acdl/adapters/terraform/adapter.py

"""ACDL Terraform adapter — stateless assembler (v1.11 RESTART, P56a).

A STATELESS ASSEMBLER. It owns no module content — no resource shape, no
nested HCL blocks, no defaults, no type-specific logic. It reads the
registry to find each L1 module's terraform/ dir, then emits a root
main.tf that instantiates each resource as a `module "<rid>" { source }`
block with resolved inputs and wired refs. Engine-specific knowledge
lives in the per-module terraform/ subdir, NOT in this file.

CLI: adapter.py <instance.json> <out_dir>
"""

import json
import os
import sys


def _load_registry(repo_root):
    """Load registry.json → {module_name: terraform_dir}."""
    with open(os.path.join(repo_root, "modules", "registry.json")) as fh:
        registry = json.load(fh)
    return {n: v.get("1.0.0", {}).get("terraform_dir")
            for n, v in registry.items()
            if v.get("1.0.0", {}).get("terraform_dir")}


def _module_name(resource):
    """Extract the module name from a resource's `module` field (s3@1.0.0 → s3)."""
    return resource.get("module", "").split("@")[0]


def _ref_expr(value, data_source_names=None, id_remap=None):
    """Translate `ref:<rid>.<output>` → `module.<rid>.<output>` (or
    `data.terraform_remote_state.platform.outputs.<output>` for data
    sources). Returns None if not a ref. id_remap rewrites expanded
    multi-resource L1 sub-ids (e.g. alb-targetgroup → alb). CAP-013."""
    if not isinstance(value, str) or not value.startswith("ref:"):
        return None
    rid, out_name = value[len("ref:"):].split(".", 1)
    if data_source_names and rid in data_source_names:
        return f"data.terraform_remote_state.platform.outputs.{out_name}"
    if id_remap:
        rid = id_remap.get(rid, rid)
    return f"module.{rid}.{out_name}"


def _tf_value(value, data_source_names=None, id_remap=None):
    """Render a Python value as a Terraform expression fragment."""
    if isinstance(value, bool):
        return "true" if value else "false"
    if isinstance(value, (int, float)) and not isinstance(value, bool):
        return str(value)
    if isinstance(value, str):
        ref = _ref_expr(value, data_source_names, id_remap)
        if ref is not None:
            return ref
        stripped = value.lstrip()
        if stripped and stripped[0] in "{[":
            try:
                parsed = json.loads(value)
                if isinstance(parsed, (dict, list)):
                    return f"jsonencode({json.dumps(parsed, sort_keys=True)})"
            except json.JSONDecodeError:
                pass
        return f'"{value}"'
    if isinstance(value, (dict, list)):
        return f"jsonencode({json.dumps(value, sort_keys=True)})"
    raise ValueError(f"unsupported input value type {type(value).__name__}")


def _emit_module_block(resource, terraform_dirs, repo_root, data_source_names=None, id_remap=None):
    """Emit a `module "<rid>" { source = ... ... }` block."""
    rid = resource["id"]
    tf_dir = terraform_dirs.get(_module_name(resource))
    if not tf_dir:
        raise ValueError(f"no terraform_dir for module '{_module_name(resource)}' (resource {rid})")
    lines = [f'module "{rid}" {{', f'  source = "{os.path.join(repo_root, tf_dir)}"']
    for in_name, value in resource.get("inputs", {}).items():
        if in_name != "region":
            lines.append(f"  {in_name} = {_tf_value(value, data_source_names, id_remap)}")
    lines.append("}")
    return "\n".join(lines)


def _emit_root_output(out_name, rid, module_output_name):
    """Emit a root output wiring a module output to a stack output."""
    return f'output "{out_name}" {{\n  value = module.{rid}.{module_output_name}\n}}'


def _child_id(group_ids):
    """Composition child id for resource ids sharing one terraform dir.
    Multi-resource L1s expand a child to `<childId>-<subType>` ids; the
    common-prefix (trailing `-` stripped) is the child id. Single-resource
    L1s: the id IS the child id."""
    if len(group_ids) == 1:
        return group_ids[0]
    return os.path.commonprefix([i + "-" for i in group_ids]).rstrip("-") or group_ids[0]


def adapt(stack_instance, out_dir):
    """Emit main.tf + terraform.tf + providers.tf to out_dir for the stack instance."""
    os.makedirs(out_dir, exist_ok=True)
    repo_root = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
    terraform_dirs = _load_registry(repo_root)

    stack = stack_instance.get("stack", {})
    resources = stack_instance.get("resources", [])
    stack_outputs = stack_instance.get("outputs", {})

    region = next((r["inputs"]["region"] for r in resources if "region" in r.get("inputs", {})), "us-east-1")
    providers_tf = f'provider "aws" {{\n  region = "{region}"\n}}\n'

    stack_name = stack.get("name", "spike")
    environment = stack.get("environment", "dev")
    account_id = os.environ.get("ACDL_AWS_ACCOUNT_ID", "581513795199")
    state_bucket = f"acdl-tfstate-{account_id}-us-east-1"
    terraform_tf = (
        'terraform {\n'
        '  required_version = ">= 1.9, < 1.10"\n'
        '  required_providers {\n'
        '    aws = {\n'
        '      source  = "hashicorp/aws"\n'
        '      version = "~> 5.0"\n'
        '    }\n'
        '  }\n'
        '  backend "s3" {\n'
        f'    bucket = "{state_bucket}"\n'
        f'    key    = "spike/{stack_name}/{environment}/terraform.tfstate"\n'
        '    region = "us-east-1"\n'
        '  }\n'
        '}\n'
    )

    data_source_names = stack_instance.get("data_sources", [])
    parts = []
    if data_source_names:
        remote_state_key = os.environ.get("ACDL_REMOTE_STATE_KEY", "platform/terraform.tfstate")
        parts.append(
            'data "terraform_remote_state" "platform" {\n'
            '  backend = "s3"\n'
            '  config = {\n'
            f'    bucket = "{state_bucket}"\n'
            f'    key    = "{remote_state_key}"\n'
            '    region = "us-east-1"\n'
            '  }\n'
            '}\n'
        )

    # Deduplicate multi-resource L1s (ecs-service, alb, ...) to ONE module
    # block per terraform dir, named by the composition child id (common
    # prefix), NOT the first sub-resource id. Stack outputs + cross-module
    # refs reference expanded sub-ids, rewritten via id_remap. CAP-013.
    groups = {}  # terraform_dir → {"ids": [...], "inputs": {}, "module": ""}
    for r in resources:
        tf_dir = terraform_dirs.get(_module_name(r))
        if not tf_dir:
            raise ValueError(f"no terraform_dir for module '{_module_name(r)}' (resource {r['id']})")
        grp = groups.setdefault(tf_dir, {"ids": [], "inputs": {}, "module": r["module"]})
        grp["ids"].append(r["id"])
        for k, v in r.get("inputs", {}).items():
            if k != "region":
                grp["inputs"].setdefault(k, v)

    id_remap = {}
    merged_resources = []
    for tf_dir, grp in groups.items():
        child_id = _child_id(grp["ids"])
        for sub_id in grp["ids"]:
            id_remap[sub_id] = child_id
        merged_resources.append({"id": child_id, "module": grp["module"], "inputs": grp["inputs"]})

    parts.extend(_emit_module_block(r, terraform_dirs, repo_root, set(data_source_names), id_remap)
                 for r in merged_resources)
    for out_name, out_spec in stack_outputs.items():
        if isinstance(out_spec, dict) and "from" in out_spec:
            rid = id_remap.get(out_spec["from"], out_spec["from"])
            parts.append(_emit_root_output(out_name, rid, out_spec.get("output", out_name)))
    main_tf = "\n\n".join(parts) + "\n"

    with open(os.path.join(out_dir, "main.tf"), "w") as fh:
        fh.write(main_tf)
    with open(os.path.join(out_dir, "terraform.tf"), "w") as fh:
        fh.write(terraform_tf)
    with open(os.path.join(out_dir, "providers.tf"), "w") as fh:
        fh.write(providers_tf)
    return out_dir


if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("usage: adapter.py <instance.json> <out_dir>", file=sys.stderr)
        sys.exit(2)
    with open(sys.argv[1], "r") as fh:
        adapt(json.load(fh), sys.argv[2])
    print(f"adapter: emitted terraform to {sys.argv[2]}", file=sys.stderr)