package com.test;
import com.spire.doc.Document;
import com.spire.doc.Section;
import com.spire.doc.documents.Paragraph;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
public class Main
{
/**
* 获取文件下所有的文件路径
*
* @param path
* @param listFileName
*/
public static void getAllFileName(String path, ArrayList<String> listFileName) {
File file = new File(path);
File [] files = file.listFiles();
String [] names = file.list();
if(names != null) {
String[] completNames = new String[names.length];
for (int i = 0; i < names.length; i++) {
completNames[i] = path + "\\" + names[i];
}
listFileName.addAll(Arrays.asList(completNames));
}
for(File a:files){
if(a.isDirectory()){
getAllFileName(a.getAbsolutePath()+"\\", listFileName);
}
}
}
/**
* 获取word文档中的文本内容
*
* @param filePath 文件路径
* @return word文档中的文本内容
*/
private static String getDocText(String filePath) {
Document document = new Document();
document.loadFromFile(filePath);
//获取文档中的文本保存为String
String text = document.getText();
int len = text.length();
int firstIndex = text.indexOf("JAVA");
if(firstIndex != -1){
return text.substring(text.indexOf("JAVA")+5, len);
}else{
return text;
}
}
public static void writeIntoFile(String content, String txtFileName ) {
FileWriter fWriter= null;
try {
fWriter = new FileWriter(txtFileName,true);
} catch (IOException e) {
e.printStackTrace();
}
try {
fWriter.write(content);
}catch(IOException ex){
ex.printStackTrace();
}finally{
try{
fWriter.flush();
fWriter.close();
} catch (IOException ex) {
ex.printStackTrace();
}
}
}
public static void main(String args[] ) throws IOException {
ArrayList<String> listFileNames = new ArrayList<String>();
getAllFileName("F:\\data\\401-500", listFileNames);
for(String name:listFileNames){
if( name.indexOf(".doc")!=-1 || name.indexOf(".docx")!=-1);
String content = getDocText(name);
String name_id = name.substring(name.indexOf(".")-3, name.indexOf("."));
name_id = name_id.replaceFirst("^0*", "");
String sql = "insert into pest.patient_report(name, report) values('"+ name_id + "','" + content + "');\n";
writeIntoFile(sql,"F:\\read_word_sql");
}
}
}
java读取doc
最新推荐文章于 2024-04-18 11:48:34 发布