Compare commits
8 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 885b9b5e44 | |||
| 298645ffdb | |||
| 330280ba48 | |||
| 02e661d219 | |||
| f7163e2689 | |||
| 091007006d | |||
| 3d66a7fc3c | |||
| e1314496dd |
5
.vscode/extensions.json
vendored
Normal file
5
.vscode/extensions.json
vendored
Normal file
@ -0,0 +1,5 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"rust-lang.rust-analyzer"
|
||||
]
|
||||
}
|
||||
@ -43,7 +43,7 @@ JSPG implements specific extensions to the Draft 2020-12 standard to support the
|
||||
#### A. Polymorphism & Referencing (`$ref`, `$family`, and Native Types)
|
||||
* **Native Type Discrimination (`variations`)**: Schemas defined inside a Postgres `type` are Entities. The validator securely and implicitly manages their `"type"` property. If an entity inherits from `user`, incoming JSON can safely define `{"type": "person"}` without errors, thanks to `compiled_variations` inheritance.
|
||||
* **Structural Inheritance & Viral Infection (`$ref`)**: `$ref` is used exclusively for structural inheritance, *never* for union creation. A Punc request schema that `$ref`s an Entity virally inherits all physical database polymorphism rules for that target.
|
||||
* **Shape Polymorphism (`$family`)**: Auto-expands polymorphic API lists based on an abstract Descendants Graph. If `{"$family": "widget"}` is used, JSPG evaluates the JSON against every schema that `$ref`s widget.
|
||||
* **Shape Polymorphism (`$family`)**: Auto-expands polymorphic API lists based on an abstract **Descendants Graph**. If `{"$family": "widget"}` is used, the Validator dynamically identifies *every* schema in the registry that `$ref`s `widget` (e.g., `stock.widget`, `task.widget`) and evaluates the JSON against all of them.
|
||||
* **Strict Matches & Depth Heuristic**: Polymorphic structures MUST match exactly **one** schema permutation. If multiple inherited struct permutations pass, JSPG applies the **Depth Heuristic Tie-Breaker**, selecting the candidate deepest in the inheritance tree.
|
||||
|
||||
#### B. Dot-Notation Schema Resolution & Database Mapping
|
||||
@ -103,6 +103,10 @@ The Queryer transforms Postgres into a pre-compiled Semantic Query Engine via th
|
||||
* **Array Inclusion**: `{"$in": [values]}`, `{"$nin": [values]}` use native `jsonb_array_elements_text()` bindings to enforce `IN` and `NOT IN` logic without runtime SQL injection risks.
|
||||
* **Text Matching (ILIKE)**: Evaluates `$eq` or `$ne` against string fields containing the `%` character natively into Postgres `ILIKE` and `NOT ILIKE` partial substring matches.
|
||||
* **Type Casting**: Safely resolves dynamic combinations by casting values instantly into the physical database types mapped in the schema (e.g. parsing `uuid` bindings to `::uuid`, formatting DateTimes to `::timestamptz`, and numbers to `::numeric`).
|
||||
* **Polymorphic SQL Generation (`$family`)**: Compiles `$family` properties by analyzing the **Physical Database Variations**, *not* the schema descendants.
|
||||
* **The Dot Convention**: When a schema requests `$family: "target.schema"`, the compiler extracts the base type (e.g. `schema`) and looks up its Physical Table definition.
|
||||
* **Multi-Table Branching**: If the Physical Table is a parent to other tables (e.g. `organization` has variations `["organization", "bot", "person"]`), the compiler generates a dynamic `CASE WHEN type = '...' THEN ...` query, expanding into `JOIN`s for each variation.
|
||||
* **Single-Table Bypass**: If the Physical Table is a leaf node with only one variation (e.g. `person` has variations `["person"]`), the compiler cleanly bypasses `CASE` generation and compiles a simple `SELECT` across the base table, as all schema extensions (e.g. `light.person`, `full.person`) are guaranteed to reside in the exact same physical row.
|
||||
|
||||
### The Stem Engine
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -32,7 +32,7 @@ pub struct Database {
|
||||
pub enums: HashMap<String, Enum>,
|
||||
pub types: HashMap<String, Type>,
|
||||
pub puncs: HashMap<String, Punc>,
|
||||
pub relations: HashMap<String, Relation>,
|
||||
pub relations: HashMap<(String, String), Vec<Relation>>,
|
||||
pub schemas: HashMap<String, Schema>,
|
||||
// Map of Schema ID -> { Entity Type -> Target Subschema Arc }
|
||||
pub stems: HashMap<String, HashMap<String, Arc<Stem>>>,
|
||||
@ -74,11 +74,12 @@ impl Database {
|
||||
}
|
||||
}
|
||||
|
||||
let mut raw_relations = Vec::new();
|
||||
if let Some(arr) = val.get("relations").and_then(|v| v.as_array()) {
|
||||
for item in arr {
|
||||
match serde_json::from_value::<Relation>(item.clone()) {
|
||||
Ok(def) => {
|
||||
db.relations.insert(def.constraint.clone(), def);
|
||||
raw_relations.push(def);
|
||||
}
|
||||
Err(e) => println!("DATABASE RELATION PARSE FAILED: {:?}", e),
|
||||
}
|
||||
@ -107,7 +108,7 @@ impl Database {
|
||||
}
|
||||
}
|
||||
|
||||
db.compile()?;
|
||||
db.compile(raw_relations)?;
|
||||
Ok(db)
|
||||
}
|
||||
|
||||
@ -138,10 +139,11 @@ impl Database {
|
||||
}
|
||||
|
||||
/// Organizes the graph of the database, compiling regex, format functions, and caching relationships.
|
||||
pub fn compile(&mut self) -> Result<(), crate::drop::Drop> {
|
||||
pub fn compile(&mut self, raw_relations: Vec<Relation>) -> Result<(), crate::drop::Drop> {
|
||||
self.collect_schemas();
|
||||
self.collect_depths();
|
||||
self.collect_descendants();
|
||||
self.collect_relations(raw_relations);
|
||||
self.compile_schemas();
|
||||
self.collect_stems()?;
|
||||
|
||||
@ -226,6 +228,95 @@ impl Database {
|
||||
self.descendants = descendants;
|
||||
}
|
||||
|
||||
fn collect_relations(&mut self, raw_relations: Vec<Relation>) {
|
||||
let mut edges: HashMap<(String, String), Vec<Relation>> = HashMap::new();
|
||||
|
||||
// For every relation, map it across all polymorphic inheritance permutations
|
||||
for relation in raw_relations {
|
||||
if let Some(_source_type_def) = self.types.get(&relation.source_type) {
|
||||
if let Some(_dest_type_def) = self.types.get(&relation.destination_type) {
|
||||
let mut src_descendants = Vec::new();
|
||||
let mut dest_descendants = Vec::new();
|
||||
|
||||
for (t_name, t_def) in &self.types {
|
||||
if t_def.hierarchy.contains(&relation.source_type) {
|
||||
src_descendants.push(t_name.clone());
|
||||
}
|
||||
if t_def.hierarchy.contains(&relation.destination_type) {
|
||||
dest_descendants.push(t_name.clone());
|
||||
}
|
||||
}
|
||||
|
||||
for p_type in &src_descendants {
|
||||
for c_type in &dest_descendants {
|
||||
// Ignore entity <-> entity generic fallbacks, they aren't useful edges
|
||||
if p_type == "entity" && c_type == "entity" {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Forward edge
|
||||
edges
|
||||
.entry((p_type.clone(), c_type.clone()))
|
||||
.or_default()
|
||||
.push(relation.clone());
|
||||
|
||||
// Reverse edge (only if types are different to avoid duplicating self-referential edges like activity parent_id)
|
||||
if p_type != c_type {
|
||||
edges
|
||||
.entry((c_type.clone(), p_type.clone()))
|
||||
.or_default()
|
||||
.push(relation.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
self.relations = edges;
|
||||
}
|
||||
|
||||
pub fn get_relation(
|
||||
&self,
|
||||
parent_type: &str,
|
||||
child_type: &str,
|
||||
prop_name: &str,
|
||||
relative_keys: Option<&Vec<String>>,
|
||||
) -> Option<&Relation> {
|
||||
if let Some(relations) = self
|
||||
.relations
|
||||
.get(&(parent_type.to_string(), child_type.to_string()))
|
||||
{
|
||||
if relations.len() == 1 {
|
||||
return Some(&relations[0]);
|
||||
}
|
||||
|
||||
// Reduce ambiguity with prefix
|
||||
for rel in relations {
|
||||
if let Some(prefix) = &rel.prefix {
|
||||
if prefix == prop_name {
|
||||
return Some(rel);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Reduce ambiguity by checking if relative payload OMITS the prefix (M:M heuristic)
|
||||
if let Some(keys) = relative_keys {
|
||||
let mut missing_prefix_rels = Vec::new();
|
||||
for rel in relations {
|
||||
if let Some(prefix) = &rel.prefix {
|
||||
if !keys.contains(prefix) {
|
||||
missing_prefix_rels.push(rel);
|
||||
}
|
||||
}
|
||||
}
|
||||
if missing_prefix_rels.len() == 1 {
|
||||
return Some(missing_prefix_rels[0]);
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
fn collect_descendants_recursively(
|
||||
target: &str,
|
||||
direct_refs: &HashMap<String, Vec<String>>,
|
||||
@ -335,17 +426,14 @@ impl Database {
|
||||
if let (Some(pt), Some(prop)) = (&parent_type, &property_name) {
|
||||
let expected_col = format!("{}_id", prop);
|
||||
let mut found = false;
|
||||
for rel in db.relations.values() {
|
||||
if (rel.source_type == *pt && rel.destination_type == entity_type)
|
||||
|| (rel.source_type == entity_type && rel.destination_type == *pt)
|
||||
{
|
||||
if rel.source_columns.contains(&expected_col) {
|
||||
relation_col = Some(expected_col.clone());
|
||||
found = true;
|
||||
break;
|
||||
}
|
||||
|
||||
if let Some(rel) = db.get_relation(pt, &entity_type, prop, None) {
|
||||
if rel.source_columns.contains(&expected_col) {
|
||||
relation_col = Some(expected_col.clone());
|
||||
found = true;
|
||||
}
|
||||
}
|
||||
|
||||
if !found {
|
||||
relation_col = Some(expected_col);
|
||||
}
|
||||
|
||||
@ -21,15 +21,12 @@ impl Merger {
|
||||
}
|
||||
|
||||
pub fn merge(&self, data: Value) -> crate::drop::Drop {
|
||||
let mut val_resolved = Value::Null;
|
||||
let mut notifications_queue = Vec::new();
|
||||
|
||||
|
||||
let result = self.merge_internal(data, &mut notifications_queue);
|
||||
|
||||
match result {
|
||||
Ok(val) => {
|
||||
val_resolved = val;
|
||||
}
|
||||
let val_resolved = match result {
|
||||
Ok(val) => val,
|
||||
Err(msg) => {
|
||||
return crate::drop::Drop::with_errors(vec![crate::drop::Error {
|
||||
code: "MERGE_FAILED".to_string(),
|
||||
@ -44,7 +41,7 @@ impl Merger {
|
||||
}
|
||||
};
|
||||
|
||||
// Execute the globally collected, pre-ordered notifications last!
|
||||
// Execute the globally collected, pre-ordered notifications last!
|
||||
for notify_sql in notifications_queue {
|
||||
if let Err(e) = self.db.execute(¬ify_sql, None) {
|
||||
return crate::drop::Drop::with_errors(vec![crate::drop::Error {
|
||||
@ -88,7 +85,11 @@ impl Merger {
|
||||
crate::drop::Drop::success_with_val(stripped_val)
|
||||
}
|
||||
|
||||
pub(crate) fn merge_internal(&self, data: Value, notifications: &mut Vec<String>) -> Result<Value, String> {
|
||||
pub(crate) fn merge_internal(
|
||||
&self,
|
||||
data: Value,
|
||||
notifications: &mut Vec<String>,
|
||||
) -> Result<Value, String> {
|
||||
match data {
|
||||
Value::Array(items) => self.merge_array(items, notifications),
|
||||
Value::Object(map) => self.merge_object(map, notifications),
|
||||
@ -96,7 +97,11 @@ impl Merger {
|
||||
}
|
||||
}
|
||||
|
||||
fn merge_array(&self, items: Vec<Value>, notifications: &mut Vec<String>) -> Result<Value, String> {
|
||||
fn merge_array(
|
||||
&self,
|
||||
items: Vec<Value>,
|
||||
notifications: &mut Vec<String>,
|
||||
) -> Result<Value, String> {
|
||||
let mut resolved_items = Vec::new();
|
||||
for item in items {
|
||||
let resolved = self.merge_internal(item, notifications)?;
|
||||
@ -105,7 +110,11 @@ impl Merger {
|
||||
Ok(Value::Array(resolved_items))
|
||||
}
|
||||
|
||||
fn merge_object(&self, obj: serde_json::Map<String, Value>, notifications: &mut Vec<String>) -> Result<Value, String> {
|
||||
fn merge_object(
|
||||
&self,
|
||||
obj: serde_json::Map<String, Value>,
|
||||
notifications: &mut Vec<String>,
|
||||
) -> Result<Value, String> {
|
||||
let queue_start = notifications.len();
|
||||
|
||||
let type_name = match obj.get("type").and_then(|v| v.as_str()) {
|
||||
@ -164,7 +173,21 @@ impl Merger {
|
||||
_ => continue,
|
||||
};
|
||||
|
||||
let relative_relation = self.get_entity_relation(type_def, &relative, &relation_name)?;
|
||||
// Attempt to extract relative object type name
|
||||
let relative_type_name = match relative.get("type").and_then(|v| v.as_str()) {
|
||||
Some(t) => t,
|
||||
None => continue,
|
||||
};
|
||||
|
||||
let relative_keys: Vec<String> = relative.keys().cloned().collect();
|
||||
|
||||
// Call central Database O(1) graph logic
|
||||
let relative_relation = self.db.get_relation(
|
||||
&type_def.name,
|
||||
relative_type_name,
|
||||
&relation_name,
|
||||
Some(&relative_keys),
|
||||
);
|
||||
|
||||
if let Some(relation) = relative_relation {
|
||||
let parent_is_source = type_def.hierarchy.contains(&relation.source_type);
|
||||
@ -253,7 +276,21 @@ impl Merger {
|
||||
_ => continue,
|
||||
};
|
||||
|
||||
let relative_relation = self.get_entity_relation(type_def, first_relative, &relation_name)?;
|
||||
// Attempt to extract relative object type name
|
||||
let relative_type_name = match first_relative.get("type").and_then(|v| v.as_str()) {
|
||||
Some(t) => t,
|
||||
None => continue,
|
||||
};
|
||||
|
||||
let relative_keys: Vec<String> = first_relative.keys().cloned().collect();
|
||||
|
||||
// Call central Database O(1) graph logic
|
||||
let relative_relation = self.db.get_relation(
|
||||
&type_def.name,
|
||||
relative_type_name,
|
||||
&relation_name,
|
||||
Some(&relative_keys),
|
||||
);
|
||||
|
||||
if let Some(relation) = relative_relation {
|
||||
let mut relative_responses = Vec::new();
|
||||
@ -272,10 +309,11 @@ impl Merger {
|
||||
&entity_fields,
|
||||
);
|
||||
|
||||
let merged_relative = match self.merge_internal(Value::Object(relative_item), notifications)? {
|
||||
Value::Object(m) => m,
|
||||
_ => continue,
|
||||
};
|
||||
let merged_relative =
|
||||
match self.merge_internal(Value::Object(relative_item), notifications)? {
|
||||
Value::Object(m) => m,
|
||||
_ => continue,
|
||||
};
|
||||
|
||||
relative_responses.push(Value::Object(merged_relative));
|
||||
}
|
||||
@ -766,101 +804,7 @@ impl Merger {
|
||||
changes
|
||||
}
|
||||
|
||||
fn reduce_entity_relations(
|
||||
&self,
|
||||
mut matching_relations: Vec<crate::database::relation::Relation>,
|
||||
relative: &serde_json::Map<String, Value>,
|
||||
relation_name: &str,
|
||||
) -> Result<Option<crate::database::relation::Relation>, String> {
|
||||
if matching_relations.is_empty() {
|
||||
return Ok(None);
|
||||
}
|
||||
if matching_relations.len() == 1 {
|
||||
return Ok(Some(matching_relations.pop().unwrap()));
|
||||
}
|
||||
|
||||
let exact_match: Vec<_> = matching_relations
|
||||
.iter()
|
||||
.filter(|r| r.prefix.as_deref() == Some(relation_name))
|
||||
.cloned()
|
||||
.collect();
|
||||
if exact_match.len() == 1 {
|
||||
return Ok(Some(exact_match.into_iter().next().unwrap()));
|
||||
}
|
||||
|
||||
matching_relations.retain(|r| {
|
||||
if let Some(prefix) = &r.prefix {
|
||||
!relative.contains_key(prefix)
|
||||
} else {
|
||||
true
|
||||
}
|
||||
});
|
||||
|
||||
if matching_relations.len() == 1 {
|
||||
Ok(Some(matching_relations.pop().unwrap()))
|
||||
} else {
|
||||
let constraints: Vec<_> = matching_relations
|
||||
.iter()
|
||||
.map(|r| r.constraint.clone())
|
||||
.collect();
|
||||
Err(format!(
|
||||
"AMBIGUOUS_TYPE_RELATIONS: Could not reduce ambiguous type relations: {}",
|
||||
constraints.join(", ")
|
||||
))
|
||||
}
|
||||
}
|
||||
|
||||
fn get_entity_relation(
|
||||
&self,
|
||||
entity_type: &crate::database::r#type::Type,
|
||||
relative: &serde_json::Map<String, Value>,
|
||||
relation_name: &str,
|
||||
) -> Result<Option<crate::database::relation::Relation>, String> {
|
||||
let relative_type_name = match relative.get("type").and_then(|v| v.as_str()) {
|
||||
Some(t) => t,
|
||||
None => return Ok(None),
|
||||
};
|
||||
|
||||
let relative_type = match self.db.types.get(relative_type_name) {
|
||||
Some(t) => t,
|
||||
None => return Ok(None),
|
||||
};
|
||||
|
||||
let mut relative_relations: Vec<crate::database::relation::Relation> = Vec::new();
|
||||
|
||||
for r in self.db.relations.values() {
|
||||
if r.source_type != "entity" && r.destination_type != "entity" {
|
||||
let condition1 = relative_type.hierarchy.contains(&r.source_type)
|
||||
&& entity_type.hierarchy.contains(&r.destination_type);
|
||||
let condition2 = entity_type.hierarchy.contains(&r.source_type)
|
||||
&& relative_type.hierarchy.contains(&r.destination_type);
|
||||
|
||||
if condition1 || condition2 {
|
||||
relative_relations.push(r.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let mut relative_relation =
|
||||
self.reduce_entity_relations(relative_relations, relative, relation_name)?;
|
||||
|
||||
if relative_relation.is_none() {
|
||||
let mut poly_relations: Vec<crate::database::relation::Relation> = Vec::new();
|
||||
for r in self.db.relations.values() {
|
||||
if r.destination_type == "entity" {
|
||||
let condition1 = relative_type.hierarchy.contains(&r.source_type);
|
||||
let condition2 = entity_type.hierarchy.contains(&r.source_type);
|
||||
|
||||
if condition1 || condition2 {
|
||||
poly_relations.push(r.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
relative_relation = self.reduce_entity_relations(poly_relations, relative, relation_name)?;
|
||||
}
|
||||
|
||||
Ok(relative_relation)
|
||||
}
|
||||
// Helper Functions
|
||||
|
||||
fn apply_entity_relation(
|
||||
source_entity: &mut serde_json::Map<String, Value>,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -97,7 +97,13 @@ impl Queryer {
|
||||
return Ok(cached_sql.value().clone());
|
||||
}
|
||||
|
||||
let compiler = compiler::SqlCompiler::new(self.db.clone());
|
||||
let compiler = compiler::Compiler {
|
||||
db: &self.db,
|
||||
filter_keys: filter_keys,
|
||||
is_stem_query: stem_opt.is_some(),
|
||||
alias_counter: 0,
|
||||
};
|
||||
|
||||
match compiler.compile(schema_id, stem_opt, filter_keys) {
|
||||
Ok(compiled_sql) => {
|
||||
self
|
||||
|
||||
@ -2,7 +2,6 @@ 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
|
||||
|
||||
|
||||
@ -1,19 +1,10 @@
|
||||
use crate::tests::types::Suite;
|
||||
use serde::Deserialize;
|
||||
use serde_json::Value;
|
||||
use std::collections::HashMap;
|
||||
use std::fs;
|
||||
use std::sync::{Arc, OnceLock, RwLock};
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct TestSuite {
|
||||
#[allow(dead_code)]
|
||||
pub description: String,
|
||||
pub database: serde_json::Value,
|
||||
pub tests: Vec<TestCase>,
|
||||
}
|
||||
|
||||
use crate::tests::types::TestCase;
|
||||
use serde_json::Value;
|
||||
|
||||
pub fn deserialize_some<'de, D>(deserializer: D) -> Result<Option<Value>, D::Error>
|
||||
where
|
||||
D: serde::Deserializer<'de>,
|
||||
@ -23,7 +14,7 @@ where
|
||||
}
|
||||
|
||||
// Type alias for easier reading
|
||||
type CompiledSuite = Arc<Vec<(TestSuite, Arc<crate::database::Database>)>>;
|
||||
type CompiledSuite = Arc<Vec<(Suite, Arc<crate::database::Database>)>>;
|
||||
|
||||
// Global cache mapping filename -> Vector of (Parsed JSON suite, Compiled Database)
|
||||
static CACHE: OnceLock<RwLock<HashMap<String, CompiledSuite>>> = OnceLock::new();
|
||||
@ -46,7 +37,7 @@ fn get_cached_file(path: &str) -> CompiledSuite {
|
||||
} else {
|
||||
let content =
|
||||
fs::read_to_string(path).unwrap_or_else(|_| panic!("Failed to read file: {}", path));
|
||||
let suites: Vec<TestSuite> = serde_json::from_str(&content)
|
||||
let suites: Vec<Suite> = serde_json::from_str(&content)
|
||||
.unwrap_or_else(|e| panic!("Failed to parse JSON in {}: {}", path, e));
|
||||
|
||||
let mut compiled_suites = Vec::new();
|
||||
|
||||
@ -1,156 +0,0 @@
|
||||
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(())
|
||||
}
|
||||
@ -1,11 +1,11 @@
|
||||
use super::expect::ExpectBlock;
|
||||
use super::expect::Expect;
|
||||
use crate::database::Database;
|
||||
use serde::Deserialize;
|
||||
use serde_json::Value;
|
||||
use std::sync::Arc;
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct TestCase {
|
||||
pub struct Case {
|
||||
pub description: String,
|
||||
|
||||
#[serde(default = "default_action")]
|
||||
@ -30,14 +30,14 @@ pub struct TestCase {
|
||||
#[serde(default)]
|
||||
pub mocks: Option<serde_json::Value>,
|
||||
|
||||
pub expect: Option<ExpectBlock>,
|
||||
pub expect: Option<Expect>,
|
||||
}
|
||||
|
||||
fn default_action() -> String {
|
||||
"validate".to_string()
|
||||
}
|
||||
|
||||
impl TestCase {
|
||||
impl Case {
|
||||
pub fn run_compile(&self, db: Arc<Database>) -> Result<(), String> {
|
||||
let expected_success = self.expect.as_ref().map(|e| e.success).unwrap_or(false);
|
||||
|
||||
@ -138,6 +138,7 @@ impl TestCase {
|
||||
))
|
||||
} else if let Some(expect) = &self.expect {
|
||||
let queries = db.executor.get_queries();
|
||||
expect.assert_pattern(&queries)?;
|
||||
expect.assert_sql(&queries)
|
||||
} else {
|
||||
Ok(())
|
||||
@ -176,6 +177,7 @@ impl TestCase {
|
||||
))
|
||||
} else if let Some(expect) = &self.expect {
|
||||
let queries = db.executor.get_queries();
|
||||
expect.assert_pattern(&queries)?;
|
||||
expect.assert_sql(&queries)
|
||||
} else {
|
||||
Ok(())
|
||||
|
||||
22
src/tests/types/expect/mod.rs
Normal file
22
src/tests/types/expect/mod.rs
Normal file
@ -0,0 +1,22 @@
|
||||
pub mod pattern;
|
||||
pub mod sql;
|
||||
|
||||
use serde::Deserialize;
|
||||
use std::collections::HashMap;
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(untagged)]
|
||||
pub enum SqlExpectation {
|
||||
Single(String),
|
||||
Multi(Vec<String>),
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct Expect {
|
||||
pub success: bool,
|
||||
pub result: Option<serde_json::Value>,
|
||||
pub errors: Option<Vec<serde_json::Value>>,
|
||||
pub stems: Option<HashMap<String, HashMap<String, serde_json::Value>>>,
|
||||
#[serde(default)]
|
||||
pub sql: Option<Vec<SqlExpectation>>,
|
||||
}
|
||||
@ -1,30 +1,13 @@
|
||||
use super::Expect;
|
||||
use regex::Regex;
|
||||
use serde::Deserialize;
|
||||
use std::collections::HashMap;
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(untagged)]
|
||||
pub enum SqlExpectation {
|
||||
Single(String),
|
||||
Multi(Vec<String>),
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct ExpectBlock {
|
||||
pub success: bool,
|
||||
pub result: Option<serde_json::Value>,
|
||||
pub errors: Option<Vec<serde_json::Value>>,
|
||||
pub stems: Option<HashMap<String, HashMap<String, serde_json::Value>>>,
|
||||
#[serde(default)]
|
||||
pub sql: Option<Vec<SqlExpectation>>,
|
||||
}
|
||||
|
||||
impl ExpectBlock {
|
||||
impl Expect {
|
||||
/// Advanced SQL execution assertion algorithm ported from `assert.go`.
|
||||
/// This compares two arrays of strings, one containing {{uuid:name}} or {{timestamp}} placeholders,
|
||||
/// and the other containing actual executed database queries. It ensures that placeholder UUIDs
|
||||
/// are consistently mapped to the same actual UUIDs across all lines, and strictly validates line-by-line sequences.
|
||||
pub fn assert_sql(&self, actual: &[String]) -> Result<(), String> {
|
||||
pub fn assert_pattern(&self, actual: &[String]) -> Result<(), String> {
|
||||
let patterns = match &self.sql {
|
||||
Some(s) => s,
|
||||
None => return Ok(()),
|
||||
@ -39,12 +22,6 @@ 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([
|
||||
@ -82,8 +59,8 @@ impl ExpectBlock {
|
||||
let aline = clean_str(aline_raw);
|
||||
|
||||
let pattern_str_raw = match pattern_expect {
|
||||
SqlExpectation::Single(s) => s.clone(),
|
||||
SqlExpectation::Multi(m) => m.join(" "),
|
||||
super::SqlExpectation::Single(s) => s.clone(),
|
||||
super::SqlExpectation::Multi(m) => m.join(" "),
|
||||
};
|
||||
|
||||
let pattern_str = clean_str(&pattern_str_raw);
|
||||
206
src/tests/types/expect/sql.rs
Normal file
206
src/tests/types/expect/sql.rs
Normal file
@ -0,0 +1,206 @@
|
||||
use super::Expect;
|
||||
use sqlparser::ast::{Expr, Query, SelectItem, Statement, TableFactor};
|
||||
use sqlparser::dialect::PostgreSqlDialect;
|
||||
use sqlparser::parser::Parser;
|
||||
use std::collections::HashSet;
|
||||
|
||||
impl Expect {
|
||||
pub fn assert_sql(&self, actual: &[String]) -> Result<(), String> {
|
||||
for query in actual {
|
||||
if let Err(e) = Self::validate_semantic_sql(query) {
|
||||
return Err(e);
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
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 {
|
||||
Self::validate_statement(&statement, sql)?;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn validate_statement(stmt: &Statement, original_sql: &str) -> Result<(), String> {
|
||||
match stmt {
|
||||
Statement::Query(query) => Self::validate_query(query, &HashSet::new(), original_sql)?,
|
||||
Statement::Insert(insert) => {
|
||||
if let Some(query) = &insert.source {
|
||||
Self::validate_query(query, &HashSet::new(), original_sql)?
|
||||
}
|
||||
}
|
||||
Statement::Update(update) => {
|
||||
if let Some(expr) = &update.selection {
|
||||
Self::validate_expr(expr, &HashSet::new(), original_sql)?;
|
||||
}
|
||||
}
|
||||
Statement::Delete(delete) => {
|
||||
if let Some(expr) = &delete.selection {
|
||||
Self::validate_expr(expr, &HashSet::new(), original_sql)?;
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn validate_query(
|
||||
query: &Query,
|
||||
available_aliases: &HashSet<String>,
|
||||
original_sql: &str,
|
||||
) -> Result<(), String> {
|
||||
if let sqlparser::ast::SetExpr::Select(select) = &*query.body {
|
||||
Self::validate_select(&select, available_aliases, original_sql)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn validate_select(
|
||||
select: &sqlparser::ast::Select,
|
||||
parent_aliases: &HashSet<String>,
|
||||
original_sql: &str,
|
||||
) -> Result<(), String> {
|
||||
let mut available_aliases = parent_aliases.clone();
|
||||
|
||||
// 1. Collect all declared table aliases in the FROM clause and JOINs
|
||||
for table_with_joins in &select.from {
|
||||
Self::collect_aliases_from_table_factor(&table_with_joins.relation, &mut available_aliases);
|
||||
for join in &table_with_joins.joins {
|
||||
Self::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 {
|
||||
Self::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 sqlparser::ast::JoinOperator::Inner(sqlparser::ast::JoinConstraint::On(expr))
|
||||
| sqlparser::ast::JoinOperator::LeftOuter(sqlparser::ast::JoinConstraint::On(expr))
|
||||
| sqlparser::ast::JoinOperator::RightOuter(sqlparser::ast::JoinConstraint::On(expr))
|
||||
| sqlparser::ast::JoinOperator::FullOuter(sqlparser::ast::JoinConstraint::On(expr))
|
||||
| sqlparser::ast::JoinOperator::Join(sqlparser::ast::JoinConstraint::On(expr)) =
|
||||
&join.join_operator
|
||||
{
|
||||
Self::validate_expr(expr, &available_aliases, original_sql)?;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 4. Validate WHERE conditions
|
||||
if let Some(selection) = &select.selection {
|
||||
Self::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 {
|
||||
subquery,
|
||||
alias: Some(table_alias),
|
||||
..
|
||||
} => {
|
||||
aliases.insert(table_alias.name.value.clone());
|
||||
// A derived table is technically a nested scope which is opaque outside, but for pure semantic checks
|
||||
// its internal contents should be validated purely within its own scope (not leaking external aliases in, usually)
|
||||
// but Postgres allows lateral correlation. We will validate its interior with an empty scope.
|
||||
let _ = Self::validate_query(subquery, &HashSet::new(), "");
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
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::Subquery(subquery) => Self::validate_query(subquery, available_aliases, sql)?,
|
||||
Expr::Exists { subquery, .. } => Self::validate_query(subquery, available_aliases, sql)?,
|
||||
Expr::InSubquery {
|
||||
expr: e, subquery, ..
|
||||
} => {
|
||||
Self::validate_expr(e, available_aliases, sql)?;
|
||||
Self::validate_query(subquery, available_aliases, sql)?;
|
||||
}
|
||||
Expr::BinaryOp { left, right, .. } => {
|
||||
Self::validate_expr(left, available_aliases, sql)?;
|
||||
Self::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, .. } => {
|
||||
Self::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)
|
||||
{
|
||||
Self::validate_expr(e, available_aliases, sql)?;
|
||||
}
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
@ -2,6 +2,6 @@ pub mod case;
|
||||
pub mod expect;
|
||||
pub mod suite;
|
||||
|
||||
pub use case::TestCase;
|
||||
pub use expect::ExpectBlock;
|
||||
pub use suite::TestSuite;
|
||||
pub use case::Case;
|
||||
pub use expect::Expect;
|
||||
pub use suite::Suite;
|
||||
|
||||
@ -1,10 +1,10 @@
|
||||
use super::case::TestCase;
|
||||
use super::case::Case;
|
||||
use serde::Deserialize;
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct TestSuite {
|
||||
pub struct Suite {
|
||||
#[allow(dead_code)]
|
||||
pub description: String,
|
||||
pub database: serde_json::Value,
|
||||
pub tests: Vec<TestCase>,
|
||||
pub tests: Vec<Case>,
|
||||
}
|
||||
|
||||
@ -68,11 +68,11 @@ impl Validator {
|
||||
code: e.code,
|
||||
message: e.message,
|
||||
details: crate::drop::ErrorDetails {
|
||||
path: e.path,
|
||||
cause: None,
|
||||
context: None,
|
||||
schema: None,
|
||||
},
|
||||
path: e.path,
|
||||
cause: None,
|
||||
context: None,
|
||||
schema: None,
|
||||
},
|
||||
})
|
||||
.collect();
|
||||
crate::drop::Drop::with_errors(errors)
|
||||
|
||||
Reference in New Issue
Block a user