mirror of
https://github.com/pgsty/minio.git
synced 2026-09-22 02:38:29 +03:00
Merge remote-tracking branch 'origin/main' into codex/docs-migration-cleanup
Signed-off-by: Feng Ruohang <rh@vonng.com> # Conflicts: # CONTRIBUTORS.md
This commit is contained in:
Feng Ruohang
@@ -133,6 +133,7 @@
|
||||
"MINIO_API_DISABLE_ODIRECT",
|
||||
"MINIO_API_GZIP_OBJECTS",
|
||||
"MINIO_API_LIST_QUORUM",
|
||||
"MINIO_API_MULTIPART_LISTING",
|
||||
"MINIO_API_OBJECT_MAX_VERSIONS",
|
||||
"MINIO_API_ODIRECT",
|
||||
"MINIO_API_REMOTE_TRANSPORT_DEADLINE",
|
||||
@@ -764,6 +765,7 @@
|
||||
"/metrics/v3",
|
||||
"/minio/grid/",
|
||||
"/minio/grid/lock/",
|
||||
"/multipart-preflight",
|
||||
"/netperf",
|
||||
"/notification",
|
||||
"/oauth2/callback",
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
__pycache__/
|
||||
@@ -0,0 +1,163 @@
|
||||
# Copyright (c) 2026 Feng Ruohang
|
||||
#
|
||||
# This program is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# This program is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
"""Pure, self-contained SVG rendering for SILO's README cards."""
|
||||
from datetime import date, timedelta
|
||||
from html import escape
|
||||
import math
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
themes = {
|
||||
'light': dict(bg='#ffffff', wash='#f2f7fc', edge='#d9e3ee', ink='#16222e',
|
||||
muted='#62758a', blue='#1d588c', copper='#b4762e', grid='#e5edf5',
|
||||
line='#2b6ca3', ring='#dce5ef', field='#f7f9fc', label='#3d4e61'),
|
||||
'dark': dict(bg='#101923', wash='#152738', edge='#2b3c50', ink='#e8eef6',
|
||||
muted='#93a3b8', blue='#7fb8e8', copper='#e0a35c', grid='#263749',
|
||||
line='#5da2dd', ring='#3a4e63', field='#0b1119', label='#b6c2d2'),
|
||||
}
|
||||
|
||||
def read_emblem(path):
|
||||
emblem = ET.parse(path).getroot()
|
||||
body = ''.join(ET.tostring(child, encoding='unicode') for child in emblem
|
||||
if child.tag.rsplit('}', 1)[-1] in ('defs', 'g'))
|
||||
return '\n'.join(line.rstrip() for line in body.splitlines()).strip()
|
||||
|
||||
|
||||
def txt(x, y, value, size=14, color=None, weight=400, anchor='start', mono=False, spacing=None):
|
||||
family = 'Menlo,Consolas,monospace' if mono else 'Arial,Helvetica,sans-serif'
|
||||
extra = f' letter-spacing="{spacing}"' if spacing is not None else ''
|
||||
return (f'<text x="{x}" y="{y}" font-family="{family}" font-size="{size}" '
|
||||
f'font-weight="{weight}" fill="{color}" text-anchor="{anchor}"{extra}>'
|
||||
f'{escape(str(value))}</text>')
|
||||
|
||||
|
||||
def start(height, theme, title, description, emblem_body):
|
||||
t = themes[theme]
|
||||
return [f'<svg xmlns="http://www.w3.org/2000/svg" width="1000" height="{height}" '
|
||||
f'viewBox="0 0 1000 {height}" role="img" aria-labelledby="title desc">',
|
||||
f'<title id="title">{escape(title)}</title><desc id="desc">{escape(description)}</desc>',
|
||||
'<defs><linearGradient id="surface" x1="0" y1="1" x2="1" y2="0">'
|
||||
f'<stop offset="0" stop-color="{t["bg"]}"/>'
|
||||
f'<stop offset="1" stop-color="{t["wash"]}"/></linearGradient>'
|
||||
'<linearGradient id="accent" x1="0" y1="0" x2="1" y2="0">'
|
||||
f'<stop offset="0" stop-color="{t["blue"]}"/>'
|
||||
f'<stop offset="1" stop-color="{t["copper"]}"/></linearGradient>'
|
||||
'<linearGradient id="area" x1="0" y1="0" x2="0" y2="1">'
|
||||
f'<stop offset="0" stop-color="{t["line"]}" stop-opacity=".22"/>'
|
||||
f'<stop offset="1" stop-color="{t["line"]}" stop-opacity=".015"/>'
|
||||
'</linearGradient></defs>',
|
||||
f'<rect x=".75" y=".75" width="998.5" height="{height-1.5}" rx="22" '
|
||||
f'fill="url(#surface)" stroke="{t["edge"]}" stroke-width="1.5"/>',
|
||||
f'<svg x="40" y="25" width="25" height="25" viewBox="230 213 570 570">{emblem_body}</svg>']
|
||||
|
||||
|
||||
def heading(parts, t, eyebrow, title, subtitle, value, value_label):
|
||||
parts.extend([
|
||||
txt(76, 43, eyebrow, 11, t['muted'], 600, mono=True, spacing=1.7),
|
||||
txt(40, 94, title, 32, t['ink'], 700),
|
||||
txt(41, 123, subtitle, 14, t['muted']),
|
||||
txt(958, 89, f'{value:,}', 45, t['ink'], 700, anchor='end'),
|
||||
txt(957, 114, value_label, 10, t['muted'], 600, anchor='end', mono=True, spacing=1.5),
|
||||
f'<path d="M40 146 H960" stroke="{t["edge"]}"/>',
|
||||
])
|
||||
|
||||
|
||||
def contributors(theme, people, snapshot, emblem_body):
|
||||
height = 206 + 76 * math.ceil(len(people) / 10)
|
||||
t = themes[theme]
|
||||
parts = start(height, theme, f'SILO community — {len(people)} contributors',
|
||||
f'The existing SILO community roll, including code, proposals and reports across related projects. '
|
||||
f'Gold rings retain the existing significant-contribution designation. Snapshot {snapshot}.', emblem_body)
|
||||
heading(parts, t, 'SILO / COMMUNITY', 'Contributors',
|
||||
'Code, proposals & reports across SILO and related projects', len(people), 'COMMUNITY CONTRIBUTORS')
|
||||
for row in range(math.ceil(len(people) / 10)):
|
||||
group = people[row * 10:(row + 1) * 10]
|
||||
row_width = len(group) * 91
|
||||
for col, person in enumerate(group):
|
||||
x = (1000 - row_width) / 2 + col * 91 + 45.5
|
||||
y = 199 + row * 76
|
||||
identifier = f'avatar-{row}-{col}'
|
||||
featured = bool(person.get('featured'))
|
||||
parts.append(f'<g><title>@{escape(person["handle"])} — {escape(person["what"])}</title>')
|
||||
parts.append(f'<defs><clipPath id="{identifier}"><circle cx="{x}" cy="{y}" r="29"/></clipPath></defs>')
|
||||
if featured:
|
||||
parts.append(f'<circle cx="{x}" cy="{y}" r="34" fill="{t["copper"]}" opacity=".09"/>')
|
||||
if person.get('avatarDataUrl'):
|
||||
parts.append(f'<image x="{x-29}" y="{y-29}" width="58" height="58" '
|
||||
f'clip-path="url(#{identifier})" href="{escape(person["avatarDataUrl"])}"/>')
|
||||
else:
|
||||
parts.append(f'<circle cx="{x}" cy="{y}" r="29" fill="{t["ring"]}"/>')
|
||||
parts.append(txt(x, y + 9, person['handle'][0].upper(), 26, t['ink'], 700, 'middle'))
|
||||
parts.append(f'<circle cx="{x}" cy="{y}" r="30.5" fill="none" '
|
||||
f'stroke="{t["copper"] if featured else t["ring"]}" stroke-width="{2 if featured else 1.25}"/></g>')
|
||||
parts.extend([
|
||||
f'<path d="M40 {height-42} H960" stroke="{t["edge"]}"/>',
|
||||
f'<circle cx="47" cy="{height-21}" r="4" fill="none" stroke="{t["copper"]}" stroke-width="1.5"/>',
|
||||
txt(61, height-17, 'Gold rings mark significant contributions', 12, t['muted']),
|
||||
txt(959, height-17, f'AS OF {snapshot}', 10, t['muted'], 500, 'end', mono=True, spacing=.6),
|
||||
'</svg>',
|
||||
])
|
||||
return ''.join(parts)
|
||||
|
||||
|
||||
def stars(theme, history, snapshot, emblem_body):
|
||||
points = history['points']
|
||||
star_count = points[-1]['stars']
|
||||
t = themes[theme]
|
||||
provenance = ('Initial history reconstructed · Daily totals since ' + history['bootstrap']['through'] + ' · UTC'
|
||||
if history['bootstrap']['reconstructed'] else 'Observed daily star totals · UTC')
|
||||
parts = start(558, theme, f'SILO star history — {star_count:,} stars',
|
||||
f'GitHub repository pgsty/silo. {star_count:,} stars as of {snapshot}. ' +
|
||||
provenance, emblem_body)
|
||||
heading(parts, t, 'SILO / GITHUB', 'Star History', 'pgsty/silo', star_count, 'GITHUB STARS')
|
||||
left, right, top, bottom = 76, 958, 177, 440
|
||||
begin = date.fromisoformat(points[0]['date'])
|
||||
end = date.fromisoformat(points[-1]['date'])
|
||||
days = max(1, (end - begin).days)
|
||||
maximum = max(500, math.ceil(max(p['stars'] for p in points) / 500) * 500)
|
||||
tick_step = 10 ** max(0, int(math.log10(maximum)))
|
||||
xy = lambda day, n: (left + (right-left)*(date.fromisoformat(day)-begin).days / days,
|
||||
bottom-(bottom-top)*n/maximum)
|
||||
for value in range(0, maximum+1, tick_step):
|
||||
y = xy(points[0]['date'], value)[1]
|
||||
parts.append(f'<path d="M{left} {y:.2f} H{right}" stroke="{t["grid"]}" stroke-dasharray="4 6"/>')
|
||||
parts.append(txt(left-16, round(y+4, 2), f'{value / 1000:g}k' if value >= 1000 else str(value), 12, t['muted'], anchor='end'))
|
||||
dates = sorted({begin + timedelta(days=round((end-begin).days*i/5)) for i in range(6)})
|
||||
ticks = [(d.isoformat(), d.strftime('%b %Y') if days > 90 else d.strftime('%b %d')) for d in dates]
|
||||
for day, label in ticks:
|
||||
x = xy(day, 0)[0]
|
||||
parts.append(f'<path d="M{x:.2f} {top} V{bottom}" stroke="{t["grid"]}" stroke-opacity=".65"/>')
|
||||
anchor = 'start' if day == points[0]['date'] else 'end' if day == snapshot else 'middle'
|
||||
parts.append(txt(round(x, 2), 466, label, 12, t['muted'], anchor=anchor))
|
||||
coords = [xy(p['date'], p['stars']) for p in points]
|
||||
line = 'M' + ' L'.join(f'{x:.2f} {y:.2f}' for x, y in coords)
|
||||
area = line + f' L{coords[-1][0]:.2f} {bottom} L{left} {bottom} Z'
|
||||
parts.extend([
|
||||
f'<path d="{area}" fill="url(#area)"/>',
|
||||
f'<path d="{line}" fill="none" stroke="url(#accent)" stroke-width="3" '
|
||||
'stroke-linecap="round" stroke-linejoin="round"/>',
|
||||
f'<path d="M{left} {bottom} H{right}" stroke="{t["edge"]}"/>',
|
||||
])
|
||||
x, y = coords[-1]
|
||||
parts.extend([
|
||||
f'<circle cx="{x}" cy="{y}" r="10" fill="{t["copper"]}" opacity=".12"/>',
|
||||
f'<circle cx="{x}" cy="{y}" r="5" fill="{t["copper"]}" stroke="{t["bg"]}" stroke-width="2"/>',
|
||||
f'<path d="M40 491 H960" stroke="{t["edge"]}"/>',
|
||||
txt(40, 516, f'{begin:%b %Y} — {end:%b %Y}'.upper(), 10, t['muted'], 500, mono=True, spacing=.7),
|
||||
txt(959, 516, f'SNAPSHOT {snapshot}', 10, t['muted'], 500, 'end', mono=True, spacing=.6),
|
||||
txt(40, 539, provenance, 11, t['muted']),
|
||||
'</svg>',
|
||||
])
|
||||
return ''.join(parts)
|
||||
@@ -0,0 +1 @@
|
||||
PyYAML==6.0.3
|
||||
@@ -0,0 +1,178 @@
|
||||
# Copyright (c) 2026 Feng Ruohang
|
||||
#
|
||||
# This program is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# This program is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
"""Regression checks for historical accuracy, contributor scope and SVG safety."""
|
||||
|
||||
import base64
|
||||
import json
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
from unittest.mock import patch
|
||||
from urllib.error import URLError
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
import render
|
||||
import update
|
||||
|
||||
NS = {'s': 'http://www.w3.org/2000/svg'}
|
||||
PNG = base64.b64decode('iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8/x8AAwMCAO+a7mgAAAAASUVORK5CYII=')
|
||||
|
||||
|
||||
def person(handle='Alice', group='reports', featured=False):
|
||||
return {'handle': handle, 'group': group, 'featured': featured,
|
||||
'what': 'A reviewed contribution', 'firstContribution': '2026-09-01'}
|
||||
|
||||
|
||||
def history():
|
||||
return {'repository': 'pgsty/silo',
|
||||
'bootstrap': {'through': '2026-09-15', 'reconstructed': True},
|
||||
'points': [{'date': '2026-09-14', 'stars': 100}, {'date': '2026-09-15', 'stars': 105}]}
|
||||
|
||||
|
||||
class HistoryTests(unittest.TestCase):
|
||||
def test_new_day_preserves_old_counts_and_unstars(self):
|
||||
before = history()
|
||||
after = update.update_history(before, '2026-09-16', 103)
|
||||
self.assertEqual(after['points'][:-1], before['points'])
|
||||
self.assertEqual(after['points'][-1], {'date': '2026-09-16', 'stars': 103})
|
||||
self.assertEqual(before, history())
|
||||
|
||||
def test_same_day_rerun_replaces_instead_of_appending(self):
|
||||
first = update.update_history(history(), '2026-09-15', 107)
|
||||
self.assertEqual(len(first['points']), 2)
|
||||
self.assertEqual(first, update.update_history(first, '2026-09-15', 107))
|
||||
|
||||
def test_missing_days_are_not_invented(self):
|
||||
result = update.update_history(history(), '2026-09-18', 106)
|
||||
self.assertEqual([p['date'] for p in result['points']], ['2026-09-14', '2026-09-15', '2026-09-18'])
|
||||
|
||||
def test_rejects_wrong_repository_and_corrupt_history(self):
|
||||
cases = []
|
||||
wrong = history(); wrong['repository'] = 'someone/else'; cases.append(wrong)
|
||||
duplicate = history(); duplicate['points'].append(duplicate['points'][-1]); cases.append(duplicate)
|
||||
unordered = history(); unordered['points'].reverse(); cases.append(unordered)
|
||||
negative = history(); negative['points'][0]['stars'] = -1; cases.append(negative)
|
||||
future = history(); future['points'][-1]['date'] = '2026-09-20'; cases.append(future)
|
||||
for case in cases:
|
||||
with self.subTest(case=case), self.assertRaises(ValueError):
|
||||
update.update_history(case, '2026-09-16', 100)
|
||||
|
||||
def test_first_run_has_no_fabricated_history(self):
|
||||
result = update.update_history(None, '2026-09-16', 10)
|
||||
self.assertFalse(result['bootstrap']['reconstructed'])
|
||||
self.assertEqual(result['points'], [{'date': '2026-09-16', 'stars': 10}])
|
||||
|
||||
|
||||
class ContributorTests(unittest.TestCase):
|
||||
def test_retries_truncated_json_before_using_it(self):
|
||||
with patch('update.request', side_effect=[b'{"partial":', b'{"ok":true}']), patch('update.time.sleep'):
|
||||
self.assertEqual(update.GitHub('').get('repos/pgsty/silo'), {'ok': True})
|
||||
|
||||
def test_paginates_past_one_full_page(self):
|
||||
class API(update.GitHub):
|
||||
def __init__(self): self.calls = []
|
||||
def get(self, path):
|
||||
self.calls.append(path)
|
||||
return list(range(100)) if 'page=1&' in path else [100]
|
||||
api = API()
|
||||
self.assertEqual(len(list(api.issues('pgsty/silo'))), 101)
|
||||
self.assertIn('state=all', api.calls[0])
|
||||
self.assertIn('page=2&', api.calls[1])
|
||||
|
||||
def test_bots_deduplication_unmerged_work_and_reviewed_credit(self):
|
||||
def issue(login, kind='issue', user_type='User'):
|
||||
item = {'user': {'login': login, 'type': user_type, 'avatar_url': ''}, 'created_at': '2026-09-02T00:00:00Z'}
|
||||
if kind != 'issue': item['pull_request'] = {'merged_at': None if kind == 'open' else '2026-09-03T00:00:00Z'}
|
||||
return item
|
||||
class API:
|
||||
def issues(self, _repo):
|
||||
return [issue('alice'), issue('Bob', 'open'), issue('Bob', 'merged'),
|
||||
issue('Carol', 'open'), issue('Copilot'), issue('robot', user_type='Bot')]
|
||||
curated = {'repositories': ['pgsty/silo', 'pgsty/mc'], 'bots': ['Copilot'],
|
||||
'people': [person('Alice', featured=True), person('Reporter'), person('Copilot')]}
|
||||
result = update.collect_people(API(), curated)
|
||||
self.assertEqual({p['handle'] for p in result}, {'Alice', 'Bob', 'Carol', 'Reporter'})
|
||||
self.assertEqual(result[0]['handle'], 'Bob')
|
||||
self.assertEqual(result[1]['handle'], 'Carol')
|
||||
self.assertTrue(next(p for p in result if p['handle'] == 'Alice')['featured'])
|
||||
self.assertEqual(next(p for p in result if p['handle'] == 'Bob')['group'], 'code')
|
||||
self.assertFalse(next(p for p in result if p['handle'] == 'Carol')['featured'])
|
||||
|
||||
def test_newer_reviewed_preview_survives_until_site_catches_up(self):
|
||||
remote = {'updated': '2026-09-16T03:00:00+00:00'}
|
||||
cached = {'updated': '2026-09-16T04:00:00+00:00'}
|
||||
self.assertIs(update.select_curated(remote, cached), cached)
|
||||
newer = {'updated': '2026-09-17T03:00:00+00:00'}
|
||||
self.assertIs(update.select_curated(newer, cached), newer)
|
||||
|
||||
def test_avatar_failure_reuses_raster_cache(self):
|
||||
previous = {**person(), 'avatarDataUrl': update.raster_data_url(PNG)}
|
||||
with patch('update.request', side_effect=URLError('unavailable')):
|
||||
result = update.add_avatars(None, [{**person(), 'avatarUrl': 'https://avatars.githubusercontent.com/u/1'}], [previous])
|
||||
self.assertEqual(result[0]['avatarDataUrl'], previous['avatarDataUrl'])
|
||||
with self.assertRaises(ValueError): update.raster_data_url(b'<svg onload="bad()"/>')
|
||||
with self.assertRaises(ValueError): update.cached_avatar({'avatarDataUrl': 'data:image/svg+xml;base64,PHN2Zy8+'})
|
||||
|
||||
def test_fetch_failure_leaves_published_assets_untouched(self):
|
||||
class API:
|
||||
def get(self, path):
|
||||
if path == 'repos/pgsty/silo': return {'full_name': 'pgsty/silo', 'stargazers_count': 106}
|
||||
raise URLError('roster unavailable')
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
out = Path(directory)
|
||||
original = json.dumps(history())
|
||||
(out / 'history.json').write_text(original)
|
||||
(out / 'contributors-light.svg').write_text('previous image')
|
||||
with self.assertRaises(URLError): update.refresh(out, API(), Path('.'))
|
||||
self.assertEqual((out / 'history.json').read_text(), original)
|
||||
self.assertEqual((out / 'contributors-light.svg').read_text(), 'previous image')
|
||||
|
||||
|
||||
class RenderTests(unittest.TestCase):
|
||||
def test_real_emblem_generates_clean_xml(self):
|
||||
emblem = render.read_emblem(Path(__file__).resolve().parents[2] / '.github/silo.svg')
|
||||
svg = render.contributors('light', [person()], '2026-09-16', emblem)
|
||||
ET.fromstring(svg)
|
||||
self.assertTrue(all(line == line.rstrip() for line in svg.splitlines()))
|
||||
|
||||
def test_all_avatars_fit_when_the_roster_grows(self):
|
||||
people = [{**person(f'person-{i}'), 'avatarDataUrl': update.raster_data_url(PNG)} for i in range(151)]
|
||||
for theme in ('light', 'dark'):
|
||||
root = ET.fromstring(render.contributors(theme, people, '2026-09-16', ''))
|
||||
images = root.findall('.//s:image', NS)
|
||||
self.assertEqual(len(images), 151)
|
||||
footer = float(root.attrib['height']) - 42
|
||||
self.assertTrue(all(float(i.attrib['y']) + float(i.attrib['height']) < footer for i in images))
|
||||
self.assertTrue(all(i.attrib['href'].startswith('data:image/png;base64,') for i in images))
|
||||
|
||||
def test_untrusted_text_is_escaped(self):
|
||||
data = [{**person(), 'what': '<script>alert("x")</script> & contributions'}]
|
||||
svg = render.contributors('light', data, '2026-09-16', '')
|
||||
root = ET.fromstring(svg)
|
||||
self.assertEqual(root.findall('.//s:script', NS), [])
|
||||
self.assertIn('<script>', svg)
|
||||
|
||||
def test_single_point_and_decreasing_star_history_render(self):
|
||||
for data in (update.update_history(None, '2026-09-16', 0), update.update_history(history(), '2026-09-16', 90)):
|
||||
for theme in ('light', 'dark'):
|
||||
svg = render.stars(theme, data, '2026-09-16', '')
|
||||
ET.fromstring(svg)
|
||||
self.assertNotIn('nan', svg.lower())
|
||||
self.assertNotIn('inf', svg.lower())
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
@@ -0,0 +1,295 @@
|
||||
#!/usr/bin/env python3
|
||||
# Copyright (c) 2026 Feng Ruohang
|
||||
#
|
||||
# This program is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# This program is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
"""Refresh the generated-asset checkout; publishing is handled by the workflow."""
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from datetime import date, datetime, timezone
|
||||
import json
|
||||
from http.client import IncompleteRead
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
from urllib.error import HTTPError, URLError
|
||||
from urllib.parse import urlparse
|
||||
from urllib.request import Request, urlopen
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
import yaml
|
||||
|
||||
import render
|
||||
|
||||
REPOSITORY = 'pgsty/silo'
|
||||
SOURCE = 'repos/pgsty/silo.pgsty.com/contents/data/home/contributors.yaml?ref=main'
|
||||
GROUPS = ('code', 'proposed', 'reports')
|
||||
HANDLE = re.compile(r'[A-Za-z0-9][A-Za-z0-9-]{0,38}\Z')
|
||||
|
||||
|
||||
def request(url, token='', limit=8 * 1024 * 1024):
|
||||
headers = {'User-Agent': 'silo-repository-cards', 'Accept': 'application/vnd.github+json'}
|
||||
if urlparse(url).netloc == 'api.github.com':
|
||||
headers['X-GitHub-Api-Version'] = '2022-11-28'
|
||||
if token:
|
||||
headers['Authorization'] = f'Bearer {token}'
|
||||
for attempt in range(3):
|
||||
try:
|
||||
with urlopen(Request(url, headers=headers), timeout=25) as response:
|
||||
data = response.read(limit + 1)
|
||||
if len(data) > limit:
|
||||
raise ValueError('Response exceeds the size limit')
|
||||
expected = response.headers.get('Content-Length')
|
||||
if expected is not None and len(data) != int(expected):
|
||||
raise URLError('Incomplete response body')
|
||||
return data
|
||||
except HTTPError as exc:
|
||||
if exc.code < 500 or attempt == 2:
|
||||
raise
|
||||
except (URLError, TimeoutError, IncompleteRead):
|
||||
if attempt == 2:
|
||||
raise
|
||||
time.sleep(attempt + 1)
|
||||
|
||||
|
||||
class GitHub:
|
||||
def __init__(self, token):
|
||||
self.token = token
|
||||
|
||||
def get(self, path):
|
||||
for attempt in range(3):
|
||||
try:
|
||||
return json.loads(request('https://api.github.com/' + path, self.token))
|
||||
except (json.JSONDecodeError, UnicodeDecodeError) as exc:
|
||||
if attempt == 2:
|
||||
raise ValueError(f'Incomplete or invalid GitHub JSON: {path}') from exc
|
||||
time.sleep(attempt + 1)
|
||||
|
||||
def issues(self, repository):
|
||||
page = 1
|
||||
while True:
|
||||
batch = self.get(f'repos/{repository}/issues?state=all&per_page=100&page={page}&sort=created&direction=asc')
|
||||
if not isinstance(batch, list):
|
||||
raise ValueError(f'Invalid issues response for {repository}')
|
||||
yield from batch
|
||||
if len(batch) < 100:
|
||||
return
|
||||
page += 1
|
||||
|
||||
|
||||
def curated_snapshot(data, revision):
|
||||
updated = str(data['updated'])
|
||||
datetime.fromisoformat(updated)
|
||||
repositories = [item['repo'] for item in data['repositories']]
|
||||
if not repositories or any(not re.fullmatch(r'pgsty/[A-Za-z0-9_.-]+', repo) for repo in repositories):
|
||||
raise ValueError('Invalid contributor repository scope')
|
||||
people = []
|
||||
for group in GROUPS:
|
||||
for entry in data[group]:
|
||||
if not HANDLE.fullmatch(entry['handle']):
|
||||
raise ValueError('Invalid GitHub contributor handle')
|
||||
people.append({
|
||||
'handle': entry['handle'], 'group': group,
|
||||
'featured': bool(entry.get('featured')), 'what': entry['what'],
|
||||
'firstContribution': str(entry.get('firstContribution', '9999-12-31')),
|
||||
})
|
||||
if not people or len({p['handle'].lower() for p in people}) != len(people):
|
||||
raise ValueError('Empty or duplicate contributor roster')
|
||||
return {'updated': updated, 'revision': revision, 'repositories': repositories,
|
||||
'bots': data.get('bots', ['Copilot', 'dependabot[bot]']), 'people': people}
|
||||
|
||||
|
||||
def select_curated(remote, cached):
|
||||
# The initial, approved preview can contain reviewed credit not published by
|
||||
# the companion site yet. Keep that newer snapshot until the site catches up.
|
||||
if cached and datetime.fromisoformat(cached['updated']) > datetime.fromisoformat(remote['updated']):
|
||||
return cached
|
||||
return remote
|
||||
|
||||
|
||||
def collect_people(api, curated):
|
||||
bots = {name.lower() for name in curated['bots']}
|
||||
people = {p['handle'].lower(): dict(p) for p in curated['people']
|
||||
if p['handle'].lower() not in bots and not p['handle'].lower().endswith('[bot]')}
|
||||
order = {p['handle'].lower(): index for index, p in enumerate(curated['people'])}
|
||||
for repository in curated['repositories']:
|
||||
print(f'Reading issue and PR authors: {repository}', flush=True)
|
||||
for issue in api.issues(repository):
|
||||
user = issue.get('user') or {}
|
||||
handle = user.get('login', '')
|
||||
key = handle.lower()
|
||||
if user.get('type') != 'User' or key in bots or key.endswith('[bot]'):
|
||||
continue
|
||||
if not HANDLE.fullmatch(handle):
|
||||
raise ValueError('Invalid issue author')
|
||||
pr = issue.get('pull_request')
|
||||
group = 'code' if pr and pr.get('merged_at') else 'proposed' if pr else 'reports'
|
||||
first = issue['created_at'][:10]
|
||||
date.fromisoformat(first)
|
||||
person = people.setdefault(key, {
|
||||
'handle': handle, 'group': group, 'featured': False,
|
||||
'what': 'Contributed an issue or pull request to SILO and related projects',
|
||||
'firstContribution': first,
|
||||
})
|
||||
person['avatarUrl'] = user.get('avatar_url', '')
|
||||
person['firstContribution'] = min(person['firstContribution'], first)
|
||||
if GROUPS.index(group) < GROUPS.index(person['group']):
|
||||
person['group'] = group
|
||||
if not people:
|
||||
raise ValueError('No human contributors were collected')
|
||||
return sorted(people.values(), key=lambda p: (
|
||||
GROUPS.index(p['group']), not p['featured'],
|
||||
order.get(p['handle'].lower(), len(order)), p['firstContribution'], p['handle'].lower()))
|
||||
|
||||
|
||||
def raster_data_url(data):
|
||||
if data.startswith(b'\x89PNG\r\n\x1a\n'):
|
||||
mime = 'image/png'
|
||||
elif data.startswith(b'\xff\xd8\xff'):
|
||||
mime = 'image/jpeg'
|
||||
elif data.startswith((b'GIF87a', b'GIF89a')):
|
||||
mime = 'image/gif'
|
||||
elif data[:4] == b'RIFF' and data[8:12] == b'WEBP':
|
||||
mime = 'image/webp'
|
||||
else:
|
||||
raise ValueError('Avatar is not a raster image')
|
||||
return f'data:{mime};base64,' + base64.b64encode(data).decode('ascii')
|
||||
|
||||
|
||||
def cached_avatar(person):
|
||||
value = person.get('avatarDataUrl', '')
|
||||
if not value:
|
||||
return ''
|
||||
prefix, encoded = value.split(',', 1)
|
||||
if prefix not in ('data:image/png;base64', 'data:image/jpeg;base64', 'data:image/gif;base64', 'data:image/webp;base64'):
|
||||
raise ValueError('Invalid cached avatar format')
|
||||
raw = base64.b64decode(encoded, validate=True)
|
||||
if len(raw) > 512 * 1024 or raster_data_url(raw) != value:
|
||||
raise ValueError('Invalid cached avatar')
|
||||
return value
|
||||
|
||||
|
||||
def add_avatars(api, people, previous):
|
||||
cached = {p['handle'].lower(): cached_avatar(p) for p in previous}
|
||||
|
||||
def update(person):
|
||||
person = dict(person)
|
||||
try:
|
||||
url = person.pop('avatarUrl', '') or api.get('users/' + person['handle'])['avatar_url']
|
||||
parsed = urlparse(url)
|
||||
if parsed.scheme != 'https' or parsed.netloc != 'avatars.githubusercontent.com':
|
||||
raise ValueError('Unexpected avatar host')
|
||||
data = request(url + ('&' if '?' in url else '?') + 's=96', limit=512 * 1024)
|
||||
person['avatarDataUrl'] = raster_data_url(data)
|
||||
except (HTTPError, URLError, TimeoutError, IncompleteRead, ValueError, KeyError) as exc:
|
||||
person.pop('avatarUrl', None)
|
||||
person['avatarDataUrl'] = cached.get(person['handle'].lower(), '')
|
||||
print(f'Avatar fallback for @{person["handle"]}: {type(exc).__name__}', file=sys.stderr)
|
||||
return person
|
||||
|
||||
with ThreadPoolExecutor(max_workers=6) as pool:
|
||||
return list(pool.map(update, people))
|
||||
|
||||
|
||||
def update_history(history, day, stars):
|
||||
date.fromisoformat(day)
|
||||
if type(stars) is not int or stars < 0:
|
||||
raise ValueError('Invalid repository star count')
|
||||
if history is None:
|
||||
history = {'repository': REPOSITORY, 'bootstrap': {'through': day, 'reconstructed': False}, 'points': []}
|
||||
if history['repository'] != REPOSITORY:
|
||||
raise ValueError('Star history belongs to a different repository')
|
||||
date.fromisoformat(history['bootstrap']['through'])
|
||||
dates = []
|
||||
for point in history['points']:
|
||||
date.fromisoformat(point['date'])
|
||||
if type(point['stars']) is not int or point['stars'] < 0:
|
||||
raise ValueError('Invalid historical star count')
|
||||
dates.append(point['date'])
|
||||
if dates != sorted(set(dates)) or any(d > day for d in dates):
|
||||
raise ValueError('History contains duplicate, unordered, or future dates')
|
||||
# Replace today's observation, preserve previous days, and allow unstars.
|
||||
points = [dict(p) for p in history['points'] if p['date'] != day]
|
||||
points.append({'date': day, 'stars': stars})
|
||||
return {**history, 'points': points}
|
||||
|
||||
|
||||
def read_json(path, default=None):
|
||||
return json.loads(path.read_text()) if path.exists() else default
|
||||
|
||||
|
||||
def refresh(output, api, source_root):
|
||||
day = datetime.now(timezone.utc).date().isoformat()
|
||||
metadata = api.get('repos/' + REPOSITORY)
|
||||
if metadata['full_name'].lower() != REPOSITORY:
|
||||
raise ValueError('Unexpected repository metadata')
|
||||
history = update_history(read_json(output / 'history.json'), day, metadata['stargazers_count'])
|
||||
source = api.get(SOURCE)
|
||||
reviewed = yaml.safe_load(base64.b64decode(source['content'], validate=False))
|
||||
curated = select_curated(curated_snapshot(reviewed, source['sha']), read_json(output / 'curated.json'))
|
||||
people = collect_people(api, curated)
|
||||
previous = read_json(output / 'contributors.json', {}).get('people', [])
|
||||
people = add_avatars(api, people, previous)
|
||||
emblem = render.read_emblem(source_root / '.github/silo.svg')
|
||||
payloads = {}
|
||||
for theme in ('light', 'dark'):
|
||||
payloads[f'contributors-{theme}.svg'] = render.contributors(theme, people, day, emblem) + '\n'
|
||||
payloads[f'star-history-{theme}.svg'] = render.stars(theme, history, day, emblem) + '\n'
|
||||
for svg in payloads.values():
|
||||
ET.fromstring(svg)
|
||||
for name, data in {
|
||||
'history.json': history,
|
||||
'curated.json': curated,
|
||||
'contributors.json': {'repository': REPOSITORY, 'updated': day, 'people': people},
|
||||
}.items():
|
||||
payloads[name] = json.dumps(data, indent=2, ensure_ascii=False) + '\n'
|
||||
payloads['README.md'] = f'''# SILO repository cards
|
||||
|
||||
Generated by [Repository Cards](https://github.com/pgsty/silo/actions/workflows/repository-cards.yml)
|
||||
at 00:00 UTC daily (08:00 Asia/Shanghai). GitHub may queue scheduled runs.
|
||||
|
||||
Snapshot: {day}. {metadata['stargazers_count']:,} stars; {len(people)} community contributors.
|
||||
|
||||
- `contributors-light.svg` / `contributors-dark.svg`: human issue and PR authors across the SILO project scope, plus reviewed acknowledgements. Bots are excluded. Gold rings follow the reviewed companion-site roster; new authors are collected automatically.
|
||||
- `star-history-light.svg` / `star-history-dark.svg`: initial history reconstructed from the then-current stargazers; later points are daily observed totals, including decreases. Missing days are not fabricated.
|
||||
- `curated.json`: a cache of reviewed contributor credit from `pgsty/silo.pgsty.com/data/home/contributors.yaml`. The approved initial preview may be newer than the published site; a newer reviewed snapshot is retained until the site catches up.
|
||||
- `contributors.json`: generated contributor data and embedded raster avatars. Failed avatar refreshes use the previous image, or an initial when no image is available.
|
||||
- `history.json`: persistent daily totals. Keep this file when regenerating images.
|
||||
|
||||
The SVGs are self-contained. Source and instructions live on the default branch;
|
||||
this branch contains generated assets only. Do not merge it into `main`.
|
||||
'''
|
||||
# Collect and validate everything before touching the publication checkout.
|
||||
output.mkdir(parents=True, exist_ok=True)
|
||||
for filename, text in payloads.items():
|
||||
(output / filename).write_text(text)
|
||||
print(f'{day}: {len(people)} contributors; {metadata["stargazers_count"]:,} stars; {len(history["points"])} history points')
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument('--output', type=Path, required=True)
|
||||
args = parser.parse_args()
|
||||
configured = os.environ.get('GITHUB_REPOSITORY', REPOSITORY)
|
||||
if configured.lower() != REPOSITORY:
|
||||
raise SystemExit('This workflow is scoped to pgsty/silo')
|
||||
refresh(args.output, GitHub(os.environ.get('GH_TOKEN', '')), Path(__file__).resolve().parents[2])
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user