chore: add script for local and container debug

scripts/debug/debug.py

@@ -0,0 +1,45 @@
+import json
+import os
+
+from kn_utils.logging import logger
+
+from image_prediction.config import CONFIG
+from image_prediction.pipeline import load_pipeline
+from image_prediction.utils.pdf_annotation import annotate_pdf
+import numpy as np
+import random
+import tensorflow as tf
+
+
+def process_pdf(pipeline, pdf_path, page_range=None):
+    with open(pdf_path, "rb") as f:
+        logger.info(f"Processing {pdf_path}")
+        predictions = list(pipeline(f.read(), page_range=page_range))
+
+    return predictions
+
+def ensure_seeds():
+    seed = 42
+    np.random.seed(seed)
+    random.seed(seed)
+    tf.random.set_seed(seed)
+
+def debug_info():
+    devices = tf.config.list_physical_devices()
+    print("Available devices:", devices)
+    current_path = os.path.dirname(os.path.abspath(__file__))
+    print(current_path)
+
+
+if __name__ == "__main__":
+    # Change to path in docker container
+    debug_file_path = "./src/debug.pdf"
+    ensure_seeds()
+    debug_info()
+
+    pipeline = load_pipeline(verbose=True, batch_size=CONFIG.service.batch_size)
+    predictions = process_pdf(pipeline, debug_file_path)
+    # This is the image that has the wrong prediction mentioned in RED-9948. The predictions should inconclusive, and
+    # the flag all passed should be false.
+    predictions = [x for x in predictions if x["representation"] == "FA30F080F0C031CE17E8CF237"]
+    print(json.dumps(predictions, indent=2))

test/unit_tests/encoder_test.py

@@ -36,7 +36,7 @@ def test_hash_encoder(images, hashed_images, base_patch_image):
 
 def test_all_hashes_have_length_of_twentyfive():
     """See RED-3814: all hashes should have 25 characters."""
-    pdf_path = Path(__file__).parents[1] / "data" / "similarImages2.pdf"
+    pdf_path = Path(__file__).parents[1] / "data" / "RED-3814" / "similarImages2.pdf"
     pdf_bytes = pdf_path.read_bytes()
     image_extractor = ParsablePDFImageExtractor()
     image_metadata_pairs = list(image_extractor.extract(pdf_bytes))