lucene入门

最近一直再研究lucene，把入门的程序和大家分享：

对索引的操作类：

public
 
class
 IndexDao {

    public
 IndexDao() {
        try
 {
            indexWriter = new
 IndexWriter(Constants.INDEX_STORE_PATH,
                    Constants.analyzer, MaxFieldLength.LIMITED);
        } catch
 (Exception e) {
            e.printStackTrace();
        }
    }
    public
 IndexDao(Directory dir) {
        try
 {
            indexWriter = new
 IndexWriter(dir,Constants.analyzer,MaxFieldLength.LIMITED);
        } catch
 (Exception e) {
            e.printStackTrace();
        }
    }
    public
 IndexDao(
boolean
 isCreate) {
        try
 {
            indexWriter = new
 IndexWriter(Constants.INDEX_STORE_PATH,Constants.analyzer, isCreate,MaxFieldLength.LIMITED);
        } catch
 (Exception e) {
            e.printStackTrace();
        }
    }

    // 索引器
    private
 IndexWriter indexWriter = 
null
;

    /**
     * 添加/创建索引
     *
     * @param folder
     * @throws IOException
     * @throws CorruptIndexException
     */
    public
 
void
 saveIndex(File folder, String[] unIndeies)
            throws
 CorruptIndexException, IOException {
        if
 (folder.isDirectory()) {
            String[] files = folder.list();
            for
 (
int
 i = 
0
; i < files.length; i++) {
                File f = new
 File(folder, files[i]);
                if
 (!f.isHidden()) {
                    if
 (f.isDirectory()) {
                        saveIndex(f, unIndeies);// ② 递归
                    }
                    String fileTyep = ReadFile.validateFile(f);
                    for
 (
int
 j = 
0
; j < unIndeies.length; j++) {
                        if
 (fileTyep.equalsIgnoreCase(unIndeies[j])) {
                            System.out.println("正在建立索引 : "
 + f.getName() + 
""
);
                            Document doc = ReadFile.indexFile(f);
                            indexWriter.addDocument(doc);
                        }
                    }
                }
            }
        }
    }

    /**
     * Term是搜索的最小单位，代表某个 Field 中的一个关键词，如：<title, lucene> new Term( "title",
     * "lucene" ); new Term( "id", "5" ); new Term( "id", UUID );
     *
     * @param term
     */
    public
 
void
 deleteIndex(Term term) {
        try
 {
            indexWriter.deleteDocuments(term);
        } catch
 (Exception e) {
            throw
 
new
 RuntimeException(e);
        } finally
 {
            try
 {
                indexWriter.close();
            } catch
 (Exception e) {
                e.printStackTrace();
            }
        }
    }

    /**
     * 更新索引 indexWriter.deleteDocuments(term); indexWriter.addDocument(doc);
     *
     * @param term
     * @param doc
     */
    public
 
void
 updateIndex(Term term, Document doc) {
        try
 {
            indexWriter.updateDocument(term, doc);
        } catch
 (Exception e) {
            throw
 
new
 RuntimeException(e);
        } finally
 {
            try
 {
                indexWriter.close();
            } catch
 (Exception e) {
                e.printStackTrace();
            }
        }
    }

    /**
     * 查询 totalPage = recordCount / pageSize; if (recordCount % pageSize &gt; 0)
     * totalPage++;
     *
     * @param queryString
     * @param firstResult
     * @param maxResults
     * @return
     */
    public
 QueryResult search(String queryString, 
int
 firstResult,
            int
 maxResults) {
        try
 {
            // 1，把要搜索的文本解析为 Query
            String[] fields = { "name"
, 
"content"
 };
            Map<String, Float> boosts = new
 HashMap<String, Float>();
            boosts.put("name"
, 2f);
            boosts.put("content"
, 3f); 
//默认为1.0f
            QueryParser queryParser = new
 MultiFieldQueryParser(fields,
                    Constants.analyzer, boosts);
            Query query = queryParser.parse(queryString);
//          Query query = IKQueryParser.parse("content", queryString);
            Date start = new
 Date();
            QueryResult result = search(query, firstResult, maxResults);
            Date end = new
 Date();
            System.out.println("检索完成，用时"
 + (end.getTime() - start.getTime())
                    + "毫秒"
);
            return
 result;
        } catch
 (Exception e) {
            throw
 
new
 RuntimeException(e);
        }
    }

    public
 QueryResult search(Query query, 
int
 firstResult, 
int
 maxResults) {
        IndexSearcher indexSearcher = null
;
        try
 {
            // 2，进行查询
            indexSearcher = new
 IndexSearcher(Constants.INDEX_STORE_PATH);
            Filter filter = new
 RangeFilter(
"size"
,
                    NumberTools.longToString(0
), NumberTools
                            .longToString(1000000
), 
true
, 
true
);
            // 排序
            Sort sort = new
 Sort();
            sort.setSort(new
 SortField(
"size"
)); 
// 默认为升序
            // sort.setSort(new SortField("size", true));
            TopDocs topDocs = indexSearcher.search(query, filter, 10000
, sort);
            int
 recordCount = topDocs.totalHits;
            List<Document> recordList = new
 ArrayList<Document>();
            // 准备高亮器
            Formatter formatter = new
 SimpleHTMLFormatter(
"<font color='red'>"
,
                    "</font>"
);
            Scorer scorer = new
 QueryScorer(query);
            Highlighter highlighter = new
 Highlighter(formatter, scorer);
            Fragmenter fragmenter = new
 SimpleFragmenter(
50
);
            highlighter.setTextFragmenter(fragmenter);
            // 3，取出当前页的数据
            int
 end = Math.min(firstResult + maxResults, topDocs.totalHits);
            for
 (
int
 i = firstResult; i < end; i++) {
                ScoreDoc scoreDoc = topDocs.scoreDocs[i];
                int
 docSn = scoreDoc.doc; 
// 文档内部编号
                Document doc = indexSearcher.doc(docSn); // 根据编号取出相应的文档
                // 高亮 返回高亮后的结果，如果当前属性值中没有出现关键字，会返回 null
                String hc = highlighter.getBestFragment(Constants.analyzer,
                        "content"
, doc.get(
"content"
));
                if
 (hc == 
null
) {
                    String content = doc.get("content"
);
                    int
 endIndex = Math.min(
50
, content.length());
                    hc = content.substring(0
, endIndex);
// 最多前50个字符
                }
                doc.getField("content"
).setValue(hc);
                recordList.add(doc);
            }
            // 返回结果
            return
 
new
 QueryResult(recordCount, recordList);
        } catch
 (Exception e) {
            throw
 
new
 RuntimeException(e);
        } finally
 {
            try
 {
                indexSearcher.close();
            } catch
 (IOException e) {
                e.printStackTrace();
            }
        }
    }

    public
 
void
 close() {
        // 对索引进行优化
        try
 {
            indexWriter.optimize();
            indexWriter.close();
        } catch
 (CorruptIndexException e) {
            e.printStackTrace();
        } catch
 (IOException e) {
            e.printStackTrace();
        }
    }

    public
 
void
 readIndex(String key, String value) {

        IndexReader reader;
        try
 {
//          Directory fsDir = FSDirectory.getDirectory(
//                  Constants.INDEX_STORE_PATH, false);
//          if (IndexReader.isLocked(fsDir)) {
//              System.out.println("------unlock-----");
//              IndexReader.unlock(fsDir);
//          }
            reader = IndexReader.open(Constants.INDEX_STORE_PATH);
            for
 (
int
 i = 
0
; i < reader.numDocs(); i++)
//          System.out.println(reader.document(i));
            System.out.println("版本："
 + reader.getVersion());
            System.out.println("索引内的文档数量："
 + reader.numDocs());
            Term term = new
 Term(key, value);
            TermDocs docs = reader.termDocs(term);
            IndexSearcher indexSearcher = null
;
            indexSearcher = new
 IndexSearcher(Constants.INDEX_STORE_PATH);
            while
 (docs.next()) {
                int
 docSn = docs.doc(); 
// 文档内部编号
                Document doc = indexSearcher.doc(docSn); // 根据编号取出相应的文档
                System.out.println("文档路径 "
 + doc.get(
"path"
));
                System.out.println("含有所查找的 "
 + term + 
"的Document的编号为: "
+ docs.doc());
                System.out.println("Term在文档中的出现 "
 + docs.freq()+
" 次"
);
            }
        } catch
 (CorruptIndexException e) {
            e.printStackTrace();
        } catch
 (IOException e) {
            e.printStackTrace();
        }
    }
}

public class IndexDao {

	public IndexDao() {
		try {
			indexWriter = new IndexWriter(Constants.INDEX_STORE_PATH,
					Constants.analyzer, MaxFieldLength.LIMITED);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
	public IndexDao(Directory dir) {
		try {
			indexWriter = new IndexWriter(dir,Constants.analyzer,MaxFieldLength.LIMITED);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
	public IndexDao(boolean isCreate) {
		try {
			indexWriter = new IndexWriter(Constants.INDEX_STORE_PATH,Constants.analyzer, isCreate,MaxFieldLength.LIMITED);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	// 索引器
	private IndexWriter indexWriter = null;

	/**
	 * 添加/创建索引
	 * 
	 * @param folder
	 * @throws IOException
	 * @throws CorruptIndexException
	 */
	public void saveIndex(File folder, String[] unIndeies)
			throws CorruptIndexException, IOException {
		if (folder.isDirectory()) {
			String[] files = folder.list();
			for (int i = 0; i < files.length; i++) {
				File f = new File(folder, files[i]);
				if (!f.isHidden()) {
					if (f.isDirectory()) {
						saveIndex(f, unIndeies);// ② 递归
					}
					String fileTyep = ReadFile.validateFile(f);
					for (int j = 0; j < unIndeies.length; j++) {
						if (fileTyep.equalsIgnoreCase(unIndeies[j])) {
							System.out.println("正在建立索引 : " + f.getName() + "");
							Document doc = ReadFile.indexFile(f);
							indexWriter.addDocument(doc);
						}
					}
				}
			}
		}
	}

	/**
	 * Term是搜索的最小单位，代表某个 Field 中的一个关键词，如：<title, lucene> new Term( "title",
	 * "lucene" ); new Term( "id", "5" ); new Term( "id", UUID );
	 * 
	 * @param term
	 */
	public void deleteIndex(Term term) {
		try {
			indexWriter.deleteDocuments(term);
		} catch (Exception e) {
			throw new RuntimeException(e);
		} finally {
			try {
				indexWriter.close();
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
	}

	/**
	 * 更新索引 indexWriter.deleteDocuments(term); indexWriter.addDocument(doc);
	 * 
	 * @param term
	 * @param doc
	 */
	public void updateIndex(Term term, Document doc) {
		try {
			indexWriter.updateDocument(term, doc);
		} catch (Exception e) {
			throw new RuntimeException(e);
		} finally {
			try {
				indexWriter.close();
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
	}

	/**
	 * 查询 totalPage = recordCount / pageSize; if (recordCount % pageSize &gt; 0)
	 * totalPage++;
	 * 
	 * @param queryString
	 * @param firstResult
	 * @param maxResults
	 * @return
	 */
	public QueryResult search(String queryString, int firstResult,
			int maxResults) {
		try {
			// 1，把要搜索的文本解析为 Query
			String[] fields = { "name", "content" };
			Map<String, Float> boosts = new HashMap<String, Float>();
			boosts.put("name", 2f);
			boosts.put("content", 3f); //默认为1.0f
			QueryParser queryParser = new MultiFieldQueryParser(fields,
					Constants.analyzer, boosts);
			Query query = queryParser.parse(queryString);
//			Query query = IKQueryParser.parse("content", queryString);
			Date start = new Date();
			QueryResult result = search(query, firstResult, maxResults);
			Date end = new Date();
			System.out.println("检索完成，用时" + (end.getTime() - start.getTime())
					+ "毫秒");
			return result;
		} catch (Exception e) {
			throw new RuntimeException(e);
		}
	}

	public QueryResult search(Query query, int firstResult, int maxResults) {
		IndexSearcher indexSearcher = null;
		try {
			// 2，进行查询
			indexSearcher = new IndexSearcher(Constants.INDEX_STORE_PATH);
			Filter filter = new RangeFilter("size",
					NumberTools.longToString(0), NumberTools
							.longToString(1000000), true, true);
			// 排序
			Sort sort = new Sort();
			sort.setSort(new SortField("size")); // 默认为升序
			// sort.setSort(new SortField("size", true));
			TopDocs topDocs = indexSearcher.search(query, filter, 10000, sort);
			int recordCount = topDocs.totalHits;
			List<Document> recordList = new ArrayList<Document>();
			// 准备高亮器
			Formatter formatter = new SimpleHTMLFormatter("<font color='red'>",
					"</font>");
			Scorer scorer = new QueryScorer(query);
			Highlighter highlighter = new Highlighter(formatter, scorer);
			Fragmenter fragmenter = new SimpleFragmenter(50);
			highlighter.setTextFragmenter(fragmenter);
			// 3，取出当前页的数据
			int end = Math.min(firstResult + maxResults, topDocs.totalHits);
			for (int i = firstResult; i < end; i++) {
				ScoreDoc scoreDoc = topDocs.scoreDocs[i];
				int docSn = scoreDoc.doc; // 文档内部编号
				Document doc = indexSearcher.doc(docSn); // 根据编号取出相应的文档
				// 高亮 返回高亮后的结果，如果当前属性值中没有出现关键字，会返回 null
				String hc = highlighter.getBestFragment(Constants.analyzer,
						"content", doc.get("content"));
				if (hc == null) {
					String content = doc.get("content");
					int endIndex = Math.min(50, content.length());
					hc = content.substring(0, endIndex);// 最多前50个字符
				}
				doc.getField("content").setValue(hc);
				recordList.add(doc);
			}
			// 返回结果
			return new QueryResult(recordCount, recordList);
		} catch (Exception e) {
			throw new RuntimeException(e);
		} finally {
			try {
				indexSearcher.close();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}

	public void close() {
		// 对索引进行优化
		try {
			indexWriter.optimize();
			indexWriter.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

	public void readIndex(String key, String value) {
		
		IndexReader reader;
		try {
//			Directory fsDir = FSDirectory.getDirectory(
//					Constants.INDEX_STORE_PATH, false);
//			if (IndexReader.isLocked(fsDir)) {
//				System.out.println("------unlock-----");
//				IndexReader.unlock(fsDir);
//			}
			reader = IndexReader.open(Constants.INDEX_STORE_PATH);
			for (int i = 0; i < reader.numDocs(); i++)
//		    System.out.println(reader.document(i));
		    System.out.println("版本：" + reader.getVersion());
			System.out.println("索引内的文档数量：" + reader.numDocs());
			Term term = new Term(key, value);
			TermDocs docs = reader.termDocs(term);
			IndexSearcher indexSearcher = null;
			indexSearcher = new IndexSearcher(Constants.INDEX_STORE_PATH);
			while (docs.next()) {
				int docSn = docs.doc(); // 文档内部编号
				Document doc = indexSearcher.doc(docSn); // 根据编号取出相应的文档
				System.out.println("文档路径 " + doc.get("path"));
				System.out.println("含有所查找的 " + term + "的Document的编号为: "+ docs.doc());
				System.out.println("Term在文档中的出现 " + docs.freq()+" 次");
			}
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
}

读取文件工具类：

public
 
class
 ReadFile {

    public
 
static
 String readWord(File f) {
        StringBuffer content = new
 StringBuffer(
""
);
// 文档内容
        try
 {
             HWPFDocument doc = new
 HWPFDocument(
new
 FileInputStream(f));
             Range range = doc.getRange();
             int
 paragraphCount = range.numParagraphs();
// 段落
             for
 (
int
 i = 
0
; i < paragraphCount; i++) {
// 遍历段落读取数据
             Paragraph pp = range.getParagraph(i);
             content.append(pp.text());
             }
//           System.out.println("-------word--------"+content.toString());
        } catch
 (Exception e) {
            System.out.println("建立索引出错 : "
 + f.getAbsolutePath() + 
""
);
            e.printStackTrace();
        }
        return
 content.toString().trim();
    }

    public
 
static
 String readPdf(File f){
        StringBuffer content = new
 StringBuffer(
""
);
// 文档内容
        PDDocument pdfDocument = null
;
        try
 {
            if
(f.length()>
10048576
){
                DecimalFormat df = new
 DecimalFormat(
"#.00"
);
                System.out.println("---------------------文件大小------"
+df.format((
double
) f.length() / 
1048576
) + 
"M"
);
                return
 f.getName();
            }
            FileInputStream fis = new
 FileInputStream(f);
            PDFTextStripper stripper = new
 PDFTextStripper();
            pdfDocument = PDDocument.load(fis);
            if
(pdfDocument.isEncrypted()){
                return
 f.getName();
            }

            StringWriter writer = new
 StringWriter();
            stripper.writeText(pdfDocument, writer);
            content.append(writer.getBuffer().toString());
            fis.close();
        } catch
 (IOException e) {
            System.out.println("建立索引出错 : "
 + f.getAbsolutePath() + 
""
);
            System.err.println("IOException="
 + e);
            //System.exit(1);
        } finally
 {
            if
 (pdfDocument != 
null
) {
                // System.err.println("Closing document " + f + "...");
                org.pdfbox.cos.COSDocument cos = pdfDocument.getDocument();
                try
 {
                    cos.close();
                    // System.err.println("Closed " + cos);
                    pdfDocument.close();
                } catch
 (IOException e) {
                    System.out.println("建立索引出错 : "
 + f.getAbsolutePath() + 
""
);
                    e.printStackTrace();
                }
            }
        }
//       System.out.println("-------pdf--------"+content.toString());
        return
 content.toString().trim();
    }

    public
 
static
 String readHtml(File f) {
        StringBuffer content = new
 StringBuffer(
""
);
        FileInputStream fis = null
;
        try
 {
            fis = new
 FileInputStream(f);
            // 读取页面 这里的字符编码要注意，要对上html头文件的一致，否则会出乱码
            BufferedReader reader = new
 BufferedReader(
new
 InputStreamReader(fis, 
"gb2312"
));
            String line = null
;
            while
 ((line = reader.readLine()) != 
null
) {
                content.append(line + "\n"
);
            }
            reader.close();
        } catch
 (Exception e) {
            System.out.println("建立索引出错 : "
 + f.getAbsolutePath() + 
""
);
            e.printStackTrace();
        }
        String contentString = content.toString();
//      System.out.println("---------htm索引----"+contentString);
        return
 contentString;
    }

    public
 
static
 String readTxt(File f) {
        StringBuffer content = new
 StringBuffer(
""
);
        try
 {
            BufferedReader reader = new
 BufferedReader(
new
 InputStreamReader(
                    new
 FileInputStream(f)));
            for
 (String line = 
null
; (line = reader.readLine()) != 
null
;) {
                content.append(line).append("\n"
);
            }
        } catch
 (IOException e) {
            System.out.println("建立索引出错 : "
 + f.getAbsolutePath() + 
""
);
            e.printStackTrace();
        }
        return
 content.toString().trim();
    }

    public
 
static
 String readExcel(File f,String fileType){
        StringBuffer content = new
 StringBuffer(
""
);
            try
{
                ExcelReader er=new
 ExcelReader(f,fileType);
                String line=er.readLine();
                content.append(line).append("\n"
);
                while
(line!=
null
){
                    line=er.readLine();
                    content.append(line).append("\n"
);
                }
                er.close();
            }catch
(Exception e){
                System.out.println("建立索引出错 : "
 + f.getAbsolutePath() + 
""
);
                e.printStackTrace();
            }
            return
 content.toString();
    }

    public
 
static
 String validateFile(File f) {
        String fileType = "otherType"
;
        String fileName = f.getName();
        if
 (fileName.lastIndexOf(
'.'
) == -
1
) {
            fileType = "dir"
;
            return
 fileType;
        }
        fileName = fileName.substring(fileName.lastIndexOf('.'
) + 
1
, fileName
                .length());

        int
 i = 
0
;
        String [] extension=Constants.EXTENSION;
        for
 (i = 
0
; i < extension.length; i++) {
            if
 (fileName.equalsIgnoreCase(extension[i])) {
                fileType = extension[i];
                break
;
            }
        }
        return
 fileType;
    }

    public
 
static
 Document indexFile(File f) {
        Document doc = new
 Document();
        try
 {
            doc.add(new
 Field(
"name"
, f.getName(), Store.YES, Index.ANALYZED));
            doc.add(new
 Field(
"size"
, NumberTools.longToString(f.length()),
                    Store.YES, Index.NOT_ANALYZED));
            doc.add(new
 Field(
"path"
, f.getAbsolutePath(), Store.YES,
                    Index.NOT_ANALYZED));
            String fileType = validateFile(f);
            if
 (fileType.equals(
"txt"
)) {
                doc.add(new
 Field(
"content"
, ReadFile.readTxt(f), Store.YES,
                        Index.ANALYZED));
            } else
 
if
 (fileType.equals(
"pdf"
)) {
                doc.add(new
 Field(
"content"
, ReadFile.readPdf(f), Store.YES,
                        Index.ANALYZED));
            } else
 
if
 (fileType.equals(
"doc"
)) {
                doc.add(new
 Field(
"content"
, ReadFile.readWord(f), Store.YES,
                        Index.ANALYZED));
            } else
 
if
 (fileType.equals(
"htm"
)) {
                doc.add(new
 Field(
"content"
, ReadFile.readHtml(f), Store.YES,
                        Index.ANALYZED));
            } else
 
if
(fileType.equals(
"xls"
)){
                doc.add(new
 Field(
"content"
, ReadFile.readExcel(f, fileType), Store.YES,
                        Index.ANALYZED));
            }else
 {
                doc.add(new
 Field(
"content"
, f.getName(), Store.YES, Index.ANALYZED));
            }
        } catch
 (Exception e) {
            System.out.println("建立索引出错 : "
 + f.getAbsolutePath() + 
""
);
            e.printStackTrace();
        }
        return
 doc;
    }
}

public class ReadFile {

	public static String readWord(File f) {
		StringBuffer content = new StringBuffer("");// 文档内容
		try {
			 HWPFDocument doc = new HWPFDocument(new FileInputStream(f));
			 Range range = doc.getRange();
			 int paragraphCount = range.numParagraphs();// 段落
			 for (int i = 0; i < paragraphCount; i++) {// 遍历段落读取数据
			 Paragraph pp = range.getParagraph(i);
			 content.append(pp.text());
			 }
//			 System.out.println("-------word--------"+content.toString());
		} catch (Exception e) {
			System.out.println("建立索引出错 : " + f.getAbsolutePath() + "");
			e.printStackTrace();
		}
		return content.toString().trim();
	}

	public static String readPdf(File f){
		StringBuffer content = new StringBuffer("");// 文档内容
		PDDocument pdfDocument = null;
		try {
			if(f.length()>10048576){
				DecimalFormat df = new DecimalFormat("#.00");
				System.out.println("---------------------文件大小------"+df.format((double) f.length() / 1048576) + "M");
				return f.getName();
			}
			FileInputStream fis = new FileInputStream(f);
			PDFTextStripper stripper = new PDFTextStripper();
			pdfDocument = PDDocument.load(fis);
			if(pdfDocument.isEncrypted()){
				return f.getName();
			}
			
			StringWriter writer = new StringWriter();
			stripper.writeText(pdfDocument, writer);
			content.append(writer.getBuffer().toString());
			fis.close();
		} catch (IOException e) {
			System.out.println("建立索引出错 : " + f.getAbsolutePath() + "");
			System.err.println("IOException=" + e);
			//System.exit(1);
		} finally {
			if (pdfDocument != null) {
				// System.err.println("Closing document " + f + "...");
				org.pdfbox.cos.COSDocument cos = pdfDocument.getDocument();
				try {
					cos.close();
					// System.err.println("Closed " + cos);
					pdfDocument.close();
				} catch (IOException e) {
					System.out.println("建立索引出错 : " + f.getAbsolutePath() + "");
					e.printStackTrace();
				}
			}
		}
//		 System.out.println("-------pdf--------"+content.toString());
		return content.toString().trim();
	}
	
	public static String readHtml(File f) {
		StringBuffer content = new StringBuffer("");
		FileInputStream fis = null;
		try {
			fis = new FileInputStream(f);
			// 读取页面 这里的字符编码要注意，要对上html头文件的一致，否则会出乱码
			BufferedReader reader = new BufferedReader(new InputStreamReader(fis, "gb2312"));
			String line = null;
			while ((line = reader.readLine()) != null) {
				content.append(line + "\n");
			}
			reader.close();
		} catch (Exception e) {
			System.out.println("建立索引出错 : " + f.getAbsolutePath() + "");
			e.printStackTrace();
		}
		String contentString = content.toString();
//		System.out.println("---------htm索引----"+contentString);
		return contentString;
	}

	public static String readTxt(File f) {
		StringBuffer content = new StringBuffer("");
		try {
			BufferedReader reader = new BufferedReader(new InputStreamReader(
					new FileInputStream(f)));
			for (String line = null; (line = reader.readLine()) != null;) {
				content.append(line).append("\n");
			}
		} catch (IOException e) {
			System.out.println("建立索引出错 : " + f.getAbsolutePath() + "");
			e.printStackTrace();
		}
		return content.toString().trim();
	}
	
	public static String readExcel(File f,String fileType){
		StringBuffer content = new StringBuffer("");
			try{
				ExcelReader er=new ExcelReader(f,fileType);	
				String line=er.readLine();
				content.append(line).append("\n");
				while(line!=null){
					line=er.readLine();
					content.append(line).append("\n");
				}
				er.close();
			}catch(Exception e){
				System.out.println("建立索引出错 : " + f.getAbsolutePath() + "");
				e.printStackTrace();
			}
			return content.toString();
	}

	public static String validateFile(File f) {
		String fileType = "otherType";
		String fileName = f.getName();
		if (fileName.lastIndexOf('.') == -1) {
			fileType = "dir";
			return fileType;
		}
		fileName = fileName.substring(fileName.lastIndexOf('.') + 1, fileName
				.length());
		
		int i = 0;
		String [] extension=Constants.EXTENSION;
		for (i = 0; i < extension.length; i++) {
			if (fileName.equalsIgnoreCase(extension[i])) {
				fileType = extension[i];
				break;
			}
		}
		return fileType;
	}

	public static Document indexFile(File f) {
		Document doc = new Document();
		try {
			doc.add(new Field("name", f.getName(), Store.YES, Index.ANALYZED));
			doc.add(new Field("size", NumberTools.longToString(f.length()),
					Store.YES, Index.NOT_ANALYZED));
			doc.add(new Field("path", f.getAbsolutePath(), Store.YES,
					Index.NOT_ANALYZED));
			String fileType = validateFile(f);
			if (fileType.equals("txt")) {
				doc.add(new Field("content", ReadFile.readTxt(f), Store.YES,
						Index.ANALYZED));
			} else if (fileType.equals("pdf")) {
				doc.add(new Field("content", ReadFile.readPdf(f), Store.YES,
						Index.ANALYZED));
			} else if (fileType.equals("doc")) {
				doc.add(new Field("content", ReadFile.readWord(f), Store.YES,
						Index.ANALYZED));
			} else if (fileType.equals("htm")) {
				doc.add(new Field("content", ReadFile.readHtml(f), Store.YES,
						Index.ANALYZED));
			} else if(fileType.equals("xls")){
				doc.add(new Field("content", ReadFile.readExcel(f, fileType), Store.YES,
						Index.ANALYZED));
			}else {
				doc.add(new Field("content", f.getName(), Store.YES, Index.ANALYZED));
			}
		} catch (Exception e) {
			System.out.println("建立索引出错 : " + f.getAbsolutePath() + "");
			e.printStackTrace();
		}
		return doc;
	}
}

 

public
 
class
 ExcelReader {
    // 创建文件输入流
    private
 BufferedReader reader = 
null
;

    // 文件类型
    private
 String filetype;

    // 文件二进制输入流
    private
 InputStream is = 
null
;

    // 当前的Sheet
    private
 
int
 currSheet;

    // 当前位置
    private
 
int
 currPosition;

    // Sheet数量
    private
 
int
 numOfSheets;

    // HSSFWorkbook
    HSSFWorkbook workbook = null
;

    // 设置Cell之间以空格分割
    private
 
static
 String EXCEL_LINE_DELIMITER = 
" "
;

    // 设置最大列数
//  private static int MAX_EXCEL_COLUMNS = 64;

    // 构造函数创建一个ExcelReader
    public

  


  
    
    分享到：
      
      
    
  

  
    
      SQL基础实例（学生课程系统）
      |
      lucene 单机 io性能提高策略
    
  
  
    
      2010-11-17 16:20
      浏览 868
      评论(0)
      
      
      分类:编程语言      
      查看更多