lucent检索技术之创建索引：使用POI读取txt/word/excel/ppt/pdf内容
在使用lucent检索文档时，必须先为各文档创建索引。索引的创建即读出文档信息（如文档名称、上传时间、文档内容等），然后再经过分词建索引写入到索引文件里。这里主要是总结下读取各类文档内容这一步。
一、之前做过一个小工具也涉及到读取word和excel内容，采用的是com组件的方式来读取。即导入COM库，引入命名空间（using Microsoft.Office.Interop.Word;using Microsoft.Office.Interop.Excel;），然后读代码如下：
读取word
public string readWORD(object filepath)
{
string filename = Convert.ToString(filepath);
Microsoft.Office.Interop.Word.Application wordapp = new Microsoft.Office.Interop.Word.Application();
object isreadonly = true;
object nullobj = System.Reflection.Missing.Value;
object missingValue = Type.Missing;
object miss = System.Reflection.Missing.Value;
object saveChanges = WdSaveOptions.wdDoNotSaveChanges;
Microsoft.Office.Interop.Word._Document doc = wordapp.Documents.Open(ref filename, ref nullobj, ref isreadonly);
string content = doc.Content.Text;
doc.Close(ref saveChanges, ref missingValue, ref missingValue);
wordapp.Quit(ref saveChanges, ref miss, ref miss);
wordapp = null;
return content;
}
读取excel
用COM读取excel代码，首先是启动excel程序打开工作表，然后取得工作表名，再读取单元格内容，比较繁琐，代码略。
另外，也可以采用OleDB读取EXCEL文件，即把excel作为一个数据库，读出内容返回datatable，代码：
public DataSet ExcelToDS(string Path)
{
string strConn = "Provider=Microsoft.Jet.OLEDB.4.0;" +"Data Source="+ Path +";"+"Extended Properties=Excel 8.0;";
OleDbConnection conn = new OleDbConnection(strConn);
conn.Open();
string strExcel = "";
OleDbDataAdapter myCommand = null;
DataSet ds = null;
strExcel="select * from [sheet1$]";
myCommand = new OleDbDataAdapter(strExcel, strConn);
ds = new DataSet();
myCommand.Fill(ds,"table1");
return ds;
}
对于EXCEL中的表即sheet([sheet1$])如果不是固定的可以使用下面的方法得到
string strConn = "Provider=Microsoft.Jet.OLEDB.4.0;" +"Data Source="+ Path +";"+"Extended Properties=Excel 8.0;";
OleDbConnection conn = new OleDbConnection(strConn);
DataTable schemaTable = objConn.GetOleDbSchemaTable(System.Data.OleDb.OleDbSchemaGuid.Tables,null);
string tableName=schemaTable.Rows[0][2].ToString().Trim();
读取ppt
public string readPPT(object filepath)
{
string file = filepath.ToString();
Microsoft.Office.Interop.PowerPoint.Application pa = new Microsoft.Office.Interop.PowerPoint.Application();
Microsoft.Office.Interop.PowerPoint.Presentation pp = pa.Presentations.Open(file, Microsoft.Office.Core.MsoTriState.msoTrue, Microsoft.Office.Core.MsoTriState.msoFalse, Microsoft.Office.Core.MsoTriState.msoFalse);
string content = "";
foreach (Microsoft.Office.Interop.PowerPoint.Slide slide in pp.Slides)
{
foreach (Microsoft.Office.Interop.PowerPoint.Shape shape in slide.Shapes)
content += shape.TextFrame.TextRange.Text.ToString();
}
pa.Quit();
pp.Close();
pa = null;
return content;
}
采用COM方式读取效率很低，而创建索引只需取得文档内容，也要求要快速高效获得要索引的文件内容。因此，COM读取不适用于创建索引。POI包含了各类文档所需的类，使用时只需添加相应的类，实现代码也简单，更重要的是能快速地取得文档内容。
二、采用POI
（1）首先下载POI包，在解决方案中通过“管理NuGet程序包”工具来下载；也可以到Apache官网下载。
（2）以下是POI读取各文档内容代码(包含读取txt、word、excel、ppt、pdf)。
/// <summary>
/// 读取各类文档内容
/// </summary>
/// <param name="filepath">文档路径</param>
/// <param name="filename">文档名称</param>
/// <returns></returns>
public string textToreader(string filepath, object filename)
{
string content = null;
FileInfo file = new FileInfo(filename.ToString());
switch (file.Extension.ToLower())
{
case ".txt":
content = readTXT(filepath);
break;
case ".doc":
content = readWORD(filepath);
break;
case ".docx":
content = readWORDX(filepath);
break;
case ".xls":
content = readEXCEL(filepath);
break;
case ".xlsx":
content = readEXCELX(filepath);
break;
case ".pdf":
content = readPDF(filepath);
break;
case ".ppt":
content = readPPT(filepath);
break;
}
return content;
}
/// <summary>
/// 读取txt
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public string readTXT(string filepath)
{
StreamReader st = new StreamReader(filepath, Encoding.GetEncoding("gb2312"));
string content = st.ReadToEnd();
return content;
}
/// <summary>
/// 读取word2003
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public string readWORD(string filepath)
{
FileInputStream fs = new FileInputStream(filepath);
HWPFDocument doc = new HWPFDocument(fs);
string content = doc.getDocumentText();
return content;
}
/// <summary>
/// 读取word2007
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public string readWORDX(string filepath)
{
FileInputStream fs = new FileInputStream(filepath);
XWPFDocument XDocument = new XWPFDocument(fs);
XWPFWordExtractor doc = new XWPFWordExtractor(XDocument);
string content = doc.getText();
return content;
}
/// <summary>
/// 读取excel2003
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public string readEXCEL(object filepath)
{
string filename = filepath.ToString();
FileStream fs = new FileStream(filename, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);//读取流
POIFSFileSystem ps = new POIFSFileSystem(fs);
HSSFWorkbook hwb = new HSSFWorkbook(ps);
ExcelExtractor extractor = new ExcelExtractor(hwb);
extractor.FormulasNotResults = true;
extractor.IncludeSheetNames = true;
string content = extractor.Text;
return content;
}
/// <summary>
/// 读取excel2007
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public string readEXCELX(string filepath)
{
//FileStream fs = new FileStream(filepath, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);//读取流
FileInputStream fis = new FileInputStream(filepath);
//POIFSFileSystem ps = new POIFSFileSystem(fs);
XSSFWorkbook hwb = new XSSFWorkbook(fis);
XSSFExcelExtractor extractor = new XSSFExcelExtractor(hwb);
string content = extractor.getText();
return content;
}
/// <summary>
/// 读取pdf
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public string readPDF(string filepath)
{
PDDocument doc = PDDocument.load(filepath);
PDFTextStripper pdfStripper = new PDFTextStripper();
string content = pdfStripper.getText(doc);
doc.close();
return content;
}
/// <summary>
/// 读取ppt2003
/// </summary>
/// <param name="filepath"></param>
/// <returns></returns>
public string readPPT(string filepath)
{
FileInputStream fs = new FileInputStream(filepath);
SlideShow ss = new SlideShow(new HSLFSlideShow(fs));
Slide[] slides = ss.getSlides();// 获得每一张幻灯片
string content = "";
for (int i = 0; i < slides.Length; i++)
{
TextRun[] t = slides[i].getTextRuns();// 为了取得幻灯片的文字内容，建立TextRun
for (int j = 0; j < t.Length; j++)
{
content += t[j].getText();
}
}
return content;
}
注：不同版本的读取对应不同的POI接口程序。
Excel 文件: xls 格式文件对应 POI API 为 HSSF ； xlsx 格式为 office 2007 的文件格式，POI 中对应的API 为XSSF。
Word 文件：doc 格式文件对应的 POI API 为 HWPF； docx 格式为 XWPF。
powerPoint 文件：ppt 格式对应的 POI API 为 HSLF； pptx 格式为 XSLF。
三、使用POITextExtractor类可实现读取office2007兼容以上版本的文档代码：
/// <summary> /// 读取word2007,excel2003/2007,ppt2003/2007 /// </summary> /// <param name="filepath"></param> /// <returns></returns> public string ReadOfficeText(string filepath) { //docx 、pptx 、xlsx、 ppt 、xls FileInputStream fs = new FileInputStream(filepath); POITextExtractor extractor = ExtractorFactory.createExtractor(fs); string text = extractor.getText(); return text; }
但是不知什么原因采用这个方法读取word2003会报错，暂时先用着上面第二点中读取word2003的方法吧。
做一个不断努力，积极向上的goodgirl-mia `(*∩_∩*)′。
