ivate

会自动把单词转为小写.导入依赖:dependencygroupIdorg.ansj/groupIdartifactIdansj_seg/artifactIdversion5.1.6/version

static

ToAnalysis.parse(str).getTerms();for

(Term

terms){System.out.println(term.getName());}

}3.2

制作并生成索引数据(输出到文件中)从制定的路径中枚举出所有的文件读取每个文件,

从文件中解析出

C:/Users/LEO/Desktop/jdk-8u361-docs-all/docs/api;创建一个

index

System.currentTimeMillis();System.out.println(***

索引制作开始!

这个过程需要把所有子目录中的文件都能获取到ArrayListFile

fileList

ArrayList();enumFile(INPUT_PATH,fileList);/***

获取到

System.out.println(fileList.size());*///

打开文件,

通过这个方法来解析单个的html文件System.out.println(开始解析:

f.getAbsolutePath());parseHTML(f);}//

end

System.currentTimeMillis();System.out.println(****

索引制作完成!

C:/Users/LEO/Desktop/jdk-8u361-docs-all/docs/api

private

进一步的获取子目录中的内容if(f.isDirectory()){enumFile(f.getAbsolutePath(),

fileList);}

endsWith是String类的方法if(f.getAbsolutePath().endsWith(.html)){fileList.add(f);}}}

}(3)

把解析出来的这些信息加入到索引当中index.addDoc(title,

url,

file:///C:/Users/LEO/Desktop/jdk-8u361-docs-all/docs/api/;String

part11

https://docs.oracle.com/javase/8/docs/api;String

part2

f.getAbsolutePath().substring(INPUT_PATH.length());return

part11

true;}}}fileReader.close();return

content.toString();}

StringBuilder();while(true){int

ret

content.replaceAll(script.*?(.*?)/script,

);//

通过这个main方法实现整个制作索引的过程要先将api文档扫描完并保存到磁盘上,

然后再启动tomcatpublic

parser.run();parser.runByThread();

}3.3

C:/Users/LEO/Desktop/jdk-8u361-docs-all/;objectMapper对象private

ObjectMapper

DocInfo();docInfo.setTitle(title);docInfo.setUrl(url);docInfo.setContent(content);synchronized

(locker1)

{docInfo.setDocId(forwardIndex.size());forwardIndex.add(docInfo);}return

docInfo;

ToAnalysis.parse(docInfo.getTitle()).getTerms();//

遍历分词结果,

WordCnt();newWordCnt.titleCount

newWordCnt);}

ToAnalysis.parse(docInfo.getContent()).getTerms();//

遍历分词结果,

WordCnt();newWordCnt.titleCount

newWordCnt);}

invertedIndex.get(entry.getKey());if

(invertedList

Weight();weight.setDocId(docInfo.getDocId());//

权重计算公式:

正文中出现的次数weight.setWeight(entry.getValue().titleCount

entry.getValue().contentCount);newInvertedList.add(weight);invertedIndex.put(entry.getKey(),

newInvertedList);}

Weight();weight.setDocId(docInfo.getDocId());//

权重计算公式:

正文中出现的次数weight.setWeight(entry.getValue().titleCount

entry.getValue().contentCount);invertedList.add(weight);}}}

}(6)

System.currentTimeMillis();System.out.println(-----

保存索引开始!

indexPathFile.exists()){indexPathFile.mkdirs();}File

forwardIndexFile

{objectMapper.writeValue(forwardIndexFile,

forwardIndex);objectMapper.writeValue(invertedIndexFile,

invertedIndex);}

System.currentTimeMillis();System.out.println(-----

保存索引完成!

System.currentTimeMillis();System.out.println(-----

加载索引开始!

objectMapper.readValue(forwardIndexFile,

new

TypeReferenceArrayListDocInfo()

{});invertedIndex

objectMapper.readValue(invertedIndexFile,

new

System.currentTimeMillis();System.out.println(-----

加载索引完成!

C:/Users/LEO/Desktop/jdk-8u361-docs-all/stop_word.txt;保存停用词private

HashSetString

ToAnalysis.parse(query).getTerms();ListTerm

terms

oldTerms){if(stopWords.contains(term.getName())){continue;}terms.add(term);}//

[触发]

说明这个词在所有文档中都不存在continue;}termResult.add(invertedList);}//

[合并]

针对触发的结果按照权重降序排序allTermResult.sort(new

ComparatorWeight()

index.getDocInfo(weight.getDocId());Result

result

Result();result.setTitle(docInfo.getTitle());result.setUrl(docInfo.getUrl());result.setDesc(GenDes(docInfo.getContent(),

terms));results.add(result);}return

results;

source.get(o1.row).get(o1.col).getDocId()

source.get(o2.row).get(o2.col).getDocId();}});//

2.2

source.get(curPos.row).get(curPos.col);if

(target.size()

的权重lastWeight.setWeight(lastWeight.getWeight()

else

当前行已经到达末尾了continue;}queue.offer(newPos);}return

target;

content.toLowerCase().replaceAll(\\b

word

loadStopWords(){try(BufferedReader

bufferedReader

FileReader(STOP_WORD_PATH))){while(true){String

line

bufferedReader.readLine();if(line

null){//

读取文件完毕break;}stopWords.add(line);}}

catch

ObjectMapper();Overrideprotected

void

的值!;System.out.println(msg);resp.sendError(404,

msg);return;}//

把当前的搜索结果进行打包resp.setContentType(application/json;

charsetutf-8);objectMapper.writeValue(resp.getWriter(),

results);}