remove huey

This commit is contained in:
Nick Sweeting
2025-12-24 23:40:18 -08:00
parent 6c769d831c
commit d95f0dc186
105 changed files with 3635 additions and 1402 deletions

View File

@@ -1,68 +0,0 @@
#!/usr/bin/env python3
"""
Install readability-extractor if not already available.
Runs at crawl start to ensure readability-extractor is installed.
Outputs JSONL for InstalledBinary.
"""
import json
import sys
from pathlib import Path
def main():
try:
from abx_pkg import Binary, NpmProvider, EnvProvider, BinProviderOverrides
NpmProvider.model_rebuild()
EnvProvider.model_rebuild()
# Note: npm package is from github:ArchiveBox/readability-extractor
readability_binary = Binary(
name='readability-extractor',
binproviders=[NpmProvider(), EnvProvider()],
overrides={'npm': {'packages': ['github:ArchiveBox/readability-extractor']}}
)
# Try to load, install if not found
try:
loaded = readability_binary.load()
if not loaded or not loaded.abspath:
raise Exception("Not loaded")
except Exception:
# Install via npm from GitHub repo
loaded = readability_binary.install()
if loaded and loaded.abspath:
# Output InstalledBinary JSONL
print(json.dumps({
'type': 'InstalledBinary',
'name': 'readability-extractor',
'abspath': str(loaded.abspath),
'version': str(loaded.version) if loaded.version else None,
'sha256': loaded.sha256,
'binprovider': loaded.loaded_binprovider.name if loaded.loaded_binprovider else 'unknown',
}))
sys.exit(0)
else:
print(json.dumps({
'type': 'Dependency',
'bin_name': 'readability-extractor',
'bin_providers': 'npm,env',
}))
print("Failed to install readability-extractor", file=sys.stderr)
sys.exit(1)
except Exception as e:
print(json.dumps({
'type': 'Dependency',
'bin_name': 'readability-extractor',
'bin_providers': 'npm,env',
}))
print(f"Error installing readability-extractor: {e}", file=sys.stderr)
sys.exit(1)
if __name__ == '__main__':
main()

View File

@@ -0,0 +1,123 @@
#!/usr/bin/env python3
"""
Validation hook for readability-extractor binary.
Runs at crawl start to verify readability-extractor is available.
Outputs JSONL for InstalledBinary and Machine config updates.
"""
import os
import sys
import json
import shutil
import hashlib
import subprocess
from pathlib import Path
def get_binary_version(abspath: str) -> str | None:
"""Get version string from binary."""
try:
result = subprocess.run(
[abspath, '--version'],
capture_output=True,
text=True,
timeout=5,
)
if result.returncode == 0 and result.stdout:
first_line = result.stdout.strip().split('\n')[0]
return first_line[:64]
except Exception:
pass
return None
def get_binary_hash(abspath: str) -> str | None:
"""Get SHA256 hash of binary."""
try:
with open(abspath, 'rb') as f:
return hashlib.sha256(f.read()).hexdigest()
except Exception:
return None
def find_readability() -> dict | None:
"""Find readability-extractor binary."""
try:
from abx_pkg import Binary, NpmProvider, EnvProvider
class ReadabilityBinary(Binary):
name: str = 'readability-extractor'
binproviders_supported = [NpmProvider(), EnvProvider()]
overrides: dict = {'npm': {'packages': ['github:ArchiveBox/readability-extractor']}}
binary = ReadabilityBinary()
loaded = binary.load()
if loaded and loaded.abspath:
return {
'name': 'readability-extractor',
'abspath': str(loaded.abspath),
'version': str(loaded.version) if loaded.version else None,
'sha256': loaded.sha256 if hasattr(loaded, 'sha256') else None,
'binprovider': loaded.binprovider.name if loaded.binprovider else 'env',
}
except ImportError:
pass
except Exception:
pass
# Fallback to shutil.which
abspath = shutil.which('readability-extractor') or os.environ.get('READABILITY_BINARY', '')
if abspath and Path(abspath).is_file():
return {
'name': 'readability-extractor',
'abspath': abspath,
'version': get_binary_version(abspath),
'sha256': get_binary_hash(abspath),
'binprovider': 'env',
}
return None
def main():
result = find_readability()
if result and result.get('abspath'):
print(json.dumps({
'type': 'InstalledBinary',
'name': result['name'],
'abspath': result['abspath'],
'version': result['version'],
'sha256': result['sha256'],
'binprovider': result['binprovider'],
}))
print(json.dumps({
'type': 'Machine',
'_method': 'update',
'key': 'config/READABILITY_BINARY',
'value': result['abspath'],
}))
if result['version']:
print(json.dumps({
'type': 'Machine',
'_method': 'update',
'key': 'config/READABILITY_VERSION',
'value': result['version'],
}))
sys.exit(0)
else:
print(json.dumps({
'type': 'Dependency',
'bin_name': 'readability-extractor',
'bin_providers': 'npm,env',
}))
print(f"readability-extractor binary not found", file=sys.stderr)
sys.exit(1)
if __name__ == '__main__':
main()

View File

@@ -0,0 +1,6 @@
<!-- Readability embed - reader-mode article view -->
<iframe src="{{ output_path }}"
class="extractor-embed readability-embed"
style="width: 100%; height: 100%; min-height: 500px; border: none; background: #fefefe;"
sandbox="allow-same-origin">
</iframe>

View File

@@ -0,0 +1,6 @@
<!-- Readability fullscreen - full reader-mode article -->
<iframe src="{{ output_path }}"
class="extractor-fullscreen readability-fullscreen"
style="width: 100%; height: 100vh; border: none; background: #fefefe;"
sandbox="allow-same-origin">
</iframe>

View File

@@ -0,0 +1 @@
📖

View File

@@ -0,0 +1,8 @@
<!-- Readability thumbnail - shows reader-mode extracted article content -->
<div class="extractor-thumbnail readability-thumbnail" style="width: 100%; height: 100px; overflow: hidden; background: #fefefe; padding: 8px; font-family: Georgia, serif; font-size: 11px; line-height: 1.4; color: #333;">
<iframe src="{{ output_path }}"
style="width: 100%; height: 300px; border: none; pointer-events: none;"
loading="lazy"
sandbox="allow-same-origin">
</iframe>
</div>

View File

@@ -2,7 +2,7 @@
Integration tests for readability plugin
Tests verify:
1. Install hook installs readability-extractor via abx-pkg
1. Validate hook checks for readability-extractor binary
2. Verify deps with abx-pkg
3. Plugin reports missing dependency correctly
4. Extraction works against real example.com content
@@ -21,7 +21,7 @@ import pytest
PLUGIN_DIR = Path(__file__).parent.parent
PLUGINS_ROOT = PLUGIN_DIR.parent
READABILITY_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_readability.py'))
READABILITY_INSTALL_HOOK = PLUGIN_DIR / 'on_Crawl__00_install_readability.py'
READABILITY_VALIDATE_HOOK = PLUGIN_DIR / 'on_Crawl__00_validate_readability.py'
TEST_URL = 'https://example.com'
@@ -101,48 +101,63 @@ def test_reports_missing_dependency_when_not_installed():
assert 'readability-extractor' in combined or 'BIN_NAME' in combined, "Should mention readability-extractor"
def test_readability_install_hook():
"""Test readability install hook to install readability-extractor if needed."""
def test_readability_validate_hook():
"""Test readability validate hook checks for readability-extractor binary."""
result = subprocess.run(
[sys.executable, str(READABILITY_INSTALL_HOOK)],
[sys.executable, str(READABILITY_VALIDATE_HOOK)],
capture_output=True,
text=True,
timeout=600
timeout=30
)
assert result.returncode == 0, f"Install hook failed: {result.stderr}"
# Verify InstalledBinary JSONL output
found_binary = False
for line in result.stdout.strip().split('\n'):
if line.strip():
try:
record = json.loads(line)
if record.get('type') == 'InstalledBinary':
assert record['name'] == 'readability-extractor'
assert record['abspath']
found_binary = True
break
except json.JSONDecodeError:
pass
assert found_binary, "Should output InstalledBinary record"
# Hook exits 0 if binary found, 1 if not found (with Dependency record)
if result.returncode == 0:
# Binary found - verify InstalledBinary JSONL output
found_binary = False
for line in result.stdout.strip().split('\n'):
if line.strip():
try:
record = json.loads(line)
if record.get('type') == 'InstalledBinary':
assert record['name'] == 'readability-extractor'
assert record['abspath']
found_binary = True
break
except json.JSONDecodeError:
pass
assert found_binary, "Should output InstalledBinary record when binary found"
else:
# Binary not found - verify Dependency JSONL output
found_dependency = False
for line in result.stdout.strip().split('\n'):
if line.strip():
try:
record = json.loads(line)
if record.get('type') == 'Dependency':
assert record['bin_name'] == 'readability-extractor'
assert 'npm' in record['bin_providers']
found_dependency = True
break
except json.JSONDecodeError:
pass
assert found_dependency, "Should output Dependency record when binary not found"
def test_verify_deps_with_abx_pkg():
"""Verify readability-extractor is available via abx-pkg after hook installation."""
"""Verify readability-extractor is available via abx-pkg."""
from abx_pkg import Binary, NpmProvider, EnvProvider, BinProviderOverrides
NpmProvider.model_rebuild()
EnvProvider.model_rebuild()
readability_binary = Binary(
name='readability-extractor',
binproviders=[NpmProvider(), EnvProvider()],
overrides={'npm': {'packages': ['github:ArchiveBox/readability-extractor']}}
)
readability_loaded = readability_binary.load()
assert readability_loaded and readability_loaded.abspath, "readability-extractor should be available after install hook"
if readability_loaded and readability_loaded.abspath:
assert True, "readability-extractor is available"
else:
pytest.skip("readability-extractor not available - Dependency record should have been emitted")
def test_extracts_article_after_installation():