完成了pdf，普通文本和word的解析

electromagnetic-common/pom.xml

@@ -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>

electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/ExcelParse.java

@@ -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 "";
+    }
+}

electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/FileParse.java

@@ -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;
+    }
+}

electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/PdfParse.java

@@ -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;
+    }
+}

electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/PptParse.java

@@ -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 "";
+    }
+}

electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/TextParse.java

@@ -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;
+    }
+}

electromagnetic-common/src/main/java/com/electromagnetic/industry/software/common/parse/WordParse.java

@@ -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;
+    }
+}

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

@@ -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);
+    }
+
 }

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

@@ -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) {
+        if (EleCommonUtil.isWinOs()) {
             File inputWord = new File(wordPath);
             File outputFile = new File(pdfPath);
-        try {
+            try(InputStream docxInputStream = Files.newInputStream(inputWord.toPath());
-            InputStream docxInputStream = Files.newInputStream(inputWord.toPath());
+                OutputStream outputStream = Files.newOutputStream(outputFile.toPath())) {
-            OutputStream outputStream = Files.newOutputStream(outputFile.toPath());
+                boolean execute = CONVERT.convert(docxInputStream)
-            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();
+                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();
+    }
 }