Added support for processing .xz and .gz files

Author: viragtripathi

README.md

@@ -165,14 +165,16 @@ Rules are written in YAML and matched against each SQL line. Example:
 > 💡 This is also the default rule if you don't provide `--rules` param.
 
 ```yaml
+# postgres_to_crdb.yaml — Comprehensive CRDB Compatibility Rules based on https://www.cockroachlabs.com/docs/v25.2/sql-feature-support
+
 - id: malformed_dml_statements
   match: '^(SELECT|INSERT|UPDATE|DELETE FROM)\s*$'
   message: "Possibly malformed or incomplete SQL statement"
   level: warning
   tags: [syntax]
 
 - id: special_char_in_identifier
-  match: '"[^"]*#\w*"'
+  match: '"[^\"]*#\w*"'
   message: "Table name contains unsupported special character (#)"
   level: error
   tags: [table, identifier]
@@ -183,11 +185,65 @@ Rules are written in YAML and matched against each SQL line. Example:
   level: error
   tags: [function]
 
-#- id: low_token_sql
-  #match: '^(\S+\s*){1,2}$'
-  #message: "Extremely short SQL likely malformed"
-  #level: warning
-  #tags: [syntax]
+- id: with_cte
+  match: '^\s*WITH\s+'
+  message: "CTE (WITH clause) detected"
+  level: warning
+  tags: [cte, syntax]
+
+- id: upsert_syntax
+  match: '^\s*UPSERT\s+'
+  message: "UPSERT syntax (CockroachDB supports but should be reviewed)"
+  level: info
+  tags: [upsert, insert]
+
+- id: json_ops
+  match: '->|->>|::json[b]?'  # Look for JSON navigation or cast
+  message: "JSON/JSONB usage detected"
+  level: info
+  tags: [json]
+
+- id: row_values
+  match: '\(.*\).*IN\s*\('  # e.g., WHERE (a, b) IN ((1, 2))
+  message: "ROW VALUES in IN clause"
+  level: warning
+  tags: [rowvalues, comparison]
+
+- id: window_function
+  match: '\bOVER\s*\('
+  message: "Window function usage (e.g., RANK, ROW_NUMBER)"
+  level: info
+  tags: [window, analytics]
+
+- id: set_ops
+  match: '\s+(UNION|INTERSECT|EXCEPT)\s+'
+  message: "Set operation (UNION, INTERSECT, EXCEPT)"
+  level: info
+  tags: [setops]
+
+- id: case_expr
+  match: '\bCASE\b.*\bWHEN\b.*\bTHEN\b'
+  message: "CASE expression detected"
+  level: info
+  tags: [case, conditional]
+
+- id: time_interval
+  match: 'INTERVAL\s+[''\"]'
+  message: "TIME INTERVAL expression"
+  level: info
+  tags: [interval, time]
+
+- id: group_by_rollup
+  match: 'GROUP BY ROLLUP\('
+  message: "ROLLUP clause used"
+  level: warning
+  tags: [aggregation, rollup]
+
+- id: filter_clause
+  match: 'FILTER\s*\(\s*WHERE'
+  message: "FILTER clause used in aggregation"
+  level: warning
+  tags: [aggregation, filter]
 ```
 
 > 📦 Multiple rule sets can be created to target different SQL dialects (e.g., `postgres_to_crdb.yaml`, `mysql_to_crdb.yaml`, etc.)