sermon-clean/sermon_clean/batch.py

"""Batch processing — run any sermon-clean subcommand across many files.

Real workflow: a preacher records 4-5 sermons on Sunday, all need the same
post-processing. Running each one by hand is tedious and error-prone.

`batch` takes a glob pattern and runs the requested subcommand on each
file. Output goes into a sibling directory tree with `<stem>-<op><ext>`
filenames. Errors are collected, not raised, so one bad file doesn't
kill the whole batch.
"""

from __future__ import annotations

import glob
import re
import shutil
import subprocess
from dataclasses import dataclass, field
from pathlib import Path
from typing import List, Optional


@dataclass
class BatchItem:
    src: Path
    output: Path
    returncode: int = 0
    stderr: str = ""
    stdout: str = ""

    @property
    def ok(self) -> bool:
        return self.returncode == 0


@dataclass
class BatchResult:
    items: List[BatchItem] = field(default_factory=list)
    n_ok: int = 0
    n_failed: int = 0

    def summary(self) -> str:
        lines = [f"batch: {self.n_ok} ok, {self.n_failed} failed (of {len(self.items)} total)"]
        for item in self.items:
            marker = "✓" if item.ok else "✗"
            lines.append(f"  {marker} {item.src.name} -> {item.output}")
            if not item.ok and item.stderr:
                # First non-empty stderr line for diagnosis
                for line in item.stderr.splitlines():
                    if line.strip():
                        lines.append(f"      stderr: {line.strip()}")
                        break
        return "\n".join(lines)


def _expand_globs(patterns: List[str]) -> List[Path]:
    """Expand a list of glob patterns into a sorted, deduped list of files."""
    seen = set()
    out = []
    for pattern in patterns:
        for path in sorted(glob.glob(pattern, recursive=True)):
            p = Path(path)
            if p.is_file() and p.resolve() not in seen:
                seen.add(p.resolve())
                out.append(p)
    return out


def _make_output_path(src: Path, output_dir: Path, suffix: str, ext: Optional[str]) -> Path:
    """Compute the output path for a given input.

    Filename pattern: <stem><suffix><ext>, where ext defaults to src.suffix.
    """
    out_ext = ext if ext is not None else src.suffix
    out_name = f"{src.stem}{suffix}{out_ext}"
    return output_dir / out_name


# Valid subcommands for batch. Keep this in sync with cli.py.
BATCH_SUBCOMMANDS = {"find", "scan", "si", "silence-index", "mb", "multiband",
                     "slices", "cut", "paste", "auto", "pipe",
                     "normalize", "silence-stats", "threshold-tune", "denoise"}


def run_batch(
    subcommand: str,
    sources: List[Path],
    output_dir: Path,
    *,
    output_suffix: str = "-fixed",
    output_extension: Optional[str] = None,
    extra_args: Optional[List[str]] = None,
) -> BatchResult:
    """Run `sermon-clean <subcommand>` over each source file.

    Args:
        subcommand: which sermon-clean subcommand to invoke.
        sources: list of input audio files.
        output_dir: directory to write outputs to. Created if missing.
        output_suffix: filename suffix for outputs (e.g. '-normalized').
            Ignored for subcommands that don't produce an output file
            (find/scan/si/mb/silence-stats/threshold-tune/slices).
        output_extension: extension override (e.g. '.wav'). Defaults to
            src.suffix.
        extra_args: additional args to pass to the subcommand. Note that
            `--suffix` is reserved by `batch` itself — strip it if you
            forward it via this param. (We don't currently forward anything
            from the batch CLI to subcommands other than the implicit
            `-o <output>`.)

    Returns:
        BatchResult with per-file success/failure.

    Raises:
        ValueError: if subcommand is not a recognized sermon-clean command.
    """
    if subcommand not in BATCH_SUBCOMMANDS:
        raise ValueError(
            f"unknown subcommand for batch: {subcommand!r}. "
            f"valid: {sorted(BATCH_SUBCOMMANDS)}"
        )

    output_dir = Path(output_dir)
    output_dir.mkdir(parents=True, exist_ok=True)

    # Find the sermon-clean executable in PATH or fall back to python -m
    sc_bin = shutil.which("sermon-clean")
    if sc_bin:
        cmd_base = [sc_bin]
    else:
        import sys
        cmd_base = [sys.executable, "-m", "sermon_clean.cli"]

    result = BatchResult()
    extra_args = extra_args or []

    for src in sources:
        src = Path(src)
        out = _make_output_path(src, output_dir, output_suffix, output_extension)
        # Build the per-file argv. -o / --output is added only for subcommands
        # that produce a single output file.
        output_subcommands = {"cut", "paste", "normalize", "denoise", "pipe"}
        argv = cmd_base + [subcommand, str(src)] + extra_args
        if subcommand in output_subcommands:
            argv += ["-o", str(out)]

        proc = subprocess.run(argv, capture_output=True, text=True)
        result.items.append(BatchItem(
            src=src,
            output=out,
            returncode=proc.returncode,
            stdout=proc.stdout,
            stderr=proc.stderr,
        ))
        if proc.returncode == 0:
            result.n_ok += 1
        else:
            result.n_failed += 1

    return result