            this.charsetCanonicalName = charset.name();
-          }
-
-          private Object readResolve() {
-            return stringFunnel(Charset.forName(charsetCanonicalName));
-          }
-
-          private static final long serialVersionUID = 0;
-
-        }
-      }