We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent b824c1a commit 7dbe1c6Copy full SHA for 7dbe1c6
pii/utils/emails_ip_addresses_detection.py
@@ -24,6 +24,7 @@
24
from gibberish_detector import detector
25
26
# Regexes for PII detection
27
+GIBBERISH_MODEL_PATH = './gibberish_data/big.model'
28
29
year_patterns = [
30
regex.compile(
@@ -149,7 +150,7 @@ def is_gibberish(matched_str):
149
150
# pip install gibberish-detector
151
# download the training corpora from https://raw.githubusercontent.com/domanchi/gibberish-detector/master/examples/big.txt
152
# run gibberish-detector train big.txt > big.model to generate the model (it takes 3 seconds)
- Detector = detector.create_from_model('gibberish_data/big.model')
153
+ Detector = detector.create_from_model(GIBBERISH_MODEL_PATH)
154
return Detector.is_gibberish(matched_str.lower())
155
156
0 commit comments