1

ruoyi-admin/src/main/java/com/ruoyi/web/controller/jarvis/TencentDocController.java

@@ -1735,9 +1735,9 @@ public class TencentDocController extends BaseController {
             Integer startRow = params.get("startRow") != null ? 
                 Integer.valueOf(params.get("startRow").toString()) : 850;
             
-            // 结束行，默认读取200行
+            // 结束行，默认到2500行
             Integer endRow = params.get("endRow") != null ? 
-                Integer.valueOf(params.get("endRow").toString()) : (startRow + 199);
+                Integer.valueOf(params.get("endRow").toString()) : 2500;
 
             if (accessToken == null || fileId == null || sheetId == null) {
                 return AjaxResult.error("文档配置不完整，请先配置 fileId 和 sheetId");
@@ -1838,8 +1838,8 @@ public class TencentDocController extends BaseController {
                     continue;
                 }
                 
-                // 清理物流链接（去除空格等）
+                // 清理物流链接（去除空格、换行符、中文等）
-                logisticsLink = logisticsLink.trim();
+                logisticsLink = cleanLogisticsLink(logisticsLink);
                 
                 try {
                     // 通过物流链接查找订单
@@ -1927,5 +1927,45 @@ public class TencentDocController extends BaseController {
             return AjaxResult.error("反向同步失败: " + e.getMessage());
         }
     }
+
+    /**
+     * 清理物流链接
+     * 去除空格、换行符、制表符、中文等特殊字符，只保留URL有效字符
+     * 
+     * @param logisticsLink 原始物流链接
+     * @return 清理后的物流链接
+     */
+    private String cleanLogisticsLink(String logisticsLink) {
+        if (logisticsLink == null) {
+            return null;
+        }
+        
+        // 去除首尾空格
+        String cleaned = logisticsLink.trim();
+        
+        // 去除换行符、制表符等空白字符
+        cleaned = cleaned.replaceAll("[\\r\\n\\t]", "");
+        
+        // 去除所有空格
+        cleaned = cleaned.replaceAll("\\s+", "");
+        
+        // 提取URL（如果包含中文或其他非URL字符，尝试提取URL部分）
+        // 匹配 http:// 或 https:// 开头的URL
+        java.util.regex.Pattern urlPattern = java.util.regex.Pattern.compile("https?://[^\\s\\u4e00-\\u9fa5]+");
+        java.util.regex.Matcher matcher = urlPattern.matcher(cleaned);
+        
+        if (matcher.find()) {
+            cleaned = matcher.group();
+        } else {
+            // 如果没有找到完整URL，尝试提取 3.cn 相关的链接
+            java.util.regex.Pattern shortUrlPattern = java.util.regex.Pattern.compile("https?://3\\.cn/[^\\s\\u4e00-\\u9fa5]+");
+            java.util.regex.Matcher shortMatcher = shortUrlPattern.matcher(cleaned);
+            if (shortMatcher.find()) {
+                cleaned = shortMatcher.group();
+            }
+        }
+        
+        return cleaned.trim();
+    }
 }