From 4350264ab795a0ad7f98fdfef9e32d34d11c2366 Mon Sep 17 00:00:00 2001 From: zhouhaibin Date: Thu, 22 May 2025 14:32:46 +0800 Subject: [PATCH] =?UTF-8?q?=E6=96=B0=E5=A2=9E=E6=8B=9B=E6=8A=95=E6=A0=87?= =?UTF-8?q?=E5=9B=BE=E7=89=87=E7=9B=B8=E4=BC=BC=E6=80=A7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../src/main/resources/application-dev.yml | 2 +- .../impl/DocumentTaskResultsServiceImpl.java | 184 +++++++++++++----- .../impl/SjjDocumentTasksServiceImpl.java | 20 +- 3 files changed, 145 insertions(+), 61 deletions(-) diff --git a/ruoyi-admin/src/main/resources/application-dev.yml b/ruoyi-admin/src/main/resources/application-dev.yml index 00042d9..0638d2d 100644 --- a/ruoyi-admin/src/main/resources/application-dev.yml +++ b/ruoyi-admin/src/main/resources/application-dev.yml @@ -52,7 +52,7 @@ spring: # url: jdbc:mysql://localhost:3306/zaojia?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8&autoReconnect=true&rewriteBatchedStatements=true&allowPublicKeyRetrieval=true&nullCatalogMeansCurrent=true # username: root # password: root - url: jdbc:mysql://10.1.21.250:3306/aitable?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8&autoReconnect=true&rewriteBatchedStatements=true&allowPublicKeyRetrieval=true&nullCatalogMeansCurrent=true + url: jdbc:mysql://10.1.21.250:3306/sjjtable?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8&autoReconnect=true&rewriteBatchedStatements=true&allowPublicKeyRetrieval=true&nullCatalogMeansCurrent=true # url: jdbc:mysql://218.0.1.42:53306/sjjtable?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8&autoReconnect=true&rewriteBatchedStatements=true&allowPublicKeyRetrieval=true&nullCatalogMeansCurrent=true username: root password: 'HXj-6nR|D8xy*h#!I&:(' diff --git a/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/DocumentTaskResultsServiceImpl.java b/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/DocumentTaskResultsServiceImpl.java index 84f7f79..c8730cc 100644 --- a/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/DocumentTaskResultsServiceImpl.java +++ b/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/DocumentTaskResultsServiceImpl.java @@ -42,6 +42,7 @@ import javax.xml.parsers.SAXParser; import java.io.*; import java.net.URLEncoder; import java.nio.charset.StandardCharsets; +import java.nio.file.Files; import java.util.Arrays; import java.util.List; import java.util.Map; @@ -243,22 +244,22 @@ public class DocumentTaskResultsServiceImpl implements IDocumentTaskResultsServi if (!"isRead".equals(field) && !"isAdopted".equals(field)) { throw new RuntimeException("不支持更新的字段: " + field); } - + // 验证值是否合法 if (!"0".equals(value) && !"1".equals(value)) { throw new RuntimeException("无效的值: " + value); } - + try { LambdaUpdateWrapper updateWrapper = Wrappers.lambdaUpdate(DocumentTaskResultDetail.class); updateWrapper.eq(DocumentTaskResultDetail::getId, id); - + if ("isRead".equals(field)) { updateWrapper.set(DocumentTaskResultDetail::getIsRead, value); } else { updateWrapper.set(DocumentTaskResultDetail::getIsAdopted, value); } - + return documentTaskResultDetailMapper.update(null, updateWrapper) > 0; } catch (Exception e) { throw new RuntimeException("更新状态失败: " + e.getMessage(), e); @@ -351,12 +352,6 @@ public class DocumentTaskResultsServiceImpl implements IDocumentTaskResultsServi // Markdown转PDF方法 private void convertMarkdownToPdf(String markdown, String outputPath) throws Exception { - // 使用flexmark-java解析Markdown -// MutableDataSet options = new MutableDataSet(); -// Parser parser = Parser.builder(options).build(); -// HtmlRenderer renderer = HtmlRenderer.builder(options).build(); -// Node document = parser.parse(markdown); -// String htmlContent = renderer.render(document); MutableDataSet options = new MutableDataSet(); // 启用表格解析 options.set(Parser.EXTENSIONS, Arrays.asList( @@ -371,7 +366,7 @@ public class DocumentTaskResultsServiceImpl implements IDocumentTaskResultsServi StrikethroughExtension.create() )) .build(); - + markdown=markdown.replaceAll("!\\[","!{}"); Node document = parser.parse(markdown); String htmlContent = renderer.render(document); // 使用 JSoup 清理 @@ -380,21 +375,12 @@ public class DocumentTaskResultsServiceImpl implements IDocumentTaskResultsServi // 配置允许的标签 Safelist safelist = Safelist.relaxed() -// .addTags("em", "strong", "div", "span","br") -// .addAttributes(":all", "style", "class"); - .addTags("em", "strong", "div", "span", "br", "table", "thead", "tbody", "tr", "th", "td") + .addTags("em", "strong", "div", "span", "br", "table", "thead", "tbody", "tr", "th", "td", "img") .addAttributes(":all", "style", "class") - .addAttributes("table", "border", "cellpadding", "cellspacing"); + .addAttributes("table", "border", "cellpadding", "cellspacing") + .addAttributes("img", "src", "alt", "width", "height"); // 允许img标签及其属性 htmlContent = Jsoup.clean(htmlContent, "", safelist, settings); - // 处理代码块 - 将code标签替换为带内联样式的div (不使用class) - htmlContent = htmlContent.replaceAll("(?s)
(.*?)
", - "
$1
"); - - // 处理行内代码 - 将行内code替换为带内联样式的span (不使用class) - htmlContent = htmlContent.replaceAll("(.*?)", - "$1"); - // 使用 NekoHTML 进一步处理 // 创建完整的HTML文档，使用微软雅黑 String html = String.format(""" @@ -437,6 +423,14 @@ public class DocumentTaskResultsServiceImpl implements IDocumentTaskResultsServi tr { page-break-inside: avoid; } + img { + width: 600px; + max-width: 100%%; + height: auto; + display: block; + margin: 20px auto; + page-break-inside: avoid; + } @@ -444,44 +438,130 @@ public class DocumentTaskResultsServiceImpl implements IDocumentTaskResultsServi """, - // 特殊处理code标签，确保其内容不被换行破坏 htmlContent.replace("
", "\n")); + // 处理图片标签，将markdown的图片语法转换为HTML的img标签 + html=html.replaceAll("!\\{}","!\\["); + html = handleImageTags(html); + // 配置Flying Saucer + ITextRenderer pdfRenderer = new ITextRenderer(); + + // 主要使用微软雅黑，但也加载其他字体作为备选 + // 从classpath加载字体 + try (InputStream is = getClass().getResourceAsStream("/fonts/msyh.ttc")) { + File tempFont = File.createTempFile("msyh", ".ttc"); + FileUtils.copyInputStreamToFile(is, tempFont); + pdfRenderer.getFontResolver().addFont(tempFont.getAbsolutePath(), BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED); + tempFont.deleteOnExit(); + } + // 设置文档 + pdfRenderer.setDocumentFromString(html); + // 设置输出编码和基础URL + pdfRenderer.getSharedContext().setBaseURL("file:///"); - // 配置Flying Saucer - ITextRenderer pdfRenderer = new ITextRenderer(); - - // 主要使用微软雅黑，但也加载其他字体作为备选 - // 从classpath加载字体 - try (InputStream is = getClass().getResourceAsStream("/fonts/msyh.ttc")) { - File tempFont = File.createTempFile("msyh", ".ttc"); - FileUtils.copyInputStreamToFile(is, tempFont); - pdfRenderer.getFontResolver().addFont(tempFont.getAbsolutePath(), BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED); - tempFont.deleteOnExit(); - } - try (InputStream consolas = getClass().getResourceAsStream("/fonts/consolas.ttf")){ - if (consolas != null) { - File tempConsolas = File.createTempFile("consolas", ".ttf"); - FileUtils.copyInputStreamToFile(consolas, tempConsolas); - pdfRenderer.getFontResolver().addFont(tempConsolas.getAbsolutePath(), BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED); - tempConsolas.deleteOnExit(); - } - } + // 布局和创建PDF + pdfRenderer.layout(); - // 设置文档 - pdfRenderer.setDocumentFromString(html); + try (OutputStream os = new FileOutputStream(outputPath)) { + pdfRenderer.createPDF(os, true); + } + } - // 设置输出编码和基础URL - pdfRenderer.getSharedContext().setBaseURL("file:///"); + /** + * 处理Markdown中的图片标签 + * @param content Markdown内容 + * @return 处理后的HTML内容 + */ + private String handleImageTags(String content) { + // 使用非贪婪模式匹配alt文本，使用平衡组模式匹配路径 + java.util.regex.Pattern pattern = java.util.regex.Pattern.compile("!\\[(.*?)\\]\\(([^()]*(?:\\([^()]*\\)[^()]*)*?)\\)"); + java.util.regex.Matcher matcher = pattern.matcher(content); + StringBuffer sb = new StringBuffer(); + + while (matcher.find()) { + String alt = matcher.group(1); + String imagePath = matcher.group(2); + + // 检查图片文件是否存在 + File imageFile = new File(imagePath); + if (!imageFile.exists() && imagePath.contains("(")) { + // 如果文件不存在且路径中包含括号，尝试修正路径 + String correctedPath = correctImagePath(imagePath); + imageFile = new File(correctedPath); + if (imageFile.exists()) { + imagePath = correctedPath; + } + } - // 布局和创建PDF - pdfRenderer.layout(); + if (imageFile.exists()) { + try { + // 将图片转换为Base64编码 + byte[] imageBytes = Files.readAllBytes(imageFile.toPath()); + String base64Image = java.util.Base64.getEncoder().encodeToString(imageBytes); + String imageType = getImageMimeType(imagePath); + + // 创建data URL，使用固定的宽度来确保图片在页面内显示 + String imgTag = String.format("\"%s\"", + imageType, base64Image, alt); + + // 替换markdown图片语法为HTML img标签 + matcher.appendReplacement(sb, imgTag.replace("$", "\\$")); + } catch (IOException e) { + // 如果处理失败，保留原始文本 + matcher.appendReplacement(sb, matcher.group(0).replace("$", "\\$")); + } + } else { + // 如果图片不存在，保留原始文本 + matcher.appendReplacement(sb, matcher.group(0).replace("$", "\\$")); + } + } + matcher.appendTail(sb); + return sb.toString(); + } - try (OutputStream os = new FileOutputStream(outputPath)) { - pdfRenderer.createPDF(os, true); - } + /** + * 修正包含括号的图片路径 + * @param originalPath 原始路径 + * @return 修正后的路径 + */ + private String correctImagePath(String originalPath) { + // 如果路径中包含多个括号，取最后一个右括号之前的内容 + int lastRightBracket = originalPath.lastIndexOf(")"); + if (lastRightBracket != -1) { + // 找到对应的左括号 + int count = 1; + int leftBracket = lastRightBracket - 1; + while (leftBracket >= 0 && count > 0) { + if (originalPath.charAt(leftBracket) == ')') { + count++; + } else if (originalPath.charAt(leftBracket) == '(') { + count--; + } + leftBracket--; + } + if (count == 0) { + // 找到匹配的括号对，返回不包含最外层括号的路径 + return originalPath.substring(0, leftBracket + 1) + originalPath.substring(lastRightBracket + 1); + } + } + return originalPath; + } + /** + * 根据文件扩展名获取MIME类型 + * @param filePath 文件路径 + * @return MIME类型 + */ + private String getImageMimeType(String filePath) { + String extension = filePath.substring(filePath.lastIndexOf(".") + 1).toLowerCase(); + return switch (extension) { + case "png" -> "image/png"; + case "jpg", "jpeg" -> "image/jpeg"; + case "gif" -> "image/gif"; + case "bmp" -> "image/bmp"; + default -> "image/jpeg"; + }; } // 添加文件到ZIP diff --git a/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/SjjDocumentTasksServiceImpl.java b/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/SjjDocumentTasksServiceImpl.java index be88978..1f3c596 100644 --- a/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/SjjDocumentTasksServiceImpl.java +++ b/zaojiaManagement/zaojia-productManagement/src/main/java/org/dromara/productManagement/service/impl/SjjDocumentTasksServiceImpl.java @@ -159,7 +159,7 @@ public class SjjDocumentTasksServiceImpl implements ISjjDocumentTasksService { new File(tenderOriginalDir).mkdirs(); new File(tenderTxtDir).mkdirs(); // 处理投标文件压缩包 - processZipFile(bidZipPath, bidOriginalDir, bidTxtDir); + processZipFile(add.getTaskName(),bidZipPath, bidOriginalDir, bidTxtDir); // 复制招标文件到任务文件夹 File tenderDoc = new File(tenderDocPath); @@ -177,7 +177,9 @@ public class SjjDocumentTasksServiceImpl implements ISjjDocumentTasksService { // 如果是PDF文件，解析其内容到招标文件TXT目录 if (tenderDocName.toLowerCase().endsWith(".pdf") && PdfParserUtils.isValidPdf(tenderDocCopy.getAbsolutePath())) { - processAndSavePdfContent(tenderDocCopy, tenderTxtDir, getSystemCharset()); + if (add.getTaskName().equals("ssjjbidAnalysis")){ + processAndSavePdfContent(tenderDocCopy, tenderTxtDir, getSystemCharset()); + } } } @@ -231,7 +233,7 @@ public class SjjDocumentTasksServiceImpl implements ISjjDocumentTasksService { * @throws IOException 解压或解析过程中发生IO错误 * @throws ZipException ZIP文件处理错误 */ - private void processZipFile(String zipFilePath, String originalDir, String txtDir) throws IOException, ZipException { + private void processZipFile(String taskName,String zipFilePath, String originalDir, String txtDir) throws IOException, ZipException { // 创建解压目标目录（如果不存在） File extractDirFile = new File(originalDir); if (!extractDirFile.exists()) { @@ -272,14 +274,14 @@ public class SjjDocumentTasksServiceImpl implements ISjjDocumentTasksService { } // 递归处理所有PDF文件 - processAllPdfFiles(extractDirFile, txtDir, bestCharset); + processAllPdfFiles(taskName,extractDirFile, txtDir, bestCharset); } catch (Exception e) { // 如果使用检测的编码失败，尝试直接整体解压 try { ZipFile zipFile = new ZipFile(zipFilePath); zipFile.setCharset(getSystemCharset()); zipFile.extractAll(originalDir); - processAllPdfFiles(extractDirFile, txtDir, getSystemCharset()); + processAllPdfFiles(taskName,extractDirFile, txtDir, getSystemCharset()); } catch (Exception e2) { System.err.println("解压失败: " + e2.getMessage()); throw new IOException("解压失败", e2); @@ -453,7 +455,7 @@ public class SjjDocumentTasksServiceImpl implements ISjjDocumentTasksService { * @param txtOutputDir PDF解析后的TXT文件输出目录 * @param charset 字符集 */ - private void processAllPdfFiles(File directory, String txtOutputDir, Charset charset) { + private void processAllPdfFiles(String taskName,File directory, String txtOutputDir, Charset charset) { if (!directory.isDirectory()) { return; } @@ -466,10 +468,12 @@ public class SjjDocumentTasksServiceImpl implements ISjjDocumentTasksService { for (File file : files) { if (file.isDirectory()) { // 递归处理子目录 - processAllPdfFiles(file, txtOutputDir, charset); + processAllPdfFiles(taskName,file, txtOutputDir, charset); } else if (file.getName().toLowerCase().endsWith(".pdf") && PdfParserUtils.isValidPdf(file.getAbsolutePath())) { // 处理PDF文件 - processAndSavePdfContent(file, txtOutputDir, charset); + if (taskName.equals("sjjbidAnalysis")){ + processAndSavePdfContent(file, txtOutputDir, charset); + } } } }