add latigation

@@ -13,6 +13,9 @@ class OCR2Exception(Exception):
 class OCR4Exception(Exception):
 class OCR4Exception(Exception):
     pass
     pass
 
 
+class LTGTException(Exception):
+    pass
+
 
 
 class GCAPException(Exception):
 class GCAPException(Exception):
     pass
     pass

@@ -702,6 +702,23 @@ class BSWorkbook(Workbook):
             if field_str is not None:
             if field_str is not None:
                 count_list.append((field_str, count))
                 count_list.append((field_str, count))
 
 
+    def ltgt_build(self, label, result_dict):
+        ws = self.create_sheet(label)
+        for key, value in result_dict.items():
+            if isinstance(value, list):
+                ws.append((key, *value))
+            elif isinstance(value, dict):
+                if 'words' in value:
+                    ws.append((key, value['words']))
+                else:
+                    for sub_key, sub_value in value.items():
+                        if isinstance(sub_value, dict):
+                            ws.append(('{0}: {1}'.format(key, sub_key), sub_value.get('words', '')))
+                        else:
+                            ws.append(('{0}: {1}'.format(key, sub_key), sub_value))
+            else:
+                ws.append((key, value))
+
     def simple_license_rebuild(self, license_summary, document_scheme):
     def simple_license_rebuild(self, license_summary, document_scheme):
         # for ic_license_dict in license_summary.get(consts.IC_CLASSIFY, []):
         # for ic_license_dict in license_summary.get(consts.IC_CLASSIFY, []):
         #     if ic_license_dict.get('类别') == '1':
         #     if ic_license_dict.get('类别') == '1':

@@ -225,3 +225,13 @@ class PDFHandler:
                 else:
                 else:
                     self.merge_il(pdf, pno, il)
                     self.merge_il(pdf, pno, il)
         self.img_count = len(self.img_path_list)
         self.img_count = len(self.img_path_list)
+
+    def extract_page_image(self):
+        self.img_path_list = []
+        self.xref_set = set()
+        os.makedirs(self.img_dir_path, exist_ok=True)
+        with fitz.Document(self.path) as pdf:
+            for pno in range(pdf.pageCount):
+                page = pdf.loadPage(pno)
+                self.page_to_png(page)
+        self.img_count = len(self.img_path_list)