feat(getPageContentText): implement getFullTextContent for enhanced text extraction

- Add new getFullTextContent function to handle various Notion text formats
- Support equation extraction from decorated text
- Handle special characters like '⁍' and '‣' with proper content resolution
- Process date mentions, link mentions, and other reference types
- Replace getTextContent with getFullTextContent in getTextArray function
- Maintain backward compatibility with existing text processing

lib/notion/getPageContentText.js

@@ -1,5 +1,3 @@
-import { getTextContent } from 'notion-utils'
-
 /**
  * 获取属性值，优先从 overrides 中读取，否则按顺序从 properties 中读取，最后返回默认值
  * @param {Object} properties 原始属性对象
@@ -15,6 +13,62 @@ function getPropertyValue(properties, keys, overrides = {}, defaultValue = '') {
   return defaultValue
 }
 
+/**
+ * 提取 Notion 装饰文本的纯文本内容。
+ * 可选传入 resolveRef 来解析引用（例如 '‣' 指向的页面标题）
+ *
+ * @param {Array} text - Notion Decoration[] 格式的文本数组
+ * @returns {string}
+ */
+function getFullTextContent(text) {
+  if (!text) return ''
+
+  if (!Array.isArray(text)) return String(text)
+
+  return text.reduce((result, item) => {
+    const value = item[0]
+    const decorations = item[1]
+
+    if (value === '⁍') {
+      // 检查是否有公式
+      const equation = decorations?.find(d => d[0] === 'e')
+      if (equation) {
+        return result + equation[1] // 提取 LaTeX 内容
+      }
+      return result // 否则什么都不加
+    }
+
+    if (value === '‣') {
+      const ref = Array.isArray(decorations) ? decorations[0] : null
+      const type = ref?.[0]
+      const data = ref?.[1]
+
+      switch (type) {
+        case 'd':
+          // 日期字符串
+          const date =
+            data?.start_date ||
+            data?.start_time ||
+            data?.end_date ||
+            data?.end_time ||
+            '[Date]'
+          return result + date
+        case 'lm':
+          // Link Mention
+          const title = data?.title || data?.href || '[Link]'
+          return result + title
+        // 用户 ID，这里不展开，默认忽略或标记
+        case 'u':
+        default:
+          return result
+      }
+    }
+
+    // 默认拼接普通文本
+    return result + value
+  }, '')
+}
+
 export function getPageContentText(post, pageBlockMap) {
   /**
    * 将对象的指定字段拼接到字符串
@@ -39,7 +93,7 @@ export function getPageContentText(post, pageBlockMap) {
   }
 
   function getTextArray(textArray) {
-    const text = textArray ? getTextContent(textArray) : ''
+    const text = textArray ? getFullTextContent(textArray) : ''
     if (text && text !== 'Untitled') {
       return text
     }