backend/app/services/pinescript/validator.py

"""
Pine Script v5 Syntax Validator.

Validates generated Pine Script code for:
  - Version declaration
  - Required structure (strategy or indicator)
  - Bracket/parenthesis matching
  - Known function signatures
  - Common mistakes and deprecated syntax
"""

from __future__ import annotations

import logging
import re
from dataclasses import dataclass
from typing import Any, Dict, List

logger = logging.getLogger(__name__)


@dataclass
class ValidationResult:
    valid: bool
    errors: List[Dict[str, Any]]
    warnings: List[Dict[str, Any]]
    stats: Dict[str, int]


# Pine Script v5 built-in functions / namespaces
VALID_NAMESPACES = {
    "ta", "math", "strategy", "input", "color", "plot", "hline",
    "plotshape", "plotchar", "fill", "bgcolor", "barcolor",
    "request", "str", "array", "matrix", "table", "line", "box",
    "label", "syminfo", "time", "timeframe", "chart",
}

VALID_TA_FUNCTIONS = {
    "sma", "ema", "wma", "rma", "vwma", "swma", "alma",
    "rsi", "macd", "stoch", "cci", "atr", "tr",
    "highest", "lowest", "highestbars", "lowestbars",
    "crossover", "crossunder", "cross",
    "change", "mom", "roc", "percentrank",
    "supertrend", "pivot_point_levels",
    "bb", "kc", "vwap",
    "stdev", "variance", "correlation",
    "barssince", "valuewhen",
    "cum", "rising", "falling",
    "dmi", "mfi", "obv",
}

DEPRECATED_V4 = {
    "study": "indicator",
    "security": "request.security",
    "input": "input.int/input.float/input.bool/input.string",
    "iff": "condition ? value1 : value2",
}


def validate_pine_script(code: str) -> Dict[str, Any]:
    """
    Validate Pine Script v5 code and return errors/warnings.
    """
    errors: List[Dict[str, Any]] = []
    warnings: List[Dict[str, Any]] = []
    lines = code.strip().split("\n")
    stats = {
        "total_lines": len(lines),
        "code_lines": 0,
        "comment_lines": 0,
    }

    if not code.strip():
        errors.append({"line": 0, "message": "Empty code"})
        return ValidationResult(
            valid=False, errors=errors, warnings=warnings, stats=stats
        ).__dict__

    # 1. Version declaration check
    has_version = False
    for i, line in enumerate(lines):
        stripped = line.strip()
        if stripped.startswith("//"):
            stats["comment_lines"] += 1
            if stripped.startswith("//@version=5"):
                has_version = True
        elif stripped:
            stats["code_lines"] += 1

    if not has_version:
        errors.append({
            "line": 1,
            "message": "Missing Pine Script v5 version declaration: //@version=5",
            "severity": "error",
        })

    # 2. Strategy or indicator declaration
    has_strategy = bool(re.search(r'\bstrategy\s*\(', code))
    has_indicator = bool(re.search(r'\bindicator\s*\(', code))
    if not has_strategy and not has_indicator:
        errors.append({
            "line": 0,
            "message": "Missing strategy() or indicator() declaration",
            "severity": "error",
        })

    # 3. Bracket matching
    open_parens = 0
    open_brackets = 0
    for i, line in enumerate(lines, 1):
        stripped = line.strip()
        if stripped.startswith("//"):
            continue
        open_parens += stripped.count("(") - stripped.count(")")
        open_brackets += stripped.count("[") - stripped.count("]")

    if open_parens != 0:
        errors.append({
            "line": 0,
            "message": f"Unmatched parentheses: {'extra (' if open_parens > 0 else 'extra )'}",
            "severity": "error",
        })
    if open_brackets != 0:
        errors.append({
            "line": 0,
            "message": f"Unmatched brackets: {'extra [' if open_brackets > 0 else 'extra ]'}",
            "severity": "error",
        })

    # 4. Deprecated v4 syntax
    for deprecated, replacement in DEPRECATED_V4.items():
        pattern = rf'\b{deprecated}\s*\('
        match = re.search(pattern, code)
        if match:
            # Find line number
            pos = match.start()
            line_num = code[:pos].count("\n") + 1
            # study() is a special case — it was renamed to indicator()
            if deprecated == "study":
                warnings.append({
                    "line": line_num,
                    "message": f"Deprecated: '{deprecated}()' was renamed to '{replacement}()' in v5",
                    "severity": "warning",
                })
            elif deprecated == "security":
                warnings.append({
                    "line": line_num,
                    "message": f"Deprecated: '{deprecated}()' should be '{replacement}()' in v5",
                    "severity": "warning",
                })

    # 5. Strategy without entry
    if has_strategy:
        if "strategy.entry" not in code:
            warnings.append({
                "line": 0,
                "message": "Strategy has no strategy.entry() calls — no trades will be executed",
                "severity": "warning",
            })

    # 6. Check for common mistakes
    if "var " in code:
        # var is valid but sometimes misused
        pass

    # Missing quotes around strings
    name_match = re.search(r'strategy\(\s*([^"\'])', code)
    if name_match:
        pos = name_match.start()
        line_num = code[:pos].count("\n") + 1
        warnings.append({
            "line": line_num,
            "message": "Strategy name should be a quoted string",
            "severity": "warning",
        })

    is_valid = len(errors) == 0

    return {
        "valid": is_valid,
        "errors": [{"line": e["line"], "message": e["message"], "severity": e.get("severity", "error")} for e in errors],
        "warnings": [{"line": w["line"], "message": w["message"], "severity": w.get("severity", "warning")} for w in warnings],
        "stats": stats,
    }