diff --git a/AGENTS.md b/AGENTS.md
index 5ff962c..7dc9d56 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -15,6 +15,10 @@ in `README.md`.
locally installed AppImages. PDF-to-PDF is a successful no-op.
- `test_exporter.py` covers exporter validation, no-op behavior, conversion
failures, and overwrite behavior.
+- `test_pptx_videos.py` covers slide discovery, extraction, temporary probing,
+ report formatting, and error handling.
+- `Jenkinsfile` runs the Python unit tests on `rust_no_docker`. CI is test-only:
+ no publishing, badges, or archived artifacts.
## Working conventions
@@ -28,7 +32,8 @@ in `README.md`.
in visual reports.
- Update `README.md` when command-line options or workflows change.
- Run checks appropriate to the change before committing. Exporter regression
- tests run with `python -m unittest test_exporter -v`. For rendering changes,
+ tests and video-report tests run with
+ `python3 -m unittest -v test_exporter test_pptx_videos`. 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
new file mode 100644
index 0000000..18be62e
--- /dev/null
+++ b/Jenkinsfile
@@ -0,0 +1,58 @@
+pipeline {
+ agent { label 'rust_no_docker' }
+
+ options {
+ skipDefaultCheckout(true)
+ timeout(time: 10, unit: 'MINUTES')
+ }
+
+ environment {
+ PYTHONUNBUFFERED = '1'
+ PYTHONDONTWRITEBYTECODE = '1'
+ NO_COLOR = '1'
+ }
+
+ stages {
+ stage('Checkout') {
+ steps {
+ deleteDir()
+ checkout scm
+ }
+ }
+
+ stage('Check Python') {
+ steps {
+ sh '''
+ set -eu
+ if ! command -v python3 >/dev/null 2>&1; then
+ echo "ERROR: python3 is required on this Jenkins worker." >&2
+ exit 1
+ fi
+ python3 --version
+ python3 -c 'import sys; sys.exit("Python 3.9 or newer is required." if sys.version_info < (3, 9) else 0)'
+ '''
+ }
+ }
+
+ stage('Tests') {
+ steps {
+ sh '''
+ set -eu
+ python3 -m unittest -v test_exporter test_pptx_videos
+ '''
+ }
+ }
+ }
+
+ post {
+ success {
+ echo 'All Python unit tests passed. No artifacts were published.'
+ }
+ failure {
+ echo 'Checkout, Python setup, or tests failed. See the build log.'
+ }
+ unstable {
+ echo 'The build is unstable. See the build log.'
+ }
+ }
+}
diff --git a/README.md b/README.md
index 5e4a1f7..c48f123 100644
--- a/README.md
+++ b/README.md
@@ -48,3 +48,32 @@ inside `images/`. Images default to 144 DPI. Existing output requires
`--overwrite`, which replaces generated files and removes stale numbered
slide/page PNGs. PDF-to-PDF is a successful no-op; other input extensions are
errors. Rendering completes in temporary storage before output is copied.
+
+## Tests and Jenkins
+
+Run the same suite locally and in Jenkins:
+
+```sh
+python3 -m unittest -v test_exporter test_pptx_videos
+```
+
+The declarative `Jenkinsfile` uses the `rust_no_docker` worker label and requires
+Git and Python 3.9 or newer. It performs a clean SCM checkout, checks Python,
+and runs the standard-library unit tests. No packages are installed.
+
+Tests cover export validation, overwrite handling, failed conversions, PPTX
+discovery and slide order, temporary video cleanup, report formats, and PDF
+compiler invocation. External CLI calls are mocked: CI does not require FFmpeg,
+Typst, DeckCraft, or PdfCraft and does not claim to verify rendering fidelity.
+
+This is a test-only pipeline on every configured branch: no build artifacts,
+archives, publication, badges, or Checks API calls. Status is reported in Jenkins.
+There are no pipeline credential bindings; SCM access uses the Jenkins job's
+configured repository credentials.
+
+Configure a Pipeline from SCM or multibranch job for this repository with
+`Jenkinsfile` as the script path (`main` is the default branch). For a Gitea-aware
+multibranch job, use the installation's Jenkins base URL plus
+`/gitea-webhook/post` as the Gitea webhook target and enable push events.
+The Jenkins administrator must supply the actual reachable URL and SCM
+credentials. This repository does not create the job or register the webhook.
diff --git a/test_exporter.py b/test_exporter.py
index 9513dfd..4ed9e9e 100644
--- a/test_exporter.py
+++ b/test_exporter.py
@@ -46,6 +46,44 @@ class ExporterTests(unittest.TestCase):
self.assertEqual(self.invoke(source, '--output', 'pdf,images', '-d', destination), 1)
self.assertFalse(destination.exists())
+ def test_pdf_render_uses_one_based_pages_and_requested_dpi(self):
+ source = self.root / 'input.pdf'
+ source.touch()
+ destination = self.root / 'output'
+ commands = []
+
+ def fake_run(command, **kwargs):
+ commands.append(command)
+ if command[1] == 'info':
+ return '{"pages": 2}'
+ Path(command[-1]).write_bytes(b'image')
+ return ''
+
+ with patch.object(exporter, 'find_cli', return_value=Path('/fake/cli')), patch.object(exporter, 'run', side_effect=fake_run):
+ self.assertEqual(self.invoke(source, '--output', 'pdf,images', '--dpi', 192, '-d', destination), 0)
+ self.assertEqual([command[4] for command in commands[1:]], ['1', '2'])
+ self.assertTrue(all(command[6] == '192' for command in commands[1:]))
+ self.assertEqual(sorted(path.name for path in (destination / 'images').iterdir()),
+ ['page-0001.png', 'page-0002.png'])
+ self.assertFalse((destination / 'input.pdf').exists())
+
+ def test_invalid_page_count_does_not_publish(self):
+ source = self.root / 'input.pdf'
+ source.touch()
+ for pages in ('0', '-1', 'null', '"2"', 'true'):
+ with self.subTest(pages=pages), \
+ patch.object(exporter, 'find_cli', return_value=Path('/fake/cli')), \
+ patch.object(exporter, 'run', return_value='{"pages": ' + pages + '}'):
+ self.assertEqual(self.invoke(source, '--output', 'images'), 1)
+ self.assertFalse((self.root / 'input_export').exists())
+
+ def test_missing_cli_does_not_create_output(self):
+ source = self.root / 'input.pptx'
+ source.touch()
+ with patch.object(exporter, 'find_cli', side_effect=RuntimeError('CLI missing')):
+ self.assertEqual(self.invoke(source, '--output', 'pdf'), 1)
+ self.assertFalse((self.root / 'input_export').exists())
+
def test_overwrite_removes_stale_pages_but_preserves_other_files(self):
source = self.root / 'input.pdf'
source.touch()
diff --git a/test_pptx_videos.py b/test_pptx_videos.py
new file mode 100644
index 0000000..eb93539
--- /dev/null
+++ b/test_pptx_videos.py
@@ -0,0 +1,161 @@
+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
+
+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 / 'clip.mp4').exists())
+ self.assertEqual(len(probed), 1)
+ self.assertFalse(probed[0].exists())
+ data = json.loads((output / '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 / '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()], ['clip.mp4'])
+ self.assertEqual((output / 'clip.mp4').read_bytes(), b'video fixture')
+
+ 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'], 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_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()