from robotoff import settings
from robotoff.products import ProductDataset
from robotoff.utils import dump_jsonl, get_logger
logger = get_logger()
def images_dimension_iter():
dataset = ProductDataset.load()
for product in dataset.stream().filter_nonempty_text_field("code"):
images = product.get("images", {})
for image_id, image_data in images.items():
if not image_id.isdigit():
continue
if "full" not in image_data["sizes"]:
continue
width = image_data["sizes"]["full"]["w"]
height = image_data["sizes"]["full"]["h"]
yield [int(width), int(height), product["code"], str(image_id)]
dump_jsonl(settings.PROJECT_DIR / "images_dimension.jsonl", images_dimension_iter())
from robotoff.insights.importer import (
AUTHORIZED_LABELS_STORE,
import_insights as import_insights_,
)
from robotoff.insights.ocr import (
extract_insights,
get_barcode_from_path,
ocr_iter,
OCRResult,
)
from robotoff.models import db, ProductInsight
from robotoff.off import get_product
from robotoff.products import get_product_store
from robotoff.utils import get_logger, jsonl_iter
logger = get_logger(__name__)
def run_from_ocr_archive(
input_: Union[str, TextIO],
insight_type: InsightType,
output: Optional[str] = None,
keep_empty: bool = False,
):
insights = generate_from_ocr_archive(input_, insight_type, keep_empty)
if output is not None:
output_f = open(output, "w")
else:
output_f = sys.stdout
def generate_ocr_insights(input_: str, insight_type: str, output: str):
from robotoff.cli import insights
from robotoff.utils import get_logger
get_logger()
insights.run_from_ocr_archive(input_, insight_type, output)