redaction 0.1.1__py3-none-any.whl

redaction/__init__.py

@@ -0,0 +1,3 @@
+"""PII redaction package using Microsoft Presidio."""
+
+__version__ = "0.1.1"

redaction/cli.py

@@ -0,0 +1,130 @@
+"""
+PII redaction script using Microsoft Presidio.
+Processes a file line by line and creates an output file with redacted content.
+"""
+
+import argparse
+import sys
+from pathlib import Path
+
+# Import Presidio
+try:
+    from presidio_analyzer import AnalyzerEngine
+    from presidio_anonymizer import AnonymizerEngine
+except ImportError:
+    print("Please install presidio: pip install presidio-analyzer presidio-anonymizer")
+    sys.exit(1)
+
+# Import rich_argparse for better CLI output
+try:
+    from rich_argparse import RichHelpFormatter
+except ImportError:
+    print("Please install rich_argparse: pip install rich-argparse")
+    RichHelpFormatter = argparse.RawDescriptionHelpFormatter
+
+
+class PresidioRedactor:
+    """Handles PII redaction using Microsoft Presidio."""
+
+    def __init__(self):
+        """Initialize Presidio engines."""
+        self.presidio_analyzer = AnalyzerEngine()
+        self.presidio_anonymizer = AnonymizerEngine()
+
+    def redact(self, text):
+        """Redact PII using Microsoft Presidio."""
+        # Analyze the text for PII
+        results = self.presidio_analyzer.analyze(text=text, language="en")
+
+        # Anonymize the detected PII if any found
+        if results:
+            anonymized = self.presidio_anonymizer.anonymize(
+                text=text, analyzer_results=results
+            )
+            return anonymized.text
+        return text
+
+    def process_file(self, input_file, output_file=None):
+        """Process a file line by line using Presidio."""
+        input_path = Path(input_file)
+        if not input_path.exists():
+            print(f"Error: Input file '{input_file}' not found.")
+            return False
+
+        # Determine output file name
+        output_path = Path(output_file or f"{input_path.stem}_redacted.txt")
+
+        print(f"Processing file: {input_path}")
+        print(f"Output file: {output_path}\n")
+
+        # Process the file
+        with open(input_path, "r", encoding="utf-8") as infile, \
+             open(output_path, "w", encoding="utf-8") as outfile:
+
+            line_count = 0
+            for line_num, line in enumerate(infile, 1):
+                line_content = line.rstrip("\n")
+
+                # Handle empty lines
+                if not line_content:
+                    outfile.write("\n")
+                    continue
+
+                line_count += 1
+
+                # Apply Presidio redaction and write output
+                outfile.write(self.redact(line_content) + "\n")
+
+                # Progress indicator for large files
+                if line_num % 100 == 0:
+                    print(f"  Processed {line_num} lines...")
+
+            print(f"\nSuccessfully processed {line_count} non-empty lines.")
+            return True
+
+
+def main():
+    """Main function to handle command-line arguments and run the redactor."""
+    parser = argparse.ArgumentParser(
+        prog="redact",
+        description="🕵️‍♂️ Redact PII from text files using Microsoft Presidio.",
+        formatter_class=RichHelpFormatter,
+        epilog="""
+Examples:
+  redact input.txt
+  redact input.txt -o cleaned.txt
+  redact sensitive_data.txt -o /path/to/output/safe_data.txt
+
+The script uses Microsoft Presidio to detect and redact personally identifiable information (PII)
+including names, email addresses, phone numbers, SSNs, credit card numbers, and more.
+        """,
+    )
+
+    parser.add_argument(
+        "input_file",
+        metavar="FILE",
+        help="Path to the input file to be redacted"
+    )
+    parser.add_argument(
+        "-o",
+        "--output",
+        dest="output_file",
+        metavar="OUTPUT",
+        help="Output file name (default: <input>_redacted.txt)",
+    )
+
+    args = parser.parse_args()
+
+    # Initialize the redactor and process the file
+    print("Initializing Presidio...\n")
+    redactor = PresidioRedactor()
+
+    if redactor.process_file(args.input_file, args.output_file):
+        print("\nRedaction complete!")
+        print("Note: Always manually review the output file to ensure all sensitive data has been properly redacted.")
+    else:
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

redaction-0.1.1.dist-info/METADATA

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: redaction
+Version: 0.1.1
+Summary: Simple redaction script
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+Requires-Dist: presidio-analyzer>=2.2.360
+Requires-Dist: presidio-anonymizer>=2.2.360
+Requires-Dist: rich-argparse>=1.7.1
+
+# 🕵️ PII Redaction Tool
+
+A no-nonsense (but kinda cool) script that wipes out personal info from text files using **Microsoft Presidio**.
+
+Does not require Torch.
+
+Tried **scrubadub** and **pii-codex**, but they didn't quite pass the vibe check — so this one gets the job done.
+
+## 🚀 Usage
+
+```bash
+pip install redaction
+
+redact file.txt
+redact file.txt -o output.txt
+redact --help
+```
+
+* By default, the redacted version lands in the same directory as your input file.
+* Use the `-o` flag to specify your own output file.
+
+## ⚙️ Installation
+
+With [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv sync
+```
+
+Or the classic pip way:
+
+```bash
+pip install -e .
+```
+
+Then you're ready to redact like a pro.
+All detected PII gets anonymized and saved into a clean, single output file — powered by **Microsoft Presidio** 🧠.
+
+<br>

redaction-0.1.1.dist-info/RECORD

@@ -0,0 +1,7 @@
+redaction/__init__.py,sha256=TwRdNaC8ErWwxAGKH6nNtjrUCd1SIHcku6ua8wxT2p4,77
+redaction/cli.py,sha256=hXTC3gQkug3LKSmbN-YSQZXPhqUuvs4NhH4pgtwkHrg,4136
+redaction-0.1.1.dist-info/METADATA,sha256=GlvKqoaG2dBkq1I-bnSenQi87gBMm_-E4TLtHR1JE5w,1113
+redaction-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+redaction-0.1.1.dist-info/entry_points.txt,sha256=F2LuWAksmF1UvO1gwxNkqh5oeF07FWYLijCckBwoGzk,46
+redaction-0.1.1.dist-info/top_level.txt,sha256=VkZVTpgmoHK91-NVsRfo1uB4b7f0FX0MSAi1H5CRk4o,10
+redaction-0.1.1.dist-info/RECORD,,

redaction-0.1.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

redaction-0.1.1.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+redact = redaction.cli:main

redaction-0.1.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+redaction