def from_dict(cls, data: JSONType) -> 'Taxonomy':
taxonomy = Taxonomy()
for key, key_data in data.items():
if key not in taxonomy:
node = TaxonomyNode(identifier=key,
names=key_data.get('name', {}))
taxonomy.add(key, node)
for key, key_data in data.items():
node = taxonomy[key]
parents = [taxonomy[ref] for ref in key_data.get('parents', [])]
node.add_parents(parents)
return taxonomy
def from_dict(cls, data: JSONType) -> "Taxonomy":
taxonomy = Taxonomy()
for key, key_data in data.items():
if key not in taxonomy:
node = TaxonomyNode(
identifier=key,
names=key_data.get("name", {}),
synonyms=key_data.get("synonyms", None),
)
taxonomy.add(key, node)
for key, key_data in data.items():
node = taxonomy[key]
parents = [taxonomy[ref] for ref in key_data.get("parents", [])]
node.add_parents(parents)
return taxonomy
def is_selected_image(product_images: JSONType, image_id: str) -> bool:
for key_prefix in ("nutrition", "front", "ingredients"):
for key, image in product_images.items():
if key.startswith(key_prefix):
if image["imgid"] == image_id:
logger.debug("Image {} is a selected image for "
"'{}'".format(image_id, key_prefix))
return True
return False
def print_generic_insight(insight: JSONType) -> None:
for key, value in insight.items():
click.echo("{}: {}".format(key, str(value)))
click.echo("url: {}/product/{}".format(settings.BaseURLProvider().get(),
insight["barcode"]))
if "source" in insight:
click.echo("image: {}{}".format(settings.OFF_IMAGE_BASE_URL,
insight["source"]))
click.echo("")
def print_generic_insight(insight: JSONType) -> None:
for key, value in insight.items():
click.echo("{}: {}".format(key, str(value)))
click.echo("url: {}".format("https://fr.openfoodfacts.org/produit/"
"{}".format(insight["barcode"])))
if "source" in insight:
click.echo("image: {}{}".format(STATIC_IMAGE_DIR_URL,
insight["source"]))
click.echo("")
def find_nutrition_image_nutrient_languages(
mentions: JSONType, ) -> Dict[str, Dict[str, int]]:
languages: Dict[str, Dict[str, int]] = {}
for nutrient, matches in mentions.items():
seen_lang: Set[str] = set()
for match in matches:
for lang in match.get("languages", []):
if lang not in seen_lang:
languages.setdefault(nutrient, {})
nutrient_languages = languages[nutrient]
nutrient_languages.setdefault(lang, 0)
nutrient_languages[lang] += 1
seen_lang.add(lang)
return languages
def is_recent_image(product_images: JSONType, image_id: str,
max_timedelta: datetime.timedelta) -> bool:
upload_datetimes = []
insight_image_upload_datetime: Optional[datetime.datetime] = None
for key, image_meta in product_images.items():
if not key.isdigit():
continue
upload_datetime = datetime.datetime.utcfromtimestamp(
int(image_meta["uploaded_t"]))
if key == image_id:
insight_image_upload_datetime = upload_datetime
else:
upload_datetimes.append(upload_datetime)
if not upload_datetimes:
logger.debug("No other images")
return True
if insight_image_upload_datetime is None:
raise ValueError("Image with ID {} not found".format(image_id))
else:
for upload_datetime in upload_datetimes:
if upload_datetime - insight_image_upload_datetime > max_timedelta:
logger.debug("More recent image: {} > {}".format(
upload_datetime, insight_image_upload_datetime))
return False
sorted_datetimes = [
str(x) for x in sorted(set(x.date() for x in upload_datetimes),
reverse=True)
]
logger.debug(
"All images were uploaded the same day or before the target "
"image:\n{} >= {}".format(insight_image_upload_datetime.date(),
", ".join(sorted_datetimes)))
return True
logger.debug("More recent images: {} < {}".format(
insight_image_upload_datetime.date(),
max(x.date() for x in upload_datetimes),
))
return False
def is_special_image(images: JSONType,
image_path: str,
image_type: str,
lang: Optional[str] = None) -> bool:
if not is_valid_image(images, image_path):
return False
image_id = pathlib.Path(image_path).stem
for image_key, image_data in images.items():
if (image_key.startswith(image_type)
and str(image_data.get("imgid")) == image_id):
if lang is None:
return True
elif image_key.endswith("_{}".format(lang)):
return True
return False