chenxudong
/
electromagnetic-data-new
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

完成了pdf，普通文本和word的解析

This commit is contained in:
chenxudong 2025-01-20 17:32:49 +08:00
parent 799fb336c1
commit a91397ebbf
9 changed files with 236 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
electromagnetic-common/pom.xml
View File

@ -65,6 +65,34 @@
<artifactId>documents4j-transformer-msoffice-word</artifactId>
<version>1.0.3</version>
</dependency>
<!--处理word文档需要的额外的jar包-->
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>4.1.2</version>
</dependency>
<!--处理word文档需要的额外的jar包-->
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml-schemas</artifactId>
<version>4.1.0</version>
</dependency>
<!-- POI-word文件处理需要 -->
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>4.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.24</version>
</dependency>
</dependencies>
</project>

11
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/ExcelParse.java Normal file
View File

@ -0,0 +1,11 @@
package com.electromagnetic.industry.software.common.parse;
import java.io.InputStream;
public class ExcelParse extends FileParse {
@Override
public String parseContent(InputStream stream, String fileType) {
return "";
}
}

18
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/FileParse.java Normal file
View File

@ -0,0 +1,18 @@
package com.electromagnetic.industry.software.common.parse;
import cn.hutool.core.util.IdUtil;
import java.io.File;
import java.io.InputStream;
public abstract class FileParse {
private static String tmpPath = Thread.currentThread().getContextClassLoader().getResource("").getPath();
public abstract String parseContent(InputStream stream, String fileType);
protected String createFileTmpPath(String fileType) {
String uuid = IdUtil.fastSimpleUUID();
return tmpPath + File.separator + uuid + "." + fileType;
}
}

21
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/PdfParse.java Normal file
View File

@ -0,0 +1,21 @@
package com.electromagnetic.industry.software.common.parse;
import com.electromagnetic.industry.software.common.util.OfficeFileUtil;
import lombok.extern.slf4j.Slf4j;
import java.io.InputStream;
@Slf4j
public class PdfParse extends FileParse {
@Override
public String parseContent(InputStream stream, String fileType) {
String res = "";
try {
String fileTmpPath = createFileTmpPath(fileType);
res = OfficeFileUtil.parsePdf(fileTmpPath);
} catch (Exception e) {
log.error("解析pdf文件失败{}", e.getMessage(), e);
}
return res;
}
}

11
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/PptParse.java Normal file
View File

@ -0,0 +1,11 @@
package com.electromagnetic.industry.software.common.parse;
import java.io.InputStream;
public class PptParse extends FileParse {
@Override
public String parseContent(InputStream stream, String fileType) {
return "";
}
}

26
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/TextParse.java Normal file
View File

@ -0,0 +1,26 @@
package com.electromagnetic.industry.software.common.parse;
import cn.hutool.core.io.FileUtil;
import lombok.extern.slf4j.Slf4j;
import java.io.InputStream;
import java.nio.charset.Charset;
@Slf4j
public class TextParse extends FileParse {
@Override
public String parseContent(InputStream stream, String fileType) {
String fileTmpPath = createFileTmpPath(fileType);
String res = "";
try {
FileUtil.writeFromStream(stream, fileTmpPath);
res = FileUtil.readString(fileTmpPath, Charset.defaultCharset());
} catch (Exception e) {
log.info("解析文件 {} 错误, 原因 {}", fileType, e.getMessage(), e);
} finally {
FileUtil.del(fileTmpPath);
}
return res;
}
}

28
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/WordParse.java Normal file
View File

@ -0,0 +1,28 @@
package com.electromagnetic.industry.software.common.parse;
import cn.hutool.core.io.FileUtil;
import com.electromagnetic.industry.software.common.util.OfficeFileUtil;
import lombok.extern.slf4j.Slf4j;
import java.io.InputStream;
@Slf4j
public class WordParse extends FileParse {
@Override
public String parseContent(InputStream stream, String fileType) {
String fileTmpPath = createFileTmpPath(fileType);
String res = "";
try {
FileUtil.writeFromStream(stream, fileTmpPath);
if (fileType.endsWith("docx")) {
return OfficeFileUtil.parseDocx(fileTmpPath);
} else {
return OfficeFileUtil.parseDoc(fileTmpPath);
}
} catch (Exception e) {
log.info("解析{}失败，原因{}", fileType, e.getMessage(), e);
}
return res;
}
}

28
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/util/EleCommonUtil.java
View File

@ -4,6 +4,7 @@ import cn.hutool.core.io.FileUtil;
import cn.hutool.core.util.StrUtil;
import cn.hutool.crypto.symmetric.AES;
import com.electromagnetic.industry.software.common.exception.BizException;
import com.electromagnetic.industry.software.common.parse.*;
import java.io.File;
import java.io.InputStream;
@ -12,10 +13,26 @@ import java.nio.file.Files;
import java.nio.file.Paths;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.HashMap;
import java.util.Map;
import java.util.regex.Pattern;
public final class EleCommonUtil {
private static final Map<String, FileParse> PARSE_MAP = new HashMap<>();
static {
PARSE_MAP.put("doc", new WordParse());
PARSE_MAP.put("docx", new WordParse());
PARSE_MAP.put("xls", new ExcelParse());
PARSE_MAP.put("xlsx", new ExcelParse());
PARSE_MAP.put("ppt", new PptParse());
PARSE_MAP.put("pptx", new PptParse());
PARSE_MAP.put("text", new TextParse());
PARSE_MAP.put("txt", new TextParse());
PARSE_MAP.put("py", new TextParse());
}
// 正则表达式模式，匹配中文字符、下划线、连字符、加号、数字和英文字符
private static final String PATTERN = "^[\\u4e00-\\u9fa5a-zA-Z0-9._\\-+]+$";
@ -59,4 +76,15 @@ public final class EleCommonUtil {
}
}
public static boolean isWinOs() {
return System.getProperty("os.name").toLowerCase().startsWith("win");
}
public static String parse(InputStream inputStream, String fileType) {
FileParse fileParse = PARSE_MAP.getOrDefault(fileType, new TextParse());
return fileParse.parseContent(inputStream, fileType);
}
}

82
electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/util/OfficeFileUtil.java
View File

@ -5,32 +5,80 @@ import com.documents4j.api.DocumentType;
import com.documents4j.api.IConverter;
import com.documents4j.job.LocalConverter;
import lombok.extern.slf4j.Slf4j;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import java.io.*;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.List;
@Slf4j
public class OfficeFileUtil {
private static final IConverter CONVERT = LocalConverter.builder().build();
public static void doc2pdf(String wordPath, String pdfPath) {
File inputWord = new File(wordPath);
File outputFile = new File(pdfPath);
try {
InputStream docxInputStream = Files.newInputStream(inputWord.toPath());
OutputStream outputStream = Files.newOutputStream(outputFile.toPath());
IConverter converter = LocalConverter.builder().build();
boolean execute = converter.convert(docxInputStream)
.as(DocumentType.DOCX)
.to(outputStream)
.as(DocumentType.PDF).schedule().get();
Assert.isTrue(execute, "转换失败");
outputStream.close();
docxInputStream.close();
log.info("转换完毕 targetPath = {}", outputFile.getAbsolutePath());
converter.shutDown();
} catch (Exception e) {
log.error("[documents4J] word转pdf失败:{}", e.toString());
if (EleCommonUtil.isWinOs()) {
File inputWord = new File(wordPath);
File outputFile = new File(pdfPath);
try(InputStream docxInputStream = Files.newInputStream(inputWord.toPath());
OutputStream outputStream = Files.newOutputStream(outputFile.toPath())) {
boolean execute = CONVERT.convert(docxInputStream)
.as(DocumentType.DOCX)
.to(outputStream)
.as(DocumentType.PDF).schedule().get();
Assert.isTrue(execute, "转换失败");
log.info("转换完毕 targetPath = {}", outputFile.getAbsolutePath());
CONVERT.shutDown();
} catch (Exception e) {
log.error("[documents4J] word转pdf失败:{}", e.toString());
}
} else {
}
}
public static String parseDocx(String wordPath) throws IOException {
InputStream fis = Files.newInputStream(Paths.get(wordPath));
XWPFDocument document = new XWPFDocument();
StringBuilder stringBuilder = new StringBuilder();
List<XWPFParagraph> paragraphs = document.getParagraphs();
for (XWPFParagraph paragraph : paragraphs) {
stringBuilder.append(paragraph.getText());
}
document.close();
fis.close();
return stringBuilder.toString();
}
public static String parsePdf(String path) throws IOException {
// 加载PDF文档
PDDocument document = PDDocument.load(new File(path));
// 创建PDFTextStripper对象来解析文本
PDFTextStripper pdfStripper = new PDFTextStripper();
// 提取文本
String text = pdfStripper.getText(document);
document.close();
return text;
}
public static String parseDoc(String path) throws IOException {
FileInputStream fis = new FileInputStream(path);
HWPFDocument document = new HWPFDocument(fis);
WordExtractor wordExtractor = new WordExtractor(document);
String[] paragraphText = wordExtractor.getParagraphText();
StringBuilder stringBuilder = new StringBuilder();
for (String paragraph : paragraphText) {
stringBuilder.append(paragraph);
}
fis.close();
return stringBuilder.toString();
}
}