Add context_text extraction for text-search-based CFI conversion

main.lua

@@ -662,6 +662,27 @@ function Bookhoard:getBookhoardUUID()
     return self.ui.doc_settings:readSetting("bookhoard_uuid")
 end
 
+function Bookhoard:getContextText()
+    if not self.ui.document or self.ui.document.info.has_pages then
+        return ""
+    end
+    local xp = self:getLastProgress()
+    if not xp then return "" end
+
+    local text = self.ui.document:getTextFromXPointer(xp)
+    if not text or text == "" then
+        text = self.ui.document:getTextFromXPointer(self.ui.document:getNormalizedXPointer(xp))
+    end
+    if not text or text == "" then return "" end
+
+    if #text > 100 then
+        text = text:sub(1, 100)
+    end
+
+    text = text:gsub("%s+", " "):match("^%s*(.-)%s*$") or ""
+    return text
+end
+
 function Bookhoard:collectBookData()
     local props = self.ui.doc_props
     local file_path = self.ui.document.file
@@ -680,6 +701,7 @@ function Bookhoard:collectBookData()
     local progress = self:getLastProgress()
     local page = self.ui:getCurrentPage()
     local total_pages = self.ui.document:getPageCount()
+    local context_text = self:getContextText()
 
     local book_data = {
         uuid = book_uuid,
@@ -688,6 +710,7 @@ function Bookhoard:collectBookData()
         authors = authors,
         percentage = percentage,
         epubcfi = progress,
+        context_text = context_text,
         page = page,
         total_pages = total_pages,
         file_path = file_path,