From e1cb78d5a1e5bea14041a52af88d1ee1e80be7cf Mon Sep 17 00:00:00 2001
From: Lukas Plank <lupl@tuta.io>
Date: Mon, 28 Oct 2024 14:01:19 +0100
Subject: [PATCH] fix: correct regex pattern for SELECT clause extraction

The new regex non-greedily matches everything after "select" and before "where".

"[\s\S]*?" basically means ".*?" but is more general because it also
matches linebreaks without the re.DOTALL flag.
See https://docs.python.org/3/library/re.html#re.DOTALL.

Fixes #122.
---
 rdfproxy/utils/sparql_utils.py | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/rdfproxy/utils/sparql_utils.py b/rdfproxy/utils/sparql_utils.py
index b76cb45..799f8d4 100644
--- a/rdfproxy/utils/sparql_utils.py
+++ b/rdfproxy/utils/sparql_utils.py
@@ -20,21 +20,21 @@
 """)
 
 
-def replace_query_select_clause(query: str, repl: str) -> str:
+def replace_query_select_clause(query: str, repl: str):
     """Replace the SELECT clause of a query with repl."""
-    if re.search(r"select\s.+", query, re.I) is None:
+    pattern = r"(select\s+[\s\S]*?)(?=\s+where)"
+
+    if re.search(pattern=pattern, string=query, flags=re.IGNORECASE) is None:
         raise Exception("Unable to obtain SELECT clause.")
 
-    count_query = re.sub(
-        pattern=r"select\s.+",
+    return re.sub(
+        pattern=pattern,
         repl=repl,
         string=query,
         count=1,
-        flags=re.I,
+        flags=re.IGNORECASE,
     )
 
-    return count_query
-
 
 def construct_count_query(query: str, model: type[_TModelInstance]) -> str:
     """Construct a generic count query from a SELECT query."""