From c457abd5f097dd13fb21543381e7cfafe7d31cfb Mon Sep 17 00:00:00 2001
From: Andi Albrecht <albrecht.andi@gmail.com>
Date: Mon, 20 Mar 2023 08:33:46 +0100
Subject: [PATCH] Remove unnecessary parts in regex for bad escaping.

The regex tried to deal with situations where escaping in the
SQL to be parsed was suspicious.

Upstream-Status: Backport
CVE: CVE-2023-30608

Reference to upstream patch:
https://github.com/andialbrecht/sqlparse/commit/c457abd5f097dd13fb21543381e7cfafe7d31cfb

[AZ: drop changes to CHANGELOG file and adjust context whitespaces]
Signed-off-by: Adrian Zaharia <Adrian.Zaharia@windriver.com>

Adjust indentation in keywords.py.
Signed-off-by: Joe Slater <joe.slater@windriver.com>
---
 sqlparse/keywords.py | 4 ++--
 tests/test_split.py  | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

--- sqlparse-0.4.3.orig/sqlparse/keywords.py
+++ sqlparse-0.4.3/sqlparse/keywords.py
@@ -72,9 +72,9 @@ SQL_REGEX = {
         (r'(?![_A-ZÀ-Ü])-?(\d+(\.\d*)|\.\d+)(?![_A-ZÀ-Ü])',
          tokens.Number.Float),
         (r'(?![_A-ZÀ-Ü])-?\d+(?![_A-ZÀ-Ü])', tokens.Number.Integer),
-        (r"'(''|\\\\|\\'|[^'])*'", tokens.String.Single),
+        (r"'(''|\\'|[^'])*'", tokens.String.Single),
         # not a real string literal in ANSI SQL:
-        (r'"(""|\\\\|\\"|[^"])*"', tokens.String.Symbol),
+        (r'"(""|\\"|[^"])*"', tokens.String.Symbol),
         (r'(""|".*?[^\\]")', tokens.String.Symbol),
         # sqlite names can be escaped with [square brackets]. left bracket
         # cannot be preceded by word character or a right bracket --
--- sqlparse-0.4.3.orig/tests/test_split.py
+++ sqlparse-0.4.3/tests/test_split.py
@@ -18,8 +18,8 @@ def test_split_semicolon():
 
 
 def test_split_backslash():
-    stmts = sqlparse.parse(r"select '\\'; select '\''; select '\\\'';")
-    assert len(stmts) == 3
+    stmts = sqlparse.parse("select '\'; select '\'';")
+    assert len(stmts) == 2
 
 
 @pytest.mark.parametrize('fn', ['function.sql',