python3-sqlparse: fix for CVE-2023-30608

sqlparse is a non-validating SQL parser module for Python. In affected
versions the SQL parser contains a regular expression that is vulnerable
to ReDoS (Regular Expression Denial of Service). This issue was introduced
by commit `e75e358`. The vulnerability may lead to Denial of Service (DoS).
This issues has been fixed in sqlparse 0.4.4 by commit `c457abd5f`. Users
are advised to upgrade. There are no known workarounds for this issue.

Signed-off-by: Narpat Mali <narpat.mali@windriver.com>
Signed-off-by: Armin Kuster <akuster808@gmail.com>

2 files changed, 76 insertions, 0 deletions

diff --git a/meta-python/recipes-devtools/python/python3-sqlparse/CVE-2023-30608.patch b/meta-python/recipes-devtools/python/python3-sqlparse/CVE-2023-30608.patch
new file mode 100644
index 0000000000..41dbf088e1
--- /dev/null
+++ b/meta-python/recipes-devtools/python/python3-sqlparse/CVE-2023-30608.patch
@@ -0,0 +1,75 @@
+From fa1cc25e1967228e5d47b9ddb626cc82dba92d7e Mon Sep 17 00:00:00 2001
+From: Andi Albrecht <albrecht.andi@gmail.com>
+Date: Wed, 31 May 2023 12:29:07 +0000
+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.
+
+CVE: CVE-2023-30608
+
+Upstream-Status: Backport [https://github.com/andialbrecht/sqlparse/commit/c457abd5f097dd13fb21543381e7cfafe7d31cfb]
+
+Signed-off-by: Narpat Mali <narpat.mali@windriver.com>
+---
+ CHANGELOG            | 15 +++++++++++++++
+ sqlparse/keywords.py |  4 ++--
+ tests/test_split.py  |  4 ++--
+ 3 files changed, 19 insertions(+), 4 deletions(-)
+
+diff --git a/CHANGELOG b/CHANGELOG
+index 65e03fc..a584003 100644
+--- a/CHANGELOG
++++ b/CHANGELOG
+@@ -1,3 +1,18 @@
++Backport CVE-2023-30608 Fix
++---------------------------
++
++Notable Changes
++
++* IMPORTANT: This release fixes a security vulnerability in the
++  parser where a regular expression vulnerable to ReDOS (Regular
++  Expression Denial of Service) was used. See the security advisory
++  for details: https://github.com/andialbrecht/sqlparse/security/advisories/GHSA-rrm6-wvj7-cwh2
++  The vulnerability was discovered by @erik-krogh from GitHub
++  Security Lab (GHSL). Thanks for reporting!
++
++* Fix regular expressions for string parsing.
++
++
+ Release 0.4.2 (Sep 10, 2021)
+ ----------------------------
+
+diff --git a/sqlparse/keywords.py b/sqlparse/keywords.py
+index 6850628..4e97477 100644
+--- a/sqlparse/keywords.py
++++ b/sqlparse/keywords.py
+@@ -66,9 +66,9 @@ 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 --
+diff --git a/tests/test_split.py b/tests/test_split.py
+index a9d7576..e79750e 100644
+--- a/tests/test_split.py
++++ b/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',
+--
+2.40.0
diff --git a/meta-python/recipes-devtools/python/python3-sqlparse_0.4.2.bb b/meta-python/recipes-devtools/python/python3-sqlparse_0.4.2.bb
index 0980ff9c24..b5cc41e730 100644
--- a/meta-python/recipes-devtools/python/python3-sqlparse_0.4.2.bb
+++ b/meta-python/recipes-devtools/python/python3-sqlparse_0.4.2.bb
@@ -6,6 +6,7 @@ LIC_FILES_CHKSUM = "file://LICENSE;md5=2b136f573f5386001ea3b7b9016222fc"
 
 SRC_URI += "file://0001-sqlparse-change-shebang-to-python3.patch \
             file://run-ptest \
+            file://CVE-2023-30608.patch \
             "
 
 SRC_URI[sha256sum] = "0c00730c74263a94e5a9919ade150dfc3b19c574389985446148402998287dae"