chore(docs): Add a validation script for SQL reference

docs/reference/sql.md

@@ -1550,7 +1550,7 @@ Since: v0.2.
 SELECT ST_Translate(ST_GeomFromText('POINT(-71.01 42.37)'), 1, 2);
 ```
 
-## vST_UnaryUnion
+## ST_UnaryUnion
 
 This variant of ST_Union operates on a single geometry input. The input geometry can be a simple Geometry type, a MultiGeometry, or a GeometryCollection. The function calculates the geometric union across all components and elements within the provided geometry object.
 

docs/scripts/validate_sql.py

@@ -0,0 +1,75 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+import sedonadb
+import difflib
+from pathlib import Path
+
+HERE = Path(__file__).parent
+
+with open(HERE.parent / "reference" / "sql.md", "r") as f:
+    lines = f.readlines()
+    # Headers with `##` are the function names.
+    funs_in_doc = [line[3:-1] for line in lines if line.startswith("## ")]
+
+
+### Check if all the functions are documented
+
+sd = sedonadb.connect()
+df = sd.sql(r"""
+SELECT DISTINCT
+  routine_name,
+  function_type,
+  CASE substr(routine_name, 1, 2)
+    WHEN 'st' THEN 'vector'
+    WHEN 'rs' THEN 'raster'
+    ELSE 'unknown'
+  END AS data_type,
+  count(*) OVER (PARTITION BY description) > 1 as has_alias
+FROM information_schema.routines
+WHERE routine_type = 'FUNCTION' AND regexp_like(routine_name, '^(st_|rs_)')
+ORDER BY routine_name
+""").to_pandas()
+funs_in_impl_set = set(df["routine_name"].tolist())
+
+funs_in_doc_set = set(f.lower() for f in funs_in_doc)
+
+funs_only_in_impl = sorted(funs_in_impl_set - funs_in_doc_set)
+funs_only_in_doc = sorted(funs_in_doc_set - funs_in_impl_set)
+
+if funs_only_in_impl or funs_only_in_doc:
+    print("\nFunctions only in implementation:\n  - ", end="")
+    print("\n  - ".join(funs_only_in_impl))
+    print("\nFunctions only in document:\n  - ", end="")
+    print("\n  - ".join(funs_only_in_doc))
+    print("\n")
+
+    raise RuntimeError(
+        "There are some mismatch between the SQL reference and the actual implementation!"
+    )
+
+
+### Check if the function order is sorted
+
+if funs_in_doc != sorted(funs_in_doc):
+    diff = difflib.unified_diff(
+        funs_in_doc, sorted(funs_in_doc), fromfile="current", tofile="sorted"
+    )
+
+    print("\n".join(diff))
+
+    raise RuntimeError("The SQL functions are not sorted in alphabetical order")