Compare commits

...

5 Commits

Author SHA1 Message Date
02e661d219 version: 1.0.72 2026-03-17 23:10:52 -04:00
f7163e2689 version: 1.0.71 2026-03-17 22:13:55 -04:00
091007006d queryer fixes in place 2026-03-17 22:13:34 -04:00
3d66a7fc3c queryer test checkpoit 2026-03-17 18:00:36 -04:00
e1314496dd queryer test checkpoint 2026-03-17 15:06:02 -04:00
19 changed files with 1559 additions and 1074 deletions

5
.vscode/extensions.json vendored Normal file
View File

@ -0,0 +1,5 @@
{
"recommendations": [
"rust-lang.rust-analyzer"
]
}

View File

@ -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

View File

@ -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);
}

View File

@ -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(&notify_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>,

View File

@ -47,7 +47,19 @@ impl SqlCompiler {
// We expect the top level to typically be an Object or Array
let is_stem_query = stem_path.is_some();
let (sql, _) = self.walk_schema(target_schema, "t1", None, filter_keys, is_stem_query, 0, String::new())?;
let mut alias_counter: usize = 0;
let (sql, _) = self.walk_schema(
target_schema,
"t1",
None,
None,
None,
filter_keys,
is_stem_query,
0,
String::new(),
&mut alias_counter,
)?;
Ok(sql)
}
@ -57,11 +69,14 @@ impl SqlCompiler {
&self,
schema: &crate::database::schema::Schema,
parent_alias: &str,
parent_table_aliases: Option<&std::collections::HashMap<String, String>>,
parent_type_def: Option<&crate::database::r#type::Type>,
prop_name_context: Option<&str>,
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
alias_counter: &mut usize,
) -> Result<(String, String), String> {
// Determine the base schema type (could be an array, object, or literal)
match &schema.obj.type_ {
@ -80,23 +95,29 @@ impl SqlCompiler {
items,
type_def,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
true,
filter_keys,
is_stem_query,
depth,
next_path,
alias_counter,
);
}
}
let (item_sql, _) = self.walk_schema(
items,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
filter_keys,
is_stem_query,
depth + 1,
next_path,
alias_counter,
)?;
return Ok((
format!("(SELECT jsonb_agg({}) FROM TODO)", item_sql),
@ -125,12 +146,15 @@ impl SqlCompiler {
schema,
type_def,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
false,
filter_keys,
is_stem_query,
depth,
current_path,
alias_counter,
);
}
@ -141,40 +165,63 @@ impl SqlCompiler {
return self.walk_schema(
target_schema,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path,
alias_counter,
);
}
return Err(format!("Unresolved $ref: {}", ref_id));
}
// Handle $family Polymorphism fallbacks for relations
if let Some(family_target) = &schema.obj.family {
let mut all_targets = vec![family_target.clone()];
if let Some(schema_id) = &schema.obj.id {
if let Some(descendants) = self.db.descendants.get(schema_id) {
all_targets.extend(descendants.clone());
let base_type_name = family_target.split('.').next_back().unwrap_or(family_target).to_string();
if let Some(type_def) = self.db.types.get(&base_type_name) {
if type_def.variations.len() == 1 {
let mut bypass_schema = crate::database::schema::Schema::default();
bypass_schema.obj.r#ref = Some(family_target.clone());
return self.walk_schema(
&std::sync::Arc::new(bypass_schema),
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path,
alias_counter,
);
}
}
let mut family_schemas = Vec::new();
for target in all_targets {
let mut ref_schema = crate::database::schema::Schema::default();
ref_schema.obj.r#ref = Some(target);
family_schemas.push(std::sync::Arc::new(ref_schema));
}
let mut sorted_variations: Vec<String> = type_def.variations.iter().cloned().collect();
sorted_variations.sort();
return self.compile_one_of(
&family_schemas,
parent_alias,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path,
);
let mut family_schemas = Vec::new();
for variation in &sorted_variations {
let mut ref_schema = crate::database::schema::Schema::default();
ref_schema.obj.r#ref = Some(variation.clone());
family_schemas.push(std::sync::Arc::new(ref_schema));
}
return self.compile_one_of(
&family_schemas,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path,
alias_counter,
);
}
}
// Handle oneOf Polymorphism fallbacks for relations
@ -182,11 +229,14 @@ impl SqlCompiler {
return self.compile_one_of(
one_of,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path,
alias_counter,
);
}
@ -195,10 +245,13 @@ impl SqlCompiler {
return self.compile_inline_object(
props,
parent_alias,
parent_table_aliases,
parent_type_def,
filter_keys,
is_stem_query,
depth,
current_path,
alias_counter,
);
}
@ -241,17 +294,18 @@ impl SqlCompiler {
schema: &crate::database::schema::Schema,
type_def: &crate::database::r#type::Type,
parent_alias: &str,
parent_table_aliases: Option<&std::collections::HashMap<String, String>>,
parent_type_def: Option<&crate::database::r#type::Type>,
prop_name: Option<&str>,
is_array: bool,
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
alias_counter: &mut usize,
) -> Result<(String, String), String> {
let local_ctx = format!("{}_{}", parent_alias, prop_name.unwrap_or("obj"));
// 1. Build FROM clauses and table aliases
let (table_aliases, from_clauses) = self.build_hierarchy_from_clauses(type_def, &local_ctx);
let (table_aliases, from_clauses) = self.build_hierarchy_from_clauses(type_def, alias_counter);
// 2. Map properties and build jsonb_build_object args
let mut select_args = self.map_properties_to_aliases(
@ -263,39 +317,79 @@ impl SqlCompiler {
is_stem_query,
depth,
&current_path,
alias_counter,
)?;
// 2.5 Inject polymorphism directly into the query object
if let Some(family_target) = &schema.obj.family {
let mut family_schemas = Vec::new();
if let Some(base_type) = self.db.types.get(family_target) {
let mut sorted_targets: Vec<String> = base_type.variations.iter().cloned().collect();
// Ensure the base type is included if not listed in variations by default
if !sorted_targets.contains(family_target) {
sorted_targets.push(family_target.clone());
}
sorted_targets.sort();
for target in sorted_targets {
let mut ref_schema = crate::database::schema::Schema::default();
ref_schema.obj.r#ref = Some(target);
family_schemas.push(std::sync::Arc::new(ref_schema));
}
} else {
// Fallback for types not strictly defined in physical DB
let mut ref_schema = crate::database::schema::Schema::default();
ref_schema.obj.r#ref = Some(family_target.clone());
family_schemas.push(std::sync::Arc::new(ref_schema));
}
let base_type_name = family_target.split('.').next_back().unwrap_or(family_target).to_string();
let base_alias = table_aliases.get(&type_def.name).cloned().unwrap_or_else(|| parent_alias.to_string());
select_args.push(format!("'id', {}.id", base_alias));
let (case_sql, _) = self.compile_one_of(&family_schemas, &base_alias, None, filter_keys, is_stem_query, depth, current_path.clone())?;
select_args.push(format!("'type', {}", case_sql));
if let Some(fam_type_def) = self.db.types.get(&base_type_name) {
if fam_type_def.variations.len() == 1 {
let mut bypass_schema = crate::database::schema::Schema::default();
bypass_schema.obj.r#ref = Some(family_target.clone());
let mut bypassed_args = self.map_properties_to_aliases(
&bypass_schema,
type_def,
&table_aliases,
parent_alias,
filter_keys,
is_stem_query,
depth,
&current_path,
alias_counter,
)?;
select_args.append(&mut bypassed_args);
} else {
let mut family_schemas = Vec::new();
let mut sorted_fam_variations: Vec<String> = fam_type_def.variations.iter().cloned().collect();
sorted_fam_variations.sort();
for variation in &sorted_fam_variations {
let mut ref_schema = crate::database::schema::Schema::default();
ref_schema.obj.r#ref = Some(variation.clone());
family_schemas.push(std::sync::Arc::new(ref_schema));
}
let base_alias = table_aliases
.get(&type_def.name)
.cloned()
.unwrap_or_else(|| parent_alias.to_string());
select_args.push(format!("'id', {}.id", base_alias));
let (case_sql, _) = self.compile_one_of(
&family_schemas,
&base_alias,
Some(&table_aliases),
parent_type_def,
None,
filter_keys,
is_stem_query,
depth,
current_path.clone(),
alias_counter,
)?;
select_args.push(format!("'type', {}", case_sql));
}
}
} else if let Some(one_of) = &schema.obj.one_of {
let base_alias = table_aliases.get(&type_def.name).cloned().unwrap_or_else(|| parent_alias.to_string());
let base_alias = table_aliases
.get(&type_def.name)
.cloned()
.unwrap_or_else(|| parent_alias.to_string());
select_args.push(format!("'id', {}.id", base_alias));
let (case_sql, _) = self.compile_one_of(one_of, &base_alias, None, filter_keys, is_stem_query, depth, current_path.clone())?;
let (case_sql, _) = self.compile_one_of(
one_of,
&base_alias,
Some(&table_aliases),
parent_type_def,
None,
filter_keys,
is_stem_query,
depth,
current_path.clone(),
alias_counter,
)?;
select_args.push(format!("'type', {}", case_sql));
}
@ -311,6 +405,8 @@ impl SqlCompiler {
type_def,
&table_aliases,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name,
filter_keys,
&current_path,
@ -342,19 +438,20 @@ impl SqlCompiler {
fn build_hierarchy_from_clauses(
&self,
type_def: &crate::database::r#type::Type,
local_ctx: &str,
alias_counter: &mut usize,
) -> (std::collections::HashMap<String, String>, Vec<String>) {
let mut table_aliases = std::collections::HashMap::new();
let mut from_clauses = Vec::new();
for (i, table_name) in type_def.hierarchy.iter().enumerate() {
let alias = format!("{}_t{}", local_ctx, i + 1);
*alias_counter += 1;
let alias = format!("{}_{}", table_name, alias_counter);
table_aliases.insert(table_name.clone(), alias.clone());
if i == 0 {
from_clauses.push(format!("agreego.{} {}", table_name, alias));
} else {
let prev_alias = format!("{}_t{}", local_ctx, i);
let prev_alias = format!("{}_{}", type_def.hierarchy[i - 1], *alias_counter - 1);
from_clauses.push(format!(
"JOIN agreego.{} {} ON {}.id = {}.id",
table_name, alias, alias, prev_alias
@ -374,12 +471,16 @@ impl SqlCompiler {
is_stem_query: bool,
depth: usize,
current_path: &str,
alias_counter: &mut usize,
) -> Result<Vec<String>, String> {
let mut select_args = Vec::new();
let grouped_fields = type_def.grouped_fields.as_ref().and_then(|v| v.as_object());
let merged_props = self.get_merged_properties(schema);
let mut sorted_keys: Vec<&String> = merged_props.keys().collect();
sorted_keys.sort();
for (prop_key, prop_schema) in &merged_props {
for prop_key in sorted_keys {
let prop_schema = &merged_props[prop_key];
let mut owner_alias = table_aliases
.get("entity")
.cloned()
@ -400,16 +501,20 @@ impl SqlCompiler {
}
let is_object_or_array = match &prop_schema.obj.type_ {
Some(crate::database::schema::SchemaTypeOrArray::Single(s)) => s == "object" || s == "array",
Some(crate::database::schema::SchemaTypeOrArray::Multiple(v)) => v.contains(&"object".to_string()) || v.contains(&"array".to_string()),
_ => false
Some(crate::database::schema::SchemaTypeOrArray::Single(s)) => {
s == "object" || s == "array"
}
Some(crate::database::schema::SchemaTypeOrArray::Multiple(v)) => {
v.contains(&"object".to_string()) || v.contains(&"array".to_string())
}
_ => false,
};
let is_primitive = prop_schema.obj.r#ref.is_none()
&& prop_schema.obj.items.is_none()
&& prop_schema.obj.properties.is_none()
&& prop_schema.obj.one_of.is_none()
&& !is_object_or_array;
let is_primitive = prop_schema.obj.r#ref.is_none()
&& prop_schema.obj.items.is_none()
&& prop_schema.obj.properties.is_none()
&& prop_schema.obj.one_of.is_none()
&& !is_object_or_array;
if is_primitive {
if let Some(ft) = type_def.field_types.as_ref().and_then(|v| v.as_object()) {
@ -428,11 +533,14 @@ impl SqlCompiler {
let (val_sql, val_type) = self.walk_schema(
prop_schema,
&owner_alias,
Some(table_aliases),
Some(type_def), // Pass current type_def as parent_type_def for child properties
Some(prop_key),
filter_keys,
is_stem_query,
depth + 1,
next_path,
alias_counter,
)?;
if val_type != "abort" {
@ -448,6 +556,8 @@ impl SqlCompiler {
type_def: &crate::database::r#type::Type,
table_aliases: &std::collections::HashMap<String, String>,
parent_alias: &str,
parent_table_aliases: Option<&std::collections::HashMap<String, String>>,
parent_type_def: Option<&crate::database::r#type::Type>,
prop_name: Option<&str>,
filter_keys: &[String],
current_path: &str,
@ -491,115 +601,171 @@ impl SqlCompiler {
let mut filter_alias = base_alias.clone();
if let Some(gf) = type_def.grouped_fields.as_ref().and_then(|v| v.as_object()) {
for (t_name, fields_val) in gf {
if let Some(fields_arr) = fields_val.as_array() {
if fields_arr.iter().any(|v| v.as_str() == Some(field_name)) {
filter_alias = table_aliases
.get(t_name)
.cloned()
.unwrap_or_else(|| base_alias.clone());
break;
for (t_name, fields_val) in gf {
if let Some(fields_arr) = fields_val.as_array() {
if fields_arr.iter().any(|v| v.as_str() == Some(field_name)) {
filter_alias = table_aliases
.get(t_name)
.cloned()
.unwrap_or_else(|| base_alias.clone());
break;
}
}
}
}
let mut is_ilike = false;
let mut cast = "";
if let Some(field_types) = type_def.field_types.as_ref().and_then(|v| v.as_object()) {
if let Some(pg_type_val) = field_types.get(field_name) {
if let Some(pg_type) = pg_type_val.as_str() {
if pg_type == "uuid" {
cast = "::uuid";
} else if pg_type == "boolean" || pg_type == "bool" {
cast = "::boolean";
} else if pg_type.contains("timestamp") || pg_type == "timestamptz" || pg_type == "date"
{
cast = "::timestamptz";
} else if pg_type == "numeric"
|| pg_type.contains("int")
|| pg_type == "real"
|| pg_type == "double precision"
{
cast = "::numeric";
} else if pg_type == "text" || pg_type.contains("char") {
let mut is_enum = false;
if let Some(props) = &schema.obj.properties {
if let Some(ps) = props.get(field_name) {
is_enum = ps.obj.enum_.is_some();
}
}
if !is_enum {
is_ilike = true;
}
}
}
}
}
let mut is_ilike = false;
let mut cast = "";
let param_index = i + 1;
let p_val = format!("${}#>>'{{}}'", param_index);
if let Some(field_types) = type_def.field_types.as_ref().and_then(|v| v.as_object()) {
if let Some(pg_type_val) = field_types.get(field_name) {
if let Some(pg_type) = pg_type_val.as_str() {
if pg_type == "uuid" {
cast = "::uuid";
} else if pg_type == "boolean" || pg_type == "bool" {
cast = "::boolean";
} else if pg_type.contains("timestamp")
|| pg_type == "timestamptz"
|| pg_type == "date"
{
cast = "::timestamptz";
} else if pg_type == "numeric"
|| pg_type.contains("int")
|| pg_type == "real"
|| pg_type == "double precision"
{
cast = "::numeric";
} else if pg_type == "text" || pg_type.contains("char") {
let mut is_enum = false;
if let Some(props) = &schema.obj.properties {
if let Some(ps) = props.get(field_name) {
is_enum = ps.obj.enum_.is_some();
}
}
if !is_enum {
is_ilike = true;
}
}
if op == "$in" || op == "$nin" {
let sql_op = if op == "$in" { "IN" } else { "NOT IN" };
let subquery = format!(
"(SELECT value{} FROM jsonb_array_elements_text(({})::jsonb))",
cast, p_val
);
where_clauses.push(format!(
"{}.{} {} {}",
filter_alias, field_name, sql_op, subquery
));
} else {
let sql_op = match op {
"$eq" => {
if is_ilike {
"ILIKE"
} else {
"="
}
}
}
"$ne" => {
if is_ilike {
"NOT ILIKE"
} else {
"!="
}
}
"$gt" => ">",
"$gte" => ">=",
"$lt" => "<",
"$lte" => "<=",
_ => {
if is_ilike {
"ILIKE"
} else {
"="
}
}
};
let param_index = i + 1;
let p_val = format!("${}#>>'{{}}'", param_index);
if op == "$in" || op == "$nin" {
let sql_op = if op == "$in" { "IN" } else { "NOT IN" };
let subquery = format!(
"(SELECT value{} FROM jsonb_array_elements_text(({})::jsonb))",
cast, p_val
);
where_clauses.push(format!(
"{}.{} {} {}",
filter_alias, field_name, sql_op, subquery
));
let param_sql = if is_ilike && (op == "$eq" || op == "$ne") {
p_val
} else {
let sql_op = match op {
"$eq" => {
if is_ilike {
"ILIKE"
} else {
"="
}
}
"$ne" => {
if is_ilike {
"NOT ILIKE"
} else {
"!="
}
}
"$gt" => ">",
"$gte" => ">=",
"$lt" => "<",
"$lte" => "<=",
_ => {
if is_ilike {
"ILIKE"
} else {
"="
}
}
};
format!("({}){}", p_val, cast)
};
let param_sql = if is_ilike && (op == "$eq" || op == "$ne") {
p_val
} else {
format!("({}){}", p_val, cast)
};
where_clauses.push(format!(
"{}.{} {} {}",
filter_alias, field_name, sql_op, param_sql
));
where_clauses.push(format!(
"{}.{} {} {}",
filter_alias, field_name, sql_op, param_sql
));
}
}
if let Some(prop) = prop_name {
if prop == "target" || prop == "source" {
where_clauses.push(format!("{}.id = {}.{}_id", base_alias, parent_alias, prop));
} else {
where_clauses.push(format!("{}.parent_id = {}.id", base_alias, parent_alias));
// Find what type the parent alias is actually mapping to
let mut relation_alias = parent_alias.to_string();
let mut relation_resolved = false;
if let Some(parent_type) = parent_type_def {
if let Some(relation) = self
.db
.get_relation(&parent_type.name, &type_def.name, prop, None)
{
let source_col = &relation.source_columns[0];
let dest_col = &relation.destination_columns[0];
let mut possible_relation_alias = None;
if let Some(pta) = parent_table_aliases {
if let Some(a) = pta.get(&relation.source_type) {
possible_relation_alias = Some(a.clone());
} else if let Some(a) = pta.get(&relation.destination_type) {
possible_relation_alias = Some(a.clone());
}
}
if let Some(pa) = possible_relation_alias {
relation_alias = pa;
}
// Determine directionality based on the Relation metadata
if relation.source_type == parent_type.name
|| parent_type.hierarchy.contains(&relation.source_type)
{
// Parent is the source
where_clauses.push(format!(
"{}.{} = {}.{}",
relation_alias, source_col, base_alias, dest_col
));
relation_resolved = true;
} else if relation.destination_type == parent_type.name
|| parent_type.hierarchy.contains(&relation.destination_type)
{
// Parent is the destination
where_clauses.push(format!(
"{}.{} = {}.{}",
base_alias, source_col, relation_alias, dest_col
));
relation_resolved = true;
}
}
}
if !relation_resolved {
// Fallback heuristics for unmapped polymorphism or abstract models
if prop == "target" || prop == "source" {
if let Some(pta) = parent_table_aliases {
if let Some(a) = pta.get("relationship") {
relation_alias = a.clone();
}
}
where_clauses.push(format!(
"{}.id = {}.{}_id",
base_alias, relation_alias, prop
));
} else {
where_clauses.push(format!("{}.parent_id = {}.id", base_alias, relation_alias));
}
}
}
@ -610,10 +776,13 @@ impl SqlCompiler {
&self,
props: &std::collections::BTreeMap<String, std::sync::Arc<crate::database::schema::Schema>>,
parent_alias: &str,
parent_table_aliases: Option<&std::collections::HashMap<String, String>>,
parent_type_def: Option<&crate::database::r#type::Type>,
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
alias_counter: &mut usize,
) -> Result<(String, String), String> {
let mut build_args = Vec::new();
for (k, v) in props {
@ -622,15 +791,18 @@ impl SqlCompiler {
} else {
format!("{}.{}", current_path, k)
};
let (child_sql, val_type) = self.walk_schema(
v,
parent_alias,
parent_table_aliases,
parent_type_def,
Some(k),
filter_keys,
is_stem_query,
depth + 1,
next_path,
alias_counter,
)?;
if val_type == "abort" {
continue;
@ -645,11 +817,14 @@ impl SqlCompiler {
&self,
schemas: &[Arc<crate::database::schema::Schema>],
parent_alias: &str,
parent_table_aliases: Option<&std::collections::HashMap<String, String>>,
parent_type_def: Option<&crate::database::r#type::Type>,
prop_name_context: Option<&str>,
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
alias_counter: &mut usize,
) -> Result<(String, String), String> {
let mut case_statements = Vec::new();
let type_col = if let Some(prop) = prop_name_context {
@ -662,16 +837,19 @@ impl SqlCompiler {
if let Some(ref_id) = &option_schema.obj.r#ref {
// Find the physical type this ref maps to
let base_type_name = ref_id.split('.').next_back().unwrap_or("").to_string();
// Generate the nested SQL for this specific target type
let (val_sql, _) = self.walk_schema(
option_schema,
parent_alias,
parent_table_aliases,
parent_type_def,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path.clone(),
alias_counter,
)?;
case_statements.push(format!(
@ -685,10 +863,9 @@ impl SqlCompiler {
return Ok(("NULL".to_string(), "string".to_string()));
}
let sql = format!(
"CASE {} ELSE NULL END",
case_statements.join(" ")
);
case_statements.sort();
let sql = format!("CASE {} ELSE NULL END", case_statements.join(" "));
Ok((sql, "object".to_string()))
}

View File

@ -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

View File

@ -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();

View File

@ -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(())
}

View File

@ -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(())

View 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>>,
}

View File

@ -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);

View 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(())
}
}

View File

@ -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;

View File

@ -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>,
}

View File

@ -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)

54
t10.json Normal file
View File

@ -0,0 +1,54 @@
[
[
"(SELECT jsonb_build_object(",
" 'id', organization_1.id,",
" 'type', CASE",
" WHEN organization_1.type = 'person' THEN",
" ((SELECT jsonb_build_object(",
" 'age', person_3.age,",
" 'archived', entity_5.archived,",
" 'created_at', entity_5.created_at,",
" 'first_name', person_3.first_name,",
" 'id', entity_5.id,",
" 'last_name', person_3.last_name,",
" 'name', entity_5.name,",
" 'type', entity_5.type",
" )",
" FROM agreego.person person_3",
" JOIN agreego.organization organization_4 ON organization_4.id = person_3.id",
" JOIN agreego.entity entity_5 ON entity_5.id = organization_4.id",
" WHERE",
" NOT entity_5.archived))",
" WHEN organization_1.type = 'bot' THEN",
" ((SELECT jsonb_build_object(",
" 'archived', entity_8.archived,",
" 'created_at', entity_8.created_at,",
" 'id', entity_8.id,",
" 'name', entity_8.name,",
" 'token', bot_6.token,",
" 'type', entity_8.type",
" )",
" FROM agreego.bot bot_6",
" JOIN agreego.organization organization_7 ON organization_7.id = bot_6.id",
" JOIN agreego.entity entity_8 ON entity_8.id = organization_7.id",
" WHERE",
" NOT entity_8.archived))",
" WHEN organization_1.type = 'organization' THEN",
" ((SELECT jsonb_build_object(",
" 'archived', entity_10.archived,",
" 'created_at', entity_10.created_at,",
" 'id', entity_10.id,",
" 'name', entity_10.name,",
" 'type', entity_10.type",
" )",
" FROM agreego.organization organization_9",
" JOIN agreego.entity entity_10 ON entity_10.id = organization_9.id",
" WHERE",
" NOT entity_10.archived))",
" ELSE NULL END",
")",
"FROM agreego.organization organization_1",
"JOIN agreego.entity entity_2 ON entity_2.id = organization_1.id",
"WHERE NOT entity_2.archived)"
]
]

164
t4.json Normal file
View File

@ -0,0 +1,164 @@
[
[
"(SELECT jsonb_build_object(",
" 'addresses',",
" (SELECT COALESCE(jsonb_agg(jsonb_build_object(",
" 'archived', entity_6.archived,",
" 'created_at', entity_6.created_at,",
" 'id', entity_6.id,",
" 'is_primary', contact_4.is_primary,",
" 'name', entity_6.name,",
" 'target',",
" (SELECT jsonb_build_object(",
" 'archived', entity_8.archived,",
" 'city', address_7.city,",
" 'created_at', entity_8.created_at,",
" 'id', entity_8.id,",
" 'name', entity_8.name,",
" 'type', entity_8.type",
" )",
" FROM agreego.address address_7",
" JOIN agreego.entity entity_8 ON entity_8.id = address_7.id",
" WHERE",
" NOT entity_8.archived",
" AND relationship_5.target_id = address_7.id),",
" 'type', entity_6.type",
" )), '[]'::jsonb)",
" FROM agreego.contact contact_4",
" JOIN agreego.relationship relationship_5 ON relationship_5.id = contact_4.id",
" JOIN agreego.entity entity_6 ON entity_6.id = relationship_5.id",
" WHERE",
" NOT entity_6.archived",
" AND contact_4.parent_id = entity_3.id),",
" 'age', person_1.age,",
" 'archived', entity_3.archived,",
" 'contacts',",
" (SELECT COALESCE(jsonb_agg(jsonb_build_object(",
" 'archived', entity_11.archived,",
" 'created_at', entity_11.created_at,",
" 'id', entity_11.id,",
" 'is_primary', contact_9.is_primary,",
" 'name', entity_11.name,",
" 'target', CASE",
" WHEN entity_11.target_type = 'address' THEN",
" ((SELECT jsonb_build_object(",
" 'archived', entity_17.archived,",
" 'city', address_16.city,",
" 'created_at', entity_17.created_at,",
" 'id', entity_17.id,",
" 'name', entity_17.name,",
" 'type', entity_17.type",
" )",
" FROM agreego.address address_16",
" JOIN agreego.entity entity_17 ON entity_17.id = address_16.id",
" WHERE",
" NOT entity_17.archived",
" AND relationship_10.target_id = address_16.id))",
" WHEN entity_11.target_type = 'email_address' THEN",
" ((SELECT jsonb_build_object(",
" 'address', email_address_14.address,",
" 'archived', entity_15.archived,",
" 'created_at', entity_15.created_at,",
" 'id', entity_15.id,",
" 'name', entity_15.name,",
" 'type', entity_15.type",
" )",
" FROM agreego.email_address email_address_14",
" JOIN agreego.entity entity_15 ON entity_15.id = email_address_14.id",
" WHERE",
" NOT entity_15.archived",
" AND relationship_10.target_id = email_address_14.id))",
" WHEN entity_11.target_type = 'phone_number' THEN",
" ((SELECT jsonb_build_object(",
" 'archived', entity_13.archived,",
" 'created_at', entity_13.created_at,",
" 'id', entity_13.id,",
" 'name', entity_13.name,",
" 'number', phone_number_12.number,",
" 'type', entity_13.type",
" )",
" FROM agreego.phone_number phone_number_12",
" JOIN agreego.entity entity_13 ON entity_13.id = phone_number_12.id",
" WHERE",
" NOT entity_13.archived",
" AND relationship_10.target_id = phone_number_12.id))",
" ELSE NULL END,",
" 'type', entity_11.type",
" )), '[]'::jsonb)",
" FROM agreego.contact contact_9",
" JOIN agreego.relationship relationship_10 ON relationship_10.id = contact_9.id",
" JOIN agreego.entity entity_11 ON entity_11.id = relationship_10.id",
" WHERE",
" NOT entity_11.archived",
" AND contact_9.parent_id = entity_3.id),",
" 'created_at', entity_3.created_at,",
" 'email_addresses',",
" (SELECT COALESCE(jsonb_agg(jsonb_build_object(",
" 'archived', entity_20.archived,",
" 'created_at', entity_20.created_at,",
" 'id', entity_20.id,",
" 'is_primary', contact_18.is_primary,",
" 'name', entity_20.name,",
" 'target',",
" (SELECT jsonb_build_object(",
" 'address', email_address_21.address,",
" 'archived', entity_22.archived,",
" 'created_at', entity_22.created_at,",
" 'id', entity_22.id,",
" 'name', entity_22.name,",
" 'type', entity_22.type",
" )",
" FROM agreego.email_address email_address_21",
" JOIN agreego.entity entity_22 ON entity_22.id = email_address_21.id",
" WHERE",
" NOT entity_22.archived",
" AND relationship_19.target_id = email_address_21.id),",
" 'type', entity_20.type",
" )), '[]'::jsonb)",
" FROM agreego.contact contact_18",
" JOIN agreego.relationship relationship_19 ON relationship_19.id = contact_18.id",
" JOIN agreego.entity entity_20 ON entity_20.id = relationship_19.id",
" WHERE",
" NOT entity_20.archived",
" AND contact_18.parent_id = entity_3.id),",
" 'first_name', person_1.first_name,",
" 'id', entity_3.id,",
" 'last_name', person_1.last_name,",
" 'name', entity_3.name,",
" 'phone_numbers',",
" (SELECT COALESCE(jsonb_agg(jsonb_build_object(",
" 'archived', entity_25.archived,",
" 'created_at', entity_25.created_at,",
" 'id', entity_25.id,",
" 'is_primary', contact_23.is_primary,",
" 'name', entity_25.name,",
" 'target',",
" (SELECT jsonb_build_object(",
" 'archived', entity_27.archived,",
" 'created_at', entity_27.created_at,",
" 'id', entity_27.id,",
" 'name', entity_27.name,",
" 'number', phone_number_26.number,",
" 'type', entity_27.type",
" )",
" FROM agreego.phone_number phone_number_26",
" JOIN agreego.entity entity_27 ON entity_27.id = phone_number_26.id",
" WHERE",
" NOT entity_27.archived",
" AND relationship_24.target_id = phone_number_26.id),",
" 'type', entity_25.type",
" )), '[]'::jsonb)",
" FROM agreego.contact contact_23",
" JOIN agreego.relationship relationship_24 ON relationship_24.id = contact_23.id",
" JOIN agreego.entity entity_25 ON entity_25.id = relationship_24.id",
" WHERE",
" NOT entity_25.archived",
" AND contact_23.parent_id = entity_3.id),",
" 'type', entity_3.type",
")",
"FROM agreego.person person_1",
"JOIN agreego.organization organization_2 ON organization_2.id = person_1.id",
"JOIN agreego.entity entity_3 ON entity_3.id = organization_2.id",
"WHERE NOT entity_3.archived)"
]
]

View File

@ -1 +1 @@
1.0.70
1.0.72