Compare commits

...

31 Commits

Author SHA1 Message Date
4a33e29628 version: 1.0.68 2026-03-16 19:39:34 -04:00
d8fc286e94 better error dropping 2026-03-16 19:39:24 -04:00
507dc6d780 version: 1.0.67 2026-03-16 18:06:45 -04:00
e340039a30 version: 1.0.66 2026-03-16 18:06:05 -04:00
08768e3d42 queryer fixes 2026-03-16 18:05:47 -04:00
6c9e6575ce version: 1.0.65 2026-03-16 06:07:44 -04:00
5d11c4c92c jspg query with familties fixes 2026-03-16 06:07:13 -04:00
25239d635b version: 1.0.64 2026-03-16 00:19:44 -04:00
3bec6a6102 fixed jspg_schemas returning a drop now 2026-03-16 00:19:32 -04:00
6444b300b3 version: 1.0.63 2026-03-15 23:03:15 -04:00
c529c8b8ea added jspg_schemas for mixer 2026-03-15 23:03:03 -04:00
2f15ae3d41 version: 1.0.62 2026-03-15 10:10:19 -04:00
f8528aa85e version: 1.0.61 2026-03-15 10:09:27 -04:00
b6f383e700 version: 1.0.60 2026-03-15 09:46:23 -04:00
db5183930d queryer supports subfiltering now 2026-03-15 07:49:05 -04:00
6de75ba525 merger notification process order testing 2026-03-15 07:31:14 -04:00
6632570712 merger improvements 2026-03-15 03:24:00 -04:00
d4347072f2 stripping schema nulls from stems 2026-03-15 00:13:33 -04:00
290464adc1 gjson pathing for stem paths 2026-03-13 23:35:37 -04:00
d6deaa0b0f version: 1.0.59 2026-03-13 01:17:50 -04:00
6a275e1d90 stems fixes and tests 2026-03-13 01:17:27 -04:00
797a0a5460 version: 1.0.58 2026-03-12 19:32:42 -04:00
cfcb259eab final queryer and merger test suite installed; docs fully up to date 2026-03-12 18:37:50 -04:00
f666e608da more tests progress 2026-03-12 18:24:13 -04:00
732034bbc7 more tests progress 2026-03-12 17:46:38 -04:00
5b183a1aba test cleanup 2026-03-11 23:19:51 -04:00
be1367930d test cleanups passing 2026-03-11 21:55:37 -04:00
44ba3e0e18 test cleanup 2026-03-11 21:11:31 -04:00
e692fc52ee all tests passing again 2026-03-11 20:38:53 -04:00
641f7b5d92 all tests passing again 2026-03-11 18:38:37 -04:00
c007d7d479 test checkpoint 2026-03-11 17:46:08 -04:00
28 changed files with 4900 additions and 1735 deletions

81
Cargo.lock generated
View File

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

View File

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

View File

@ -38,6 +38,8 @@ The Validator provides strict, schema-driven evaluation for the "Punc" architect
### Custom Features & Deviations
JSPG implements specific extensions to the Draft 2020-12 standard to support the Punc architecture's object-oriented needs while heavily optimizing for zero-runtime lookups.
* **Caching Strategy**: The Validator caches the pre-compiled `Database` registry in memory upon initialization (`jspg_setup`). This registry holds the comprehensive graph of schema boundaries, Types, ENUMs, and Foreign Key relationships, acting as the Single Source of Truth for all validation operations without polling Postgres.
#### 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.
@ -71,12 +73,15 @@ The Merger provides an automated, high-performance graph synchronization engine
### Core Features
* **Caching Strategy**: The Merger leverages the `Validator`'s in-memory `Database` registry to instantly resolve Foreign Key mapping graphs. It additionally utilizes the concurrent `GLOBAL_JSPG` application memory (`DashMap`) to cache statically constructed SQL `SELECT` strings used during deduplication (`lk_`) and difference tracking calculations.
* **Deep Graph Merging**: The Merger walks arbitrary levels of deeply nested JSON schemas (e.g. tracking an `order`, its `customer`, and an array of its `lines`). It intelligently discovers the correct parent-to-child or child-to-parent Foreign Keys stored in the registry and automatically maps the UUIDs across the relationships during UPSERT.
* **Prefix Foreign Key Matching**: Handles scenario where multiple relations point to the same table by using database Foreign Key constraint prefixes (`fk_`). For example, if a schema has `shipping_address` and `billing_address`, the merger resolves against `fk_shipping_address_entity` vs `fk_billing_address_entity` automatically to correctly route object properties.
* **Dynamic Deduplication & Lookups**: If a nested object is provided without an `id`, the Merger utilizes Postgres `lk_` index constraints defined in the schema registry (e.g. `lk_person` mapped to `first_name` and `last_name`). It dynamically queries these unique matching constraints to discover the correct UUID to perform an UPDATE, preventing data duplication.
* **Hierarchical Table Inheritance**: The Punc system uses distributed table inheritance (e.g. `person` inherits `user` inherits `organization` inherits `entity`). The Merger splits the incoming JSON payload and performs atomic row updates across *all* relevant tables in the lineage map.
* **The Archive Paradigm**: Data is never deleted in the Punc system. The Merger securely enforces referential integrity by toggling the `archived` Boolean flag on the base `entity` table rather than issuing SQL `DELETE` commands.
* **Change Tracking & Reactivity**: The Merger diffs the incoming JSON against the existing database row (utilizing static, `DashMap`-cached `lk_` SELECT string templates). Every detected change is recorded into the `agreego.change` audit table, tracking the user mapping. It then natively uses `pg_notify` to broadcast a completely flat row-level diff out to the Go WebSocket server for O(1) routing.
* **Flat Structural Beats (Unidirectional Flow)**: The Merger purposefully DOES NOT trace or hydrate outbound Foreign Keys or nested parent structures during writes. It emits completely flat, mathematically perfect structural deltas via `pg_notify` representing only the exact Postgres rows that changed. This guarantees the write-path remains O(1) lightning fast. It is the strict responsibility of the upstream Punc Framework (the Go `Speaker`) to intercept these flat beats, evaluate them against active Websocket Schema Topologies, and dynamically issue targeted `jspg_query` reads to hydrate the exact contextual subgraphs required by listening clients.
* **Pre-Order Notification Traversal**: To support proper topological hydration on the upstream Go Framework, the Merger decouples the `pg_notify` execution from the physical database write execution. The engine collects structural changes and explicitly fires `pg_notify` SQL statements in strict **Pre-Order** (Parent -> Relations -> Children). This guarantees that WebSocket clients receive the parent entity `Beat` prior to any nested child entities, ensuring stable unidirectional data flows without hydration race conditions.
* **Many-to-Many Graph Edge Management**: Operates seamlessly with the global `agreego.relationship` table, allowing the system to represent and merge arbitrary reified M:M relationships directionally between any two entities.
* **Sparse Updates**: Empty JSON strings `""` are directly bound as explicit SQL `NULL` directives to clear data, whilst omitted (missing) properties skip UPDATE execution entirely, ensuring partial UI submissions do not wipe out sibling fields.
* **Unified Return Structure**: To eliminate UI hydration race conditions and multi-user duplication, `jspg_merge` explicitly strips the response graph and returns only the root `{ "id": "uuid" }` (or an array of IDs for list insertions). External APIs can then explicitly call read APIs to fetch the resulting graph, while the UI relies 100% implicitly on the flat `pg_notify` pipeline for reactive state synchronization.
@ -89,23 +94,33 @@ The Merger provides an automated, high-performance graph synchronization engine
The Queryer transforms Postgres into a pre-compiled Semantic Query Engine via the `jspg_query(schema_id text, cue jsonb)` API, designed to serve the exact shape of Punc responses directly via SQL.
### Core Features
* **Caching Strategy (DashMap SQL Caching)**: The Queryer securely caches its compiled, static SQL string templates per schema permutation inside the `GLOBAL_JSPG` concurrent `DashMap`. This eliminates recursive AST schema crawling on consecutive requests. Furthermore, it evaluates the strings via Postgres SPI (Server Programming Interface) Prepared Statements, leveraging native database caching of execution plans for extreme performance.
* **Schema-to-SQL Compilation**: Compiles JSON Schema ASTs spanning deep arrays directly into static, pre-planned SQL multi-JOIN queries. This explicitly features the `Smart Merge` evaluation engine which natively translates properties through `allOf` and `$ref` inheritances, mapping JSON fields specifically to their physical database table aliases during translation.
* **DashMap SQL Caching**: Executes compiled SQL via Postgres SPI execution, securely caching the static string compilation templates per schema permutation inside the `GLOBAL_JSPG` application memory, drastically reducing repetitive schema crawling.
* **Dynamic Filtering**: Binds parameters natively through `cue.filters` objects. Dynamically handles string formatting (e.g. parsing `uuid` or formatting date-times) and safely escapes complex combinations utilizing `ILIKE` operations correctly mapped to the originating structural table.
### 4. The Stem Engine
* **Dynamic Filtering**: Binds parameters natively through `cue.filters` objects. The queryer enforces a strict, structured, MongoDB-style operator syntax to map incoming JSON request paths directly to their originating structural table columns.
* **Equality / Inequality**: `{"$eq": value}`, `{"$ne": value}` automatically map to `=` and `!=`.
* **Comparison**: `{"$gt": ...}`, `{"$gte": ...}`, `{"$lt": ...}`, `{"$lte": ...}` directly compile to Postgres comparison operators (`> `, `>=`, `<`, `<=`).
* **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`).
### The Stem Engine
Rather than over-fetching heavy Entity payloads and trimming them, Punc Framework Websockets depend on isolated subgraphs defined as **Stems**.
A `Stem` is **not a JSON Pointer** or a physical path string (like `/properties/contacts/items/phone_number`). It is simply a declaration of an **Entity Type boundary** that exists somewhere within the compiled JSON Schema graph.
A `Stem` is a declaration of an **Entity Type boundary** that exists somewhere within the compiled JSON Schema graph, expressed using **`gjson` multipath syntax** (e.g., `contacts.#.phone_numbers.#`).
Because `pg_notify` (Beats) fire rigidly from physical Postgres tables (e.g. `{"type": "phone_number"}`), the Go Framework only ever needs to know: "Does the schema `with_contacts.person` contain the `phone_number` Entity anywhere inside its tree?"
Because `pg_notify` (Beats) fire rigidly from physical Postgres tables (e.g. `{"type": "phone_number"}`), the Go Framework only ever needs to know: "Does the schema `with_contacts.person` contain the `phone_number` Entity anywhere inside its tree, and if so, what is the gjson path to iterate its payload?"
* **Initialization:** During startup (`jspg_stems()`), the database crawls all Schemas and maps out every physical Entity Type it references. It builds a flat dictionary of `Schema ID -> [Entity Types]` (e.g. `with_contacts.person -> ["person", "contact", "phone_number", "email_address"]`).
* **Relationship Path Squashing:** When calculating nested string paths structurally to discover these boundaries, JSPG intentionally **omits** properties natively named `target` or `source` if they belong to a native database `relationship` table override. This ensures paths like `phone_numbers/contact/target` correctly register their beat resolution pattern as `phone_numbers/contact/phone_number`.
* **Initialization:** During startup (`jspg_stems()`), the database crawls all Schemas and maps out every physical Entity Type it references. It builds a highly optimized `HashMap<String, HashMap<String, Arc<Stem>>>` providing strictly `O(1)` memory lookups mapping `Schema ID -> { Stem Path -> Entity Type }`.
* **GJSON Pathing:** Unlike standard JSON Pointers, stems utilize `.#` array iterator syntax. The Go web server consumes this native path (e.g. `lines.#`) across the raw Postgres JSON byte payload, extracting all active UUIDs in one massive sub-millisecond sweep without unmarshaling Go ASTs.
* **Polymorphic Condition Selectors:** When trailing paths would otherwise collide because of abstract polymorphic type definitions (e.g., a `target` property bounded by a `oneOf` taking either `phone_number` or `email_address`), JSPG natively appends evaluated `gjson` type conditions into the path (e.g. `contacts.#.target#(type=="phone_number")`). This guarantees `O(1)` key uniqueness in the HashMap while retaining extreme array extraction speeds natively without runtime AST evaluation.
* **Identifier Prioritization:** When determining if a nested object boundary is an Entity, JSPG natively prioritizes defined `$id` tags over `$ref` inheritance pointers to prevent polymorphic boundaries from devolving into their generic base classes.
* **Cyclical Deduplication:** Because Punc relationships often reference back on themselves via deeply nested classes, the Stem Engine applies intelligent path deduplication. If the active `current_path` already ends with the target entity string, it traverses the inheritance properties without appending the entity to the stem path again, eliminating infinite powerset loops.
* **Relationship Path Squashing:** When calculating string paths structurally, JSPG intentionally **omits** properties natively named `target` or `source` if they belong to a native database `relationship` table override.
* **The Go Router**: The Golang Punc framework uses this exact mapping to register WebSocket Beat frequencies exclusively on the Entity types discovered.
* **The Queryer Execution**: When the Go framework asks JSPG to hydrate a partial `phone_number` stem for the `with_contacts.person` schema, instead of jumping through string paths, the SQL Compiler simply reaches into the Schema's AST using the `phone_number` Type string, pulls out exactly that entity's mapping rules, and returns a fully correlated `SELECT` block! This natively handles nested array properties injected via `oneOf` or array references efficiently bypassing runtime powerset expansion.
* **Performance:** These Stem execution structures are fully statically compiled via SPI and map perfectly to `O(1)` real-time routing logic on the application tier.
## 5. Testing & Execution Architecture
JSPG implements a strict separation of concerns to bypass the need to boot a full PostgreSQL cluster for unit and integration testing. Because `pgrx::spi::Spi` directly links to PostgreSQL C-headers, building the library with `cargo test` on macOS natively normally results in fatal `dyld` crashes.
@ -118,7 +133,8 @@ To solve this, JSPG introduces the `DatabaseExecutor` trait inside `src/database
### Universal Test Harness (`src/tests/`)
JSPG abandons the standard `cargo pgrx test` model in favor of native OS testing for a >1000x speed increase (`~0.05s` execution).
1. **JSON Fixtures**: All core interactions are defined abstractly as JSON arrays in `fixtures/`. Each file contains suites of `TestCase` objects with an `action` flag (`validate`, `merge`, `query`).
1. **JSON Fixtures**: All core interactions are defined abstractly as JSON arrays in `fixtures/`. Each file contains suites of `TestCase` objects with an `action` flag (`compile`, `validate`, `merge`, `query`).
2. **`build.rs` Generator**: The build script traverses the JSON fixtures, extracts their structural identities, and generates standard `#[test]` blocks into `src/tests/fixtures.rs`.
3. **Modular Test Dispatcher**: The `src/tests/types/` module deserializes the abstract JSON test payloads into `Suite`, `Case`, and `Expect` data structures.
4. **Unit Context Execution**: When `cargo test` executes, the `Runner` feeds the JSON payloads directly into `case.execute(db)`. Because the tests run natively inside the module via `#cfg(test)`, the Rust compiler globally erases `pgrx` C-linkage, instantiates the `MockExecutor`, and allows for pure structural evaluation of complex database logic completely in memory.
* The `compile` action natively asserts the exact output shape of `jspg_stems`, allowing structural and relationship mapping logic to be tested purely through JSON without writing brute-force manual tests in Rust.
4. **Unit Context Execution**: When `cargo test` executes, the runner iterates the JSON payloads. Because the tests run natively inside the module via `#cfg(test)`, the Rust compiler globally erases `pgrx` C-linkage, instantiates the `MockExecutor`, and allows for pure structural evaluation of complex database logic completely in memory in parallel.

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

312
fixtures/stems.json Normal file
View File

@ -0,0 +1,312 @@
[
{
"description": "Stem Engine Unit Tests",
"database": {
"puncs": [],
"enums": [],
"relations": [
{
"id": "rel1",
"type": "relation",
"constraint": "fk_contact_entity",
"source_type": "contact",
"source_columns": [
"entity_id"
],
"destination_type": "person",
"destination_columns": [
"id"
],
"prefix": null
},
{
"id": "rel2",
"type": "relation",
"constraint": "fk_relationship_target",
"source_type": "relationship",
"source_columns": [
"target_id",
"target_type"
],
"destination_type": "entity",
"destination_columns": [
"id",
"type"
],
"prefix": "target"
}
],
"types": [
{
"name": "entity",
"hierarchy": [
"entity"
],
"schemas": [
{
"$id": "entity",
"type": "object",
"properties": {}
}
]
},
{
"name": "person",
"hierarchy": [
"person",
"entity"
],
"schemas": [
{
"$id": "person",
"$ref": "entity",
"properties": {}
}
]
},
{
"name": "email_address",
"hierarchy": [
"email_address",
"entity"
],
"schemas": [
{
"$id": "email_address",
"$ref": "entity",
"properties": {}
}
]
},
{
"name": "phone_number",
"hierarchy": [
"phone_number",
"entity"
],
"schemas": [
{
"$id": "phone_number",
"$ref": "entity",
"properties": {}
}
]
},
{
"name": "relationship",
"relationship": true,
"hierarchy": [
"relationship",
"entity"
],
"schemas": [
{
"$id": "relationship",
"$ref": "entity",
"properties": {}
}
]
},
{
"name": "contact",
"relationship": true,
"hierarchy": [
"contact",
"relationship",
"entity"
],
"schemas": [
{
"$id": "contact",
"$ref": "relationship",
"properties": {
"target": {
"oneOf": [
{
"$ref": "phone_number"
},
{
"$ref": "email_address"
}
]
}
}
}
]
},
{
"name": "save_person",
"schemas": [
{
"$id": "save_person.response",
"$ref": "person",
"properties": {
"contacts": {
"type": "array",
"items": {
"$ref": "contact"
}
}
}
}
]
}
]
},
"tests": [
{
"description": "correctly squashes deep oneOf refs through array paths",
"action": "compile",
"expect": {
"success": true,
"stems": {
"contact": {
"": {
"schema": {
"$id": "contact",
"$ref": "relationship",
"properties": {
"target": {
"oneOf": [
{
"$ref": "phone_number"
},
{
"$ref": "email_address"
}
]
}
}
},
"type": "contact"
},
"target#(type==\"email_address\")": {
"relation": "target_id",
"schema": {
"$id": "email_address",
"$ref": "entity",
"properties": {}
},
"type": "email_address"
},
"target#(type==\"phone_number\")": {
"relation": "target_id",
"schema": {
"$id": "phone_number",
"$ref": "entity",
"properties": {}
},
"type": "phone_number"
}
},
"email_address": {
"": {
"schema": {
"$id": "email_address",
"$ref": "entity",
"properties": {}
},
"type": "email_address"
}
},
"entity": {
"": {
"schema": {
"$id": "entity",
"properties": {},
"type": "object"
},
"type": "entity"
}
},
"person": {
"": {
"schema": {
"$id": "person",
"$ref": "entity",
"properties": {}
},
"type": "person"
}
},
"phone_number": {
"": {
"schema": {
"$id": "phone_number",
"$ref": "entity",
"properties": {}
},
"type": "phone_number"
}
},
"relationship": {
"": {
"schema": {
"$id": "relationship",
"$ref": "entity",
"properties": {}
},
"type": "relationship"
}
},
"save_person.response": {
"": {
"schema": {
"$id": "save_person.response",
"$ref": "person",
"properties": {
"contacts": {
"items": {
"$ref": "contact"
},
"type": "array"
}
}
},
"type": "person"
},
"contacts.#": {
"relation": "contacts_id",
"schema": {
"$id": "contact",
"$ref": "relationship",
"properties": {
"target": {
"oneOf": [
{
"$ref": "phone_number"
},
{
"$ref": "email_address"
}
]
}
}
},
"type": "contact"
},
"contacts.#.target#(type==\"email_address\")": {
"relation": "target_id",
"schema": {
"$id": "email_address",
"$ref": "entity",
"properties": {}
},
"type": "email_address"
},
"contacts.#.target#(type==\"phone_number\")": {
"relation": "target_id",
"schema": {
"$id": "phone_number",
"$ref": "entity",
"properties": {}
},
"type": "phone_number"
}
}
}
}
}
]
}
]

17
src/bin/ast_explore.rs Normal file
View File

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

View File

@ -1,6 +1,9 @@
#[cfg(test)]
use crate::database::executors::DatabaseExecutor;
#[cfg(test)]
use regex::Regex;
#[cfg(test)]
use serde_json::Value;
#[cfg(test)]
use std::cell::RefCell;
@ -9,6 +12,7 @@ pub struct MockState {
pub captured_queries: Vec<String>,
pub query_responses: Vec<Result<Value, String>>,
pub execute_responses: Vec<Result<(), String>>,
pub mocks: Vec<Value>,
}
#[cfg(test)]
@ -18,6 +22,7 @@ impl MockState {
captured_queries: Default::default(),
query_responses: Default::default(),
execute_responses: Default::default(),
mocks: Default::default(),
}
}
}
@ -44,6 +49,15 @@ impl DatabaseExecutor for MockExecutor {
MOCK_STATE.with(|state| {
let mut s = state.borrow_mut();
s.captured_queries.push(sql.to_string());
if !s.mocks.is_empty() {
if let Some(matches) = parse_and_match_mocks(sql, &s.mocks) {
if !matches.is_empty() {
return Ok(Value::Array(matches));
}
}
}
if s.query_responses.is_empty() {
return Ok(Value::Array(vec![]));
}
@ -76,6 +90,13 @@ impl DatabaseExecutor for MockExecutor {
MOCK_STATE.with(|state| state.borrow().captured_queries.clone())
}
#[cfg(test)]
fn set_mocks(&self, mocks: Vec<Value>) {
MOCK_STATE.with(|state| {
state.borrow_mut().mocks = mocks;
});
}
#[cfg(test)]
fn reset_mocks(&self) {
MOCK_STATE.with(|state| {
@ -83,6 +104,93 @@ impl DatabaseExecutor for MockExecutor {
s.captured_queries.clear();
s.query_responses.clear();
s.execute_responses.clear();
s.mocks.clear();
});
}
}
#[cfg(test)]
fn parse_and_match_mocks(sql: &str, mocks: &[Value]) -> Option<Vec<Value>> {
let sql_upper = sql.to_uppercase();
if !sql_upper.starts_with("SELECT") {
return None;
}
// 1. Extract table name
let table_regex = Regex::new(r#"(?i)\s+FROM\s+(?:[a-zA-Z_]\w*\.)?"?([a-zA-Z_]\w*)"?"#).ok()?;
let table = if let Some(caps) = table_regex.captures(sql) {
caps.get(1)?.as_str()
} else {
return None;
};
// 2. Extract WHERE conditions
let mut conditions = Vec::new();
if let Some(where_idx) = sql_upper.find(" WHERE ") {
let mut where_end = sql_upper.find(" ORDER BY ").unwrap_or(sql.len());
if let Some(limit_idx) = sql_upper.find(" LIMIT ") {
if limit_idx < where_end {
where_end = limit_idx;
}
}
let where_clause = &sql[where_idx + 7..where_end];
let and_regex = Regex::new(r"(?i)\s+AND\s+").ok()?;
let parts = and_regex.split(where_clause);
for part in parts {
if let Some(eq_idx) = part.find('=') {
let left = part[..eq_idx]
.trim()
.split('.')
.last()
.unwrap_or("")
.trim_matches('"');
let right = part[eq_idx + 1..].trim().trim_matches('\'');
conditions.push((left.to_string(), right.to_string()));
} else if part.to_uppercase().contains(" IS NULL") {
let left = part[..part.to_uppercase().find(" IS NULL").unwrap()]
.trim()
.split('.')
.last()
.unwrap_or("")
.replace('"', ""); // Remove quotes explicitly
conditions.push((left, "null".to_string()));
}
}
}
// 3. Find matching mocks
let mut matches = Vec::new();
for mock in mocks {
if let Some(mock_obj) = mock.as_object() {
if let Some(t) = mock_obj.get("type") {
if t.as_str() != Some(table) {
continue;
}
}
let mut matches_all = true;
for (k, v) in &conditions {
let mock_val_str = match mock_obj.get(k) {
Some(Value::String(s)) => s.clone(),
Some(Value::Number(n)) => n.to_string(),
Some(Value::Bool(b)) => b.to_string(),
Some(Value::Null) => "null".to_string(),
_ => {
matches_all = false;
break;
}
};
if mock_val_str != *v {
matches_all = false;
break;
}
}
if matches_all {
matches.push(mock.clone());
}
}
}
Some(matches)
}

View File

@ -25,4 +25,7 @@ pub trait DatabaseExecutor: Send + Sync {
#[cfg(test)]
fn reset_mocks(&self);
#[cfg(test)]
fn set_mocks(&self, mocks: Vec<Value>);
}

View File

@ -25,6 +25,7 @@ impl DatabaseExecutor for SpiExecutor {
}
Spi::connect(|client| {
pgrx::notice!("JSPG_SQL: {}", sql);
match client.select(sql, Some(args_with_oid.len() as i64), &args_with_oid) {
Ok(tup_table) => {
let mut results = Vec::new();
@ -53,6 +54,7 @@ impl DatabaseExecutor for SpiExecutor {
}
Spi::connect_mut(|client| {
pgrx::notice!("JSPG_SQL: {}", sql);
match client.update(sql, Some(args_with_oid.len() as i64), &args_with_oid) {
Ok(_) => Ok(()),
Err(e) => Err(format!("SPI Execution Failure: {}", e)),

View File

@ -265,11 +265,12 @@ impl Database {
String::from(""),
None,
None,
false,
&mut inner_map,
Vec::new(),
&mut errors,
);
if !inner_map.is_empty() {
println!("SCHEMA: {} STEMS: {:?}", schema_id, inner_map.keys());
db_stems.insert(schema_id, inner_map);
}
}
@ -287,24 +288,20 @@ impl Database {
db: &Database,
root_schema_id: &str,
schema: &Schema,
mut current_path: String,
current_path: String,
parent_type: Option<String>,
property_name: Option<String>,
is_polymorphic: bool,
inner_map: &mut HashMap<String, Arc<Stem>>,
seen_entities: Vec<String>,
errors: &mut Vec<crate::drop::Error>,
) {
let mut is_entity = false;
let mut entity_type = String::new();
let mut examine_id = None;
if let Some(ref r) = schema.obj.r#ref {
examine_id = Some(r.clone());
} else if let Some(ref id) = schema.obj.id {
examine_id = Some(id.clone());
}
if let Some(target) = examine_id {
let parts: Vec<&str> = target.split('.').collect();
// First check if the Schema's $id is a native Database Type
if let Some(ref id) = schema.obj.id {
let parts: Vec<&str> = id.split('.').collect();
if let Some(last_seg) = parts.last() {
if db.types.contains_key(*last_seg) {
is_entity = true;
@ -313,6 +310,26 @@ impl Database {
}
}
// If not found via $id, check the $ref pointer
// This allows ad-hoc schemas (like `save_person.response`) to successfully adopt the Type of what they $ref
if !is_entity {
if let Some(ref r) = schema.obj.r#ref {
let parts: Vec<&str> = r.split('.').collect();
if let Some(last_seg) = parts.last() {
if db.types.contains_key(*last_seg) {
is_entity = true;
entity_type = last_seg.to_string();
}
}
}
}
if is_entity {
if seen_entities.contains(&entity_type) {
return; // Break cyclical schemas!
}
}
let mut relation_col = None;
if is_entity {
if let (Some(pt), Some(prop)) = (&parent_type, &property_name) {
@ -334,31 +351,21 @@ impl Database {
}
}
let mut final_path = current_path.clone();
if is_polymorphic && !final_path.is_empty() && !final_path.ends_with(&entity_type) {
if final_path.ends_with(".#") {
final_path = format!("{}(type==\"{}\")", final_path, entity_type);
} else {
final_path = format!("{}#(type==\"{}\")", final_path, entity_type);
}
}
let stem = Stem {
r#type: entity_type.clone(),
relation: relation_col,
schema: Arc::new(schema.clone()),
};
let mut branch_path = current_path.clone();
if !current_path.is_empty() {
branch_path = format!("{}/{}", current_path, entity_type);
}
if inner_map.contains_key(&branch_path) {
errors.push(crate::drop::Error {
code: "STEM_COLLISION".to_string(),
message: format!("The stem path `{}` resolves to multiple Entity boundaries. This usually occurs during un-wrapped $family or oneOf polymorphic schemas where multiple Entities are directly assigned to the same property. To fix this, encapsulate the polymorphic branch.", branch_path),
details: crate::drop::ErrorDetails {
path: root_schema_id.to_string(),
},
});
}
inner_map.insert(branch_path.clone(), Arc::new(stem));
// Update current_path for structural children
current_path = branch_path;
inner_map.insert(final_path, Arc::new(stem));
}
let next_parent = if is_entity {
@ -367,33 +374,22 @@ impl Database {
parent_type.clone()
};
let pass_seen = if is_entity {
let mut ns = seen_entities.clone();
ns.push(entity_type.clone());
ns
} else {
seen_entities.clone()
};
// Properties branch
if let Some(props) = &schema.obj.properties {
for (k, v) in props {
// Bypass target and source properties if we are in a relationship
if let Some(parent_str) = &next_parent {
if let Some(pt) = db.types.get(parent_str) {
if pt.relationship && (k == "target" || k == "source") {
Self::discover_stems(
db,
root_schema_id,
v,
current_path.clone(),
next_parent.clone(),
Some(k.clone()),
inner_map,
errors,
);
continue;
}
}
}
// Standard Property Pathing
let next_path = if current_path.is_empty() {
k.clone()
} else {
format!("{}/{}", current_path, k)
format!("{}.{}", current_path, k)
};
Self::discover_stems(
@ -403,7 +399,9 @@ impl Database {
next_path,
next_parent.clone(),
Some(k.clone()),
false,
inner_map,
pass_seen.clone(),
errors,
);
}
@ -411,18 +409,47 @@ impl Database {
// Array Item branch
if let Some(items) = &schema.obj.items {
let next_path = if current_path.is_empty() {
String::from("#")
} else {
format!("{}.#", current_path)
};
Self::discover_stems(
db,
root_schema_id,
items,
current_path.clone(),
next_path,
next_parent.clone(),
property_name.clone(),
false,
inner_map,
pass_seen.clone(),
errors,
);
}
// Follow external reference if we didn't just crawl local properties
if schema.obj.properties.is_none() && schema.obj.items.is_none() && schema.obj.one_of.is_none()
{
if let Some(ref r) = schema.obj.r#ref {
if let Some(target_schema) = db.schemas.get(r) {
Self::discover_stems(
db,
root_schema_id,
target_schema,
current_path.clone(),
next_parent.clone(),
property_name.clone(),
is_polymorphic,
inner_map,
seen_entities.clone(),
errors,
);
}
}
}
// Polymorphism branch
if let Some(arr) = &schema.obj.one_of {
for v in arr {
@ -433,7 +460,9 @@ impl Database {
current_path.clone(),
next_parent.clone(),
property_name.clone(),
true,
inner_map,
pass_seen.clone(),
errors,
);
}
@ -447,7 +476,9 @@ impl Database {
current_path.clone(),
next_parent.clone(),
property_name.clone(),
is_polymorphic,
inner_map,
pass_seen.clone(),
errors,
);
}

View File

@ -5,7 +5,6 @@ use std::sync::Arc;
// Schema mirrors the Go Punc Generator's schema struct for consistency.
// It is an order-preserving representation of a JSON Schema.
pub fn deserialize_some<'de, D>(deserializer: D) -> Result<Option<Value>, D::Error>
where
D: serde::Deserializer<'de>,
@ -13,117 +12,159 @@ where
let v = Value::deserialize(deserializer)?;
Ok(Some(v))
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct SchemaObject {
// Core Schema Keywords
#[serde(rename = "$id")]
#[serde(skip_serializing_if = "Option::is_none")]
pub id: Option<String>,
#[serde(rename = "$ref")]
#[serde(skip_serializing_if = "Option::is_none")]
pub r#ref: Option<String>,
/*
Note: The `Ref` field in the Go struct is a pointer populated by the linker.
In Rust, we might handle this differently (e.g., separate lookup or Rc/Arc),
so we omit the direct recursive `Ref` field for now and rely on `ref_string`.
*/
#[serde(skip_serializing_if = "Option::is_none")]
pub description: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub title: Option<String>,
#[serde(default)] // Allow missing type
#[serde(rename = "type")]
#[serde(skip_serializing_if = "Option::is_none")]
pub type_: Option<SchemaTypeOrArray>, // Handles string or array of strings
// Object Keywords
#[serde(skip_serializing_if = "Option::is_none")]
pub properties: Option<BTreeMap<String, Arc<Schema>>>,
#[serde(rename = "patternProperties")]
#[serde(skip_serializing_if = "Option::is_none")]
pub pattern_properties: Option<BTreeMap<String, Arc<Schema>>>,
#[serde(rename = "additionalProperties")]
#[serde(skip_serializing_if = "Option::is_none")]
pub additional_properties: Option<Arc<Schema>>,
#[serde(rename = "$family")]
#[serde(skip_serializing_if = "Option::is_none")]
pub family: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub required: Option<Vec<String>>,
// dependencies can be schema dependencies or property dependencies
#[serde(skip_serializing_if = "Option::is_none")]
pub dependencies: Option<BTreeMap<String, Dependency>>,
// Array Keywords
#[serde(rename = "items")]
#[serde(skip_serializing_if = "Option::is_none")]
pub items: Option<Arc<Schema>>,
#[serde(rename = "prefixItems")]
#[serde(skip_serializing_if = "Option::is_none")]
pub prefix_items: Option<Vec<Arc<Schema>>>,
// String Validation
#[serde(rename = "minLength")]
#[serde(skip_serializing_if = "Option::is_none")]
pub min_length: Option<f64>,
#[serde(rename = "maxLength")]
#[serde(skip_serializing_if = "Option::is_none")]
pub max_length: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub pattern: Option<String>,
// Array Validation
#[serde(rename = "minItems")]
#[serde(skip_serializing_if = "Option::is_none")]
pub min_items: Option<f64>,
#[serde(rename = "maxItems")]
#[serde(skip_serializing_if = "Option::is_none")]
pub max_items: Option<f64>,
#[serde(rename = "uniqueItems")]
#[serde(skip_serializing_if = "Option::is_none")]
pub unique_items: Option<bool>,
#[serde(rename = "contains")]
#[serde(skip_serializing_if = "Option::is_none")]
pub contains: Option<Arc<Schema>>,
#[serde(rename = "minContains")]
#[serde(skip_serializing_if = "Option::is_none")]
pub min_contains: Option<f64>,
#[serde(rename = "maxContains")]
#[serde(skip_serializing_if = "Option::is_none")]
pub max_contains: Option<f64>,
// Object Validation
#[serde(rename = "minProperties")]
#[serde(skip_serializing_if = "Option::is_none")]
pub min_properties: Option<f64>,
#[serde(rename = "maxProperties")]
#[serde(skip_serializing_if = "Option::is_none")]
pub max_properties: Option<f64>,
#[serde(rename = "propertyNames")]
#[serde(skip_serializing_if = "Option::is_none")]
pub property_names: Option<Arc<Schema>>,
// Numeric Validation
#[serde(skip_serializing_if = "Option::is_none")]
pub format: Option<String>,
#[serde(rename = "enum")]
#[serde(skip_serializing_if = "Option::is_none")]
pub enum_: Option<Vec<Value>>, // `enum` is a reserved keyword in Rust
#[serde(
default,
rename = "const",
deserialize_with = "crate::database::schema::deserialize_some"
)]
#[serde(skip_serializing_if = "Option::is_none")]
pub const_: Option<Value>,
// Numeric Validation
#[serde(rename = "multipleOf")]
#[serde(skip_serializing_if = "Option::is_none")]
pub multiple_of: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub minimum: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub maximum: Option<f64>,
#[serde(rename = "exclusiveMinimum")]
#[serde(skip_serializing_if = "Option::is_none")]
pub exclusive_minimum: Option<f64>,
#[serde(rename = "exclusiveMaximum")]
#[serde(skip_serializing_if = "Option::is_none")]
pub exclusive_maximum: Option<f64>,
// Combining Keywords
#[serde(rename = "allOf")]
#[serde(skip_serializing_if = "Option::is_none")]
pub all_of: Option<Vec<Arc<Schema>>>,
#[serde(rename = "oneOf")]
#[serde(skip_serializing_if = "Option::is_none")]
pub one_of: Option<Vec<Arc<Schema>>>,
#[serde(rename = "not")]
#[serde(skip_serializing_if = "Option::is_none")]
pub not: Option<Arc<Schema>>,
#[serde(rename = "if")]
#[serde(skip_serializing_if = "Option::is_none")]
pub if_: Option<Arc<Schema>>,
#[serde(rename = "then")]
#[serde(skip_serializing_if = "Option::is_none")]
pub then_: Option<Arc<Schema>>,
#[serde(rename = "else")]
#[serde(skip_serializing_if = "Option::is_none")]
pub else_: Option<Arc<Schema>>,
// Custom Vocabularies
#[serde(skip_serializing_if = "Option::is_none")]
pub form: Option<Vec<String>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub display: Option<Vec<String>>,
#[serde(rename = "enumNames")]
#[serde(skip_serializing_if = "Option::is_none")]
pub enum_names: Option<Vec<String>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub control: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub actions: Option<BTreeMap<String, Action>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub computer: Option<String>,
#[serde(default)]
#[serde(skip_serializing_if = "Option::is_none")]
pub extensible: Option<bool>,
#[serde(skip)]
@ -331,7 +372,9 @@ pub enum SchemaTypeOrArray {
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Action {
#[serde(skip_serializing_if = "Option::is_none")]
pub navigate: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub punc: Option<String>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]

View File

@ -8,10 +8,5 @@ pub struct Stem {
#[serde(skip_serializing_if = "Option::is_none")]
pub relation: Option<String>,
// The actual database schema node mapping for
// O(1) jump table execution for queryer.
//
// Automatically skipped from `jspg_stems()` JSON payload output.
#[serde(skip)]
pub schema: Arc<Schema>,
}

View File

@ -67,6 +67,10 @@ pub struct Error {
#[derive(Debug, Serialize, Deserialize, Clone)]
pub struct ErrorDetails {
pub path: String,
// Extensions can be added here (package, cause, etc)
// For now, validator only provides path
#[serde(skip_serializing_if = "Option::is_none")]
pub cause: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub context: Option<Vec<String>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub schema: Option<String>,
}

View File

@ -1,79 +0,0 @@
# Entity Engine (jspg)
## Overview
This document outlines the architecture for moving the complex, CPU-bound row merging (`merge_entity`) and dynamic querying (`query_entity`) functionality out of PL/pgSQL and directly into the Rust-based `jspg` extension.
By treating the `jspg` schema registry as the absolute Single Source of Truth, we can leverage Rust and the Postgres query planner (via SPI) to achieve near O(1) execution planning for deeply nested reads, complex relational writes, and partial hydration beats.
## The Problem
Historically, `agreego.merge_entity` (PL/pgSQL) handled nested writes by segmenting JSON, resolving types, searching hierarchies, and dynamically concatenating `INSERT`/`UPDATE` statements. `agreego.query_entity` was conceived to do the same for reads (handling base security, inheritance JOINs, and filtering automatically).
However, this design hits three major limitations:
1. **CPU Bound Operations**: PL/pgSQL is comparatively slow at complex string concatenation and massive JSON graph traversals.
2. **Query Planning Cache Busting**: Generating massive, dynamic SQL strings prevents Postgres from caching query plans. `EXECUTE dynamic_sql` forces the planner to re-evaluate statistics and execution paths on every function call, leading to extreme latency spikes at scale.
3. **The Hydration Beat Problem**: The Punc framework requires fetching specific UI "fragments" (e.g. just the `target` of a specific `contact` array element) to feed WebSockets. Hand-rolling CTEs for every possible sub-tree permutation to serve beats will quickly become unmaintainable.
## The Solution: Semantic Engine Database
By migrating `merge_entity` and `query_entity` to `jspg`, we turn the database into a pre-compiled Semantic Engine.
1. **Schema-to-SQL Compilation**: During the connection lifecycle (`cache_json_schemas()`), `jspg` statically analyzes the JSON Schema AST. It acts as a compiler, translating the schema layout into perfectly optimized, multi-JOIN SQL query strings for *every* node/fragment in the schema.
2. **Prepared Statements (SPI)**: `jspg` feeds these computed SQL strings into the Postgres SPI (Server Programming Interface) using `Spi::prepare()`. Postgres calculates the query execution plan *once* and caches it in memory.
3. **Instant Execution**: When a Punc needs data, `jspg` retrieves the cached PreparedStatement, securely binds binary parameters, and executes the pre-planned query instantly.
## Architecture
### 1. The `cache_json_schemas()` Expansion
The initialization function must now ingest `types` and `agreego.relation` data so the internal `Registry` holds the full Relational Graph.
During schema compilation, if a schema is associated with a database Type, it triggers the **SQL Compiler Phase**:
- It builds a table-resolution AST mapping to `JOIN` clauses based on foreign keys.
- It translates JSON schema properties to `SELECT jsonb_build_object(...)`.
- It generates static SQL for `INSERT`, `UPDATE`, and `SELECT` (including path-based fragment SELECTs).
- It calls `Spi::prepare()` to cache these plans inside the Session Context.
### 2. `agreego.query_entity` (Reads)
* **API**: `agreego.query_entity(schema_id TEXT, fragment_path TEXT, cue JSONB)`
* **Execution**:
* Rust locates the target Schema in memory.
* It uses the `fragment_path` (e.g., `/` for a full read, or `/contacts/0/target` for a hydration beat) to fetch the exact PreparedStatement.
* It binds variables (Row Level Security IDs, filtering, pagination limit/offset) parsed from the `cue`.
* SPI returns the heavily nested, pre-aggregated `JSONB` instantly.
### 3. Unified Aggregations & Computeds (Schema `query` objects)
We replace the concept of a complex string parser (PEL) with native structured JSON JSON objects using the `query` keyword.
A structured `query` block in the schema:
```json
"total": {
"type": "number",
"readOnly": true,
"query": {
"aggregate": "sum",
"source": "lines",
"field": "amount"
}
}
```
* **Frontend (Dart)**: The Go generator parses the JSON object directly and emits the native UI aggregation code (e.g. `lines.fold(...)`) for instant UI updates before the server responds.
* **Backend (jspg)**: The Rust SQL compiler natively deserializes the `query` object into an internal struct. It recognizes the `aggregate` instruction and outputs a Postgres native aggregation: `(SELECT SUM(amount) FROM agreego.invoice_line WHERE invoice_id = t1.id)` as a column in the prepared `SELECT` statement.
* **Unification**: The database-calculated value acts as the authoritative truth, synchronizing and correcting the client automatically on the resulting `beat`.
### 4. `agreego.merge_entity` (Writes)
* **API**: `agreego.merge_entity(cue JSONB)`
* **Execution**:
* Parses the incoming `cue` JSON via `serde_json` at C-like speeds.
* Recursively validates and *constructively masks* the tree against the strict schema.
* Traverses the relational graph (which is fully loaded in the `jspg` registry).
* Binds the new values directly into the cached `INSERT` or `UPDATE` SPI prepared statements for each table in the hierarchy.
* Evaluates field differences and natively uses `pg_notify` to fire atomic row-level changes for the Go Beat framework.
## Roadmap
1. **Relational Ingestion**: Update `cache_json_schemas` to pass relational metadata (`agreego.relation` rows) into the `jspg` registry cache.
2. **The SQL Compiler**: Build the AST-to-String compiler in Rust that reads properties, `$ref`s, and `$family` trees to piece together generic SQL.
3. **SPI Caching**: Integrate `Spi::prepare` into the `Validator` creation phase.
4. **Rust `merge_entity`**: Port the constructive structural extraction loop from PL/pgSQL to Rust.
5. **Rust `query_entity`**: Abstract the query runtime, mapping Punc JSON `filters` arrays to SPI-bound parameters safely.

View File

@ -31,6 +31,9 @@ fn jspg_failure() -> JsonB {
message: "JSPG extension has not been initialized via jspg_setup".to_string(),
details: crate::drop::ErrorDetails {
path: "".to_string(),
cause: None,
context: None,
schema: None,
},
};
let drop = crate::drop::Drop::with_errors(vec![error]);
@ -111,9 +114,7 @@ pub fn jspg_validate(schema_id: &str, instance: JsonB) -> JsonB {
}
#[cfg_attr(not(test), pg_extern)]
pub fn jspg_stems() -> JsonB {
use serde_json::{Map, Value};
pub fn jspg_schemas() -> JsonB {
let engine_opt = {
let lock = GLOBAL_JSPG.read().unwrap();
lock.clone()
@ -121,9 +122,30 @@ pub fn jspg_stems() -> JsonB {
match engine_opt {
Some(engine) => {
JsonB(serde_json::to_value(&engine.database.stems).unwrap_or(Value::Object(Map::new())))
let schemas_json = serde_json::to_value(&engine.database.schemas)
.unwrap_or(serde_json::Value::Object(serde_json::Map::new()));
let drop = crate::drop::Drop::success_with_val(schemas_json);
JsonB(serde_json::to_value(drop).unwrap())
}
None => JsonB(Value::Object(Map::new())),
None => jspg_failure(),
}
}
#[cfg_attr(not(test), pg_extern)]
pub fn jspg_stems() -> JsonB {
let engine_opt = {
let lock = GLOBAL_JSPG.read().unwrap();
lock.clone()
};
match engine_opt {
Some(engine) => {
let stems_json = serde_json::to_value(&engine.database.stems)
.unwrap_or(serde_json::Value::Object(serde_json::Map::new()));
let drop = crate::drop::Drop::success_with_val(stems_json);
JsonB(serde_json::to_value(drop).unwrap())
}
None => jspg_failure(),
}
}

View File

@ -21,63 +21,93 @@ impl Merger {
}
pub fn merge(&self, data: Value) -> crate::drop::Drop {
match self.merge_internal(data) {
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) => {
let stripped_val = match val {
Value::Object(mut map) => {
val_resolved = val;
}
Err(msg) => {
return crate::drop::Drop::with_errors(vec![crate::drop::Error {
code: "MERGE_FAILED".to_string(),
message: msg,
details: crate::drop::ErrorDetails {
path: "".to_string(),
cause: None,
context: None,
schema: None,
},
}]);
}
};
// 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 {
code: "MERGE_FAILED".to_string(),
message: format!("Executor Error in pre-ordered notify: {:?}", e),
details: crate::drop::ErrorDetails {
path: "".to_string(),
cause: None,
context: None,
schema: None,
},
}]);
}
}
let stripped_val = match val_resolved {
Value::Object(mut map) => {
let mut out = serde_json::Map::new();
if let Some(id) = map.remove("id") {
out.insert("id".to_string(), id);
}
Value::Object(out)
}
Value::Array(arr) => {
let mut out_arr = Vec::new();
for item in arr {
if let Value::Object(mut map) = item {
let mut out = serde_json::Map::new();
if let Some(id) = map.remove("id") {
out.insert("id".to_string(), id);
}
Value::Object(out)
out_arr.push(Value::Object(out));
} else {
out_arr.push(Value::Null);
}
Value::Array(arr) => {
let mut out_arr = Vec::new();
for item in arr {
if let Value::Object(mut map) = item {
let mut out = serde_json::Map::new();
if let Some(id) = map.remove("id") {
out.insert("id".to_string(), id);
}
out_arr.push(Value::Object(out));
} else {
out_arr.push(Value::Null);
}
}
Value::Array(out_arr)
}
other => other,
};
crate::drop::Drop::success_with_val(stripped_val)
}
Value::Array(out_arr)
}
Err(msg) => crate::drop::Drop::with_errors(vec![crate::drop::Error {
code: "MERGE_FAILED".to_string(),
message: msg,
details: crate::drop::ErrorDetails {
path: "".to_string(),
},
}]),
}
other => other,
};
crate::drop::Drop::success_with_val(stripped_val)
}
pub(crate) fn merge_internal(&self, data: Value) -> 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),
Value::Object(map) => self.merge_object(map),
Value::Array(items) => self.merge_array(items, notifications),
Value::Object(map) => self.merge_object(map, notifications),
_ => Err("Invalid merge payload: root must be an Object or Array".to_string()),
}
}
fn merge_array(&self, items: Vec<Value>) -> 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)?;
let resolved = self.merge_internal(item, notifications)?;
resolved_items.push(resolved);
}
Ok(Value::Array(resolved_items))
}
fn merge_object(&self, obj: serde_json::Map<String, Value>) -> 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()) {
Some(t) => t.to_string(),
None => return Err("Missing required 'type' field on object".to_string()),
@ -147,7 +177,7 @@ impl Merger {
}
}
let merged_relative = match self.merge_internal(Value::Object(relative))? {
let merged_relative = match self.merge_internal(Value::Object(relative), notifications)? {
Value::Object(m) => m,
_ => continue,
};
@ -174,7 +204,7 @@ impl Merger {
&entity_fields,
);
let merged_relative = match self.merge_internal(Value::Object(relative))? {
let merged_relative = match self.merge_internal(Value::Object(relative), notifications)? {
Value::Object(m) => m,
_ => continue,
};
@ -242,7 +272,7 @@ impl Merger {
&entity_fields,
);
let merged_relative = match self.merge_internal(Value::Object(relative_item))? {
let merged_relative = match self.merge_internal(Value::Object(relative_item), notifications)? {
Value::Object(m) => m,
_ => continue,
};
@ -255,7 +285,7 @@ impl Merger {
}
// 7. Perform change tracking
self.merge_entity_change(
let notify_sql = self.merge_entity_change(
&entity_fields,
entity_fetched.as_ref(),
entity_change_kind.as_deref(),
@ -263,6 +293,10 @@ impl Merger {
&timestamp,
)?;
if let Some(sql) = notify_sql {
notifications.insert(queue_start, sql);
}
// Produce the full tree response
let mut final_response = serde_json::Map::new();
if let Some(fetched) = entity_fetched {
@ -396,6 +430,19 @@ impl Merger {
let mut lookup_complete = false;
if !entity_type.lookup_fields.is_empty() {
lookup_complete = true;
for column in &entity_type.lookup_fields {
match entity_fields.get(column) {
Some(Value::Null) | None => {
lookup_complete = false;
break;
}
Some(Value::String(s)) if s.is_empty() => {
lookup_complete = false;
break;
}
_ => {}
}
}
}
if id_val.is_none() && !lookup_complete {
@ -434,11 +481,7 @@ impl Merger {
if column == "type" {
lookup_predicates.push(format!("t1.\"{}\" = {}", column, Self::quote_literal(val)));
} else {
if val.as_str() == Some("") || val.is_null() {
lookup_predicates.push(format!("\"{}\" IS NULL", column));
} else {
lookup_predicates.push(format!("\"{}\" = {}", column, Self::quote_literal(val)));
}
lookup_predicates.push(format!("\"{}\" = {}", column, Self::quote_literal(val)));
}
}
format!("WHERE {}", lookup_predicates.join(" AND "))
@ -605,10 +648,10 @@ impl Merger {
entity_change_kind: Option<&str>,
user_id: &str,
timestamp: &str,
) -> Result<(), String> {
) -> Result<Option<String>, String> {
let change_kind = match entity_change_kind {
Some(k) => k,
None => return Ok(()),
None => return Ok(None),
};
let id_str = entity_fields.get("id").unwrap();
@ -688,12 +731,8 @@ impl Merger {
.db
.execute(&change_sql, None)
.map_err(|e| format!("Executor Error in change: {:?}", e))?;
self
.db
.execute(&notify_sql, None)
.map_err(|e| format!("Executor Error in notify: {:?}", e))?;
Ok(())
Ok(Some(notify_sql))
}
fn compare_entities(

View File

@ -47,7 +47,7 @@ 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)?;
let (sql, _) = self.walk_schema(target_schema, "t1", None, filter_keys, is_stem_query, 0, String::new())?;
Ok(sql)
}
@ -61,17 +61,21 @@ impl SqlCompiler {
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
) -> Result<(String, String), String> {
// Determine the base schema type (could be an array, object, or literal)
match &schema.obj.type_ {
Some(crate::database::schema::SchemaTypeOrArray::Single(t)) if t == "array" => {
// Handle Arrays:
if let Some(items) = &schema.obj.items {
let next_path = if current_path.is_empty() {
String::from("#")
} else {
format!("{}.#", current_path)
};
if let Some(ref_id) = &items.obj.r#ref {
if let Some(type_def) = self.db.types.get(ref_id) {
if is_stem_query && depth > 0 {
return Ok(("".to_string(), "abort".to_string()));
}
return self.compile_entity_node(
items,
type_def,
@ -81,6 +85,7 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth,
next_path,
);
}
}
@ -91,6 +96,7 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth + 1,
next_path,
)?;
return Ok((
format!("(SELECT jsonb_agg({}) FROM TODO)", item_sql),
@ -107,17 +113,14 @@ impl SqlCompiler {
// Determine if this schema represents a Database Entity
let mut resolved_type = None;
// Target is generally a specific schema (e.g. 'base.person'), but it tells us what physical
// database table hierarchy it maps to via the `schema.id` prefix/suffix convention.
if let Some(lookup_key) = schema.obj.id.as_ref().or(schema.obj.r#ref.as_ref()) {
if let Some(family_target) = schema.obj.family.as_ref() {
resolved_type = self.db.types.get(family_target);
} else if let Some(lookup_key) = schema.obj.id.as_ref().or(schema.obj.r#ref.as_ref()) {
let base_type_name = lookup_key.split('.').next_back().unwrap_or("").to_string();
resolved_type = self.db.types.get(&base_type_name);
}
if let Some(type_def) = resolved_type {
if is_stem_query && depth > 0 {
return Ok(("".to_string(), "abort".to_string()));
}
return self.compile_entity_node(
schema,
type_def,
@ -127,6 +130,7 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth,
current_path,
);
}
@ -141,10 +145,50 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth,
current_path,
);
}
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 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));
}
return self.compile_one_of(
&family_schemas,
parent_alias,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path,
);
}
// Handle oneOf Polymorphism fallbacks for relations
if let Some(one_of) = &schema.obj.one_of {
return self.compile_one_of(
one_of,
parent_alias,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path,
);
}
// Just an inline object definition?
if let Some(props) = &schema.obj.properties {
@ -154,6 +198,7 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth,
current_path,
);
}
@ -201,76 +246,57 @@ impl SqlCompiler {
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
) -> Result<(String, String), String> {
// We are compiling a query block for an Entity.
let mut select_args = Vec::new();
// Mapping table hierarchy to aliases, e.g., ["person", "user", "organization", "entity"]
let local_ctx = format!("{}_{}", parent_alias, prop_name.unwrap_or("obj"));
// e.g., parent_t1_contact -> we'll use t1 for the first of this block, t2 for the second, etc.
// Actually, local_ctx can just be exactly that prop's unique path.
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);
table_aliases.insert(table_name.clone(), alias.clone());
// 1. Build FROM clauses and table aliases
let (table_aliases, from_clauses) = self.build_hierarchy_from_clauses(type_def, &local_ctx);
if i == 0 {
from_clauses.push(format!("agreego.{} {}", table_name, alias));
} else {
// Join to previous
let prev_alias = format!("{}_t{}", local_ctx, i);
from_clauses.push(format!(
"JOIN agreego.{} {} ON {}.id = {}.id",
table_name, alias, alias, prev_alias
));
}
}
// 2. Map properties and build jsonb_build_object args
let mut select_args = self.map_properties_to_aliases(
schema,
type_def,
&table_aliases,
parent_alias,
filter_keys,
is_stem_query,
depth,
&current_path,
)?;
// Now, let's map properties from the schema to the correct table alias using grouped_fields
// grouped_fields is { "person": ["first_name", ...], "user": ["password"], ... }
let grouped_fields = type_def.grouped_fields.as_ref().and_then(|v| v.as_object());
let merged_props = self.get_merged_properties(schema);
for (prop_key, prop_schema) in &merged_props {
// Find which table owns this property
// Find which table owns this property
let mut owner_alias = table_aliases
.get("entity")
.cloned()
.unwrap_or_else(|| format!("{}_t_err", parent_alias));
if let Some(gf) = grouped_fields {
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(prop_key)) {
owner_alias = table_aliases
.get(t_name)
.cloned()
.unwrap_or_else(|| parent_alias.to_string());
break;
}
}
// 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));
}
// Now we know `owner_alias`, e.g., `parent_t1` or `parent_t3`.
// Walk the property to get its SQL value
let (val_sql, val_type) = self.walk_schema(
prop_schema,
&owner_alias,
Some(prop_key),
filter_keys,
is_stem_query,
depth + 1,
)?;
if val_type == "abort" {
continue;
}
select_args.push(format!("'{}', {}", prop_key, val_sql));
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));
} 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());
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())?;
select_args.push(format!("'type', {}", case_sql));
}
let jsonb_obj_sql = if select_args.is_empty() {
@ -279,91 +305,17 @@ impl SqlCompiler {
format!("jsonb_build_object({})", select_args.join(", "))
};
let base_alias = table_aliases
.get(&type_def.name)
.cloned()
.unwrap_or_else(|| "err".to_string());
// 3. Build WHERE clauses
let where_clauses = self.build_filter_where_clauses(
schema,
type_def,
&table_aliases,
parent_alias,
prop_name,
filter_keys,
&current_path,
)?;
let mut where_clauses = Vec::new();
where_clauses.push(format!("NOT {}.archived", base_alias));
// Filter Mapping - Only append filters if this is the ROOT table query (i.e. parent_alias is "t1")
// Because cue.filters operates strictly on top-level root properties right now.
if parent_alias == "t1" {
for (i, filter_key) in filter_keys.iter().enumerate() {
// Find which table owns this filter key
let mut filter_alias = base_alias.clone(); // default to root table (e.g. t3 entity)
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(filter_key)) {
filter_alias = table_aliases
.get(t_name)
.cloned()
.unwrap_or_else(|| base_alias.clone());
break;
}
}
}
}
let mut is_ilike = false;
let mut cast = "";
// Use PostgreSQL column type metadata for exact argument casting
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(filter_key) {
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") {
// Determine if this is an enum in the schema locally to avoid ILIKE on strict enums
let mut is_enum = false;
if let Some(props) = &schema.obj.properties {
if let Some(ps) = props.get(filter_key) {
is_enum = ps.obj.enum_.is_some();
}
}
if !is_enum {
is_ilike = true;
}
}
}
}
}
// Add to WHERE clause using 1-indexed args pointer: $1, $2
if is_ilike {
let param = format!("${}#>>'{{}}'", i + 1);
where_clauses.push(format!("{}.{} ILIKE {}", filter_alias, filter_key, param));
} else {
let param = format!("(${}#>>'{{}}'){}", i + 1, cast);
where_clauses.push(format!("{}.{} = {}", filter_alias, filter_key, param));
}
}
}
// Resolve FK relationship constraint if this is a nested subquery
if let Some(_prop) = prop_name {
// MOCK relation resolution (will integrate with `get_entity_relation` properly)
// By default assume FK is parent_id on child
where_clauses.push(format!("{}.parent_id = {}.id", base_alias, parent_alias));
}
// Wrap the object in the final array or object SELECT
let selection = if is_array {
format!("COALESCE(jsonb_agg({}), '[]'::jsonb)", jsonb_obj_sql)
} else {
@ -387,6 +339,268 @@ impl SqlCompiler {
))
}
fn build_hierarchy_from_clauses(
&self,
type_def: &crate::database::r#type::Type,
local_ctx: &str,
) -> (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);
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);
from_clauses.push(format!(
"JOIN agreego.{} {} ON {}.id = {}.id",
table_name, alias, alias, prev_alias
));
}
}
(table_aliases, from_clauses)
}
fn map_properties_to_aliases(
&self,
schema: &crate::database::schema::Schema,
type_def: &crate::database::r#type::Type,
table_aliases: &std::collections::HashMap<String, String>,
parent_alias: &str,
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: &str,
) -> 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);
for (prop_key, prop_schema) in &merged_props {
let mut owner_alias = table_aliases
.get("entity")
.cloned()
.unwrap_or_else(|| format!("{}_t_err", parent_alias));
if let Some(gf) = grouped_fields {
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(prop_key)) {
owner_alias = table_aliases
.get(t_name)
.cloned()
.unwrap_or_else(|| parent_alias.to_string());
break;
}
}
}
}
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
};
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()) {
if !ft.contains_key(prop_key) {
continue; // Skip frontend virtual properties (e.g. `computer` fields, `created`) missing from physical table fields
}
}
}
let next_path = if current_path.is_empty() {
prop_key.clone()
} else {
format!("{}.{}", current_path, prop_key)
};
let (val_sql, val_type) = self.walk_schema(
prop_schema,
&owner_alias,
Some(prop_key),
filter_keys,
is_stem_query,
depth + 1,
next_path,
)?;
if val_type != "abort" {
select_args.push(format!("'{}', {}", prop_key, val_sql));
}
}
Ok(select_args)
}
fn build_filter_where_clauses(
&self,
schema: &crate::database::schema::Schema,
type_def: &crate::database::r#type::Type,
table_aliases: &std::collections::HashMap<String, String>,
parent_alias: &str,
prop_name: Option<&str>,
filter_keys: &[String],
current_path: &str,
) -> Result<Vec<String>, String> {
let base_alias = table_aliases
.get(&type_def.name)
.cloned()
.unwrap_or_else(|| "err".to_string());
let mut where_clauses = Vec::new();
where_clauses.push(format!("NOT {}.archived", base_alias));
for (i, filter_key) in filter_keys.iter().enumerate() {
let mut parts = filter_key.split(':');
let full_field_path = parts.next().unwrap_or(filter_key);
let op = parts.next().unwrap_or("$eq");
let field_name = if current_path.is_empty() {
if full_field_path.contains('.') || full_field_path.contains('#') {
continue;
}
full_field_path
} else {
let prefix = format!("{}.", current_path);
if full_field_path.starts_with(&prefix) {
let remainder = &full_field_path[prefix.len()..];
if remainder.contains('.') || remainder.contains('#') {
continue;
}
remainder
} else {
continue;
}
};
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;
}
}
}
}
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 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
));
} 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_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
));
}
}
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));
}
}
Ok(where_clauses)
}
fn compile_inline_object(
&self,
props: &std::collections::BTreeMap<String, std::sync::Arc<crate::database::schema::Schema>>,
@ -394,9 +608,16 @@ impl SqlCompiler {
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
) -> Result<(String, String), String> {
let mut build_args = Vec::new();
for (k, v) in props {
let next_path = if current_path.is_empty() {
k.clone()
} else {
format!("{}.{}", current_path, k)
};
let (child_sql, val_type) = self.walk_schema(
v,
parent_alias,
@ -404,6 +625,7 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth + 1,
next_path,
)?;
if val_type == "abort" {
continue;
@ -413,4 +635,56 @@ impl SqlCompiler {
let combined = format!("jsonb_build_object({})", build_args.join(", "));
Ok((combined, "object".to_string()))
}
fn compile_one_of(
&self,
schemas: &[Arc<crate::database::schema::Schema>],
parent_alias: &str,
prop_name_context: Option<&str>,
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
) -> Result<(String, String), String> {
let mut case_statements = Vec::new();
let type_col = if let Some(prop) = prop_name_context {
format!("{}_type", prop)
} else {
"type".to_string()
};
for option_schema in schemas {
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,
prop_name_context,
filter_keys,
is_stem_query,
depth,
current_path.clone(),
)?;
case_statements.push(format!(
"WHEN {}.{} = '{}' THEN ({})",
parent_alias, type_col, base_type_name, val_sql
));
}
}
if case_statements.is_empty() {
return Ok(("NULL".to_string(), "string".to_string()));
}
let sql = format!(
"CASE {} ELSE NULL END",
case_statements.join(" ")
);
Ok((sql, "object".to_string()))
}
}

View File

@ -24,61 +24,111 @@ impl Queryer {
stem_opt: Option<&str>,
filters: Option<&serde_json::Value>,
) -> crate::drop::Drop {
let filters_map: Option<&serde_json::Map<String, serde_json::Value>> =
filters.and_then(|f| f.as_object());
let filters_map = filters.and_then(|f| f.as_object());
// Generate Permutation Cache Key: schema_id + sorted filter keys
let mut filter_keys: Vec<String> = Vec::new();
if let Some(fm) = filters_map {
for key in fm.keys() {
filter_keys.push(key.clone());
// 1. Process filters into structured $op keys and linear values
let (filter_keys, args) = match self.parse_filter_entries(filters_map) {
Ok(res) => res,
Err(msg) => {
return crate::drop::Drop::with_errors(vec![crate::drop::Error {
code: "FILTER_PARSE_FAILED".to_string(),
message: msg.clone(),
details: crate::drop::ErrorDetails {
path: "".to_string(), // filters apply to the root query
cause: Some(msg),
context: filters.map(|f| vec![f.to_string()]),
schema: Some(schema_id.to_string()),
},
}]);
}
}
filter_keys.sort();
};
let stem_key = stem_opt.unwrap_or("/");
let cache_key = format!("{}(Stem:{}):{}", schema_id, stem_key, filter_keys.join(","));
let sql = if let Some(cached_sql) = self.cache.get(&cache_key) {
cached_sql.value().clone()
} else {
// Compile the massive base SQL string
let compiler = compiler::SqlCompiler::new(self.db.clone());
match compiler.compile(schema_id, stem_opt, &filter_keys) {
Ok(compiled_sql) => {
self.cache.insert(cache_key.clone(), compiled_sql.clone());
compiled_sql
}
Err(e) => {
return crate::drop::Drop::with_errors(vec![crate::drop::Error {
code: "QUERY_COMPILATION_FAILED".to_string(),
message: e,
details: crate::drop::ErrorDetails {
path: schema_id.to_string(),
},
}]);
}
}
// 2. Fetch from cache or compile
let sql = match self.get_or_compile_sql(&cache_key, schema_id, stem_opt, &filter_keys) {
Ok(sql) => sql,
Err(drop) => return drop,
};
// 2. Prepare the execution arguments from the filters
let mut args: Vec<serde_json::Value> = Vec::new();
// 3. Execute via Database Executor
self.execute_sql(schema_id, &sql, &args)
}
fn parse_filter_entries(
&self,
filters_map: Option<&serde_json::Map<String, serde_json::Value>>,
) -> Result<(Vec<String>, Vec<serde_json::Value>), String> {
let mut filter_entries: Vec<(String, serde_json::Value)> = Vec::new();
if let Some(fm) = filters_map {
for (_i, key) in filter_keys.iter().enumerate() {
if let Some(val) = fm.get(key) {
args.push(val.clone());
for (key, val) in fm {
if let Some(obj) = val.as_object() {
for (op, op_val) in obj {
if !op.starts_with('$') {
return Err(format!("Filter operator must start with '$', got: {}", op));
}
filter_entries.push((format!("{}:{}", key, op), op_val.clone()));
}
} else {
return Err(format!(
"Filter for field '{}' must be an object with operators like $eq, $in, etc.",
key
));
}
}
}
filter_entries.sort_by(|a, b| a.0.cmp(&b.0));
// 3. Execute via Database Executor
match self.db.query(&sql, Some(&args)) {
let filter_keys: Vec<String> = filter_entries.iter().map(|(k, _)| k.clone()).collect();
let args: Vec<serde_json::Value> = filter_entries.into_iter().map(|(_, v)| v).collect();
Ok((filter_keys, args))
}
fn get_or_compile_sql(
&self,
cache_key: &str,
schema_id: &str,
stem_opt: Option<&str>,
filter_keys: &[String],
) -> Result<String, crate::drop::Drop> {
if let Some(cached_sql) = self.cache.get(cache_key) {
return Ok(cached_sql.value().clone());
}
let compiler = compiler::SqlCompiler::new(self.db.clone());
match compiler.compile(schema_id, stem_opt, filter_keys) {
Ok(compiled_sql) => {
self
.cache
.insert(cache_key.to_string(), compiled_sql.clone());
Ok(compiled_sql)
}
Err(e) => Err(crate::drop::Drop::with_errors(vec![crate::drop::Error {
code: "QUERY_COMPILATION_FAILED".to_string(),
message: e.clone(),
details: crate::drop::ErrorDetails {
path: "".to_string(),
cause: Some(e),
context: None,
schema: Some(schema_id.to_string()),
},
}])),
}
}
fn execute_sql(
&self,
schema_id: &str,
sql: &str,
args: &[serde_json::Value],
) -> crate::drop::Drop {
match self.db.query(sql, Some(args)) {
Ok(serde_json::Value::Array(table)) => {
if table.is_empty() {
crate::drop::Drop::success_with_val(serde_json::Value::Null)
} else {
// We expect the query to return a single JSONB column, already unpacked from row[0]
crate::drop::Drop::success_with_val(table.first().unwrap().clone())
}
}
@ -86,14 +136,20 @@ impl Queryer {
code: "QUERY_FAILED".to_string(),
message: format!("Expected array from generic query, got: {:?}", other),
details: crate::drop::ErrorDetails {
path: schema_id.to_string(),
path: "".to_string(),
cause: Some(format!("Expected array, got {}", other)),
context: Some(vec![sql.to_string()]),
schema: Some(schema_id.to_string()),
},
}]),
Err(e) => crate::drop::Drop::with_errors(vec![crate::drop::Error {
code: "QUERY_FAILED".to_string(),
message: format!("SPI error in queryer: {}", e),
details: crate::drop::ErrorDetails {
path: schema_id.to_string(),
path: "".to_string(),
cause: Some(format!("SPI error in queryer: {}", e)),
context: Some(vec![sql.to_string()]),
schema: Some(schema_id.to_string()),
},
}]),
}

View File

@ -1434,39 +1434,45 @@ fn test_queryer_0_3() {
}
#[test]
fn test_queryer_1_0() {
fn test_queryer_0_4() {
let path = format!("{}/fixtures/queryer.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 0).unwrap();
crate::tests::runner::run_test_case(&path, 0, 4).unwrap();
}
#[test]
fn test_queryer_1_1() {
fn test_queryer_0_5() {
let path = format!("{}/fixtures/queryer.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 1).unwrap();
crate::tests::runner::run_test_case(&path, 0, 5).unwrap();
}
#[test]
fn test_queryer_1_2() {
fn test_queryer_0_6() {
let path = format!("{}/fixtures/queryer.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 2).unwrap();
crate::tests::runner::run_test_case(&path, 0, 6).unwrap();
}
#[test]
fn test_queryer_1_3() {
fn test_queryer_0_7() {
let path = format!("{}/fixtures/queryer.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 3).unwrap();
crate::tests::runner::run_test_case(&path, 0, 7).unwrap();
}
#[test]
fn test_queryer_1_4() {
fn test_queryer_0_8() {
let path = format!("{}/fixtures/queryer.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 4).unwrap();
crate::tests::runner::run_test_case(&path, 0, 8).unwrap();
}
#[test]
fn test_queryer_1_5() {
fn test_queryer_0_9() {
let path = format!("{}/fixtures/queryer.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 5).unwrap();
crate::tests::runner::run_test_case(&path, 0, 9).unwrap();
}
#[test]
fn test_queryer_0_10() {
let path = format!("{}/fixtures/queryer.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 0, 10).unwrap();
}
#[test]
@ -3443,6 +3449,12 @@ fn test_if_then_else_13_1() {
crate::tests::runner::run_test_case(&path, 13, 1).unwrap();
}
#[test]
fn test_stems_0_0() {
let path = format!("{}/fixtures/stems.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 0, 0).unwrap();
}
#[test]
fn test_empty_string_0_0() {
let path = format!("{}/fixtures/emptyString.json", env!("CARGO_MANIFEST_DIR"));
@ -8514,31 +8526,43 @@ fn test_merger_0_0() {
}
#[test]
fn test_merger_1_0() {
fn test_merger_0_1() {
let path = format!("{}/fixtures/merger.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 0).unwrap();
crate::tests::runner::run_test_case(&path, 0, 1).unwrap();
}
#[test]
fn test_merger_1_1() {
fn test_merger_0_2() {
let path = format!("{}/fixtures/merger.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 1).unwrap();
crate::tests::runner::run_test_case(&path, 0, 2).unwrap();
}
#[test]
fn test_merger_1_2() {
fn test_merger_0_3() {
let path = format!("{}/fixtures/merger.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 1, 2).unwrap();
crate::tests::runner::run_test_case(&path, 0, 3).unwrap();
}
#[test]
fn test_merger_2_0() {
fn test_merger_0_4() {
let path = format!("{}/fixtures/merger.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 2, 0).unwrap();
crate::tests::runner::run_test_case(&path, 0, 4).unwrap();
}
#[test]
fn test_merger_2_1() {
fn test_merger_0_5() {
let path = format!("{}/fixtures/merger.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 2, 1).unwrap();
crate::tests::runner::run_test_case(&path, 0, 5).unwrap();
}
#[test]
fn test_merger_0_6() {
let path = format!("{}/fixtures/merger.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 0, 6).unwrap();
}
#[test]
fn test_merger_0_7() {
let path = format!("{}/fixtures/merger.json", env!("CARGO_MANIFEST_DIR"));
crate::tests::runner::run_test_case(&path, 0, 7).unwrap();
}

View File

@ -2,6 +2,7 @@ use crate::*;
pub mod runner;
pub mod types;
use serde_json::json;
pub mod sql_validator;
// Database module tests moved to src/database/executors/mock.rs
@ -49,6 +50,25 @@ fn test_library_api() {
})
);
// 3. Validate jspg_schemas
let schemas_drop = jspg_schemas();
assert_eq!(
schemas_drop.0,
json!({
"type": "drop",
"response": {
"test_schema": {
"$id": "test_schema",
"type": "object",
"properties": {
"name": { "type": "string" }
},
"required": ["name"]
}
}
})
);
// 4. Validate Happy Path
let happy_drop = jspg_validate("test_schema", JsonB(json!({"name": "Neo"})));
assert_eq!(

View File

@ -95,19 +95,18 @@ pub fn run_test_case(path: &str, suite_idx: usize, case_idx: usize) -> Result<()
let mut failures = Vec::<String>::new();
// 4. Run Tests
// Provide fallback for legacy expectations if `expect` block was missing despite migration script
let _expected_success = test
.expect
.as_ref()
.map(|e| e.success)
.unwrap_or(test.valid.unwrap_or(false));
let _expected_errors = test
.expect
.as_ref()
.and_then(|e| e.errors.clone())
.unwrap_or(test.expect_errors.clone().unwrap_or(vec![]));
match test.action.as_str() {
"compile" => {
let result = test.run_compile(db.clone());
if let Err(e) = result {
println!("TEST COMPILE ERROR FOR '{}': {}", test.description, e);
failures.push(format!(
"[{}] Compile Test '{}' failed. Error: {}",
group.description, test.description, e
));
}
}
"validate" => {
let result = test.run_validate(db.clone());
if let Err(e) = result {

156
src/tests/sql_validator.rs Normal file
View File

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

View File

@ -31,10 +31,6 @@ pub struct TestCase {
pub mocks: Option<serde_json::Value>,
pub expect: Option<ExpectBlock>,
// Legacy support for older tests to avoid migrating them all instantly
pub valid: Option<bool>,
pub expect_errors: Option<Vec<serde_json::Value>>,
}
fn default_action() -> String {
@ -42,16 +38,39 @@ fn default_action() -> String {
}
impl TestCase {
pub fn execute(&self, db: Arc<Database>) -> Result<(), String> {
match self.action.as_str() {
"validate" => self.run_validate(db),
"merge" => self.run_merge(db),
"query" => self.run_query(db),
_ => Err(format!(
"Unknown action '{}' for test '{}'",
self.action, self.description
)),
pub fn run_compile(&self, db: Arc<Database>) -> Result<(), String> {
let expected_success = self.expect.as_ref().map(|e| e.success).unwrap_or(false);
// We assume db has already been setup and compiled successfully by runner.rs's `jspg_setup`
// We just need to check if there are compilation errors vs expected success
let got_success = true; // Setup ensures success unless setup fails, which runner handles
if expected_success != got_success {
return Err(format!(
"Expected success: {}, Got: {}",
expected_success, got_success
));
}
// Assert stems
if let Some(expect) = &self.expect {
if let Some(expected_stems) = &expect.stems {
// Convert the Db stems (HashMap<String, HashMap<String, Arc<Stem>>>) to matching JSON shape
let db_stems_json = serde_json::to_value(&db.stems).unwrap();
let expect_stems_json = serde_json::to_value(expected_stems).unwrap();
if db_stems_json != expect_stems_json {
let expected_pretty = serde_json::to_string_pretty(&expect_stems_json).unwrap();
let got_pretty = serde_json::to_string_pretty(&db_stems_json).unwrap();
return Err(format!(
"Stem validation failed.\nExpected:\n{}\n\nGot:\n{}",
expected_pretty, got_pretty
));
}
}
}
Ok(())
}
pub fn run_validate(&self, db: Arc<Database>) -> Result<(), String> {
@ -59,18 +78,7 @@ impl TestCase {
let validator = Validator::new(db);
let expected_success = self
.expect
.as_ref()
.map(|e| e.success)
.unwrap_or(self.valid.unwrap_or(false));
// _expected_errors is preserved for future diffing if needed
let _expected_errors = self
.expect
.as_ref()
.and_then(|e| e.errors.clone())
.unwrap_or(self.expect_errors.clone().unwrap_or(vec![]));
let expected_success = self.expect.as_ref().map(|e| e.success).unwrap_or(false);
let schema_id = &self.schema_id;
if !validator.db.schemas.contains_key(schema_id) {
@ -102,6 +110,12 @@ impl TestCase {
}
pub fn run_merge(&self, db: Arc<Database>) -> Result<(), String> {
if let Some(mocks) = &self.mocks {
if let Some(arr) = mocks.as_array() {
db.executor.set_mocks(arr.clone());
}
}
use crate::merger::Merger;
let merger = Merger::new(db.clone());
@ -134,6 +148,12 @@ impl TestCase {
}
pub fn run_query(&self, db: Arc<Database>) -> Result<(), String> {
if let Some(mocks) = &self.mocks {
if let Some(arr) = mocks.as_array() {
db.executor.set_mocks(arr.clone());
}
}
use crate::queryer::Queryer;
let queryer = Queryer::new(db.clone());

View File

@ -1,12 +1,22 @@
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<String>>,
pub sql: Option<Vec<SqlExpectation>>,
}
impl ExpectBlock {
@ -29,8 +39,13 @@ impl ExpectBlock {
));
}
use regex::Regex;
use std::collections::HashMap;
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([
(
@ -53,9 +68,27 @@ impl ExpectBlock {
// Placeholder regex: {{type:name}} or {{type}}
let ph_rx = Regex::new(r"\{\{([a-z]+)(?:[:]([^}]+))?\}\}").unwrap();
for (i, pattern_str) in patterns.iter().enumerate() {
let aline = &actual[i];
let mut pp = regex::escape(pattern_str);
let clean_str = |s: &str| -> String {
let mut s = ws_re.replace_all(s, " ").into_owned();
for token in ["(", ")", ",", "{", "}", "\"", "=", "'"] {
s = s.replace(&format!(" {}", token), token);
s = s.replace(&format!("{} ", token), token);
}
s.trim().to_string()
};
for (i, pattern_expect) in patterns.iter().enumerate() {
let aline_raw = &actual[i];
let aline = clean_str(aline_raw);
let pattern_str_raw = match pattern_expect {
SqlExpectation::Single(s) => s.clone(),
SqlExpectation::Multi(m) => m.join(" "),
};
let pattern_str = clean_str(&pattern_str_raw);
let mut pp = regex::escape(&pattern_str);
pp = pp.replace(r"\{\{", "{{").replace(r"\}\}", "}}");
let mut cap_names = HashMap::new(); // cg_X -> var_name
@ -96,7 +129,7 @@ impl ExpectBlock {
Err(e) => return Err(format!("Bad constructed regex: {} -> {}", final_rx_str, e)),
};
if let Some(captures) = final_rx.captures(aline) {
if let Some(captures) = final_rx.captures(&aline) {
for (cg_name, var_name) in cap_names {
if let Some(m) = captures.name(&cg_name) {
let matched_str = m.as_str();

View File

@ -67,7 +67,12 @@ impl Validator {
.map(|e| crate::drop::Error {
code: e.code,
message: e.message,
details: crate::drop::ErrorDetails { path: e.path },
details: crate::drop::ErrorDetails {
path: e.path,
cause: None,
context: None,
schema: None,
},
})
.collect();
crate::drop::Drop::with_errors(errors)
@ -76,7 +81,12 @@ impl Validator {
Err(e) => crate::drop::Drop::with_errors(vec![crate::drop::Error {
code: e.code,
message: e.message,
details: crate::drop::ErrorDetails { path: e.path },
details: crate::drop::ErrorDetails {
path: e.path,
cause: None,
context: None,
schema: None,
},
}]),
}
} else {
@ -84,7 +94,10 @@ impl Validator {
code: "SCHEMA_NOT_FOUND".to_string(),
message: format!("Schema {} not found", schema_id),
details: crate::drop::ErrorDetails {
path: "".to_string(),
path: "/".to_string(),
cause: None,
context: None,
schema: None,
},
}])
}

View File

@ -1,62 +0,0 @@
Compiling jspg v0.1.0 (/Users/awgneo/Repositories/thoughtpatterns/cellular/jspg)
Finished `test` profile [unoptimized + debuginfo] target(s) in 26.14s
Running unittests src/lib.rs (target/debug/deps/jspg-99ace086c3537f5a)
running 1 test
 Using PgConfig("pg18") and `pg_config` from /opt/homebrew/opt/postgresql@18/bin/pg_config
 Building extension with features pg_test pg18
 Running command "/opt/homebrew/bin/cargo" "build" "--lib" "--features" "pg_test pg18" "--no-default-features" "--message-format=json-render-diagnostics"
Compiling jspg v0.1.0 (/Users/awgneo/Repositories/thoughtpatterns/cellular/jspg)
Finished `dev` profile [unoptimized + debuginfo] target(s) in 7.10s
 Installing extension
 Copying control file to /opt/homebrew/share/postgresql@18/extension/jspg.control
 Copying shared library to /opt/homebrew/lib/postgresql@18/jspg.dylib
 Discovered 351 SQL entities: 1 schemas (1 unique), 350 functions, 0 types, 0 enums, 0 sqls, 0 ords, 0 hashes, 0 aggregates, 0 triggers
 Rebuilding pgrx_embed, in debug mode, for SQL generation with features pg_test pg18
Compiling jspg v0.1.0 (/Users/awgneo/Repositories/thoughtpatterns/cellular/jspg)
Finished `dev` profile [unoptimized + debuginfo] target(s) in 10.63s
 Writing SQL entities to /opt/homebrew/share/postgresql@18/extension/jspg--0.1.0.sql
 Finished installing jspg
[2026-03-01 22:54:19.068 EST] [82952] [69a509eb.14408]: LOG: starting PostgreSQL 18.1 (Homebrew) on aarch64-apple-darwin25.2.0, compiled by Apple clang version 17.0.0 (clang-1700.6.3.2), 64-bit
[2026-03-01 22:54:19.070 EST] [82952] [69a509eb.14408]: LOG: listening on IPv6 address "::1", port 32218
[2026-03-01 22:54:19.070 EST] [82952] [69a509eb.14408]: LOG: listening on IPv4 address "127.0.0.1", port 32218
[2026-03-01 22:54:19.071 EST] [82952] [69a509eb.14408]: LOG: listening on Unix socket "/Users/awgneo/Repositories/thoughtpatterns/cellular/jspg/target/test-pgdata/.s.PGSQL.32218"
[2026-03-01 22:54:19.077 EST] [82958] [69a509eb.1440e]: LOG: database system was shut down at 2026-03-01 22:49:02 EST
 Creating database pgrx_tests
thread 'tests::pg_test_typed_refs_0' (29092254) panicked at /Users/awgneo/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/pgrx-tests-0.16.1/src/framework.rs:166:9:
Postgres Messages:
[2026-03-01 22:54:19.068 EST] [82952] [69a509eb.14408]: LOG: starting PostgreSQL 18.1 (Homebrew) on aarch64-apple-darwin25.2.0, compiled by Apple clang version 17.0.0 (clang-1700.6.3.2), 64-bit
[2026-03-01 22:54:19.070 EST] [82952] [69a509eb.14408]: LOG: listening on IPv6 address "::1", port 32218
[2026-03-01 22:54:19.070 EST] [82952] [69a509eb.14408]: LOG: listening on IPv4 address "127.0.0.1", port 32218
[2026-03-01 22:54:19.071 EST] [82952] [69a509eb.14408]: LOG: listening on Unix socket "/Users/awgneo/Repositories/thoughtpatterns/cellular/jspg/target/test-pgdata/.s.PGSQL.32218"
[2026-03-01 22:54:19.081 EST] [82952] [69a509eb.14408]: LOG: database system is ready to accept connections

Test Function Messages:
[2026-03-01 22:54:20.058 EST] [82982] [69a509ec.14426]: LOG: statement: START TRANSACTION
[2026-03-01 22:54:20.058 EST] [82982] [69a509ec.14426]: LOG: statement: SELECT "tests"."test_typed_refs_0"();
[2026-03-01 22:54:20.062 EST] [82982] [69a509ec.14426]: ERROR: called `Result::unwrap()` on an `Err` value: "[Entity inheritance and native type discrimination] Test 'Valid person against organization schema (implicit type allowance)' failed. Expected: true, Got: false. Errors: [ValidationError { code: \"CONST_VIOLATED\", message: \"Value does not match const\", path: \"/type\" }, ValidationError { code: \"STRICT_PROPERTY_VIOLATION\", message: \"Unexpected property 'first_name'\", path: \"/first_name\" }, ValidationError { code: \"STRICT_PROPERTY_VIOLATION\", message: \"Unexpected property 'first_name'\", path: \"/first_name\" }, ValidationError { code: \"STRICT_PROPERTY_VIOLATION\", message: \"Unexpected property 'first_name'\", path: \"/first_name\" }]\n[Entity inheritance and native type discrimination] Test 'Valid organization against organization schema' failed. Expected: true, Got: false. Errors: [ValidationError { code: \"CONST_VIOLATED\", message: \"Value does not match const\", path: \"/type\" }]\n[Entity inheritance and native type discrimination] Test 'Invalid entity against organization schema (ancestor not allowed)' failed. Expected: false, Got: true. Errors: []"
[2026-03-01 22:54:20.062 EST] [82982] [69a509ec.14426]: STATEMENT: SELECT "tests"."test_typed_refs_0"();
[2026-03-01 22:54:20.062 EST] [82982] [69a509ec.14426]: LOG: statement: ROLLBACK

Client Error:
called `Result::unwrap()` on an `Err` value: "[Entity inheritance and native type discrimination] Test 'Valid person against organization schema (implicit type allowance)' failed. Expected: true, Got: false. Errors: [ValidationError { code: \"CONST_VIOLATED\", message: \"Value does not match const\", path: \"/type\" }, ValidationError { code: \"STRICT_PROPERTY_VIOLATION\", message: \"Unexpected property 'first_name'\", path: \"/first_name\" }, ValidationError { code: \"STRICT_PROPERTY_VIOLATION\", message: \"Unexpected property 'first_name'\", path: \"/first_name\" }, ValidationError { code: \"STRICT_PROPERTY_VIOLATION\", message: \"Unexpected property 'first_name'\", path: \"/first_name\" }]\n[Entity inheritance and native type discrimination] Test 'Valid organization against organization schema' failed. Expected: true, Got: false. Errors: [ValidationError { code: \"CONST_VIOLATED\", message: \"Value does not match const\", path: \"/type\" }]\n[Entity inheritance and native type discrimination] Test 'Invalid entity against organization schema (ancestor not allowed)' failed. Expected: false, Got: true. Errors: []"
postgres location: fixtures.rs
rust location: <unknown>
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
test tests::pg_test_typed_refs_0 ... FAILED
failures:
failures:
tests::pg_test_typed_refs_0
test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 343 filtered out; finished in 21.82s
error: test failed, to rerun pass `--lib`

View File

@ -1 +1 @@
1.0.57
1.0.68