poi操作word 2003/doc

小咪咪 2022-02-15 04:49 660阅读 0赞

### poi操作word 2003/doc ###

*  HWPFDocument中的要素
 *  maven引用
 *  通过WordExtractor读取文本
 *  通过HWPFDocument读文件
 *  通过HWPFDocument写文件

# HWPFDocument中的要素 #

Range 表示一个范围(内容：Section,Paragraph,CharacterRun)
    Section 文档中的一个小节,文档由多个小节组成（内容：Paragraph）
    Paragraph 段落（内容：CharacterRun）
    CharacterRun 具有相同属性的文本
    Table 表格
    TableRow 表格对应的行
    TableCell 表格对应的单元格
    ***Section、Paragraph、CharacterRun和Table都继承自Range***

# maven引用 #

<dependency>
    	<groupId>org.apache.poi</groupId>
    	<artifactId>poi-scratchpad</artifactId>
    	<version>3.17</version>
    </dependency>
    <dependency>
    	<groupId>commons-io</groupId>
    	<artifactId>commons-io</artifactId>
    	<version>2.0</version>
    </dependency>
    <dependency>
    	<groupId>commons-lang</groupId>
    	<artifactId>commons-lang</artifactId>
    	<version>2.0</version>
    </dependency>

# 通过WordExtractor读取文本 #

//读取文本
    InputStream is = new FileInputStream("d://04.doc");
    WordExtractor extractor = new WordExtractor(is);
    String text = extractor.getText();//抓取文本,里面有许多空格和换行
    //抓取文本，提取的结果也可能包含了一些其他的crud比特
    String textFromPieces = extractor.getTextFromPieces();

/** * 输出书签信息 * @param bookmarks */
    private void printBookmarks(Bookmarks bookmarks) { 
    	int count = bookmarks.getBookmarksCount();
    	System.out.println("书签数量：" + count);
    	Bookmark bookmark;
    	for (int i = 0; i < count; i++) { 
    		bookmark = bookmarks.getBookmark(i);
    		System.out.println("书签" + (i + 1) + "的名称是：" + bookmark.getName());
    		System.out.println("开始位置：" + bookmark.getStart());
    		System.out.println("结束位置：" + bookmark.getEnd());
    	}
    }
    
    /** * 输出SummaryInfomation * @param info */
    private void printSummary(SummaryInformation info) { 
    	System.out.println(info.getAuthor());// 作者
    	System.out.println(info.getCharCount());// 字符统计
    	System.out.println(info.getPageCount());// 页数
    	System.out.println(info.getTitle());// 标题
    	System.out.println(info.getSubject());// 主题
    }

# 通过HWPFDocument读文件 #

InputStream is = new FileInputStream("d://04.doc");
    HWPFDocument hwpfDocument = new HWPFDocument(is);
    // 抓取文本，提取的结果也可能包含了一些其他的crud比特
    String text1 = hwpfDocument.getDocumentText();
    System.err.println(text1);
    
    Range range = hwpfDocument.getRange();
    String text2 = range.text();// 抓取文本,里面有许多空格和换行
    System.err.println(text2);

/** * 打印段落 * @param range */
    private void printParagraph(Range range) { 
    	int num = range.numParagraphs();
    	for (int i = 0; i < num; i++) { 
    		Paragraph para = range.getParagraph(i);
    		if (para.isInList()) { 
    			System.out.println("list: " + para.text());
    		}
    	}
    }

/** * 打印小节 * @param range */
    private void printSection(Range range) { 
    	int secNum = range.numSections();
    	System.out.println(secNum);
    	for (int i = 0; i < secNum; i++) { 
    		Section section = range.getSection(i);
    		System.out.println(section.getMarginLeft());
    		System.out.println(section.getMarginRight());
    		System.out.println(section.getMarginTop());
    		System.out.println(section.getMarginBottom());
    		System.out.println(section.getPageHeight());
    		System.out.println(section.text());
    	}
    }

# 通过HWPFDocument写文件 #

public static void main(String[] args) throws IOException { 
    	String wordMouldFile = "d://tmp//module.doc";
    	Map<String, String> replaceMap = new HashMap<String, String>();
    	String outputFile = "d://tmp//导出.doc";
    	replaceMap.put("title1", "标题一");
    	replaceMap.put("content1", "内容一");
    	replaceMap.put("title2", "标题二");
    	replaceMap.put("content2", "内容二");
    	HWPFDocumentUtil hwpfDocumentUtil = new HWPFDocumentUtil(wordMouldFile, replaceMap);
    	hwpfDocumentUtil.exportWord(new File(outputFile));
    	String readWordText = HWPFDocumentUtil.readWordText(outputFile);
    	System.err.println(readWordText);
    }

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI2MjY0MjM3_size_16_color_FFFFFF_t_70]

/** * 模板导出Word文档（2003/doc） * @author Administrator * */
    public class HWPFDocumentUtil { 
    	/** Word文档模板 */
    	private String wordMouldFile;
    	private Map<String, String> replaceMap;
    	public HWPFDocumentUtil(String wordMouldFile, Map<String, String> replaceMap) { 
    		super();
    		this.wordMouldFile = wordMouldFile;
    		this.replaceMap = replaceMap;
    	}
    
    	public static String readWordText(String filename) throws IOException { 
    		if (StringUtils.isBlank(filename)) { 
    			return "";
    		}
    		File file = new File(filename);
    		if (!file.exists()) { 
    			throw new FileNotFoundException(filename);
    		}
    		
    		InputStream is = null;
    		HWPFDocument hwpfDocument = null;
    		try { 
    			is = new FileInputStream(filename);
    			hwpfDocument = new HWPFDocument(is);
    			Range range = hwpfDocument.getRange();
    			String text = range.text();
    			return StringUtils.trimToEmpty(text);
    		} catch (IOException e) { 
    			throw e;
    		} finally { 
    			IOUtils.closeQuietly(is);
    			hwpfDocument.close();
    			hwpfDocument=null;
    		}
    	}
    
    	
    	public void exportWord(File outFile) { 
    		InputStream is = null;
    		HWPFDocument doc = null;
    		OutputStream os = null;
    		try { 
    			is = new FileInputStream(wordMouldFile);
    			doc = new HWPFDocument(is);
    			Range range = doc.getRange();//获取文档内容区域
    			Set<String> keySet = replaceMap.keySet();
    			for(String key : keySet) { 
    				String value = replaceMap.get(key);
    				range.replaceText("$" + key, value);
    			}
    			os = new FileOutputStream(outFile);
    			// 把doc输出到输出流中
    			doc.write(os);
    		} catch (IOException e) { 
    			throw new RuntimeException(e);
    		} finally { 
    			try { 
    				doc.close();
    				doc = null;
    			} catch (IOException e) { 
    				e.printStackTrace();
    			}
    			IOUtils.closeQuietly(is);
    			IOUtils.closeQuietly(os);
    		}
    	}
    	...[get set 忽略]
    }

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI2MjY0MjM3_size_16_color_FFFFFF_t_70]: /images/20220215/14a860b649454bcea4b8041eebb968d9.png