From b2838cf914de13907cfe34543e1c699f7b9c92d8 Mon Sep 17 00:00:00 2001
From: Nitwix <niels.lachat@protonmail.ch>
Date: Sat, 12 Apr 2025 22:58:37 +0200
Subject: [PATCH] Fix passport OCR B -> 8

---
 tests/dummy.py                   | 19 +++++++++++++------
 tests/test_extraction.py         |  2 +-
 tests/test_parser.py             |  6 ++++--
 utils/parsers/passport_parser.py |  5 ++++-
 4 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/tests/dummy.py b/tests/dummy.py
index 87c43f8..48f32b3 100644
--- a/tests/dummy.py
+++ b/tests/dummy.py
@@ -1,4 +1,5 @@
 from datetime import date
+import glob
 import json
 from typing import Any
 import config
@@ -111,10 +112,16 @@ def dummy_data() -> ExtractedData:
         profile=dummy_profile(),
     )
 
-def dummy_client_data() -> dict[str, Any]:
-    # TODO make generic
-    resp_path = f"{config.GAME_FILES_DIR}/fc3b1f5a-296d-4cd0-a560-cfa5a6f8d302/000000_decision_accept_active/000000_response.json"
-    out = {}
-    with open(resp_path, "r") as file:
-        out = json.loads(file.read())["client_data"]
+def dummy_client_data() -> list[dict[str, Any]]:
+    glob_str = f"{config.GAME_FILES_DIR}/**/*_response.json"
+    responses = glob.glob(glob_str, recursive=True)
+    out = []
+    for resp_path in responses:
+        c_data = None
+        with open(resp_path, "r") as file:
+            loaded = json.loads(file.read())
+            print(f"Loaded {resp_path}")
+            c_data = loaded["client_data"]
+        if not c_data is None:
+            out.append(c_data)
     return out
\ No newline at end of file
diff --git a/tests/test_extraction.py b/tests/test_extraction.py
index ef05ad0..1e1a4da 100644
--- a/tests/test_extraction.py
+++ b/tests/test_extraction.py
@@ -3,6 +3,6 @@ from tests.dummy import dummy_client_data
 
 
 def test_extract_passport() -> None:
-    client_data = dummy_client_data()
+    client_data = dummy_client_data()[0]
     passport = extract_passport(client_data)
     passport
\ No newline at end of file
diff --git a/tests/test_parser.py b/tests/test_parser.py
index db98168..20acae5 100644
--- a/tests/test_parser.py
+++ b/tests/test_parser.py
@@ -3,5 +3,7 @@ from utils.parsers.passport_parser import process_passport
 
 
 def test_passport_parser() -> None:
-    client_data = dummy_client_data()
-    process_passport(client_data.get("passport"))
\ No newline at end of file
+    client_data = dummy_client_data()[0]
+
+    passport = process_passport(client_data.get("passport"))
+    passport
\ No newline at end of file
diff --git a/utils/parsers/passport_parser.py b/utils/parsers/passport_parser.py
index 1b392c2..58d2b6e 100644
--- a/utils/parsers/passport_parser.py
+++ b/utils/parsers/passport_parser.py
@@ -25,10 +25,13 @@ def process_passport(passport_b64: str) -> str:
     tesseract_text = pytesseract.image_to_string(image, lang='eng')
     out_dict = {}
     if not mrz_obj is None:
+        number_raw = str(mrz_obj.number)
+        # It's not called a 'Hack'athon for nothing...
+        number = number_raw.replace("B", "8")
         out_dict = {
             "country": mrz_obj.country,
             "names": mrz_obj.names,
-            "number": mrz_obj.number,
+            "number": number,
             "surname": mrz_obj.surname,
             "mrz": mrz_obj.aux["text"],
         }