Spaces:
Runtime error
Runtime error
Commit
·
d1e3e7b
1
Parent(s):
22701ae
test
Browse files- app.py +6 -0
- badwords.py +2682 -0
- en.arpa.bin +3 -0
- en.sp.model +3 -0
- filtering.py +879 -0
- languages_id.py +231 -0
- lid.176.bin +3 -0
- normalization.py +52 -0
- requirements.txt → packages.txt +0 -0
- parameters_filtering.py +852 -0
- stopwords.py +0 -0
app.py
CHANGED
|
@@ -13,6 +13,8 @@ import numpy as np
|
|
| 13 |
|
| 14 |
import matplotlib.pyplot as plt
|
| 15 |
|
|
|
|
|
|
|
| 16 |
|
| 17 |
class Visualization:
|
| 18 |
def __init__(
|
|
@@ -390,6 +392,9 @@ class Visualization:
|
|
| 390 |
ax.set_ylabel("frequency in the documents")
|
| 391 |
st.pyplot(fig)
|
| 392 |
|
|
|
|
|
|
|
|
|
|
| 393 |
def download_data(self):
|
| 394 |
st.header("Download data")
|
| 395 |
|
|
@@ -408,6 +413,7 @@ class Visualization:
|
|
| 408 |
self.filtering_of_words()
|
| 409 |
self.plot_distributions_filtering_parameters()
|
| 410 |
#self.plot_zipf_law()
|
|
|
|
| 411 |
self.download_data()
|
| 412 |
|
| 413 |
|
|
|
|
| 13 |
|
| 14 |
import matplotlib.pyplot as plt
|
| 15 |
|
| 16 |
+
from filtering import Filtering
|
| 17 |
+
|
| 18 |
|
| 19 |
class Visualization:
|
| 20 |
def __init__(
|
|
|
|
| 392 |
ax.set_ylabel("frequency in the documents")
|
| 393 |
st.pyplot(fig)
|
| 394 |
|
| 395 |
+
def check_personal_doc(self):
|
| 396 |
+
pass
|
| 397 |
+
|
| 398 |
def download_data(self):
|
| 399 |
st.header("Download data")
|
| 400 |
|
|
|
|
| 413 |
self.filtering_of_words()
|
| 414 |
self.plot_distributions_filtering_parameters()
|
| 415 |
#self.plot_zipf_law()
|
| 416 |
+
self.check_personal_doc()
|
| 417 |
self.download_data()
|
| 418 |
|
| 419 |
|
badwords.py
ADDED
|
@@ -0,0 +1,2682 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Merge
|
| 2 |
+
# https://github.com/zacanger/profane-words
|
| 3 |
+
# and
|
| 4 |
+
# https://github.com/thisandagain/washyourmouthoutwithsoap/blob/develop/data/build.json
|
| 5 |
+
# and
|
| 6 |
+
# https://github.com/LDNOOBW/List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
english_badwords = [
|
| 10 |
+
"abuse",
|
| 11 |
+
"anal",
|
| 12 |
+
"anilingus",
|
| 13 |
+
"anus",
|
| 14 |
+
"aroused",
|
| 15 |
+
"arse",
|
| 16 |
+
"arsehole",
|
| 17 |
+
"ass",
|
| 18 |
+
"asses",
|
| 19 |
+
"assfuck",
|
| 20 |
+
"asshat",
|
| 21 |
+
"asshole",
|
| 22 |
+
"assholes",
|
| 23 |
+
"autoerotic",
|
| 24 |
+
"bangbros",
|
| 25 |
+
"banging",
|
| 26 |
+
"bareback",
|
| 27 |
+
"bastard",
|
| 28 |
+
"bastards",
|
| 29 |
+
"bazongas",
|
| 30 |
+
"bbw",
|
| 31 |
+
"bdsm",
|
| 32 |
+
"biatch",
|
| 33 |
+
"bicurious",
|
| 34 |
+
"bigass",
|
| 35 |
+
"bigtits",
|
| 36 |
+
"bimbo",
|
| 37 |
+
"bimbos",
|
| 38 |
+
"bitch",
|
| 39 |
+
"bitches",
|
| 40 |
+
"bitching",
|
| 41 |
+
"blowjob",
|
| 42 |
+
"blowjobs",
|
| 43 |
+
"boche",
|
| 44 |
+
"boner",
|
| 45 |
+
"boners",
|
| 46 |
+
"boob",
|
| 47 |
+
"boobies",
|
| 48 |
+
"boobs",
|
| 49 |
+
"booty",
|
| 50 |
+
"brothel",
|
| 51 |
+
"buceta",
|
| 52 |
+
"bugger",
|
| 53 |
+
"buggered",
|
| 54 |
+
"buggery",
|
| 55 |
+
"bukkake",
|
| 56 |
+
"bule",
|
| 57 |
+
"buttcheeks",
|
| 58 |
+
"buttfuck",
|
| 59 |
+
"butthead",
|
| 60 |
+
"butthole",
|
| 61 |
+
"buttplug",
|
| 62 |
+
"cameltoe",
|
| 63 |
+
"camgirl",
|
| 64 |
+
"camwhore",
|
| 65 |
+
"chink",
|
| 66 |
+
"chinks",
|
| 67 |
+
"cialis",
|
| 68 |
+
"clit",
|
| 69 |
+
"clitoris",
|
| 70 |
+
"clits",
|
| 71 |
+
"clitty",
|
| 72 |
+
"clusterfuck",
|
| 73 |
+
"cock",
|
| 74 |
+
"cock-head",
|
| 75 |
+
"cockblock",
|
| 76 |
+
"cockfight",
|
| 77 |
+
"cockhead",
|
| 78 |
+
"cocks",
|
| 79 |
+
"cocksman",
|
| 80 |
+
"cocksucker",
|
| 81 |
+
"cocksucking",
|
| 82 |
+
"coital",
|
| 83 |
+
"coitus",
|
| 84 |
+
"coochie",
|
| 85 |
+
"cooly",
|
| 86 |
+
"coon",
|
| 87 |
+
"coons",
|
| 88 |
+
"copulate",
|
| 89 |
+
"cowgirl",
|
| 90 |
+
"crabs",
|
| 91 |
+
"creampie",
|
| 92 |
+
"cum",
|
| 93 |
+
"cumming",
|
| 94 |
+
"cums",
|
| 95 |
+
"cumshot",
|
| 96 |
+
"cumshots",
|
| 97 |
+
"cumslut",
|
| 98 |
+
"cunnilingus",
|
| 99 |
+
"cunny",
|
| 100 |
+
"cunt",
|
| 101 |
+
"cunts",
|
| 102 |
+
"cybersex",
|
| 103 |
+
"darkey",
|
| 104 |
+
"darkie",
|
| 105 |
+
"darkies",
|
| 106 |
+
"darky",
|
| 107 |
+
"deepthroat",
|
| 108 |
+
"deepthroating",
|
| 109 |
+
"dick",
|
| 110 |
+
"dickhole",
|
| 111 |
+
"dicks",
|
| 112 |
+
"dildo",
|
| 113 |
+
"dildos",
|
| 114 |
+
"dogging",
|
| 115 |
+
"doggy-style",
|
| 116 |
+
"doggystyle",
|
| 117 |
+
"dominatrix",
|
| 118 |
+
"dommes",
|
| 119 |
+
"dong",
|
| 120 |
+
"dp",
|
| 121 |
+
"dupa",
|
| 122 |
+
"dyke",
|
| 123 |
+
"dykes",
|
| 124 |
+
"ecchi",
|
| 125 |
+
"ejaculate",
|
| 126 |
+
"ejaculated",
|
| 127 |
+
"ejaculates",
|
| 128 |
+
"ejaculating",
|
| 129 |
+
"ejaculation",
|
| 130 |
+
"ejaculations",
|
| 131 |
+
"enema",
|
| 132 |
+
"erect",
|
| 133 |
+
"erection",
|
| 134 |
+
"ero",
|
| 135 |
+
"erotic",
|
| 136 |
+
"erotism",
|
| 137 |
+
"escort",
|
| 138 |
+
"fag",
|
| 139 |
+
"fagging",
|
| 140 |
+
"faggot",
|
| 141 |
+
"fagot",
|
| 142 |
+
"fagots",
|
| 143 |
+
"fags",
|
| 144 |
+
"felch",
|
| 145 |
+
"fellate",
|
| 146 |
+
"fellatio",
|
| 147 |
+
"femdom",
|
| 148 |
+
"fetish",
|
| 149 |
+
"figging",
|
| 150 |
+
"fingerbang",
|
| 151 |
+
"fingering",
|
| 152 |
+
"fisted",
|
| 153 |
+
"fister",
|
| 154 |
+
"fisting",
|
| 155 |
+
"floozy",
|
| 156 |
+
"fondle",
|
| 157 |
+
"footfetish",
|
| 158 |
+
"footjob",
|
| 159 |
+
"foreskin",
|
| 160 |
+
"fornicate",
|
| 161 |
+
"foursome",
|
| 162 |
+
"fuck",
|
| 163 |
+
"fuckable",
|
| 164 |
+
"fuckbook",
|
| 165 |
+
"fuckboy",
|
| 166 |
+
"fuckbuddy",
|
| 167 |
+
"fucked",
|
| 168 |
+
"fucker",
|
| 169 |
+
"fuckers",
|
| 170 |
+
"fuckfest",
|
| 171 |
+
"fuckhole",
|
| 172 |
+
"fuckin",
|
| 173 |
+
"fucking",
|
| 174 |
+
"fucks",
|
| 175 |
+
"fuk",
|
| 176 |
+
"fukin",
|
| 177 |
+
"fuking",
|
| 178 |
+
"g-spot",
|
| 179 |
+
"gangbang",
|
| 180 |
+
"gangbanged",
|
| 181 |
+
"gangbanger",
|
| 182 |
+
"gangbangs",
|
| 183 |
+
"genital",
|
| 184 |
+
"genitals",
|
| 185 |
+
"gigolo",
|
| 186 |
+
"glans",
|
| 187 |
+
"gonad",
|
| 188 |
+
"gonads",
|
| 189 |
+
"gook",
|
| 190 |
+
"gringo",
|
| 191 |
+
"gringos",
|
| 192 |
+
"grope",
|
| 193 |
+
"gspot",
|
| 194 |
+
"guido",
|
| 195 |
+
"handjob",
|
| 196 |
+
"haole",
|
| 197 |
+
"hapa",
|
| 198 |
+
"hardcore",
|
| 199 |
+
"hardon",
|
| 200 |
+
"harem",
|
| 201 |
+
"hentai",
|
| 202 |
+
"hindoo",
|
| 203 |
+
"hoe",
|
| 204 |
+
"hoes",
|
| 205 |
+
"honky",
|
| 206 |
+
"hooker",
|
| 207 |
+
"hookers",
|
| 208 |
+
"hooter",
|
| 209 |
+
"hooters",
|
| 210 |
+
"hori",
|
| 211 |
+
"horndog",
|
| 212 |
+
"horney",
|
| 213 |
+
"horniest",
|
| 214 |
+
"horny",
|
| 215 |
+
"humped",
|
| 216 |
+
"humper",
|
| 217 |
+
"humping",
|
| 218 |
+
"hussy",
|
| 219 |
+
"hymen",
|
| 220 |
+
"ikey",
|
| 221 |
+
"incest",
|
| 222 |
+
"injun",
|
| 223 |
+
"intercourse",
|
| 224 |
+
"interracial",
|
| 225 |
+
"jack-off",
|
| 226 |
+
"jackoff",
|
| 227 |
+
"jailbait",
|
| 228 |
+
"jerk-off",
|
| 229 |
+
"jerkoff",
|
| 230 |
+
"jiggy",
|
| 231 |
+
"jism",
|
| 232 |
+
"jizz",
|
| 233 |
+
"jizzed",
|
| 234 |
+
"kaffir",
|
| 235 |
+
"kafir",
|
| 236 |
+
"kike",
|
| 237 |
+
"kikes",
|
| 238 |
+
"kinkster",
|
| 239 |
+
"kinky",
|
| 240 |
+
"kkk",
|
| 241 |
+
"klan",
|
| 242 |
+
"kraut",
|
| 243 |
+
"labia",
|
| 244 |
+
"lapdance",
|
| 245 |
+
"libido",
|
| 246 |
+
"licker",
|
| 247 |
+
"licking",
|
| 248 |
+
"limey",
|
| 249 |
+
"lingerie",
|
| 250 |
+
"livesex",
|
| 251 |
+
"lolita",
|
| 252 |
+
"lovemaking",
|
| 253 |
+
"lust",
|
| 254 |
+
"lusting",
|
| 255 |
+
"masochist",
|
| 256 |
+
"masterbate",
|
| 257 |
+
"masterbating",
|
| 258 |
+
"masterbation",
|
| 259 |
+
"masturbate",
|
| 260 |
+
"masturbating",
|
| 261 |
+
"masturbation",
|
| 262 |
+
"milf",
|
| 263 |
+
"minge",
|
| 264 |
+
"missionary",
|
| 265 |
+
"molest",
|
| 266 |
+
"molestation",
|
| 267 |
+
"molester",
|
| 268 |
+
"munging",
|
| 269 |
+
"muschi",
|
| 270 |
+
"nads",
|
| 271 |
+
"naked",
|
| 272 |
+
"necked",
|
| 273 |
+
"necro",
|
| 274 |
+
"negress",
|
| 275 |
+
"negro",
|
| 276 |
+
"negroes",
|
| 277 |
+
"negroid",
|
| 278 |
+
"negros",
|
| 279 |
+
"nig",
|
| 280 |
+
"nigar",
|
| 281 |
+
"nigga",
|
| 282 |
+
"niggas",
|
| 283 |
+
"niggaz",
|
| 284 |
+
"nigger",
|
| 285 |
+
"niggers",
|
| 286 |
+
"nigra",
|
| 287 |
+
"nipple",
|
| 288 |
+
"nipples",
|
| 289 |
+
"nookie",
|
| 290 |
+
"nooky",
|
| 291 |
+
"nooner",
|
| 292 |
+
"nude",
|
| 293 |
+
"nudie",
|
| 294 |
+
"nudity",
|
| 295 |
+
"nymph",
|
| 296 |
+
"nympho",
|
| 297 |
+
"nymphomania",
|
| 298 |
+
"orgasim",
|
| 299 |
+
"orgasm",
|
| 300 |
+
"orgasms",
|
| 301 |
+
"orgies",
|
| 302 |
+
"orgy",
|
| 303 |
+
"orifice",
|
| 304 |
+
"p0rn",
|
| 305 |
+
"paedophile",
|
| 306 |
+
"pantie",
|
| 307 |
+
"panties",
|
| 308 |
+
"panty",
|
| 309 |
+
"pastie",
|
| 310 |
+
"pecker",
|
| 311 |
+
"pedo",
|
| 312 |
+
"pedophile",
|
| 313 |
+
"pedophilia",
|
| 314 |
+
"pedophiliac",
|
| 315 |
+
"peeper",
|
| 316 |
+
"peepshow",
|
| 317 |
+
"pegging",
|
| 318 |
+
"penetrate",
|
| 319 |
+
"penetration",
|
| 320 |
+
"penile",
|
| 321 |
+
"penis",
|
| 322 |
+
"penises",
|
| 323 |
+
"penus",
|
| 324 |
+
"perv",
|
| 325 |
+
"phallic",
|
| 326 |
+
"phonesex",
|
| 327 |
+
"pickaninnies",
|
| 328 |
+
"pimp",
|
| 329 |
+
"playboy",
|
| 330 |
+
"playgirl",
|
| 331 |
+
"poontang",
|
| 332 |
+
"porn",
|
| 333 |
+
"porno",
|
| 334 |
+
"pornography",
|
| 335 |
+
"pornos",
|
| 336 |
+
"pr0n",
|
| 337 |
+
"premature",
|
| 338 |
+
"preteen",
|
| 339 |
+
"pron",
|
| 340 |
+
"prostitute",
|
| 341 |
+
"pube",
|
| 342 |
+
"pubes",
|
| 343 |
+
"pubic",
|
| 344 |
+
"pubis",
|
| 345 |
+
"punani",
|
| 346 |
+
"pussies",
|
| 347 |
+
"pussy",
|
| 348 |
+
"pussys",
|
| 349 |
+
"pusy",
|
| 350 |
+
"puta",
|
| 351 |
+
"puto",
|
| 352 |
+
"queef",
|
| 353 |
+
"quickie",
|
| 354 |
+
"quicky",
|
| 355 |
+
"quim",
|
| 356 |
+
"randy",
|
| 357 |
+
"rape",
|
| 358 |
+
"raped",
|
| 359 |
+
"raper",
|
| 360 |
+
"raping",
|
| 361 |
+
"rapist",
|
| 362 |
+
"rectum",
|
| 363 |
+
"redneck",
|
| 364 |
+
"rednecks",
|
| 365 |
+
"redskin",
|
| 366 |
+
"redskins",
|
| 367 |
+
"rimjob",
|
| 368 |
+
"rimming",
|
| 369 |
+
"russki",
|
| 370 |
+
"s&m",
|
| 371 |
+
"sadism",
|
| 372 |
+
"sadist",
|
| 373 |
+
"sambo",
|
| 374 |
+
"santorum",
|
| 375 |
+
"schlong",
|
| 376 |
+
"scissoring",
|
| 377 |
+
"semen",
|
| 378 |
+
"sex",
|
| 379 |
+
"sexed",
|
| 380 |
+
"sexi",
|
| 381 |
+
"sexing",
|
| 382 |
+
"sexo",
|
| 383 |
+
"sexpot",
|
| 384 |
+
"sextoy",
|
| 385 |
+
"sexual",
|
| 386 |
+
"sexually",
|
| 387 |
+
"sexx",
|
| 388 |
+
"sexxx",
|
| 389 |
+
"sexxxy",
|
| 390 |
+
"sexxy",
|
| 391 |
+
"sexy",
|
| 392 |
+
"sh!t",
|
| 393 |
+
"sh1t",
|
| 394 |
+
"shagging",
|
| 395 |
+
"shemale",
|
| 396 |
+
"sissy",
|
| 397 |
+
"skank",
|
| 398 |
+
"skanks",
|
| 399 |
+
"slapper",
|
| 400 |
+
"slut",
|
| 401 |
+
"sluts",
|
| 402 |
+
"slutting",
|
| 403 |
+
"slutty",
|
| 404 |
+
"smut",
|
| 405 |
+
"smutty",
|
| 406 |
+
"sodomise",
|
| 407 |
+
"sodomite",
|
| 408 |
+
"sodomize",
|
| 409 |
+
"sodomy",
|
| 410 |
+
"spank",
|
| 411 |
+
"sperm",
|
| 412 |
+
"spic",
|
| 413 |
+
"spick",
|
| 414 |
+
"splooge",
|
| 415 |
+
"spooge",
|
| 416 |
+
"squaw",
|
| 417 |
+
"squirting",
|
| 418 |
+
"steamy",
|
| 419 |
+
"stiffy",
|
| 420 |
+
"strapon",
|
| 421 |
+
"suck",
|
| 422 |
+
"sucked",
|
| 423 |
+
"sucker",
|
| 424 |
+
"sucking",
|
| 425 |
+
"sucks",
|
| 426 |
+
"swallow",
|
| 427 |
+
"swallower",
|
| 428 |
+
"swinger",
|
| 429 |
+
"teabagging",
|
| 430 |
+
"testical",
|
| 431 |
+
"testicle",
|
| 432 |
+
"testicles",
|
| 433 |
+
"testis",
|
| 434 |
+
"threesome",
|
| 435 |
+
"threeway",
|
| 436 |
+
"titfuck",
|
| 437 |
+
"titjob",
|
| 438 |
+
"tits",
|
| 439 |
+
"tittie",
|
| 440 |
+
"titties",
|
| 441 |
+
"titty",
|
| 442 |
+
"tittyfuck",
|
| 443 |
+
"tity",
|
| 444 |
+
"toots",
|
| 445 |
+
"topless",
|
| 446 |
+
"trannie",
|
| 447 |
+
"tranny",
|
| 448 |
+
"tribadism",
|
| 449 |
+
"twat",
|
| 450 |
+
"twats",
|
| 451 |
+
"undies",
|
| 452 |
+
"undressing",
|
| 453 |
+
"upskirt",
|
| 454 |
+
"vag",
|
| 455 |
+
"vagina",
|
| 456 |
+
"vaginal",
|
| 457 |
+
"viagra",
|
| 458 |
+
"vibrator",
|
| 459 |
+
"virgin",
|
| 460 |
+
"vixen",
|
| 461 |
+
"voyeur",
|
| 462 |
+
"vulva",
|
| 463 |
+
"wank",
|
| 464 |
+
"wanker",
|
| 465 |
+
"wanking",
|
| 466 |
+
"wazoo",
|
| 467 |
+
"wedgie",
|
| 468 |
+
"wench",
|
| 469 |
+
"wetback",
|
| 470 |
+
"whore",
|
| 471 |
+
"whored",
|
| 472 |
+
"whorehouse",
|
| 473 |
+
"whores",
|
| 474 |
+
"whoring",
|
| 475 |
+
"wigger",
|
| 476 |
+
"willie",
|
| 477 |
+
"willies",
|
| 478 |
+
"willy",
|
| 479 |
+
"wog",
|
| 480 |
+
"wop",
|
| 481 |
+
"x-rated",
|
| 482 |
+
"xxx",
|
| 483 |
+
"xxxxxx",
|
| 484 |
+
"yaoi",
|
| 485 |
+
"yid",
|
| 486 |
+
"zoophile",
|
| 487 |
+
"zoophilia",
|
| 488 |
+
]
|
| 489 |
+
|
| 490 |
+
badwords = {
|
| 491 |
+
"ar": english_badwords
|
| 492 |
+
+ [
|
| 493 |
+
"احتلام",
|
| 494 |
+
"اغتصاب",
|
| 495 |
+
"بز",
|
| 496 |
+
"بزاز",
|
| 497 |
+
"بظر",
|
| 498 |
+
"بيضان",
|
| 499 |
+
"تمص",
|
| 500 |
+
"ثدي",
|
| 501 |
+
"جماع",
|
| 502 |
+
"حلمة",
|
| 503 |
+
"خنثي",
|
| 504 |
+
"خول",
|
| 505 |
+
"زب",
|
| 506 |
+
"سحاق",
|
| 507 |
+
"سحاقية",
|
| 508 |
+
"سكس",
|
| 509 |
+
"شاذ",
|
| 510 |
+
"شرج",
|
| 511 |
+
"شرموطة",
|
| 512 |
+
"شهوة",
|
| 513 |
+
"طيز",
|
| 514 |
+
"عاهرة",
|
| 515 |
+
"عرص",
|
| 516 |
+
"فرج",
|
| 517 |
+
"قحبة",
|
| 518 |
+
"قضيب",
|
| 519 |
+
"كس",
|
| 520 |
+
"لبوة",
|
| 521 |
+
"لحس",
|
| 522 |
+
"لعق",
|
| 523 |
+
"لواط",
|
| 524 |
+
"لوطي",
|
| 525 |
+
"مبادل",
|
| 526 |
+
"متناك",
|
| 527 |
+
"متناكة",
|
| 528 |
+
"مص",
|
| 529 |
+
"مفلقسة",
|
| 530 |
+
"نيك",
|
| 531 |
+
],
|
| 532 |
+
"ca": english_badwords
|
| 533 |
+
+ [
|
| 534 |
+
"avortament",
|
| 535 |
+
"anal",
|
| 536 |
+
"anus",
|
| 537 |
+
"cul",
|
| 538 |
+
"ass-fucker",
|
| 539 |
+
"asss",
|
| 540 |
+
"asshole",
|
| 541 |
+
"assholes",
|
| 542 |
+
"bolera",
|
| 543 |
+
"boles",
|
| 544 |
+
"bastardo",
|
| 545 |
+
"bellend",
|
| 546 |
+
"bestial",
|
| 547 |
+
"bestialitat",
|
| 548 |
+
"puta",
|
| 549 |
+
"femelles",
|
| 550 |
+
"picant",
|
| 551 |
+
"sagnant",
|
| 552 |
+
"mamada",
|
| 553 |
+
"bollok",
|
| 554 |
+
"boob",
|
| 555 |
+
"pits",
|
| 556 |
+
"buceta",
|
| 557 |
+
"bum",
|
| 558 |
+
"culata",
|
| 559 |
+
"catifa muncher",
|
| 560 |
+
"picar",
|
| 561 |
+
"cipa",
|
| 562 |
+
"clitoris",
|
| 563 |
+
"polla",
|
| 564 |
+
"galletejador",
|
| 565 |
+
"gallines",
|
| 566 |
+
"coon",
|
| 567 |
+
"merda",
|
| 568 |
+
"cum",
|
| 569 |
+
"correguda",
|
| 570 |
+
"cunillingus",
|
| 571 |
+
"boig",
|
| 572 |
+
"maleït",
|
| 573 |
+
"consolador",
|
| 574 |
+
"consoladors",
|
| 575 |
+
"dink",
|
| 576 |
+
"canalla",
|
| 577 |
+
"duche",
|
| 578 |
+
"dique",
|
| 579 |
+
"ejaculació",
|
| 580 |
+
"ejaculat",
|
| 581 |
+
"ejacula",
|
| 582 |
+
"ejaculant",
|
| 583 |
+
"fag",
|
| 584 |
+
"fagging",
|
| 585 |
+
"fagot",
|
| 586 |
+
"fagots",
|
| 587 |
+
"fanny",
|
| 588 |
+
"felching",
|
| 589 |
+
"fel.lació",
|
| 590 |
+
"brida",
|
| 591 |
+
"follar",
|
| 592 |
+
"follat",
|
| 593 |
+
"escuradents",
|
| 594 |
+
"follant",
|
| 595 |
+
"folles",
|
| 596 |
+
"fucks",
|
| 597 |
+
"empacadora de llaminadures",
|
| 598 |
+
"déu maldit",
|
| 599 |
+
"deu meu",
|
| 600 |
+
"infern",
|
| 601 |
+
"hore",
|
| 602 |
+
"córrer",
|
| 603 |
+
"retrocés",
|
| 604 |
+
"kock",
|
| 605 |
+
"llavis",
|
| 606 |
+
"lujuria",
|
| 607 |
+
"lució",
|
| 608 |
+
"masoquista",
|
| 609 |
+
"masturbarse",
|
| 610 |
+
"puta mare",
|
| 611 |
+
"nazi",
|
| 612 |
+
"nigger",
|
| 613 |
+
"negres",
|
| 614 |
+
"orgasim",
|
| 615 |
+
"orgasme",
|
| 616 |
+
"orgasmes",
|
| 617 |
+
"pecker",
|
| 618 |
+
"penis",
|
| 619 |
+
"piss",
|
| 620 |
+
"mossegat",
|
| 621 |
+
"pisser",
|
| 622 |
+
"pisses",
|
| 623 |
+
"pissing",
|
| 624 |
+
"treure de polleguera",
|
| 625 |
+
"caca",
|
| 626 |
+
"porno",
|
| 627 |
+
"pornografia",
|
| 628 |
+
"picades",
|
| 629 |
+
"pube",
|
| 630 |
+
"coques",
|
| 631 |
+
"gatet",
|
| 632 |
+
"violació",
|
| 633 |
+
"violador",
|
| 634 |
+
"recte",
|
| 635 |
+
"retard",
|
| 636 |
+
"rimming",
|
| 637 |
+
"sàdic",
|
| 638 |
+
"cargolar",
|
| 639 |
+
"escrot",
|
| 640 |
+
"semen",
|
| 641 |
+
"sexe",
|
| 642 |
+
"shag",
|
| 643 |
+
"borratxos",
|
| 644 |
+
"transsexual",
|
| 645 |
+
"mossegar",
|
| 646 |
+
"shitted",
|
| 647 |
+
"skank",
|
| 648 |
+
"smegma",
|
| 649 |
+
"smut",
|
| 650 |
+
"arrebat",
|
| 651 |
+
"fill de puta",
|
| 652 |
+
"spac",
|
| 653 |
+
"spunk",
|
| 654 |
+
"testicle",
|
| 655 |
+
"tit",
|
| 656 |
+
"tetas",
|
| 657 |
+
"titt",
|
| 658 |
+
"turd",
|
| 659 |
+
"vagina",
|
| 660 |
+
"viagra",
|
| 661 |
+
"vulva",
|
| 662 |
+
"wang",
|
| 663 |
+
"wank",
|
| 664 |
+
"x classificat",
|
| 665 |
+
"xxx",
|
| 666 |
+
],
|
| 667 |
+
"en": english_badwords,
|
| 668 |
+
"es": english_badwords
|
| 669 |
+
+ [
|
| 670 |
+
"Asesinato",
|
| 671 |
+
"Bollera",
|
| 672 |
+
"Cabrón",
|
| 673 |
+
"Caca",
|
| 674 |
+
"Chupada",
|
| 675 |
+
"Chupapollas",
|
| 676 |
+
"Chupetón",
|
| 677 |
+
"Concha de tu madre",
|
| 678 |
+
"Coprofagía",
|
| 679 |
+
"Coño",
|
| 680 |
+
"Culo",
|
| 681 |
+
"Drogas",
|
| 682 |
+
"Esperma",
|
| 683 |
+
"Fiesta de salchichas",
|
| 684 |
+
"Follador",
|
| 685 |
+
"Follar",
|
| 686 |
+
"Gilipichis",
|
| 687 |
+
"Gilipollas",
|
| 688 |
+
"Hacer una paja",
|
| 689 |
+
"Haciendo el amor",
|
| 690 |
+
"Heroína",
|
| 691 |
+
"Hija de puta",
|
| 692 |
+
"Hijaputa",
|
| 693 |
+
"Hijo de puta",
|
| 694 |
+
"Hijoputa",
|
| 695 |
+
"Idiota",
|
| 696 |
+
"Imbécil",
|
| 697 |
+
"Jilipollas",
|
| 698 |
+
"Kapullo",
|
| 699 |
+
"Lameculos",
|
| 700 |
+
"Maciza",
|
| 701 |
+
"Macizorra",
|
| 702 |
+
"Mamada",
|
| 703 |
+
"Marica",
|
| 704 |
+
"Mariconazo",
|
| 705 |
+
"Maricón",
|
| 706 |
+
"Mierda",
|
| 707 |
+
"Nazi",
|
| 708 |
+
"Orina",
|
| 709 |
+
"Pedo",
|
| 710 |
+
"Pendejo",
|
| 711 |
+
"Pervertido",
|
| 712 |
+
"Pezón",
|
| 713 |
+
"Pinche",
|
| 714 |
+
"Pis",
|
| 715 |
+
"Prostituta",
|
| 716 |
+
"Puta",
|
| 717 |
+
"Racista",
|
| 718 |
+
"Ramera",
|
| 719 |
+
"Semen",
|
| 720 |
+
"Sexo",
|
| 721 |
+
"Sexo oral",
|
| 722 |
+
"Soplagaitas",
|
| 723 |
+
"Soplapollas",
|
| 724 |
+
"Sádico",
|
| 725 |
+
"Tetas grandes",
|
| 726 |
+
"Travesti",
|
| 727 |
+
"Trio",
|
| 728 |
+
"Tía buena",
|
| 729 |
+
"Verga",
|
| 730 |
+
"Vulva",
|
| 731 |
+
"aborto",
|
| 732 |
+
"agallas",
|
| 733 |
+
"anal",
|
| 734 |
+
"ano",
|
| 735 |
+
"arrebatar",
|
| 736 |
+
"asno",
|
| 737 |
+
"atornillar",
|
| 738 |
+
"bastardo",
|
| 739 |
+
"bestial",
|
| 740 |
+
"bestialidad",
|
| 741 |
+
"bolas",
|
| 742 |
+
"bollok",
|
| 743 |
+
"bolsa de pelota",
|
| 744 |
+
"brida",
|
| 745 |
+
"buceta",
|
| 746 |
+
"cabron",
|
| 747 |
+
"cagadas",
|
| 748 |
+
"cagado",
|
| 749 |
+
"cagando",
|
| 750 |
+
"campana",
|
| 751 |
+
"carajo",
|
| 752 |
+
"chupar la polla",
|
| 753 |
+
"cipa",
|
| 754 |
+
"clítoris",
|
| 755 |
+
"concha",
|
| 756 |
+
"consolador",
|
| 757 |
+
"consoladores",
|
| 758 |
+
"corrida",
|
| 759 |
+
"coño",
|
| 760 |
+
"coños",
|
| 761 |
+
"culo",
|
| 762 |
+
"culos",
|
| 763 |
+
"cunillingus",
|
| 764 |
+
"córneo",
|
| 765 |
+
"de mierda",
|
| 766 |
+
"dique",
|
| 767 |
+
"duche",
|
| 768 |
+
"enojado",
|
| 769 |
+
"escroto",
|
| 770 |
+
"espacio",
|
| 771 |
+
"estúpido",
|
| 772 |
+
"extremo",
|
| 773 |
+
"eyacula",
|
| 774 |
+
"eyaculación",
|
| 775 |
+
"eyaculado",
|
| 776 |
+
"eyacular",
|
| 777 |
+
"fagging",
|
| 778 |
+
"felación",
|
| 779 |
+
"felching",
|
| 780 |
+
"folla",
|
| 781 |
+
"follada",
|
| 782 |
+
"follador de culo",
|
| 783 |
+
"folladores",
|
| 784 |
+
"follar",
|
| 785 |
+
"fudge packer",
|
| 786 |
+
"gallos",
|
| 787 |
+
"grieta",
|
| 788 |
+
"hacerse una paja",
|
| 789 |
+
"hijo de puta",
|
| 790 |
+
"hore",
|
| 791 |
+
"infierno",
|
| 792 |
+
"kock",
|
| 793 |
+
"labios vaginales",
|
| 794 |
+
"los pechos",
|
| 795 |
+
"lujuria",
|
| 796 |
+
"madre folladora",
|
| 797 |
+
"maldita sea",
|
| 798 |
+
"maldito",
|
| 799 |
+
"maldito sea",
|
| 800 |
+
"mamada",
|
| 801 |
+
"mapache",
|
| 802 |
+
"maricones",
|
| 803 |
+
"maricón",
|
| 804 |
+
"martillo",
|
| 805 |
+
"masoquista",
|
| 806 |
+
"masturbarse",
|
| 807 |
+
"mear",
|
| 808 |
+
"mierda",
|
| 809 |
+
"molesto",
|
| 810 |
+
"muncher alfombra",
|
| 811 |
+
"nazi",
|
| 812 |
+
"negro",
|
| 813 |
+
"niggers",
|
| 814 |
+
"orgasimo",
|
| 815 |
+
"orgasmo",
|
| 816 |
+
"orgasmos",
|
| 817 |
+
"orinando",
|
| 818 |
+
"pelusa",
|
| 819 |
+
"pene",
|
| 820 |
+
"perra",
|
| 821 |
+
"perras",
|
| 822 |
+
"perro follador",
|
| 823 |
+
"pinchazo",
|
| 824 |
+
"pinchazos",
|
| 825 |
+
"pisser",
|
| 826 |
+
"polla",
|
| 827 |
+
"porno",
|
| 828 |
+
"pornografía",
|
| 829 |
+
"pube",
|
| 830 |
+
"puta",
|
| 831 |
+
"putas",
|
| 832 |
+
"pájaro carpintero",
|
| 833 |
+
"quejas",
|
| 834 |
+
"recto",
|
| 835 |
+
"retardar",
|
| 836 |
+
"rimming",
|
| 837 |
+
"sangriento",
|
| 838 |
+
"semen",
|
| 839 |
+
"sexo",
|
| 840 |
+
"skank",
|
| 841 |
+
"smegma",
|
| 842 |
+
"sádico",
|
| 843 |
+
"testículo",
|
| 844 |
+
"teta",
|
| 845 |
+
"tetas",
|
| 846 |
+
"tirón",
|
| 847 |
+
"tizón",
|
| 848 |
+
"tonto",
|
| 849 |
+
"transexual",
|
| 850 |
+
"vagina",
|
| 851 |
+
"vete a la mierda",
|
| 852 |
+
"viagra",
|
| 853 |
+
"violación",
|
| 854 |
+
"violador",
|
| 855 |
+
"vulva",
|
| 856 |
+
"wang",
|
| 857 |
+
"x clasificado",
|
| 858 |
+
"xxx",
|
| 859 |
+
"zurullo",
|
| 860 |
+
],
|
| 861 |
+
"eu": english_badwords
|
| 862 |
+
+ [
|
| 863 |
+
"abortu",
|
| 864 |
+
"anal",
|
| 865 |
+
"ipurdi",
|
| 866 |
+
"kabroi",
|
| 867 |
+
"puta",
|
| 868 |
+
"clitoris",
|
| 869 |
+
"cunillingus",
|
| 870 |
+
"madarikatu",
|
| 871 |
+
"zakil",
|
| 872 |
+
"hazia isuri",
|
| 873 |
+
"arraio",
|
| 874 |
+
"izorratu",
|
| 875 |
+
"infernu",
|
| 876 |
+
"emagaldu",
|
| 877 |
+
"lizunkeri",
|
| 878 |
+
"lizun",
|
| 879 |
+
"masokista",
|
| 880 |
+
"masturbatu",
|
| 881 |
+
"nazi",
|
| 882 |
+
"beltz",
|
| 883 |
+
"orgasmo",
|
| 884 |
+
"pixa",
|
| 885 |
+
"porno",
|
| 886 |
+
"pornografia",
|
| 887 |
+
"alu",
|
| 888 |
+
"bortxaketa",
|
| 889 |
+
"bortxatzaile",
|
| 890 |
+
"sadista",
|
| 891 |
+
"ipurzulo",
|
| 892 |
+
"hazi",
|
| 893 |
+
"semen",
|
| 894 |
+
"sexu",
|
| 895 |
+
"kaka",
|
| 896 |
+
"putaseme",
|
| 897 |
+
"barrabil",
|
| 898 |
+
"titi",
|
| 899 |
+
"bagina",
|
| 900 |
+
"viagra",
|
| 901 |
+
],
|
| 902 |
+
"fr": english_badwords
|
| 903 |
+
+ [
|
| 904 |
+
"MALPT",
|
| 905 |
+
"anal",
|
| 906 |
+
"anus",
|
| 907 |
+
"arracher",
|
| 908 |
+
"avortement",
|
| 909 |
+
"baise",
|
| 910 |
+
"baiser",
|
| 911 |
+
"baiseur de chien",
|
| 912 |
+
"baiseurs",
|
| 913 |
+
"baisée",
|
| 914 |
+
"bander",
|
| 915 |
+
"bellend",
|
| 916 |
+
"bestial",
|
| 917 |
+
"bestialité",
|
| 918 |
+
"bigornette",
|
| 919 |
+
"bite",
|
| 920 |
+
"bitte",
|
| 921 |
+
"bloblos",
|
| 922 |
+
"bollok",
|
| 923 |
+
"boob",
|
| 924 |
+
"bordel",
|
| 925 |
+
"bourré",
|
| 926 |
+
"bourrée",
|
| 927 |
+
"bout",
|
| 928 |
+
"brackmard",
|
| 929 |
+
"branlage",
|
| 930 |
+
"branler",
|
| 931 |
+
"branlette",
|
| 932 |
+
"branleur",
|
| 933 |
+
"branleuse",
|
| 934 |
+
"bride",
|
| 935 |
+
"brouter le cresson",
|
| 936 |
+
"buceta",
|
| 937 |
+
"caca",
|
| 938 |
+
"chatte",
|
| 939 |
+
"chattes",
|
| 940 |
+
"chiasse",
|
| 941 |
+
"chienne",
|
| 942 |
+
"chiennes",
|
| 943 |
+
"chier",
|
| 944 |
+
"chiottes",
|
| 945 |
+
"chié",
|
| 946 |
+
"cipa",
|
| 947 |
+
"clito",
|
| 948 |
+
"clitoris",
|
| 949 |
+
"clochard",
|
| 950 |
+
"cochonneries",
|
| 951 |
+
"con",
|
| 952 |
+
"connard",
|
| 953 |
+
"connards",
|
| 954 |
+
"connasse",
|
| 955 |
+
"conne",
|
| 956 |
+
"convoitise",
|
| 957 |
+
"coq",
|
| 958 |
+
"coqs",
|
| 959 |
+
"corné",
|
| 960 |
+
"couilles",
|
| 961 |
+
"cramouille",
|
| 962 |
+
"cran",
|
| 963 |
+
"cul",
|
| 964 |
+
"culs",
|
| 965 |
+
"cunillingus",
|
| 966 |
+
"damné",
|
| 967 |
+
"des balles",
|
| 968 |
+
"digue",
|
| 969 |
+
"duché",
|
| 970 |
+
"déconne",
|
| 971 |
+
"déconner",
|
| 972 |
+
"emballeur de fudge",
|
| 973 |
+
"emmerdant",
|
| 974 |
+
"emmerder",
|
| 975 |
+
"emmerdeur",
|
| 976 |
+
"emmerdeuse",
|
| 977 |
+
"enculer",
|
| 978 |
+
"enculeur",
|
| 979 |
+
"enculeurs",
|
| 980 |
+
"enculé",
|
| 981 |
+
"enculée",
|
| 982 |
+
"enfer",
|
| 983 |
+
"enfoiré",
|
| 984 |
+
"enfoirée",
|
| 985 |
+
"espacer",
|
| 986 |
+
"fagging",
|
| 987 |
+
"fagot",
|
| 988 |
+
"fagots",
|
| 989 |
+
"faire chier",
|
| 990 |
+
"fellation",
|
| 991 |
+
"fente",
|
| 992 |
+
"fille de pute",
|
| 993 |
+
"fils de pute",
|
| 994 |
+
"folle",
|
| 995 |
+
"foutre",
|
| 996 |
+
"fuckings",
|
| 997 |
+
"gerbe",
|
| 998 |
+
"gerber",
|
| 999 |
+
"godemiché",
|
| 1000 |
+
"godes",
|
| 1001 |
+
"gouine",
|
| 1002 |
+
"grande folle",
|
| 1003 |
+
"grogniasse",
|
| 1004 |
+
"gueule",
|
| 1005 |
+
"hore",
|
| 1006 |
+
"jouir",
|
| 1007 |
+
"kock",
|
| 1008 |
+
"la putain de ta mère",
|
| 1009 |
+
"les lèvres",
|
| 1010 |
+
"les seins",
|
| 1011 |
+
"luxure",
|
| 1012 |
+
"masochiste",
|
| 1013 |
+
"masturber",
|
| 1014 |
+
"merde",
|
| 1015 |
+
"merdeuse",
|
| 1016 |
+
"merdeux",
|
| 1017 |
+
"merdique",
|
| 1018 |
+
"meuf",
|
| 1019 |
+
"mère enculée",
|
| 1020 |
+
"ménage à trois",
|
| 1021 |
+
"mésange",
|
| 1022 |
+
"nazi",
|
| 1023 |
+
"negro",
|
| 1024 |
+
"nique ta mère",
|
| 1025 |
+
"nique ta race",
|
| 1026 |
+
"nègre",
|
| 1027 |
+
"nègres",
|
| 1028 |
+
"orgasim",
|
| 1029 |
+
"orgasme",
|
| 1030 |
+
"orgasmes",
|
| 1031 |
+
"palucher",
|
| 1032 |
+
"penchant",
|
| 1033 |
+
"pipe",
|
| 1034 |
+
"pipi",
|
| 1035 |
+
"piquer",
|
| 1036 |
+
"piqûres",
|
| 1037 |
+
"pisse",
|
| 1038 |
+
"pisser",
|
| 1039 |
+
"porno",
|
| 1040 |
+
"pornographie",
|
| 1041 |
+
"pouffiasse",
|
| 1042 |
+
"pousse-crotte",
|
| 1043 |
+
"pube",
|
| 1044 |
+
"putain",
|
| 1045 |
+
"putain de",
|
| 1046 |
+
"pute",
|
| 1047 |
+
"pédale",
|
| 1048 |
+
"pédé",
|
| 1049 |
+
"pénis",
|
| 1050 |
+
"péter",
|
| 1051 |
+
"queue",
|
| 1052 |
+
"quéquette",
|
| 1053 |
+
"ramoner",
|
| 1054 |
+
"rectum",
|
| 1055 |
+
"retard",
|
| 1056 |
+
"rimming",
|
| 1057 |
+
"râpé",
|
| 1058 |
+
"sac de billes",
|
| 1059 |
+
"sac à foutre",
|
| 1060 |
+
"sac à merde",
|
| 1061 |
+
"sadique",
|
| 1062 |
+
"salaud",
|
| 1063 |
+
"salope",
|
| 1064 |
+
"salopes",
|
| 1065 |
+
"sanglant",
|
| 1066 |
+
"scrotum",
|
| 1067 |
+
"se branler",
|
| 1068 |
+
"seins",
|
| 1069 |
+
"sexe",
|
| 1070 |
+
"skank",
|
| 1071 |
+
"smegma",
|
| 1072 |
+
"sperme",
|
| 1073 |
+
"suce",
|
| 1074 |
+
"suceuse",
|
| 1075 |
+
"tanche",
|
| 1076 |
+
"tapette",
|
| 1077 |
+
"tapis muncher",
|
| 1078 |
+
"testicule",
|
| 1079 |
+
"teuch",
|
| 1080 |
+
"titt",
|
| 1081 |
+
"transexuelle",
|
| 1082 |
+
"tremper",
|
| 1083 |
+
"tringler",
|
| 1084 |
+
"trique",
|
| 1085 |
+
"troncher",
|
| 1086 |
+
"trou du cul",
|
| 1087 |
+
"turlute",
|
| 1088 |
+
"vagin",
|
| 1089 |
+
"viagra",
|
| 1090 |
+
"violeur",
|
| 1091 |
+
"vulve",
|
| 1092 |
+
"wang",
|
| 1093 |
+
"x évalué",
|
| 1094 |
+
"xxx",
|
| 1095 |
+
"zigounette",
|
| 1096 |
+
"zizi",
|
| 1097 |
+
"zut",
|
| 1098 |
+
"éjaculant",
|
| 1099 |
+
"éjaculation",
|
| 1100 |
+
"éjacule",
|
| 1101 |
+
"éjaculer",
|
| 1102 |
+
"éjaculé",
|
| 1103 |
+
"étron",
|
| 1104 |
+
],
|
| 1105 |
+
"hi": english_badwords
|
| 1106 |
+
+ [
|
| 1107 |
+
"aand",
|
| 1108 |
+
"aandu",
|
| 1109 |
+
"balatkar",
|
| 1110 |
+
"balatkari",
|
| 1111 |
+
"behen chod",
|
| 1112 |
+
"beti chod",
|
| 1113 |
+
"bhadva",
|
| 1114 |
+
"bhadve",
|
| 1115 |
+
"bhandve",
|
| 1116 |
+
"bhangi",
|
| 1117 |
+
"bhootni ke",
|
| 1118 |
+
"bhosad",
|
| 1119 |
+
"bhosadi ke",
|
| 1120 |
+
"bitching",
|
| 1121 |
+
"blowjob",
|
| 1122 |
+
"bollok",
|
| 1123 |
+
"boobe",
|
| 1124 |
+
"buceta",
|
| 1125 |
+
"chakke",
|
| 1126 |
+
"chinaal",
|
| 1127 |
+
"chinki",
|
| 1128 |
+
"chod",
|
| 1129 |
+
"chodu",
|
| 1130 |
+
"chodu bhagat",
|
| 1131 |
+
"chooche",
|
| 1132 |
+
"choochi",
|
| 1133 |
+
"choope",
|
| 1134 |
+
"choot",
|
| 1135 |
+
"choot ke baal",
|
| 1136 |
+
"chootia",
|
| 1137 |
+
"chootiya",
|
| 1138 |
+
"chuche",
|
| 1139 |
+
"chuchi",
|
| 1140 |
+
"chudaap",
|
| 1141 |
+
"chudai khanaa",
|
| 1142 |
+
"chudam chudai",
|
| 1143 |
+
"chude",
|
| 1144 |
+
"chut",
|
| 1145 |
+
"chut ka chuha",
|
| 1146 |
+
"chut ka churan",
|
| 1147 |
+
"chut ka mail",
|
| 1148 |
+
"chut ke baal",
|
| 1149 |
+
"chut ke dhakkan",
|
| 1150 |
+
"chut maarli",
|
| 1151 |
+
"chutad",
|
| 1152 |
+
"chutadd",
|
| 1153 |
+
"chutan",
|
| 1154 |
+
"chutia",
|
| 1155 |
+
"chutiya",
|
| 1156 |
+
"cipa",
|
| 1157 |
+
"cunillingus",
|
| 1158 |
+
"dink",
|
| 1159 |
+
"duche",
|
| 1160 |
+
"ejaculated",
|
| 1161 |
+
"ejaculates",
|
| 1162 |
+
"ejaculating",
|
| 1163 |
+
"fagging",
|
| 1164 |
+
"fagots",
|
| 1165 |
+
"felching",
|
| 1166 |
+
"fuckers",
|
| 1167 |
+
"fuckings",
|
| 1168 |
+
"fucks",
|
| 1169 |
+
"gaand",
|
| 1170 |
+
"gaandfat",
|
| 1171 |
+
"gaandmasti",
|
| 1172 |
+
"gaandufad",
|
| 1173 |
+
"gandfattu",
|
| 1174 |
+
"gandu",
|
| 1175 |
+
"gashti",
|
| 1176 |
+
"gasti",
|
| 1177 |
+
"ghassa",
|
| 1178 |
+
"ghasti",
|
| 1179 |
+
"gucchi",
|
| 1180 |
+
"gucchu",
|
| 1181 |
+
"harami",
|
| 1182 |
+
"haramzade",
|
| 1183 |
+
"hawas",
|
| 1184 |
+
"hawas ke pujari",
|
| 1185 |
+
"hijda",
|
| 1186 |
+
"hijra",
|
| 1187 |
+
"jhant",
|
| 1188 |
+
"jhant chaatu",
|
| 1189 |
+
"jhant ka keeda",
|
| 1190 |
+
"jhant ke baal",
|
| 1191 |
+
"jhant ke pissu",
|
| 1192 |
+
"jhantu",
|
| 1193 |
+
"kamine",
|
| 1194 |
+
"kaminey",
|
| 1195 |
+
"kanjar",
|
| 1196 |
+
"kutta",
|
| 1197 |
+
"kutta kamina",
|
| 1198 |
+
"kutte ki aulad",
|
| 1199 |
+
"kutte ki jat",
|
| 1200 |
+
"kuttiya",
|
| 1201 |
+
"loda",
|
| 1202 |
+
"lodu",
|
| 1203 |
+
"lund",
|
| 1204 |
+
"lund choos",
|
| 1205 |
+
"lund ka bakkal",
|
| 1206 |
+
"lund khajoor",
|
| 1207 |
+
"lundtopi",
|
| 1208 |
+
"lundure",
|
| 1209 |
+
"lusting",
|
| 1210 |
+
"maa ki chut",
|
| 1211 |
+
"maal",
|
| 1212 |
+
"madar chod",
|
| 1213 |
+
"madarchod",
|
| 1214 |
+
"madhavchod",
|
| 1215 |
+
"masochist",
|
| 1216 |
+
"mooh mein le",
|
| 1217 |
+
"mutth",
|
| 1218 |
+
"mutthal",
|
| 1219 |
+
"najayaz",
|
| 1220 |
+
"najayaz aulaad",
|
| 1221 |
+
"najayaz paidaish",
|
| 1222 |
+
"orgasim",
|
| 1223 |
+
"paki",
|
| 1224 |
+
"pataka",
|
| 1225 |
+
"patakha",
|
| 1226 |
+
"pisser",
|
| 1227 |
+
"pisses",
|
| 1228 |
+
"pissing",
|
| 1229 |
+
"pube",
|
| 1230 |
+
"pussies",
|
| 1231 |
+
"raand",
|
| 1232 |
+
"randaap",
|
| 1233 |
+
"randi",
|
| 1234 |
+
"randi rona",
|
| 1235 |
+
"rimming",
|
| 1236 |
+
"saala",
|
| 1237 |
+
"saala kutta",
|
| 1238 |
+
"saali kutti",
|
| 1239 |
+
"saali randi",
|
| 1240 |
+
"shagging",
|
| 1241 |
+
"shite",
|
| 1242 |
+
"shitted",
|
| 1243 |
+
"shitting",
|
| 1244 |
+
"shitty",
|
| 1245 |
+
"skank",
|
| 1246 |
+
"sluts",
|
| 1247 |
+
"spac",
|
| 1248 |
+
"suar",
|
| 1249 |
+
"suar ke lund",
|
| 1250 |
+
"suar ki aulad",
|
| 1251 |
+
"tatte",
|
| 1252 |
+
"tatti",
|
| 1253 |
+
"teri maa ka bhosada",
|
| 1254 |
+
"teri maa ka boba chusu",
|
| 1255 |
+
"teri maa ki behenchod ",
|
| 1256 |
+
"teri maa ki chut",
|
| 1257 |
+
"tharak",
|
| 1258 |
+
"tharki",
|
| 1259 |
+
"titt",
|
| 1260 |
+
"tu chuda",
|
| 1261 |
+
"turd",
|
| 1262 |
+
"wank",
|
| 1263 |
+
"xxx",
|
| 1264 |
+
"अंडकोश की थैली",
|
| 1265 |
+
"अंडा",
|
| 1266 |
+
"अरे नहीं",
|
| 1267 |
+
"अश्लील",
|
| 1268 |
+
"उल्लू",
|
| 1269 |
+
"एक्स रेटेड",
|
| 1270 |
+
"ओगाज़्म",
|
| 1271 |
+
"कमबख्त",
|
| 1272 |
+
"काम करना",
|
| 1273 |
+
"कामोद्दीपक चित्र",
|
| 1274 |
+
"कालीन का चूरा",
|
| 1275 |
+
"किन्नर",
|
| 1276 |
+
"कुतिया",
|
| 1277 |
+
"कुत्ते-कमीने",
|
| 1278 |
+
"कून",
|
| 1279 |
+
"कॉक",
|
| 1280 |
+
"गड़बड़",
|
| 1281 |
+
"गधा कमीने",
|
| 1282 |
+
"गधे",
|
| 1283 |
+
"गर्भपात",
|
| 1284 |
+
"गुदा",
|
| 1285 |
+
"गेंद का थैला",
|
| 1286 |
+
"गेंदों",
|
| 1287 |
+
"गोली चलाने की आवाज़",
|
| 1288 |
+
"घटिया इंसान",
|
| 1289 |
+
"चाकलेट का रंग",
|
| 1290 |
+
"चिंक",
|
| 1291 |
+
"चुभन",
|
| 1292 |
+
"चूची",
|
| 1293 |
+
"चूतड़",
|
| 1294 |
+
"चोंच",
|
| 1295 |
+
"छीनना",
|
| 1296 |
+
"जी में आये करो",
|
| 1297 |
+
"झटका बंद",
|
| 1298 |
+
"ठगना पैकर",
|
| 1299 |
+
"डिल्डो",
|
| 1300 |
+
"दुष्ट",
|
| 1301 |
+
"दूर जाने का अभद्र संकेत देना",
|
| 1302 |
+
"धत् तेरे की",
|
| 1303 |
+
"नरक",
|
| 1304 |
+
"नाजी",
|
| 1305 |
+
"निकला हुआ किनारा",
|
| 1306 |
+
"नितंब",
|
| 1307 |
+
"पंगा लेना",
|
| 1308 |
+
"पिछाड़ी",
|
| 1309 |
+
"पीड़न कामुक",
|
| 1310 |
+
"पेशाब",
|
| 1311 |
+
"पॉर्न",
|
| 1312 |
+
"फटना",
|
| 1313 |
+
"फूहड़",
|
| 1314 |
+
"बकवास",
|
| 1315 |
+
"बट",
|
| 1316 |
+
"बलात्कार",
|
| 1317 |
+
"बहुत मदहोश",
|
| 1318 |
+
"बांध",
|
| 1319 |
+
"बिल्ली",
|
| 1320 |
+
"बेल अंत",
|
| 1321 |
+
"बेवकूफों",
|
| 1322 |
+
"बोल पड़ना",
|
| 1323 |
+
"भगवान-शापित",
|
| 1324 |
+
"भगशेफ",
|
| 1325 |
+
"मल",
|
| 1326 |
+
"मलाशय",
|
| 1327 |
+
"माँ कमीने",
|
| 1328 |
+
"मुखमैथुन",
|
| 1329 |
+
"मुर्गा",
|
| 1330 |
+
"मुर्गा के",
|
| 1331 |
+
"मुर्गा चूसने वाला",
|
| 1332 |
+
"मूर्ख",
|
| 1333 |
+
"मैल",
|
| 1334 |
+
"योनि",
|
| 1335 |
+
"योनी",
|
| 1336 |
+
"यौन-संबंध",
|
| 1337 |
+
"रक्तरंजित",
|
| 1338 |
+
"लानत है",
|
| 1339 |
+
"लिंग",
|
| 1340 |
+
"लुटेरा",
|
| 1341 |
+
"लेबिया",
|
| 1342 |
+
"वहशी",
|
| 1343 |
+
"वहशीता",
|
| 1344 |
+
"वियाग्रा",
|
| 1345 |
+
"वीर्य",
|
| 1346 |
+
"वेश्या",
|
| 1347 |
+
"वैंग",
|
| 1348 |
+
"वो साले",
|
| 1349 |
+
"शिफ़्ट को",
|
| 1350 |
+
"शिश्नमल",
|
| 1351 |
+
"संभोग सुख",
|
| 1352 |
+
"सह",
|
| 1353 |
+
"सह शॉट",
|
| 1354 |
+
"साहस",
|
| 1355 |
+
"सिगरेट",
|
| 1356 |
+
"सींग का बना हुआ",
|
| 1357 |
+
"स्तन",
|
| 1358 |
+
"स्तनों",
|
| 1359 |
+
"हवस",
|
| 1360 |
+
"हस्तमैथुन",
|
| 1361 |
+
"होमोसेक्सुअल",
|
| 1362 |
+
"होर",
|
| 1363 |
+
],
|
| 1364 |
+
"id": english_badwords
|
| 1365 |
+
+ [
|
| 1366 |
+
"abortus",
|
| 1367 |
+
"anal",
|
| 1368 |
+
"dubur",
|
| 1369 |
+
"pantat",
|
| 1370 |
+
"bajingan",
|
| 1371 |
+
"keledai",
|
| 1372 |
+
"keparat",
|
| 1373 |
+
"tas bola",
|
| 1374 |
+
"bola",
|
| 1375 |
+
"bellend",
|
| 1376 |
+
"kejam",
|
| 1377 |
+
"kebinatangan",
|
| 1378 |
+
"menggerutu",
|
| 1379 |
+
"pelacur",
|
| 1380 |
+
"berdarah",
|
| 1381 |
+
"blowjob",
|
| 1382 |
+
"bollok",
|
| 1383 |
+
"dada",
|
| 1384 |
+
"payudara",
|
| 1385 |
+
"buceta",
|
| 1386 |
+
"gelandangan",
|
| 1387 |
+
"pengunyah karpet",
|
| 1388 |
+
"celah",
|
| 1389 |
+
"cipa",
|
| 1390 |
+
"kelentit",
|
| 1391 |
+
"kokang",
|
| 1392 |
+
"pengisap ayam",
|
| 1393 |
+
"ayam",
|
| 1394 |
+
"coon",
|
| 1395 |
+
"sampah",
|
| 1396 |
+
"air mani",
|
| 1397 |
+
"cumshot",
|
| 1398 |
+
"cunillingus",
|
| 1399 |
+
"vagina",
|
| 1400 |
+
"mengutuk",
|
| 1401 |
+
"kontol",
|
| 1402 |
+
"dildo",
|
| 1403 |
+
"dink",
|
| 1404 |
+
"anjing-keparat",
|
| 1405 |
+
"duche",
|
| 1406 |
+
"tanggul",
|
| 1407 |
+
"berejakulasi",
|
| 1408 |
+
"ejakulasi",
|
| 1409 |
+
"homo",
|
| 1410 |
+
"fagging",
|
| 1411 |
+
"kayu bakar",
|
| 1412 |
+
"penggemar",
|
| 1413 |
+
"felching",
|
| 1414 |
+
"fellatio",
|
| 1415 |
+
"flens",
|
| 1416 |
+
"brengsek",
|
| 1417 |
+
"kacau",
|
| 1418 |
+
"sialan",
|
| 1419 |
+
"persetan",
|
| 1420 |
+
"pengepakan fudge",
|
| 1421 |
+
"terkutuk",
|
| 1422 |
+
"ya tuhan",
|
| 1423 |
+
"neraka",
|
| 1424 |
+
"hore",
|
| 1425 |
+
"terangsang",
|
| 1426 |
+
"kock",
|
| 1427 |
+
"labia",
|
| 1428 |
+
"nafsu",
|
| 1429 |
+
"bernafsu",
|
| 1430 |
+
"masokis",
|
| 1431 |
+
"masturbasi",
|
| 1432 |
+
"keparat ibu",
|
| 1433 |
+
"nazi",
|
| 1434 |
+
"orang negro",
|
| 1435 |
+
"negro",
|
| 1436 |
+
"orgasim",
|
| 1437 |
+
"orgasme",
|
| 1438 |
+
"cotok",
|
| 1439 |
+
"penis",
|
| 1440 |
+
"kencing",
|
| 1441 |
+
"kesal",
|
| 1442 |
+
"pisser",
|
| 1443 |
+
"bikin",
|
| 1444 |
+
"buritan",
|
| 1445 |
+
"porno",
|
| 1446 |
+
"pornografi",
|
| 1447 |
+
"tusukan",
|
| 1448 |
+
"menusuk",
|
| 1449 |
+
"pube",
|
| 1450 |
+
"pussies",
|
| 1451 |
+
"memperkosa",
|
| 1452 |
+
"pemerkosa",
|
| 1453 |
+
"memperlambat",
|
| 1454 |
+
"rimming",
|
| 1455 |
+
"sadis",
|
| 1456 |
+
"meniduri",
|
| 1457 |
+
"skrotum",
|
| 1458 |
+
"seks",
|
| 1459 |
+
"bercinta",
|
| 1460 |
+
"waria",
|
| 1461 |
+
"kotoran",
|
| 1462 |
+
"shite",
|
| 1463 |
+
"kengerian",
|
| 1464 |
+
"dikirim",
|
| 1465 |
+
"buang hajat",
|
| 1466 |
+
"menyebalkan",
|
| 1467 |
+
"smegma",
|
| 1468 |
+
"jelaga",
|
| 1469 |
+
"merebut",
|
| 1470 |
+
"dasar bajingan",
|
| 1471 |
+
"ruang",
|
| 1472 |
+
"keberanian",
|
| 1473 |
+
"buah pelir",
|
| 1474 |
+
"titt",
|
| 1475 |
+
"viagra",
|
| 1476 |
+
"vulva",
|
| 1477 |
+
"wang",
|
| 1478 |
+
"terima kasih",
|
| 1479 |
+
"x diberi peringkat",
|
| 1480 |
+
"xxx",
|
| 1481 |
+
],
|
| 1482 |
+
"kn": english_badwords
|
| 1483 |
+
+ [
|
| 1484 |
+
"ಗರ್ಭಪಾತ",
|
| 1485 |
+
"ಗುದ",
|
| 1486 |
+
"ಗುದದ್ವಾರ",
|
| 1487 |
+
"ಕತ್ತೆ",
|
| 1488 |
+
"ಆಶ್-ಫಕರ್",
|
| 1489 |
+
"ಅಸ್ಹೋಲ್",
|
| 1490 |
+
"ಅಸೋಲೆಸ್",
|
| 1491 |
+
"ಬಾಲ್ಬಾಗ್",
|
| 1492 |
+
"ಚೆಂಡುಗಳು",
|
| 1493 |
+
"ಬಾಸ್ಟರ್ಡ್",
|
| 1494 |
+
"ಬೆಲೆಂಡ್",
|
| 1495 |
+
"ಮೃದ್ವಂಗಿ",
|
| 1496 |
+
"ಪ್ರಾಣಿಜನ್ಯತೆ",
|
| 1497 |
+
"ಬಿಚ್",
|
| 1498 |
+
"ಬಿಟ್ಚಿಸ್",
|
| 1499 |
+
"ಬೆಚಿಂಗ್",
|
| 1500 |
+
"ರಕ್ತಸಿಕ್ತ",
|
| 1501 |
+
"ಬ್ಲೋಜಾಬ್",
|
| 1502 |
+
"ಬೊಲ್ಲೊಕ್",
|
| 1503 |
+
"ಕುರುಚಲು ಗಿಡ",
|
| 1504 |
+
"ಬೂಬಿಗಳು",
|
| 1505 |
+
"ಸ್ತನಗಳನ್ನು",
|
| 1506 |
+
"ಬುಕೆಟಾ",
|
| 1507 |
+
"ತಿಕ",
|
| 1508 |
+
"ಬಟ್",
|
| 1509 |
+
"ಕಾರ್ಪೆಟ್ ಮಂಚರ್",
|
| 1510 |
+
"ಚಿಂಕ್",
|
| 1511 |
+
"ಸಿಪಾ",
|
| 1512 |
+
"ಚಂದ್ರನಾಡಿ",
|
| 1513 |
+
"ಕೋಳಿ",
|
| 1514 |
+
"ಕೋಳಿ ಸಕ್ಕರ್",
|
| 1515 |
+
"ಕಾಕ್ಸ್",
|
| 1516 |
+
"ಕೂನ್",
|
| 1517 |
+
"ಅಮೇಧ್ಯ",
|
| 1518 |
+
"ಕಮ್",
|
| 1519 |
+
"ಕಮ್ಶಾಟ್",
|
| 1520 |
+
"ಕುನಿಲ್ಲಸ್",
|
| 1521 |
+
"ಕಂಟ್",
|
| 1522 |
+
"ಡ್ಯಾಮ್",
|
| 1523 |
+
"ಡಿಕ್",
|
| 1524 |
+
"ದ್ವಿಧ್ರುವಿ",
|
| 1525 |
+
"dildos",
|
| 1526 |
+
"ಡಿಂಕ್",
|
| 1527 |
+
"ನಾಯಿ-ಫಕರ್",
|
| 1528 |
+
"ಡಚೆ",
|
| 1529 |
+
"ಡೈಕ್",
|
| 1530 |
+
"ಹೊರಹೊಮ್ಮಿಸು",
|
| 1531 |
+
"ಸ್ಫೂರ್ತಿ",
|
| 1532 |
+
"ಎಜಾಕ್ಯುಲೇಟ್ಸ್",
|
| 1533 |
+
"ಇಜಲಲೇಟಿಂಗ್",
|
| 1534 |
+
"ಉದ್ಗಾರ",
|
| 1535 |
+
"ತಮಾಷೆ",
|
| 1536 |
+
"ಮಂದಗತಿ",
|
| 1537 |
+
"ಮಬ್ಬು",
|
| 1538 |
+
"fagots",
|
| 1539 |
+
"ಫ್ಯಾನಿ",
|
| 1540 |
+
"ಹೊಡೆತ",
|
| 1541 |
+
"ಪತನ",
|
| 1542 |
+
"ಚಾಚುಪಟ್ಟಿ",
|
| 1543 |
+
"ಫಕ್",
|
| 1544 |
+
"ನಾಶವಾಗಿದ್ದನು",
|
| 1545 |
+
"ಫಕರ್",
|
| 1546 |
+
"fuckers",
|
| 1547 |
+
"ಫಕಿಂಗ್",
|
| 1548 |
+
"ಫಕಿಂಗ್ಸ್",
|
| 1549 |
+
"ಇಷ್ಟಪಡುತ್ತಾನೆ",
|
| 1550 |
+
"ಮಿಠಾಯಿ ಪ್ಯಾಕರ್",
|
| 1551 |
+
"ದೇವರನ್ನು ಹಾನಿಗೊಳಗಾಯಿತು",
|
| 1552 |
+
"ಗಾಡ್ಡಮ್",
|
| 1553 |
+
"ನರಕ",
|
| 1554 |
+
"ಹೋರ್",
|
| 1555 |
+
"ಮೊನಚಾದ",
|
| 1556 |
+
"ಜರ್ಕ್-ಆಫ್",
|
| 1557 |
+
"ಕೋಕ್",
|
| 1558 |
+
"ಯೋನಿಯ",
|
| 1559 |
+
"ಕಾಮ",
|
| 1560 |
+
"ಕಾಮುಕ",
|
| 1561 |
+
"ಮಾಸೋಚಿಸ್ಟ್",
|
| 1562 |
+
"ಹಸ್ತಮೈಥುನ ಮಾಡು",
|
| 1563 |
+
"ತಾಯಿ ಫಕರ್",
|
| 1564 |
+
"ನಾಜಿ",
|
| 1565 |
+
"ನಿಗರ್",
|
| 1566 |
+
"ನಿಗ್ಗರ್ಗಳು",
|
| 1567 |
+
"ಒರಾಸಿಮ್",
|
| 1568 |
+
"ಪರಾಕಾಷ್ಠೆ",
|
| 1569 |
+
"ಪರಾಕಾಷ್ಠೆಗಳನ್ನು",
|
| 1570 |
+
"ಪೆಕರ್",
|
| 1571 |
+
"ಶಿಶ್ನ",
|
| 1572 |
+
"ಮೂತ್ರ ವಿಸರ್ಜಿಸು",
|
| 1573 |
+
"ನಿರುತ್ಸಾಹಗೊಂಡಿದೆ",
|
| 1574 |
+
"ಪಿಸರ್",
|
| 1575 |
+
"ಮೂತ್ರಪಿಂಡಗಳು",
|
| 1576 |
+
"pissing",
|
| 1577 |
+
"ಪಿಸ್ಸಾಫ್",
|
| 1578 |
+
"ಪೂಪ್",
|
| 1579 |
+
"ಅಶ್ಲೀಲತೆ",
|
| 1580 |
+
"ಅಶ್ಲೀಲ",
|
| 1581 |
+
"ಚುಚ್ಚು",
|
| 1582 |
+
"ಪ್ರಿಕ್ಸ್",
|
| 1583 |
+
"ಪಬ್",
|
| 1584 |
+
"ಪುಸಿಗಳು",
|
| 1585 |
+
"ಪುಸಿ",
|
| 1586 |
+
"ಅತ್ಯಾಚಾರ",
|
| 1587 |
+
"ಅತ್ಯಾಚಾರಿ",
|
| 1588 |
+
"ಗುದನಾಳದ",
|
| 1589 |
+
"ರಿಟಾರ್ಡ್",
|
| 1590 |
+
"ಹಚ್ಚುವುದು",
|
| 1591 |
+
"ದುಃಖಗಾರ",
|
| 1592 |
+
"ತಿರುಗಿಸುವುದು",
|
| 1593 |
+
"ಸ್ಕ್ರೋಟಮ್",
|
| 1594 |
+
"ವೀರ್ಯ",
|
| 1595 |
+
"ಲೈಂಗಿಕತೆ",
|
| 1596 |
+
"ಶಾಗ್",
|
| 1597 |
+
"ಶಾಗ್ಗಿಂಗ್",
|
| 1598 |
+
"ಶೆಮೇಲ್",
|
| 1599 |
+
"ಶಿಟ್",
|
| 1600 |
+
"ಷೈಟ್",
|
| 1601 |
+
"ಶಿಟ್ಸ್",
|
| 1602 |
+
"shitted",
|
| 1603 |
+
"ಅಲುಗಾಡುವಿಕೆ",
|
| 1604 |
+
"ಅಸಹ್ಯ",
|
| 1605 |
+
"ಸ್ಕಾಂಕ್",
|
| 1606 |
+
"ಸೂಳೆ",
|
| 1607 |
+
"ಸ್ಲಟ್ಗಳು",
|
| 1608 |
+
"ಸ್ಮೆಗ್ಮಾ",
|
| 1609 |
+
"ಕೊಳೆತ",
|
| 1610 |
+
"ಸ್ನ್ಯಾಚ್",
|
| 1611 |
+
"ಮಗ-ಆಫ್-ಬಿಚ್",
|
| 1612 |
+
"spac",
|
| 1613 |
+
"ಉಬ್ಬು",
|
| 1614 |
+
"ವೃಷಣ",
|
| 1615 |
+
"ಟಿಟ್",
|
| 1616 |
+
"ಚೇಕಡಿ ಹಕ್ಕಿಗಳು",
|
| 1617 |
+
"turd",
|
| 1618 |
+
"ಯೋನಿ",
|
| 1619 |
+
"ವಯಾಗ್ರ",
|
| 1620 |
+
"ವಾಂಗ್",
|
| 1621 |
+
"ಮುಷ್ಕರ",
|
| 1622 |
+
"x ರೇಟೆಡ್",
|
| 1623 |
+
"xxx",
|
| 1624 |
+
],
|
| 1625 |
+
"ml": english_badwords
|
| 1626 |
+
+ [
|
| 1627 |
+
"ഗർഭഛിദ്രം",
|
| 1628 |
+
"വിശപ്പ്",
|
| 1629 |
+
"മലദ്വാരം",
|
| 1630 |
+
"കഴുത",
|
| 1631 |
+
"അസി ഫക്കർ",
|
| 1632 |
+
"കഴുതകളെ",
|
| 1633 |
+
"ആസ്ഹോൾ",
|
| 1634 |
+
"അശ്ളീലങ്ങൾ",
|
| 1635 |
+
"ബോൾബാഗ്",
|
| 1636 |
+
"പന്തുകൾ",
|
| 1637 |
+
"തന്തയില്ലാത്തവൻ",
|
| 1638 |
+
"ബെല്ലെൻഡ്",
|
| 1639 |
+
"മൃഗീയമായ",
|
| 1640 |
+
"മൃഗീയത",
|
| 1641 |
+
"ബിച്ച്",
|
| 1642 |
+
"ബിച്ചുകൾ",
|
| 1643 |
+
"ബിപിഡിംഗ്",
|
| 1644 |
+
"രക്തരൂക്ഷിതമായ",
|
| 1645 |
+
"ആശ്വാസം",
|
| 1646 |
+
"ബലോക്ക്",
|
| 1647 |
+
"ബോബ്",
|
| 1648 |
+
"പൂക്കൾ",
|
| 1649 |
+
"സ്തനങ്ങൾ",
|
| 1650 |
+
"ബ്യൂട്ടാ",
|
| 1651 |
+
"ബം",
|
| 1652 |
+
"മയക്കുമരുന്ന്",
|
| 1653 |
+
"പരവതാനി മാൻച്ചർ",
|
| 1654 |
+
"ചുംബ്",
|
| 1655 |
+
"സിപാ",
|
| 1656 |
+
"ക്ലോറിസിസ്",
|
| 1657 |
+
"കോക്ക്",
|
| 1658 |
+
"കോക്ക് സക്കർ",
|
| 1659 |
+
"കോക്സ്",
|
| 1660 |
+
"കോൺ",
|
| 1661 |
+
"ക്രാപ്പ്",
|
| 1662 |
+
"ശുക്ലം",
|
| 1663 |
+
"പുരുഷാരം",
|
| 1664 |
+
"സി",
|
| 1665 |
+
"മുഷിഞ്ഞ",
|
| 1666 |
+
"കഷ്ടം",
|
| 1667 |
+
"ഡിക്ക്",
|
| 1668 |
+
"ഡിൽഡോ",
|
| 1669 |
+
"dildos",
|
| 1670 |
+
"ഡൈൻ",
|
| 1671 |
+
"നായ-ഫക്കർ",
|
| 1672 |
+
"ഡച്ച്",
|
| 1673 |
+
"ഡൈകെ",
|
| 1674 |
+
"ശമിപ്പിക്കുക",
|
| 1675 |
+
"മോഷ്ടിച്ചു",
|
| 1676 |
+
"വികാരങ്ങൾ",
|
| 1677 |
+
"വിരസത",
|
| 1678 |
+
"മടി",
|
| 1679 |
+
"ക്ഷീണിപ്പിക്കുക",
|
| 1680 |
+
"fagot",
|
| 1681 |
+
"വഞ്ചന",
|
| 1682 |
+
"ഫാനി",
|
| 1683 |
+
"വേദന",
|
| 1684 |
+
"flange",
|
| 1685 |
+
"ഊമ്പി",
|
| 1686 |
+
"സംഭോഗം ചെയ്യുക",
|
| 1687 |
+
"ഫക്കർ",
|
| 1688 |
+
"നർമ്മം",
|
| 1689 |
+
"ഫഡ്ജ് പാക്കർ",
|
| 1690 |
+
"ദൈവം-കൊള്ളിത",
|
| 1691 |
+
"ഗോഡ്ഡം",
|
| 1692 |
+
"നരകം",
|
| 1693 |
+
"വയ്ക്കുക",
|
| 1694 |
+
"വൃത്തികെട്ട",
|
| 1695 |
+
"ജെർക് ഓഫ്",
|
| 1696 |
+
"കിക്ക്",
|
| 1697 |
+
"ലാബിയ",
|
| 1698 |
+
"മോഹം",
|
| 1699 |
+
"മോഹഭംഗം",
|
| 1700 |
+
"മാസോച്ചിസ്റ്റ്",
|
| 1701 |
+
"സ്വയംഭോഗം ചെയ്യുക",
|
| 1702 |
+
"അമ്മ ഫക്കർ",
|
| 1703 |
+
"നാസി",
|
| 1704 |
+
"നിഗർ",
|
| 1705 |
+
"മയക്കുമരുന്നുകൾ",
|
| 1706 |
+
"രതിമൂർച്ഛ",
|
| 1707 |
+
"പെക്കർ",
|
| 1708 |
+
"ലിംഗം",
|
| 1709 |
+
"മൂത്രമൊഴിക്കുക",
|
| 1710 |
+
"കുഴഞ്ഞുവീഴുന്നു",
|
| 1711 |
+
"പിസ്സർ",
|
| 1712 |
+
"പിസ്സകൾ",
|
| 1713 |
+
"pissing",
|
| 1714 |
+
"പിസ്സോഫ്",
|
| 1715 |
+
"poop",
|
| 1716 |
+
"അശ്ലീലം",
|
| 1717 |
+
"അശ്ലീലത",
|
| 1718 |
+
"പ്രാവി",
|
| 1719 |
+
"വിസർജ്യങ്ങൾ",
|
| 1720 |
+
"പ്യൂബ്",
|
| 1721 |
+
"pussies",
|
| 1722 |
+
"pussy",
|
| 1723 |
+
"ബലാൽസംഗം",
|
| 1724 |
+
"ബലാത്സംഗം",
|
| 1725 |
+
"മലാശയം",
|
| 1726 |
+
"തുടരുക",
|
| 1727 |
+
"റിമ്മിംഗ്",
|
| 1728 |
+
"സചിസ്റ്റ്",
|
| 1729 |
+
"വഞ്ചി",
|
| 1730 |
+
"പുല്ല്",
|
| 1731 |
+
"ബീജം",
|
| 1732 |
+
"ശവം",
|
| 1733 |
+
"ഷാഗിംഗ്",
|
| 1734 |
+
"അവൾ",
|
| 1735 |
+
"ഷീറ്റ്",
|
| 1736 |
+
"ഷെയ്റ്റ്",
|
| 1737 |
+
"shits",
|
| 1738 |
+
"തിന്നിട്ടില്ല",
|
| 1739 |
+
"ഷോർട്ട്",
|
| 1740 |
+
"ഷൈറ്റി",
|
| 1741 |
+
"സ്കാൻ",
|
| 1742 |
+
"മന്ദഹസരം",
|
| 1743 |
+
"സ്നെഗമാ",
|
| 1744 |
+
"പുഞ്ചിരി",
|
| 1745 |
+
"പിടിക്കുക",
|
| 1746 |
+
"വെറുക്കപ്പെട്ടയാൾ",
|
| 1747 |
+
"സ്പെയ്ക്",
|
| 1748 |
+
"തുളച്ച്",
|
| 1749 |
+
"വൃഷണം",
|
| 1750 |
+
"പേ",
|
| 1751 |
+
"ടിത്ത്",
|
| 1752 |
+
"കുഴപ്പമില്ല",
|
| 1753 |
+
"യോനി",
|
| 1754 |
+
"വരാഗ്ര",
|
| 1755 |
+
"വാൽവ",
|
| 1756 |
+
"വാങ്",
|
| 1757 |
+
"വാൻ",
|
| 1758 |
+
"വേശ്യ",
|
| 1759 |
+
"x റേറ്റുചെയ്തു",
|
| 1760 |
+
"xxx",
|
| 1761 |
+
],
|
| 1762 |
+
"mr": english_badwords
|
| 1763 |
+
+ [
|
| 1764 |
+
"गर्भपात",
|
| 1765 |
+
"गुदा",
|
| 1766 |
+
"गाढव",
|
| 1767 |
+
"गांडुळ",
|
| 1768 |
+
"asses",
|
| 1769 |
+
"asshole",
|
| 1770 |
+
"assholes",
|
| 1771 |
+
"ballbag",
|
| 1772 |
+
"चेंडू",
|
| 1773 |
+
"बॅस्टर्ड",
|
| 1774 |
+
"बेलेंड",
|
| 1775 |
+
"बेस्टियल",
|
| 1776 |
+
"प्राण्यांबरोबर",
|
| 1777 |
+
"कुत्री",
|
| 1778 |
+
"बिट्स",
|
| 1779 |
+
"खूनी",
|
| 1780 |
+
"blowjob",
|
| 1781 |
+
"बोलोक",
|
| 1782 |
+
"बोब",
|
| 1783 |
+
"स्तन",
|
| 1784 |
+
"बसीटा",
|
| 1785 |
+
"बम",
|
| 1786 |
+
"बट",
|
| 1787 |
+
"कार्पेट मुन्चर",
|
| 1788 |
+
"चिंक",
|
| 1789 |
+
"सिपा",
|
| 1790 |
+
"क्लिटोरिस",
|
| 1791 |
+
"मुर्ख",
|
| 1792 |
+
"मांसाहारी",
|
| 1793 |
+
"कॉक्स",
|
| 1794 |
+
"कॉनन",
|
| 1795 |
+
"बकवास",
|
| 1796 |
+
"सह",
|
| 1797 |
+
"cumshot",
|
| 1798 |
+
"कनिलिंगस",
|
| 1799 |
+
"कांट",
|
| 1800 |
+
"धिक्कार",
|
| 1801 |
+
"डिक",
|
| 1802 |
+
"dildo",
|
| 1803 |
+
"डिल्डो",
|
| 1804 |
+
"डंक",
|
| 1805 |
+
"duche",
|
| 1806 |
+
"डाईक",
|
| 1807 |
+
"उद्गार",
|
| 1808 |
+
"उत्साही",
|
| 1809 |
+
"ejaculates",
|
| 1810 |
+
"उत्सुकता",
|
| 1811 |
+
"स्खलन",
|
| 1812 |
+
"फॅग",
|
| 1813 |
+
"फॅगिंग",
|
| 1814 |
+
"फॅगॉट",
|
| 1815 |
+
"फॅगॉट्स",
|
| 1816 |
+
"फॅनी",
|
| 1817 |
+
"फेलिंग",
|
| 1818 |
+
"फॅलेटीओ",
|
| 1819 |
+
"निकला",
|
| 1820 |
+
"fucked",
|
| 1821 |
+
"गुप्तचर",
|
| 1822 |
+
"fuckers",
|
| 1823 |
+
"fucking",
|
| 1824 |
+
"fuckings",
|
| 1825 |
+
"fucks",
|
| 1826 |
+
"फडगे पॅकर",
|
| 1827 |
+
"देव-शापित",
|
| 1828 |
+
"देव",
|
| 1829 |
+
"नरक",
|
| 1830 |
+
"होरे",
|
| 1831 |
+
"शिंग",
|
| 1832 |
+
"झटका बंद",
|
| 1833 |
+
"कॉक",
|
| 1834 |
+
"लॅबिया",
|
| 1835 |
+
"वासना",
|
| 1836 |
+
"मासोचिस्ट",
|
| 1837 |
+
"हस्तमैथुन करा",
|
| 1838 |
+
"आई माकड",
|
| 1839 |
+
"नाझी",
|
| 1840 |
+
"निगर",
|
| 1841 |
+
"निगार",
|
| 1842 |
+
"ऑर्गॅसिम",
|
| 1843 |
+
"संभोग",
|
| 1844 |
+
"orgasms",
|
| 1845 |
+
"चापटी",
|
| 1846 |
+
"पुरुषाचे जननेंद्रिय",
|
| 1847 |
+
"पेशी",
|
| 1848 |
+
"pissed",
|
| 1849 |
+
"पिसर",
|
| 1850 |
+
"pisses",
|
| 1851 |
+
"पिसिंग",
|
| 1852 |
+
"पिसोफ",
|
| 1853 |
+
"घाट",
|
| 1854 |
+
"अश्लील",
|
| 1855 |
+
"पोर्नोग्राफी",
|
| 1856 |
+
"मुरुम",
|
| 1857 |
+
"प्रिक्स",
|
| 1858 |
+
"प्यूब",
|
| 1859 |
+
"pussies",
|
| 1860 |
+
"मांजर",
|
| 1861 |
+
"बलात्कार",
|
| 1862 |
+
"गुदाशय",
|
| 1863 |
+
"मंद",
|
| 1864 |
+
"rimming",
|
| 1865 |
+
"दुःखी",
|
| 1866 |
+
"screwing",
|
| 1867 |
+
"स्क्रोटम",
|
| 1868 |
+
"वीर्य",
|
| 1869 |
+
"लिंग",
|
| 1870 |
+
"शेग",
|
| 1871 |
+
"shagging",
|
| 1872 |
+
"शेमले",
|
| 1873 |
+
"विचित्र",
|
| 1874 |
+
"shite",
|
| 1875 |
+
"shits",
|
| 1876 |
+
"shitted",
|
| 1877 |
+
"shitting",
|
| 1878 |
+
"shitty",
|
| 1879 |
+
"घाणेरडा",
|
| 1880 |
+
"फट",
|
| 1881 |
+
"sluts",
|
| 1882 |
+
"सुगंध",
|
| 1883 |
+
"स्मट",
|
| 1884 |
+
"छेडछाड",
|
| 1885 |
+
"मुलगा-एक-कुत्री",
|
| 1886 |
+
"spac",
|
| 1887 |
+
"तिरस्कार",
|
| 1888 |
+
"परीक्षक",
|
| 1889 |
+
"शीर्षक",
|
| 1890 |
+
"टिट",
|
| 1891 |
+
"टर्ड",
|
| 1892 |
+
"योनी",
|
| 1893 |
+
"वियाग्रा",
|
| 1894 |
+
"वल्वा",
|
| 1895 |
+
"वांग",
|
| 1896 |
+
"विंक",
|
| 1897 |
+
"वेश्या",
|
| 1898 |
+
"एक्स रेट केले",
|
| 1899 |
+
"xxx",
|
| 1900 |
+
],
|
| 1901 |
+
"pt": english_badwords
|
| 1902 |
+
+ [
|
| 1903 |
+
"aborto",
|
| 1904 |
+
"amador",
|
| 1905 |
+
"anal",
|
| 1906 |
+
"aparafusar",
|
| 1907 |
+
"aranha",
|
| 1908 |
+
"ariano",
|
| 1909 |
+
"arrebatar",
|
| 1910 |
+
"ass-filho da puta",
|
| 1911 |
+
"asses",
|
| 1912 |
+
"balalao",
|
| 1913 |
+
"bastardo",
|
| 1914 |
+
"bate uma",
|
| 1915 |
+
"bellend",
|
| 1916 |
+
"bestial",
|
| 1917 |
+
"bestialidade",
|
| 1918 |
+
"bicha",
|
| 1919 |
+
"bichano",
|
| 1920 |
+
"bichanos",
|
| 1921 |
+
"bichas",
|
| 1922 |
+
"biscate",
|
| 1923 |
+
"bissexual",
|
| 1924 |
+
"boceta",
|
| 1925 |
+
"bolas",
|
| 1926 |
+
"bollok",
|
| 1927 |
+
"boob",
|
| 1928 |
+
"boquete",
|
| 1929 |
+
"bosta",
|
| 1930 |
+
"braulio de borracha",
|
| 1931 |
+
"buceta",
|
| 1932 |
+
"bumbum",
|
| 1933 |
+
"bunda",
|
| 1934 |
+
"burro",
|
| 1935 |
+
"cabrao",
|
| 1936 |
+
"cacete",
|
| 1937 |
+
"cadela",
|
| 1938 |
+
"cadelas",
|
| 1939 |
+
"cagando",
|
| 1940 |
+
"cagar",
|
| 1941 |
+
"calçado",
|
| 1942 |
+
"camisinha",
|
| 1943 |
+
"caralho",
|
| 1944 |
+
"cerveja",
|
| 1945 |
+
"chochota",
|
| 1946 |
+
"chupar",
|
| 1947 |
+
"cipa",
|
| 1948 |
+
"clitoris",
|
| 1949 |
+
"clitóris",
|
| 1950 |
+
"cobiçoso",
|
| 1951 |
+
"cocaína",
|
| 1952 |
+
"cocô",
|
| 1953 |
+
"coito",
|
| 1954 |
+
"colhoes",
|
| 1955 |
+
"com tesão",
|
| 1956 |
+
"comedor de tapetes",
|
| 1957 |
+
"comer",
|
| 1958 |
+
"cona",
|
| 1959 |
+
"consolo",
|
| 1960 |
+
"coon",
|
| 1961 |
+
"coragem",
|
| 1962 |
+
"corno",
|
| 1963 |
+
"cu",
|
| 1964 |
+
"cunillingus",
|
| 1965 |
+
"dar o rabo",
|
| 1966 |
+
"desgraçado",
|
| 1967 |
+
"dildo",
|
| 1968 |
+
"dildos",
|
| 1969 |
+
"dink",
|
| 1970 |
+
"dog-filho da puta",
|
| 1971 |
+
"droga",
|
| 1972 |
+
"duche",
|
| 1973 |
+
"dum raio",
|
| 1974 |
+
"ejacula",
|
| 1975 |
+
"ejaculado",
|
| 1976 |
+
"ejacular",
|
| 1977 |
+
"ejaculação",
|
| 1978 |
+
"empacotador de fudge",
|
| 1979 |
+
"escroto",
|
| 1980 |
+
"esporra",
|
| 1981 |
+
"estuprador",
|
| 1982 |
+
"estupro",
|
| 1983 |
+
"fagging",
|
| 1984 |
+
"fanny",
|
| 1985 |
+
"fecal",
|
| 1986 |
+
"felação",
|
| 1987 |
+
"felching",
|
| 1988 |
+
"fenda",
|
| 1989 |
+
"filho da puta",
|
| 1990 |
+
"filhos da puta",
|
| 1991 |
+
"foda",
|
| 1992 |
+
"foda-se",
|
| 1993 |
+
"fode",
|
| 1994 |
+
"foder",
|
| 1995 |
+
"fodido",
|
| 1996 |
+
"frango assado",
|
| 1997 |
+
"galo",
|
| 1998 |
+
"galos",
|
| 1999 |
+
"gozada",
|
| 2000 |
+
"gozar",
|
| 2001 |
+
"grelho",
|
| 2002 |
+
"heroína",
|
| 2003 |
+
"homem gay",
|
| 2004 |
+
"homoerótico",
|
| 2005 |
+
"homosexual",
|
| 2006 |
+
"hore",
|
| 2007 |
+
"idiota",
|
| 2008 |
+
"idiotas",
|
| 2009 |
+
"inferno",
|
| 2010 |
+
"kock",
|
| 2011 |
+
"lolita",
|
| 2012 |
+
"luxúria",
|
| 2013 |
+
"lábios",
|
| 2014 |
+
"lésbica",
|
| 2015 |
+
"maldito",
|
| 2016 |
+
"mama",
|
| 2017 |
+
"masoquista",
|
| 2018 |
+
"masturbar",
|
| 2019 |
+
"merda",
|
| 2020 |
+
"merdas",
|
| 2021 |
+
"mesa",
|
| 2022 |
+
"mijando",
|
| 2023 |
+
"mijar",
|
| 2024 |
+
"nazista",
|
| 2025 |
+
"negro",
|
| 2026 |
+
"niggers",
|
| 2027 |
+
"não me chateies",
|
| 2028 |
+
"orgasim",
|
| 2029 |
+
"orgasmo",
|
| 2030 |
+
"orgasmos",
|
| 2031 |
+
"otário",
|
| 2032 |
+
"paneleiro",
|
| 2033 |
+
"passar um cheque",
|
| 2034 |
+
"pau",
|
| 2035 |
+
"peidar",
|
| 2036 |
+
"peitos",
|
| 2037 |
+
"peituda",
|
| 2038 |
+
"pica",
|
| 2039 |
+
"picadas",
|
| 2040 |
+
"pinto",
|
| 2041 |
+
"pisser",
|
| 2042 |
+
"porcaria",
|
| 2043 |
+
"porno",
|
| 2044 |
+
"pornografia",
|
| 2045 |
+
"pornô",
|
| 2046 |
+
"porra",
|
| 2047 |
+
"prostituta",
|
| 2048 |
+
"pube",
|
| 2049 |
+
"punheta",
|
| 2050 |
+
"puta",
|
| 2051 |
+
"puta que pariu",
|
| 2052 |
+
"puta que te pariu",
|
| 2053 |
+
"putaria",
|
| 2054 |
+
"puto",
|
| 2055 |
+
"pênis",
|
| 2056 |
+
"queca",
|
| 2057 |
+
"retardar",
|
| 2058 |
+
"reto",
|
| 2059 |
+
"rimming",
|
| 2060 |
+
"sacanagem",
|
| 2061 |
+
"saco",
|
| 2062 |
+
"saco de bola",
|
| 2063 |
+
"sangrento",
|
| 2064 |
+
"sapatona",
|
| 2065 |
+
"sexo",
|
| 2066 |
+
"shite",
|
| 2067 |
+
"skank",
|
| 2068 |
+
"smegma",
|
| 2069 |
+
"spac",
|
| 2070 |
+
"sujeira",
|
| 2071 |
+
"sádico",
|
| 2072 |
+
"sêmen",
|
| 2073 |
+
"testículo",
|
| 2074 |
+
"tetas",
|
| 2075 |
+
"titt",
|
| 2076 |
+
"torneira",
|
| 2077 |
+
"transando",
|
| 2078 |
+
"transar",
|
| 2079 |
+
"transsexual",
|
| 2080 |
+
"trepada",
|
| 2081 |
+
"vadia",
|
| 2082 |
+
"vadias",
|
| 2083 |
+
"vagabunda",
|
| 2084 |
+
"vagabundo",
|
| 2085 |
+
"vagina",
|
| 2086 |
+
"vai tomar no cu",
|
| 2087 |
+
"vai-te foder",
|
| 2088 |
+
"veado",
|
| 2089 |
+
"viagra",
|
| 2090 |
+
"vibrador",
|
| 2091 |
+
"vulva",
|
| 2092 |
+
"wang",
|
| 2093 |
+
"x avaliado",
|
| 2094 |
+
"xana",
|
| 2095 |
+
"xixi",
|
| 2096 |
+
"xochota",
|
| 2097 |
+
"xxx",
|
| 2098 |
+
"ânus",
|
| 2099 |
+
],
|
| 2100 |
+
"te": english_badwords
|
| 2101 |
+
+ [
|
| 2102 |
+
"గర్భస్రావం",
|
| 2103 |
+
"అంగ",
|
| 2104 |
+
"పాయువు",
|
| 2105 |
+
"గాడిద",
|
| 2106 |
+
"గాడిద-fucker",
|
| 2107 |
+
"asses",
|
| 2108 |
+
"assholes",
|
| 2109 |
+
"బాల్బ్యాగ్",
|
| 2110 |
+
"బంతుల్లో",
|
| 2111 |
+
"బాస్టర్డ్",
|
| 2112 |
+
"బెల్లెండ్",
|
| 2113 |
+
"మృగ",
|
| 2114 |
+
"బెస్టియాలిటీ",
|
| 2115 |
+
"బిచ్",
|
| 2116 |
+
"bitches",
|
| 2117 |
+
"బిట్చింగ్",
|
| 2118 |
+
"బ్లడీ",
|
| 2119 |
+
"blowjob",
|
| 2120 |
+
"బోల్లక",
|
| 2121 |
+
"బూబ్",
|
| 2122 |
+
"వక్షోజాలను",
|
| 2123 |
+
"ఛాతీ",
|
| 2124 |
+
"buceta",
|
| 2125 |
+
"బం",
|
| 2126 |
+
"బట్",
|
| 2127 |
+
"కార్పెట్ ముంచర్",
|
| 2128 |
+
"చింక్",
|
| 2129 |
+
"cipa",
|
| 2130 |
+
"స్త్రీగుహ్యాంకురము",
|
| 2131 |
+
"ఆత్మవిశ్వాసం",
|
| 2132 |
+
"కాక్-సక్కర్",
|
| 2133 |
+
"కాక్స్",
|
| 2134 |
+
"కూన్",
|
| 2135 |
+
"చెత్త",
|
| 2136 |
+
"కం",
|
| 2137 |
+
"cumshot",
|
| 2138 |
+
"క్యునిల్లింగస్",
|
| 2139 |
+
"కంట్",
|
| 2140 |
+
"తిట్టు",
|
| 2141 |
+
"డిక్",
|
| 2142 |
+
"లైంగిక సంతృప్తి కోసం స్త్రీలు ఉపయోగించే పురుషాంగము వంటి పరికరము",
|
| 2143 |
+
"డిల్డోస్",
|
| 2144 |
+
"dink",
|
| 2145 |
+
"కుక్క-fucker",
|
| 2146 |
+
"డూష్",
|
| 2147 |
+
"డైక్",
|
| 2148 |
+
"స్ఖలించు",
|
| 2149 |
+
"ఎజాక్యులేటెడ్",
|
| 2150 |
+
"ఎజాక్యులేట్స్",
|
| 2151 |
+
"ఎరాక్యులేటింగ్",
|
| 2152 |
+
"స్ఖలనం",
|
| 2153 |
+
"నవుకరు",
|
| 2154 |
+
"ఫాగ్గింగ్",
|
| 2155 |
+
"ఫాగాట్",
|
| 2156 |
+
"ఫగాట్స్",
|
| 2157 |
+
"fanny",
|
| 2158 |
+
"ఫెల్చింగ్",
|
| 2159 |
+
"కుడుచుట",
|
| 2160 |
+
"అచ్చు",
|
| 2161 |
+
"ఫక్",
|
| 2162 |
+
"ఇబ్బంది పెట్టాడు",
|
| 2163 |
+
"fucker",
|
| 2164 |
+
"ఫకర్స్",
|
| 2165 |
+
"ఫకింగ్",
|
| 2166 |
+
"ఫకింగ్స్",
|
| 2167 |
+
"ఫక్స్",
|
| 2168 |
+
"ఫడ్జ్ ప్యాకర్",
|
| 2169 |
+
"దేవతలా మంచిది",
|
| 2170 |
+
"గాడ్డామ్",
|
| 2171 |
+
"నరకం",
|
| 2172 |
+
"హోర్",
|
| 2173 |
+
"horny",
|
| 2174 |
+
"జెర్క్-ఆఫ్",
|
| 2175 |
+
"కాక్",
|
| 2176 |
+
"పెదవి",
|
| 2177 |
+
"కామం",
|
| 2178 |
+
"మనసు పడ్డట్లు చిత్రించారు",
|
| 2179 |
+
"masochist",
|
| 2180 |
+
"హస్తప్రయోగం",
|
| 2181 |
+
"తల్లి ఫెకర్",
|
| 2182 |
+
"నాజీ",
|
| 2183 |
+
"నిగ్గర్",
|
| 2184 |
+
"నిగ్గర్స్",
|
| 2185 |
+
"ఆర్గాసిమ్",
|
| 2186 |
+
"స్కలనం",
|
| 2187 |
+
"orgasms",
|
| 2188 |
+
"pecker",
|
| 2189 |
+
"పురుషాంగం",
|
| 2190 |
+
"విసర్జన",
|
| 2191 |
+
"pissed",
|
| 2192 |
+
"పిస్సర్",
|
| 2193 |
+
"పిస్సీస్",
|
| 2194 |
+
"పిస్సింగ్",
|
| 2195 |
+
"పిస్సాఫ్",
|
| 2196 |
+
"poop",
|
| 2197 |
+
"శృంగార",
|
| 2198 |
+
"పోర్నో",
|
| 2199 |
+
"అశ్లీల",
|
| 2200 |
+
"బుడతడు",
|
| 2201 |
+
"ప్రిక్స్",
|
| 2202 |
+
"ప్యూబ్",
|
| 2203 |
+
"pussies",
|
| 2204 |
+
"పుస్సీ",
|
| 2205 |
+
"రేప్",
|
| 2206 |
+
"ఉన్నప్పటికీ బలాత్కారం",
|
| 2207 |
+
"పురీషనాళం",
|
| 2208 |
+
"రిటార్డ్",
|
| 2209 |
+
"రిమ్మింగ్",
|
| 2210 |
+
"పీడన కాముకత",
|
| 2211 |
+
"screwing",
|
| 2212 |
+
"స్క్రోటమ్",
|
| 2213 |
+
"వీర్యం",
|
| 2214 |
+
"సెక్స్",
|
| 2215 |
+
"బొచ్చు",
|
| 2216 |
+
"షగ్గింగ్",
|
| 2217 |
+
"షీమేల్",
|
| 2218 |
+
"ఒంటి",
|
| 2219 |
+
"షైట్",
|
| 2220 |
+
"షిట్స్",
|
| 2221 |
+
"షిట్టెడ్",
|
| 2222 |
+
"షిట్టింగ్",
|
| 2223 |
+
"shitty",
|
| 2224 |
+
"స్కాన్క్",
|
| 2225 |
+
"నీతి",
|
| 2226 |
+
"స్లట్స్",
|
| 2227 |
+
"శిశ్న",
|
| 2228 |
+
"స్మట్",
|
| 2229 |
+
"స్నాచ్",
|
| 2230 |
+
"ఒక బిచ్ కుమారుడు ఆఫ్",
|
| 2231 |
+
"spac",
|
| 2232 |
+
"స్పంక్",
|
| 2233 |
+
"వృషణాలు",
|
| 2234 |
+
"తునక",
|
| 2235 |
+
"టిట్స్",
|
| 2236 |
+
"టిట్",
|
| 2237 |
+
"turd",
|
| 2238 |
+
"యోని",
|
| 2239 |
+
"వయాగ్రా",
|
| 2240 |
+
"జననాంగం",
|
| 2241 |
+
"వాంగ్",
|
| 2242 |
+
"వ్యాంక్",
|
| 2243 |
+
"వేశ్య",
|
| 2244 |
+
"x రేట్",
|
| 2245 |
+
"xxx",
|
| 2246 |
+
],
|
| 2247 |
+
"vi": english_badwords
|
| 2248 |
+
+ [
|
| 2249 |
+
"sự phá thai",
|
| 2250 |
+
"hậu môn",
|
| 2251 |
+
"mông",
|
| 2252 |
+
"đồ ngu",
|
| 2253 |
+
"lừa",
|
| 2254 |
+
"lỗ đít",
|
| 2255 |
+
"túi bóng",
|
| 2256 |
+
"những quả bóng",
|
| 2257 |
+
"đồ khốn",
|
| 2258 |
+
"tuyệt vời",
|
| 2259 |
+
"mục sư",
|
| 2260 |
+
"lòng tốt",
|
| 2261 |
+
"chó cái",
|
| 2262 |
+
"dính máu",
|
| 2263 |
+
"công việc thổi",
|
| 2264 |
+
"bollok",
|
| 2265 |
+
"boob",
|
| 2266 |
+
"ngực",
|
| 2267 |
+
"buceta",
|
| 2268 |
+
"ăn mày",
|
| 2269 |
+
"thảm muncher",
|
| 2270 |
+
"sứt mẻ",
|
| 2271 |
+
"cipa",
|
| 2272 |
+
"âm vật",
|
| 2273 |
+
"gà",
|
| 2274 |
+
"gà hút",
|
| 2275 |
+
"gà trống",
|
| 2276 |
+
"coon",
|
| 2277 |
+
"tào lao",
|
| 2278 |
+
"kiêm",
|
| 2279 |
+
"cum",
|
| 2280 |
+
"cunillingus",
|
| 2281 |
+
"lồn",
|
| 2282 |
+
"chỉ trích",
|
| 2283 |
+
"tinh ranh",
|
| 2284 |
+
"dương vật giả",
|
| 2285 |
+
"dink",
|
| 2286 |
+
"chó-chó",
|
| 2287 |
+
"duche",
|
| 2288 |
+
"đê",
|
| 2289 |
+
"xuất tinh",
|
| 2290 |
+
"fag",
|
| 2291 |
+
"đóng băng",
|
| 2292 |
+
"fagot",
|
| 2293 |
+
"đồ ăn vặt",
|
| 2294 |
+
"người hâm mộ",
|
| 2295 |
+
"nỉ",
|
| 2296 |
+
"thất bại",
|
| 2297 |
+
"mặt bích",
|
| 2298 |
+
"chết tiệt",
|
| 2299 |
+
"quái",
|
| 2300 |
+
"đụ",
|
| 2301 |
+
"ôm",
|
| 2302 |
+
"đóng gói fudge",
|
| 2303 |
+
"địa ngục",
|
| 2304 |
+
"có",
|
| 2305 |
+
"sừng",
|
| 2306 |
+
"giật",
|
| 2307 |
+
"kock",
|
| 2308 |
+
"môi âm",
|
| 2309 |
+
"ham muốn",
|
| 2310 |
+
"khổ dâm",
|
| 2311 |
+
"thủ dâm",
|
| 2312 |
+
"mẹ kiếp",
|
| 2313 |
+
"nazi",
|
| 2314 |
+
"người da đen",
|
| 2315 |
+
"người mách nước",
|
| 2316 |
+
"cực khoái",
|
| 2317 |
+
"người mổ",
|
| 2318 |
+
"dương vật",
|
| 2319 |
+
"đi tiểu",
|
| 2320 |
+
"bực mình",
|
| 2321 |
+
"đái",
|
| 2322 |
+
"phân",
|
| 2323 |
+
"khiêu dâm",
|
| 2324 |
+
"nội dung khiêu dâm",
|
| 2325 |
+
"châm",
|
| 2326 |
+
"chích",
|
| 2327 |
+
"pube",
|
| 2328 |
+
"pussies",
|
| 2329 |
+
"âm hộ",
|
| 2330 |
+
"hiếp dâm",
|
| 2331 |
+
"trực tràng",
|
| 2332 |
+
"chậm phát triển",
|
| 2333 |
+
"xé",
|
| 2334 |
+
"người tàn bạo",
|
| 2335 |
+
"vặn vít",
|
| 2336 |
+
"bìu",
|
| 2337 |
+
"tinh dịch",
|
| 2338 |
+
"tình dục",
|
| 2339 |
+
"lông",
|
| 2340 |
+
"xáo trộn",
|
| 2341 |
+
"đồng tính",
|
| 2342 |
+
"cứt",
|
| 2343 |
+
"shite",
|
| 2344 |
+
"ván trượt",
|
| 2345 |
+
"đĩ",
|
| 2346 |
+
"quần lót",
|
| 2347 |
+
"smegma",
|
| 2348 |
+
"xì trum",
|
| 2349 |
+
"con trai",
|
| 2350 |
+
"spac",
|
| 2351 |
+
"spunk",
|
| 2352 |
+
"tinh hoàn",
|
| 2353 |
+
"ăn miếng trả miếng",
|
| 2354 |
+
"titt",
|
| 2355 |
+
"cỏ",
|
| 2356 |
+
"âm đạo",
|
| 2357 |
+
"viagra",
|
| 2358 |
+
"âm môn",
|
| 2359 |
+
"wang",
|
| 2360 |
+
"đã ngủ",
|
| 2361 |
+
"con điếm",
|
| 2362 |
+
"x đánh giá",
|
| 2363 |
+
"xxx",
|
| 2364 |
+
],
|
| 2365 |
+
"zh": english_badwords
|
| 2366 |
+
+ [
|
| 2367 |
+
"13.",
|
| 2368 |
+
"13点",
|
| 2369 |
+
"㞗",
|
| 2370 |
+
"三级片",
|
| 2371 |
+
"下三烂",
|
| 2372 |
+
"下贱",
|
| 2373 |
+
"个老子的",
|
| 2374 |
+
"九游",
|
| 2375 |
+
"乳",
|
| 2376 |
+
"乳交",
|
| 2377 |
+
"乳头",
|
| 2378 |
+
"乳房",
|
| 2379 |
+
"乳波臀浪",
|
| 2380 |
+
"交配",
|
| 2381 |
+
"仆街",
|
| 2382 |
+
"仆街",
|
| 2383 |
+
"他奶奶",
|
| 2384 |
+
"他奶奶的",
|
| 2385 |
+
"他奶娘的",
|
| 2386 |
+
"他妈",
|
| 2387 |
+
"他妈ㄉ王八蛋",
|
| 2388 |
+
"他妈地",
|
| 2389 |
+
"他妈的",
|
| 2390 |
+
"他娘",
|
| 2391 |
+
"他马的",
|
| 2392 |
+
"你个傻比",
|
| 2393 |
+
"你他马的",
|
| 2394 |
+
"你全家",
|
| 2395 |
+
"你奶奶的",
|
| 2396 |
+
"你她马的",
|
| 2397 |
+
"你妈",
|
| 2398 |
+
"你妈的",
|
| 2399 |
+
"你娘",
|
| 2400 |
+
"你娘卡好",
|
| 2401 |
+
"你娘咧",
|
| 2402 |
+
"你它妈的",
|
| 2403 |
+
"你它马的",
|
| 2404 |
+
"你是鸡",
|
| 2405 |
+
"你是鸭",
|
| 2406 |
+
"你老味",
|
| 2407 |
+
"你老母",
|
| 2408 |
+
"你老闆",
|
| 2409 |
+
"你马的",
|
| 2410 |
+
"做爱",
|
| 2411 |
+
"傻比",
|
| 2412 |
+
"傻逼",
|
| 2413 |
+
"册那",
|
| 2414 |
+
"冚家拎",
|
| 2415 |
+
"冚家鏟",
|
| 2416 |
+
"军妓",
|
| 2417 |
+
"几八",
|
| 2418 |
+
"几叭",
|
| 2419 |
+
"几巴",
|
| 2420 |
+
"几芭",
|
| 2421 |
+
"刚度",
|
| 2422 |
+
"刚瘪三",
|
| 2423 |
+
"包皮",
|
| 2424 |
+
"十三点",
|
| 2425 |
+
"卖B",
|
| 2426 |
+
"卖比",
|
| 2427 |
+
"卖淫",
|
| 2428 |
+
"卵",
|
| 2429 |
+
"卵子",
|
| 2430 |
+
"双峰微颤",
|
| 2431 |
+
"口交",
|
| 2432 |
+
"口肯",
|
| 2433 |
+
"叫床",
|
| 2434 |
+
"吃屎",
|
| 2435 |
+
"后庭",
|
| 2436 |
+
"吹箫",
|
| 2437 |
+
"咸家伶",
|
| 2438 |
+
"咸家鏟",
|
| 2439 |
+
"塞你公",
|
| 2440 |
+
"塞你娘",
|
| 2441 |
+
"塞你母",
|
| 2442 |
+
"塞你爸",
|
| 2443 |
+
"塞你老师",
|
| 2444 |
+
"塞你老母",
|
| 2445 |
+
"处女",
|
| 2446 |
+
"外阴",
|
| 2447 |
+
"大卵子",
|
| 2448 |
+
"大卵泡",
|
| 2449 |
+
"大鸡巴",
|
| 2450 |
+
"奶",
|
| 2451 |
+
"奶奶的熊",
|
| 2452 |
+
"奶子",
|
| 2453 |
+
"奸",
|
| 2454 |
+
"奸你",
|
| 2455 |
+
"她妈地",
|
| 2456 |
+
"她妈的",
|
| 2457 |
+
"她马的",
|
| 2458 |
+
"妈B",
|
| 2459 |
+
"妈个B",
|
| 2460 |
+
"妈个比",
|
| 2461 |
+
"妈个老比",
|
| 2462 |
+
"妈妈的",
|
| 2463 |
+
"妈比",
|
| 2464 |
+
"妈的",
|
| 2465 |
+
"妈的B",
|
| 2466 |
+
"妈逼",
|
| 2467 |
+
"妓",
|
| 2468 |
+
"妓女",
|
| 2469 |
+
"妓院",
|
| 2470 |
+
"妳她妈的",
|
| 2471 |
+
"妳妈的",
|
| 2472 |
+
"妳娘的",
|
| 2473 |
+
"妳老母的",
|
| 2474 |
+
"妳马的",
|
| 2475 |
+
"姘头",
|
| 2476 |
+
"姣西",
|
| 2477 |
+
"姦",
|
| 2478 |
+
"娘个比",
|
| 2479 |
+
"娘的",
|
| 2480 |
+
"���子",
|
| 2481 |
+
"婊子养的",
|
| 2482 |
+
"嫖娼",
|
| 2483 |
+
"嫖客",
|
| 2484 |
+
"它妈地",
|
| 2485 |
+
"它妈的",
|
| 2486 |
+
"密洞",
|
| 2487 |
+
"射你",
|
| 2488 |
+
"射精",
|
| 2489 |
+
"小乳头",
|
| 2490 |
+
"小卵子",
|
| 2491 |
+
"小卵泡",
|
| 2492 |
+
"小瘪三",
|
| 2493 |
+
"小肉粒",
|
| 2494 |
+
"小骚比",
|
| 2495 |
+
"小骚货",
|
| 2496 |
+
"小鸡巴",
|
| 2497 |
+
"小鸡鸡",
|
| 2498 |
+
"尻",
|
| 2499 |
+
"屁眼",
|
| 2500 |
+
"屁股",
|
| 2501 |
+
"屄",
|
| 2502 |
+
"屌",
|
| 2503 |
+
"屎忽",
|
| 2504 |
+
"巨乳",
|
| 2505 |
+
"干x娘",
|
| 2506 |
+
"干七八",
|
| 2507 |
+
"干你",
|
| 2508 |
+
"干你妈",
|
| 2509 |
+
"干你娘",
|
| 2510 |
+
"干你老母",
|
| 2511 |
+
"干你良",
|
| 2512 |
+
"干妳妈",
|
| 2513 |
+
"干妳娘",
|
| 2514 |
+
"干妳老母",
|
| 2515 |
+
"干妳马",
|
| 2516 |
+
"干您娘",
|
| 2517 |
+
"干机掰",
|
| 2518 |
+
"干死CS",
|
| 2519 |
+
"干死GM",
|
| 2520 |
+
"干死你",
|
| 2521 |
+
"干死客服",
|
| 2522 |
+
"幹",
|
| 2523 |
+
"强奸",
|
| 2524 |
+
"强奸你",
|
| 2525 |
+
"性",
|
| 2526 |
+
"性交",
|
| 2527 |
+
"性器",
|
| 2528 |
+
"性无能",
|
| 2529 |
+
"性爱",
|
| 2530 |
+
"情色",
|
| 2531 |
+
"想上你",
|
| 2532 |
+
"懆您妈",
|
| 2533 |
+
"懆您娘",
|
| 2534 |
+
"懒8",
|
| 2535 |
+
"懒八",
|
| 2536 |
+
"懒叫",
|
| 2537 |
+
"懒教",
|
| 2538 |
+
"成人",
|
| 2539 |
+
"我操你祖宗十八代",
|
| 2540 |
+
"扒光",
|
| 2541 |
+
"打炮",
|
| 2542 |
+
"打飞机",
|
| 2543 |
+
"抽插",
|
| 2544 |
+
"招妓",
|
| 2545 |
+
"插你",
|
| 2546 |
+
"插死你",
|
| 2547 |
+
"撒尿",
|
| 2548 |
+
"撚",
|
| 2549 |
+
"操你",
|
| 2550 |
+
"操你全家",
|
| 2551 |
+
"操你奶奶",
|
| 2552 |
+
"操你妈",
|
| 2553 |
+
"操你娘",
|
| 2554 |
+
"操你祖宗",
|
| 2555 |
+
"操你老妈",
|
| 2556 |
+
"操你老母",
|
| 2557 |
+
"操妳",
|
| 2558 |
+
"操妳全家",
|
| 2559 |
+
"操妳妈",
|
| 2560 |
+
"操妳娘",
|
| 2561 |
+
"操妳祖宗",
|
| 2562 |
+
"操机掰",
|
| 2563 |
+
"操比",
|
| 2564 |
+
"操逼",
|
| 2565 |
+
"放荡",
|
| 2566 |
+
"日他娘",
|
| 2567 |
+
"日你",
|
| 2568 |
+
"日你妈",
|
| 2569 |
+
"日你老娘",
|
| 2570 |
+
"日你老母",
|
| 2571 |
+
"日批",
|
| 2572 |
+
"月经",
|
| 2573 |
+
"机八",
|
| 2574 |
+
"机巴",
|
| 2575 |
+
"机机歪歪",
|
| 2576 |
+
"杂种",
|
| 2577 |
+
"柒",
|
| 2578 |
+
"浪叫",
|
| 2579 |
+
"淫",
|
| 2580 |
+
"淫乱",
|
| 2581 |
+
"淫妇",
|
| 2582 |
+
"淫棍",
|
| 2583 |
+
"淫水",
|
| 2584 |
+
"淫秽",
|
| 2585 |
+
"淫荡",
|
| 2586 |
+
"淫西",
|
| 2587 |
+
"湿透的内裤",
|
| 2588 |
+
"激情",
|
| 2589 |
+
"灨你娘",
|
| 2590 |
+
"烂货",
|
| 2591 |
+
"烂逼",
|
| 2592 |
+
"爛",
|
| 2593 |
+
"狗屁",
|
| 2594 |
+
"狗日",
|
| 2595 |
+
"狗狼养的",
|
| 2596 |
+
"玉杵",
|
| 2597 |
+
"王八蛋",
|
| 2598 |
+
"瓜娃子",
|
| 2599 |
+
"瓜婆娘",
|
| 2600 |
+
"瓜批",
|
| 2601 |
+
"瘪三",
|
| 2602 |
+
"白烂",
|
| 2603 |
+
"白痴",
|
| 2604 |
+
"白癡",
|
| 2605 |
+
"硬膠",
|
| 2606 |
+
"祖宗",
|
| 2607 |
+
"私服",
|
| 2608 |
+
"笨實",
|
| 2609 |
+
"笨蛋",
|
| 2610 |
+
"粉腸",
|
| 2611 |
+
"精子",
|
| 2612 |
+
"老二",
|
| 2613 |
+
"老味",
|
| 2614 |
+
"老母",
|
| 2615 |
+
"老瘪三",
|
| 2616 |
+
"老骚比",
|
| 2617 |
+
"老骚货",
|
| 2618 |
+
"肉壁",
|
| 2619 |
+
"肉棍子",
|
| 2620 |
+
"肉棒",
|
| 2621 |
+
"肉缝",
|
| 2622 |
+
"肏",
|
| 2623 |
+
"肛交",
|
| 2624 |
+
"肥西",
|
| 2625 |
+
"色情",
|
| 2626 |
+
"花柳",
|
| 2627 |
+
"荡妇",
|
| 2628 |
+
"賤",
|
| 2629 |
+
"贝肉",
|
| 2630 |
+
"贱B",
|
| 2631 |
+
"贱人",
|
| 2632 |
+
"贱货",
|
| 2633 |
+
"贼你妈",
|
| 2634 |
+
"赛你老母",
|
| 2635 |
+
"赛妳阿母",
|
| 2636 |
+
"赣您娘",
|
| 2637 |
+
"躝癱",
|
| 2638 |
+
"轮奸",
|
| 2639 |
+
"迷药",
|
| 2640 |
+
"逼",
|
| 2641 |
+
"逼样",
|
| 2642 |
+
"野鸡",
|
| 2643 |
+
"閪",
|
| 2644 |
+
"阳具",
|
| 2645 |
+
"阳萎",
|
| 2646 |
+
"阴唇",
|
| 2647 |
+
"阴户",
|
| 2648 |
+
"阴核",
|
| 2649 |
+
"阴毛",
|
| 2650 |
+
"阴茎",
|
| 2651 |
+
"阴道",
|
| 2652 |
+
"阴部",
|
| 2653 |
+
"陰莖",
|
| 2654 |
+
"雞巴",
|
| 2655 |
+
"靠北",
|
| 2656 |
+
"靠母",
|
| 2657 |
+
"靠爸",
|
| 2658 |
+
"靠背",
|
| 2659 |
+
"靠腰",
|
| 2660 |
+
"驶你公",
|
| 2661 |
+
"驶你娘",
|
| 2662 |
+
"驶你母",
|
| 2663 |
+
"驶你爸",
|
| 2664 |
+
"驶你老师",
|
| 2665 |
+
"驶你老母",
|
| 2666 |
+
"骚比",
|
| 2667 |
+
"骚货",
|
| 2668 |
+
"骚逼",
|
| 2669 |
+
"鬼公",
|
| 2670 |
+
"鳩",
|
| 2671 |
+
"鸡8",
|
| 2672 |
+
"鸡八",
|
| 2673 |
+
"鸡叭",
|
| 2674 |
+
"鸡吧",
|
| 2675 |
+
"鸡奸",
|
| 2676 |
+
"鸡巴",
|
| 2677 |
+
"鸡芭",
|
| 2678 |
+
"鸡鸡",
|
| 2679 |
+
"龟儿子",
|
| 2680 |
+
"龟头",
|
| 2681 |
+
],
|
| 2682 |
+
}
|
en.arpa.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e90c9b25af01dcaa2667ed45d012d891269760fc6eccfe8dbbd161eb20e01d7d
|
| 3 |
+
size 4403509656
|
en.sp.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:262c0b0bd4ebc592e439453bc7e006d0ed12d1914e206a1fb8c7fba091f52c4d
|
| 3 |
+
size 1389058
|
filtering.py
ADDED
|
@@ -0,0 +1,879 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
|
| 3 |
+
import numpy as np
|
| 4 |
+
|
| 5 |
+
import fasttext
|
| 6 |
+
|
| 7 |
+
import sentencepiece
|
| 8 |
+
import kenlm
|
| 9 |
+
|
| 10 |
+
import pathlib
|
| 11 |
+
|
| 12 |
+
from languages_id import langs_id
|
| 13 |
+
from parameters_filtering import parameters_filtering
|
| 14 |
+
from normalization import normalization
|
| 15 |
+
from stopwords import stopwords
|
| 16 |
+
from badwords import badwords
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
class LoadParameters:
|
| 20 |
+
@staticmethod
|
| 21 |
+
def load_parameters(lang_dataset_id):
|
| 22 |
+
if lang_dataset_id in parameters_filtering:
|
| 23 |
+
param = parameters_filtering[lang_dataset_id]
|
| 24 |
+
else:
|
| 25 |
+
param = parameters_filtering["default"]
|
| 26 |
+
return param
|
| 27 |
+
|
| 28 |
+
@staticmethod
|
| 29 |
+
def load_stopwords(lang_dataset_id):
|
| 30 |
+
stopwords_lang_id = langs_id.loc[
|
| 31 |
+
langs_id["dataset_id"] == lang_dataset_id, "stopwords_id"
|
| 32 |
+
].iloc[0]
|
| 33 |
+
if stopwords_lang_id:
|
| 34 |
+
stopwords_lang = set(stopwords[stopwords_lang_id])
|
| 35 |
+
else:
|
| 36 |
+
stopwords_lang = None
|
| 37 |
+
return stopwords_lang
|
| 38 |
+
|
| 39 |
+
@staticmethod
|
| 40 |
+
def load_badwords(lang_dataset_id):
|
| 41 |
+
badwords_lang_id = langs_id.loc[
|
| 42 |
+
langs_id["dataset_id"] == lang_dataset_id, "badwords_id"
|
| 43 |
+
].iloc[0]
|
| 44 |
+
if badwords_lang_id:
|
| 45 |
+
badwords_lang = set(badwords[badwords_lang_id])
|
| 46 |
+
else:
|
| 47 |
+
badwords_lang = None
|
| 48 |
+
return badwords_lang
|
| 49 |
+
|
| 50 |
+
@staticmethod
|
| 51 |
+
def load_model_lang_id(lang_dataset_id, path_fasttext_model):
|
| 52 |
+
fasttext_lang_id = langs_id.loc[
|
| 53 |
+
langs_id["dataset_id"] == lang_dataset_id, "fasttext_id"
|
| 54 |
+
].iloc[0]
|
| 55 |
+
if fasttext_lang_id:
|
| 56 |
+
model_lang_id = fasttext.load_model(path_fasttext_model)
|
| 57 |
+
else:
|
| 58 |
+
model_lang_id = None
|
| 59 |
+
return model_lang_id
|
| 60 |
+
|
| 61 |
+
@staticmethod
|
| 62 |
+
def load_sentencepiece_model(lang_dataset_id, path_sentencepiece_model):
|
| 63 |
+
sentencepiece_lang_id = langs_id.loc[
|
| 64 |
+
langs_id["dataset_id"] == lang_dataset_id, "sentencepiece_id"
|
| 65 |
+
].iloc[0]
|
| 66 |
+
if sentencepiece_lang_id:
|
| 67 |
+
sentencepiece_model = sentencepiece.SentencePieceProcessor()
|
| 68 |
+
sentencepiece_model.load(path_sentencepiece_model)
|
| 69 |
+
else:
|
| 70 |
+
sentencepiece_model = None
|
| 71 |
+
return sentencepiece_model
|
| 72 |
+
|
| 73 |
+
@staticmethod
|
| 74 |
+
def load_kenlm_model(lang_dataset_id, path_kenlm_model):
|
| 75 |
+
kenlm_lang_id = langs_id.loc[
|
| 76 |
+
langs_id["dataset_id"] == lang_dataset_id, "kenlm_id"
|
| 77 |
+
].iloc[0]
|
| 78 |
+
if kenlm_lang_id:
|
| 79 |
+
kenlm_model = kenlm.Model(path_kenlm_model)
|
| 80 |
+
else:
|
| 81 |
+
kenlm_model = None
|
| 82 |
+
return kenlm_model
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
class ModifyingDocuments:
|
| 86 |
+
@staticmethod
|
| 87 |
+
def remove_empty_el_from_list(list_):
|
| 88 |
+
return [el for el in list_ if el]
|
| 89 |
+
|
| 90 |
+
@staticmethod
|
| 91 |
+
def remove_non_printing_characters(document, non_printing_characters_re):
|
| 92 |
+
return non_printing_characters_re.sub("", document)
|
| 93 |
+
|
| 94 |
+
@staticmethod
|
| 95 |
+
def uniform_whitespace(
|
| 96 |
+
document,
|
| 97 |
+
whitespace=[
|
| 98 |
+
" ",
|
| 99 |
+
" ",
|
| 100 |
+
" ",
|
| 101 |
+
" ",
|
| 102 |
+
" ",
|
| 103 |
+
" ",
|
| 104 |
+
" ",
|
| 105 |
+
" ",
|
| 106 |
+
" ",
|
| 107 |
+
" ",
|
| 108 |
+
"",
|
| 109 |
+
"",
|
| 110 |
+
],
|
| 111 |
+
):
|
| 112 |
+
"""There are different whitespace characters."""
|
| 113 |
+
whitespace = set(whitespace)
|
| 114 |
+
document = "".join(
|
| 115 |
+
[char if char not in whitespace else " " for char in document]
|
| 116 |
+
)
|
| 117 |
+
return document
|
| 118 |
+
|
| 119 |
+
@staticmethod
|
| 120 |
+
def replace_digits_with_zeros(document, digits_re):
|
| 121 |
+
return digits_re.sub("0", document)
|
| 122 |
+
|
| 123 |
+
@staticmethod
|
| 124 |
+
def replace_unicode_punctuation(document, unicode_punctuation):
|
| 125 |
+
return "".join(unicode_punctuation.get(c, c) for c in document)
|
| 126 |
+
|
| 127 |
+
@staticmethod
|
| 128 |
+
def normalization(
|
| 129 |
+
document,
|
| 130 |
+
remove_non_printing_characters,
|
| 131 |
+
strip,
|
| 132 |
+
lower_case,
|
| 133 |
+
uniform_whitespace,
|
| 134 |
+
replace_digits_with_zeros,
|
| 135 |
+
replace_unicode_punctuation,
|
| 136 |
+
non_printing_characters_re=normalization["non_printing_characters_re"],
|
| 137 |
+
digits_re=normalization["digits_re"],
|
| 138 |
+
unicode_punctuation=normalization["unicode_punctuation"],
|
| 139 |
+
):
|
| 140 |
+
if remove_non_printing_characters:
|
| 141 |
+
document = ModifyingDocuments.remove_non_printing_characters(
|
| 142 |
+
document, non_printing_characters_re
|
| 143 |
+
)
|
| 144 |
+
if strip:
|
| 145 |
+
document = document.strip()
|
| 146 |
+
if not document:
|
| 147 |
+
return document
|
| 148 |
+
if lower_case:
|
| 149 |
+
document = document.lower()
|
| 150 |
+
if uniform_whitespace:
|
| 151 |
+
document = ModifyingDocuments.uniform_whitespace(document)
|
| 152 |
+
if replace_digits_with_zeros:
|
| 153 |
+
document = ModifyingDocuments.replace_digits_with_zeros(document, digits_re)
|
| 154 |
+
if replace_unicode_punctuation:
|
| 155 |
+
document = ModifyingDocuments.replace_unicode_punctuation(
|
| 156 |
+
document, unicode_punctuation
|
| 157 |
+
)
|
| 158 |
+
return document
|
| 159 |
+
|
| 160 |
+
@staticmethod
|
| 161 |
+
def tokenization(document, sentencepiece_model, join_on_whitespace):
|
| 162 |
+
document_tokenized = sentencepiece_model.encode_as_pieces(document)
|
| 163 |
+
if join_on_whitespace:
|
| 164 |
+
document_tokenized = " ".join(document_tokenized)
|
| 165 |
+
return document_tokenized
|
| 166 |
+
|
| 167 |
+
@staticmethod
|
| 168 |
+
def split_on_whitespace(
|
| 169 |
+
document,
|
| 170 |
+
new_line=False,
|
| 171 |
+
tab=False,
|
| 172 |
+
):
|
| 173 |
+
"""This method also removes concatenated spaces."""
|
| 174 |
+
sep = [" "] + new_line * ["\n"] + tab * ["\t"]
|
| 175 |
+
sep = "|".join(sep)
|
| 176 |
+
split_document = re.split(sep, document)
|
| 177 |
+
split_document = ModifyingDocuments.remove_empty_el_from_list(split_document)
|
| 178 |
+
return split_document
|
| 179 |
+
|
| 180 |
+
@staticmethod
|
| 181 |
+
def strip(document, strip_characters):
|
| 182 |
+
"""Way faster than document.strip(strip_characters)
|
| 183 |
+
since strip_characters is now a set instead of a str,
|
| 184 |
+
and it contains a lot of elements (all the emojis)."""
|
| 185 |
+
if not document:
|
| 186 |
+
return document
|
| 187 |
+
beg_ind = 0
|
| 188 |
+
end_ind = len(document)
|
| 189 |
+
for i in range(len(document)):
|
| 190 |
+
if document[i] in strip_characters:
|
| 191 |
+
beg_ind += 1
|
| 192 |
+
else:
|
| 193 |
+
break
|
| 194 |
+
for i in range(1, len(document) + 1):
|
| 195 |
+
if document[-i] in strip_characters:
|
| 196 |
+
end_ind -= 1
|
| 197 |
+
else:
|
| 198 |
+
break
|
| 199 |
+
document_stripped = document[beg_ind:end_ind]
|
| 200 |
+
return document_stripped
|
| 201 |
+
|
| 202 |
+
@staticmethod
|
| 203 |
+
def get_words_from_document(
|
| 204 |
+
document, sentencepiece_model_tok, lower_case, strip_characters
|
| 205 |
+
):
|
| 206 |
+
"""Get words from a document. Non reversible since the document
|
| 207 |
+
is split on multiple characters, words are stripped of
|
| 208 |
+
special characters and characters are converted to lower case.
|
| 209 |
+
Useful to compute ratios, like the stopwords ratio."""
|
| 210 |
+
if sentencepiece_model_tok:
|
| 211 |
+
document_normalized = ModifyingDocuments.normalization(
|
| 212 |
+
document=document,
|
| 213 |
+
remove_non_printing_characters=True,
|
| 214 |
+
strip=True,
|
| 215 |
+
lower_case=True,
|
| 216 |
+
uniform_whitespace=True,
|
| 217 |
+
replace_digits_with_zeros=True,
|
| 218 |
+
replace_unicode_punctuation=True,
|
| 219 |
+
)
|
| 220 |
+
words = ModifyingDocuments.tokenization(
|
| 221 |
+
document_normalized, sentencepiece_model_tok, join_on_whitespace=False
|
| 222 |
+
)
|
| 223 |
+
else:
|
| 224 |
+
words = ModifyingDocuments.split_on_whitespace(
|
| 225 |
+
document, new_line=True, tab=True
|
| 226 |
+
)
|
| 227 |
+
if lower_case:
|
| 228 |
+
words = [word.lower() for word in words]
|
| 229 |
+
if strip_characters:
|
| 230 |
+
words = [ModifyingDocuments.strip(word, strip_characters) for word in words]
|
| 231 |
+
words = ModifyingDocuments.remove_empty_el_from_list(words)
|
| 232 |
+
return words
|
| 233 |
+
|
| 234 |
+
@staticmethod
|
| 235 |
+
def words_augmentation(words, group_size, join_char):
|
| 236 |
+
"""Augment words, especially for Chinese (without a space between words)
|
| 237 |
+
and Vietnamese (with a space between syllables)."""
|
| 238 |
+
augmentation = [
|
| 239 |
+
join_char.join(words[i : i + group_size])
|
| 240 |
+
for i in range(len(words) - group_size + 1)
|
| 241 |
+
]
|
| 242 |
+
return augmentation
|
| 243 |
+
|
| 244 |
+
@staticmethod
|
| 245 |
+
def split_on_newline_tab_whitespace(document):
|
| 246 |
+
"""First split on "\n", then on "\t", then on " "."""
|
| 247 |
+
sentences = document.split("\n")
|
| 248 |
+
sentences = [sentence.split("\t") for sentence in sentences]
|
| 249 |
+
sentences = [
|
| 250 |
+
[
|
| 251 |
+
ModifyingDocuments.split_on_whitespace(subsentence)
|
| 252 |
+
for subsentence in sentence
|
| 253 |
+
]
|
| 254 |
+
for sentence in sentences
|
| 255 |
+
]
|
| 256 |
+
return sentences
|
| 257 |
+
|
| 258 |
+
@staticmethod
|
| 259 |
+
def merge_on_whitespace_tab_newline(sentences):
|
| 260 |
+
"""Invert the method split_on_newline_tab_whitespace.
|
| 261 |
+
Removes concatenated separators."""
|
| 262 |
+
sentences = [
|
| 263 |
+
[" ".join(subsentence) for subsentence in sentence if subsentence]
|
| 264 |
+
for sentence in sentences
|
| 265 |
+
]
|
| 266 |
+
sentences = ["\t".join(sentence) for sentence in sentences if sentence]
|
| 267 |
+
if not sentences:
|
| 268 |
+
return ""
|
| 269 |
+
document = "\n".join(sentences)
|
| 270 |
+
return document
|
| 271 |
+
|
| 272 |
+
@staticmethod
|
| 273 |
+
def should_keep_word_with_incorrect_substrings(
|
| 274 |
+
word, strip_characters, incorrect_word_substrings
|
| 275 |
+
):
|
| 276 |
+
word = ModifyingDocuments.strip(word, strip_characters)
|
| 277 |
+
should_keep = all(
|
| 278 |
+
[(i_substr not in word) for i_substr in incorrect_word_substrings]
|
| 279 |
+
)
|
| 280 |
+
return should_keep
|
| 281 |
+
|
| 282 |
+
@staticmethod
|
| 283 |
+
def remove_words_with_incorrect_substrings(
|
| 284 |
+
document,
|
| 285 |
+
strip_characters,
|
| 286 |
+
incorrect_word_substrings,
|
| 287 |
+
):
|
| 288 |
+
sentences = ModifyingDocuments.split_on_newline_tab_whitespace(document)
|
| 289 |
+
sentences = [
|
| 290 |
+
[
|
| 291 |
+
[
|
| 292 |
+
word
|
| 293 |
+
for word in subsentence
|
| 294 |
+
if ModifyingDocuments.should_keep_word_with_incorrect_substrings(
|
| 295 |
+
word, strip_characters, incorrect_word_substrings
|
| 296 |
+
)
|
| 297 |
+
]
|
| 298 |
+
for subsentence in sentence
|
| 299 |
+
]
|
| 300 |
+
for sentence in sentences
|
| 301 |
+
]
|
| 302 |
+
document = ModifyingDocuments.merge_on_whitespace_tab_newline(sentences)
|
| 303 |
+
return document
|
| 304 |
+
|
| 305 |
+
@staticmethod
|
| 306 |
+
def should_keep_long_word(word, strip_characters, length_word_max_cutoff):
|
| 307 |
+
"""If the word is too long but it contains only one
|
| 308 |
+
special character, it might be a concatenation of one word,
|
| 309 |
+
a punctuation, and another word, with no space between them.
|
| 310 |
+
In this case, we give the word a pass."""
|
| 311 |
+
if len(word) <= length_word_max_cutoff:
|
| 312 |
+
return True
|
| 313 |
+
word = ModifyingDocuments.strip(word, strip_characters)
|
| 314 |
+
if not word: # The word consisted only of strip characters
|
| 315 |
+
return False
|
| 316 |
+
if len(word) <= length_word_max_cutoff:
|
| 317 |
+
return True
|
| 318 |
+
return False
|
| 319 |
+
|
| 320 |
+
def remove_long_words(
|
| 321 |
+
document,
|
| 322 |
+
strip_characters,
|
| 323 |
+
length_word_max_cutoff,
|
| 324 |
+
):
|
| 325 |
+
sentences = ModifyingDocuments.split_on_newline_tab_whitespace(document)
|
| 326 |
+
sentences = [
|
| 327 |
+
[
|
| 328 |
+
[
|
| 329 |
+
word
|
| 330 |
+
for word in subsentence
|
| 331 |
+
if ModifyingDocuments.should_keep_long_word(
|
| 332 |
+
word,
|
| 333 |
+
strip_characters,
|
| 334 |
+
length_word_max_cutoff,
|
| 335 |
+
)
|
| 336 |
+
]
|
| 337 |
+
for subsentence in sentence
|
| 338 |
+
]
|
| 339 |
+
for sentence in sentences
|
| 340 |
+
]
|
| 341 |
+
document = ModifyingDocuments.merge_on_whitespace_tab_newline(sentences)
|
| 342 |
+
return document
|
| 343 |
+
|
| 344 |
+
@staticmethod
|
| 345 |
+
def modifying_documents(
|
| 346 |
+
document,
|
| 347 |
+
cond_uniform_whitespace,
|
| 348 |
+
cond_replace_unicode_punctuation,
|
| 349 |
+
cond_remove_words_with_incorrect_substrings,
|
| 350 |
+
strip_characters,
|
| 351 |
+
incorrect_word_substrings,
|
| 352 |
+
cond_remove_long_words,
|
| 353 |
+
length_word_max_cutoff,
|
| 354 |
+
):
|
| 355 |
+
document = ModifyingDocuments.normalization(
|
| 356 |
+
document=document,
|
| 357 |
+
remove_non_printing_characters=False,
|
| 358 |
+
strip=True,
|
| 359 |
+
lower_case=False,
|
| 360 |
+
uniform_whitespace=cond_uniform_whitespace,
|
| 361 |
+
replace_digits_with_zeros=False,
|
| 362 |
+
replace_unicode_punctuation=cond_replace_unicode_punctuation,
|
| 363 |
+
)
|
| 364 |
+
if cond_remove_words_with_incorrect_substrings:
|
| 365 |
+
document = ModifyingDocuments.remove_words_with_incorrect_substrings(
|
| 366 |
+
document,
|
| 367 |
+
strip_characters,
|
| 368 |
+
incorrect_word_substrings,
|
| 369 |
+
)
|
| 370 |
+
if cond_remove_long_words:
|
| 371 |
+
document = ModifyingDocuments.remove_long_words(
|
| 372 |
+
document,
|
| 373 |
+
strip_characters,
|
| 374 |
+
length_word_max_cutoff,
|
| 375 |
+
)
|
| 376 |
+
return document
|
| 377 |
+
|
| 378 |
+
|
| 379 |
+
class FunctionDatasetModifyingDocuments:
|
| 380 |
+
def __init__(self, lang_dataset_id):
|
| 381 |
+
self.lang_dataset_id = lang_dataset_id
|
| 382 |
+
self.param = LoadParameters.load_parameters(lang_dataset_id)
|
| 383 |
+
|
| 384 |
+
def __call__(self, example):
|
| 385 |
+
example["text"] = ModifyingDocuments.modifying_documents(
|
| 386 |
+
document=example["text"],
|
| 387 |
+
cond_uniform_whitespace=self.param["cond_uniform_whitespace"],
|
| 388 |
+
cond_replace_unicode_punctuation=self.param[
|
| 389 |
+
"cond_replace_unicode_punctuation"
|
| 390 |
+
],
|
| 391 |
+
cond_remove_words_with_incorrect_substrings=self.param[
|
| 392 |
+
"cond_remove_words_with_incorrect_substrings"
|
| 393 |
+
],
|
| 394 |
+
strip_characters=self.param["strip_characters"],
|
| 395 |
+
incorrect_word_substrings=self.param["incorrect_word_substrings"],
|
| 396 |
+
cond_remove_long_words=self.param["cond_remove_long_words"],
|
| 397 |
+
length_word_max_cutoff=self.param["length_word_max_cutoff"],
|
| 398 |
+
)
|
| 399 |
+
return example
|
| 400 |
+
|
| 401 |
+
def __reduce__(self):
|
| 402 |
+
return (self.__class__, (self.lang_dataset_id,))
|
| 403 |
+
|
| 404 |
+
|
| 405 |
+
class Filtering:
|
| 406 |
+
@staticmethod
|
| 407 |
+
def check_number_words(
|
| 408 |
+
document,
|
| 409 |
+
sentencepiece_model_tok,
|
| 410 |
+
strip_characters,
|
| 411 |
+
number_words_min_cutoff,
|
| 412 |
+
number_words_max_cutoff,
|
| 413 |
+
):
|
| 414 |
+
words = ModifyingDocuments.get_words_from_document(
|
| 415 |
+
document,
|
| 416 |
+
sentencepiece_model_tok,
|
| 417 |
+
lower_case=False,
|
| 418 |
+
strip_characters=strip_characters,
|
| 419 |
+
)
|
| 420 |
+
cond = (len(words) >= number_words_min_cutoff) and (
|
| 421 |
+
len(words) <= number_words_max_cutoff
|
| 422 |
+
)
|
| 423 |
+
return cond
|
| 424 |
+
|
| 425 |
+
@staticmethod
|
| 426 |
+
def compute_repetitions_ratio(document, repetitions_length):
|
| 427 |
+
def get_freq_ngrams(document, n):
|
| 428 |
+
ngrams = [document[i : i + n] for i in range(len(document) - n + 1)]
|
| 429 |
+
freq_ngrams = {}
|
| 430 |
+
for ngram in ngrams:
|
| 431 |
+
freq_ngrams[ngram] = freq_ngrams.get(ngram, 0) + 1
|
| 432 |
+
return freq_ngrams
|
| 433 |
+
|
| 434 |
+
freq_ngrams = get_freq_ngrams(document, repetitions_length)
|
| 435 |
+
if len(freq_ngrams) == 0:
|
| 436 |
+
return 0
|
| 437 |
+
freq_ngrams = list(freq_ngrams.values())
|
| 438 |
+
freq_ngrams = sorted(freq_ngrams, reverse=True)
|
| 439 |
+
num_rep_ngrams = int(np.sqrt(len(freq_ngrams)))
|
| 440 |
+
repetitions_ratio = sum(freq_ngrams[:num_rep_ngrams]) / sum(freq_ngrams)
|
| 441 |
+
return repetitions_ratio
|
| 442 |
+
|
| 443 |
+
@staticmethod
|
| 444 |
+
def check_repetitions_removal(
|
| 445 |
+
document,
|
| 446 |
+
repetitions_length,
|
| 447 |
+
repetitions_max_cutoff,
|
| 448 |
+
):
|
| 449 |
+
repetitions_ratio = Filtering.compute_repetitions_ratio(
|
| 450 |
+
document, repetitions_length
|
| 451 |
+
)
|
| 452 |
+
cond = repetitions_ratio <= repetitions_max_cutoff
|
| 453 |
+
return cond
|
| 454 |
+
|
| 455 |
+
@staticmethod
|
| 456 |
+
def compute_special_characters_ratio(document, special_characters):
|
| 457 |
+
special_characters_ratio = len(
|
| 458 |
+
[char for char in document if char in special_characters]
|
| 459 |
+
) / len(document)
|
| 460 |
+
return special_characters_ratio
|
| 461 |
+
|
| 462 |
+
@staticmethod
|
| 463 |
+
def check_special_characters(
|
| 464 |
+
document,
|
| 465 |
+
special_characters,
|
| 466 |
+
special_characters_max_cutoff,
|
| 467 |
+
):
|
| 468 |
+
special_characters_ratio = Filtering.compute_special_characters_ratio(
|
| 469 |
+
document, special_characters
|
| 470 |
+
)
|
| 471 |
+
cond = special_characters_ratio <= special_characters_max_cutoff
|
| 472 |
+
return cond
|
| 473 |
+
|
| 474 |
+
@staticmethod
|
| 475 |
+
def compute_stopwords_ratio(
|
| 476 |
+
document,
|
| 477 |
+
sentencepiece_model_tok,
|
| 478 |
+
strip_characters,
|
| 479 |
+
cond_words_augmentation,
|
| 480 |
+
words_augmentation_group_sizes,
|
| 481 |
+
words_augmentation_join_char,
|
| 482 |
+
stopwords,
|
| 483 |
+
):
|
| 484 |
+
words = ModifyingDocuments.get_words_from_document(
|
| 485 |
+
document,
|
| 486 |
+
sentencepiece_model_tok,
|
| 487 |
+
lower_case=True,
|
| 488 |
+
strip_characters=strip_characters,
|
| 489 |
+
)
|
| 490 |
+
if not words:
|
| 491 |
+
return 0
|
| 492 |
+
augmentation = []
|
| 493 |
+
if cond_words_augmentation:
|
| 494 |
+
augmentation = [
|
| 495 |
+
ModifyingDocuments.words_augmentation(
|
| 496 |
+
words, group_size, words_augmentation_join_char
|
| 497 |
+
)
|
| 498 |
+
for group_size in words_augmentation_group_sizes
|
| 499 |
+
]
|
| 500 |
+
augmentation = [word for augm in augmentation for word in augm]
|
| 501 |
+
stopwords_ratio = len(
|
| 502 |
+
[word for word in words + augmentation if word in stopwords]
|
| 503 |
+
) / len(words)
|
| 504 |
+
if stopwords_ratio > 1.0:
|
| 505 |
+
stopwords_ratio = 1.0
|
| 506 |
+
return stopwords_ratio
|
| 507 |
+
|
| 508 |
+
@staticmethod
|
| 509 |
+
def check_stopwords(
|
| 510 |
+
document,
|
| 511 |
+
sentencepiece_model_tok,
|
| 512 |
+
strip_characters,
|
| 513 |
+
cond_words_augmentation,
|
| 514 |
+
words_augmentation_group_sizes,
|
| 515 |
+
words_augmentation_join_char,
|
| 516 |
+
stopwords,
|
| 517 |
+
stopwords_min_cutoff,
|
| 518 |
+
):
|
| 519 |
+
cond = True
|
| 520 |
+
if stopwords:
|
| 521 |
+
stopwords_ratio = Filtering.compute_stopwords_ratio(
|
| 522 |
+
document,
|
| 523 |
+
sentencepiece_model_tok,
|
| 524 |
+
strip_characters,
|
| 525 |
+
cond_words_augmentation,
|
| 526 |
+
words_augmentation_group_sizes,
|
| 527 |
+
words_augmentation_join_char,
|
| 528 |
+
stopwords,
|
| 529 |
+
)
|
| 530 |
+
cond = stopwords_ratio >= stopwords_min_cutoff
|
| 531 |
+
return cond
|
| 532 |
+
|
| 533 |
+
@staticmethod
|
| 534 |
+
def compute_badwords_ratio(
|
| 535 |
+
document,
|
| 536 |
+
sentencepiece_model_tok,
|
| 537 |
+
strip_characters,
|
| 538 |
+
cond_words_augmentation,
|
| 539 |
+
words_augmentation_group_sizes,
|
| 540 |
+
words_augmentation_join_char,
|
| 541 |
+
badwords,
|
| 542 |
+
):
|
| 543 |
+
words = ModifyingDocuments.get_words_from_document(
|
| 544 |
+
document,
|
| 545 |
+
sentencepiece_model_tok,
|
| 546 |
+
lower_case=True,
|
| 547 |
+
strip_characters=strip_characters,
|
| 548 |
+
)
|
| 549 |
+
if not words:
|
| 550 |
+
return 0
|
| 551 |
+
augmentation = []
|
| 552 |
+
if cond_words_augmentation:
|
| 553 |
+
augmentation = [
|
| 554 |
+
ModifyingDocuments.words_augmentation(
|
| 555 |
+
words, group_size, words_augmentation_join_char
|
| 556 |
+
)
|
| 557 |
+
for group_size in words_augmentation_group_sizes
|
| 558 |
+
]
|
| 559 |
+
augmentation = [word for augm in augmentation for word in augm]
|
| 560 |
+
badwords_ratio = len(
|
| 561 |
+
[word for word in words + augmentation if word in badwords]
|
| 562 |
+
) / len(words)
|
| 563 |
+
if badwords_ratio > 1.0:
|
| 564 |
+
badwords_ratio = 1.0
|
| 565 |
+
for word in augmentation:
|
| 566 |
+
if word in badwords:
|
| 567 |
+
print(word)
|
| 568 |
+
return badwords_ratio
|
| 569 |
+
|
| 570 |
+
@staticmethod
|
| 571 |
+
def check_badwords(
|
| 572 |
+
document,
|
| 573 |
+
sentencepiece_model_tok,
|
| 574 |
+
strip_characters,
|
| 575 |
+
cond_words_augmentation,
|
| 576 |
+
words_augmentation_group_sizes,
|
| 577 |
+
words_augmentation_join_char,
|
| 578 |
+
badwords,
|
| 579 |
+
badwords_max_cutoff,
|
| 580 |
+
):
|
| 581 |
+
cond = True
|
| 582 |
+
if badwords:
|
| 583 |
+
badwords_ratio = Filtering.compute_badwords_ratio(
|
| 584 |
+
document,
|
| 585 |
+
sentencepiece_model_tok,
|
| 586 |
+
strip_characters,
|
| 587 |
+
cond_words_augmentation,
|
| 588 |
+
words_augmentation_group_sizes,
|
| 589 |
+
words_augmentation_join_char,
|
| 590 |
+
badwords,
|
| 591 |
+
)
|
| 592 |
+
cond = badwords_ratio <= badwords_max_cutoff
|
| 593 |
+
return cond
|
| 594 |
+
|
| 595 |
+
@staticmethod
|
| 596 |
+
def compute_lang_id_pred_score(document, model_lang_id):
|
| 597 |
+
document = document.lower().replace("\n", " ")
|
| 598 |
+
pred = model_lang_id.predict(document)
|
| 599 |
+
lang_pred_fasttext_id = pred[0][0].replace("__label__", "")
|
| 600 |
+
score_pred = pred[1][0]
|
| 601 |
+
lang_pred_dataset_id = langs_id.loc[
|
| 602 |
+
langs_id["fasttext_id"] == lang_pred_fasttext_id, "dataset_id"
|
| 603 |
+
]
|
| 604 |
+
if len(lang_pred_dataset_id) > 0:
|
| 605 |
+
lang_pred_dataset_id = lang_pred_dataset_id.iloc[0]
|
| 606 |
+
else:
|
| 607 |
+
lang_pred_dataset_id = "unknown"
|
| 608 |
+
return lang_pred_dataset_id, score_pred
|
| 609 |
+
|
| 610 |
+
@staticmethod
|
| 611 |
+
def check_lang_id(
|
| 612 |
+
document,
|
| 613 |
+
lang_dataset_id,
|
| 614 |
+
model_lang_id,
|
| 615 |
+
lang_id_min_cutoff,
|
| 616 |
+
):
|
| 617 |
+
cond = True
|
| 618 |
+
if model_lang_id:
|
| 619 |
+
lang_pred_dataset_id, score_pred = Filtering.compute_lang_id_pred_score(
|
| 620 |
+
document, model_lang_id
|
| 621 |
+
)
|
| 622 |
+
cond = (lang_pred_dataset_id == lang_dataset_id) and (
|
| 623 |
+
score_pred >= lang_id_min_cutoff
|
| 624 |
+
)
|
| 625 |
+
return cond
|
| 626 |
+
|
| 627 |
+
@staticmethod
|
| 628 |
+
def compute_perplexity_score(document, sentencepiece_model, kenlm_model):
|
| 629 |
+
document = ModifyingDocuments.normalization(
|
| 630 |
+
document=document,
|
| 631 |
+
remove_non_printing_characters=True,
|
| 632 |
+
strip=True,
|
| 633 |
+
lower_case=True,
|
| 634 |
+
uniform_whitespace=True,
|
| 635 |
+
replace_digits_with_zeros=True,
|
| 636 |
+
replace_unicode_punctuation=True,
|
| 637 |
+
)
|
| 638 |
+
document = ModifyingDocuments.tokenization(
|
| 639 |
+
document, sentencepiece_model, join_on_whitespace=True
|
| 640 |
+
)
|
| 641 |
+
doc_log_score, doc_length = 0, 0
|
| 642 |
+
for line in document.split("\n"):
|
| 643 |
+
log_score = kenlm_model.score(line)
|
| 644 |
+
length = len(line.split()) + 1
|
| 645 |
+
doc_log_score += log_score
|
| 646 |
+
doc_length += length
|
| 647 |
+
pp_score = 10.0 ** (-doc_log_score / doc_length)
|
| 648 |
+
pp_score = round(pp_score, 1)
|
| 649 |
+
return pp_score
|
| 650 |
+
|
| 651 |
+
@staticmethod
|
| 652 |
+
def check_perplexity(
|
| 653 |
+
document,
|
| 654 |
+
sentencepiece_model,
|
| 655 |
+
kenlm_model,
|
| 656 |
+
perplexity_max_cutoff,
|
| 657 |
+
):
|
| 658 |
+
cond = True
|
| 659 |
+
if kenlm_model:
|
| 660 |
+
score = Filtering.compute_perplexity_score(
|
| 661 |
+
document, sentencepiece_model, kenlm_model
|
| 662 |
+
)
|
| 663 |
+
cond = score <= perplexity_max_cutoff
|
| 664 |
+
return cond
|
| 665 |
+
|
| 666 |
+
@staticmethod
|
| 667 |
+
def filtering(
|
| 668 |
+
document,
|
| 669 |
+
cond_check_number_words,
|
| 670 |
+
sentencepiece_model_tok,
|
| 671 |
+
strip_characters,
|
| 672 |
+
number_words_min_cutoff,
|
| 673 |
+
number_words_max_cutoff,
|
| 674 |
+
cond_check_repetitions_removal,
|
| 675 |
+
repetitions_length,
|
| 676 |
+
repetitions_max_cutoff,
|
| 677 |
+
cond_check_special_characters,
|
| 678 |
+
special_characters,
|
| 679 |
+
special_characters_max_cutoff,
|
| 680 |
+
cond_words_augmentation,
|
| 681 |
+
words_augmentation_group_sizes,
|
| 682 |
+
words_augmentation_join_char,
|
| 683 |
+
cond_check_stopwords,
|
| 684 |
+
stopwords,
|
| 685 |
+
stopwords_min_cutoff,
|
| 686 |
+
cond_check_badwords,
|
| 687 |
+
badwords,
|
| 688 |
+
badwords_max_cutoff,
|
| 689 |
+
cond_check_lang_id,
|
| 690 |
+
lang_dataset_id,
|
| 691 |
+
model_lang_id,
|
| 692 |
+
lang_id_min_cutoff,
|
| 693 |
+
cond_check_perplexity,
|
| 694 |
+
sentencepiece_model,
|
| 695 |
+
kenlm_model,
|
| 696 |
+
perplexity_max_cutoff,
|
| 697 |
+
):
|
| 698 |
+
if cond_check_number_words:
|
| 699 |
+
if not Filtering.check_number_words(
|
| 700 |
+
document,
|
| 701 |
+
sentencepiece_model_tok,
|
| 702 |
+
strip_characters,
|
| 703 |
+
number_words_min_cutoff,
|
| 704 |
+
number_words_max_cutoff,
|
| 705 |
+
):
|
| 706 |
+
return False
|
| 707 |
+
if cond_check_repetitions_removal:
|
| 708 |
+
if not Filtering.check_repetitions_removal(
|
| 709 |
+
document,
|
| 710 |
+
repetitions_length,
|
| 711 |
+
repetitions_max_cutoff,
|
| 712 |
+
):
|
| 713 |
+
return False
|
| 714 |
+
if cond_check_special_characters:
|
| 715 |
+
if not Filtering.check_special_characters(
|
| 716 |
+
document,
|
| 717 |
+
special_characters,
|
| 718 |
+
special_characters_max_cutoff,
|
| 719 |
+
):
|
| 720 |
+
return False
|
| 721 |
+
if cond_check_stopwords:
|
| 722 |
+
if not Filtering.check_stopwords(
|
| 723 |
+
document,
|
| 724 |
+
sentencepiece_model_tok,
|
| 725 |
+
strip_characters,
|
| 726 |
+
cond_words_augmentation,
|
| 727 |
+
words_augmentation_group_sizes,
|
| 728 |
+
words_augmentation_join_char,
|
| 729 |
+
stopwords,
|
| 730 |
+
stopwords_min_cutoff,
|
| 731 |
+
):
|
| 732 |
+
return False
|
| 733 |
+
if cond_check_badwords:
|
| 734 |
+
if not Filtering.check_badwords(
|
| 735 |
+
document,
|
| 736 |
+
sentencepiece_model_tok,
|
| 737 |
+
strip_characters,
|
| 738 |
+
cond_words_augmentation,
|
| 739 |
+
words_augmentation_group_sizes,
|
| 740 |
+
words_augmentation_join_char,
|
| 741 |
+
badwords,
|
| 742 |
+
badwords_max_cutoff,
|
| 743 |
+
):
|
| 744 |
+
return False
|
| 745 |
+
if cond_check_lang_id:
|
| 746 |
+
if not Filtering.check_lang_id(
|
| 747 |
+
document,
|
| 748 |
+
lang_dataset_id,
|
| 749 |
+
model_lang_id,
|
| 750 |
+
lang_id_min_cutoff,
|
| 751 |
+
):
|
| 752 |
+
return False
|
| 753 |
+
if cond_check_perplexity:
|
| 754 |
+
if not Filtering.check_perplexity(
|
| 755 |
+
document,
|
| 756 |
+
sentencepiece_model,
|
| 757 |
+
kenlm_model,
|
| 758 |
+
perplexity_max_cutoff,
|
| 759 |
+
):
|
| 760 |
+
return False
|
| 761 |
+
return True
|
| 762 |
+
|
| 763 |
+
|
| 764 |
+
class FunctionDatasetFiltering:
|
| 765 |
+
def __init__(
|
| 766 |
+
self,
|
| 767 |
+
lang_dataset_id,
|
| 768 |
+
path_fasttext_model,
|
| 769 |
+
path_sentencepiece_model,
|
| 770 |
+
path_kenlm_model,
|
| 771 |
+
):
|
| 772 |
+
self.lang_dataset_id = lang_dataset_id
|
| 773 |
+
self.path_fasttext_model = path_fasttext_model
|
| 774 |
+
self.path_sentencepiece_model = path_sentencepiece_model
|
| 775 |
+
self.path_kenlm_model = path_kenlm_model
|
| 776 |
+
|
| 777 |
+
self.param = LoadParameters.load_parameters(lang_dataset_id)
|
| 778 |
+
self.stopwords = LoadParameters.load_stopwords(lang_dataset_id)
|
| 779 |
+
self.badwords = LoadParameters.load_badwords(lang_dataset_id)
|
| 780 |
+
self.model_lang_id = LoadParameters.load_model_lang_id(
|
| 781 |
+
lang_dataset_id, path_fasttext_model
|
| 782 |
+
)
|
| 783 |
+
self.sentencepiece_model = LoadParameters.load_sentencepiece_model(
|
| 784 |
+
lang_dataset_id, path_sentencepiece_model
|
| 785 |
+
)
|
| 786 |
+
self.sentencepiece_model_tok = (
|
| 787 |
+
self.sentencepiece_model if self.param["tokenization"] else None
|
| 788 |
+
)
|
| 789 |
+
self.kenlm_model = LoadParameters.load_kenlm_model(
|
| 790 |
+
lang_dataset_id, path_kenlm_model
|
| 791 |
+
)
|
| 792 |
+
|
| 793 |
+
def __call__(self, example):
|
| 794 |
+
keep_example = Filtering.filtering(
|
| 795 |
+
document=example["text"],
|
| 796 |
+
cond_check_number_words=self.param["cond_check_number_words"],
|
| 797 |
+
sentencepiece_model_tok=self.sentencepiece_model_tok,
|
| 798 |
+
strip_characters=self.param["strip_characters"],
|
| 799 |
+
number_words_min_cutoff=self.param["number_words_min_cutoff"],
|
| 800 |
+
number_words_max_cutoff=self.param["number_words_max_cutoff"],
|
| 801 |
+
cond_check_repetitions_removal=self.param["check_repetitions_removal"],
|
| 802 |
+
repetitions_length=self.param["repetitions_length"],
|
| 803 |
+
repetitions_max_cutoff=self.param["repetitions_max_cutoff"],
|
| 804 |
+
cond_check_special_characters=self.param["cond_check_special_characters"],
|
| 805 |
+
special_characters=self.param["special_characters"],
|
| 806 |
+
special_characters_max_cutoff=self.param["special_characters_max_cutoff"],
|
| 807 |
+
cond_words_augmentation=self.param["cond_words_augmentation"],
|
| 808 |
+
words_augmentation_group_sizes=self.param["words_augmentation_group_sizes"],
|
| 809 |
+
words_augmentation_join_char=self.param["words_augmentation_join_char"],
|
| 810 |
+
cond_check_stopwords=self.param["cond_check_stopwords"],
|
| 811 |
+
stopwords=self.stopwords,
|
| 812 |
+
stopwords_min_cutoff=self.param["stopwords_min_cutoff"],
|
| 813 |
+
cond_check_badwords=self.param["cond_check_badwords"],
|
| 814 |
+
badwords=self.badwords,
|
| 815 |
+
badwords_max_cutoff=self.param["badwords_max_cutoff"],
|
| 816 |
+
cond_check_lang_id=self.param["cond_check_lang_id"],
|
| 817 |
+
lang_dataset_id=self.lang_dataset_id,
|
| 818 |
+
model_lang_id=self.model_lang_id,
|
| 819 |
+
lang_id_min_cutoff=self.param["lang_id_min_cutoff"],
|
| 820 |
+
cond_check_perplexity=self.param["cond_check_perplexity"],
|
| 821 |
+
sentencepiece_model=self.sentencepiece_model,
|
| 822 |
+
kenlm_model=self.kenlm_model,
|
| 823 |
+
perplexity_max_cutoff=self.param["perplexity_max_cutoff"],
|
| 824 |
+
)
|
| 825 |
+
return keep_example
|
| 826 |
+
|
| 827 |
+
def __reduce__(self):
|
| 828 |
+
return (
|
| 829 |
+
self.__class__,
|
| 830 |
+
(
|
| 831 |
+
self.lang_dataset_id,
|
| 832 |
+
self.path_fasttext_model,
|
| 833 |
+
self.path_sentencepiece_model,
|
| 834 |
+
self.path_kenlm_model,
|
| 835 |
+
),
|
| 836 |
+
)
|
| 837 |
+
|
| 838 |
+
|
| 839 |
+
class DatasetFiltering:
|
| 840 |
+
def __init__(
|
| 841 |
+
self,
|
| 842 |
+
dataset,
|
| 843 |
+
lang_dataset_id,
|
| 844 |
+
path_fasttext_model,
|
| 845 |
+
path_sentencepiece_model,
|
| 846 |
+
path_kenlm_model,
|
| 847 |
+
num_proc,
|
| 848 |
+
path_dir_save_dataset,
|
| 849 |
+
):
|
| 850 |
+
self.ds = dataset
|
| 851 |
+
self.lang_dataset_id = lang_dataset_id
|
| 852 |
+
self.path_fasttext_model = path_fasttext_model
|
| 853 |
+
self.path_sentencepiece_model = path_sentencepiece_model
|
| 854 |
+
self.path_kenlm_model = path_kenlm_model
|
| 855 |
+
self.num_proc = num_proc
|
| 856 |
+
self.path_dir_save_dataset = path_dir_save_dataset
|
| 857 |
+
|
| 858 |
+
def modifying_documents(self):
|
| 859 |
+
dataset_modifying_documents = FunctionDatasetModifyingDocuments(
|
| 860 |
+
self.lang_dataset_id
|
| 861 |
+
)
|
| 862 |
+
self.ds = self.ds.map(dataset_modifying_documents, num_proc=self.num_proc)
|
| 863 |
+
|
| 864 |
+
def filtering(self):
|
| 865 |
+
func_dataset_filtering = FunctionDatasetFiltering(
|
| 866 |
+
self.lang_dataset_id,
|
| 867 |
+
self.path_fasttext_model,
|
| 868 |
+
self.path_sentencepiece_model,
|
| 869 |
+
self.path_kenlm_model,
|
| 870 |
+
)
|
| 871 |
+
self.ds = self.ds.filter(func_dataset_filtering, num_proc=self.num_proc)
|
| 872 |
+
|
| 873 |
+
def save_dataset(self):
|
| 874 |
+
pathlib.Path(self.path_dir_save_dataset).mkdir(parents=True, exist_ok=True)
|
| 875 |
+
path_dir_save_dataset = pathlib.PurePath(
|
| 876 |
+
self.path_dir_save_dataset, self.lang_dataset_id
|
| 877 |
+
)
|
| 878 |
+
pathlib.Path(path_dir_save_dataset).mkdir(parents=True, exist_ok=True)
|
| 879 |
+
self.ds.save_to_disk(path_dir_save_dataset)
|
languages_id.py
ADDED
|
@@ -0,0 +1,231 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import pandas as pd
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
langs_id = [
|
| 5 |
+
{
|
| 6 |
+
"lang": "Afrikaans",
|
| 7 |
+
"dataset_id": "af",
|
| 8 |
+
"stopwords_id": "af",
|
| 9 |
+
"badwords_id": None,
|
| 10 |
+
"fasttext_id": "af",
|
| 11 |
+
"sentencepiece_id": "af",
|
| 12 |
+
"kenlm_id": "af",
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"lang": "Arabic",
|
| 16 |
+
"dataset_id": "ar",
|
| 17 |
+
"stopwords_id": "ar",
|
| 18 |
+
"badwords_id": "ar",
|
| 19 |
+
"fasttext_id": "ar",
|
| 20 |
+
"sentencepiece_id": "ar",
|
| 21 |
+
"kenlm_id": "ar",
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"lang": "Egyptian Arabic",
|
| 25 |
+
"dataset_id": "arz",
|
| 26 |
+
"stopwords_id": None,
|
| 27 |
+
"badwords_id": None,
|
| 28 |
+
"fasttext_id": "arz",
|
| 29 |
+
"sentencepiece_id": None,
|
| 30 |
+
"kenlm_id": None,
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"lang": "Assamese",
|
| 34 |
+
"dataset_id": "as",
|
| 35 |
+
"stopwords_id": None,
|
| 36 |
+
"badwords_id": None,
|
| 37 |
+
"fasttext_id": "as",
|
| 38 |
+
"sentencepiece_id": None,
|
| 39 |
+
"kenlm_id": None,
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"lang": "Bengali",
|
| 43 |
+
"dataset_id": "bn",
|
| 44 |
+
"stopwords_id": "bn",
|
| 45 |
+
"badwords_id": None,
|
| 46 |
+
"fasttext_id": "bn",
|
| 47 |
+
"sentencepiece_id": "bn",
|
| 48 |
+
"kenlm_id": "bn",
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"lang": "Catalan",
|
| 52 |
+
"dataset_id": "ca",
|
| 53 |
+
"stopwords_id": "ca",
|
| 54 |
+
"badwords_id": "ca",
|
| 55 |
+
"fasttext_id": "ca",
|
| 56 |
+
"sentencepiece_id": "ca",
|
| 57 |
+
"kenlm_id": "ca",
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"lang": "English",
|
| 61 |
+
"dataset_id": "en",
|
| 62 |
+
"stopwords_id": "en",
|
| 63 |
+
"badwords_id": "en",
|
| 64 |
+
"fasttext_id": "en",
|
| 65 |
+
"sentencepiece_id": "en",
|
| 66 |
+
"kenlm_id": "en",
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"lang": "Spanish",
|
| 70 |
+
"dataset_id": "es",
|
| 71 |
+
"stopwords_id": "es",
|
| 72 |
+
"badwords_id": "es",
|
| 73 |
+
"fasttext_id": "es",
|
| 74 |
+
"sentencepiece_id": "es",
|
| 75 |
+
"kenlm_id": "es",
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"lang": "Basque",
|
| 79 |
+
"dataset_id": "eu",
|
| 80 |
+
"stopwords_id": "eu",
|
| 81 |
+
"badwords_id": "eu",
|
| 82 |
+
"fasttext_id": "eu",
|
| 83 |
+
"sentencepiece_id": None,
|
| 84 |
+
"kenlm_id": None,
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"lang": "French",
|
| 88 |
+
"dataset_id": "fr",
|
| 89 |
+
"stopwords_id": "fr",
|
| 90 |
+
"badwords_id": "fr",
|
| 91 |
+
"fasttext_id": "fr",
|
| 92 |
+
"sentencepiece_id": "fr",
|
| 93 |
+
"kenlm_id": "fr",
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"lang": "Gujarati",
|
| 97 |
+
"dataset_id": "gu",
|
| 98 |
+
"stopwords_id": None,
|
| 99 |
+
"badwords_id": None,
|
| 100 |
+
"fasttext_id": "gu",
|
| 101 |
+
"sentencepiece_id": "gu",
|
| 102 |
+
"kenlm_id": "gu",
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"lang": "Hindi",
|
| 106 |
+
"dataset_id": "hi",
|
| 107 |
+
"stopwords_id": "hi",
|
| 108 |
+
"badwords_id": "hi",
|
| 109 |
+
"fasttext_id": "hi",
|
| 110 |
+
"sentencepiece_id": "hi",
|
| 111 |
+
"kenlm_id": "hi",
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"lang": "Indonesian",
|
| 115 |
+
"dataset_id": "id",
|
| 116 |
+
"stopwords_id": "id",
|
| 117 |
+
"badwords_id": "id",
|
| 118 |
+
"fasttext_id": "id",
|
| 119 |
+
"sentencepiece_id": "id",
|
| 120 |
+
"kenlm_id": "id",
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"lang": "Kannada",
|
| 124 |
+
"dataset_id": "kn",
|
| 125 |
+
"stopwords_id": None,
|
| 126 |
+
"badwords_id": "kn",
|
| 127 |
+
"fasttext_id": "kn",
|
| 128 |
+
"sentencepiece_id": "kn",
|
| 129 |
+
"kenlm_id": "kn",
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"lang": "Malayalam",
|
| 133 |
+
"dataset_id": "ml",
|
| 134 |
+
"stopwords_id": None,
|
| 135 |
+
"badwords_id": "ml",
|
| 136 |
+
"fasttext_id": "ml",
|
| 137 |
+
"sentencepiece_id": "ml",
|
| 138 |
+
"kenlm_id": "ml",
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"lang": "Marathi",
|
| 142 |
+
"dataset_id": "mr",
|
| 143 |
+
"stopwords_id": "mr",
|
| 144 |
+
"badwords_id": "mr",
|
| 145 |
+
"fasttext_id": "mr",
|
| 146 |
+
"sentencepiece_id": "mr",
|
| 147 |
+
"kenlm_id": "mr",
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"lang": "Portuguese",
|
| 151 |
+
"dataset_id": "pt",
|
| 152 |
+
"stopwords_id": "pt",
|
| 153 |
+
"badwords_id": "pt",
|
| 154 |
+
"fasttext_id": "pt",
|
| 155 |
+
"sentencepiece_id": "pt",
|
| 156 |
+
"kenlm_id": "pt",
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"lang": "Somali",
|
| 160 |
+
"dataset_id": "so",
|
| 161 |
+
"stopwords_id": "so",
|
| 162 |
+
"badwords_id": None,
|
| 163 |
+
"fasttext_id": "so",
|
| 164 |
+
"sentencepiece_id": None,
|
| 165 |
+
"kenlm_id": None,
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"lang": "Swahili",
|
| 169 |
+
"dataset_id": "sw",
|
| 170 |
+
"stopwords_id": "sw",
|
| 171 |
+
"badwords_id": None,
|
| 172 |
+
"fasttext_id": "sw",
|
| 173 |
+
"sentencepiece_id": None,
|
| 174 |
+
"kenlm_id": None,
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"lang": "Tamil",
|
| 178 |
+
"dataset_id": "ta",
|
| 179 |
+
"stopwords_id": None,
|
| 180 |
+
"badwords_id": None,
|
| 181 |
+
"fasttext_id": "ta",
|
| 182 |
+
"sentencepiece_id": None,
|
| 183 |
+
"kenlm_id": None,
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"lang": "Telugu",
|
| 187 |
+
"dataset_id": "te",
|
| 188 |
+
"stopwords_id": None,
|
| 189 |
+
"badwords_id": "te",
|
| 190 |
+
"fasttext_id": "te",
|
| 191 |
+
"sentencepiece_id": None,
|
| 192 |
+
"kenlm_id": None,
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"lang": "Urdu",
|
| 196 |
+
"dataset_id": "ur",
|
| 197 |
+
"stopwords_id": "ur",
|
| 198 |
+
"badwords_id": None,
|
| 199 |
+
"fasttext_id": "ur",
|
| 200 |
+
"sentencepiece_id": None,
|
| 201 |
+
"kenlm_id": None,
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"lang": "Vietnamese",
|
| 205 |
+
"dataset_id": "vi",
|
| 206 |
+
"stopwords_id": "vi",
|
| 207 |
+
"badwords_id": "vi",
|
| 208 |
+
"fasttext_id": "vi",
|
| 209 |
+
"sentencepiece_id": None,
|
| 210 |
+
"kenlm_id": None,
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"lang": "Yoruba",
|
| 214 |
+
"dataset_id": "yo",
|
| 215 |
+
"stopwords_id": "yo",
|
| 216 |
+
"badwords_id": None,
|
| 217 |
+
"fasttext_id": "yo",
|
| 218 |
+
"sentencepiece_id": None,
|
| 219 |
+
"kenlm_id": None,
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"lang": "Chinese",
|
| 223 |
+
"dataset_id": "zh",
|
| 224 |
+
"stopwords_id": "zh",
|
| 225 |
+
"badwords_id": "zh",
|
| 226 |
+
"fasttext_id": "zh",
|
| 227 |
+
"sentencepiece_id": "zh",
|
| 228 |
+
"kenlm_id": "zh",
|
| 229 |
+
},
|
| 230 |
+
]
|
| 231 |
+
langs_id = pd.DataFrame(langs_id)
|
lid.176.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e69ec5451bc261cc7844e49e4792a85d7f09c06789ec800fc4a44aec362764e
|
| 3 |
+
size 131266198
|
normalization.py
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
from typing import Dict
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
non_printing_characters_re = re.compile(
|
| 6 |
+
f"[{''.join(map(chr, list(range(0,32)) + list(range(127,160))))}]"
|
| 7 |
+
)
|
| 8 |
+
|
| 9 |
+
digits_re: re.Pattern = re.compile(r"\d")
|
| 10 |
+
|
| 11 |
+
unicode_punctuation: Dict[str, str] = {
|
| 12 |
+
"，": ",",
|
| 13 |
+
"。": ".",
|
| 14 |
+
"、": ",",
|
| 15 |
+
"„": '"',
|
| 16 |
+
"”": '"',
|
| 17 |
+
"“": '"',
|
| 18 |
+
"«": '"',
|
| 19 |
+
"»": '"',
|
| 20 |
+
"１": '"',
|
| 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 |
+
normalization = {
|
| 49 |
+
"non_printing_characters_re": non_printing_characters_re,
|
| 50 |
+
"digits_re": digits_re,
|
| 51 |
+
"unicode_punctuation": unicode_punctuation,
|
| 52 |
+
}
|
requirements.txt → packages.txt
RENAMED
|
File without changes
|
parameters_filtering.py
ADDED
|
@@ -0,0 +1,852 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import string
|
| 2 |
+
import emoji
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
main_special_characters = string.punctuation + string.digits + string.whitespace
|
| 6 |
+
other_special_characters = (
|
| 7 |
+
" ’“”–ー一▬…✦�£•€«»°·═"
|
| 8 |
+
"×士＾˘⇓↓↑←→（）§″′´¿−±∈¢ø‚„½¼¾¹²³―⁃，ˌ¸‹›ʺˈʻ¦‐⠀‰
‑≤≥‖"
|
| 9 |
+
"◆●■►▼▲▴∆▻¡★☆✱ːº。¯˜¥ɪ≈†上ン：∼⁄・♡✓⊕․．⋅÷１‟；،、¨ाাी्े◦˚"
|
| 10 |
+
"゜ʼ≖ʼ¤ッツシ℃√！【】‿∞➤～πه۩☛₨➩☻๑٪♥ıॽ《‘©﴿٬x？▷Г♫∟™ª₪®「—"
|
| 11 |
+
"❖」﴾》"
|
| 12 |
+
)
|
| 13 |
+
emoji = list(emoji.UNICODE_EMOJI["en"].keys())
|
| 14 |
+
|
| 15 |
+
special_characters_default = set(main_special_characters + other_special_characters)
|
| 16 |
+
special_characters_default.update(emoji)
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
parameters_filtering_default = {
|
| 20 |
+
"cond_uniform_whitespace": True,
|
| 21 |
+
"cond_replace_unicode_punctuation": False,
|
| 22 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 23 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 24 |
+
"cond_remove_long_words": False,
|
| 25 |
+
"length_word_max_cutoff": 50,
|
| 26 |
+
"cond_check_number_words": True,
|
| 27 |
+
"tokenization": False,
|
| 28 |
+
"strip_characters": special_characters_default,
|
| 29 |
+
"number_words_min_cutoff": 1,
|
| 30 |
+
"number_words_max_cutoff": 100000,
|
| 31 |
+
"check_repetitions_removal": True,
|
| 32 |
+
"repetitions_length": 10,
|
| 33 |
+
"repetitions_max_cutoff": 0.106,
|
| 34 |
+
"cond_check_special_characters": True,
|
| 35 |
+
"special_characters": special_characters_default,
|
| 36 |
+
"special_characters_max_cutoff": 0.4,
|
| 37 |
+
"cond_words_augmentation": False,
|
| 38 |
+
"words_augmentation_group_sizes": [],
|
| 39 |
+
"words_augmentation_join_char": "",
|
| 40 |
+
"cond_check_stopwords": False,
|
| 41 |
+
"stopwords_min_cutoff": 0,
|
| 42 |
+
"cond_check_badwords": False,
|
| 43 |
+
"badwords_max_cutoff": 0.2,
|
| 44 |
+
"cond_check_lang_id": True,
|
| 45 |
+
"lang_id_min_cutoff": 0.70,
|
| 46 |
+
"cond_check_perplexity": False,
|
| 47 |
+
"perplexity_max_cutoff": 3000000,
|
| 48 |
+
}
|
| 49 |
+
|
| 50 |
+
parameters_filtering_af = {
|
| 51 |
+
"cond_uniform_whitespace": True,
|
| 52 |
+
"cond_replace_unicode_punctuation": False,
|
| 53 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 54 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 55 |
+
"cond_remove_long_words": True,
|
| 56 |
+
"length_word_max_cutoff": 25,
|
| 57 |
+
"cond_check_number_words": True,
|
| 58 |
+
"tokenization": False,
|
| 59 |
+
"strip_characters": special_characters_default,
|
| 60 |
+
"number_words_min_cutoff": 1,
|
| 61 |
+
"number_words_max_cutoff": 100000,
|
| 62 |
+
"check_repetitions_removal": True,
|
| 63 |
+
"repetitions_length": 10,
|
| 64 |
+
"repetitions_max_cutoff": 0.106,
|
| 65 |
+
"cond_check_special_characters": True,
|
| 66 |
+
"special_characters": special_characters_default,
|
| 67 |
+
"special_characters_max_cutoff": 0.3,
|
| 68 |
+
"cond_words_augmentation": False,
|
| 69 |
+
"words_augmentation_group_sizes": [],
|
| 70 |
+
"words_augmentation_join_char": "",
|
| 71 |
+
"cond_check_stopwords": True,
|
| 72 |
+
"stopwords_min_cutoff": 0,
|
| 73 |
+
"cond_check_badwords": False,
|
| 74 |
+
"badwords_max_cutoff": 0.2,
|
| 75 |
+
"cond_check_lang_id": True,
|
| 76 |
+
"lang_id_min_cutoff": 0.6,
|
| 77 |
+
"cond_check_perplexity": True,
|
| 78 |
+
"perplexity_max_cutoff": 3000000,
|
| 79 |
+
}
|
| 80 |
+
|
| 81 |
+
parameters_filtering_ar = {
|
| 82 |
+
"cond_uniform_whitespace": True,
|
| 83 |
+
"cond_replace_unicode_punctuation": False,
|
| 84 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 85 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 86 |
+
"cond_remove_long_words": True,
|
| 87 |
+
"length_word_max_cutoff": 25,
|
| 88 |
+
"cond_check_number_words": True,
|
| 89 |
+
"tokenization": False,
|
| 90 |
+
"strip_characters": special_characters_default,
|
| 91 |
+
"number_words_min_cutoff": 1,
|
| 92 |
+
"number_words_max_cutoff": 100000,
|
| 93 |
+
"check_repetitions_removal": True,
|
| 94 |
+
"repetitions_length": 10,
|
| 95 |
+
"repetitions_max_cutoff": 0.106,
|
| 96 |
+
"cond_check_special_characters": True,
|
| 97 |
+
"special_characters": special_characters_default,
|
| 98 |
+
"special_characters_max_cutoff": 0.45,
|
| 99 |
+
"cond_words_augmentation": False,
|
| 100 |
+
"words_augmentation_group_sizes": [],
|
| 101 |
+
"words_augmentation_join_char": "",
|
| 102 |
+
"cond_check_stopwords": True,
|
| 103 |
+
"stopwords_min_cutoff": 0,
|
| 104 |
+
"cond_check_badwords": False,
|
| 105 |
+
"badwords_max_cutoff": 0.2,
|
| 106 |
+
"cond_check_lang_id": True,
|
| 107 |
+
"lang_id_min_cutoff": 0.75,
|
| 108 |
+
"cond_check_perplexity": True,
|
| 109 |
+
"perplexity_max_cutoff": 1000000,
|
| 110 |
+
}
|
| 111 |
+
|
| 112 |
+
parameters_filtering_arz = {
|
| 113 |
+
"cond_uniform_whitespace": True,
|
| 114 |
+
"cond_replace_unicode_punctuation": False,
|
| 115 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 116 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 117 |
+
"cond_remove_long_words": True,
|
| 118 |
+
"length_word_max_cutoff": 25,
|
| 119 |
+
"cond_check_number_words": True,
|
| 120 |
+
"tokenization": False,
|
| 121 |
+
"strip_characters": special_characters_default,
|
| 122 |
+
"number_words_min_cutoff": 1,
|
| 123 |
+
"number_words_max_cutoff": 100000,
|
| 124 |
+
"check_repetitions_removal": True,
|
| 125 |
+
"repetitions_length": 10,
|
| 126 |
+
"repetitions_max_cutoff": 0.106,
|
| 127 |
+
"cond_check_special_characters": True,
|
| 128 |
+
"special_characters": special_characters_default,
|
| 129 |
+
"special_characters_max_cutoff": 0.5,
|
| 130 |
+
"cond_words_augmentation": False,
|
| 131 |
+
"words_augmentation_group_sizes": [],
|
| 132 |
+
"words_augmentation_join_char": "",
|
| 133 |
+
"cond_check_stopwords": True,
|
| 134 |
+
"stopwords_min_cutoff": 0,
|
| 135 |
+
"cond_check_badwords": False,
|
| 136 |
+
"badwords_max_cutoff": 0.2,
|
| 137 |
+
"cond_check_lang_id": True,
|
| 138 |
+
"lang_id_min_cutoff": 0.75,
|
| 139 |
+
"cond_check_perplexity": False,
|
| 140 |
+
"perplexity_max_cutoff": 3000000,
|
| 141 |
+
}
|
| 142 |
+
|
| 143 |
+
parameters_filtering_as = {
|
| 144 |
+
"cond_uniform_whitespace": True,
|
| 145 |
+
"cond_replace_unicode_punctuation": False,
|
| 146 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 147 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 148 |
+
"cond_remove_long_words": True,
|
| 149 |
+
"length_word_max_cutoff": 25,
|
| 150 |
+
"cond_check_number_words": True,
|
| 151 |
+
"tokenization": False,
|
| 152 |
+
"strip_characters": special_characters_default,
|
| 153 |
+
"number_words_min_cutoff": 1,
|
| 154 |
+
"number_words_max_cutoff": 100000,
|
| 155 |
+
"check_repetitions_removal": True,
|
| 156 |
+
"repetitions_length": 10,
|
| 157 |
+
"repetitions_max_cutoff": 0.106,
|
| 158 |
+
"cond_check_special_characters": True,
|
| 159 |
+
"special_characters": special_characters_default,
|
| 160 |
+
"special_characters_max_cutoff": 0.25,
|
| 161 |
+
"cond_words_augmentation": False,
|
| 162 |
+
"words_augmentation_group_sizes": [],
|
| 163 |
+
"words_augmentation_join_char": "",
|
| 164 |
+
"cond_check_stopwords": True,
|
| 165 |
+
"stopwords_min_cutoff": 0,
|
| 166 |
+
"cond_check_badwords": False,
|
| 167 |
+
"badwords_max_cutoff": 0.2,
|
| 168 |
+
"cond_check_lang_id": True,
|
| 169 |
+
"lang_id_min_cutoff": 0.75,
|
| 170 |
+
"cond_check_perplexity": False,
|
| 171 |
+
"perplexity_max_cutoff": 3000000,
|
| 172 |
+
}
|
| 173 |
+
|
| 174 |
+
parameters_filtering_bn = {
|
| 175 |
+
"cond_uniform_whitespace": True,
|
| 176 |
+
"cond_replace_unicode_punctuation": False,
|
| 177 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 178 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 179 |
+
"cond_remove_long_words": True,
|
| 180 |
+
"length_word_max_cutoff": 30,
|
| 181 |
+
"cond_check_number_words": True,
|
| 182 |
+
"tokenization": False,
|
| 183 |
+
"strip_characters": special_characters_default,
|
| 184 |
+
"number_words_min_cutoff": 1,
|
| 185 |
+
"number_words_max_cutoff": 100000,
|
| 186 |
+
"check_repetitions_removal": True,
|
| 187 |
+
"repetitions_length": 10,
|
| 188 |
+
"repetitions_max_cutoff": 0.106,
|
| 189 |
+
"cond_check_special_characters": True,
|
| 190 |
+
"special_characters": special_characters_default,
|
| 191 |
+
"special_characters_max_cutoff": 0.275,
|
| 192 |
+
"cond_words_augmentation": False,
|
| 193 |
+
"words_augmentation_group_sizes": [],
|
| 194 |
+
"words_augmentation_join_char": "",
|
| 195 |
+
"cond_check_stopwords": True,
|
| 196 |
+
"stopwords_min_cutoff": 0.05,
|
| 197 |
+
"cond_check_badwords": False,
|
| 198 |
+
"badwords_max_cutoff": 0.2,
|
| 199 |
+
"cond_check_lang_id": True,
|
| 200 |
+
"lang_id_min_cutoff": 0.75,
|
| 201 |
+
"cond_check_perplexity": False,
|
| 202 |
+
"perplexity_max_cutoff": 575000,
|
| 203 |
+
}
|
| 204 |
+
|
| 205 |
+
parameters_filtering_ca = {
|
| 206 |
+
"cond_uniform_whitespace": True,
|
| 207 |
+
"cond_replace_unicode_punctuation": False,
|
| 208 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 209 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 210 |
+
"cond_remove_long_words": True,
|
| 211 |
+
"length_word_max_cutoff": 30,
|
| 212 |
+
"cond_check_number_words": True,
|
| 213 |
+
"tokenization": False,
|
| 214 |
+
"strip_characters": special_characters_default,
|
| 215 |
+
"number_words_min_cutoff": 1,
|
| 216 |
+
"number_words_max_cutoff": 100000,
|
| 217 |
+
"check_repetitions_removal": True,
|
| 218 |
+
"repetitions_length": 10,
|
| 219 |
+
"repetitions_max_cutoff": 0.106,
|
| 220 |
+
"cond_check_special_characters": True,
|
| 221 |
+
"special_characters": special_characters_default,
|
| 222 |
+
"special_characters_max_cutoff": 0.35,
|
| 223 |
+
"cond_words_augmentation": False,
|
| 224 |
+
"words_augmentation_group_sizes": [],
|
| 225 |
+
"words_augmentation_join_char": "",
|
| 226 |
+
"cond_check_stopwords": True,
|
| 227 |
+
"stopwords_min_cutoff": 0,
|
| 228 |
+
"cond_check_badwords": False,
|
| 229 |
+
"badwords_max_cutoff": 0.2,
|
| 230 |
+
"cond_check_lang_id": True,
|
| 231 |
+
"lang_id_min_cutoff": 0.75,
|
| 232 |
+
"cond_check_perplexity": True,
|
| 233 |
+
"perplexity_max_cutoff": 1750000,
|
| 234 |
+
}
|
| 235 |
+
|
| 236 |
+
parameters_filtering_en = {
|
| 237 |
+
"cond_uniform_whitespace": True,
|
| 238 |
+
"cond_replace_unicode_punctuation": False,
|
| 239 |
+
"cond_remove_words_with_incorrect_substrings": True,
|
| 240 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 241 |
+
"cond_remove_long_words": True,
|
| 242 |
+
"length_word_max_cutoff": 25,
|
| 243 |
+
"cond_check_number_words": True,
|
| 244 |
+
"tokenization": False,
|
| 245 |
+
"strip_characters": special_characters_default,
|
| 246 |
+
"number_words_min_cutoff": 20,
|
| 247 |
+
"number_words_max_cutoff": 100000,
|
| 248 |
+
"check_repetitions_removal": True,
|
| 249 |
+
"repetitions_length": 10,
|
| 250 |
+
"repetitions_max_cutoff": 0.106,
|
| 251 |
+
"cond_check_special_characters": True,
|
| 252 |
+
"special_characters": special_characters_default,
|
| 253 |
+
"special_characters_max_cutoff": 0.4,
|
| 254 |
+
"cond_words_augmentation": False,
|
| 255 |
+
"words_augmentation_group_sizes": [],
|
| 256 |
+
"words_augmentation_join_char": "",
|
| 257 |
+
"cond_check_stopwords": True,
|
| 258 |
+
"stopwords_min_cutoff": 0.3,
|
| 259 |
+
"cond_check_badwords": True,
|
| 260 |
+
"badwords_max_cutoff": 0.045,
|
| 261 |
+
"cond_check_lang_id": True,
|
| 262 |
+
"lang_id_min_cutoff": 0.80,
|
| 263 |
+
"cond_check_perplexity": True,
|
| 264 |
+
"perplexity_max_cutoff": 2500,
|
| 265 |
+
}
|
| 266 |
+
|
| 267 |
+
parameters_filtering_es = {
|
| 268 |
+
"cond_uniform_whitespace": True,
|
| 269 |
+
"cond_replace_unicode_punctuation": False,
|
| 270 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 271 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 272 |
+
"cond_remove_long_words": True,
|
| 273 |
+
"length_word_max_cutoff": 30,
|
| 274 |
+
"cond_check_number_words": True,
|
| 275 |
+
"tokenization": False,
|
| 276 |
+
"strip_characters": special_characters_default,
|
| 277 |
+
"number_words_min_cutoff": 1,
|
| 278 |
+
"number_words_max_cutoff": 100000,
|
| 279 |
+
"check_repetitions_removal": True,
|
| 280 |
+
"repetitions_length": 10,
|
| 281 |
+
"repetitions_max_cutoff": 0.106,
|
| 282 |
+
"cond_check_special_characters": True,
|
| 283 |
+
"special_characters": special_characters_default,
|
| 284 |
+
"special_characters_max_cutoff": 0.3,
|
| 285 |
+
"cond_words_augmentation": False,
|
| 286 |
+
"words_augmentation_group_sizes": [],
|
| 287 |
+
"words_augmentation_join_char": "",
|
| 288 |
+
"cond_check_stopwords": True,
|
| 289 |
+
"stopwords_min_cutoff": 0.2,
|
| 290 |
+
"cond_check_badwords": False,
|
| 291 |
+
"badwords_max_cutoff": 0.2,
|
| 292 |
+
"cond_check_lang_id": True,
|
| 293 |
+
"lang_id_min_cutoff": 0.75,
|
| 294 |
+
"cond_check_perplexity": True,
|
| 295 |
+
"perplexity_max_cutoff": 2500000,
|
| 296 |
+
}
|
| 297 |
+
|
| 298 |
+
parameters_filtering_eu = {
|
| 299 |
+
"cond_uniform_whitespace": True,
|
| 300 |
+
"cond_replace_unicode_punctuation": False,
|
| 301 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 302 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 303 |
+
"cond_remove_long_words": True,
|
| 304 |
+
"length_word_max_cutoff": 35,
|
| 305 |
+
"cond_check_number_words": True,
|
| 306 |
+
"tokenization": False,
|
| 307 |
+
"strip_characters": special_characters_default,
|
| 308 |
+
"number_words_min_cutoff": 1,
|
| 309 |
+
"number_words_max_cutoff": 100000,
|
| 310 |
+
"check_repetitions_removal": True,
|
| 311 |
+
"repetitions_length": 10,
|
| 312 |
+
"repetitions_max_cutoff": 0.106,
|
| 313 |
+
"cond_check_special_characters": True,
|
| 314 |
+
"special_characters": special_characters_default,
|
| 315 |
+
"special_characters_max_cutoff": 0.3,
|
| 316 |
+
"cond_words_augmentation": False,
|
| 317 |
+
"words_augmentation_group_sizes": [],
|
| 318 |
+
"words_augmentation_join_char": "",
|
| 319 |
+
"cond_check_stopwords": True,
|
| 320 |
+
"stopwords_min_cutoff": 0,
|
| 321 |
+
"cond_check_badwords": False,
|
| 322 |
+
"badwords_max_cutoff": 0.2,
|
| 323 |
+
"cond_check_lang_id": True,
|
| 324 |
+
"lang_id_min_cutoff": 0.75,
|
| 325 |
+
"cond_check_perplexity": False,
|
| 326 |
+
"perplexity_max_cutoff": 3000000,
|
| 327 |
+
}
|
| 328 |
+
|
| 329 |
+
parameters_filtering_fr = {
|
| 330 |
+
"cond_uniform_whitespace": True,
|
| 331 |
+
"cond_replace_unicode_punctuation": False,
|
| 332 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 333 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 334 |
+
"cond_remove_long_words": True,
|
| 335 |
+
"length_word_max_cutoff": 30,
|
| 336 |
+
"cond_check_number_words": True,
|
| 337 |
+
"tokenization": False,
|
| 338 |
+
"strip_characters": special_characters_default,
|
| 339 |
+
"number_words_min_cutoff": 1,
|
| 340 |
+
"number_words_max_cutoff": 100000,
|
| 341 |
+
"check_repetitions_removal": True,
|
| 342 |
+
"repetitions_length": 10,
|
| 343 |
+
"repetitions_max_cutoff": 0.106,
|
| 344 |
+
"cond_check_special_characters": True,
|
| 345 |
+
"special_characters": special_characters_default,
|
| 346 |
+
"special_characters_max_cutoff": 0.35,
|
| 347 |
+
"cond_words_augmentation": False,
|
| 348 |
+
"words_augmentation_group_sizes": [],
|
| 349 |
+
"words_augmentation_join_char": "",
|
| 350 |
+
"cond_check_stopwords": True,
|
| 351 |
+
"stopwords_min_cutoff": 0.15,
|
| 352 |
+
"cond_check_badwords": False,
|
| 353 |
+
"badwords_max_cutoff": 0.2,
|
| 354 |
+
"cond_check_lang_id": True,
|
| 355 |
+
"lang_id_min_cutoff": 0.75,
|
| 356 |
+
"cond_check_perplexity": True,
|
| 357 |
+
"perplexity_max_cutoff": 3000000,
|
| 358 |
+
}
|
| 359 |
+
|
| 360 |
+
parameters_filtering_gu = {
|
| 361 |
+
"cond_uniform_whitespace": True,
|
| 362 |
+
"cond_replace_unicode_punctuation": False,
|
| 363 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 364 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 365 |
+
"cond_remove_long_words": True,
|
| 366 |
+
"length_word_max_cutoff": 30,
|
| 367 |
+
"cond_check_number_words": True,
|
| 368 |
+
"tokenization": False,
|
| 369 |
+
"strip_characters": special_characters_default,
|
| 370 |
+
"number_words_min_cutoff": 1,
|
| 371 |
+
"number_words_max_cutoff": 100000,
|
| 372 |
+
"check_repetitions_removal": True,
|
| 373 |
+
"repetitions_length": 10,
|
| 374 |
+
"repetitions_max_cutoff": 0.106,
|
| 375 |
+
"cond_check_special_characters": True,
|
| 376 |
+
"special_characters": special_characters_default,
|
| 377 |
+
"special_characters_max_cutoff": 0.3,
|
| 378 |
+
"cond_words_augmentation": False,
|
| 379 |
+
"words_augmentation_group_sizes": [],
|
| 380 |
+
"words_augmentation_join_char": "",
|
| 381 |
+
"cond_check_stopwords": True,
|
| 382 |
+
"stopwords_min_cutoff": 0,
|
| 383 |
+
"cond_check_badwords": False,
|
| 384 |
+
"badwords_max_cutoff": 0.2,
|
| 385 |
+
"cond_check_lang_id": True,
|
| 386 |
+
"lang_id_min_cutoff": 0.75,
|
| 387 |
+
"cond_check_perplexity": True,
|
| 388 |
+
"perplexity_max_cutoff": 250000,
|
| 389 |
+
}
|
| 390 |
+
|
| 391 |
+
parameters_filtering_hi = {
|
| 392 |
+
"cond_uniform_whitespace": True,
|
| 393 |
+
"cond_replace_unicode_punctuation": False,
|
| 394 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 395 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 396 |
+
"cond_remove_long_words": True,
|
| 397 |
+
"length_word_max_cutoff": 25,
|
| 398 |
+
"cond_check_number_words": True,
|
| 399 |
+
"tokenization": False,
|
| 400 |
+
"strip_characters": special_characters_default,
|
| 401 |
+
"number_words_min_cutoff": 1,
|
| 402 |
+
"number_words_max_cutoff": 100000,
|
| 403 |
+
"check_repetitions_removal": True,
|
| 404 |
+
"repetitions_length": 10,
|
| 405 |
+
"repetitions_max_cutoff": 0.106,
|
| 406 |
+
"cond_check_special_characters": True,
|
| 407 |
+
"special_characters": special_characters_default,
|
| 408 |
+
"special_characters_max_cutoff": 0.35,
|
| 409 |
+
"cond_words_augmentation": False,
|
| 410 |
+
"words_augmentation_group_sizes": [],
|
| 411 |
+
"words_augmentation_join_char": "",
|
| 412 |
+
"cond_check_stopwords": True,
|
| 413 |
+
"stopwords_min_cutoff": 0,
|
| 414 |
+
"cond_check_badwords": False,
|
| 415 |
+
"badwords_max_cutoff": 0.2,
|
| 416 |
+
"cond_check_lang_id": True,
|
| 417 |
+
"lang_id_min_cutoff": 0.75,
|
| 418 |
+
"cond_check_perplexity": True,
|
| 419 |
+
"perplexity_max_cutoff": 600000,
|
| 420 |
+
}
|
| 421 |
+
|
| 422 |
+
parameters_filtering_id = {
|
| 423 |
+
"cond_uniform_whitespace": True,
|
| 424 |
+
"cond_replace_unicode_punctuation": False,
|
| 425 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 426 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 427 |
+
"cond_remove_long_words": True,
|
| 428 |
+
"length_word_max_cutoff": 30,
|
| 429 |
+
"cond_check_number_words": True,
|
| 430 |
+
"tokenization": False,
|
| 431 |
+
"strip_characters": special_characters_default,
|
| 432 |
+
"number_words_min_cutoff": 1,
|
| 433 |
+
"number_words_max_cutoff": 100000,
|
| 434 |
+
"check_repetitions_removal": True,
|
| 435 |
+
"repetitions_length": 10,
|
| 436 |
+
"repetitions_max_cutoff": 0.106,
|
| 437 |
+
"cond_check_special_characters": True,
|
| 438 |
+
"special_characters": special_characters_default,
|
| 439 |
+
"special_characters_max_cutoff": 0.25,
|
| 440 |
+
"cond_words_augmentation": False,
|
| 441 |
+
"words_augmentation_group_sizes": [],
|
| 442 |
+
"words_augmentation_join_char": "",
|
| 443 |
+
"cond_check_stopwords": True,
|
| 444 |
+
"stopwords_min_cutoff": 0.25,
|
| 445 |
+
"cond_check_badwords": False,
|
| 446 |
+
"badwords_max_cutoff": 0.2,
|
| 447 |
+
"cond_check_lang_id": True,
|
| 448 |
+
"lang_id_min_cutoff": 0.75,
|
| 449 |
+
"cond_check_perplexity": True,
|
| 450 |
+
"perplexity_max_cutoff": 2500000,
|
| 451 |
+
}
|
| 452 |
+
|
| 453 |
+
parameters_filtering_kn = {
|
| 454 |
+
"cond_uniform_whitespace": True,
|
| 455 |
+
"cond_replace_unicode_punctuation": False,
|
| 456 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 457 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 458 |
+
"cond_remove_long_words": True,
|
| 459 |
+
"length_word_max_cutoff": 50,
|
| 460 |
+
"cond_check_number_words": True,
|
| 461 |
+
"tokenization": False,
|
| 462 |
+
"strip_characters": special_characters_default,
|
| 463 |
+
"number_words_min_cutoff": 1,
|
| 464 |
+
"number_words_max_cutoff": 100000,
|
| 465 |
+
"check_repetitions_removal": True,
|
| 466 |
+
"repetitions_length": 10,
|
| 467 |
+
"repetitions_max_cutoff": 0.106,
|
| 468 |
+
"cond_check_special_characters": True,
|
| 469 |
+
"special_characters": special_characters_default,
|
| 470 |
+
"special_characters_max_cutoff": 0.25,
|
| 471 |
+
"cond_words_augmentation": False,
|
| 472 |
+
"words_augmentation_group_sizes": [],
|
| 473 |
+
"words_augmentation_join_char": "",
|
| 474 |
+
"cond_check_stopwords": True,
|
| 475 |
+
"stopwords_min_cutoff": 0,
|
| 476 |
+
"cond_check_badwords": False,
|
| 477 |
+
"badwords_max_cutoff": 0.2,
|
| 478 |
+
"cond_check_lang_id": True,
|
| 479 |
+
"lang_id_min_cutoff": 0.75,
|
| 480 |
+
"cond_check_perplexity": True,
|
| 481 |
+
"perplexity_max_cutoff": 400000,
|
| 482 |
+
}
|
| 483 |
+
|
| 484 |
+
parameters_filtering_ml = {
|
| 485 |
+
"cond_uniform_whitespace": True,
|
| 486 |
+
"cond_replace_unicode_punctuation": False,
|
| 487 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 488 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 489 |
+
"cond_remove_long_words": True,
|
| 490 |
+
"length_word_max_cutoff": 50,
|
| 491 |
+
"cond_check_number_words": True,
|
| 492 |
+
"tokenization": False,
|
| 493 |
+
"strip_characters": special_characters_default,
|
| 494 |
+
"number_words_min_cutoff": 1,
|
| 495 |
+
"number_words_max_cutoff": 100000,
|
| 496 |
+
"check_repetitions_removal": True,
|
| 497 |
+
"repetitions_length": 10,
|
| 498 |
+
"repetitions_max_cutoff": 0.106,
|
| 499 |
+
"cond_check_special_characters": True,
|
| 500 |
+
"special_characters": special_characters_default,
|
| 501 |
+
"special_characters_max_cutoff": 0.2,
|
| 502 |
+
"cond_words_augmentation": False,
|
| 503 |
+
"words_augmentation_group_sizes": [],
|
| 504 |
+
"words_augmentation_join_char": "",
|
| 505 |
+
"cond_check_stopwords": True,
|
| 506 |
+
"stopwords_min_cutoff": 0,
|
| 507 |
+
"cond_check_badwords": False,
|
| 508 |
+
"badwords_max_cutoff": 0.2,
|
| 509 |
+
"cond_check_lang_id": True,
|
| 510 |
+
"lang_id_min_cutoff": 0.75,
|
| 511 |
+
"cond_check_perplexity": True,
|
| 512 |
+
"perplexity_max_cutoff": 1600000,
|
| 513 |
+
}
|
| 514 |
+
|
| 515 |
+
parameters_filtering_mr = {
|
| 516 |
+
"cond_uniform_whitespace": True,
|
| 517 |
+
"cond_replace_unicode_punctuation": False,
|
| 518 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 519 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 520 |
+
"cond_remove_long_words": True,
|
| 521 |
+
"length_word_max_cutoff": 30,
|
| 522 |
+
"cond_check_number_words": True,
|
| 523 |
+
"tokenization": False,
|
| 524 |
+
"strip_characters": special_characters_default,
|
| 525 |
+
"number_words_min_cutoff": 1,
|
| 526 |
+
"number_words_max_cutoff": 100000,
|
| 527 |
+
"check_repetitions_removal": True,
|
| 528 |
+
"repetitions_length": 10,
|
| 529 |
+
"repetitions_max_cutoff": 0.106,
|
| 530 |
+
"cond_check_special_characters": True,
|
| 531 |
+
"special_characters": special_characters_default,
|
| 532 |
+
"special_characters_max_cutoff": 0.25,
|
| 533 |
+
"cond_words_augmentation": False,
|
| 534 |
+
"words_augmentation_group_sizes": [],
|
| 535 |
+
"words_augmentation_join_char": "",
|
| 536 |
+
"cond_check_stopwords": True,
|
| 537 |
+
"stopwords_min_cutoff": 0,
|
| 538 |
+
"cond_check_badwords": False,
|
| 539 |
+
"badwords_max_cutoff": 0.2,
|
| 540 |
+
"cond_check_lang_id": True,
|
| 541 |
+
"lang_id_min_cutoff": 0.75,
|
| 542 |
+
"cond_check_perplexity": True,
|
| 543 |
+
"perplexity_max_cutoff": 425000,
|
| 544 |
+
}
|
| 545 |
+
|
| 546 |
+
parameters_filtering_pt = {
|
| 547 |
+
"cond_uniform_whitespace": True,
|
| 548 |
+
"cond_replace_unicode_punctuation": False,
|
| 549 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 550 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 551 |
+
"cond_remove_long_words": True,
|
| 552 |
+
"length_word_max_cutoff": 30,
|
| 553 |
+
"cond_check_number_words": True,
|
| 554 |
+
"tokenization": False,
|
| 555 |
+
"strip_characters": special_characters_default,
|
| 556 |
+
"number_words_min_cutoff": 1,
|
| 557 |
+
"number_words_max_cutoff": 100000,
|
| 558 |
+
"check_repetitions_removal": True,
|
| 559 |
+
"repetitions_length": 10,
|
| 560 |
+
"repetitions_max_cutoff": 0.106,
|
| 561 |
+
"cond_check_special_characters": True,
|
| 562 |
+
"special_characters": special_characters_default,
|
| 563 |
+
"special_characters_max_cutoff": 0.3,
|
| 564 |
+
"cond_words_augmentation": False,
|
| 565 |
+
"words_augmentation_group_sizes": [],
|
| 566 |
+
"words_augmentation_join_char": "",
|
| 567 |
+
"cond_check_stopwords": True,
|
| 568 |
+
"stopwords_min_cutoff": 0.15,
|
| 569 |
+
"cond_check_badwords": False,
|
| 570 |
+
"badwords_max_cutoff": 0.2,
|
| 571 |
+
"cond_check_lang_id": True,
|
| 572 |
+
"lang_id_min_cutoff": 0.75,
|
| 573 |
+
"cond_check_perplexity": True,
|
| 574 |
+
"perplexity_max_cutoff": 3000000,
|
| 575 |
+
}
|
| 576 |
+
|
| 577 |
+
parameters_filtering_so = {
|
| 578 |
+
"cond_uniform_whitespace": True,
|
| 579 |
+
"cond_replace_unicode_punctuation": False,
|
| 580 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 581 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 582 |
+
"cond_remove_long_words": False,
|
| 583 |
+
"length_word_max_cutoff": 1000,
|
| 584 |
+
"cond_check_number_words": True,
|
| 585 |
+
"tokenization": False,
|
| 586 |
+
"strip_characters": special_characters_default,
|
| 587 |
+
"number_words_min_cutoff": 1,
|
| 588 |
+
"number_words_max_cutoff": 100000,
|
| 589 |
+
"check_repetitions_removal": True,
|
| 590 |
+
"repetitions_length": 10,
|
| 591 |
+
"repetitions_max_cutoff": 0.106,
|
| 592 |
+
"cond_check_special_characters": True,
|
| 593 |
+
"special_characters": special_characters_default,
|
| 594 |
+
"special_characters_max_cutoff": 0.3,
|
| 595 |
+
"cond_words_augmentation": False,
|
| 596 |
+
"words_augmentation_group_sizes": [],
|
| 597 |
+
"words_augmentation_join_char": "",
|
| 598 |
+
"cond_check_stopwords": False,
|
| 599 |
+
"stopwords_min_cutoff": 0,
|
| 600 |
+
"cond_check_badwords": False,
|
| 601 |
+
"badwords_max_cutoff": 0.2,
|
| 602 |
+
"cond_check_lang_id": True,
|
| 603 |
+
"lang_id_min_cutoff": 0.75,
|
| 604 |
+
"cond_check_perplexity": False,
|
| 605 |
+
"perplexity_max_cutoff": 3000000,
|
| 606 |
+
}
|
| 607 |
+
|
| 608 |
+
parameters_filtering_sw = {
|
| 609 |
+
"cond_uniform_whitespace": True,
|
| 610 |
+
"cond_replace_unicode_punctuation": False,
|
| 611 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 612 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 613 |
+
"cond_remove_long_words": True,
|
| 614 |
+
"length_word_max_cutoff": 30,
|
| 615 |
+
"cond_check_number_words": True,
|
| 616 |
+
"tokenization": False,
|
| 617 |
+
"strip_characters": special_characters_default,
|
| 618 |
+
"number_words_min_cutoff": 1,
|
| 619 |
+
"number_words_max_cutoff": 100000,
|
| 620 |
+
"check_repetitions_removal": True,
|
| 621 |
+
"repetitions_length": 10,
|
| 622 |
+
"repetitions_max_cutoff": 0.106,
|
| 623 |
+
"cond_check_special_characters": True,
|
| 624 |
+
"special_characters": special_characters_default,
|
| 625 |
+
"special_characters_max_cutoff": 0.275,
|
| 626 |
+
"cond_words_augmentation": False,
|
| 627 |
+
"words_augmentation_group_sizes": [],
|
| 628 |
+
"words_augmentation_join_char": "",
|
| 629 |
+
"cond_check_stopwords": True,
|
| 630 |
+
"stopwords_min_cutoff": 0,
|
| 631 |
+
"cond_check_badwords": False,
|
| 632 |
+
"badwords_max_cutoff": 0.2,
|
| 633 |
+
"cond_check_lang_id": True,
|
| 634 |
+
"lang_id_min_cutoff": 0.75,
|
| 635 |
+
"cond_check_perplexity": False,
|
| 636 |
+
"perplexity_max_cutoff": 3000000,
|
| 637 |
+
}
|
| 638 |
+
|
| 639 |
+
parameters_filtering_ta = {
|
| 640 |
+
"cond_uniform_whitespace": True,
|
| 641 |
+
"cond_replace_unicode_punctuation": False,
|
| 642 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 643 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 644 |
+
"cond_remove_long_words": True,
|
| 645 |
+
"length_word_max_cutoff": 50,
|
| 646 |
+
"cond_check_number_words": True,
|
| 647 |
+
"tokenization": False,
|
| 648 |
+
"strip_characters": special_characters_default,
|
| 649 |
+
"number_words_min_cutoff": 1,
|
| 650 |
+
"number_words_max_cutoff": 100000,
|
| 651 |
+
"check_repetitions_removal": True,
|
| 652 |
+
"repetitions_length": 10,
|
| 653 |
+
"repetitions_max_cutoff": 0.106,
|
| 654 |
+
"cond_check_special_characters": True,
|
| 655 |
+
"special_characters": special_characters_default,
|
| 656 |
+
"special_characters_max_cutoff": 0.25,
|
| 657 |
+
"cond_words_augmentation": False,
|
| 658 |
+
"words_augmentation_group_sizes": [],
|
| 659 |
+
"words_augmentation_join_char": "",
|
| 660 |
+
"cond_check_stopwords": True,
|
| 661 |
+
"stopwords_min_cutoff": 0,
|
| 662 |
+
"cond_check_badwords": False,
|
| 663 |
+
"badwords_max_cutoff": 0.2,
|
| 664 |
+
"cond_check_lang_id": True,
|
| 665 |
+
"lang_id_min_cutoff": 0.75,
|
| 666 |
+
"cond_check_perplexity": False,
|
| 667 |
+
"perplexity_max_cutoff": 3000000,
|
| 668 |
+
}
|
| 669 |
+
|
| 670 |
+
parameters_filtering_te = {
|
| 671 |
+
"cond_uniform_whitespace": True,
|
| 672 |
+
"cond_replace_unicode_punctuation": False,
|
| 673 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 674 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 675 |
+
"cond_remove_long_words": True,
|
| 676 |
+
"length_word_max_cutoff": 35,
|
| 677 |
+
"cond_check_number_words": True,
|
| 678 |
+
"tokenization": False,
|
| 679 |
+
"strip_characters": special_characters_default,
|
| 680 |
+
"number_words_min_cutoff": 1,
|
| 681 |
+
"number_words_max_cutoff": 100000,
|
| 682 |
+
"check_repetitions_removal": True,
|
| 683 |
+
"repetitions_length": 10,
|
| 684 |
+
"repetitions_max_cutoff": 0.106,
|
| 685 |
+
"cond_check_special_characters": True,
|
| 686 |
+
"special_characters": special_characters_default,
|
| 687 |
+
"special_characters_max_cutoff": 0.25,
|
| 688 |
+
"cond_words_augmentation": False,
|
| 689 |
+
"words_augmentation_group_sizes": [],
|
| 690 |
+
"words_augmentation_join_char": "",
|
| 691 |
+
"cond_check_stopwords": True,
|
| 692 |
+
"stopwords_min_cutoff": 0,
|
| 693 |
+
"cond_check_badwords": False,
|
| 694 |
+
"badwords_max_cutoff": 0.2,
|
| 695 |
+
"cond_check_lang_id": True,
|
| 696 |
+
"lang_id_min_cutoff": 0.75,
|
| 697 |
+
"cond_check_perplexity": False,
|
| 698 |
+
"perplexity_max_cutoff": 3000000,
|
| 699 |
+
}
|
| 700 |
+
|
| 701 |
+
parameters_filtering_ur = {
|
| 702 |
+
"cond_uniform_whitespace": True,
|
| 703 |
+
"cond_replace_unicode_punctuation": False,
|
| 704 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 705 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 706 |
+
"cond_remove_long_words": True,
|
| 707 |
+
"length_word_max_cutoff": 30,
|
| 708 |
+
"cond_check_number_words": True,
|
| 709 |
+
"tokenization": False,
|
| 710 |
+
"strip_characters": special_characters_default,
|
| 711 |
+
"number_words_min_cutoff": 1,
|
| 712 |
+
"number_words_max_cutoff": 100000,
|
| 713 |
+
"check_repetitions_removal": True,
|
| 714 |
+
"repetitions_length": 10,
|
| 715 |
+
"repetitions_max_cutoff": 0.106,
|
| 716 |
+
"cond_check_special_characters": True,
|
| 717 |
+
"special_characters": special_characters_default,
|
| 718 |
+
"special_characters_max_cutoff": 0.4,
|
| 719 |
+
"cond_words_augmentation": False,
|
| 720 |
+
"words_augmentation_group_sizes": [],
|
| 721 |
+
"words_augmentation_join_char": "",
|
| 722 |
+
"cond_check_stopwords": True,
|
| 723 |
+
"stopwords_min_cutoff": 0,
|
| 724 |
+
"cond_check_badwords": False,
|
| 725 |
+
"badwords_max_cutoff": 0.2,
|
| 726 |
+
"cond_check_lang_id": True,
|
| 727 |
+
"lang_id_min_cutoff": 0.75,
|
| 728 |
+
"cond_check_perplexity": False,
|
| 729 |
+
"perplexity_max_cutoff": 3000000,
|
| 730 |
+
}
|
| 731 |
+
|
| 732 |
+
parameters_filtering_vi = {
|
| 733 |
+
"cond_uniform_whitespace": True,
|
| 734 |
+
"cond_replace_unicode_punctuation": False,
|
| 735 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 736 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 737 |
+
"cond_remove_long_words": True,
|
| 738 |
+
"length_word_max_cutoff": 30,
|
| 739 |
+
"cond_check_number_words": True,
|
| 740 |
+
"tokenization": False,
|
| 741 |
+
"strip_characters": special_characters_default,
|
| 742 |
+
"number_words_min_cutoff": 1,
|
| 743 |
+
"number_words_max_cutoff": 100000,
|
| 744 |
+
"check_repetitions_removal": True,
|
| 745 |
+
"repetitions_length": 10,
|
| 746 |
+
"repetitions_max_cutoff": 0.106,
|
| 747 |
+
"cond_check_special_characters": True,
|
| 748 |
+
"special_characters": special_characters_default,
|
| 749 |
+
"special_characters_max_cutoff": 0.35,
|
| 750 |
+
"cond_words_augmentation": True,
|
| 751 |
+
"words_augmentation_group_sizes": [2, 3],
|
| 752 |
+
"words_augmentation_join_char": " ",
|
| 753 |
+
"cond_check_stopwords": True,
|
| 754 |
+
"stopwords_min_cutoff": 0,
|
| 755 |
+
"cond_check_badwords": False,
|
| 756 |
+
"badwords_max_cutoff": 0.2,
|
| 757 |
+
"cond_check_lang_id": True,
|
| 758 |
+
"lang_id_min_cutoff": 0.75,
|
| 759 |
+
"cond_check_perplexity": False,
|
| 760 |
+
"perplexity_max_cutoff": 3000000,
|
| 761 |
+
}
|
| 762 |
+
|
| 763 |
+
parameters_filtering_yo = {
|
| 764 |
+
"cond_uniform_whitespace": True,
|
| 765 |
+
"cond_replace_unicode_punctuation": False,
|
| 766 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 767 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 768 |
+
"cond_remove_long_words": True,
|
| 769 |
+
"length_word_max_cutoff": 30,
|
| 770 |
+
"cond_check_number_words": True,
|
| 771 |
+
"tokenization": False,
|
| 772 |
+
"strip_characters": special_characters_default,
|
| 773 |
+
"number_words_min_cutoff": 1,
|
| 774 |
+
"number_words_max_cutoff": 100000,
|
| 775 |
+
"check_repetitions_removal": True,
|
| 776 |
+
"repetitions_length": 10,
|
| 777 |
+
"repetitions_max_cutoff": 0.106,
|
| 778 |
+
"cond_check_special_characters": True,
|
| 779 |
+
"special_characters": special_characters_default,
|
| 780 |
+
"special_characters_max_cutoff": 0.3,
|
| 781 |
+
"cond_words_augmentation": False,
|
| 782 |
+
"words_augmentation_group_sizes": [],
|
| 783 |
+
"words_augmentation_join_char": "",
|
| 784 |
+
"cond_check_stopwords": True,
|
| 785 |
+
"stopwords_min_cutoff": 0,
|
| 786 |
+
"cond_check_badwords": False,
|
| 787 |
+
"badwords_max_cutoff": 0.2,
|
| 788 |
+
"cond_check_lang_id": True,
|
| 789 |
+
"lang_id_min_cutoff": 0.75,
|
| 790 |
+
"cond_check_perplexity": False,
|
| 791 |
+
"perplexity_max_cutoff": 3000000,
|
| 792 |
+
}
|
| 793 |
+
|
| 794 |
+
parameters_filtering_zh = {
|
| 795 |
+
"cond_uniform_whitespace": True,
|
| 796 |
+
"cond_replace_unicode_punctuation": False,
|
| 797 |
+
"cond_remove_words_with_incorrect_substrings": False,
|
| 798 |
+
"incorrect_word_substrings": ["http", "www", ".com", "href", "//"],
|
| 799 |
+
"cond_remove_long_words": False,
|
| 800 |
+
"length_word_max_cutoff": 1000,
|
| 801 |
+
"cond_check_number_words": True,
|
| 802 |
+
"tokenization": True,
|
| 803 |
+
"strip_characters": special_characters_default,
|
| 804 |
+
"number_words_min_cutoff": 1,
|
| 805 |
+
"number_words_max_cutoff": 100000,
|
| 806 |
+
"check_repetitions_removal": True,
|
| 807 |
+
"repetitions_length": 10,
|
| 808 |
+
"repetitions_max_cutoff": 0.106,
|
| 809 |
+
"cond_check_special_characters": True,
|
| 810 |
+
"special_characters": special_characters_default,
|
| 811 |
+
"special_characters_max_cutoff": 0.4,
|
| 812 |
+
"cond_words_augmentation": True,
|
| 813 |
+
"words_augmentation_group_sizes": [2, 3],
|
| 814 |
+
"words_augmentation_join_char": "",
|
| 815 |
+
"cond_check_stopwords": False,
|
| 816 |
+
"stopwords_min_cutoff": 0,
|
| 817 |
+
"cond_check_badwords": False,
|
| 818 |
+
"badwords_max_cutoff": 0.2,
|
| 819 |
+
"cond_check_lang_id": True,
|
| 820 |
+
"lang_id_min_cutoff": 0.75,
|
| 821 |
+
"cond_check_perplexity": False,
|
| 822 |
+
"perplexity_max_cutoff": 3000000,
|
| 823 |
+
}
|
| 824 |
+
|
| 825 |
+
parameters_filtering = {
|
| 826 |
+
"default": parameters_filtering_default,
|
| 827 |
+
"af": parameters_filtering_af,
|
| 828 |
+
"ar": parameters_filtering_ar,
|
| 829 |
+
"arz": parameters_filtering_arz,
|
| 830 |
+
"as": parameters_filtering_as,
|
| 831 |
+
"bn": parameters_filtering_bn,
|
| 832 |
+
"ca": parameters_filtering_ca,
|
| 833 |
+
"en": parameters_filtering_en,
|
| 834 |
+
"es": parameters_filtering_es,
|
| 835 |
+
"eu": parameters_filtering_eu,
|
| 836 |
+
"fr": parameters_filtering_fr,
|
| 837 |
+
"gu": parameters_filtering_gu,
|
| 838 |
+
"hi": parameters_filtering_hi,
|
| 839 |
+
"id": parameters_filtering_id,
|
| 840 |
+
"kn": parameters_filtering_kn,
|
| 841 |
+
"ml": parameters_filtering_ml,
|
| 842 |
+
"mr": parameters_filtering_mr,
|
| 843 |
+
"pt": parameters_filtering_pt,
|
| 844 |
+
"so": parameters_filtering_so,
|
| 845 |
+
"sw": parameters_filtering_sw,
|
| 846 |
+
"ta": parameters_filtering_ta,
|
| 847 |
+
"te": parameters_filtering_te,
|
| 848 |
+
"ur": parameters_filtering_ur,
|
| 849 |
+
"vi": parameters_filtering_vi,
|
| 850 |
+
"yo": parameters_filtering_yo,
|
| 851 |
+
"zh": parameters_filtering_zh,
|
| 852 |
+
}
|
stopwords.py
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|