From 2bdc7ee91736b44b9b4e8e61ea6081b5b1a99b68 Mon Sep 17 00:00:00 2001
From: Test User <test@example.com>
Date: Sat, 7 Feb 2026 17:45:08 -0600
Subject: [PATCH] Fix tokenization of escaped backslashes in SQL string
 literals (issue #814)

The regex pattern for matching single-quoted strings did not handle
escaped backslashes (\) properly. This caused strings like '\', '\'
to be incorrectly tokenized as a single string with a comma instead of
two separate string literals.

Changes:
- Add \\ to the string literal patterns in SQL_REGEX to match
  escaped backslashes as valid content within string literals
- Add test case for escaped backslash tokenization

Fixes #814
---
 sqlparse/keywords.py   |  4 ++--
 tests/test_tokenize.py | 15 +++++++++++++++
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/sqlparse/keywords.py b/sqlparse/keywords.py
index 874431f4..64834437 100644
--- a/sqlparse/keywords.py
+++ b/sqlparse/keywords.py
@@ -59,9 +59,9 @@
     (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 --
diff --git a/tests/test_tokenize.py b/tests/test_tokenize.py
index e368e83e..f22bf9f0 100644
--- a/tests/test_tokenize.py
+++ b/tests/test_tokenize.py
@@ -99,6 +99,21 @@ def test_single_quotes():
     assert repr(p.tokens[0])[:len(tst)] == tst
 
 
+def test_single_quotes_escaped_backslash():
+    # issue 814 - Incorrect Tokenization of Escaped Backslashes
+    # A string containing an escaped backslash (\\) should be tokenized
+    # as a single string literal, not split incorrectly.
+    sql = r"SELECT '\\', '\\'"
+    tokens = list(lexer.tokenize(sql))
+    # Should be: SELECT, ws, '\\', ,, ws, '\\'
+    assert tokens[0] == (T.Keyword.DML, 'SELECT')
+    assert tokens[1] == (T.Whitespace, ' ')
+    assert tokens[2] == (T.String.Single, "'\\\\'")
+    assert tokens[3] == (T.Punctuation, ',')
+    assert tokens[4] == (T.Whitespace, ' ')
+    assert tokens[5] == (T.String.Single, "'\\\\'")
+
+
 def test_tokenlist_first():
     p = sqlparse.parse(' select foo')[0]
     first = p.token_first()