version: 1.0.66

Cargo.lock

@@ -55,6 +55,15 @@ version = "1.0.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5f0e0fee31ef5ed1ba1316088939cea399010ed7731dba877ed44aeb407a75ea"
 
+[[package]]
+name = "ar_archive_writer"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7eb93bbb63b9c227414f6eb3a0adfddca591a8ce1e9b60661bb08969b87e340b"
+dependencies = [
+ "object",
+]
+
 [[package]]
 name = "async-trait"
 version = "0.1.89"
@@ -874,6 +883,7 @@ dependencies = [
  "regex-syntax",
  "serde",
  "serde_json",
+ "sqlparser",
  "url",
  "uuid",
  "xxhash-rust",
@@ -1040,6 +1050,15 @@ dependencies = [
  "objc2-core-foundation",
 ]
 
+[[package]]
+name = "object"
+version = "0.37.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff76201f031d8863c38aa7f905eca4f53abbfa15f609db4277d44cd8938f33fe"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "once_cell"
 version = "1.21.3"
@@ -1377,6 +1396,16 @@ dependencies = [
  "unarray",
 ]
 
+[[package]]
+name = "psm"
+version = "0.1.30"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3852766467df634d74f0b2d7819bf8dc483a0eb2e3b0f50f756f9cfe8b0d18d8"
+dependencies = [
+ "ar_archive_writer",
+ "cc",
+]
+
 [[package]]
 name = "quick-error"
 version = "1.2.3"
@@ -1442,6 +1471,26 @@ dependencies = [
  "rand_core",
 ]
 
+[[package]]
+name = "recursive"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0786a43debb760f491b1bc0269fe5e84155353c67482b9e60d0cfb596054b43e"
+dependencies = [
+ "recursive-proc-macro-impl",
+ "stacker",
+]
+
+[[package]]
+name = "recursive-proc-macro-impl"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76009fbe0614077fc1a2ce255e3a1881a2e3a3527097d5dc6d8212c585e7e38b"
+dependencies = [
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "redox_syscall"
 version = "0.5.18"
@@ -1669,12 +1718,35 @@ dependencies = [
  "windows-sys 0.60.2",
 ]
 
+[[package]]
+name = "sqlparser"
+version = "0.61.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dbf5ea8d4d7c808e1af1cbabebca9a2abe603bcefc22294c5b95018d53200cb7"
+dependencies = [
+ "log",
+ "recursive",
+]
+
 [[package]]
 name = "stable_deref_trait"
 version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
 
+[[package]]
+name = "stacker"
+version = "0.1.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d74a23609d509411d10e2176dc2a4346e3b4aea2e7b1869f19fdedbc71c013"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "libc",
+ "psm",
+ "windows-sys 0.59.0",
+]
+
 [[package]]
 name = "stringprep"
 version = "0.1.5"
@@ -2323,6 +2395,15 @@ dependencies = [
  "windows-link",
 ]
 
+[[package]]
+name = "windows-sys"
+version = "0.59.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
+dependencies = [
+ "windows-targets 0.52.6",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.60.2"

Cargo.toml

@@ -23,6 +23,7 @@ indexmap = { version = "2.13.0", features = ["serde"] }
 moka = { version = "0.12.14", features = ["sync"] }
 xxhash-rust = { version = "0.8.15", features = ["xxh64"] }
 dashmap = "6.1.0"
+sqlparser = "0.61.0"
 
 [dev-dependencies]
 pgrx-tests = "0.16.1"
@@ -38,6 +39,10 @@ crate-type = ["cdylib", "lib"]
 name = "pgrx_embed_jspg"
 path = "src/bin/pgrx_embed.rs"
 
+[[bin]]
+name = "ast_explore"
+path = "src/bin/ast_explore.rs"
+
 [features]
 default = ["pg18"]
 pg18 = ["pgrx/pg18", "pgrx-tests/pg18" ]

fix_queryer.py

@@ -1,136 +0,0 @@
-import json
-
-file_path = "fixtures/queryer.json"
-with open(file_path, "r") as f:
-    data = json.load(f)
-
-# Find the test case
-test_case = next(tc for tc in data if tc.get("description") == "Base entity family select on polymorphic tree")
-
-# The sql is an array of strings
-expected_sql = test_case["expect"]["sql"][0]
-
-# We need to extract the entity block and move it
-# The blocks are delimited by "    WHEN t1_obj_t1.type = "
-# Actually, the easiest way is to re-build the expected_sql from the actual output logged,
-# or simply swap the entity block in the array strings.
-# But since we just want to reorder the WHEN clauses...
-
-# Let's just fix it by string manipulation or we can just replace the whole expect[sql][0] block
-new_sql = [
-    "(SELECT jsonb_build_object(",
-    "    'id', t1_obj_t1.id,",
-    "    'type', CASE WHEN t1_obj_t1.type = 'address' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'city', t1_obj_t1_obj_t1.city,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.address t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'contact' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t3.archived,",
-    "        'created_at', t1_obj_t1_obj_t3.created_at,",
-    "        'id', t1_obj_t1_obj_t3.id,",
-    "        'is_primary', t1_obj_t1_obj_t1.is_primary,",
-    "        'name', t1_obj_t1_obj_t3.name,",
-    "        'type', t1_obj_t1_obj_t3.type)",
-    "    FROM agreego.contact t1_obj_t1_obj_t1",
-    "    JOIN agreego.relationship t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    JOIN agreego.entity t1_obj_t1_obj_t3 ON t1_obj_t1_obj_t3.id = t1_obj_t1_obj_t2.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'email_address' THEN ((SELECT jsonb_build_object(",
-    "        'address', t1_obj_t1_obj_t1.address,",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.email_address t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'entity' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t1.archived,",
-    "        'created_at', t1_obj_t1_obj_t1.created_at,",
-    "        'id', t1_obj_t1_obj_t1.id,",
-    "        'name', t1_obj_t1_obj_t1.name,",
-    "        'type', t1_obj_t1_obj_t1.type)",
-    "    FROM agreego.entity t1_obj_t1_obj_t1",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'order' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'customer_id', t1_obj_t1_obj_t1.customer_id,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'total', t1_obj_t1_obj_t1.total,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.order t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'order_line' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'order_id', t1_obj_t1_obj_t1.order_id,",
-    "        'price', t1_obj_t1_obj_t1.price,",
-    "        'product', t1_obj_t1_obj_t1.product,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.order_line t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'organization' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.organization t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'person' THEN ((SELECT jsonb_build_object(",
-    "        'age', t1_obj_t1_obj_t1.age,",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'first_name', t1_obj_t1_obj_t1.first_name,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'last_name', t1_obj_t1_obj_t1.last_name,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.person t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'phone_number' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'number', t1_obj_t1_obj_t1.number,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.phone_number t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    WHEN t1_obj_t1.type = 'relationship' THEN ((SELECT jsonb_build_object(",
-    "        'archived', t1_obj_t1_obj_t2.archived,",
-    "        'created_at', t1_obj_t1_obj_t2.created_at,",
-    "        'id', t1_obj_t1_obj_t2.id,",
-    "        'name', t1_obj_t1_obj_t2.name,",
-    "        'type', t1_obj_t1_obj_t2.type)",
-    "    FROM agreego.relationship t1_obj_t1_obj_t1",
-    "    JOIN agreego.entity t1_obj_t1_obj_t2 ON t1_obj_t1_obj_t2.id = t1_obj_t1_obj_t1.id",
-    "    WHERE NOT t1_obj_t1_obj_t1.archived))",
-    "    ELSE NULL END)",
-    "FROM agreego.entity t1_obj_t1",
-    "WHERE NOT t1_obj_t1.archived)"
-]
-
-test_case["expect"]["sql"][0] = new_sql
-
-with open(file_path, "w") as f:
-    json.dump(data, f, indent=4)
-
-print("Fixed queryer.json expected sql array ordering.")
-

src/bin/ast_explore.rs

@@ -0,0 +1,17 @@
+use sqlparser::dialect::PostgreSqlDialect;
+use sqlparser::parser::Parser;
+use std::env;
+
+fn main() {
+    let sql = "SELECT t1_obj_t1_addresses_t1_target_t2.archived, t1.id FROM person t1 JOIN address t1_obj_t1_addresses ON true";
+    let dialect = PostgreSqlDialect {};
+    
+    match Parser::parse_sql(&dialect, sql) {
+        Ok(ast) => {
+            println!("{:#?}", ast);
+        }
+        Err(e) => {
+            println!("Error: {:?}", e);
+        }
+    }
+}

src/tests/mod.rs

@@ -2,6 +2,7 @@ use crate::*;
 pub mod runner;
 pub mod types;
 use serde_json::json;
+pub mod sql_validator;
 
 // Database module tests moved to src/database/executors/mock.rs
 

src/tests/sql_validator.rs

@@ -0,0 +1,156 @@
+use sqlparser::ast::{
+    Expr, Join, JoinConstraint, JoinOperator, Query, Select, SelectItem, SetExpr, Statement,
+    TableFactor, TableWithJoins, Ident,
+};
+use sqlparser::dialect::PostgreSqlDialect;
+use sqlparser::parser::Parser;
+use std::collections::HashSet;
+
+pub fn validate_semantic_sql(sql: &str) -> Result<(), String> {
+    let dialect = PostgreSqlDialect {};
+    let statements = match Parser::parse_sql(&dialect, sql) {
+        Ok(s) => s,
+        Err(e) => return Err(format!("SQL Syntax Error: {}\nSQL: {}", e, sql)),
+    };
+
+    for statement in statements {
+        validate_statement(&statement, sql)?;
+    }
+
+    Ok(())
+}
+
+fn validate_statement(stmt: &Statement, original_sql: &str) -> Result<(), String> {
+    match stmt {
+        Statement::Query(query) => validate_query(query, original_sql)?,
+        Statement::Insert(insert) => {
+            if let Some(query) = &insert.source {
+                 validate_query(query, original_sql)?
+            }
+        }
+        Statement::Update(update) => {
+            if let Some(expr) = &update.selection {
+                validate_expr(expr, &HashSet::new(), original_sql)?;
+            }
+        }
+        Statement::Delete(delete) => {
+            if let Some(expr) = &delete.selection {
+                validate_expr(expr, &HashSet::new(), original_sql)?;
+            }
+        }
+        _ => {}
+    }
+    Ok(())
+}
+
+fn validate_query(query: &Query, original_sql: &str) -> Result<(), String> {
+    if let SetExpr::Select(select) = &*query.body {
+        validate_select(select, original_sql)?;
+    }
+    Ok(())
+}
+
+fn validate_select(select: &Select, original_sql: &str) -> Result<(), String> {
+    let mut available_aliases = HashSet::new();
+
+    // 1. Collect all declared table aliases in the FROM clause and JOINs
+    for table_with_joins in &select.from {
+        collect_aliases_from_table_factor(&table_with_joins.relation, &mut available_aliases);
+        for join in &table_with_joins.joins {
+            collect_aliases_from_table_factor(&join.relation, &mut available_aliases);
+        }
+    }
+
+    // 2. Validate all SELECT projection fields
+    for projection in &select.projection {
+        if let SelectItem::UnnamedExpr(expr) | SelectItem::ExprWithAlias { expr, .. } = projection {
+            validate_expr(expr, &available_aliases, original_sql)?;
+        }
+    }
+
+    // 3. Validate ON conditions in joins 
+    for table_with_joins in &select.from {
+        for join in &table_with_joins.joins {
+            if let JoinOperator::Inner(JoinConstraint::On(expr))
+            | JoinOperator::LeftOuter(JoinConstraint::On(expr))
+            | JoinOperator::RightOuter(JoinConstraint::On(expr))
+            | JoinOperator::FullOuter(JoinConstraint::On(expr))
+            | JoinOperator::Join(JoinConstraint::On(expr)) = &join.join_operator
+            {
+                validate_expr(expr, &available_aliases, original_sql)?;
+            }
+        }
+    }
+
+    // 4. Validate WHERE conditions
+    if let Some(selection) = &select.selection {
+        validate_expr(selection, &available_aliases, original_sql)?;
+    }
+
+    Ok(())
+}
+
+fn collect_aliases_from_table_factor(tf: &TableFactor, aliases: &mut HashSet<String>) {
+    match tf {
+        TableFactor::Table { name, alias, .. } => {
+            if let Some(table_alias) = alias {
+                aliases.insert(table_alias.name.value.clone());
+            } else if let Some(last) = name.0.last() {
+                 match last {
+                     sqlparser::ast::ObjectNamePart::Identifier(i) => {
+                         aliases.insert(i.value.clone());
+                     }
+                     _ => {}
+                 }
+            }
+        }
+        TableFactor::Derived { alias: Some(table_alias), .. } => {
+            aliases.insert(table_alias.name.value.clone());
+        }
+        _ => {}
+    }
+}
+
+fn validate_expr(expr: &Expr, available_aliases: &HashSet<String>, sql: &str) -> Result<(), String> {
+    match expr {
+        Expr::CompoundIdentifier(idents) => {
+            if idents.len() == 2 {
+                let alias = &idents[0].value;
+                if !available_aliases.is_empty() && !available_aliases.contains(alias) {
+                    return Err(format!(
+                        "Semantic Error: Orchestrated query referenced table alias '{}' but it was not declared in the query's FROM/JOIN clauses.\nAvailable aliases: {:?}\nSQL: {}",
+                        alias, available_aliases, sql
+                    ));
+                }
+            } else if idents.len() > 2 {
+                let alias = &idents[1].value; // In form schema.table.column, 'table' is idents[1]
+                if !available_aliases.is_empty() && !available_aliases.contains(alias) {
+                    return Err(format!(
+                        "Semantic Error: Orchestrated query referenced table '{}' but it was not mapped.\nAvailable aliases: {:?}\nSQL: {}",
+                        alias, available_aliases, sql
+                    ));
+                }
+            }
+        }
+        Expr::BinaryOp { left, right, .. } => {
+            validate_expr(left, available_aliases, sql)?;
+            validate_expr(right, available_aliases, sql)?;
+        }
+        Expr::IsFalse(e) | Expr::IsNotFalse(e) | Expr::IsTrue(e) | Expr::IsNotTrue(e) 
+        | Expr::IsNull(e) | Expr::IsNotNull(e) | Expr::InList { expr: e, .. }
+        | Expr::Nested(e) | Expr::UnaryOp { expr: e, .. } | Expr::Cast { expr: e, .. }
+        | Expr::Like { expr: e, .. } | Expr::ILike { expr: e, .. } | Expr::AnyOp { left: e, .. }
+        | Expr::AllOp { left: e, .. } => {
+             validate_expr(e, available_aliases, sql)?;
+        }
+        Expr::Function(func) => {
+            if let sqlparser::ast::FunctionArguments::List(args) = &func.args {
+                if let Some(sqlparser::ast::FunctionArg::Unnamed(sqlparser::ast::FunctionArgExpr::Expr(e))) = args.args.get(0) {
+                    validate_expr(e, available_aliases, sql)?;
+                }
+            }
+        }
+        _ => {}
+    }
+    Ok(())
+}

src/tests/types/expect.rs

@@ -39,6 +39,12 @@ impl ExpectBlock {
       ));
     }
 
+    for query in actual {
+      if let Err(e) = crate::tests::sql_validator::validate_semantic_sql(query) {
+        return Err(e);
+      }
+    }
+
     let ws_re = Regex::new(r"\s+").unwrap();
 
     let types = HashMap::from([

version

@@ -1 +1 @@
-1.0.65
+1.0.66