DocumentAnalysis:使用 Hadoop 进行维基百科文档分析-源码

[{"title":"（ 53 个子文件 84KB ） DocumentAnalysis:使用 Hadoop 进行维基百科文档分析-源码","children":[{"title":"DocumentAnalysis-master","children":[{"title":".gitignore <span style='color:#111;'> 21B </span>","children":null,"spread":false},{"title":"packup.sh~ <span style='color:#111;'> 51B </span>","children":null,"spread":false},{"title":"packup.sh <span style='color:#111;'> 42B </span>","children":null,"spread":false},{"title":"BigData.jar <span style='color:#111;'> 34.45KB </span>","children":null,"spread":false},{"title":"src","children":[{"title":"categoryTFIDF","children":[{"title":"CategoryTFIDF.java <span style='color:#111;'> 2.46KB </span>","children":null,"spread":false},{"title":"CategoryTFIDF2.java <span style='color:#111;'> 2.55KB </span>","children":null,"spread":false}],"spread":true},{"title":"xmlDriver","children":[{"title":"XMLDriver.java <span style='color:#111;'> 4.44KB </span>","children":null,"spread":false}],"spread":true},{"title":"documentParser","children":[{"title":"TextParser.java <span style='color:#111;'> 1.51KB </span>","children":null,"spread":false},{"title":"XMLParser.java <span style='color:#111;'> 868B </span>","children":null,"spread":false}],"spread":true},{"title":"Writables","children":[{"title":"Map2ValueWritable.java <span style='color:#111;'> 1.00KB </span>","children":null,"spread":false},{"title":"Map1ValueWritable.java <span style='color:#111;'> 977B </span>","children":null,"spread":false},{"title":"Reduce1KeyWritable.java <span style='color:#111;'> 842B </span>","children":null,"spread":false}],"spread":true},{"title":"wordTFIDF","children":[{"title":"CountDocNum.java <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false},{"title":"WordTFIDF.java <span style='color:#111;'> 3.13KB </span>","children":null,"spread":false},{"title":"WordTFIDF2.java <span style='color:#111;'> 2.69KB </span>","children":null,"spread":false},{"title":"CountWordInitial.java <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false}],"spread":true},{"title":"DocumentAnalysis.java <span style='color:#111;'> 6.44KB </span>","children":null,"spread":false},{"title":"addPosition","children":[{"title":"AddPosition.java <span style='color:#111;'> 3.01KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"bin","children":[{"title":"categoryTFIDF","children":[{"title":"CategoryTFIDF2.class <span style='color:#111;'> 428B </span>","children":null,"spread":false},{"title":"CategoryTFIDF2$Reduce.class <span style='color:#111;'> 2.25KB </span>","children":null,"spread":false},{"title":"CategoryTFIDF$Reduce.class <span style='color:#111;'> 2.93KB </span>","children":null,"spread":false},{"title":"CategoryTFIDF.class <span style='color:#111;'> 423B </span>","children":null,"spread":false},{"title":"CategoryTFIDF2$Map.class <span style='color:#111;'> 3.63KB </span>","children":null,"spread":false},{"title":"CategoryTFIDF$Map.class <span style='color:#111;'> 3.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"xmlDriver","children":[{"title":"XMLDriver$XmlInputFormat1$XmlRecordReader.class <span style='color:#111;'> 4.16KB </span>","children":null,"spread":false},{"title":"XMLDriver.class <span style='color:#111;'> 362B </span>","children":null,"spread":false},{"title":"XMLDriver$XmlInputFormat1.class <span style='color:#111;'> 1.18KB </span>","children":null,"spread":false}],"spread":true},{"title":"documentParser","children":[{"title":"XMLParser.class <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false},{"title":"TextParser.class <span style='color:#111;'> 2.12KB </span>","children":null,"spread":false}],"spread":true},{"title":"Writables","children":[{"title":"Map2ValueWritable.class <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"Map1ValueWritable.class <span style='color:#111;'> 1.73KB </span>","children":null,"spread":false},{"title":"Reduce1KeyWritable.class <span style='color:#111;'> 1.65KB </span>","children":null,"spread":false}],"spread":true},{"title":"wordTFIDF","children":[{"title":"CountDocNum$PPartition.class <span style='color:#111;'> 973B </span>","children":null,"spread":false},{"title":"CountWordInitial$Reduce.class <span style='color:#111;'> 2.09KB </span>","children":null,"spread":false},{"title":"WordTFIDF2.class <span style='color:#111;'> 392B </span>","children":null,"spread":false},{"title":"CountDocNum.class <span style='color:#111;'> 456B </span>","children":null,"spread":false},{"title":"CountDocNum$Map.class <span style='color:#111;'> 1.98KB </span>","children":null,"spread":false},{"title":"CountDocNum$Reduce.class <span style='color:#111;'> 2.25KB </span>","children":null,"spread":false},{"title":"CountWordInitial.class <span style='color:#111;'> 486B </span>","children":null,"spread":false},{"title":"WordTFIDF.class <span style='color:#111;'> 387B </span>","children":null,"spread":false},{"title":"WordTFIDF$Reduce.class <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false},{"title":"CountWordInitial$PPartition.class <span style='color:#111;'> 989B </span>","children":null,"spread":false},{"title":"WordTFIDF2$Map.class <span style='color:#111;'> 3.57KB </span>","children":null,"spread":false},{"title":"WordTFIDF$Map.class <span style='color:#111;'> 3.75KB </span>","children":null,"spread":false},{"title":"CountWordInitial$Map.class <span style='color:#111;'> 2.52KB </span>","children":null,"spread":false},{"title":"WordTFIDF2$Reduce.class <span style='color:#111;'> 2.57KB </span>","children":null,"spread":false}],"spread":false},{"title":"addPosition","children":[{"title":"AddPosition$Map.class <span style='color:#111;'> 4.00KB </span>","children":null,"spread":false},{"title":"AddPosition.class <span style='color:#111;'> 405B </span>","children":null,"spread":false},{"title":"AddPosition$Reduce.class <span style='color:#111;'> 2.37KB </span>","children":null,"spread":false}],"spread":true},{"title":"DocumentAnalysis.class <span style='color:#111;'> 5.12KB </span>","children":null,"spread":false}],"spread":true},{"title":".classpath <span style='color:#111;'> 16.77KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 488B </span>","children":null,"spread":false},{"title":".project <span style='color:#111;'> 427B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]