cdsl-cad/cadfs_to_cdsl/featurescript_parser.py

from __future__ import annotations

from typing import Any
from .featurescript_lexer import Token, lex
from .ir import Call, FeatureIR, ModelIR, SketchIR


def _string(value: Any) -> Any:
    if isinstance(value, str) and len(value) >= 2 and value[0] in {'"', "'"} and value[-1] == value[0]:
        try:
            return bytes(value[1:-1], "utf-8").decode("unicode_escape")
        except Exception:
            return value[1:-1]
    return value


class Parser:
    def __init__(self, source: str):
        self.source, self.tokens, self.i = source, lex(source), 0

    def peek(self) -> Token: return self.tokens[self.i]
    def pop(self) -> Token:
        token = self.tokens[self.i]; self.i += 1; return token
    def accept(self, value: str) -> bool:
        if self.peek().value == value: self.i += 1; return True
        return False

    def primary(self) -> Any:
        token = self.pop()
        if token.value == "(":
            value = self.expression(); self.accept(")"); return value
        if token.kind == "string": return _string(token.value)
        if token.kind == "number": return float(token.value)
        if token.kind == "ident":
            if self.accept("("):
                args = []
                while self.peek().kind != "eof" and self.peek().value != ")":
                    args.append(self.expression());
                    if not self.accept(","): break
                self.accept(")")
                return Call(token.value, args, token.line)
            return token.value
        if token.value == "[":
            values = []
            while self.peek().kind != "eof" and self.peek().value != "]":
                values.append(self.expression());
                if not self.accept(","): break
            self.accept("]"); return values
        if token.value == "{":
            obj: dict[str, Any] = {}
            while self.peek().kind != "eof" and self.peek().value != "}":
                key = _string(self.pop().value); self.accept(":"); obj[str(key)] = self.expression()
                if not self.accept(","): break
            self.accept("}"); return obj
        return token.value

    def expression(self, minimum: int = 0) -> Any:
        left = self.primary()
        precedence = {"+": 10, "-": 10, "*": 20, "/": 20}
        while self.peek().value in precedence and precedence[self.peek().value] >= minimum:
            op = self.pop(); right = self.expression(precedence[op.value] + 1)
            left = Call("__binary__", [left, op.value, right], op.line)
        return left

    def statements(self) -> list[Call]:
        found: list[Call] = []; environment: dict[str, Any] = {}
        while self.peek().kind != "eof":
            if self.peek().kind == "ident" and self.i + 1 < len(self.tokens) and self.tokens[self.i + 1].value == "=":
                name = self.pop().value; self.pop()
                try:
                    environment[name] = self.expression()
                    if isinstance(environment[name], Call) and environment[name].name == "newSketch":
                        value = environment[name]
                        value.args = [_resolve(arg, environment) for arg in value.args]
                        found.append(value)
                except Exception: pass
            elif self.peek().kind == "ident" and self.i + 1 < len(self.tokens) and self.tokens[self.i + 1].value == "(":
                value = self.expression()
                if isinstance(value, Call):
                    value.args = [_resolve(arg, environment) for arg in value.args]
                    found.append(value)
            else: self.i += 1
        return found


def _resolve(value: Any, environment: dict[str, Any], seen: set[str] | None = None) -> Any:
    seen = seen or set()
    if isinstance(value, str) and value in environment and value not in seen:
        return _resolve(environment[value], environment, seen | {value})
    if isinstance(value, Call): return Call(value.name, [_resolve(arg, environment, seen) for arg in value.args], value.line, value.raw)
    if isinstance(value, list): return [_resolve(arg, environment, seen) for arg in value]
    if isinstance(value, dict): return {key: _resolve(arg, environment, seen) for key, arg in value.items()}
    return value


def symbolic_string(value: Any) -> str:
    if isinstance(value, Call) and value.name == "__binary__" and value.args[1] == "+":
        return symbolic_string(value.args[0]) + symbolic_string(value.args[2])
    if isinstance(value, str): return "" if value == "id" else value
    return str(value)


def _arg_map(call: Call) -> dict[str, Any]:
    # Object literals are parsed as dictionaries; FeatureScript operation calls
    # conventionally put the definition map in the final argument.
    return next((arg for arg in reversed(call.args) if isinstance(arg, dict)), {})


def parse_featurescript(source: str, sample_id: str = "unknown") -> ModelIR:
    parser = Parser(source); calls = parser.statements(); model = ModelIR(sample_id, raw_source=source)
    for call in calls:
        if call.name == "newSketch":
            definition = _arg_map(call)
            fid = symbolic_string(call.args[1]) if len(call.args) > 1 else f"sketch_{len(model.sketches)}"
            sketch_ir = SketchIR(fid, definition.get("sketchPlane"), [])
            model.sketches.append(sketch_ir); model.steps.append(sketch_ir)
        elif call.name in {"skLineSegment", "skCircle", "skArc", "skEllipse", "skFitSpline", "skPoint"}:
            # Attach sketch entities to the most recently declared sketch.
            if model.sketches:
                args = _arg_map(call); eid = str(call.args[1]) if len(call.args) > 1 else f"E{len(model.sketches[-1].entities)}"
                model.sketches[-1].entities.append(FeatureIR(eid, call.name, args, line_start=call.line, raw_source=call.name))
        elif call.name in {"extrude", "revolve", "fillet", "chamfer", "hole", "linearPattern", "mirror", "cPlane", "referenceAxis", "shell", "loft", "sweep", "circularPattern", "booleanBodies", "transform"}:
            fid = symbolic_string(call.args[1]) if len(call.args) > 1 else f"feature_{len(model.features)}"
            feature_ir = FeatureIR(fid, call.name, _arg_map(call), line_start=call.line, raw_source=call.name)
            model.features.append(feature_ir); model.steps.append(feature_ir)
    return model