refactor: add off sdk

pyproject.toml

@@ -78,6 +78,7 @@ lark = "~1.1.4"
 h5py = "~3.8.0"
 opencv-contrib-python = "~4.7.0.72"
 toml = "~0.10.2"
+openfoodfacts = "~0.1.5"
 
 [tool.poetry.dependencies.sentry-sdk]
 version = "~1.14.0"

robotoff/insights/importer.py

@@ -863,7 +863,7 @@ def add_optional_fields(cls, insight: ProductInsight, product: Optional[Product]
         campaigns = []
         if (
             insight.value_tag in taxonomy
-            and "agribalyse_food_code" in taxonomy[insight.value_tag].additional_data
+            and "agribalyse_food_code" in taxonomy[insight.value_tag].properties
         ):
             # This category is linked to an agribalyse category, add it as a
             # campaign tag

robotoff/off.py

@@ -6,6 +6,7 @@
 from urllib.parse import urlparse
 
 import requests
+from openfoodfacts.images import split_barcode
 from requests.exceptions import JSONDecodeError
 
 from robotoff import settings
@@ -95,41 +96,6 @@ def get_barcode_from_path(path: str) -> Optional[str]:
     return barcode or None
 
 
-BARCODE_PATH_REGEX = re.compile(r"^(...)(...)(...)(.*)$")
-
-
-def split_barcode(barcode: str) -> list[str]:
-    """Split barcode in the same way as done by Product Opener to generate a
-    product image folder.
-
-    :param barcode: The barcode of the product. For the pro platform only,
-        it must be prefixed with the org ID using the format
-        `{ORG_ID}/{BARCODE}`
-    :raises ValueError: raise a ValueError if `barcode` is invalid
-    :return: a list containing the splitted barcode
-    """
-    org_id = None
-    if "/" in barcode:
-        # For the pro platform, `barcode` is expected to be in the format
-        # `{ORG_ID}/{BARCODE}` (ex: `org-lea-nature/3307130803004`)
-        org_id, barcode = barcode.split("/", maxsplit=1)
-
-    if not barcode.isdigit():
-        raise ValueError(f"unknown barcode format: {barcode}")
-
-    match = BARCODE_PATH_REGEX.fullmatch(barcode)
-
-    splits = [x for x in match.groups() if x] if match else [barcode]
-
-    if org_id is not None:
-        # For the pro platform only, images and OCRs belonging to an org
-        # are stored in a folder named after the org for all its products, ex:
-        # https://images.pro.openfoodfacts.org/images/products/org-lea-nature/330/713/080/3004/1.jpg
-        splits.append(org_id)
-
-    return splits
-
-
 def _generate_file_path(product_id: ProductIdentifier, image_id: str, suffix: str):
     splitted_barcode = split_barcode(product_id.barcode)
     return f"/{'/'.join(splitted_barcode)}/{image_id}{suffix}"

robotoff/prediction/category/neural/keras_category_classifier_3_0/preprocessing.py

@@ -8,7 +8,7 @@
 import numpy as np
 
 from robotoff import settings
-from robotoff.taxonomy import Taxonomy, fetch_taxonomy
+from robotoff.taxonomy import Taxonomy
 from robotoff.types import JSONType
 from robotoff.utils.text import KeywordProcessor
 
@@ -35,11 +35,7 @@
 
 @functools.cache
 def get_ingredient_taxonomy():
-    return fetch_taxonomy(
-        "",
-        V3_MODEL_DATA_DIR / "ingredients.full.json.gz",
-        offline=True,
-    )
+    return Taxonomy.from_path(V3_MODEL_DATA_DIR / "ingredients.full.json.gz")
 
 
 @functools.cache