优化业务逻辑和基础库的大标题区间和字段的识别精度

src/components/SidebarPanel.tsx

@@ -128,7 +128,7 @@ export function SidebarPanel({ sourceUrl, jobInfo, onClose }: SidebarPanelProps)
   }
 
   /** 开启循环扫描（每秒执行一次） */
-  const startScanLoop = (params: { siteMode?: "beisen"; sectionResults?: any[]; expandedResults?: any[] }) => {
+  const startScanLoop = (params: { siteMode?: "beisen"; sectionResults?: any[]; expandedResults?: any[]; excludeTexts?: Set<string> }) => {
     stopScanLoop()
     const hasFullData = !!(params.sectionResults && params.expandedResults)
     // 立即执行一次
@@ -459,10 +459,33 @@ export function SidebarPanel({ sourceUrl, jobInfo, onClose }: SidebarPanelProps)
       hideFillingOverlay()                   // 填写完成，移除遮罩
 
       // 停止第一次循环扫描，开启第二次循环扫描（传入 sectionResults + expandedResults，分段精确）
+      // 构建排除集合：从简历数据中提取所有值，避免将已填值误认为标签
+      const scanExcludeTexts = new Set<string>()
+      const scanResumeData = fillResult.resumeData || resumeData
+      if (scanResumeData) {
+        const main = scanResumeData.main
+        if (main) {
+          for (const val of Object.values(main)) {
+            if (typeof val === "string" && val.trim()) scanExcludeTexts.add(val.trim())
+            if (Array.isArray(val)) val.forEach((v) => { if (typeof v === "string" && v.trim()) scanExcludeTexts.add(v.trim()) })
+          }
+        }
+        const expKeys: ("education" | "work" | "internship" | "project" | "competition")[] = ["education", "work", "internship", "project", "competition"]
+        for (const sec of expKeys) {
+          const items = scanResumeData[sec]
+          if (!Array.isArray(items)) continue
+          for (const item of items) {
+            for (const val of Object.values(item as Record<string, any>)) {
+              if (typeof val === "string" && val.trim()) scanExcludeTexts.add(val.trim())
+            }
+          }
+        }
+      }
       startScanLoop({
         siteMode: scanSiteMode,
         sectionResults: fillResult.sectionResults,
         expandedResults: fillResult.expandedResults,
+        excludeTexts: scanExcludeTexts,
       })
       
     } catch (e) {
@@ -487,8 +510,49 @@ export function SidebarPanel({ sourceUrl, jobInfo, onClose }: SidebarPanelProps)
       const currentHost = window.location.hostname
       const siteMode = currentHost.includes("zhiye.com") ? "beisen" as const : undefined
 
+      // 从简历数据和缓存数据中提取所有已填值，构建排除集合
+      // 避免 findLabelForInput 把这些值文字误认为是表单字段标签
+      const excludeTexts = new Set<string>()
+      if (resumeData) {
+        // 主表字段值
+        const main = resumeData.main
+        if (main) {
+          for (const val of Object.values(main)) {
+            if (typeof val === "string" && val.trim()) excludeTexts.add(val.trim())
+            if (Array.isArray(val)) val.forEach((v) => { if (typeof v === "string" && v.trim()) excludeTexts.add(v.trim()) })
+          }
+        }
+        // 5大经历字段值
+        const expSections: ("education" | "work" | "internship" | "project" | "competition")[] = ["education", "work", "internship", "project", "competition"]
+        for (const sec of expSections) {
+          const items = resumeData[sec]
+          if (!Array.isArray(items)) continue
+          for (const item of items) {
+            for (const val of Object.values(item as Record<string, any>)) {
+              if (typeof val === "string" && val.trim()) excludeTexts.add(val.trim())
+            }
+          }
+        }
+      }
+      // 缓存中已记住的表单字段值
+      if (cacheData.unfilledFormData) {
+        for (const sec of cacheData.unfilledFormData as any[]) {
+          const items = sec.formItems
+          if (!items) continue
+          if (sec.isExperience && Array.isArray(items)) {
+            for (const seg of items) {
+              if (Array.isArray(seg)) {
+                for (const f of seg) { if (f.value && typeof f.value === "string") excludeTexts.add(f.value.trim()) }
+              }
+            }
+          } else if (Array.isArray(items)) {
+            for (const f of items) { if (f.value && typeof f.value === "string") excludeTexts.add(f.value.trim()) }
+          }
+        }
+      }
+
       // 调用 fillStats 扫描页面所有字段
-      const titleStats = scanPageFields({ siteMode })
+      const titleStats = scanPageFields({ siteMode, excludeTexts })
 
       // 提取非简历格式字段（B2阶段字段）
       const nonResumeData = extractNonResumeFields(titleStats)