lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

Merge branch 'master' of https://github.com/dnet-team/dnet-dedup

This commit is contained in:
Michele De Bonis 2018-11-12 14:11:26 +01:00
parent b5062f5429 2a509b18fa
commit 72a9b3139e
2 changed files with 19 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
dnet-pace-core/pom.xml
View File

@ -6,7 +6,7 @@
<parent> <parent>
<groupId>eu.dnetlib</groupId> <groupId>eu.dnetlib</groupId>
<artifactId>dnet-dedup</artifactId> <artifactId>dnet-dedup</artifactId>
<version>3.0.1-SNAPSHOT</version> <version>3.0.3-SNAPSHOT</version>
<relativePath>../pom.xml</relativePath> <relativePath>../pom.xml</relativePath>
</parent> </parent>
@ -59,10 +59,17 @@
<groupId>org.reflections</groupId> <groupId>org.reflections</groupId>
<artifactId>reflections</artifactId> <artifactId>reflections</artifactId>
</dependency> </dependency>
<dependency> <dependency>
<groupId>org.apache.spark</groupId> <groupId>com.fasterxml.jackson.core</groupId>
<artifactId>spark-core_2.11</artifactId> <artifactId>jackson-databind</artifactId>
</dependency> </dependency>
<dependency>
<groupId>org.codehaus.jackson</groupId>
<artifactId>jackson-mapper-asl</artifactId>
</dependency>
</dependencies> </dependencies>
</project> </project>

22
dnet-pace-core/src/main/java/eu/dnetlib/pace/common/AbstractPaceFunctions.java
View File

@ -1,26 +1,22 @@
package eu.dnetlib.pace.common; package eu.dnetlib.pace.common;
import java.text.Normalizer;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import com.google.common.collect.Maps;
import eu.dnetlib.pace.distance.algo.JaroWinklerNormalizedName;
import org.apache.commons.collections.CollectionUtils;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang.StringUtils;
import com.google.common.base.Joiner; import com.google.common.base.Joiner;
import com.google.common.collect.Iterables; import com.google.common.collect.Iterables;
import com.google.common.collect.Lists; import com.google.common.collect.Lists;
import com.google.common.collect.Sets; import com.google.common.collect.Sets;
import eu.dnetlib.pace.clustering.NGramUtils; import eu.dnetlib.pace.clustering.NGramUtils;
import eu.dnetlib.pace.distance.algo.JaroWinklerNormalizedName;
import eu.dnetlib.pace.model.Field; import eu.dnetlib.pace.model.Field;
import eu.dnetlib.pace.model.FieldList; import eu.dnetlib.pace.model.FieldList;
import eu.dnetlib.pace.model.FieldListImpl; import eu.dnetlib.pace.model.FieldListImpl;
import org.apache.spark.util.CollectionsUtils; import org.apache.commons.collections.CollectionUtils;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang.StringUtils;
import java.text.Normalizer;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/** /**
* Set of common functions * Set of common functions