Open_Ultra_SAST/src/openultrasast/cpg/backend.py

"""The Joern subprocess seam — the single place this codebase touches a CPG engine (Req 4.1, 4.4, 4.5).

Joern is JVM/Scala. Everything crosses one subprocess boundary: ``joern-parse`` builds a ``cpg.bin`` from a
source tree, then ``joern --script`` runs a CPGQL script that prints a JSON payload. Nothing is imported
in-process, so the core install keeps ``dependencies = []`` and an absent engine costs a recorded reason
rather than a traceback.

Two rules hold everywhere below:

* **Fail closed.** A build or query that errors, times out, or prints something unparseable yields *no*
  verdict. The model layer then reports ``suspicion``. A wrong verdict is worse than no verdict — that is the
  whole reason this arbiter exists.
* **Fence the payload.** Joern prints a banner, compilation notices and a REPL prompt on stdout. The script
  brackets its JSON between markers so parsing can never swallow the noise around it.

We do not build a control-flow or dataflow engine here (Req 4.4): the CFG, PDG and call graph our flat IR
lacks are exactly what is being adopted.
"""

from __future__ import annotations

import json
import logging
import os
import shutil
import subprocess
import tempfile
from collections.abc import Callable, Mapping
from dataclasses import dataclass, field
from pathlib import Path
from typing import Protocol

logger = logging.getLogger(__name__)

QUERIES_DIR = Path(__file__).resolve().parent / "queries"

# The payload fence. Joern's stdout carries a banner and a prompt; the script prints these around its JSON.
BEGIN = "---OUSAST-CPG-BEGIN---"
END = "---OUSAST-CPG-END---"

BUILD_TIMEOUT_SECONDS = 900  # a large tree takes minutes; the go/no-go records what it actually cost
QUERY_TIMEOUT_SECONDS = 300
# A JVM with no -Xmx takes a quarter of physical RAM for its heap. On a contributor's laptop that is the
# difference between a scan running in the background and a scan the machine notices, and it made the
# first repository measurements unreproducible: runs were killed under memory pressure at different
# points, so the numbers described the host, not the engine. Bound it, and let the operator raise it.
CPG_HEAP_MB = 2048
HEAP_ENV = "OPENULTRASAST_CPG_HEAP_MB"

# `joern-parse` detects the language and then shells out to a frontend, and on a large tree it can fail where
# the frontend alone succeeds -- measured on a 637-file WordPress plugin, where joern-parse threw after
# applying overlays while `php2cpg` on the same tree produced a 4.3MB CPG with no errors. Joern's own message
# recommends the direct route for large codebases, so this is the documented fallback rather than a
# workaround. The names are Joern's frontend executables.
_FRONTENDS = {
    "php": "php2cpg",
    "python": "pysrc2cpg",
    "javascript": "jssrc2cpg",
    "typescript": "jssrc2cpg",
    "java": "javasrc2cpg",
    "c": "c2cpg",
    "c_cpp": "c2cpg",
}

Runner = Callable[..., subprocess.CompletedProcess[str]]


def extract_payload(stdout: str) -> object | None:
    """The JSON between the fence markers, or ``None`` when it is absent or malformed."""
    start = stdout.find(BEGIN)
    end = stdout.find(END, start + 1) if start >= 0 else -1
    if start < 0 or end < 0:
        return None
    body = stdout[start + len(BEGIN) : end].strip()
    try:
        payload: object = json.loads(body)
    except json.JSONDecodeError:
        logger.debug("cpg query payload was not valid JSON")
        return None
    return payload


@dataclass(frozen=True)
class CpgResult:
    """A built CPG and the ways to query it. Opaque: only ``model/`` reads through these.

    ``run_batch`` is optional so a backend that cannot answer many questions in one invocation still fits
    this shape -- the driver falls back to ``run``, once per request. But a backend that CAN batch must
    attach it HERE, because this is the driver's only way to discover the capability. Leaving it off does
    not fail: it silently costs a JVM per region, which is how batching sat unreachable behind a passing
    test suite until a repository scan made the cost visible.
    """

    cpg_path: Path
    run: Callable[[str, Mapping[str, object]], object | None]
    run_batch: Callable[[str, Mapping[str, Mapping[str, object]]], dict[str, list[object]] | None] | None = None


class CpgBackend(Protocol):
    def available(self) -> bool: ...

    def build(self, root: Path) -> CpgResult | None: ...


@dataclass
class NullBackend:
    """No engine. Every verdict degrades to ``suspicion`` and the caller records ``cpg_unavailable``."""

    reason: str = "cpg_unavailable"

    def available(self) -> bool:
        return False

    def build(self, root: Path) -> CpgResult | None:
        del root
        return None


@dataclass
class JoernBackend:
    """``joern-parse`` then ``joern --script``, both out of process and both timeout-bounded."""

    runner: Runner | None = None
    build_timeout: int = BUILD_TIMEOUT_SECONDS
    query_timeout: int = QUERY_TIMEOUT_SECONDS
    heap_mb: int = 0  # 0 means read the environment, then fall back to CPG_HEAP_MB
    queries_dir: Path = field(default_factory=lambda: QUERIES_DIR)

    def available(self) -> bool:
        from .capability import has_cpg

        return has_cpg()

    def build(self, root: Path, *, language: str = "") -> CpgResult | None:
        """Build a CPG for ``root``. ``None`` on any failure — the caller degrades, never guesses.

        ``language`` lets a failed ``joern-parse`` retry through the frontend directly, which is what Joern
        itself advises for a large codebase and what a 637-file WordPress plugin needed.
        """
        parse = shutil.which("joern-parse")
        if parse is None and os.environ.get("OPENULTRASAST_JOERN_PROBE", "").strip().lower() not in {"1", "on", "true", "yes"}:
            return None
        scratch = Path(tempfile.mkdtemp(prefix="ousast-cpg-"))
        cpg_path = scratch / "cpg.bin"
        command = [parse or "joern-parse", self._heap_flag(), str(root), "--output", str(cpg_path)]
        completed = self._run(command, timeout=self.build_timeout, cwd=scratch)
        if completed is None or completed.returncode != 0 or not cpg_path.is_file():
            detail = (completed.stderr or completed.stdout or "")[-400:] if completed is not None else "timeout"
            logger.warning("cpg build failed for %s: %s", root, detail)
            if not self._build_with_frontend(root, cpg_path, scratch, language):
                return None
        return CpgResult(
            cpg_path=cpg_path,
            run=lambda query, params: self.query(cpg_path, query, params),
            run_batch=lambda query, requests: self.query_batch(cpg_path, query, requests),
        )

    def _build_with_frontend(self, root: Path, cpg_path: Path, scratch: Path, language: str) -> bool:
        """Retry the build through the language frontend alone. False when there is nothing to retry with."""
        frontend = _FRONTENDS.get(language.lower())
        if not frontend:
            return False
        binary = shutil.which(frontend)
        if binary is None:
            logger.warning("no frontend %s on PATH to retry the build for %s", frontend, root)
            return False
        completed = self._run([binary, self._heap_flag(), str(root), "-o", str(cpg_path)], timeout=self.build_timeout, cwd=scratch)
        if completed is None or completed.returncode != 0 or not cpg_path.is_file():
            detail = (completed.stderr or completed.stdout or "")[-400:] if completed is not None else "timeout"
            logger.warning("%s also failed for %s: %s", frontend, root, detail)
            return False
        logger.info("built the cpg for %s with %s after joern-parse failed", root, frontend)
        return True

    def query_batch(self, cpg_path: Path, query: str, requests: Mapping[str, Mapping[str, object]]) -> dict[str, list[object]] | None:
        """Run ONE script invocation carrying many requests, keyed back to their ids.

        JVM startup, not CPG construction, is what dominates a repository scan: every ``joern --script`` call
        starts a JVM of roughly thirty seconds, and issuing one per region per family put a ten-line Python
        file at four minutes and a thousand regions at about fifty hours. The CPG is already built and loaded
        by then; the work itself is milliseconds. So the batch carries the whole scan's questions in one
        parameter and the script loops over them.

        Fails closed like every other path here, and says which kind of nothing it is: an engine that could
        not answer returns ``None`` while a genuine empty answer is ``{}``. That distinction is the whole
        point -- "no rows" and "could not ask" look identical to a caller that only sees a dict, and a
        117k-line PHP CPG that threw while loading turned a failed scan into a clean bill of health.
        """
        script = self.queries_dir / f"{query}.sc"
        if not script.is_file():
            logger.warning("no such cpg query: %s", script)
            return None
        payload = json.dumps({rid: {k: _render(v) for k, v in req.items()} for rid, req in requests.items()})
        # Through a FILE, never the command line. Linux caps a single argument at MAX_ARG_STRLEN (128KB)
        # whatever ARG_MAX says, and a repository blows through that: 2500 taint requests over a 637-file
        # WordPress plugin is a 1.49MB payload. execve returns E2BIG, `_run` catches the OSError, this returns
        # {} -- and {} reads as "no rows found". The scan reported 500 regions examined and nothing found, in
        # 0.05 seconds of taint query, which is a quiet failure of exactly the kind the rung ladder cannot
        # catch because no verdict was ever produced to label.
        requests_file = cpg_path.parent / f"{query}-requests.json"
        try:
            requests_file.write_text(payload)
        except OSError as exc:
            logger.warning("could not stage cpg batch %s: %s", query, exc)
            return None
        command = [
            shutil.which("joern") or "joern",
            self._heap_flag(),
            "--script",
            str(script),
            "--param",
            f"cpgFile={cpg_path}",
            "--param",
            f"requestsFile={requests_file}",
        ]
        completed = self._run(command, timeout=self.query_timeout, cwd=cpg_path.parent)
        if completed is None or completed.returncode != 0:
            detail = (completed.stderr or "")[-400:] if completed is not None else "timeout"
            logger.warning("cpg batch %s failed: %s", query, detail)
            return None
        parsed = extract_payload(completed.stdout or "")
        if not isinstance(parsed, Mapping):
            # Unparseable output is a failure, not an empty answer. A 117k-line PHP CPG that throws while
            # loading printed a stack trace and no payload, and returning {} made the whole scan read as a
            # clean repository -- 500 regions examined, nothing found, no degradation recorded.
            logger.warning("cpg batch %s returned no parseable payload", query)
            return None
        # A request the engine did not answer is absent, not empty: the caller must be able to tell them apart.
        return {str(rid): list(rows) for rid, rows in parsed.items() if isinstance(rows, list)}

    def query(self, cpg_path: Path, query: str, params: Mapping[str, object]) -> object | None:
        """Run a shipped CPGQL script against a built CPG and return its fenced JSON payload."""
        script = self.queries_dir / f"{query}.sc"
        if not script.is_file():
            logger.warning("no such cpg query: %s", script)
            return None
        command = [shutil.which("joern") or "joern", self._heap_flag(), "--script", str(script), "--param", f"cpgFile={cpg_path}"]
        for key, value in sorted(params.items()):
            command += ["--param", f"{key}={_render(value)}"]
        # Joern writes a `workspace/` beside the working directory; run it inside the CPG's own scratch dir so
        # it can never land in the repository being analysed.
        completed = self._run(command, timeout=self.query_timeout, cwd=cpg_path.parent)
        if completed is None or completed.returncode != 0:
            detail = (completed.stderr or "")[-400:] if completed is not None else "timeout"
            logger.warning("cpg query %s failed: %s", query, detail)
            return None
        return extract_payload(completed.stdout or "")

    def _heap_flag(self) -> str:
        """``-J-Xmx``: both launchers forward ``-J`` arguments to the JVM."""
        if self.heap_mb > 0:
            return f"-J-Xmx{self.heap_mb}m"
        configured = os.environ.get(HEAP_ENV, "").strip()
        return f"-J-Xmx{configured if configured.isdigit() else CPG_HEAP_MB}m"

    def _run(self, command: list[str], *, timeout: int, cwd: Path | None = None) -> subprocess.CompletedProcess[str] | None:
        run = self.runner if self.runner is not None else subprocess.run
        try:
            return run(command, capture_output=True, text=True, timeout=timeout, check=False, cwd=str(cwd) if cwd else None)
        except (OSError, subprocess.SubprocessError):
            return None


def _render(value: object) -> str:
    """CPGQL parameters are strings; a sequence becomes a comma-separated list the script splits."""
    if isinstance(value, str):
        return value
    if isinstance(value, (list, tuple, set, frozenset)):
        return ",".join(sorted(str(item) for item in value))
    return str(value)


def resolve_cpg_backend(*, runner: Runner | None = None) -> CpgBackend:
    """The backend for this machine: Joern when it is installed, else the null one."""
    from .capability import has_cpg

    return JoernBackend(runner=runner) if has_cpg() else NullBackend()


__all__ = [
    "BEGIN",
    "END",
    "CpgBackend",
    "CpgResult",
    "JoernBackend",
    "NullBackend",
    "extract_payload",
    "resolve_cpg_backend",
]