Added support for processing .xz and .gz files

Author: viragtripathi

README.md

@@ -38,7 +38,13 @@ A powerful CLI tool to extract, deduplicate, and analyze SQL logs for **Cockroac
 
 ## 📦 Installation
 
-### Option A: Local Dev Install
+### Option A: Quick Install from PyPI
+
+```bash
+pip install crdb-sql-audit
+```
+
+### Option B: Local Dev Install
 ```bash
 git clone https://github.com/your-org/crdb-sql-audit.git
 cd crdb-sql-audit
@@ -47,7 +53,7 @@ source venv/bin/activate
 pip install .
 ```
 
-### Option B: Build via `pyproject.toml`
+### Option C: Build via `pyproject.toml`
 ```bash
 python -m build
 pip install dist/crdb_sql_audit-0.2.0-py3-none-any.whl
@@ -139,6 +145,20 @@ split -b 50M sql_only.log chunks/sql_chunk_
 crdb-sql-audit --dir chunks --terms execute,pg_ --out output/report
 ```
 
+### 🗜 Supported Log Formats
+
+This tool automatically supports reading:
+
+* ✅ Regular `.log` or `.txt` files
+* ✅ Compressed files: `.gz`, `.xz`
+* ✅ Folders with mixed log formats
+
+You can pass these directly using `--file` or `--dir`:
+
+```bash
+crdb-sql-audit --file logs/app.log.gz --out output/report_from_gz
+```
+
 ## 📚 Rule Engine Format
 
 Rules are written in YAML and matched against each SQL line. Example:

crdb_sql_audit/audit.py

@@ -2,12 +2,22 @@
 import re
 import shutil
 import logging
+import gzip
+import lzma
 import importlib.resources as pkg_resources
 import pandas as pd
 import matplotlib.pyplot as plt
 
 from .rules_engine import load_rules, apply_rules
 
+def open_log_file(path):
+    if path.endswith(".gz"):
+        return gzip.open(path, "rt", encoding="utf-8", errors="ignore")
+    elif path.endswith(".xz"):
+        return lzma.open(path, "rt", encoding="utf-8", errors="ignore")
+    else:
+        return open(path, "r", encoding="utf-8", errors="ignore")
+
 def extract_sql(logs_path, search_terms, raw_mode=False):
     seen_sql = set()
 
@@ -20,7 +30,7 @@ def extract_sql(logs_path, search_terms, raw_mode=False):
 
     for path in paths:
         if os.path.isfile(path):
-            with open(path, "r", encoding="utf-8", errors="ignore") as f:
+            with open_log_file(path) as f:
                 for line in f:
                     if any(term in line for term in search_terms):
                         if raw_mode:

crdb_sql_audit/main.py

@@ -4,7 +4,7 @@
 import sys
 from crdb_sql_audit.audit import extract_sql, analyze_compatibility, generate_reports
 
-__version__ = "0.2.6"
+__version__ = "0.2.7"
 
 logging.basicConfig(
     level=logging.INFO,

pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "crdb-sql-audit"
-version = "0.2.6"
-description = "Analyze PostgreSQL SQL logs for CockroachDB compatibility"
+version = "0.2.7"
+description = "Analyze SQL logs for CockroachDB compatibility"
 authors = [
     { name = "Virag Tripathi", email = "virag.tripathi@gmail.com" }
 ]