a little updates

core/data_translate.py

@@ -0,0 +1,66 @@
+import os
+import json
+import json_repair
+import re
+import fitz
+import pandas as pd
+from utils.gpt_utils import chat
+from utils.pdf_util import PDFUtil
+from utils.sql_query_util import query_document_fund_mapping, query_investment_by_provider
+from utils.logger import logger
+
+
+class Translate_PDF:
+    def __init__(self, pdf_file: str, output_folder: str, target_language: str = "English") -> None:
+        self.pdf_file = pdf_file
+        if not os.path.exists(self.pdf_file):
+            raise Exception(f"File {self.pdf_file} not found")
+        if not os.path.exists(output_folder):
+            os.makedirs(output_folder)
+        self.output_folder = output_folder
+        self.target_language = target_language
+    
+    
+    def start_job(self):
+        try:
+            pdf_util = PDFUtil(self.pdf_file)
+            page_text_dict = self.get_pdf_page_text_dict()
+            
+            total_text = ""
+            for page_num, page_text in page_text_dict.items():
+                logger.info(f"Translate from page {page_num}")
+                total_text += f"----------------- Page {page_num} -----------------\n"
+                if page_text.strip() == "":
+                    total_text += "\n\n"
+                    continue
+                total_text += self.translate_text(page_text) + "\n"
+            if self.output_folder:
+                output_file = os.path.join(self.output_folder, os.path.basename(self.pdf_file).replace(".pdf", "_translated.txt"))
+                with open(output_file, "w", encoding="utf-8") as f:
+                    f.write(total_text)
+        except Exception as e:
+            logger.error(f"Error: {e}")
+            raise Exception(e)
+    
+    def get_pdf_page_text_dict(self) -> dict:
+        pdf_util = PDFUtil(self.pdf_file)
+        success, text, page_text_dict = pdf_util.extract_text()
+        return page_text_dict
+    
+    def translate_text(self, text: str):
+        instructions = f"Context: \n{text}\n\nInstructions: Translate the contex in {self.target_language}. \n"
+        instructions += "Please output the translated text in the following JSON format: {\"translated_text\": \"translated text\"} \n\n"
+        instructions += "Answer: \n"
+        response, with_error = chat(
+            instructions, response_format={"type": "json_object"}
+        )
+        try:
+            data = json.loads(response)
+        except:
+            try:
+                data = json_repair.loads(response)
+            except:
+                data = {"translated_text": ""}
+        return data.get("translated_text", "")
+        
+    

main.py

@@ -624,7 +624,16 @@ def test_mapping_raw_name():
     print(mapping_info)
     
 
+def test_translate_pdf():
+    from core.data_translate import Translate_PDF
+    pdf_file = r"/data/emea_ar/pdf/451063582.pdf"
+    output_folder = r"/data/translate/output/"
+    translate_pdf = Translate_PDF(pdf_file, output_folder)
+    translate_pdf.start_job()
+
+
 if __name__ == "__main__":
+    # test_translate_pdf()
     pdf_folder = r"/data/emea_ar/pdf/"
     page_filter_ground_truth_file = (
         r"/data/emea_ar/ground_truth/page_filter/datapoint_page_info_88_documents.xlsx"
@@ -821,45 +830,98 @@ if __name__ == "__main__":
     # 543243585,
     # 543243654
     # """
+    # check_db_mapping_doc_id_list = [
+    #     "511052670",
+    #     "520733219",
+    #     "524306810",
+    #     "526747539",
+    #     "528783089",
+    #     "532422720",
+    #     "532438210",
+    #     "534112077",
+    #     "534538571",
+    #     "534538682",
+    #     "535798742",
+    #     "536299372",
+    #     "539566148",
+    #     "539604165",
+    #     "540056900",
+    #     "541343431",
+    #     "541669780",
+    #     "541669996",
+    #     "541670397",
+    #     "541923319",
+    #     "542335994",
+    #     "543243585",
+    #     "543243654",
+    #     "543244170",
+    #     "543519140",
+    #     "543519615",
+    #     "543628379",
+    #     "543809340",
+    #     "543944737"
+    # ]
+    
+    # documents in Final list of EMEA documents.xlsx as typical documents
     check_db_mapping_doc_id_list = [
-        "511052670",
+        "532500349",
-        "520733219",
+        "535324239",
-        "524306810",
+        "532442891",
-        "526747539",
+        "543243650",
-        "528783089",
+        "528588598",
-        "532422720",
+        "532437639",
-        "532438210",
+        "527525440",
-        "534112077",
+        "534987291",
-        "534538571",
+        "534112055",
-        "534538682",
+        "533482585",
-        "535798742",
+        "544208174",
-        "536299372",
+        "534547266",
-        "539566148",
+        "544713166",
-        "539604165",
+        "526463547",
-        "540056900",
+        "534535569",
-        "541343431",
+        "534106067",
-        "541669780",
+        "532486560",
-        "541669996",
+        "532781760",
-        "541670397",
+        "533727067",
-        "541923319",
+        "527256381",
-        "542335994",
+        "533392425",
-        "543243585",
+        "532179676",
-        "543243654",
+        "534300608",
-        "543244170",
+        "539233950",
-        "543519140",
+        "533727908",
-        "543519615",
+        "532438414",
-        "543628379",
+        "533681744",
-        "543809340",
+        "537654645",
-        "543944737"
+        "533594905",
+        "537926443",
+        "533499655",
+        "533862814",
+        "544918611",
+        "539087870",
+        "536343790"
         ]
-    # special_doc_id_list = check_mapping_doc_id_list
     special_doc_id_list = check_db_mapping_doc_id_list
-    special_doc_id_list = ["423418540"]
+    # special_doc_id_list = ["425595958",
+    #                         "451063582",
+    #                         "451878128",
+    #                         "466580448",
+    #                         "481482392",
+    #                         "492029971",
+    #                         "508704368",
+    #                         "510300817",
+    #                         "512745032",
+    #                         "514213638",
+    #                         "527525440",
+    #                         "532422548",
+    #                         "532998065",
+    #                         "534535767",
+    #                         "536344026",
+    #                         "540307575"]
     output_mapping_child_folder = r"/data/emea_ar/output/mapping_data/docs/"
     output_mapping_total_folder = r"/data/emea_ar/output/mapping_data/total/"
     re_run_extract_data = True
     re_run_mapping_data = True
-    force_save_total_data = False
+    force_save_total_data = True
     calculate_metrics = False
 
     extract_ways = ["text"]

prepare_data.py

@@ -997,12 +997,12 @@ if __name__ == "__main__":
         r"/data/emea_ar/basic_information/English/lux_english_ar_top_100_provider_random_small_document.xlsx"
     )
     
-    doc_provider_file_path = r"/data/emea_ar/basic_information/English/emea_sample_doc_from_Kshitij.xlsx"
+    doc_provider_file_path = r"/data/emea_ar/basic_information/English/sample_doc/emea_final_typical_case/Final list of EMEA documents.xlsx"
     pdf_folder = r"/data/emea_ar/pdf/"
     download_pdf(
         doc_provider_file_path=doc_provider_file_path,
-        sheet_name="Sample EMEA Docs",
+        sheet_name="Sheet1",
-        doc_id_column="Document ID",
+        doc_id_column="Document Id",
         pdf_path=pdf_folder)
     # output_pdf_page_text(pdf_folder, output_folder)
     
@@ -1014,12 +1014,14 @@ if __name__ == "__main__":
     #              'latest_ar_document_most_mapping', 
     #              pdf_folder)
     
-    output_data_folder = r"/data/emea_ar/basic_information/English/top_100_provider_latest_document_most_mapping/"
+    
+    doc_mapping_file_path = r"/data/emea_ar/basic_information/English/sample_doc/emea_final_typical_case/doc_ar_data_for_final_list_emea_documents.xlsx"
+    output_data_folder = r"/data/emea_ar/basic_information/English/sample_doc/emea_final_typical_case/"
     # statistics_document(pdf_folder=pdf_folder,
-    #                     doc_mapping_file_path=latest_top_100_provider_ar_data_file, 
+    #                     doc_mapping_file_path=doc_mapping_file_path, 
-    #                     sheet_name="latest_doc_ar_data",
+    #                     sheet_name="doc_ar_data_in_db",
     #                     output_folder=output_data_folder,
-    #                     output_file="latest_doc_ar_mapping_statistics.xlsx")
+    #                     output_file="doc_ar_data_statistics.xlsx")
     # get_document_extracted_share_diff_by_db()
     # statistics_provider_mapping(
     #     provider_mapping_data_file=provider_mapping_data_file,