From c2d2e54670aecb748cc145c0141aea9f5d8d38c9 Mon Sep 17 00:00:00 2001
From: Blade He <Blade.He@morningstar.com>
Date: Tue, 12 Nov 2024 11:40:19 -0600
Subject: [PATCH] "total match" logic for single word value, need consider the
 "\n" char scenario

---
 main.py           |  2 +-
 utils/pdf_util.py | 16 ++++++++--------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/main.py b/main.py
index 33d7acd..55ee1fd 100644
--- a/main.py
+++ b/main.py
@@ -1110,7 +1110,7 @@ if __name__ == "__main__":
                             "546046730",
                             "546919329"
                             ]
-    # special_doc_id_list = ["501380775"]
+    special_doc_id_list = ["479742284"]
     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 = False
diff --git a/utils/pdf_util.py b/utils/pdf_util.py
index 4ddea7d..3040a87 100644
--- a/utils/pdf_util.py
+++ b/utils/pdf_util.py
@@ -519,13 +519,13 @@ class PDFUtil:
                     if start_index == -1:
                         continue
                     if start_index > 0:
-                        previous_char = text[start_index - 1]
-                        if previous_char not in [" ", "("]:
+                        previous_char = text[start_index - 1].strip()
+                        if previous_char not in ["", " ", "("]:
                             continue
                     end_index = start_index + len(pure_text_block)
                     if end_index < len(text):
-                        next_char = text[end_index]
-                        if next_char not in [" ", "%", ")"]:
+                        next_char = text[end_index].strip()
+                        if next_char not in ["", " ", "%", ")"]:
                             continue
                     new_matching_val_area.append(area)
             matching_val_area = new_matching_val_area
@@ -561,13 +561,13 @@ class PDFUtil:
                                     # get start and end index of the highlight_text_inside_block in text
                                     start_index = text.find(highlight_text_inside_block)
                                     if start_index > 0:
-                                        previous_char = text[start_index - 1]
-                                        if previous_char not in [" ", "("]:
+                                        previous_char = text[start_index - 1].strip()
+                                        if previous_char not in ["", " ", "("]:
                                             continue
                                     end_index = start_index + len(highlight_text_inside_block)
                                     if end_index < len(text):
-                                        next_char = text[end_index]
-                                        if next_char not in [" ", "%", ")"]:
+                                        next_char = text[end_index].strip()
+                                        if next_char not in ["", " ", "%", ")"]:
                                             continue
                                     highlight_bbox_list.append(area)
                         else: