File size: 5,823 Bytes
641ff3e 2a4b347 641ff3e 2a4b347 641ff3e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 |
# %%
from typing import List
from presidio_analyzer import AnalyzerEngine, PatternRecognizer, EntityRecognizer, Pattern, RecognizerResult
from presidio_analyzer.nlp_engine import SpacyNlpEngine, NlpArtifacts
import spacy
spacy.prefer_gpu()
from spacy.cli.download import download
import re
# %%
model_name = "en_core_web_lg" #"en_core_web_trf"
score_threshold = 0.001
# %% [markdown]
# #### Custom recognisers
# %%
# Custom title recogniser
import re
titles_list = ["Sir", "Ma'am", "Madam", "Mr", "Mr.", "Mrs", "Mrs.", "Ms", "Ms.", "Miss", "Dr", "Dr.", "Professor"]
titles_regex = '\\b' + ' \\b|\\b'.join(rf"{re.escape(street_type)}" for street_type in titles_list) + ' \\b'
titles_pattern = Pattern(name="titles_pattern",regex=titles_regex, score = 1)
titles_recogniser = PatternRecognizer(supported_entity="TITLES", patterns = [titles_pattern])
# %%
# Custom postcode recogniser
# Define the regex pattern in a Presidio `Pattern` object:
ukpostcode_pattern = Pattern(name="ukpostcode_pattern",regex="\\b(?:[A-Z][A-HJ-Y]?[0-9][0-9A-Z]? ?[0-9][A-Z]{2}|GIR ?0A{2})\\b|(?:[A-Z][A-HJ-Y]?[0-9][0-9A-Z]? ?[0-9]{1}?)$|\\b(?:[A-Z][A-HJ-Y]?[0-9][0-9A-Z]?)\\b", score = 1)
# Define the recognizer with one or more patterns
ukpostcode_recogniser = PatternRecognizer(supported_entity="UKPOSTCODE", patterns = [ukpostcode_pattern])
# %%
# Examples for testing
#text = "I live in 510 Broad st SE5 9NG ."
#numbers_result = ukpostcode_recogniser.analyze(text=text, entities=["UKPOSTCODE"])
#print("Result:")
#print(numbers_result)
# %%
def extract_street_name(text:str) -> str:
"""
Extracts the street name and preceding word (that should contain at least one number) from the given text.
"""
street_types = [
'Street', 'St', 'Boulevard', 'Blvd', 'Highway', 'Hwy', 'Broadway', 'Freeway',
'Causeway', 'Cswy', 'Expressway', 'Way', 'Walk', 'Lane', 'Ln', 'Road', 'Rd',
'Avenue', 'Ave', 'Circle', 'Cir', 'Cove', 'Cv', 'Drive', 'Dr', 'Parkway', 'Pkwy',
'Park', 'Court', 'Ct', 'Square', 'Sq', 'Loop', 'Place', 'Pl', 'Parade', 'Estate',
'Alley', 'Arcade', 'Avenue', 'Ave', 'Bay', 'Bend', 'Brae', 'Byway', 'Close', 'Corner', 'Cove',
'Crescent', 'Cres', 'Cul-de-sac', 'Dell', 'Drive', 'Dr', 'Esplanade', 'Glen', 'Green', 'Grove', 'Heights', 'Hts',
'Mews', 'Parade', 'Path', 'Piazza', 'Promenade', 'Quay', 'Ridge', 'Row', 'Terrace', 'Ter', 'Track', 'Trail', 'View', 'Villas',
'Marsh', 'Embankment', 'Cut', 'Hill', 'Passage', 'Rise', 'Vale', 'Side'
]
# Dynamically construct the regex pattern with all possible street types
street_types_pattern = '|'.join(rf"{re.escape(street_type)}" for street_type in street_types)
# The overall regex pattern to capture the street name and preceding word(s)
pattern = rf'(?P<preceding_word>\w*\d\w*)\s*'
pattern += rf'(?P<street_name>\w+\s*\b(?:{street_types_pattern})\b)'
# Find all matches in text
matches = re.finditer(pattern, text, re.IGNORECASE)
start_positions = []
end_positions = []
for match in matches:
preceding_word = match.group('preceding_word').strip()
street_name = match.group('street_name').strip()
start_pos = match.start()
end_pos = match.end()
print(f"Start: {start_pos}, End: {end_pos}")
print(f"Preceding words: {preceding_word}")
print(f"Street name: {street_name}")
print()
start_positions.append(start_pos)
end_positions.append(end_pos)
return start_positions, end_positions
# %%
# Some examples for testing
#text = "1234 Main Street, 5678 Oak Rd, 9ABC Elm Blvd, 42 Eagle st."
#text = "Roberto lives in Five 10 Broad st in Oregon"
#text = "Roberto lives in 55 Oregon Square"
#text = "There is 51a no way I will do that"
#text = "I am writing to apply for"
#extract_street_name(text)
# %%
class StreetNameRecognizer(EntityRecognizer):
def load(self) -> None:
"""No loading is required."""
pass
def analyze(self, text: str, entities: List[str], nlp_artifacts: NlpArtifacts) -> List[RecognizerResult]:
"""
Logic for detecting a specific PII
"""
start_pos, end_pos = extract_street_name(text)
results = []
for i in range(0, len(start_pos)):
result = RecognizerResult(
entity_type="STREETNAME",
start = start_pos[i],
end = end_pos[i],
score= 1
)
results.append(result)
return results
street_recogniser = StreetNameRecognizer(supported_entities=["STREETNAME"])
# %%
# Create a class inheriting from SpacyNlpEngine
class LoadedSpacyNlpEngine(SpacyNlpEngine):
def __init__(self, loaded_spacy_model):
super().__init__()
self.nlp = {"en": loaded_spacy_model}
# %%
# Load spacy model
try:
import en_core_web_lg
nlp = en_core_web_lg.load()
print("Successfully imported spaCy model")
except:
download("en_core_web_lg")
nlp = spacy.load("en_core_web_lg")
print("Successfully downloaded and imported spaCy model")
# Pass the loaded model to the new LoadedSpacyNlpEngine
loaded_nlp_engine = LoadedSpacyNlpEngine(loaded_spacy_model = nlp)
# %%
nlp_analyser = AnalyzerEngine(nlp_engine=loaded_nlp_engine,
default_score_threshold=score_threshold,
supported_languages=["en"],
log_decision_process=True,
)
# %%
nlp_analyser.registry.add_recognizer(street_recogniser)
nlp_analyser.registry.add_recognizer(ukpostcode_recogniser)
nlp_analyser.registry.add_recognizer(titles_recogniser)
|