本文整理汇总了Java中org.apache.lucene.benchmark.byTask.feeds.DocMaker类的典型用法代码示例。如果您正苦于以下问题:Java DocMaker类的具体用法?Java DocMaker怎么用?Java DocMaker使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
DocMaker类属于org.apache.lucene.benchmark.byTask.feeds包,在下文中一共展示了DocMaker类的9个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Java代码示例。
示例1: createPerfRunData
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
private PerfRunData createPerfRunData(File file,
boolean allowEmptyDocs,
String docMakerName) throws Exception {
Properties props = new Properties();
props.setProperty("doc.maker", docMakerName);
props.setProperty("line.file.out", file.getAbsolutePath());
props.setProperty("directory", "RAMDirectory"); // no accidental FS dir.
if (allowEmptyDocs) {
props.setProperty("sufficient.fields", ",");
}
if (docMakerName.equals(LegalJustDateDocMaker.class.getName())) {
props.setProperty("line.fields", DocMaker.DATE_FIELD);
props.setProperty("sufficient.fields", DocMaker.DATE_FIELD);
}
Config config = new Config(props);
return new PerfRunData(config);
}
开发者ID:europeana,项目名称:search,代码行数:18,代码来源:WriteLineDocTaskTest.java
示例2: ExtractWikipedia
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
public ExtractWikipedia(DocMaker docMaker, File outputDir) {
this.outputDir = outputDir;
this.docMaker = docMaker;
System.out.println("Deleting all files in " + outputDir);
File[] files = outputDir.listFiles();
for (int i = 0; i < files.length; i++) {
files[i].delete();
}
}
开发者ID:europeana,项目名称:search,代码行数:10,代码来源:ExtractWikipedia.java
示例3: extract
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
public void extract() throws Exception {
Document doc = null;
System.out.println("Starting Extraction");
long start = System.currentTimeMillis();
try {
while ((doc = docMaker.makeDocument()) != null) {
create(doc.get(DocMaker.ID_FIELD), doc.get(DocMaker.TITLE_FIELD), doc
.get(DocMaker.DATE_FIELD), doc.get(DocMaker.BODY_FIELD));
}
} catch (NoMoreDataException e) {
//continue
}
long finish = System.currentTimeMillis();
System.out.println("Extraction took " + (finish - start) + " ms");
}
开发者ID:europeana,项目名称:search,代码行数:16,代码来源:ExtractWikipedia.java
示例4: main
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
File wikipedia = null;
File outputDir = new File("./enwiki");
boolean keepImageOnlyDocs = true;
for (int i = 0; i < args.length; i++) {
String arg = args[i];
if (arg.equals("--input") || arg.equals("-i")) {
wikipedia = new File(args[i + 1]);
i++;
} else if (arg.equals("--output") || arg.equals("-o")) {
outputDir = new File(args[i + 1]);
i++;
} else if (arg.equals("--discardImageOnlyDocs") || arg.equals("-d")) {
keepImageOnlyDocs = false;
}
}
Properties properties = new Properties();
properties.setProperty("docs.file", wikipedia.getAbsolutePath());
properties.setProperty("content.source.forever", "false");
properties.setProperty("keep.image.only.docs", String.valueOf(keepImageOnlyDocs));
Config config = new Config(properties);
ContentSource source = new EnwikiContentSource();
source.setConfig(config);
DocMaker docMaker = new DocMaker();
docMaker.setConfig(config, source);
docMaker.resetInputs();
if (wikipedia.exists()) {
System.out.println("Extracting Wikipedia to: " + outputDir + " using EnwikiContentSource");
outputDir.mkdirs();
ExtractWikipedia extractor = new ExtractWikipedia(docMaker, outputDir);
extractor.extract();
} else {
printUsage();
}
}
开发者ID:europeana,项目名称:search,代码行数:40,代码来源:ExtractWikipedia.java
示例5: lineFileOut
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
@Override
protected PrintWriter lineFileOut(Document doc) {
IndexableField titleField = doc.getField(DocMaker.TITLE_FIELD);
if (titleField!=null && titleField.stringValue().startsWith("Category:")) {
return categoryLineFileOut;
}
return super.lineFileOut(doc);
}
开发者ID:europeana,项目名称:search,代码行数:9,代码来源:WriteEnwikiLineDocTask.java
示例6: setup
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
@Override
public void setup() throws Exception {
super.setup();
DocMaker docMaker = getRunData().getDocMaker();
if (docSize > 0) {
doc = docMaker.makeDocument(docSize);
} else {
doc = docMaker.makeDocument();
}
}
开发者ID:europeana,项目名称:search,代码行数:11,代码来源:AddDocTask.java
示例7: doLogic
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
@Override
public int doLogic() throws Exception {
final String docID = doc.get(DocMaker.ID_FIELD);
if (docID == null) {
throw new IllegalStateException("document must define the docid field");
}
final IndexWriter iw = getRunData().getIndexWriter();
iw.updateDocument(new Term(DocMaker.ID_FIELD, docID), doc);
return 1;
}
开发者ID:europeana,项目名称:search,代码行数:11,代码来源:UpdateDocTask.java
示例8: PerfRunData
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
public PerfRunData (Config config) throws Exception {
this.config = config;
// analyzer (default is standard analyzer)
analyzer = NewAnalyzerTask.createAnalyzer(config.get("analyzer",
"org.apache.lucene.analysis.standard.StandardAnalyzer"));
// content source
String sourceClass = config.get("content.source", "org.apache.lucene.benchmark.byTask.feeds.SingleDocSource");
contentSource = Class.forName(sourceClass).asSubclass(ContentSource.class).newInstance();
contentSource.setConfig(config);
// doc maker
docMaker = Class.forName(config.get("doc.maker",
"org.apache.lucene.benchmark.byTask.feeds.DocMaker")).asSubclass(DocMaker.class).newInstance();
docMaker.setConfig(config, contentSource);
// facet source
facetSource = Class.forName(config.get("facet.source",
"org.apache.lucene.benchmark.byTask.feeds.RandomFacetSource")).asSubclass(FacetSource.class).newInstance();
facetSource.setConfig(config);
// query makers
readTaskQueryMaker = new HashMap<>();
qmkrClass = Class.forName(config.get("query.maker","org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker")).asSubclass(QueryMaker.class);
// index stuff
reinit(false);
// statistic points
points = new Points(config);
if (Boolean.valueOf(config.get("log.queries","false")).booleanValue()) {
System.out.println("------------> queries:");
System.out.println(getQueryMaker(new SearchTask(this)).printQueries());
}
}
开发者ID:europeana,项目名称:search,代码行数:35,代码来源:PerfRunData.java
示例9: PerfRunData
import org.apache.lucene.benchmark.byTask.feeds.DocMaker; //导入依赖的package包/类
public PerfRunData (Config config) throws Exception {
this.config = config;
// analyzer (default is standard analyzer)
analyzer = NewAnalyzerTask.createAnalyzer(config.get("analyzer",
"org.apache.lucene.analysis.standard.StandardAnalyzer"));
// content source
String sourceClass = config.get("content.source", "org.apache.lucene.benchmark.byTask.feeds.SingleDocSource");
contentSource = Class.forName(sourceClass).asSubclass(ContentSource.class).newInstance();
contentSource.setConfig(config);
// doc maker
docMaker = Class.forName(config.get("doc.maker",
"org.apache.lucene.benchmark.byTask.feeds.DocMaker")).asSubclass(DocMaker.class).newInstance();
docMaker.setConfig(config, contentSource);
// facet source
facetSource = Class.forName(config.get("facet.source",
"org.apache.lucene.benchmark.byTask.feeds.RandomFacetSource")).asSubclass(FacetSource.class).newInstance();
facetSource.setConfig(config);
// query makers
readTaskQueryMaker = new HashMap<Class<? extends ReadTask>,QueryMaker>();
qmkrClass = Class.forName(config.get("query.maker","org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker")).asSubclass(QueryMaker.class);
// index stuff
reinit(false);
// statistic points
points = new Points(config);
if (Boolean.valueOf(config.get("log.queries","false")).booleanValue()) {
System.out.println("------------> queries:");
System.out.println(getQueryMaker(new SearchTask(this)).printQueries());
}
}
开发者ID:pkarmstr,项目名称:NYBC,代码行数:35,代码来源:PerfRunData.java
注:本文中的org.apache.lucene.benchmark.byTask.feeds.DocMaker类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论