def flag_image(ocr_result: OCRResult) -> List[Dict]:
safe_search_annotation = ocr_result.get_safe_search_annotation()
label_annotations = ocr_result.get_label_annotations()
insights: List[Dict] = []
if safe_search_annotation:
for key in ('adult', 'violence'):
value: SafeSearchAnnotationLikelihood = \
getattr(safe_search_annotation, key)
if value >= SafeSearchAnnotationLikelihood.VERY_LIKELY:
insights.append({
'type': key,
'likelihood': value.name,
})
for label_annotation in label_annotations:
if (label_annotation.description in ('Face', 'Head', 'Selfie')
and label_annotation.score >= 0.8):
insights.append({
'type': label_annotation.description.lower(),
'likelihood': label_annotation.score
})
break
return insights
def find_expiration_date(ocr_result: OCRResult) -> List[Dict]:
# Parse expiration date
# "À consommer de préférence avant",
results = []
for type_, ocr_regex in EXPIRATION_DATE_REGEX.items():
text = ocr_result.get_text(ocr_regex)
if not text:
continue
for match in ocr_regex.regex.finditer(text):
raw = match.group(0)
if not ocr_regex.processing_func:
continue
date = ocr_regex.processing_func(match)
if date is None:
continue
if date.year > 2025 or date.year < 2015:
continue
value = date.strftime("%d/%m/%Y")
results.append({
"raw": raw,
"text": value,
"type": type_,
"notify": ocr_regex.notify,
})
return results
def find_labels(ocr_result: OCRResult) -> List[Dict]:
results = []
for label_tag, regex_list in LABELS_REGEX.items():
for ocr_regex in regex_list:
text = ocr_result.get_text(ocr_regex)
if not text:
continue
for match in ocr_regex.regex.finditer(text):
if ocr_regex.processing_func:
label_value = ocr_regex.processing_func(match)
else:
label_value = label_tag
results.append({
'label_tag': label_value,
'text': match.group(),
'notify': ocr_regex.notify,
})
for logo_annotation in ocr_result.logo_annotations:
if logo_annotation.description in LOGO_ANNOTATION_LABELS:
label_tag = LOGO_ANNOTATION_LABELS[logo_annotation.description]
results.append({
'label_tag': label_tag,
'automatic_processing': False,
'confidence': logo_annotation.score,
'model': 'google-cloud-vision',
})
return results
def find_nutrient_values(ocr_result: OCRResult) -> List[Dict]:
nutrients: JSONType = {}
for regex_code, ocr_regex in NUTRIENT_VALUES_REGEX.items():
text = ocr_result.get_text(ocr_regex)
if not text:
continue
for match in ocr_regex.regex.finditer(text):
value = match.group(2).replace(',', '.')
unit = match.group(3)
nutrients.setdefault(regex_code, [])
nutrients[regex_code].append({
"raw": match.group(0),
"nutrient": regex_code,
'value': value,
'unit': unit,
})
if not nutrients:
return []
return [
{
'nutrients': nutrients,
'notify': False,
}
]
def find_image_orientation(ocr_result: OCRResult) -> List[Dict]:
orientation_result = ocr_result.get_orientation()
if (orientation_result is None
or orientation_result.orientation == ImageOrientation.up):
return []
return [orientation_result.to_json()]
def get_text(ocr_result: OCRResult) -> str:
"""Extract text from the OCR result and prepare it.
Args:
ocr_result (OCRResult): The OCR result to process.
Returns:
str: The text extracted and prepared.
"""
text = ocr_result.get_full_text()
if text is None:
# Using `OCRResult.text_annotations` directly instead of
# `OCRResult.get_text_annotations()` because the latter contains
# the text duplicated
text = ocr_result.text_annotations[0].text
return text
def find_packager_codes(ocr_result: OCRResult) -> List[Dict]:
results = []
for regex_code, ocr_regex in PACKAGER_CODE.items():
text = ocr_result.get_text(ocr_regex)
if not text:
continue
for match in ocr_regex.regex.finditer(text):
if ocr_regex.processing_func is not None:
value = ocr_regex.processing_func(match)
results.append({
"raw": match.group(0),
"text": value,
"type": regex_code,
"notify": ocr_regex.notify,
})
return results
def find_product_weight(ocr_result: OCRResult) -> List[Dict]:
results = []
for type_, ocr_regex in PRODUCT_WEIGHT_REGEX.items():
text = ocr_result.get_text(ocr_regex)
if not text:
continue
for match in ocr_regex.regex.finditer(text):
if ocr_regex.processing_func is None:
continue
result = ocr_regex.processing_func(match)
result['matcher_type'] = type_
result['priority'] = ocr_regex.priority
result['notify'] = ocr_regex.notify
results.append(result)
return results
def find_traces(ocr_result: OCRResult) -> List[Dict]:
results = []
text = ocr_result.get_text(TRACES_REGEX)
if not text:
return []
for match in TRACES_REGEX.regex.finditer(text):
raw = match.group()
end_idx = match.end()
captured = text[end_idx:end_idx + 100]
result = {
'raw': raw,
'text': captured,
'notify': TRACES_REGEX.notify,
}
results.append(result)
return results
def find_nutrient_values(ocr_result: OCRResult) -> List[Dict]:
results = []
for regex_code, ocr_regex in NUTRIENT_VALUES_REGEX.items():
text = ocr_result.get_text(ocr_regex)
if not text:
continue
for match in ocr_regex.regex.finditer(text):
value = match.group(2).replace(',', '.')
unit = match.group(3)
results.append({
"raw": match.group(0),
"nutrient": regex_code,
'value': value,
'unit': unit,
'notify': ocr_regex.notify,
})
return results
def find_stores(ocr_result: OCRResult) -> List[Dict]:
results = []
text = ocr_result.get_text(STORE_REGEX)
if not text:
return []
for match in STORE_REGEX.regex.finditer(text):
groups = match.groups()
for idx, match_str in enumerate(groups):
if match_str is not None:
store, _ = SORTED_STORES[idx]
results.append({
'store': store,
'store_tag': get_store_tag(store),
'text': match_str,
'notify': store in NOTIFY_STORES,
})
break
return results
def find_brands(ocr_result: OCRResult) -> List[Dict]:
results = []
text = ocr_result.get_text(BRAND_REGEX)
if not text:
return []
for match in BRAND_REGEX.regex.finditer(text):
groups = match.groups()
for idx, match_str in enumerate(groups):
if match_str is not None:
brand, _ = SORTED_BRANDS[idx]
results.append({
'brand': brand,
'brand_tag': get_brand_tag(brand),
'text': match_str,
'notify': brand in NOTIFY_BRANDS,
})
return results
for logo_annotation in ocr_result.logo_annotations:
if logo_annotation.description in LOGO_ANNOTATION_BRANDS:
brand = LOGO_ANNOTATION_BRANDS[logo_annotation.description]
results.append({
'brand': brand,
'brand_tag': get_brand_tag(brand),
'automatic_processing': False,
'confidence': logo_annotation.score,
'model': 'google-cloud-vision',
'notify': False,
})
return results
return results
def test_ocr_result_extraction_non_regression(ocr_name: str):
with (data_dir / ocr_name).open("r") as f:
data = json.load(f)
result = OCRResult.from_json(data)
assert result
