Download json wikipedia Free Java Code

Description

Json Wikipedia, contains code to convert the Wikipedia xml dump in a json dump.

Source Files

The download file json-wikipedia-master.zip has the following entries.


.gitignore/* w  ww. j a va 2  s.c  o m*/
README.md
lib/info/bliki/wiki/bliki-core/3.0.16/_maven.repositories
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16-sources.jar
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16-sources.jar.sha1
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16.jar
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16.jar.lastUpdated
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16.jar.sha1
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16.pom
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16.pom.lastUpdated
lib/info/bliki/wiki/bliki-core/3.0.16/bliki-core-3.0.16.pom.sha1
lib/info/bliki/wiki/bliki-core/3.0.16/m2e-lastUpdated.properties
lib/info/bliki/wiki/bliki-core/3.0.19/bliki-core-3.0.19.jar.lastUpdated
lib/info/bliki/wiki/bliki-core/3.0.19/bliki-core-3.0.19.pom.lastUpdated
lib/info/bliki/wiki/bliki/3.0.16/_maven.repositories
lib/info/bliki/wiki/bliki/3.0.16/bliki-3.0.16.pom
lib/info/bliki/wiki/bliki/3.0.16/bliki-3.0.16.pom.lastUpdated
lib/info/bliki/wiki/bliki/3.0.16/bliki-3.0.16.pom.sha1
lib/it/cnr/isti/hpc/hpc-utils/0.0.5/_maven.repositories
lib/it/cnr/isti/hpc/hpc-utils/0.0.5/hpc-utils-0.0.5.jar
lib/it/cnr/isti/hpc/hpc-utils/0.0.5/hpc-utils-0.0.5.pom
lib/it/cnr/isti/hpc/parent/0.0.7-SNAPSHOT/_maven.repositories
lib/it/cnr/isti/hpc/parent/0.0.7-SNAPSHOT/maven-metadata-local.xml
lib/it/cnr/isti/hpc/parent/0.0.7-SNAPSHOT/parent-0.0.7-SNAPSHOT.pom
lib/it/cnr/isti/hpc/parent/0.0.7-SNAPSHOT/resolver-status.properties
logback.xml
pom.xml
scripts/config.sh
scripts/convert-xml-dump-in-one-article-per-line.py
scripts/convert-xml-dump-to-json.sh
scripts/get-summary.sh
scripts/get-titles-and-types.sh
src/main/java/it/cnr/isti/hpc/wikipedia/article/Article.java
src/main/java/it/cnr/isti/hpc/wikipedia/article/ArticleSummarizer.java
src/main/java/it/cnr/isti/hpc/wikipedia/article/Language.java
src/main/java/it/cnr/isti/hpc/wikipedia/article/Link.java
src/main/java/it/cnr/isti/hpc/wikipedia/article/Table.java
src/main/java/it/cnr/isti/hpc/wikipedia/article/Template.java
src/main/java/it/cnr/isti/hpc/wikipedia/cli/GetDumpSummaryCLI.java
src/main/java/it/cnr/isti/hpc/wikipedia/cli/GetTitleAndTypeCLI.java
src/main/java/it/cnr/isti/hpc/wikipedia/cli/GetTitlesCLI.java
src/main/java/it/cnr/isti/hpc/wikipedia/cli/JsonToLineCLI.java
src/main/java/it/cnr/isti/hpc/wikipedia/cli/MediawikiToJsonCLI.java
src/main/java/it/cnr/isti/hpc/wikipedia/parser/ArticleParser.java
src/main/java/it/cnr/isti/hpc/wikipedia/parser/Locale.java
src/main/java/it/cnr/isti/hpc/wikipedia/parser/LocalizedMediaWikiParserFactory.java
src/main/java/it/cnr/isti/hpc/wikipedia/parser/MediaWikiParserFactory.java
src/main/java/it/cnr/isti/hpc/wikipedia/reader/WikipediaArticleReader.java
src/main/java/it/cnr/isti/hpc/wikipedia/reader/filter/DisambiguationFilter.java
src/main/java/it/cnr/isti/hpc/wikipedia/reader/filter/RedirectFilter.java
src/main/java/it/cnr/isti/hpc/wikipedia/reader/filter/ShortTitleFilter.java
src/main/java/it/cnr/isti/hpc/wikipedia/reader/filter/TitleFilter.java
src/main/java/it/cnr/isti/hpc/wikipedia/reader/filter/TypeFilter.java
src/main/java/it/cnr/isti/hpc/wikipedia/reader/filter/UnknownTypeFilter.java
src/main/resources/lang/locale-en.properties
src/main/resources/lang/locale-es.properties
src/main/resources/lang/locale-it.properties
src/main/webapp/WEB-INF/web.xml
src/test/java/it/cnr/isti/hpc/wikipedia/article/ArticleSummarizerTest.java
src/test/java/it/cnr/isti/hpc/wikipedia/article/en/ArticleTest.java
src/test/java/it/cnr/isti/hpc/wikipedia/article/it/ArticleTest.java
src/test/java/it/cnr/isti/hpc/wikipedia/reader/WikipediaArticleReaderTest.java
src/test/resources/en/article.txt
src/test/resources/en/hdis.txt
src/test/resources/en/liberalism.txt
src/test/resources/en/mercedes.txt
src/test/resources/en/mercedes.xml
src/test/resources/it/xml-dump/article-with-infobox.txt
src/test/resources/it/xml-dump/article.txt
src/test/resources/it/xml-dump/categories.xml.gz
src/test/resources/it/xml-dump/list.txt
src/test/resources/it/xml-dump/small-dump.xml.gz
src/test/resources/it/xml-dump/table.txt
src/test/resources/misc/en-wikipedia-articles-1000-1.json.gz
src/test/resources/misc/en-wikipedia-articles-1000-2.json.gz
src/test/resources/misc/json-articles.json
src/test/resources/misc/kennedy.json
src/test/resources/misc/redirect.txt
src/test/resources/misc/redirect.xml
src/test/resources/misc/test-index-10-articles.json
src/test/resources/misc/wikipedia-small-test.xml.bz2

Download

Click the following link to download json-wikipedia-master.zip.

json-wikipedia-master.zip




















Home »
  Java Free Code »
    Development »




Algebra
Algorithm
Ant
Bytecode
Compiler
DataMining
DSL
Eclipse
Example
File
Git
Intellij
JavaBean
JAX
jBPM
JDK8
JME
JMX
JodaTime
JRuby
JSE
JSON
JVM
Lambda
libgdx
Library
log4j
Markdown
Math
Maven
Netbeans
NIO
NLP
OSGi
Plugin
Scala
SDK
slf4j
Template
Thread
Tutorial
Unicode
Utility
ZooKeeper