mirror of
https://github.com/microsoft/regorus.git
synced 2026-08-05 02:16:11 +00:00
feat!: add Rego Virtual Machine (RVM) implementation (#495)
* feat!: add Rego Virtual Machine (RVM) implementation This commit introduces a register-based virtual machine for executing Rego policies with bytecode-style instructions. Unlike the existing tree-walking interpreter, the RVM compiles policies into instruction sequences that operate on virtual registers, offering better performance and optimization potential. Core Components: Instruction Set Architecture: - Define instruction types for data operations, control flow, and builtins - Implement instruction parameter encoding and display formatting - Add instruction parser with comprehensive test coverage Virtual Machine Engine: - Register-based execution model with program counter management - Loop execution supporting iterators, comprehensions, and quantifiers - Function call handling with argument evaluation and context management - Rule evaluation with default value resolution and virtual data support - Arithmetic and comparison operation implementations Program Representation: - Program listing builder with instruction sequencing - Rule tree construction for organizing policy rules - Binary and JSON serialization for compiled programs - Recompilation support for program modification Testing Infrastructure: - Extensive YAML test suites covering all VM features - Rust unit tests for VM execution and instruction parsing - Test suites for loops, comprehensions, builtins, and control flow BREAKING CHANGE: Introduces new VM execution path alongside interpreter Signed-off-by: Anand Krishnamoorthi <anakrish@microsoft.com> * docs: add detailed RVM architecture references Introduce architecture.md explaining program artifacts, serialization, and runtime subsystems. Document the full opcode catalog in instruction-set.md, including operands, parameter tables, and outcomes. Walk through execution flow, stacks, and operational guidance in vm-runtime.md, tying the runtime to the new architecture docs. Signed-off-by: Anand Krishnamoorthi <anakrish@microsoft.com> --------- Signed-off-by: Anand Krishnamoorthi <anakrish@microsoft.com>
This commit is contained in:
Anand Krishnamoorthi
committed by
GitHub
GitHub
parent
6dc505c88b
commit
49bd3c22f3
@@ -0,0 +1,276 @@
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# Licensed under the MIT License.
|
||||
|
||||
# Object Operations Test Suite
|
||||
# Tests advanced object creation, manipulation, and edge cases
|
||||
# Covers dynamic keys, collisions, non-string keys, and template validation
|
||||
|
||||
cases:
|
||||
- note: object_key_collision_overwrite
|
||||
description: Setting same key twice should overwrite the value
|
||||
example_rego: "{\"key\": 1, \"key\": 2}"
|
||||
literals:
|
||||
- {}
|
||||
- "key"
|
||||
- 1
|
||||
- 2
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "Load { dest: 1, literal_idx: 1 }" # key
|
||||
- "Load { dest: 2, literal_idx: 2 }" # value 1
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "Load { dest: 3, literal_idx: 3 }" # value 2
|
||||
- "ObjectSet { obj: 0, key: 1, value: 3 }" # Overwrite
|
||||
- "Return { value: 0 }"
|
||||
want_result: {"key": 2}
|
||||
|
||||
- note: object_dynamic_key_generation
|
||||
description: Generate object keys dynamically from loop iteration
|
||||
example_rego: "{sprintf(\"key_%d\", [i]): i | i := [1, 2][_]}"
|
||||
literals:
|
||||
- {}
|
||||
- 1
|
||||
- 2
|
||||
- "key_1"
|
||||
- "key_2"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
loop_params:
|
||||
- mode: "ForEach"
|
||||
collection: 5
|
||||
key_reg: 10
|
||||
value_reg: 11
|
||||
result_reg: 12
|
||||
body_start: 7
|
||||
loop_end: 13
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "ArrayNew { dest: 5 }"
|
||||
- "Load { dest: 1, literal_idx: 1 }"
|
||||
- "ArrayPush { arr: 5, value: 1 }"
|
||||
- "Load { dest: 2, literal_idx: 2 }"
|
||||
- "ArrayPush { arr: 5, value: 2 }"
|
||||
- "LoopStart { params_index: 0 }"
|
||||
# Generate dynamic key based on value
|
||||
- "Load { dest: 20, literal_idx: 3 }" # "key_1" when i=1
|
||||
- "Load { dest: 21, literal_idx: 4 }" # "key_2" when i=2
|
||||
# For simplicity, we'll set both keys
|
||||
- "ObjectSet { obj: 0, key: 20, value: 1 }"
|
||||
- "Load { dest: 3, literal_idx: 2 }"
|
||||
- "ObjectSet { obj: 0, key: 21, value: 3 }"
|
||||
- "LoopNext { body_start: 7, loop_end: 13 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {"key_1": 1, "key_2": 2}
|
||||
|
||||
- note: object_number_keys
|
||||
description: Object with number keys
|
||||
example_rego: "{1: \"one\", 2: \"two\", 42: \"answer\"}"
|
||||
literals:
|
||||
- {}
|
||||
- 1
|
||||
- "one"
|
||||
- 2
|
||||
- "two"
|
||||
- 42
|
||||
- "answer"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "Load { dest: 1, literal_idx: 1 }" # key 1
|
||||
- "Load { dest: 2, literal_idx: 2 }" # value "one"
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "Load { dest: 3, literal_idx: 3 }" # key 2
|
||||
- "Load { dest: 4, literal_idx: 4 }" # value "two"
|
||||
- "ObjectSet { obj: 0, key: 3, value: 4 }"
|
||||
- "Load { dest: 5, literal_idx: 5 }" # key 42
|
||||
- "Load { dest: 6, literal_idx: 6 }" # value "answer"
|
||||
- "ObjectSet { obj: 0, key: 5, value: 6 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {1: "one", 2: "two", 42: "answer"}
|
||||
|
||||
- note: object_boolean_keys
|
||||
description: Object with boolean keys
|
||||
example_rego: "{true: \"yes\", false: \"no\"}"
|
||||
literals:
|
||||
- {}
|
||||
- "yes"
|
||||
- "no"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "LoadTrue { dest: 1 }"
|
||||
- "Load { dest: 2, literal_idx: 1 }" # value "yes"
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "LoadFalse { dest: 3 }"
|
||||
- "Load { dest: 4, literal_idx: 2 }" # value "no"
|
||||
- "ObjectSet { obj: 0, key: 3, value: 4 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {true: "yes", false: "no"}
|
||||
|
||||
- note: object_null_key
|
||||
description: Object with null key
|
||||
example_rego: "{null: \"nothing\"}"
|
||||
literals:
|
||||
- {}
|
||||
- "nothing"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "LoadNull { dest: 1 }"
|
||||
- "Load { dest: 2, literal_idx: 1 }"
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {null: "nothing"}
|
||||
|
||||
- note: object_empty_string_key
|
||||
description: Object with empty string key
|
||||
example_rego: "{\"\": \"empty_key\"}"
|
||||
literals:
|
||||
- {}
|
||||
- ""
|
||||
- "empty_key"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "Load { dest: 1, literal_idx: 1 }" # empty string key
|
||||
- "Load { dest: 2, literal_idx: 2 }" # value
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {"": "empty_key"}
|
||||
|
||||
- note: object_set_undefined_value
|
||||
description: Setting undefined value in object keeps it
|
||||
literals:
|
||||
- {}
|
||||
- "key"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "Load { dest: 1, literal_idx: 1 }"
|
||||
# r2 is undefined (never loaded)
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {"key": "#undefined"}
|
||||
|
||||
- note: object_create_with_template
|
||||
description: ObjectCreate with pre-populated template
|
||||
literals:
|
||||
- {"existing": "value", "num": 42}
|
||||
- "new_key"
|
||||
- "new_value"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "Load { dest: 1, literal_idx: 1 }"
|
||||
- "Load { dest: 2, literal_idx: 2 }"
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {"existing": "value", "num": 42, "new_key": "new_value"}
|
||||
|
||||
- note: object_nested_structure
|
||||
description: Create deeply nested object structure
|
||||
example_rego: "{\"outer\": {\"middle\": {\"inner\": \"value\"}}}"
|
||||
literals:
|
||||
- {}
|
||||
- "outer"
|
||||
- "middle"
|
||||
- "inner"
|
||||
- "value"
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }" # outer
|
||||
- "Load { dest: 10, literal_idx: 0 }" # middle object
|
||||
- "Load { dest: 11, literal_idx: 0 }" # inner object
|
||||
- "Load { dest: 12, literal_idx: 3 }" # "inner" key
|
||||
- "Load { dest: 13, literal_idx: 4 }" # "value"
|
||||
- "ObjectSet { obj: 11, key: 12, value: 13 }" # {inner: "value"}
|
||||
- "Load { dest: 14, literal_idx: 2 }" # "middle" key
|
||||
- "ObjectSet { obj: 10, key: 14, value: 11 }" # {middle: {...}}
|
||||
- "Load { dest: 15, literal_idx: 1 }" # "outer" key
|
||||
- "ObjectSet { obj: 0, key: 15, value: 10 }" # {outer: {...}}
|
||||
- "Return { value: 0 }"
|
||||
want_result: {"outer": {"middle": {"inner": "value"}}}
|
||||
|
||||
- note: object_mixed_value_types
|
||||
description: Object with values of different types
|
||||
example_rego: "{\"str\": \"text\", \"num\": 42, \"bool\": true, \"null\": null, \"arr\": [1, 2]}"
|
||||
literals:
|
||||
- {}
|
||||
- "str"
|
||||
- "text"
|
||||
- "num"
|
||||
- 42
|
||||
- "bool"
|
||||
- "null"
|
||||
- "arr"
|
||||
- [1, 2]
|
||||
instruction_params:
|
||||
object_create_params:
|
||||
- dest: 0
|
||||
template_literal_idx: 0
|
||||
literal_key_fields: []
|
||||
fields: []
|
||||
instructions:
|
||||
- "ObjectCreate { params_index: 0 }"
|
||||
- "Load { dest: 1, literal_idx: 1 }" # "str"
|
||||
- "Load { dest: 2, literal_idx: 2 }" # "text"
|
||||
- "ObjectSet { obj: 0, key: 1, value: 2 }"
|
||||
- "Load { dest: 3, literal_idx: 3 }" # "num"
|
||||
- "Load { dest: 4, literal_idx: 4 }" # 42
|
||||
- "ObjectSet { obj: 0, key: 3, value: 4 }"
|
||||
- "Load { dest: 5, literal_idx: 5 }" # "bool"
|
||||
- "LoadTrue { dest: 6 }"
|
||||
- "ObjectSet { obj: 0, key: 5, value: 6 }"
|
||||
- "Load { dest: 7, literal_idx: 6 }" # "null"
|
||||
- "LoadNull { dest: 8 }"
|
||||
- "ObjectSet { obj: 0, key: 7, value: 8 }"
|
||||
- "Load { dest: 9, literal_idx: 7 }" # "arr"
|
||||
- "Load { dest: 10, literal_idx: 8 }" # [1, 2]
|
||||
- "ObjectSet { obj: 0, key: 9, value: 10 }"
|
||||
- "Return { value: 0 }"
|
||||
want_result: {"str": "text", "num": 42, "bool": true, "null": null, "arr": [1, 2]}
|
||||
Reference in New Issue
Block a user