gwc-pybundle 1.4.5__py3-none-any.whl

pybundle/context.py

@@ -0,0 +1,362 @@
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass, field, asdict
+import json
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Iterable, TYPE_CHECKING
+
+from .tools import which
+
+if TYPE_CHECKING:
+    from .steps.base import StepResult
+
+
+def fmt_tool(path: str | None) -> str:
+    if path:
+        return path
+    return "\x1b[31m<missing>\x1b[0m"
+
+
+@dataclass(frozen=True)
+class Tooling:
+    git: str | None
+    python: str | None
+    pip: str | None
+    zip: str | None
+    tar: str | None
+    uname: str | None
+
+    # analysis/debug tools
+    ruff: str | None
+    mypy: str | None
+    pytest: str | None
+    rg: str | None
+    tree: str | None
+    npm: str | None
+    
+    # code quality tools (v1.3.0)
+    vulture: str | None
+    radon: str | None
+    interrogate: str | None
+    pylint: str | None
+    
+    # dependency analysis tools (v1.3.1)
+    pipdeptree: str | None
+    pip_licenses: str | None
+    
+    # performance profiling tools (v1.4.0)
+    line_profiler: str | None
+
+    @staticmethod
+    def detect(strict_paths: bool = False) -> "Tooling":
+        """Detect available tools, optionally enforcing trusted paths.
+
+        Args:
+            strict_paths: If True, only accept tools in trusted system directories
+        """
+        return Tooling(
+            git=which("git", strict=strict_paths),
+            python=which("python", strict=strict_paths)
+            or which("python3", strict=strict_paths),
+            pip=which("pip", strict=strict_paths) or which("pip3", strict=strict_paths),
+            zip=which("zip", strict=strict_paths),
+            tar=which("tar", strict=strict_paths),
+            uname=which("uname", strict=strict_paths),
+            ruff=which("ruff", strict=strict_paths),
+            mypy=which("mypy", strict=strict_paths),
+            pytest=which("pytest", strict=strict_paths),
+            rg=which("rg", strict=strict_paths),
+            tree=which("tree", strict=strict_paths),
+            npm=which("npm", strict=strict_paths),
+            vulture=which("vulture", strict=strict_paths),
+            radon=which("radon", strict=strict_paths),
+            interrogate=which("interrogate", strict=strict_paths),
+            pylint=which("pylint", strict=strict_paths),
+            pipdeptree=which("pipdeptree", strict=strict_paths),
+            pip_licenses=which("pip-licenses", strict=strict_paths),
+            line_profiler=which("kernprof", strict=strict_paths),
+        )
+
+
+@dataclass(frozen=True)
+class RunOptions:
+    no_ruff: bool | None = None
+    no_mypy: bool | None = None
+    no_pylance: bool | None = None
+    no_pytest: bool | None = None
+    no_bandit: bool | None = None
+    no_pip_audit: bool | None = None
+    no_coverage: bool | None = None
+    no_rg: bool | None = None
+    no_error_refs: bool | None = None
+    no_context: bool | None = None
+    no_compileall: bool | None = None
+    
+    # code quality tools (v1.3.0)
+    no_vulture: bool | None = None
+    no_radon: bool | None = None
+    no_interrogate: bool | None = None
+    no_duplication: bool | None = None
+    
+    # dependency analysis tools (v1.3.1)
+    no_pipdeptree: bool | None = None
+    no_unused_deps: bool | None = None
+    no_license_scan: bool | None = None
+    no_dependency_sizes: bool | None = None
+    
+    # performance profiling (v1.4.0)
+    no_profile: bool | None = None
+    profile_entry_point: str | None = None
+    profile_memory: bool = True  # v1.4.2: enabled by default
+    enable_line_profiler: bool = False  # requires @profile decorators
+    
+    # test quality & coverage (v1.4.1)
+    test_flakiness_runs: int = 3
+    slow_test_threshold: float = 1.0
+    enable_mutation_testing: bool = False
+
+    strict_paths: bool = False  # Enforce trusted path validation
+
+    ruff_target: str = "."
+    mypy_target: str = "."
+    pytest_args: list[str] = field(default_factory=lambda: ["-q"])
+
+    error_max_files: int = 250
+    context_depth: int = 2
+    context_max_files: int = 600
+
+
+@dataclass
+class BundleContext:
+    root: Path
+    options: RunOptions
+    outdir: Path
+    profile_name: str
+    ts: str
+    workdir: Path
+    srcdir: Path
+    logdir: Path
+    metadir: Path
+    runlog: Path
+    summary_json: Path
+    manifest_json: Path
+    archive_format: str
+    name_prefix: str
+    strict: bool
+    redact: bool
+    keep_workdir: bool
+    tools: Tooling
+    results: list["StepResult"] = field(default_factory=list)
+    command_used: str = ""
+    json_mode: bool = False
+    archive_path: Path | None = None
+    duration_ms: int | None = None
+
+    def have(self, cmd: str) -> bool:
+        return getattr(self.tools, cmd, None) is not None
+
+    @staticmethod
+    def utc_ts() -> str:
+        return datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
+
+    @classmethod
+    def create(
+        cls,
+        *,
+        root: Path,
+        options: RunOptions | None = None,
+        outdir: Path,
+        profile_name: str,
+        archive_format: str,
+        name_prefix: str | None,
+        strict: bool,
+        redact: bool,
+        keep_workdir: bool,
+        json_mode: bool = False,
+    ) -> "BundleContext":
+        ts = cls.utc_ts()
+        outdir.mkdir(parents=True, exist_ok=True)
+
+        workdir = outdir / f"pybundle_{profile_name}_{ts}"
+        srcdir = workdir / "src"
+        logdir = workdir / "logs"
+        metadir = workdir / "meta"
+
+        srcdir.mkdir(parents=True, exist_ok=True)
+        logdir.mkdir(parents=True, exist_ok=True)
+        metadir.mkdir(parents=True, exist_ok=True)
+
+        runlog = workdir / "RUN_LOG.txt"
+        summary_json = workdir / "SUMMARY.json"
+        manifest_json = workdir / "MANIFEST.json"
+
+        options = options or RunOptions()
+        tools = Tooling.detect(strict_paths=options.strict_paths)
+        prefix = name_prefix or f"pybundle_{profile_name}_{ts}"
+
+        return cls(
+            root=root,
+            options=options,
+            outdir=outdir,
+            profile_name=profile_name,
+            ts=ts,
+            workdir=workdir,
+            srcdir=srcdir,
+            logdir=logdir,
+            metadir=metadir,
+            runlog=runlog,
+            summary_json=summary_json,
+            manifest_json=manifest_json,
+            archive_format=archive_format,
+            name_prefix=prefix,
+            strict=strict,
+            redact=redact,
+            keep_workdir=keep_workdir,
+            tools=tools,
+            json_mode=json_mode,
+        )
+
+    def rel(self, p: Path) -> str:
+        try:
+            return str(p.relative_to(self.root))
+        except Exception:
+            return str(p)
+
+    def redact_text(self, text: str) -> str:
+        if not self.redact:
+            return text
+        # Minimal default redaction rules (you can expand with a rules file later)
+        rules: Iterable[tuple[str, str]] = [
+            (
+                r"(?i)(api[_-]?key)\s*[:=]\s*['\"]?([A-Za-z0-9_\-]{10,})",
+                r"\1=<REDACTED>",
+            ),
+            (r"(?i)(token)\s*[:=]\s*['\"]?([A-Za-z0-9_\-\.]{10,})", r"\1=<REDACTED>"),
+            (r"(?i)(password|passwd|pwd)\s*[:=]\s*['\"]?([^'\"\s]+)", r"\1=<REDACTED>"),
+            (r"(?i)(dsn)\s*[:=]\s*['\"]?([^'\"\s]+)", r"\1=<REDACTED>"),
+        ]
+        out = text
+        for pat, repl in rules:
+            out = re.sub(pat, repl, out)
+        return out
+
+    def write_runlog(self, line: str) -> None:
+        self.runlog.parent.mkdir(parents=True, exist_ok=True)
+        with self.runlog.open("a", encoding="utf-8") as f:
+            f.write(line.rstrip() + "\n")
+
+    def print_doctor(self, profile) -> None:
+        from .doctor import plan_for_profile, print_tool_info
+
+        print(f"Root: {self.root}")
+        print(f"Out:  {self.outdir}\n")
+
+        # Enhanced tool information with security validation
+        print_tool_info(self)
+        print()
+
+        # Options (super useful)
+        print("Options:")
+        o = self.options
+        print(f"  strict_paths:      {o.strict_paths}")
+        print(f"  ruff_target:       {o.ruff_target}")
+        print(f"  mypy_target:       {o.mypy_target}")
+        print(f"  pytest_args:       {' '.join(o.pytest_args)}")
+        print(f"  no_ruff:           {o.no_ruff}")
+        print(f"  no_mypy:           {o.no_mypy}")
+        print(f"  no_pylance:        {o.no_pylance}")
+        print(f"  no_pytest:         {o.no_pytest}")
+        print(f"  no_bandit:         {o.no_bandit}")
+        print(f"  no_pip_audit:      {o.no_pip_audit}")
+        print(f"  no_coverage:       {o.no_coverage}")
+        print(f"  no_rg:             {o.no_rg}")
+        print(f"  no_error_refs:     {o.no_error_refs}")
+        print(f"  no_context:        {o.no_context}")
+        print(f"  error_max_files:   {o.error_max_files}")
+        print(f"  context_depth:     {o.context_depth}")
+        print(f"  context_max_files: {o.context_max_files}")
+        print()
+
+        # Plan
+        plan = plan_for_profile(self, profile)
+
+        print(f"Plan ({profile.name}):")
+        for item in plan:
+            out = f" -> {item.out_rel}" if item.out_rel else ""
+            if item.status == "RUN":
+                print(f"  RUN  {item.name:<28}{out}")
+            else:
+                why = f" ({item.reason})" if item.reason else ""
+                print(f"  SKIP {item.name:<28}{out}{why}")
+
+    def doctor_report(self, profile) -> dict:
+        from .doctor import plan_for_profile
+
+        plan = plan_for_profile(self, profile)
+
+        tools = {}
+        for k, v in asdict(self.tools).items():
+            tools[k] = {"present": v is not None, "path": v}
+
+        o = self.options
+        return {
+            "status": "ok",
+            "command": "doctor",
+            "profile": profile.name,
+            "root": str(self.root),
+            "outdir": str(self.outdir),
+            "tools": tools,
+            "options": {
+                "ruff_target": o.ruff_target,
+                "mypy_target": o.mypy_target,
+                "pytest_args": list(o.pytest_args),
+                "no_ruff": o.no_ruff,
+                "no_mypy": o.no_mypy,
+                "no_pylance": o.no_pylance,
+                "no_pytest": o.no_pytest,
+                "no_bandit": o.no_bandit,
+                "no_pip_audit": o.no_pip_audit,
+                "no_coverage": o.no_coverage,
+                "no_rg": o.no_rg,
+                "no_error_refs": o.no_error_refs,
+                "no_context": o.no_context,
+                "no_vulture": o.no_vulture,
+                "no_radon": o.no_radon,
+                "no_interrogate": o.no_interrogate,
+                "no_duplication": o.no_duplication,
+                "no_pipdeptree": o.no_pipdeptree,
+                "no_unused_deps": o.no_unused_deps,
+                "no_license_scan": o.no_license_scan,
+                "no_dependency_sizes": o.no_dependency_sizes,
+                "no_profile": o.no_profile,
+                "profile_entry_point": o.profile_entry_point,
+                "profile_memory": o.profile_memory,
+                "enable_line_profiler": o.enable_line_profiler,
+                "test_flakiness_runs": o.test_flakiness_runs,
+                "slow_test_threshold": o.slow_test_threshold,
+                "enable_mutation_testing": o.enable_mutation_testing,
+                "error_max_files": o.error_max_files,
+                "context_depth": o.context_depth,
+                "context_max_files": o.context_max_files,
+            },
+            "plan": [
+                {
+                    "name": item.name,
+                    "status": item.status,  # "RUN" or "SKIP"
+                    "out_rel": item.out_rel,
+                    "reason": item.reason,
+                }
+                for item in plan
+            ],
+        }
+
+    def emit(self, msg: str) -> None:
+        """Human output only."""
+        if not self.json_mode:
+            print(msg)
+
+    def emit_json(self, payload: dict) -> None:
+        """JSON output only (stdout contract)."""
+        print(json.dumps(payload, ensure_ascii=False))

pybundle/doctor.py

@@ -0,0 +1,148 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any, Callable, TypeVar
+
+from .steps.shell import ShellStep
+from .steps.ruff import RuffCheckStep, RuffFormatCheckStep
+from .steps.mypy import MypyStep
+from .steps.pytest import PytestStep
+from .steps.rg_scans import RipgrepScanStep
+from .tools import is_path_trusted
+
+T = TypeVar("T")
+
+
+@dataclass(frozen=True)
+class PlanItem:
+    name: str
+    status: str  # "RUN" | "SKIP"
+    out_rel: str | None
+    reason: str
+
+
+EvalFn = Callable[[Any, T], PlanItem]
+
+
+def _out(step: Any) -> str | None:
+    return (
+        getattr(step, "out_rel", None)
+        or getattr(step, "outfile_rel", None)
+        or getattr(step, "outfile", None)
+    )
+
+
+def eval_shell(ctx: Any, step: ShellStep) -> PlanItem:
+    if step.require_cmd and not ctx.have(step.require_cmd):
+        return PlanItem(
+            step.name, "SKIP", _out(step), f"missing tool: {step.require_cmd}"
+        )
+    return PlanItem(step.name, "RUN", _out(step), "")
+
+
+def eval_ruff(ctx: Any, step: Any) -> PlanItem:
+    if ctx.options.no_ruff:
+        return PlanItem(step.name, "SKIP", _out(step), "disabled by --no-ruff")
+    if not ctx.have("ruff"):
+        return PlanItem(step.name, "SKIP", _out(step), "missing tool: ruff")
+    return PlanItem(step.name, "RUN", _out(step), "")
+
+
+def eval_mypy(ctx: Any, step: MypyStep) -> PlanItem:
+    if ctx.options.no_mypy:
+        return PlanItem(step.name, "SKIP", _out(step), "disabled by --no-mypy")
+    if not ctx.have("mypy"):
+        return PlanItem(step.name, "SKIP", _out(step), "missing tool: mypy")
+    return PlanItem(step.name, "RUN", _out(step), "")
+
+
+def eval_pytest(ctx: Any, step: PytestStep) -> PlanItem:
+    if ctx.options.no_pytest:
+        return PlanItem(step.name, "SKIP", _out(step), "disabled by --no-pytest")
+    if not ctx.have("pytest"):
+        return PlanItem(step.name, "SKIP", _out(step), "missing tool: pytest")
+    if (
+        not (ctx.root / "tests").exists()
+        and not (ctx.root / "sentra" / "tests").exists()
+    ):
+        return PlanItem(step.name, "SKIP", _out(step), "no tests/ directory found")
+    return PlanItem(step.name, "RUN", _out(step), "")
+
+
+def eval_rg(ctx: Any, step: Any) -> PlanItem:
+    if ctx.options.no_rg:
+        return PlanItem(step.name, "SKIP", _out(step), "disabled by --no-rg")
+    if not ctx.have("rg"):
+        return PlanItem(step.name, "SKIP", _out(step), "missing tool: rg")
+    return PlanItem(step.name, "RUN", _out(step), "")
+
+
+REGISTRY: list[tuple[type[Any], Callable[[Any, Any], PlanItem]]] = [
+    (ShellStep, eval_shell),
+    (RuffCheckStep, eval_ruff),
+    (RuffFormatCheckStep, eval_ruff),
+    (MypyStep, eval_mypy),
+    (PytestStep, eval_pytest),
+    (RipgrepScanStep, eval_rg),
+]
+
+
+def plan_for_profile(ctx: Any, profile: Any) -> list[PlanItem]:
+    items: list[PlanItem] = []
+    for step in profile.steps:
+        item: PlanItem | None = None
+
+        for cls, fn in REGISTRY:
+            if isinstance(step, cls):
+                item = fn(ctx, step)
+                break
+        if item is None:
+            item = PlanItem(step.name, "RUN", _out(step), "")
+        items.append(item)
+    return items
+
+
+def print_tool_info(ctx: Any) -> None:
+    """Print tool availability with security validation status."""
+
+    tools_data = [
+        ("git", ctx.tools.git),
+        ("python", ctx.tools.python),
+        ("pip", ctx.tools.pip),
+        ("zip", ctx.tools.zip),
+        ("tar", ctx.tools.tar),
+        ("uname", ctx.tools.uname),
+        ("ruff", ctx.tools.ruff),
+        ("mypy", ctx.tools.mypy),
+        ("pytest", ctx.tools.pytest),
+        ("rg", ctx.tools.rg),
+        ("tree", ctx.tools.tree),
+        ("npm", ctx.tools.npm),
+        # Code quality tools (v1.3.0)
+        ("vulture", ctx.tools.vulture),
+        ("radon", ctx.tools.radon),
+        ("interrogate", ctx.tools.interrogate),
+        ("pylint", ctx.tools.pylint),
+        # Dependency analysis tools (v1.3.1)
+        ("pipdeptree", ctx.tools.pipdeptree),
+        ("pip-licenses", ctx.tools.pip_licenses),
+        # Performance profiling tools (v1.4.0)
+        ("line_profiler", ctx.tools.line_profiler),
+    ]
+
+    print("\n🔧 Tool Detection:")
+    print("=" * 70)
+
+    for name, path in tools_data:
+        if path:
+            trusted = is_path_trusted(path)
+            trust_marker = "✅" if trusted else "⚠️ "
+            print(f"  {name:10} {trust_marker} {path}")
+        else:
+            print(f"  {name:10} ❌ <missing>")
+
+    if ctx.options.strict_paths:
+        print("\n⚠️  STRICT-PATHS MODE ENABLED")
+        print("   Only tools in trusted directories are available.")
+
+    print("=" * 70)

pybundle/filters.py

@@ -0,0 +1,178 @@
+from fnmatch import fnmatch
+from pathlib import Path
+
+EXCLUDE_PATTERNS = {
+    "*.egg",
+    "*.egg-info",
+    "*.appimage",
+    "*.deb",
+    "*.rpm",
+    "*.exe",
+    "*.msi",
+    "*.dmg",
+    "*.pkg",
+    "*.so",
+    "*.dll",
+    "*.dylib",
+    "*.db",
+    "*.sqlite",
+    "*.sqlite3",
+    "*.zip",
+    "*.tar",
+    "*.gz",
+    "*.tgz",
+    "*.bz2",
+    "*.xz",
+    "*.7z",
+    "*.rej",
+    "*.orig",
+}
+
+DEFAULT_EXCLUDE_DIRS = {
+    ".git",
+    ".venv",
+    ".mypy_cache",
+    ".ruff_cache",
+    ".pytest_cache",
+    "__pycache__",
+    "node_modules",
+    "dist",
+    "build",
+    "target",
+    ".next",
+    ".nuxt",
+    "artifacts",
+    ".cache",
+    ".hg",
+    ".svn",
+    "venv",
+    ".direnv",
+    ".pybundle-venv",
+    "binaries",
+    "out",
+    ".svelte-kit",
+}
+
+DEFAULT_INCLUDE_FILES = [
+    "pyproject.toml",
+    "requirements.txt",
+    "poetry.lock",
+    "pdm.lock",
+    "uv.lock",
+    "setup.cfg",
+    "setup.py",
+    "mypy.ini",
+    "ruff.toml",
+    ".ruff.toml",
+    "pytest.ini",
+    "tox.ini",
+    ".python-version",
+    "README.md",
+    "README.rst",
+    "README.txt",
+    "CHANGELOG.md",
+    "LICENSE",
+    "LICENSE.md",
+    ".tox",
+    ".nox",
+    ".direnv",
+    "requirements-dev.txt",
+    "package.json",
+    "package-lock.json",
+    "pnpm-lock.yaml",
+    "yarn.lock",
+    "tsconfig.json",
+    "vite.config.js",
+    "vite.config.ts",
+    "webpack.config.js",
+    "webpack.config.ts",
+    "Cargo.toml",
+    "Cargo.lock",
+    "tauri.conf.json",
+    "tauri.conf.json5",
+    "tauri.conf.toml",
+]
+
+DEFAULT_INCLUDE_DIRS = [
+    "src",
+    "tests",
+    "tools",
+    "docs",
+    ".github",
+    "app",
+    "templates",
+    "static",
+    "src-tauri",
+    "frontend",
+    "web",
+    "ui",
+]
+
+DEFAULT_INCLUDE_GLOBS = [
+    "*.py",
+    "*/**/*.py",
+    "templates/**/*",
+    "static/**/*",
+]
+
+DEFAULT_EXCLUDE_FILE_EXTS: set[str] = {
+    ".appimage",
+    ".deb",
+    ".rpm",
+    ".exe",
+    ".msi",
+    ".dmg",
+    ".pkg",
+    ".so",
+    ".dll",
+    ".dylib",
+    ".db",
+    ".sqlite",
+    ".sqlite3",
+    ".zip",
+    ".tar",
+    ".gz",
+    ".tgz",
+    ".bz2",
+    ".xz",
+    ".7z",
+    ".git",
+    ".venv",
+    ".mypy_cache",
+    ".ruff_cache",
+    ".pytest_cache",
+    "__pycache__",
+    "node_modules",
+    "dist",
+    "build",
+    "artifacts",
+    ".cache",
+}
+
+
+def is_excluded_by_name(
+    name: str, *, exclude_names: set[str], exclude_patterns: set[str]
+) -> bool:
+    if name in exclude_names:
+        return True
+    return any(fnmatch(name, pat) for pat in exclude_patterns)
+
+
+def is_excluded_name(self, name: str) -> bool:
+    return is_excluded_by_name(
+        name, exclude_names=self.exclude_dirs, exclude_patterns=self.exclude_patterns
+    )
+
+
+def is_excluded_path(
+    rel: Path,
+    exclude_names: set[str],
+    exclude_patterns: set[str],
+) -> bool:
+    # Exclude if *any* part matches (dirs) OR the final filename matches
+    for part in rel.parts:
+        if is_excluded_by_name(
+            part, exclude_names=exclude_names, exclude_patterns=exclude_patterns
+        ):
+            return True
+    return False