Compare commits

...

16 Commits

Author SHA1 Message Date
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
18 changed files with 2673 additions and 1633 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

@ -80,6 +80,8 @@ The Merger provides an automated, high-performance graph synchronization engine
* **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.
@ -101,22 +103,24 @@ The Queryer transforms Postgres into a pre-compiled Semantic Query Engine via th
* **Array Inclusion**: `{"$in": [values]}`, `{"$nin": [values]}` use native `jsonb_array_elements_text()` bindings to enforce `IN` and `NOT IN` logic without runtime SQL injection risks.
* **Text Matching (ILIKE)**: Evaluates `$eq` or `$ne` against string fields containing the `%` character natively into Postgres `ILIKE` and `NOT ILIKE` partial substring matches.
* **Type Casting**: Safely resolves dynamic combinations by casting values instantly into the physical database types mapped in the schema (e.g. parsing `uuid` bindings to `::uuid`, formatting DateTimes to `::timestamptz`, and numbers to `::numeric`).
### 4. The Stem Engine
### 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"]`).
* **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 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.

View File

@ -1213,21 +1213,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"date_of_birth\":\"2000-01-01\",",
" \"first_name\":\"Bob\",",
" \"id\":\"{{uuid:customer_id}}\",",
" \"last_name\":\"Smith\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"type\":\"person\"",
" }",
"}')"
],
[
"INSERT INTO agreego.\"entity\" (",
" \"created_at\",",
@ -1295,6 +1280,21 @@
" \"type\":\"order\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"date_of_birth\":\"2000-01-01\",",
" \"first_name\":\"Bob\",",
" \"id\":\"{{uuid:customer_id}}\",",
" \"last_name\":\"Smith\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"type\":\"person\"",
" }",
"}')"
]
]
}
@ -1409,21 +1409,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:line_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"order_id\":\"abc\",",
" \"price\":99.0,",
" \"product\":\"Widget\",",
" \"type\":\"order_line\"",
" }",
"}')"
],
[
"INSERT INTO agreego.change (",
" changes,",
@ -1457,6 +1442,21 @@
" \"type\":\"order\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:line_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"order_id\":\"abc\",",
" \"price\":99.0,",
" \"product\":\"Widget\",",
" \"type\":\"order_line\"",
" }",
"}')"
]
]
}
@ -1587,19 +1587,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:phone1_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"number\":\"555-0001\",",
" \"type\":\"phone_number\"",
" }",
"}')"
],
[
"INSERT INTO agreego.\"entity\" (",
" \"created_at\",",
@ -1661,23 +1648,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:contact1_id}}\",",
" \"is_primary\":true,",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"source_id\":\"{{uuid:person_id}}\",",
" \"source_type\":\"person\",",
" \"target_id\":\"{{uuid:phone1_id}}\",",
" \"target_type\":\"phone_number\",",
" \"type\":\"contact\"",
" }",
"}')"
],
[
"INSERT INTO agreego.\"entity\" (",
" \"created_at\",",
@ -1722,19 +1692,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:phone2_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"number\":\"555-0002\",",
" \"type\":\"phone_number\"",
" }",
"}')"
],
[
"INSERT INTO agreego.\"entity\" (",
" \"created_at\",",
@ -1796,23 +1753,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:contact2_id}}\",",
" \"is_primary\":false,",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"source_id\":\"{{uuid:person_id}}\",",
" \"source_type\":\"person\",",
" \"target_id\":\"{{uuid:phone2_id}}\",",
" \"target_type\":\"phone_number\",",
" \"type\":\"contact\"",
" }",
"}')"
],
[
"INSERT INTO agreego.\"entity\" (",
" \"created_at\",",
@ -1857,19 +1797,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"address\":\"test@example.com\",",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:email1_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"type\":\"email_address\"",
" }",
"}')"
],
[
"INSERT INTO agreego.\"entity\" (",
" \"created_at\",",
@ -1931,23 +1858,6 @@
" '00000000-0000-0000-0000-000000000000'",
")"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:contact3_id}}\",",
" \"is_primary\":false,",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"source_id\":\"{{uuid:person_id}}\",",
" \"source_type\":\"person\",",
" \"target_id\":\"{{uuid:email1_id}}\",",
" \"target_type\":\"email_address\",",
" \"type\":\"contact\"",
" }",
"}')"
],
[
"INSERT INTO agreego.change (",
" changes,",
@ -1982,6 +1892,96 @@
" \"type\":\"person\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:contact1_id}}\",",
" \"is_primary\":true,",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"source_id\":\"{{uuid:person_id}}\",",
" \"source_type\":\"person\",",
" \"target_id\":\"{{uuid:phone1_id}}\",",
" \"target_type\":\"phone_number\",",
" \"type\":\"contact\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:phone1_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"number\":\"555-0001\",",
" \"type\":\"phone_number\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:contact2_id}}\",",
" \"is_primary\":false,",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"source_id\":\"{{uuid:person_id}}\",",
" \"source_type\":\"person\",",
" \"target_id\":\"{{uuid:phone2_id}}\",",
" \"target_type\":\"phone_number\",",
" \"type\":\"contact\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:phone2_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"number\":\"555-0002\",",
" \"type\":\"phone_number\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:contact3_id}}\",",
" \"is_primary\":false,",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"source_id\":\"{{uuid:person_id}}\",",
" \"source_type\":\"person\",",
" \"target_id\":\"{{uuid:email1_id}}\",",
" \"target_type\":\"email_address\",",
" \"type\":\"contact\"",
" }",
"}')"
],
[
"SELECT pg_notify('entity', '{",
" \"complete\":{",
" \"address\":\"test@example.com\",",
" \"created_at\":\"{{timestamp}}\",",
" \"created_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"id\":\"{{uuid:email1_id}}\",",
" \"modified_at\":\"{{timestamp}}\",",
" \"modified_by\":\"00000000-0000-0000-0000-000000000000\",",
" \"type\":\"email_address\"",
" }",
"}')"
]
]
}

File diff suppressed because it is too large Load Diff

View File

@ -10,9 +10,13 @@
"type": "relation",
"constraint": "fk_contact_entity",
"source_type": "contact",
"source_columns": ["entity_id"],
"source_columns": [
"entity_id"
],
"destination_type": "person",
"destination_columns": ["id"],
"destination_columns": [
"id"
],
"prefix": null
},
{
@ -20,88 +24,132 @@
"type": "relation",
"constraint": "fk_relationship_target",
"source_type": "relationship",
"source_columns": ["target_id", "target_type"],
"source_columns": [
"target_id",
"target_type"
],
"destination_type": "entity",
"destination_columns": ["id", "type"],
"destination_columns": [
"id",
"type"
],
"prefix": "target"
}
],
"types": [
{
"name": "entity",
"hierarchy": ["entity"],
"schemas": [{
"$id": "entity",
"type": "object",
"properties": {}
}]
"hierarchy": [
"entity"
],
"schemas": [
{
"$id": "entity",
"type": "object",
"properties": {}
}
]
},
{
"name": "person",
"hierarchy": ["person", "entity"],
"schemas": [{
"$id": "person",
"$ref": "entity",
"properties": {}
}]
"hierarchy": [
"person",
"entity"
],
"schemas": [
{
"$id": "person",
"$ref": "entity",
"properties": {}
}
]
},
{
"name": "email_address",
"hierarchy": ["email_address", "entity"],
"schemas": [{
"$id": "email_address",
"$ref": "entity",
"properties": {}
}]
"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": {}
}]
"hierarchy": [
"phone_number",
"entity"
],
"schemas": [
{
"$id": "phone_number",
"$ref": "entity",
"properties": {}
}
]
},
{
"name": "relationship",
"relationship": true,
"hierarchy": ["relationship", "entity"],
"schemas": [{
"$id": "relationship",
"$ref": "entity",
"properties": {}
}]
"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" }
]
"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": { "$ref": "contact" }
"schemas": [
{
"$id": "save_person.response",
"$ref": "person",
"properties": {
"contacts": {
"type": "array",
"items": {
"$ref": "contact"
}
}
}
}
}]
]
}
]
},
@ -112,59 +160,148 @@
"expect": {
"success": true,
"stems": {
"save_person.response": {
"": {
"type": "person"
},
"contacts/contact": {
"type": "contact",
"relation": "contacts_id"
},
"contacts/contact/email_address": {
"type": "email_address",
"relation": "target_id"
},
"contacts/contact/phone_number": {
"type": "phone_number",
"relation": "target_id"
}
},
"contact": {
"": {
"schema": {
"$id": "contact",
"$ref": "relationship",
"properties": {
"target": {
"oneOf": [
{
"$ref": "phone_number"
},
{
"$ref": "email_address"
}
]
}
}
},
"type": "contact"
},
"email_address": {
"type": "email_address",
"relation": "target_id"
"target#(type==\"email_address\")": {
"relation": "target_id",
"schema": {
"$id": "email_address",
"$ref": "entity",
"properties": {}
},
"type": "email_address"
},
"phone_number": {
"type": "phone_number",
"relation": "target_id"
}
},
"person": {
"": {
"type": "person"
"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"
}
},
"phone_number": {
"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",
"$ref": "entity",
"properties": {}
},
"type": "relationship"
}
},
"entity": {
"save_person.response": {
"": {
"type": "entity"
"schema": {
"$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

@ -265,12 +265,12 @@ impl Database {
String::from(""),
None,
None,
true,
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);
}
}
@ -288,11 +288,12 @@ 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_root: bool,
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;
@ -323,6 +324,12 @@ impl Database {
}
}
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) {
@ -344,46 +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 = if is_root {
String::new()
} else if current_path.is_empty() {
entity_type.clone()
} else {
format!("{}/{}", current_path, entity_type)
};
// DEDUPLICATION: If we just recursed into the EXACT same entity type definition,
// do not append again and do not re-register the stem.
let already_registered =
if current_path == entity_type || current_path.ends_with(&format!("/{}", entity_type)) {
branch_path = current_path.clone();
true
} else {
false
};
if !already_registered {
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 {
@ -392,34 +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()),
false,
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(
@ -431,6 +401,7 @@ impl Database {
Some(k.clone()),
false,
inner_map,
pass_seen.clone(),
errors,
);
}
@ -438,15 +409,22 @@ 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, // Arrays themselves aren't polymorphic branches, their items might be
false,
inner_map,
pass_seen.clone(),
errors,
);
}
@ -463,8 +441,9 @@ impl Database {
current_path.clone(),
next_parent.clone(),
property_name.clone(),
false,
is_polymorphic,
inner_map,
seen_entities.clone(),
errors,
);
}
@ -481,8 +460,9 @@ impl Database {
current_path.clone(),
next_parent.clone(),
property_name.clone(),
false,
true,
inner_map,
pass_seen.clone(),
errors,
);
}
@ -496,8 +476,9 @@ impl Database {
current_path.clone(),
next_parent.clone(),
property_name.clone(),
false,
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

@ -111,9 +111,7 @@ 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 +119,30 @@ 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 +21,87 @@ 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(),
},
}]);
}
};
// 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(),
},
}]);
}
}
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 +171,7 @@ 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 +198,7 @@ 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 +266,7 @@ 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 +279,7 @@ 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 +287,10 @@ 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 {
@ -614,10 +642,10 @@ 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();
@ -697,12 +725,8 @@ 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,
);
}
@ -201,6 +246,7 @@ impl SqlCompiler {
filter_keys: &[String],
is_stem_query: bool,
depth: usize,
current_path: String,
) -> Result<(String, String), String> {
let local_ctx = format!("{}_{}", parent_alias, prop_name.unwrap_or("obj"));
@ -208,7 +254,7 @@ impl SqlCompiler {
let (table_aliases, from_clauses) = self.build_hierarchy_from_clauses(type_def, &local_ctx);
// 2. Map properties and build jsonb_build_object args
let select_args = self.map_properties_to_aliases(
let mut select_args = self.map_properties_to_aliases(
schema,
type_def,
&table_aliases,
@ -216,8 +262,43 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth,
&current_path,
)?;
// 2.5 Inject polymorphism directly into the query object
if let Some(family_target) = &schema.obj.family {
let mut family_schemas = Vec::new();
if let Some(base_type) = self.db.types.get(family_target) {
let mut sorted_targets: Vec<String> = base_type.variations.iter().cloned().collect();
// Ensure the base type is included if not listed in variations by default
if !sorted_targets.contains(family_target) {
sorted_targets.push(family_target.clone());
}
sorted_targets.sort();
for target in sorted_targets {
let mut ref_schema = crate::database::schema::Schema::default();
ref_schema.obj.r#ref = Some(target);
family_schemas.push(std::sync::Arc::new(ref_schema));
}
} else {
// Fallback for types not strictly defined in physical DB
let mut ref_schema = crate::database::schema::Schema::default();
ref_schema.obj.r#ref = Some(family_target.clone());
family_schemas.push(std::sync::Arc::new(ref_schema));
}
let base_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() {
"jsonb_build_object()".to_string()
} else {
@ -232,6 +313,7 @@ impl SqlCompiler {
parent_alias,
prop_name,
filter_keys,
&current_path,
)?;
let selection = if is_array {
@ -291,6 +373,7 @@ impl SqlCompiler {
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());
@ -316,6 +399,32 @@ impl SqlCompiler {
}
}
let is_object_or_array = match &prop_schema.obj.type_ {
Some(crate::database::schema::SchemaTypeOrArray::Single(s)) => s == "object" || s == "array",
Some(crate::database::schema::SchemaTypeOrArray::Multiple(v)) => v.contains(&"object".to_string()) || v.contains(&"array".to_string()),
_ => false
};
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,
@ -323,6 +432,7 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth + 1,
next_path,
)?;
if val_type != "abort" {
@ -340,6 +450,7 @@ impl SqlCompiler {
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)
@ -349,15 +460,32 @@ impl SqlCompiler {
let mut where_clauses = Vec::new();
where_clauses.push(format!("NOT {}.archived", base_alias));
if parent_alias == "t1" {
for (i, filter_key) in filter_keys.iter().enumerate() {
let mut parts = filter_key.split(':');
let field_name = parts.next().unwrap_or(filter_key);
let op = parts.next().unwrap_or("$eq");
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 mut filter_alias = base_alias.clone();
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;
}
};
if let Some(gf) = type_def.grouped_fields.as_ref().and_then(|v| v.as_object()) {
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)) {
@ -459,12 +587,15 @@ impl SqlCompiler {
"{}.{} {} {}",
filter_alias, field_name, sql_op, param_sql
));
}
}
}
if let Some(_prop) = prop_name {
where_clauses.push(format!("{}.parent_id = {}.id", base_alias, parent_alias));
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)
@ -477,9 +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,
@ -487,6 +625,7 @@ impl SqlCompiler {
filter_keys,
is_stem_query,
depth + 1,
next_path,
)?;
if val_type == "abort" {
continue;
@ -496,4 +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

@ -1469,6 +1469,12 @@ fn test_queryer_0_9() {
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]
fn test_not_0_0() {
let path = format!("{}/fixtures/not.json", env!("CARGO_MANIFEST_DIR"));

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!(

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

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

View File

@ -1 +1 @@
1.0.59
1.0.66