From a22de66e47a0dcb4d0886d92c910f547329498f9 Mon Sep 17 00:00:00 2001 From: Dandaedre Date: Tue, 20 Oct 2026 14:53:37 +0200 Subject: [PATCH] Retire Python reporter and cross-language parity checks --- AGENTS.md | 31 +- Jenkinsfile | 3 - README.md | 2 +- docs/ci.md | 25 +- docs/development.md | 16 +- docs/pptx-videos.md | 26 +- scripts/ci_tools.py | 40 --- scripts/fetch_ffprobe.py | 34 +-- scripts/parity.py | 65 ----- tests/test_ci_tools.py | 42 --- tests/test_fetch_ffprobe.py | 21 -- tests/test_playback.py | 167 ----------- tests/test_pptx_videos.py | 275 ------------------ tools/ontime.py | 63 ---- tools/playback.py | 121 -------- tools/pptx_videos.py | 552 ------------------------------------ 16 files changed, 58 insertions(+), 1425 deletions(-) delete mode 100644 scripts/ci_tools.py delete mode 100644 scripts/parity.py delete mode 100644 tests/test_ci_tools.py delete mode 100644 tests/test_playback.py delete mode 100644 tests/test_pptx_videos.py delete mode 100644 tools/ontime.py delete mode 100644 tools/playback.py delete mode 100644 tools/pptx_videos.py diff --git a/AGENTS.md b/AGENTS.md index f6e3330..102e81a 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -8,20 +8,13 @@ with quick-start examples and links to detailed documentation in `docs/`. - `crates/pptx-reporter/` is the Rust reporter: shared core, CLI and egui desktop interface. PDF compilation and DejaVu fonts are embedded. Discover FFprobe beside the app, - under `bin/`, or on PATH. Keep report/JSON/Ontime behavior compatible with the - Python reference; `scripts/parity.py` verifies real-media parity. - The document exporter is outside the Rust migration scope. + under `bin/`, or on PATH. It is the sole PPTX video reporter; the Python + implementation and cross-language parity harness are retired. Preserve the + established report/JSON/Ontime behavior with Rust regression tests in + `crates/pptx-reporter/tests/`. Apply trims, retain looping/unsupported timing + in reports, and omit those cases from Ontime and playback totals. + The document exporter remains Python. -- `tools/pptx_videos.py` discovers and extracts embedded PPTX videos, maps them to - slides, probes metadata with FFmpeg's `ffprobe`, and generates timing reports - in Markdown, plain text, JSON, HTML, Typst, PDF, and Ontime 4 JSON. Markdown - and Ontime are the defaults. PDF reports compile through the Typst CLI. - Its output root contains `videos/` for media and `reports/` for reports and - Typst sources; report media links are relative to `reports/`. -- `tools/ontime.py` maps video references into an importable Ontime rundown. -- `tools/playback.py` reads per-shape trims and flags looping/unsupported timing. - Keep these cases in reports but omit them from Ontime and playback totals. - `tests/test_playback.py` covers the XML and effective-duration behavior. - `tools/progress.py` provides shared transient terminal progress and plain logs for redirected output; `tests/test_progress.py` checks display cleanup. - `tools/exporter.py` uses DeckCraft to export PPTX presentations to PDF or PNG slides, @@ -33,9 +26,7 @@ with quick-start examples and links to detailed documentation in `docs/`. output or replace existing files. - `tests/test_exporter.py` covers exporter validation, no-op behavior, conversion failures, and overwrite behavior. -- `tests/test_pptx_videos.py` covers slide discovery, extraction, temporary probing, - report formatting, and error handling. -- `Jenkinsfile` runs Python/Rust tests, parity, lint, docs and coverage on +- `Jenkinsfile` runs Python/Rust tests, lint, docs and coverage on `rust_no_docker`. The explicitly requested badge workflow archives exactly three SVGs and publishes them only from main during cleanup. CI never creates releases or uploads release binaries. Cross and `rust_realease` are separate, @@ -49,8 +40,8 @@ with quick-start examples and links to detailed documentation in `docs/`. - `tools/` and `tests/`: Python prototypes and their regression tests. - `crates//`: each Rust port owns its source, assets, build script and tests. - Root Cargo workspace: shared version/metadata, lockfile, profiles and target directory. -- Keep Python references while parity is useful; add future Rust tools as workspace - members and include every member in CI checks and coverage. +- Retire Python prototypes once their Rust replacements are validated. Add future + Rust tools as workspace members and include every member in CI checks and coverage. ## Working conventions @@ -65,8 +56,8 @@ with quick-start examples and links to detailed documentation in `docs/`. - Keep tools in `tools/`, tests in `tests/`, and specialized documentation in `docs/`. Update the relevant docs when options or workflows change; keep the README's examples and links current. -- Run checks appropriate to the change before committing. Exporter regression - tests and video-report tests run with +- Run checks appropriate to the change before committing. Python exporter, CI and packaging + tests run with `python3 -m unittest discover -s tests -v`. For rendering changes, test with the actual external tools when available and inspect visual output. Report any checks that could not be completed. diff --git a/Jenkinsfile b/Jenkinsfile index 4b296e2..3b8f4e9 100644 --- a/Jenkinsfile +++ b/Jenkinsfile @@ -59,9 +59,6 @@ pipeline { python3 -m unittest discover -s tests -v cargo test --locked --workspace --all-features cargo build --locked --workspace --all-features - export PATH="$PWD/downloads/ci-tools/bin:$PATH" - python3 scripts/ci_tools.py - python3 scripts/parity.py target/debug/pptx-reporter python3 scripts/ci.py tests-passed ''' } diff --git a/README.md b/README.md index efdb42b..83616c6 100644 --- a/README.md +++ b/README.md @@ -35,7 +35,7 @@ opening reports, and reading video timings. ## More documentation - [Reporter](docs/rust-reporter.md) · [Windows quick start](docs/windows-quickstart.txt) -- [Report options and Python reference](docs/pptx-videos.md) +- [Report formats and timing semantics](docs/pptx-videos.md) - [Document exports](docs/exporter.md) - [Development](docs/development.md) · [CI and coverage](docs/ci.md) - [Cross builds and portable releases](docs/releases.md) diff --git a/docs/ci.md b/docs/ci.md index 59bab62..5c68767 100644 --- a/docs/ci.md +++ b/docs/ci.md @@ -3,23 +3,18 @@ Jenkins must use a Multibranch Pipeline supplying `BRANCH_NAME`, with the `rust_no_docker` worker, Python 3.11+ and Rust. SCM credentials, webhooks and the publication mount are administrator setup. -CI checks formatting, Clippy, rustdoc, Python/Rust tests, real-media parity and +CI checks formatting, Clippy, rustdoc, Python/Rust tests and whole-workspace Rust coverage. It never creates tags or release artifacts. -Parity reuses FFmpeg, FFprobe and Typst from PATH when available. Otherwise -`scripts/ci_tools.py` fetches checksum-verified FFmpeg/FFprobe on Linux x86-64 -and installs locked `typst-cli 0.13.1` with Cargo under ignored -`downloads/ci-tools/`. No sudo is needed; missing tools require network access -and a first-time Typst build can take several minutes. To provision locally: +The Python reporter and cross-language parity checks are retired. CI uses the +Rust reporter's own regression tests and embedded PDF engine, plus Python +exporter and CI/packaging tests. It does not provision FFmpeg, FFprobe or the +Typst CLI. FFprobe remains an application runtime dependency and is fetched +separately when packaging portable releases. -```sh -export PATH="$PWD/downloads/ci-tools/bin:$PATH" -python3 scripts/ci_tools.py -``` - -A test, provisioning or parity failure still fails the build, but does not skip -the independent coverage stage. The test-passed marker requires all of them to -succeed; fresh measured coverage can therefore accompany a failing test badge. +A test failure still fails the build but does not skip the independent coverage +stage. The test-passed marker requires all required tests to succeed; fresh +measured coverage can therefore accompany a failing test badge. ## Measurement @@ -44,7 +39,7 @@ unrounded covered/count totals, logs the measurement and floor before PASS/FAIL, and retains tool failure status even when a valid measurement exists. `init` removes stale output. CI creates `.tests-passed-${BUILD_NUMBER}` only -after all required tests and parity pass. A valid measurement creates +after all required tests pass. A valid measurement creates `.coverage-ready-${BUILD_NUMBER}` even below the floor. Cleanup preserves that measurement; unavailable coverage becomes neutral `-%`. Temporary `coverage/summary.json`, diagnostics and markers are deleted after processing. diff --git a/docs/development.md b/docs/development.md index b6b240a..ec53f19 100644 --- a/docs/development.md +++ b/docs/development.md @@ -7,11 +7,12 @@ | `tools/` | Python prototypes and document utilities | | `tests/` | Python regression and CI/packaging tests | | `crates//` | Rust ports, each with its own source, tests and assets | -| `scripts/` | Shared CI, parity and release helpers | +| `scripts/` | Shared CI and release helpers | | `docs/` | Tool usage and specialized workflows | Prototype in Python, then add a Rust workspace member when the workflow is -stable. Keep the Python implementation as a parity reference while useful. +stable. Retire the Python implementation once the Rust port is validated. +The PPTX reporter is now Rust-only; the document exporter remains Python. Avoid speculative shared crates; extract common code when multiple tools need it. The root `Cargo.toml` owns workspace metadata, the shared version and build @@ -31,13 +32,14 @@ cargo test --locked --workspace --all-features RUSTDOCFLAGS="-D warnings" cargo doc --locked --workspace --all-features --no-deps python3 -m unittest discover -s tests -v cargo build --locked --workspace --all-features -python3 scripts/parity.py target/debug/pptx-reporter ``` -Parity requires FFmpeg, FFprobe and the Typst CLI for the Python reference. -It compares JSON/Ontime for real media with trims, loops, custom timing and -orphan media, and generates every report format. Python exporter tests mock -external document applications. Inspect rendering changes visually as well. +Rust regression tests cover archive parsing, trimming, loops, report formats, +Ontime, CLI errors and GUI state; both PDF layouts compile with the embedded +engine. Probe-process tests use a controlled stub. No external FFmpeg, FFprobe +or Typst CLI is required for CI. The application still needs FFprobe at runtime. +Python exporter tests mock external document applications. Inspect rendering +changes visually as well. `cargo build -p pptx-reporter --no-default-features` builds the CLI without the GUI or PDF engine; add `--features pdf` to restore embedded PDFs. diff --git a/docs/pptx-videos.md b/docs/pptx-videos.md index 6c4aae5..3b7dca3 100644 --- a/docs/pptx-videos.md +++ b/docs/pptx-videos.md @@ -1,25 +1,26 @@ -# Report options and Python reference +# Report formats and timing semantics -Report semantics apply to both implementations. Commands below use the Python -reference; for the desktop app and Rust CLI see [Reporter](rust-reporter.md). -Only the Python implementation needs the external Typst CLI for PDFs. +Use the Rust CLI below, or see the [illustrated desktop guide](user-guide.md). +Run source commands from the repository root. With a prebuilt CLI, replace +`cargo run --locked --bin pptx-reporter --` with `pptx-reporter` (or +`pptx-reporter.exe` on Windows). The Python reporter has been retired. Extract videos and create Markdown and Ontime timing reports: ```sh -python3 tools/pptx_videos.py presentation.pptx +cargo run --locked --bin pptx-reporter -- presentation.pptx ``` Generate one or more report formats without keeping newly extracted videos: ```sh -python3 tools/pptx_videos.py presentation.pptx --timings-only --report html,pdf -python3 tools/pptx_videos.py presentation.pptx --report all +cargo run --locked --bin pptx-reporter -- presentation.pptx --timings-only --report html,pdf +cargo run --locked --bin pptx-reporter -- presentation.pptx --report all ``` `--report` accepts comma-separated formats and can be repeated. Markdown and Ontime are included by default; an explicit `--report` replaces this selection. -Use `--report all` for every format, including both PDF layouts (requires Typst) +Use `--report all` for every format, including both built-in PDF layouts and Ontime. The output root is `_videos`, or the directory supplied with `-o`. Extracted media goes in `videos/`; all reports and Typst sources go in @@ -39,7 +40,7 @@ relative to the report directory too. `--timings-only` reuses media in `videos/` when available, otherwise probes temporary copies without creating that folder. `--extract-only` creates no report folder. -PDF uses the Typst CLI and retains `timings.typ` +PDF uses the embedded Typst engine and retains `timings.typ` for editing. HTML and Typst/PDF include colored summary cards and pills; Markdown and TXT use aligned tables. JSON includes numeric durations in seconds, sizes in bytes, and slide references. @@ -47,7 +48,7 @@ sizes in bytes, and slide references. For a compact portrait PDF with slide numbers, media names, and duration pills: ```sh -python3 tools/pptx_videos.py presentation.pptx --timings-only --report pdf-dense +cargo run --locked --bin pptx-reporter -- presentation.pptx --timings-only --report pdf-dense ``` This creates `timings-dense.pdf` and its editable `timings-dense.typ` source. @@ -58,8 +59,7 @@ from the start and end. Looping videos carry an amber **Looping** pill next to their name and a dash instead of a finite duration. Use `--report pdf,pdf-dense` to produce both layouts. -Timings require `ffprobe` (from FFmpeg); PDF additionally requires `typst` on -`PATH`. Use `--extract-only` to extract without a report. Presentations with no +Timings require `ffprobe` (from FFmpeg); PDF generation needs no external CLI. Use `--extract-only` to extract without a report. Presentations with no embedded videos produce no output. ## Playback durations and trimming @@ -103,7 +103,7 @@ and [animation timing properties](https://learn.microsoft.com/en-us/dotnet/api/d ## Ontime import ```sh -python3 tools/pptx_videos.py presentation.pptx --timings-only --report ontime +cargo run --locked --bin pptx-reporter -- presentation.pptx --timings-only --report ontime ``` This writes `timings.ontime.json`, a native **Ontime 4** project. It is separate diff --git a/scripts/ci_tools.py b/scripts/ci_tools.py deleted file mode 100644 index b1ae825..0000000 --- a/scripts/ci_tools.py +++ /dev/null @@ -1,40 +0,0 @@ -#!/usr/bin/env python3 -"""Supply missing parity tools locally, without sudo or changing the worker.""" -from pathlib import Path -import os -import platform -import shutil -import subprocess - -try: - from .fetch_ffprobe import fetch -except ImportError: - from fetch_ffprobe import fetch - -ROOT = Path(__file__).resolve().parents[1] -TYPST_VERSION = "0.13.1" - - -def prepare(): - install = ROOT / "downloads/ci-tools" - bindir = install / "bin" - bindir.mkdir(parents=True, exist_ok=True) - os.environ["PATH"] = str(bindir) + os.pathsep + os.environ.get("PATH", "") - for program in ("ffmpeg", "ffprobe"): - if not shutil.which(program): - if platform.system() != "Linux" or platform.machine().lower() not in ("x86_64", "amd64"): - raise RuntimeError(f"Install {program} on PATH; automatic CI provisioning needs Linux x86-64") - binary, _ = fetch("x86_64-unknown-linux-gnu", program=program) - link = bindir / program - link.unlink(missing_ok=True) - link.symlink_to(binary.resolve()) - subprocess.run([program, "-version"], check=True, stdout=subprocess.DEVNULL, timeout=30) - print(f"Parity dependency ready: {program}", flush=True) - if not shutil.which("typst"): - subprocess.run(["cargo", "install", "typst-cli", "--version", TYPST_VERSION, - "--locked", "--root", str(install)], check=True) - subprocess.run(["typst", "--version"], check=True, timeout=30) - - -if __name__ == "__main__": - prepare() diff --git a/scripts/fetch_ffprobe.py b/scripts/fetch_ffprobe.py index f2cac37..597ec82 100644 --- a/scripts/fetch_ffprobe.py +++ b/scripts/fetch_ffprobe.py @@ -1,5 +1,5 @@ #!/usr/bin/env python3 -"""Fetch verified FFprobe for releases; share validation with CI FFmpeg setup.""" +"""Fetch verified FFprobe binaries for release packaging, never into source control.""" import argparse import hashlib import json @@ -62,11 +62,9 @@ def validate_binary(path, target): raise ValueError(f"Unsupported target: {target}") -def unpack(archive, destination, target, program="ffprobe"): - """Copy the selected program and notices without extracting archive paths.""" - if program not in ("ffprobe", "ffmpeg"): - raise ValueError("Unsupported FFmpeg program") - executable = program + (".exe" if "windows" in target else "") +def unpack(archive, destination, target): + """Copy only FFprobe and upstream notices; never extract archive paths directly.""" + executable = "ffprobe.exe" if "windows" in target else "ffprobe" notices = destination / "licenses" notices.mkdir() found = False @@ -84,7 +82,7 @@ def unpack(archive, destination, target, program="ffprobe"): raise ValueError(f"Archive member too large: {name}") if is_binary: if found or path.parent.name != "bin": - raise ValueError(f"Expected exactly one bin/{executable} executable") + raise ValueError("Expected exactly one bin/ffprobe executable") found = True output = destination / executable else: @@ -109,19 +107,17 @@ def unpack(archive, destination, target, program="ffprobe"): continue member(info.name, info.size, info.isfile(), lambda i=info: bundle.extractfile(i)) if not found or not licensed: - raise ValueError(f"Archive must include {program} and its upstream license") + raise ValueError("Archive must include FFprobe and its upstream license") binary = destination / executable validate_binary(binary, target) binary.chmod(0o755) return binary, notices -def fetch(target, cache=None, release="latest", expected_sha256=None, program="ffprobe"): - if program not in ("ffprobe", "ffmpeg"): - raise ValueError("Unsupported FFmpeg program") +def fetch(target, cache=None, release="latest", expected_sha256=None): if target not in ASSETS: raise ValueError(f"Unsupported target: {target}") - cache = Path(cache) if cache is not None else ROOT / "downloads" / program + cache = Path(cache) if cache is not None else ROOT / "downloads" / "ffprobe" cache.mkdir(parents=True, exist_ok=True) with tempfile.TemporaryDirectory(prefix=".fetch-", dir=cache) as temporary: temporary = Path(temporary) @@ -142,9 +138,7 @@ def fetch(target, cache=None, release="latest", expected_sha256=None, program="f if not url.startswith("https://github.com/BtbN/FFmpeg-Builds/releases/download/"): raise ValueError("Unexpected upstream download URL") folder = cache / target / digest - if program != "ffprobe": - folder = cache / program / target / digest - binary = folder / (program + (".exe" if "windows" in target else "")) + binary = folder / ("ffprobe.exe" if "windows" in target else "ffprobe") notices = folder / "licenses" if folder.exists(): if folder.is_symlink(): @@ -160,7 +154,7 @@ def fetch(target, cache=None, release="latest", expected_sha256=None, program="f if binary.name not in receipt["files"] or receipt["archive_sha256"] != digest: raise ValueError("Invalid FFprobe cache receipt") validate_binary(binary, target) - print(f"Using verified {program} cache: {binary}", flush=True) + print(f"Using verified FFprobe cache: {binary}", flush=True) return binary, notices archive = temporary / asset["name"] print(f"Downloading {asset['name']} ({asset['size'] / 1048576:.1f} MiB)", flush=True) @@ -169,7 +163,7 @@ def fetch(target, cache=None, release="latest", expected_sha256=None, program="f raise ValueError("FFprobe archive SHA-256 mismatch; nothing installed") stage = temporary / "bundle" stage.mkdir() - staged_binary, staged_notices = unpack(archive, stage, target, program) + staged_binary, staged_notices = unpack(archive, stage, target) native = platform.machine().lower() in ("amd64", "x86_64") and ( (os.name == "nt" and "windows" in target) or (platform.system() == "Linux" and "linux" in target)) @@ -178,8 +172,8 @@ def fetch(target, cache=None, release="latest", expected_sha256=None, program="f result = subprocess.run([str(staged_binary.resolve()), "-version"], check=True, capture_output=True, text=True, timeout=30) lines = result.stdout.splitlines() - if not lines or not lines[0].startswith(f"{program} version "): - raise ValueError(f"Downloaded executable did not identify itself as {program}") + if not lines or not lines[0].startswith("ffprobe version "): + raise ValueError("Downloaded executable did not identify itself as FFprobe") version = lines[0] receipt = { "provider": "https://github.com/BtbN/FFmpeg-Builds", @@ -192,7 +186,7 @@ def fetch(target, cache=None, release="latest", expected_sha256=None, program="f (staged_notices / "provenance.json").write_text(json.dumps(receipt, indent=2) + "\n") folder.parent.mkdir(parents=True, exist_ok=True) stage.rename(folder) - print(f"Verified {program}: {binary}", flush=True) + print(f"Verified FFprobe: {binary}", flush=True) return binary, notices diff --git a/scripts/parity.py b/scripts/parity.py deleted file mode 100644 index 4b24cc9..0000000 --- a/scripts/parity.py +++ /dev/null @@ -1,65 +0,0 @@ -#!/usr/bin/env python3 -"""Compare Rust results to the Python reference using real media and both PDF layouts.""" -import json -from pathlib import Path -import shutil -import subprocess -import sys -import tempfile -import zipfile - -ROOT = Path(__file__).resolve().parents[1] -sys.path.insert(0, str(ROOT)) -from tests.test_playback import PlaybackTests, picture, timing - - -def main(): - binary = Path(sys.argv[1]).resolve() - for tool in ("ffmpeg", "ffprobe", "typst"): - if not shutil.which(tool): - raise SystemExit(f"Parity check requires {tool} on PATH.") - with tempfile.TemporaryDirectory(prefix="reporter-parity-") as temporary: - root = Path(temporary) - clip = root / "clip.mp4" - subprocess.run(["ffmpeg", "-v", "error", "-f", "lavfi", "-i", "color=c=blue:s=32x24:r=10", - "-t", "10", "-c:v", "mpeg4", str(clip)], check=True) - fixture = PlaybackTests() - fixture.setUp() - try: - source = fixture.deck([ - (picture("2", '') + picture("3", ''), - timing("2", 'dur="indefinite"')), - (picture("2", ''), timing("2", 'repeatCount="indefinite"')), - (picture("2"), timing("2", 'spd="200000"')), - (picture("2", ''), ''), - (picture("2"), timing("99", 'repeatCount="indefinite"')), - (picture("2"), timing("2", children='')), - (picture("2"), timing("2", media_attrs='numSld="2"')), - ]) - presentation = root / "Présentation & .pptx" - with zipfile.ZipFile(source) as old, zipfile.ZipFile(presentation, "w") as new: - for name in old.namelist(): - new.writestr(name, clip.read_bytes() if name.endswith(".mp4") else old.read(name)) - new.writestr("ppt/media/orphan.mp4", clip.read_bytes()) - for runner, output in [([sys.executable, str(ROOT / "tools/pptx_videos.py")], root / "python"), - ([str(binary)], root / "rust")]: - subprocess.run([*runner, str(presentation), "--timings-only", "--report", "all", - "-o", str(output)], check=True) - assert not (output / "videos").exists() - for filename in ("timings.json", "timings.ontime.json"): - expected = json.loads((root / "python/reports" / filename).read_text()) - actual = json.loads((root / "rust/reports" / filename).read_text()) - if actual != expected: - raise AssertionError(f"{filename} differs:\nPython: {expected}\nRust: {actual}") - for name in ("timings.pdf", "timings-dense.pdf"): - assert (root / "rust/reports" / name).read_bytes().startswith(b"%PDF") - # Optional retained review samples, only at an explicitly supplied location. - if len(sys.argv) > 2: - shutil.copytree(root / "rust", Path(sys.argv[2]), dirs_exist_ok=True) - print("PASS: Python/Rust report and Ontime JSON match; all formats and both PDFs generated.") - finally: - fixture.doCleanups() - - -if __name__ == "__main__": - main() diff --git a/tests/test_ci_tools.py b/tests/test_ci_tools.py deleted file mode 100644 index feb6c3b..0000000 --- a/tests/test_ci_tools.py +++ /dev/null @@ -1,42 +0,0 @@ -import os -from pathlib import Path -import tempfile -import unittest -from unittest.mock import patch - -from scripts import ci_tools - - -class CIToolsTests(unittest.TestCase): - def test_installed_tools_are_checked_without_downloads(self): - with tempfile.TemporaryDirectory() as temp, patch.object(ci_tools, "ROOT", Path(temp)), \ - patch.dict(os.environ), patch.object(ci_tools.shutil, "which", return_value="/usr/bin/tool"), \ - patch.object(ci_tools, "fetch") as fetch, patch.object(ci_tools.subprocess, "run") as run: - ci_tools.prepare() - fetch.assert_not_called() - self.assertEqual([call.args[0][0] for call in run.call_args_list], ["ffmpeg", "ffprobe", "typst"]) - - def test_missing_tools_are_provisioned_locally_and_typst_is_pinned(self): - with tempfile.TemporaryDirectory() as temp, patch.object(ci_tools, "ROOT", Path(temp)), \ - patch.dict(os.environ), patch.object(ci_tools.shutil, "which", return_value=None), \ - patch.object(ci_tools.platform, "system", return_value="Linux"), \ - patch.object(ci_tools.platform, "machine", return_value="x86_64"), \ - patch.object(ci_tools.subprocess, "run") as run: - binary = Path(temp) / "downloaded" - binary.write_bytes(b"fixture") - with patch.object(ci_tools, "fetch", return_value=(binary, Path(temp))) as fetch: - ci_tools.prepare() - self.assertEqual([c.kwargs["program"] for c in fetch.call_args_list], ["ffmpeg", "ffprobe"]) - self.assertEqual((Path(temp) / "downloads/ci-tools/bin/ffmpeg").resolve(), binary) - install = next(c.args[0] for c in run.call_args_list if c.args[0][0] == "cargo") - self.assertIn("--locked", install) - self.assertEqual(install[install.index("--version") + 1], "0.13.1") - - def test_download_failure_propagates(self): - with tempfile.TemporaryDirectory() as temp, patch.object(ci_tools, "ROOT", Path(temp)), \ - patch.dict(os.environ), patch.object(ci_tools.shutil, "which", return_value=None), \ - patch.object(ci_tools.platform, "system", return_value="Linux"), \ - patch.object(ci_tools.platform, "machine", return_value="x86_64"), \ - patch.object(ci_tools, "fetch", side_effect=ValueError("checksum mismatch")): - with self.assertRaisesRegex(ValueError, "checksum mismatch"): - ci_tools.prepare() diff --git a/tests/test_fetch_ffprobe.py b/tests/test_fetch_ffprobe.py index d661a46..d3a3d5b 100644 --- a/tests/test_fetch_ffprobe.py +++ b/tests/test_fetch_ffprobe.py @@ -66,27 +66,6 @@ class FetchTests(unittest.TestCase): fetcher.fetch(WINDOWS, cache) self.assertFalse(list(cache.glob(".fetch-*"))) - def test_ci_ffmpeg_selection_and_cache_are_separate(self): - content = bundle([("build/bin/ffprobe.exe", pe()), ("build/bin/ffmpeg.exe", pe()), - ("build/LICENSE", b"notice")]) - digest = hashlib.sha256(content).hexdigest() - name = fetcher.ASSETS[WINDOWS] - release = {"id": 1, "assets": [{"id": 2, "name": name, "digest": "sha256:" + digest, - "size": len(content), "browser_download_url": - "https://github.com/BtbN/FFmpeg-Builds/releases/download/latest/" + name}]} - def download(url, destination, limit=None): - destination.write_bytes(json.dumps(release).encode() if url.startswith(fetcher.API) else content) - with tempfile.TemporaryDirectory() as temp, patch.object(fetcher, "download", side_effect=download), \ - patch.object(fetcher.platform, "machine", return_value="test-host"): - encoder, _ = fetcher.fetch(WINDOWS, Path(temp), program="ffmpeg") - probe, _ = fetcher.fetch(WINDOWS, Path(temp)) - self.assertEqual(encoder.name, "ffmpeg.exe") - self.assertEqual(probe.name, "ffprobe.exe") - self.assertNotEqual(encoder.parent, probe.parent) - self.assertEqual(fetcher.fetch(WINDOWS, Path(temp), program="ffmpeg")[0], encoder) - with self.assertRaisesRegex(ValueError, "Unsupported"): - fetcher.fetch(WINDOWS, Path(temp), program="other") - def test_checksum_mismatch_leaves_no_installed_files(self): name = fetcher.ASSETS[WINDOWS] release = {"id": 1, "assets": [{"id": 2, "name": name, "digest": "sha256:" + "0" * 64, diff --git a/tests/test_playback.py b/tests/test_playback.py deleted file mode 100644 index 85ed979..0000000 --- a/tests/test_playback.py +++ /dev/null @@ -1,167 +0,0 @@ -import contextlib -import io -import json -from pathlib import Path -import tempfile -import unittest -from unittest.mock import patch -import zipfile - -from tools import pptx_videos as videos -from tools.playback import P14, time_offset - - -def picture(shape_id, trim=''): - return f''' - - - {trim} - ''' - - -def timing(shape_id, attrs='', children='', media_attrs=''): - return f''' - {children} - - ''' - - -class PlaybackTests(unittest.TestCase): - def setUp(self): - self.temp = tempfile.TemporaryDirectory() - self.addCleanup(self.temp.cleanup) - self.root = Path(self.temp.name) - - def deck(self, slides): - path = self.root / 'trimmed.pptx' - with zipfile.ZipFile(path, 'w') as archive: - archive.writestr('ppt/media/shared.mp4', b'media') - for index, (shapes, animation) in enumerate(slides, 1): - archive.writestr(f'ppt/slides/slide{index}.xml', f''' - - {shapes} - {animation} - ''') - archive.writestr(f'ppt/slides/_rels/slide{index}.xml.rels', f''' - - - - ''') - return path - - def report(self, slides, duration=10): - path = self.deck(slides) - with zipfile.ZipFile(path) as archive: - parts, uses, external = videos.discover(archive) - settings = videos.playback_settings(archive, parts) - return videos.report_data(path, [('ppt/media/shared.mp4', 'shared.mp4', 5, duration, '32×24', 'mpeg4')], - uses, external, self.root, settings) - - def test_time_offset_units_and_invalid_values(self): - for value, expected in [('1500', 1.5), ('1.25s', 1.25), ('1min', 60), ('0.5h', 1800), - ('250ms', .25), ('1000µs', .001), ('1000μs', .001), ('1000000ns', .001)]: - self.assertAlmostEqual(time_offset(value), expected) - for value in ('-1', 'NaN', 'Infinity', '1:30', '2seconds', ''): - with self.subTest(value=value), self.assertRaises(ValueError): - time_offset(value) - - def test_trim_end_is_amount_removed_not_end_timestamp(self): - data = self.report([(picture('2', ''), - timing('2', 'dur="indefinite"'))]) - self.assertEqual(len(data['playbacks']), 1) # legacy + p14 references are deduplicated - playback = data['playbacks'][0] - self.assertEqual(playback['duration_seconds'], 6.5) - self.assertEqual(playback['original_duration_seconds'], 10) - self.assertEqual(playback['trim_start_seconds'], 1.5) - self.assertEqual(playback['trim_end_seconds'], 2) - self.assertEqual(playback['playback_status'], 'trimmed') - event = next(iter(json.loads(videos.render_report(data, 'ontime'))['rundowns']['default']['entries'].values())) - self.assertEqual(event['duration'], 6500) - - def test_distinct_trims_on_same_slide_and_other_slides(self): - data = self.report([ - (picture('2', '') + picture('3', ''), ''), - (picture('2', ''), ''), - ]) - self.assertEqual([p['duration_seconds'] for p in data['playbacks']], [9, 8, 7]) - self.assertEqual(data['embedded_videos'], 1) - self.assertEqual(data['total_size_bytes'], 5) - self.assertEqual(data['total_duration_seconds'], 24) - self.assertEqual(data['total_media_duration_seconds'], 10) - events = json.loads(videos.render_report(data, 'ontime'))['rundowns']['default']['entries'] - self.assertEqual(len(events), 3) - self.assertEqual([e['duration'] for e in events.values()], [9000, 8000, 7000]) - - def test_loop_remains_in_all_reports_but_not_ontime_or_total(self): - data = self.report([ - (picture('2'), timing('2', 'repeatCount="indefinite" dur="indefinite"')), - (picture('2', ''), timing('2', 'dur="indefinite"')), - ]) - self.assertEqual(data['playbacks'][0]['playback_status'], 'looping') - self.assertIsNone(data['playbacks'][0]['duration_seconds']) - self.assertEqual(data['total_duration_seconds'], 9) - for format in ('md', 'txt', 'html', 'typst', 'pdf-dense'): - with self.subTest(format=format): - self.assertIn('Looping', videos.render_report(data, format)) - project = json.loads(videos.render_report(data, 'ontime')) - events = list(project['rundowns']['default']['entries'].values()) - self.assertEqual(len(events), 1) - self.assertEqual(events[0]['cue'], 'Slide 2') - self.assertEqual(events[0]['timeStart'], 0) - self.assertEqual(events[0]['duration'], 9000) - - def test_only_loops_produce_empty_ontime_rundown(self): - data = self.report([(picture('2'), timing('2', 'repeatCount="2000"'))]) - project = json.loads(videos.render_report(data, 'ontime')) - self.assertEqual(project['rundowns']['default']['order'], []) - self.assertEqual(project['rundowns']['default']['entries'], {}) - - def test_unsupported_timing_is_not_exported(self): - cases = [ - timing('2', 'spd="200000"'), - timing('2', 'autoRev="1"'), - timing('2', 'dur="3000"'), - timing('2', children=''), - timing('2', media_attrs='numSld="2"'), - ] - for animation in cases: - with self.subTest(animation=animation): - data = self.report([(picture('2'), animation)]) - self.assertEqual(data['playbacks'][0]['playback_status'], 'custom-timing') - self.assertIsNone(data['playbacks'][0]['duration_seconds']) - project = json.loads(videos.render_report(data, 'ontime')) - self.assertEqual(project['rundowns']['default']['order'], []) - - def test_inherited_repeat_and_unrelated_timing(self): - repeated = '' + timing('2') + '' - self.assertEqual(self.report([(picture('2'), repeated)])['playbacks'][0]['playback_status'], 'looping') - unrelated = timing('99', 'repeatCount="indefinite"') - self.assertEqual(self.report([(picture('2'), unrelated)])['playbacks'][0]['duration_seconds'], 10) - - def test_invalid_trim_is_visible_and_excluded(self): - for trim in ('st="-1"', 'end="NaN"', 'st="8s" end="3s"', 'st="10s"'): - with self.subTest(trim=trim): - data = self.report([(picture('2', f''), '')]) - self.assertEqual(data['playbacks'][0]['playback_status'], 'invalid-trim') - self.assertIn('Invalid trim', videos.render_report(data, 'md')) - project = json.loads(videos.render_report(data, 'ontime')) - self.assertEqual(project['rundowns']['default']['entries'], {}) - - def test_end_to_end_timings_only_uses_trim_without_modifying_media(self): - source = self.deck([(picture('2', ''), '')]) - with patch('sys.argv', ['pptx_videos.py', str(source), '--timings-only', '--report', 'json,ontime']), \ - patch.object(videos.shutil, 'which', return_value='/ffprobe'), \ - patch.object(videos, 'probe', return_value=(10, '32×24', 'mpeg4')), \ - contextlib.redirect_stdout(io.StringIO()): - self.assertEqual(videos.main(), 0) - output = self.root / 'trimmed_videos' - self.assertFalse((output / 'videos').exists()) - data = json.loads((output / 'reports/timings.json').read_text()) - self.assertEqual(data['videos'][0]['duration_seconds'], 10) - self.assertEqual(data['playbacks'][0]['duration_seconds'], 7) - self.assertEqual(data['playbacks'][0]['original_duration_seconds'], 10) - - -if __name__ == '__main__': - unittest.main() diff --git a/tests/test_pptx_videos.py b/tests/test_pptx_videos.py deleted file mode 100644 index a793348..0000000 --- a/tests/test_pptx_videos.py +++ /dev/null @@ -1,275 +0,0 @@ -from collections import defaultdict -import contextlib -import io -import json -from pathlib import Path -import subprocess -import tempfile -import unittest -from unittest.mock import patch -import zipfile - -from tools import pptx_videos as videos - - -class VideoTests(unittest.TestCase): - def setUp(self): - self.temp = tempfile.TemporaryDirectory() - self.addCleanup(self.temp.cleanup) - self.root = Path(self.temp.name) - - def invoke(self, source, *args): - with patch('sys.argv', ['pptx_videos.py', str(source), *args]), \ - contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(io.StringIO()): - return videos.main() - - def deck(self, name='sample.pptx', media=True): - path = self.root / name - with zipfile.ZipFile(path, 'w') as archive: - if media: - archive.writestr('ppt/media/clip.mp4', b'video fixture') - return path - - def test_discovery_uses_presentation_order_and_relationships(self): - source = self.root / 'ordered.pptx' - with zipfile.ZipFile(source, 'w') as archive: - archive.writestr('ppt/presentation.xml', f''' - - - ''') - archive.writestr('ppt/_rels/presentation.xml.rels', f''' - - - - ''') - for number in (1, 2): - archive.writestr(f'ppt/slides/slide{number}.xml', f''' - - - ''') - archive.writestr(f'ppt/slides/_rels/slide{number}.xml.rels', f''' - - - - ''') - archive.writestr(f'ppt/media/clip{number}.mp4', b'video') - archive.writestr('ppt/media/audio.mp3', b'audio') - with zipfile.ZipFile(source) as archive: - parts, uses, external = videos.discover(archive) - self.assertEqual(parts, ['ppt/media/clip1.mp4', 'ppt/media/clip2.mp4']) - self.assertEqual(uses['ppt/media/clip2.mp4'], {1}) - self.assertEqual(uses['ppt/media/clip1.mp4'], {2}) - self.assertEqual(external, {1, 2}) - - def test_empty_deck_creates_no_output_and_requires_no_tools(self): - source = self.deck(media=False) - with patch.object(videos.shutil, 'which', side_effect=AssertionError('No tools needed')): - self.assertEqual(self.invoke(source, '--timings-only', '--report', 'pdf'), 0) - self.assertFalse((self.root / 'sample_videos').exists()) - - def test_timings_only_probes_temporary_copy_then_removes_it(self): - source = self.deck() - probed = [] - - def probe(path): - self.assertEqual(path.read_bytes(), b'video fixture') - probed.append(path) - return 1.25, '1920×1080', 'h264' - - with patch.object(videos.shutil, 'which', return_value='/ffprobe'), patch.object(videos, 'probe', side_effect=probe): - self.assertEqual(self.invoke(source, '--timings-only', '--report', 'json,md'), 0) - output = self.root / 'sample_videos' - self.assertFalse((output / 'videos').exists()) - self.assertEqual(len(probed), 1) - self.assertFalse(probed[0].exists()) - data = json.loads((output / 'reports' / 'timings.json').read_text()) - self.assertEqual(data['videos'][0]['duration_seconds'], 1.25) - self.assertIsNone(data['videos'][0]['extracted_file']) - self.assertNotIn('[clip.mp4]', (output / 'reports' / 'timings.md').read_text()) - - def test_extract_only_does_not_probe_or_write_reports(self): - source = self.deck() - with patch.object(videos, 'probe', side_effect=AssertionError('No probing')): - self.assertEqual(self.invoke(source, '--extract-only'), 0) - output = self.root / 'sample_videos' - self.assertEqual([p.name for p in output.iterdir()], ['videos']) - self.assertEqual((output / 'videos' / 'clip.mp4').read_bytes(), b'video fixture') - - def test_separate_folders_and_relative_media_links(self): - source = self.root / 'linked.pptx' - with zipfile.ZipFile(source, 'w') as archive: - archive.writestr('ppt/media/clip #1.mp4', b'video fixture') - output = self.root / 'custom output' - media = output / 'videos' / 'clip #1.mp4' - reports = output / 'reports' - with patch.object(videos.shutil, 'which', return_value='/ffprobe'), \ - patch.object(videos, 'probe', return_value=(1.25, '32×24', 'mpeg4')) as probe: - self.assertEqual(self.invoke(source, '-o', str(output), '--report', 'md,html,json'), 0) - probe.assert_called_once_with(media) - probe.reset_mock() - self.assertEqual(self.invoke(source, '-o', str(output), '--timings-only', '--report', 'json'), 0) - probe.assert_called_once_with(media) - self.assertEqual({p.name for p in output.iterdir()}, {'videos', 'reports'}) - self.assertEqual(media.read_bytes(), b'video fixture') - self.assertIn('](../videos/clip%20%231.mp4)', (reports / 'timings.md').read_text()) - self.assertIn('href="../videos/clip%20%231.mp4"', (reports / 'timings.html').read_text()) - data = json.loads((reports / 'timings.json').read_text()) - self.assertEqual(data['videos'][0]['extracted_file'], '../videos/clip #1.mp4') - self.assertEqual((reports / data['videos'][0]['extracted_file']).resolve(), media.resolve()) - - def test_all_reports_generate_every_format_once(self): - source = self.deck() - - def compile_pdf(command, **kwargs): - self.assertEqual(command[:2], ['typst', 'compile']) - Path(command[-1]).write_bytes(b'%PDF-test') - - with patch.object(videos.shutil, 'which', return_value='/tool'), \ - patch.object(videos, 'probe', return_value=(1.25, '32×24', 'mpeg4')), \ - patch.object(videos.subprocess, 'run', side_effect=compile_pdf) as compiler: - self.assertEqual(self.invoke(source, '--timings-only', '--report', ' ALL,md', '--report', 'pdf'), 0) - self.assertEqual(compiler.call_count, 2) - self.assertEqual( - {p.name for p in (self.root / 'sample_videos' / 'reports').iterdir()}, - {'timings.html', 'timings.typ', 'timings.pdf', 'timings.md', - 'timings.txt', 'timings.json', 'timings.ontime.json', - 'timings-dense.typ', 'timings-dense.pdf'}, - ) - - def test_default_reports_include_ontime_and_explicit_choice_overrides(self): - source = self.deck() - with patch.object(videos.shutil, 'which', return_value='/ffprobe'), \ - patch.object(videos, 'probe', return_value=(1.25, '32×24', 'mpeg4')): - self.assertEqual(self.invoke(source, '--timings-only'), 0) - output = self.root / 'sample_videos' / 'reports' - self.assertEqual({p.name for p in output.iterdir()}, {'timings.md', 'timings.ontime.json'}) - other = self.deck(name='explicit.pptx') - self.assertEqual(self.invoke(other, '--timings-only', '--report', 'json,ontime'), 0) - output = self.root / 'explicit_videos' / 'reports' - self.assertEqual({p.name for p in output.iterdir()}, {'timings.json', 'timings.ontime.json'}) - other = self.deck(name='markdown.pptx') - self.assertEqual(self.invoke(other, '--timings-only', '--report', 'md'), 0) - self.assertEqual({p.name for p in (self.root / 'markdown_videos' / 'reports').iterdir()}, {'timings.md'}) - - def test_ontime_expands_shared_videos_in_slide_order(self): - project = json.loads(videos.render_report(self.report(), 'ontime')) - self.assertEqual(project['settings']['version'], '4.0.0') - rundown = project['rundowns']['default'] - events = [rundown['entries'][event_id] for event_id in rundown['order']] - self.assertEqual([event['cue'] for event in events], ['Slide 2', 'Slide 10', 'Slide 12', 'Unreferenced']) - self.assertEqual([event['duration'] for event in events], [1000, 2500, 1000, 0]) - self.assertEqual([event['timeStart'] for event in events], [0, 1000, 3500, 4500]) - self.assertEqual([event['linkStart'] for event in events], [False, True, True, True]) - self.assertEqual([event['skip'] for event in events], [False, False, False, True]) - self.assertTrue(all(event['endAction'] == 'none' for event in events)) - self.assertEqual(len(set(rundown['order'])), 4) - self.assertEqual(project, json.loads(videos.render_report(self.report(), 'ontime'))) - - def test_ontime_skips_unknown_duration_and_preserves_milliseconds(self): - data = self.report() - data['playbacks'][0]['duration_seconds'] = None - data['playbacks'][1]['duration_seconds'] = 2.345 - events = list(json.loads(videos.render_report(data, 'ontime'))['rundowns']['default']['entries'].values()) - self.assertTrue(events[0]['skip']) - self.assertIn('Duration unknown', events[0]['note']) - self.assertEqual(events[1]['duration'], 2345) - self.assertEqual(events[1]['timeStart'], 0) - self.assertFalse(events[1]['linkStart']) - - def test_ontime_rejects_invalid_durations_without_invalid_json(self): - for seconds in (float('nan'), float('inf'), -1, 86400): - with self.subTest(seconds=seconds): - data = self.report() - data['playbacks'][0]['duration_seconds'] = seconds - project = json.loads(videos.render_report(data, 'ontime')) - event = next(iter(project['rundowns']['default']['entries'].values())) - self.assertEqual(event['duration'], 0) - self.assertTrue(event['skip']) - - def report(self): - rows = [ - ('a', 'clip.mp4', 1024, 2.5, '1920×1080', 'h264'), - ('b', 'A #1.mp4', 512, 1.0, '32×24', 'mpeg4'), - ('c', 'unused.mp4', 128, None, 'Unknown', 'Unknown'), - ] - return videos.report_data(Path('Review & plans.pptx'), rows, - defaultdict(set, a={10}, b={2, 12}), {5}, self.root) - - def test_reports_sort_numerically_and_preserve_unknown_duration(self): - data = self.report() - self.assertEqual([v['slides'] for v in data['videos']], [[2, 12], [10], []]) - self.assertEqual(data['total_duration_seconds'], 4.5) - self.assertEqual(data['total_media_duration_seconds'], 3.5) - self.assertEqual(data['known_durations'], 2) - decoded = json.loads(videos.render_report(data, 'json')) - self.assertIsNone(decoded['videos'][-1]['duration_seconds']) - self.assertEqual(decoded['external_media_slides'], [5]) - - def test_text_tables_align_and_put_duration_second(self): - for format in ('md', 'txt'): - with self.subTest(format=format): - lines = [line for line in videos.render_report(self.report(), format).splitlines() if line.startswith('|')] - self.assertEqual(lines[0].split('|')[2].strip(), 'Duration') - columns = {tuple(i for i, char in enumerate(line) if char == '|') for line in lines} - self.assertEqual(len(columns), 1) - self.assertIn('Unreferenced', lines[-1]) - - def test_visual_reports_escape_document_data(self): - data = self.report() - rendered = videos.render_report(data, 'html') - self.assertIn('Review & plans.pptx', rendered) - self.assertIn('A <clip> #1.mp4', rendered) - self.assertNotIn('', rendered) - data['presentation'] = 'Quotes " and #panic("oops").pptx' - rendered = videos.render_report(data, 'typst') - self.assertIn(videos.typst_string(data['presentation']), rendered) - self.assertEqual(videos.typst_string('a\\b"\n'), '"a\\\\b\\"\\u{a}"') - - def test_pdf_generation_keeps_source_and_invokes_typst(self): - def compile_pdf(command, **kwargs): - self.assertEqual(command[:2], ['typst', 'compile']) - self.assertTrue(Path(command[2]).is_file()) - Path(command[3]).write_bytes(b'%PDF-test') - - with patch.object(videos.subprocess, 'run', side_effect=compile_pdf) as run, contextlib.redirect_stdout(io.StringIO()): - videos.write_reports(self.report(), ['pdf'], self.root) - run.assert_called_once() - self.assertTrue((self.root / 'timings.typ').is_file()) - self.assertEqual((self.root / 'timings.pdf').read_bytes(), b'%PDF-test') - - def test_dense_pdf_has_portrait_media_table_and_discreet_title(self): - source = videos.render_report(self.report(), 'pdf-dense') - self.assertNotIn('flipped: true', source) - self.assertIn('columns: (30mm, 1fr, auto)', source) - self.assertIn('table.header(strong("Slide(s)"), strong("Media"), strong("Duration"))', source) - self.assertIn('"2", "A #1.mp4", pill("00:00:01.000"', source) - self.assertIn('"12", "A #1.mp4", pill("00:00:01.000"', source) - self.assertIn('"Unreferenced", "unused.mp4", pill("Unknown"', source) - self.assertIn('#par(text(size: 10pt, fill: rgb("#626b80"), "Video timings — Review & plans.pptx"))', source) - for unwanted in ('metric(', 'Embedded videos', 'Total duration', 'Resolution', 'Codec'): - self.assertNotIn(unwanted, source) - self.assertIn('text(size: 7pt', source) - self.assertIn('trimming', source) - - def test_dense_pdf_compiles_its_own_source(self): - with patch.object(videos.subprocess, 'run') as compiler, contextlib.redirect_stdout(io.StringIO()): - videos.write_reports(self.report(), ['pdf-dense'], self.root) - command = compiler.call_args.args[0] - self.assertEqual(command, ['typst', 'compile', str(self.root / 'timings-dense.typ'), - str(self.root / 'timings-dense.pdf')]) - self.assertFalse((self.root / 'timings.typ').exists()) - - def test_failed_probe_returns_unknown_metadata(self): - failure = subprocess.CalledProcessError(1, ['ffprobe']) - with patch.object(videos.subprocess, 'run', side_effect=failure): - self.assertEqual(videos.probe(self.root / 'bad.mp4'), (None, 'Unknown', 'Unknown')) - - def test_invalid_archive_fails_without_output(self): - source = self.root / 'bad.pptx' - source.write_bytes(b'not a zip') - self.assertEqual(self.invoke(source, '--timings-only'), 1) - self.assertFalse((self.root / 'bad_videos').exists()) - - -if __name__ == '__main__': - unittest.main() diff --git a/tools/ontime.py b/tools/ontime.py deleted file mode 100644 index 325da93..0000000 --- a/tools/ontime.py +++ /dev/null @@ -1,63 +0,0 @@ -"""Create an Ontime 4 project from a video timing report.""" -import math -from uuid import NAMESPACE_URL, uuid5 - - -def ontime_project(data): - """Expand shared videos into slide cues; retain uncertain cues as skipped.""" - occurrences = [ - (slide, video) - for video in data.get('playbacks', data['videos']) - if video.get('ontime_eligible', True) - for slide in (video['slides'] or [None]) - ] - occurrences.sort(key=lambda item: (item[0] if item[0] is not None else math.inf, - item[1]['name'], item[1]['archive_path'])) - entries = {} - elapsed = 0 - has_previous = False - for slide, video in occurrences: - seconds = video['duration_seconds'] - valid = seconds is not None and math.isfinite(seconds) and 0 <= seconds <= 86399 - duration = round(seconds * 1000) if valid else 0 - skipped = not valid or slide is None - cue = f'Slide {slide}' if slide is not None else 'Unreferenced' - note = f'{data["presentation"]} — {video["archive_path"]}.' - if not valid: - note += ' Duration unknown or outside Ontime limits; review before enabling.' - if slide is None: - note += ' No slide reference; review before enabling.' - event_id = uuid5(NAMESPACE_URL, f'{data["presentation"]}/{video["archive_path"]}#{slide}:{video.get("shape_id", "")}').hex - entries[event_id] = { - 'id': event_id, 'type': 'event', 'cue': cue, 'title': video['name'], - 'note': note, 'duration': duration, 'timeStart': elapsed % 86400000, - 'timeEnd': (elapsed + duration) % 86400000, - 'timeStrategy': 'lock-duration', 'linkStart': has_previous, - 'timerType': 'count-down', 'endAction': 'none', - 'skip': skipped, 'colour': '#b7791f' if skipped else '#5744b5', - 'timeWarning': min(120000, duration // 5), - 'timeDanger': min(60000, duration // 10), - 'countToEnd': False, 'flag': False, 'custom': {}, 'triggers': [], - } - if not skipped: - elapsed += duration - has_previous = True - description = ( - 'Video cues in slide order, one per supported video occurrence. ' - 'Times start at midnight and are linked; set the first cue to your show start. ' - 'PowerPoint trims are applied. Loops and unsupported timing are omitted. ' - 'Unknown durations and unreferenced media are skipped pending review.' - ) - if data['external_media_slides']: - description += ' External media was not exported (slides: ' + ', '.join(map(str, data['external_media_slides'])) + ').' - return { - 'settings': {'version': '4.0.0'}, - 'project': {'title': data['presentation'], 'description': description}, - 'rundowns': {'default': { - 'id': 'default', 'title': 'Video timings', 'entries': entries, - 'order': list(entries), 'flatOrder': list(entries), 'revision': 0, - }}, - 'customFields': {}, 'urlPresets': [], 'viewSettings': {}, - 'automation': {'enabledAutomations': False, 'enabledOscIn': False, - 'triggers': [], 'automations': {}}, - } diff --git a/tools/playback.py b/tools/playback.py deleted file mode 100644 index 5c53acd..0000000 --- a/tools/playback.py +++ /dev/null @@ -1,121 +0,0 @@ -"""Read per-shape PowerPoint video trims and flag unsupported timing.""" -import math -import re - -P = 'http://schemas.openxmlformats.org/presentationml/2006/main' -P14 = 'http://schemas.microsoft.com/office/powerpoint/2010/main' -R = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' - - -def time_offset(value): - """Office ST_UniversalTimeOffset: default unit is milliseconds.""" - match = re.fullmatch(r'(\d+(?:\.\d+)?)(h|min|s|ms|[μµ]s|ns)?', value.strip()) - if not match: - raise ValueError(f'Invalid time offset: {value}') - seconds = float(match[1]) * { - None: .001, 'h': 3600, 'min': 60, 's': 1, - 'ms': .001, 'μs': .000001, 'µs': .000001, 'ns': .000000001, - }[match[2]] - if not math.isfinite(seconds): - raise ValueError('Non-finite time offset') - return seconds - - -def shape_playbacks(root, relationships, video_parts, slide): - parents = {child: parent for parent in root.iter() for child in parent} - result = [] - for shape in root.iter(): - if shape.tag not in (f'{{{P}}}pic', f'{{{P}}}sp', f'{{{P}}}graphicFrame'): - continue - identity = shape.find(f'.//{{{P}}}cNvPr') - shape_id = identity.get('id') if identity is not None else None - parts = {} - for el in shape.iter(): - if el.tag.rsplit('}', 1)[-1] not in ('videoFile', 'media'): - continue - for attr in (f'{{{R}}}embed', f'{{{R}}}link'): - part = relationships.get(el.get(attr), (None, ''))[0] - if part in video_parts: - parts.setdefault(part, []) - if el.tag == f'{{{P14}}}media': - parts[part].extend(el.findall(f'{{{P14}}}trim')) - for part, trims in parts.items(): - item = {'archive_path': part, 'slide': slide, 'shape_id': shape_id, - 'trim_start_seconds': 0.0, 'trim_end_seconds': 0.0, - 'playback_status': 'normal', 'playback_notes': []} - try: - values = {(time_offset(t.get('st', '0')), time_offset(t.get('end', '0'))) for t in trims} - if len(values) > 1: - raise ValueError('Conflicting trims') - if values: - item['trim_start_seconds'], item['trim_end_seconds'] = values.pop() - except ValueError: - item['playback_status'] = 'invalid-trim' - item['playback_notes'].append('Invalid or conflicting trim settings.') - if shape_id is not None: - for media in root.iter(f'{{{P}}}cMediaNode'): - target = media.find(f'{{{P}}}tgtEl/{{{P}}}spTgt') - if target is None or target.get('spid') != shape_id: - continue - # The media node and its ancestor timing containers can repeat. - timing = list(media.findall(f'{{{P}}}cTn')) - parent = parents.get(media) - while parent is not None: - if parent.tag == f'{{{P}}}cTn': - timing.append(parent) - parent = parents.get(parent) - for node in timing: - repeat = node.get('repeatCount') - repeated = repeat is not None and repeat not in ('1000', '1000.0', '100%') - if repeated or node.get('repeatDur') not in (None, '0'): - item['playback_status'] = 'looping' - item['playback_notes'].append('Repeated playback; not exported to Ontime.') - unsupported = ( - node.get('spd') not in (None, '100000', '100%') - or node.get('autoRev') in ('1', 'true') - or node.get('accel') not in (None, '0', '0%') - or node.get('decel') not in (None, '0', '0%') - or node.get('tmFilter') is not None - or node.find(f'{{{P}}}endCondLst') is not None - ) - if unsupported: - if item['playback_status'] != 'looping': - item['playback_status'] = 'custom-timing' - item['playback_notes'].append('Custom speed, reverse, or end conditions are not simulated.') - if media.get('numSld') not in (None, '1'): - if item['playback_status'] != 'looping': - item['playback_status'] = 'custom-timing' - item['playback_notes'].append('Playback across slides is not simulated.') - # Natural media duration is commonly encoded as "indefinite". - # A finite timing cap needs timeline evaluation, not trim maths. - for node in media.findall(f'{{{P}}}cTn'): - if node.get('dur') not in (None, 'indefinite', 'media'): - if item['playback_status'] != 'looping': - item['playback_status'] = 'custom-timing' - item['playback_notes'].append('Explicit animation duration is not simulated.') - item['playback_notes'] = list(dict.fromkeys(item['playback_notes'])) - if item not in result: - result.append(item) - return result - - -def effective_playback(video, settings): - result = {**video, **settings} - result['slides'] = [settings['slide']] if settings['slide'] is not None else [] - original = video['duration_seconds'] - result['original_duration_seconds'] = original - start, end = settings['trim_start_seconds'], settings['trim_end_seconds'] - status = settings['playback_status'] - result['duration_seconds'] = None - if status == 'normal': - if original is None: - status = 'unknown' - elif start + end >= original and (start or end): - status = 'invalid-trim' - result['playback_notes'] = [*settings['playback_notes'], 'Trim removes the whole media or exceeds its duration.'] - else: - result['duration_seconds'] = round(original - start - end, 9) - status = 'trimmed' if start or end else 'normal' - result['playback_status'] = status - result['ontime_eligible'] = status in ('normal', 'trimmed', 'unknown') - return result diff --git a/tools/pptx_videos.py b/tools/pptx_videos.py deleted file mode 100644 index 076f88a..0000000 --- a/tools/pptx_videos.py +++ /dev/null @@ -1,552 +0,0 @@ -#!/usr/bin/env python3 -"""Extract embedded PPTX videos and report their slide references and metadata.""" -import argparse -import html -import json -import math -import posixpath -import re -import shutil -import subprocess -import sys -import tempfile -import zipfile -from collections import defaultdict -from pathlib import Path -from urllib.parse import quote -from xml.etree import ElementTree as ET - -if __package__: - from .ontime import ontime_project - from .progress import Progress, status - from .playback import effective_playback, shape_playbacks -else: - from ontime import ontime_project - from progress import Progress, status - from playback import effective_playback, shape_playbacks - -VIDEO_EXTS = {'.mp4', '.m4v', '.mov', '.avi', '.wmv', '.webm', '.mpg', '.mpeg', '.mkv', '.asf', '.3gp', '.ts'} -REL_NS = 'http://schemas.openxmlformats.org/package/2006/relationships' -R_NS = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' -P_NS = 'http://schemas.openxmlformats.org/presentationml/2006/main' -REPORT_FORMATS = ('html', 'typst', 'pdf', 'pdf-dense', 'md', 'txt', 'json', 'ontime') -HEADERS = ('Slide(s)', 'Duration', 'Video', 'Size', 'Resolution', 'Codec', 'Original', 'Playback') -REPORT_NOTES = ( - 'Duration applies PowerPoint trimming per video occurrence. Original is the media file duration.', - 'Videos linked externally are not downloaded. Slide numbers follow presentation order.', -) - - -def xml(z, name): - try: - return ET.fromstring(z.read(name)) - except (KeyError, ET.ParseError): - return None - - -def rels(z, source): - directory, basename = posixpath.split(source) - path = posixpath.join(directory, '_rels', basename + '.rels') - root = xml(z, path) - if root is None: - return {} - result = {} - for rel in root.findall(f'{{{REL_NS}}}Relationship'): - rid = rel.get('Id') - target = rel.get('Target', '') - if not rid: - continue - if rel.get('TargetMode', '').lower() == 'external': - result[rid] = (None, rel.get('Type', '')) - else: - # Targets can be package-root absolute or relative to the source part. - target = target.split('#', 1)[0].split('?', 1)[0] - resolved = posixpath.normpath(target.lstrip('/') if target.startswith('/') else posixpath.join(directory, target)) - result[rid] = (resolved, rel.get('Type', '')) - return result - - -def slide_paths(z): - root = xml(z, 'ppt/presentation.xml') - mapping = rels(z, 'ppt/presentation.xml') - if root is not None: - ordered = [] - for slide in root.findall(f'.//{{{P_NS}}}sldId'): - target = mapping.get(slide.get(f'{{{R_NS}}}id'), (None, ''))[0] - if target: - ordered.append(target) - if ordered: - return ordered - return sorted((n for n in z.namelist() if re.fullmatch(r'ppt/slides/slide\d+\.xml', n)), key=lambda n: int(re.search(r'slide(\d+)', n).group(1))) - - -def discover(z): - """Map actual archive media parts to presentation-order slide numbers.""" - names = set(z.namelist()) - videos = sorted((n for n in names if n.startswith('ppt/media/') and Path(n).suffix.lower() in VIDEO_EXTS)) - uses = defaultdict(set) - external = set() - for index, slide in enumerate(slide_paths(z), 1): - root = xml(z, slide) - if root is None: - continue - mapping = rels(z, slide) - # Only relationships referenced by videoFile or p14:media elements; - # excludes audio-only attachments and poster images. - for el in root.iter(): - tag = el.tag.rsplit('}', 1)[-1] - if tag not in ('videoFile', 'media'): - continue - for attr in (f'{{{R_NS}}}link', f'{{{R_NS}}}embed'): - rid = el.get(attr) - if not rid or rid not in mapping: - continue - target, rel_type = mapping[rid] - if tag == 'media' and not rel_type.endswith('/media'): - continue - if target is None: - if tag == 'videoFile' or rel_type.endswith('/media'): - external.add(index) - elif target in names and Path(target).suffix.lower() in VIDEO_EXTS: - uses[target].add(index) - return videos, uses, external - - -def size_fmt(n): - for unit in ('B', 'KiB', 'MiB', 'GiB', 'TiB'): - if n < 1024 or unit == 'TiB': - return f'{n:.0f} {unit}' if unit == 'B' else f'{n:.2f} {unit}' - n /= 1024 - - -def playback_settings(z, videos): - settings = defaultdict(list) - for index, slide in enumerate(slide_paths(z), 1): - root = xml(z, slide) - if root is not None: - for item in shape_playbacks(root, rels(z, slide), set(videos), index): - settings[item['archive_path']].append(item) - return settings - - -def time_fmt(seconds): - if seconds is None: - return 'Unknown' - millis = round(seconds * 1000) - h, rem = divmod(millis, 3600000) - m, rem = divmod(rem, 60000) - s, ms = divmod(rem, 1000) - return f'{h:02}:{m:02}:{s:02}.{ms:03}' - - -def probe(path): - try: - p = subprocess.run(['ffprobe', '-v', 'error', '-show_entries', 'format=duration:stream=codec_type,width,height,codec_name', '-of', 'json', str(path)], capture_output=True, text=True, check=True) - data = json.loads(p.stdout) - duration = data.get('format', {}).get('duration') - duration = float(duration) if duration not in (None, 'N/A') else None - if duration is not None and (not math.isfinite(duration) or duration < 0): - duration = None - streams = data.get('streams', []) - video = next((s for s in streams if s.get('codec_type') == 'video'), {}) - resolution = f"{video['width']}×{video['height']}" if video.get('width') and video.get('height') else 'Unknown' - return duration, resolution, video.get('codec_name', 'Unknown') - except (subprocess.CalledProcessError, OSError, ValueError, json.JSONDecodeError): - return None, 'Unknown', 'Unknown' - - -def esc(s): - return str(s).replace('|', '\\|').replace('\n', ' ') - - -def aligned_table(cells, markdown=True): - headers = HEADERS - widths = [max(3, *(len(row[i]) for row in [headers, *cells])) for i in range(len(headers))] - right_aligned = {1, 3, 6} - - def render(row): - return '| ' + ' | '.join( - value.rjust(widths[i]) if i in right_aligned else value.ljust(widths[i]) - for i, value in enumerate(row) - ) + ' |' - - separators = [ - '-' * (width - 1) + ':' if markdown and i in right_aligned else '-' * width - for i, width in enumerate(widths) - ] - return [render(headers), render(separators), *(render(row) for row in cells)] - - -def report_formats(value): - formats = [item.strip().lower() for item in value.split(',')] - if any(item not in (*REPORT_FORMATS, 'all') for item in formats): - raise argparse.ArgumentTypeError('Choose comma-separated formats from: ' + ', '.join((*REPORT_FORMATS, 'all'))) - return list(dict.fromkeys( - format for item in formats for format in (REPORT_FORMATS if item == 'all' else (item,)) - )) - - -def report_data(source, rows, uses, external, out, settings=None): - videos = [] - for part, name, size, duration, resolution, codec in sorted( - rows, key=lambda row: (min(uses[row[0]], default=float('inf')), row[1])): - videos.append({ - 'slides': sorted(uses[part]), 'duration_seconds': duration, - 'name': name, 'size_bytes': size, 'resolution': resolution, - 'codec': codec, 'archive_path': part, - 'extracted_file': f'../videos/{name}' if (out / 'videos' / name).is_file() else None, - }) - playbacks = [] - for video in videos: - occurrences = list((settings or {}).get(video['archive_path'], [])) - covered = {item['slide'] for item in occurrences} - # Retain references without recognized shape metadata, and orphan media. - for slide in (video['slides'] or [None]): - if slide not in covered: - occurrences.append({'slide': slide, 'shape_id': None, - 'trim_start_seconds': 0.0, 'trim_end_seconds': 0.0, - 'playback_status': 'normal', 'playback_notes': []}) - playbacks.extend(effective_playback(video, item) for item in occurrences) - playbacks.sort(key=lambda item: (item['slide'] if item['slide'] is not None else math.inf, - item['name'], item['shape_id'] or '')) - return { - 'presentation': source.name, - 'embedded_videos': len(videos), - 'total_size_bytes': sum(v['size_bytes'] for v in videos), - 'total_duration_seconds': sum(v['duration_seconds'] for v in playbacks if v['duration_seconds'] is not None), - 'total_media_duration_seconds': sum(v['duration_seconds'] for v in videos if v['duration_seconds'] is not None), - 'known_durations': sum(v['duration_seconds'] is not None for v in videos), - 'known_playback_durations': sum(v['duration_seconds'] is not None for v in playbacks), - 'playbacks': playbacks, - 'videos': videos, 'external_media_slides': sorted(external), - 'notes': list(REPORT_NOTES), - } - - -def typst_string(value): - # Encode as a literal string, never as executable Typst markup. - return '"' + ''.join( - '\\' + c if c in ('\\', '"') else f'\\u{{{ord(c):x}}}' if ord(c) < 32 else c - for c in value - ) + '"' - - -def trim_detail(video): - start = video.get('trim_start_seconds', 0) - end = video.get('trim_end_seconds', 0) - if not (start or end): - return '' - return f'Trim removed · start {time_fmt(start)} · end {time_fmt(end)}' - - -def typst_media(video, dense=False): - """Keep playback annotations with the media, without adding table columns.""" - detail = trim_detail(video) - if not detail and video['playback_status'] != 'looping': - return typst_string(video['name']) - content = '#' + typst_string(video['name']) - if video['playback_status'] == 'looping': - colors = '"#fff0ce", "#805300"' if dense else 'bg: "#fff0ce", fg: "#805300"' - content += f' #pill("Looping", {colors})' - if detail: - content += '\n#par(leading: 2pt, text(size: 7pt, fill: rgb("#626b80"), ' + typst_string(detail) + '))' - return '[' + content + ']' - - -def render_report(data, format): - if format == 'ontime': - return json.dumps(ontime_project(data), ensure_ascii=False, indent=2, allow_nan=False) + '\n' - title = f'Video timings — {data["presentation"]}' - report_rows = data['playbacks'] - metrics = [ - ('Embedded videos', str(data['embedded_videos'])), - ('Total duration', time_fmt(data['total_duration_seconds'])), - ('Total size', size_fmt(data['total_size_bytes'])), - ('Durations available', f'{data["known_playback_durations"]} / {len(report_rows)}'), - ] - summary = [ - f'Embedded videos: {data["embedded_videos"]}', - f'Total size: {size_fmt(data["total_size_bytes"])}', - f'Total duration: {time_fmt(data["total_duration_seconds"])} ' - f'({data["known_playback_durations"]}/{len(report_rows)} occurrences with known playback duration)', - ] - notes = list(data['notes']) - if data['external_media_slides']: - notes.append('Slides with external media links: ' + - ', '.join(map(str, data['external_media_slides'])) + ' (not extracted).') - labels = {'looping': 'Looping', 'custom-timing': 'Custom timing', 'invalid-trim': 'Invalid trim'} - cells = [ - [', '.join(map(str, v['slides'])) or 'Unreferenced', - labels.get(v['playback_status'], time_fmt(v['duration_seconds'])), v['name'], size_fmt(v['size_bytes']), - v['resolution'], v['codec'], time_fmt(v['original_duration_seconds']), v['playback_status']] - for v in report_rows - ] - if format == 'json': - return json.dumps(data, ensure_ascii=False, indent=2, allow_nan=False) + '\n' - if format in ('md', 'txt'): - for row, video in zip(cells, report_rows): - detail = trim_detail(video) - if detail: - row[7] += '; ' + detail - row[:] = [esc(value) if format == 'md' else value.replace('\n', ' ') for value in row] - if format == 'md' and video['extracted_file']: - row[2] = f'[{row[2]}]({quote(video["extracted_file"])})' - lines = [('# ' if format == 'md' else '') + title, ''] - lines += ['- ' + line for line in summary] - lines += ['', *aligned_table(cells, markdown=format == 'md'), ''] - lines += [('> ' if format == 'md' else '') + note for note in notes] - return '\n'.join(lines) + '\n' - if format == 'html': - table_rows = [] - for row, video in zip(cells, report_rows): - row = [html.escape(value) for value in row] - row[0] = ' '.join(f'{slide}' for slide in video['slides']) or 'Unreferenced' - duration_class = 'duration' if video['duration_seconds'] is not None else 'warning' - row[1] = f'{row[1]}' - row[5] = f'{row[5]}' - if video['extracted_file']: - row[2] = f'{row[2]}' - if video['playback_status'] == 'looping': - row[1] = '—' - row[2] += ' Looping' - detail = trim_detail(video) - if detail: - row[2] += f'{html.escape(detail)}' - table_rows.append('' + ''.join(f'{value}' for value in row) + '') - return ( - '\n\n' - '\n' - f'{html.escape(title)}\n' - '\n' - '
Presentation media report

Video timings

' - f'

{html.escape(data["presentation"])}

' + - ''.join(f'
{html.escape(label)}{html.escape(value)}
' for label, value in metrics) + - '
' + - ''.join(f'' for heading in HEADERS) + - '\n' + '\n'.join(table_rows) + - '
{heading}
' + - ''.join(f'

{html.escape(note)}

' for note in notes) + - '
\n' - ) - if format == 'pdf-dense': - lines = [ - '#set page(paper: "a4", margin: 14mm,', - ' footer: context align(right, text(size: 7pt, fill: rgb("#626b80"), counter(page).display("1"))))', - '#set text(font: "DejaVu Sans", size: 9pt, fill: rgb("#172033"))', - '#set par(justify: false)', - '#let pill(body, bg, fg) = box(fill: rgb(bg), radius: 20pt,', - ' inset: (x: 7pt, y: 2pt), text(size: 8pt, fill: rgb(fg), body))', - '#par(text(size: 10pt, fill: rgb("#626b80"), ' + typst_string(title) + '))', - '#v(4pt)', - '#table(', - ' columns: (30mm, 1fr, auto),', - ' align: (left + horizon, left + horizon, right + horizon),', - ' inset: (x: 8pt, y: 4pt),', - ' stroke: (top: none, left: none, right: none, bottom: 0.4pt + rgb("#e2e6f0")),', - ' fill: (x, y) => if y == 0 { rgb("#eeeafd") } else if calc.even(y) { rgb("#f8f9fc") },', - ' table.header(strong("Slide(s)"), strong("Media"), strong("Duration")),', - ] - for row, video in zip(cells, report_rows): - bg, fg = ('#e3f4ee', '#176349') if video['duration_seconds'] is not None else ('#fff0ce', '#805300') - duration = '"—"' if video['playback_status'] == 'looping' else f'pill({typst_string(row[1])}, "{bg}", "{fg}")' - lines.append(f' {typst_string(row[0])}, {typst_media(video, dense=True)}, {duration},') - lines += [')', '#v(6pt)'] - lines += ['#par(text(size: 7pt, fill: rgb("#626b80"), ' + typst_string(note) + '))' for note in notes] - return '\n'.join(lines) + '\n' - if format == 'typst': - lines = [ - '#set page(paper: "a4", flipped: true, margin: 16mm,', - ' footer: context align(right, text(size: 8pt, fill: rgb("#626b80"), counter(page).display("1"))))', - '#set text(font: "DejaVu Sans", size: 9pt, fill: rgb("#172033"))', - '#set par(justify: false)', - '#let pill(body, bg: "#eeeafd", fg: "#49359b") = box(', - ' fill: rgb(bg), radius: 20pt, inset: (x: 7pt, y: 3pt),', - ' text(size: 8pt, weight: "medium", fill: rgb(fg), body))', - '#let metric(label, value) = block(width: 100%, fill: rgb("#f3f1fc"),', - ' radius: 8pt, inset: 12pt)[', - ' #text(size: 8pt, fill: rgb("#626b80"), label)', - ' #v(5pt)', - ' #text(size: 17pt, weight: "bold", fill: rgb("#49359b"), value)', - ']', - '#text(size: 8pt, weight: "bold", fill: rgb("#5744b5"), tracking: 1pt)[PRESENTATION MEDIA REPORT]', - '#v(5pt)', - '#text(size: 28pt, weight: "bold")[Video timings]', - '#par(text(fill: rgb("#626b80"), ' + typst_string(data['presentation']) + '))', - '#v(8pt)', - '#grid(columns: (1fr, 1fr, 1fr, 1fr), gutter: 10pt,', - ] - lines += [' metric(' + typst_string(label) + ', ' + typst_string(value) + '),' for label, value in metrics] - lines += [')'] - lines += [ - '#v(16pt)', - '#table(', - ' columns: (22mm, auto, 1fr, auto, auto, auto, auto, auto),', - ' align: (left + horizon, right + horizon, left + horizon, right + horizon, left + horizon, left + horizon, right + horizon, left + horizon),', - ' inset: 5pt,', - ' stroke: (top: none, left: none, right: none, bottom: 0.4pt + rgb("#e2e6f0")),', - ' fill: (x, y) => if y == 0 { rgb("#eeeafd") } else if calc.even(y) { rgb("#f8f9fc") },', - ' table.header(' + ', '.join('text(size: 8pt, weight: "bold", fill: rgb("#49359b"), ' + typst_string(h) + ')' for h in HEADERS) + '),', - ] - for row, video in zip(cells, report_rows): - values = [typst_string(value) for value in row] - values[0] = '[' + ' '.join('#pill(' + typst_string(str(slide)) + ')' for slide in video['slides']) + ']' if video['slides'] else 'text(size: 8pt, fill: rgb("#626b80"), "Unreferenced")' - bg, fg = ('#e3f4ee', '#176349') if video['duration_seconds'] is not None else ('#fff0ce', '#805300') - values[1] = f'pill({values[1]}, bg: "{bg}", fg: "{fg}")' - if video['playback_status'] == 'looping': - values[1] = '"—"' - values[2] = typst_media(video) - values[5] = f'pill({values[5]}, bg: "#edf0f6", fg: "#566176")' - lines.append(' ' + ', '.join(values) + ',') - lines += [')', '#v(10pt)'] - lines += ['#par(text(size: 8pt, fill: rgb("#626b80"), ' + typst_string(note) + '))' for note in notes] - return '\n'.join(lines) + '\n' - raise ValueError(f'Unsupported report format: {format}') - - -def write_reports(data, formats, out): - # Keep the source beside the PDF so it can be edited and compiled again. - if 'pdf' in formats and 'typst' not in formats: - formats = [*formats, 'typst'] - for format in formats: - if format == 'pdf': - continue - extension = {'typst': 'typ', 'ontime': 'ontime.json'}.get(format, format) - report = out / ('timings-dense.typ' if format == 'pdf-dense' else f'timings.{extension}') - status(f'Writing report: {report}') - report.write_text(render_report(data, format), encoding='utf-8') - status(f'Report: {report}', 'success', persist=True) - for format in ('pdf', 'pdf-dense'): - if format not in formats: - continue - stem = 'timings-dense' if format == 'pdf-dense' else 'timings' - report = out / f'{stem}.pdf' - status(f'Compiling PDF with Typst: {report}') - subprocess.run(['typst', 'compile', str((out / f'{stem}.typ').resolve()), - str(report.resolve())], check=True, capture_output=True, text=True) - status(f'Report: {report}', 'success', persist=True) - - -def main(): - parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.ArgumentDefaultsHelpFormatter) - parser.add_argument('presentation', type=Path, help='Source .pptx file') - parser.add_argument('-o', '--output', type=Path, help='Output directory (default: _videos)') - mode = parser.add_mutually_exclusive_group() - mode.add_argument('--extract-only', action='store_true', help='Extract embedded videos without a report') - mode.add_argument('--timings-only', action='store_true', help='Report video timings without keeping newly extracted videos') - parser.add_argument('--overwrite', action='store_true', help='Overwrite already extracted files') - parser.add_argument('--report', type=report_formats, action='append', metavar='FORMAT[,FORMAT...]', - help='Report formats: html, typst, pdf, pdf-dense, md, txt, json, ontime, or all. Repeatable; default: md,ontime. PDFs require typst and keep their .typ sources.') - args = parser.parse_args() - if args.extract_only and args.report: - parser.error('--report cannot be combined with --extract-only.') - formats = list(dict.fromkeys(format for group in (args.report or [['md', 'ontime']]) for format in group)) - source = args.presentation - if not source.is_file(): - parser.error(f'Not a file: {source}') - out = args.output or source.with_name(source.stem + '_videos') - video_dir = out / 'videos' - report_dir = out / 'reports' - try: - with Progress() as progress, zipfile.ZipFile(source) as z: - status(f'Scanning presentation: {source}') - videos, uses, external = discover(z) - settings = playback_settings(z, videos) if not args.extract_only else {} - if external: - status(f'External media on slide(s) {", ".join(map(str, sorted(external)))} will not be downloaded.', 'warning') - if not videos: - status('No embedded video files found; no output created.', 'warning') - return 0 - status(f'Found {len(videos)} embedded video(s), {size_fmt(sum(z.getinfo(part).file_size for part in videos))} in the presentation.') - if not args.extract_only and shutil.which('ffprobe') is None: - parser.error('ffprobe is required for timings. Install ffmpeg or use --extract-only.') - if not args.extract_only and {'pdf', 'pdf-dense'}.intersection(formats) and shutil.which('typst') is None: - parser.error('typst is required for PDF reports. Install the Typst CLI or choose --report typst to generate source only.') - mode_label = 'extraction only' if args.extract_only else 'timings only' if args.timings_only else 'extraction and timings' - status(f'Mode: {mode_label}. Output: {out}') - if not args.timings_only: - video_dir.mkdir(parents=True, exist_ok=True) - rows = [] - total_bytes = 0 - progress.set(0, len(videos)) - for index, part in enumerate(videos, 1): - name = posixpath.basename(part) - dest = video_dir / name - slides = ', '.join(map(str, sorted(uses[part]))) or 'unreferenced' - status(f'[{index}/{len(videos)}] {name} — {size_fmt(z.getinfo(part).file_size)} — slide(s): {slides}') - if not args.timings_only: - if dest.exists() and not args.overwrite: - status(f' Keeping existing file: {dest}') - else: - status(f' Extracting to: {dest}') - with z.open(part) as src, dest.open('wb') as dst: - shutil.copyfileobj(src, dst) - status(' Extraction complete.', 'success') - if args.extract_only: - progress.set(index) - continue - if not dest.is_file(): - # A seekable temporary file supports media whose metadata - # cannot be read reliably from a pipe. - with tempfile.TemporaryDirectory(prefix='pptx-videos-') as tmp: - temporary_video = Path(tmp) / name - status(' Extracting a temporary copy for probing...') - with z.open(part) as src, temporary_video.open('wb') as dst: - shutil.copyfileobj(src, dst) - size = temporary_video.stat().st_size - status(' Probing temporary video with ffprobe...') - duration, resolution, codec = probe(temporary_video) - status(' Temporary copy removed.') - else: - size = dest.stat().st_size - status(f' Probing with ffprobe: {dest}') - duration, resolution, codec = probe(dest) - total_bytes += size - status(f' Original duration: {time_fmt(duration)} | Resolution: {resolution} | Codec: {codec}', - 'success' if duration is not None else 'warning') - if duration is None: - status(' ffprobe could not determine the duration; continuing with available metadata.', 'warning') - rows.append((part, name, size, duration, resolution, codec)) - progress.set(index) - if args.extract_only: - status(f'Done: {len(videos)} video(s) processed. Output: {video_dir}', 'success', persist=True) - return 0 - report_dir.mkdir(parents=True, exist_ok=True) - data = report_data(source, rows, uses, external, out, settings) - write_reports(data, formats, report_dir) - status(f'Done: {data["known_playback_durations"]}/{len(data["playbacks"])} playback durations available, {time_fmt(data["total_duration_seconds"])} total, {size_fmt(total_bytes)}.', 'success', persist=True) - return 0 - except subprocess.CalledProcessError as e: - status(f'Typst compilation failed: {e.stderr.strip()}', 'error') - return 1 - except (zipfile.BadZipFile, OSError, ET.ParseError) as e: - status(str(e), 'error') - return 1 - - -if __name__ == '__main__': - sys.exit(main())