def extract_ocr_insights(
ocr_url: str, insight_types: Iterable[InsightType]
) -> Dict[InsightType, ProductInsights]:
source_image = get_source_from_ocr_url(ocr_url)
barcode = get_barcode_from_url(ocr_url)
if barcode is None:
raise ValueError("cannot extract barcode fro URL: {}".format(ocr_url))
ocr_result = get_ocr_result(ocr_url)
if ocr_result is None:
logger.info("Error during OCR extraction: {}".format(ocr_url))
return {}
results = {}
for insight_type in insight_types:
insights = ocr.extract_insights(ocr_result, insight_type)
if insights:
results[insight_type] = ProductInsights(
barcode=barcode,
insights=insights,
source_image=source_image,
type=insight_type,
)
return results
def extract_ocr_insights(ocr_url: str) -> JSONType:
r = requests.get(ocr_url)
if r.status_code == 404:
logger.info("OCR JSON {} not found".format(ocr_url))
return {}
r.raise_for_status()
ocr_data: Dict = requests.get(ocr_url).json()
ocr_result = ocr.OCRResult.from_json(ocr_data)
if ocr_result is None:
logger.info("Error during OCR extraction: {}".format(ocr_url))
return {}
results = {}
for insight_type in (InsightType.label.name,
InsightType.packager_code.name,
InsightType.product_weight.name,
InsightType.image_flag.name,
InsightType.expiration_date.name,
InsightType.brand.name, InsightType.store.name):
insights = ocr.extract_insights(ocr_result, insight_type)
if insights:
results[insight_type] = insights
return results
def get_insights_from_product_name(barcode: str, product_name: str) -> Dict:
results = {}
for insight_type in PRODUCT_NAME_INSIGHT_TYPES:
insights = ocr.extract_insights(product_name, insight_type)
if insights:
for insight in insights:
insight["source"] = "product_name"
results[insight_type] = {
"insights": insights,
"barcode": barcode,
"type": insight_type,
}
return results
def get_insights_from_product_name(
barcode: str, product_name: str) -> Dict[InsightType, ProductInsights]:
results = {}
for insight_type in PRODUCT_NAME_INSIGHT_TYPES:
insights = ocr.extract_insights(product_name, insight_type)
if insights:
for insight in insights:
insight.data["source"] = "product_name"
results[insight_type] = ProductInsights(
insights=insights,
barcode=barcode,
type=insight_type,
)
return results
def extract_ocr_insights(ocr_url: str,
insight_types: Iterable[str]) -> JSONType:
r = http_session.get(ocr_url)
r.raise_for_status()
ocr_data: Dict = r.json()
ocr_result = ocr.OCRResult.from_json(ocr_data)
if ocr_result is None:
logger.info("Error during OCR extraction: {}".format(ocr_url))
return {}
results = {}
for insight_type in insight_types:
insights = ocr.extract_insights(ocr_result, insight_type)
if insights:
results[insight_type] = insights
return results
def run_from_ocr_archive(input_: str, insight_type: str,
output: Optional[str]):
if output is not None:
output_f = open(output, 'w')
else:
output_f = sys.stdout
with contextlib.closing(output_f):
for source, ocr_json in ocr_iter(input_):
if source is None:
continue
barcode: Optional[str] = get_barcode_from_path(source)
if barcode is None:
click.echo("cannot extract barcode from source "
"{}".format(source),
err=True)
continue
ocr_result: Optional[OCRResult] = OCRResult.from_json(ocr_json)
if ocr_result is None:
continue
insights = extract_insights(ocr_result, insight_type)
if insights:
item = {
'insights': insights,
'barcode': barcode,
'type': insight_type,
}
if source:
item['source'] = source
output_f.write(json.dumps(item) + '\n')
def generate_from_ocr_archive(
input_: Union[str, TextIO, pathlib.Path],
insight_type: InsightType,
keep_empty: bool = False,
) -> Iterable[ProductInsights]:
for source_image, ocr_json in ocr_iter(input_):
if source_image is None:
continue
barcode: Optional[str] = get_barcode_from_path(source_image)
if barcode is None:
click.echo(
"cannot extract barcode from source "
"{}".format(source_image),
err=True,
)
continue
ocr_result: Optional[OCRResult] = OCRResult.from_json(ocr_json)
if ocr_result is None:
continue
insights = extract_insights(ocr_result, insight_type)
# Do not produce output if insights is empty and we don't want to keep it
if not keep_empty and not insights:
continue
yield ProductInsights(
insights=insights,
barcode=barcode,
type=insight_type,
source_image=source_image,
)