Updated script and README.md

unixwzrd · unixwzrd · commit 69a11c578cbf · 2025-04-25T02:08:23.000-05:00
diff --git a/README.md b/README.md
@@ -40,6 +40,15 @@ options:
 python bin/cleanup-text.py <input_file>
 ```
 
+## What's in this repo:
+
+- [bin/cleanup-text.py](bin/cleanup-text.py) - The script that cleans up the text.
+- [setup.sh](setup.sh) - A script that sets up the environment to run the script.
+- [LICENSE](LICENSE) - The license for the project.
+- [README.md](README.md) - This file.
+- [requirements.txt](requirements.txt) - The dependencies for the project.
+- [data/](data/) - A directory with sample files full of unicode to test with.
+
 ## Coming SOon
 - macSO Shortcut
 
diff --git a/bin/cleanup-text.py b/bin/cleanup-text.py
@@ -1,10 +1,16 @@
 #!/usr/bin/env python3
-import sys
+#
 import argparse
 import re
+import sys
+
 from unidecode import unidecode
 
+
 def clean_text(text):
+    """
+    Clean Unicode quirks from text.
+    """
     replacements = {
         '\u2018': "'", '\u2019': "'",
         '\u201C': '"', '\u201D': '"',
@@ -15,6 +21,7 @@ def clean_text(text):
     text = re.sub(r'[\u200B\u200C\u200D\uFEFF]', '', text)
     return unidecode(text)
 
+
 def main():
     parser = argparse.ArgumentParser(description="Clean Unicode quirks from text.")
     parser.add_argument('infile', nargs='?', type=argparse.FileType('r'), default=sys.stdin,
@@ -27,5 +34,6 @@ def main():
     cleaned = clean_text(input_text)
     args.output.write(cleaned)
 
+
 if __name__ == '__main__':
-    main()
+    main()
