publish

TelechaBot · May 14, 2024 · e13ab8c · e13ab8c
1 parent 290c13c
commit e13ab8c
Show file tree

Hide file tree

Showing 13 changed files with 34 additions and 12 deletions.
diff --git a/playground/usage.py b/playground/usage.py
@@ -1,6 +1,6 @@
 import io
 
-from cleanse_speech import DLFA
+from cleanse_speech.dlfa import DLFA
 
 if __name__ == '__main__':
     dfa = DLFA(words_resource=[

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "cleanse-speech"
-version = "0.1.0"
+version = "0.1.1"
 description = "An intelligent Python library designed to detect and filter offensive language, ensuring respectful and constructive communication in any digital space."
 authors = [
     { name = "llmkira", email = "me@dianas.cyou" },

diff --git a/src/cleanse-speech/__init__.py b/src/cleanse-speech/__init__.py
diff --git a/src/cleanse_speech/__init__.py b/src/cleanse_speech/__init__.py
@@ -0,0 +1,7 @@
+from .bookshelf import SpamShelf
+from .dlfa import DLFA
+
+__all__ = [
+    'DLFA',
+    'SpamShelf',
+]
diff --git a/src/cleanse-speech/bin/cn_advertisement.bin → src/cleanse_speech/bin/cn_advertisement.bin b/src/cleanse-speech/bin/cn_advertisement.bin → src/cleanse_speech/bin/cn_advertisement.bin
diff --git a/src/cleanse-speech/bin/cn_general.bin → src/cleanse_speech/bin/cn_general.bin b/src/cleanse-speech/bin/cn_general.bin → src/cleanse_speech/bin/cn_general.bin
diff --git a/src/cleanse-speech/bin/cn_netease.bin → src/cleanse_speech/bin/cn_netease.bin b/src/cleanse-speech/bin/cn_netease.bin → src/cleanse_speech/bin/cn_netease.bin
diff --git a/src/cleanse-speech/bin/cn_politics.bin → src/cleanse_speech/bin/cn_politics.bin b/src/cleanse-speech/bin/cn_politics.bin → src/cleanse_speech/bin/cn_politics.bin
diff --git a/src/cleanse-speech/bin/cn_pornographic.bin → src/cleanse_speech/bin/cn_pornographic.bin b/src/cleanse-speech/bin/cn_pornographic.bin → src/cleanse_speech/bin/cn_pornographic.bin
diff --git a/src/cleanse-speech/bookshelf.py → src/cleanse_speech/bookshelf.py b/src/cleanse-speech/bookshelf.py → src/cleanse_speech/bookshelf.py
diff --git a/src/cleanse-speech/dlfa.py → src/cleanse_speech/dlfa.py b/src/cleanse-speech/dlfa.py → src/cleanse_speech/dlfa.py
diff --git a/tests/__init__.py b/tests/__init__.py
@@ -1,3 +0,0 @@
-
-
-

diff --git a/tests/test_dfa.py b/tests/test_dfa.py
@@ -0,0 +1,25 @@
+import io
+
+import pytest
+
+from cleanse_speech import DLFA
+
+
+@pytest.fixture
+def test_censor():
+    dfa = DLFA(words_resource=[
+        ['你好'],
+        io.BytesIO(b'sensitive'),
+    ])
+    assert dfa.censor_text('This is a 你好 word.', 10) == 'This is a ** word.'
+    assert dfa.censor_text('This is a sensitive word.', 10) == 'This is a ********* word.'
+
+
+def test_contains_illegal():
+    dfa = DLFA(words_resource=[
+        ['你好'],
+        io.BytesIO(b'sensitive'),
+    ])
+    assert dfa.contains_illegal('This is a 你好 word.')
+    assert dfa.contains_illegal('This is a sensitive word.')
+    assert not dfa.contains_illegal('This is a normal word.')