sonatoki 0.8.3__tar.gz → 0.8.4__tar.gz

{sonatoki-0.8.3 → sonatoki-0.8.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sonatoki
-Version: 0.8.3
+Version: 0.8.4
 Summary: ilo li moku e toki li pana e sona ni: ni li toki ala toki pona?
 Author-Email: "jan Kekan San (@gregdan3)" <gregory.danielson3@gmail.com>
 License: AGPL-3.0-or-later

{sonatoki-0.8.3 → sonatoki-0.8.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sonatoki"
-version = "0.8.3"
+version = "0.8.4"
 description = "ilo li moku e toki li pana e sona ni: ni li toki ala toki pona?"
 authors = [
     { name = "jan Kekan San (@gregdan3)", email = "gregory.danielson3@gmail.com" },

{sonatoki-0.8.3 → sonatoki-0.8.4}/src/sonatoki/Preprocessors.py

@@ -83,6 +83,19 @@ class MarkdownURLs(RegexPreprocessor):
     replace = r"\1"
 
 
+class Emails(RegexPreprocessor):
+    """Attempt to remove emails, for a particularly strong definition of
+    "email".
+
+    https://www.regular-expressions.info/email.html
+    """
+
+    pattern = re.compile(
+        r"\b[a-zA-Z0-9._%+-]{2,}@[a-zA-Z0-9.-]{2,}\.[a-zA-Z]{2,24}\b",
+        flags=re.IGNORECASE,
+    )
+
+
 class Reference(RegexPreprocessor):
     """Remove text contained in double brackets.
 
@@ -228,6 +241,7 @@ RECOMMENDED_PREPROCESSORS: List[Type[Preprocessor]] = [
     Reference,
     MarkdownURLs,
     URLs,
+    Emails,
     Emoji,
 ]
 
@@ -242,6 +256,7 @@ __all__ = [
     "DiscordMentions",
     "DiscordSpecial",
     "DoubleQuotes",
+    "Emails",
     "Emoji",
     "MarkdownURLs",
     "RECOMMENDED_PREPROCESSORS",

{sonatoki-0.8.3 → sonatoki-0.8.4}/tests/test_preprocessors.py

@@ -24,6 +24,7 @@ from sonatoki.Preprocessors import (
     DiscordMentions,
     AngleBracketObject,
 )
+from src.sonatoki.Preprocessors import Emails
 
 
 def extract_bracket_content(markdown_text: str) -> Optional[str]:
@@ -31,7 +32,7 @@ def extract_bracket_content(markdown_text: str) -> Optional[str]:
     if start == -1:
         return None
 
-    end = markdown_text.rfind("]")
+    end = markdown_text.find("](")
     if end == -1 or end <= start:
         return None
 
@@ -54,11 +55,19 @@ def test_URLs(s: str):
 @example("[[] silly mode activated](https://discord.gg/)")
 @example("[https://example.com/](http://example.com)")
 @example("[192.168.0.255](http://localhost:80)")
+@example("[text](https://bad.worse]/)")
 def test_MarkdownURLs(s: str):
     bracket_content = extract_bracket_content(s)
     assert MarkdownURLs.process(s) == bracket_content
 
 
+@given(st.from_regex(Emails.pattern, fullmatch=True))
+@example("mun@pona.la")
+@example("tokipona@alinome.com")
+def test_Emails(s: str):
+    assert Emails.process(s).strip() == ""
+
+
 @given(st.from_regex(Spoilers.pattern, fullmatch=True))
 @example("|| | ||")
 @example("|| content\n\n\ncontent ||")