JAVA POI处理WORD

来源：互联网发布：小学生学编程视频教程编辑：程序博客网时间：2024/04/26 13:07

JAVA POI处理WORD

转载：http://w26.iteye.com/blog/974442

JavaApacheSVN

关键字：POI WORD HWPF

WORD文本组成：文本、图、表和宏。HWPF主要关注文本。

1.
File Information Block (FIB): 文件信息块

2.
文本提取 text extraction
基本文本提取： org.apache.poi.hwpf.extractor.WordExtractor
getText() ： TEXT
getParagraphText() ： TEXT
getTextFromPieces() ： YMMV

特殊文本提取： org.apache.poi.hwpf.HWPFDocument
getRange()

输入流： HWPFDocument

3.
页眉和页脚：
a. 创建 org.apache.poi.hwpf.HWPFDocument
b. 创建 org.apache.poi.hwpf.usermodel.HeaderStores

4.
插入文本
Range 范围 Paragraph 段落 CharacterRun ？
insertBefore()
insertAfter()
delete()

5.
读取WORD文档
a. 首先是 File Information Block (FIB)：它指定文件的大小，位置，文本开始位置。
b. 开始读取文本块
non-unicode 块与 unicode 块的偏移值需要通过掩码来区分。

6.
文本样式
a. 段落样式
b. 字条样式

7.
官方单元测试代码
http://svn.apache.org/viewvc/poi/trunk/src/scratchpad/testcases/org/apache/poi/hwpf/

8.
示例
本程序主要是提取WORD的表格到EXCEL.
运行方法: wordTable2Excel．需要c:\test.doc存在．

WordTable.java

Java代码

package cn.bisoft.java.poi;
import java.io.FileInputStream;
import org.apache.poi.hwpf.HWPFDocument;
import org.junit.Test;
public class WordTable {
/**
* 转换WORD中的表格内容到EXCEL
*/
@Test
public void wordTable2Excel()
{
String docName = "c:\\test.doc";
/** 1. 读取WORD表格内容 */
HWPFDocument doc = null;
try {
doc = new HWPFDocument(new FileInputStream(docName));
} catch (Exception e) {
e.printStackTrace();
}
String text = doc.getRange().text();
/** 2. 放置分隔符:将不可见字符使用空格(32)替换 */
char[] charArray = text.toCharArray();
for(int i = 0; i < charArray.length; i++)
{
if (charArray[i] <= 31)
{
charArray[i] = 32;
}
}
text = String.valueOf(charArray);
/** 3. 将内容用空格切片 */
String[] textArray = text.trim().replaceAll("[ ]+", " ").split(" ");
/** 4.将数据加载到WORD表格模型对象 */
WordTableModel wtm = new WordTableModel();
for(int i = 0; i < textArray.length; i++)
{
String s = textArray[i].trim();
// 行首单元格正则匹配
if (s.matches("^[a-zA-Z]$") || s.matches("^[0-9]{2}$") || s.matches("^[0-9]{3}$") || s.matches("^[0-9]{4}$"))
{
// 换行
wtm.resetMap();
}
// 加载数据, 每行内容按顺序加载到相应单元格
wtm.autoMap(s.trim());
}
// 结束加载
wtm.endAutoMap();
/** 5. 保存到EXCEL文件*/
wtm.save2Excel("c:\\test.xls", "sheet1");
}
}

package cn.bisoft.java.poi;import java.io.FileInputStream;import org.apache.poi.hwpf.HWPFDocument;import org.junit.Test;public class WordTable {/** * 转换WORD中的表格内容到EXCEL */@Testpublic void wordTable2Excel(){String docName = "c:\\test.doc";/** 1. 读取WORD表格内容 */HWPFDocument doc = null;try {doc = new HWPFDocument(new FileInputStream(docName));} catch (Exception e) {e.printStackTrace();} String text = doc.getRange().text();/** 2. 放置分隔符:将不可见字符使用空格(32)替换 */char[] charArray = text.toCharArray();for(int i = 0; i < charArray.length; i++){if (charArray[i] <= 31){charArray[i] = 32;}}text = String.valueOf(charArray);/** 3. 将内容用空格切片 */String[] textArray = text.trim().replaceAll("[ ]+", " ").split(" ");/** 4.将数据加载到WORD表格模型对象 */WordTableModel wtm = new WordTableModel();for(int i = 0; i < textArray.length; i++){String s = textArray[i].trim();// 行首单元格正则匹配if (s.matches("^[a-zA-Z]$") || s.matches("^[0-9]{2}$") || s.matches("^[0-9]{3}$") || s.matches("^[0-9]{4}$")){// 换行 wtm.resetMap();}// 加载数据, 每行内容按顺序加载 到相应单元格wtm.autoMap(s.trim());}// 结束加载wtm.endAutoMap();/** 5. 保存到EXCEL文件*/wtm.save2Excel("c:\\test.xls", "sheet1");}}

WordTableModel

Java代码

package cn.bisoft.java.poi;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import cn.bisoft.java.poi.util.ExcelUtil;
public class WordTableModel {
public static String SINGLE_WORD = "^[a-z][A-Z]$";
public static String SINGLE_NUMBER = "^[0-9]$";
public static String SINGLE_VAR = "^[0-9a-zA-Z_]$";
public static String PSTN = "^[0-9]{4}[- ]?[0-9]{7}$"; // 固定号码
public static String MSISDN = "^1[0-9]{10}$"; // 移动号码
public static String IDCARD = "(^\\d{15}$)|(^\\d{17}([0-9]|[Xx])$)"; //身份证
public static String EMAIL = "^\\w{3,}@\\w.{3,}\\w{2,}$"; // 电子邮件
private String[][] table = new String[100000][1000];
private int curColumn = 0;
private int curRow = 0;
public void autoMap(String value)
{
table[curRow][curColumn] = value;
curColumn++;
}
public void resetMap()
{
curColumn = 0;
curRow++;
}
public void endAutoMap()
{
curRow++;
}
/**
* @param fileName
*/
public void save2Excel(String fileName, String sheetName)
{
Sheet sheet = ExcelUtil.createSheet(fileName, sheetName);
for(int i = 0; i < curRow; i++)
{
Row row = sheet.createRow(i);
for(int j = 0; j < curColumn; j++)
{
Cell cell = row.createCell(j);
cell.setCellValue(table[i][j]);
}
}
ExcelUtil.saveSheet(fileName, sheet);
}
}

package cn.bisoft.java.poi;import org.apache.poi.ss.usermodel.Cell;import org.apache.poi.ss.usermodel.Row;import org.apache.poi.ss.usermodel.Sheet;import cn.bisoft.java.poi.util.ExcelUtil;public class WordTableModel {public static  String SINGLE_WORD = "^[a-z][A-Z]$";public static  String SINGLE_NUMBER = "^[0-9]$";public static  String SINGLE_VAR = "^[0-9a-zA-Z_]$";public static  String PSTN = "^[0-9]{4}[- ]?[0-9]{7}$"; // 固定号码public static  String MSISDN = "^1[0-9]{10}$"; // 移动号码public static  String IDCARD = "(^\\d{15}$)|(^\\d{17}([0-9]|[Xx])$)"; //身份证public static  String EMAIL = "^\\w{3,}@\\w.{3,}\\w{2,}$"; // 电子邮件private String[][] table = new String[100000][1000];private int curColumn = 0;private int curRow = 0;public void autoMap(String value){table[curRow][curColumn] = value;curColumn++;}public void resetMap(){curColumn = 0;curRow++;}public void endAutoMap(){curRow++;}/** * @param fileName */public void save2Excel(String fileName, String sheetName){Sheet sheet = ExcelUtil.createSheet(fileName, sheetName);for(int i = 0; i < curRow; i++){Row row = sheet.createRow(i);for(int j = 0; j < curColumn; j++){Cell cell = row.createCell(j);cell.setCellValue(table[i][j]);}}ExcelUtil.saveSheet(fileName, sheet);}}

ExcelUtil

Java代码

package cn.bisoft.java.poi.util;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
public class ExcelUtil {
public static Sheet createSheet(String fileName, String sheetName)
{
Workbook wb = new HSSFWorkbook();
FileOutputStream fileOut = null;
Sheet sheet = null;
try {
fileOut = new FileOutputStream(fileName);
sheet = wb.createSheet(sheetName);
wb.write(fileOut);
fileOut.close();
} catch (FileNotFoundException e1) {
e1.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return sheet;
}
public static void saveSheet(String fileName, Sheet sheet)
{
FileOutputStream fileOut = null;
try {
fileOut = new FileOutputStream(fileName);
sheet.getWorkbook().write(fileOut);
fileOut.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}