File size: 24,370 Bytes
7977885 ed07d1b 7977885 0ba324f ed07d1b f92661d 0ba324f f92661d cca436c 60a2fc8 0ba324f f92661d 389b9a4 f7f39ba c325020 f7f39ba c325020 f7f39ba c325020 f7f39ba c325020 f7f39ba ed07d1b 60a2fc8 149cadc ed07d1b cca436c c325020 cca436c 9d58132 0ba324f cca436c 29331c9 c325020 29331c9 06e91ec 0ba324f f92661d 389b9a4 d735235 389b9a4 ed07d1b f92661d 0ba324f cca436c c325020 06e91ec c325020 ed07d1b 60a2fc8 149cadc 06e91ec f7f39ba 60a2fc8 cca436c 0ba324f 7977885 0ba324f 7977885 40360ea 7977885 0ba324f 7977885 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 | #!/usr/bin/env python3
"""Validate static website links, anchors, image assets, and JSON data.
This is a local integrity check for the GitHub Pages / Hugging Face static
website. It intentionally does not fetch external URLs; it verifies that the
published local surface is self-consistent.
"""
from __future__ import annotations
import argparse
import json
import re
from dataclasses import dataclass
from datetime import datetime, timezone
from html.parser import HTMLParser
from pathlib import Path
from urllib.parse import unquote, urlsplit
from PIL import Image
ROOT = Path(__file__).resolve().parents[1]
DEFAULT_DOCS = ROOT / "docs"
DEFAULT_OUTPUT = DEFAULT_DOCS / "data/website_integrity.json"
DEFAULT_SITE_BASE = "/ropedia-xperience-10m-task-suite/"
LOCAL_ATTRS = {"href", "src"}
SKIP_SCHEMES = {"http", "https", "mailto", "tel", "data", "javascript"}
IMAGE_SUFFIXES = {".jpg", ".jpeg", ".png", ".webp"}
@dataclass
class Reference:
source: Path
tag: str
attr: str
raw: str
path_part: str
fragment: str
class SiteParser(HTMLParser):
def __init__(self, source: Path):
super().__init__(convert_charrefs=True)
self.source = source
self.ids: list[str] = []
self.references: list[Reference] = []
self.images: list[str] = []
def handle_starttag(self, tag: str, attrs):
attr_map = dict(attrs)
element_id = attr_map.get("id") or attr_map.get("name")
if element_id:
self.ids.append(element_id)
for attr in LOCAL_ATTRS:
raw = attr_map.get(attr)
if not raw:
continue
parsed = urlsplit(raw)
if parsed.scheme in SKIP_SCHEMES or parsed.netloc:
continue
path_part = unquote(parsed.path)
fragment = unquote(parsed.fragment)
if not path_part and not fragment:
continue
self.references.append(Reference(self.source, tag, attr, raw, path_part, fragment))
if tag == "img" and attr == "src":
self.images.append(path_part)
def parse_html(path: Path) -> SiteParser:
parser = SiteParser(path)
parser.feed(path.read_text(encoding="utf-8", errors="ignore"))
return parser
def normalize_path_part(path_part: str, site_base: str) -> str:
if path_part in {"", "/"}:
return path_part
normalized_base = "/" + site_base.strip("/") + "/"
if path_part == normalized_base:
return "/index.html"
if path_part.startswith(normalized_base):
return "/" + path_part[len(normalized_base):]
return path_part
def resolve_reference(docs_root: Path, source: Path, path_part: str, site_base: str) -> Path:
path_part = normalize_path_part(path_part, site_base)
if not path_part:
return source
base = docs_root if path_part.startswith("/") else source.parent
resolved = (base / path_part.lstrip("/")).resolve()
if resolved.is_dir():
return resolved / "index.html"
return resolved
def relative(path: Path, root: Path) -> str:
try:
return path.relative_to(root).as_posix()
except ValueError:
return path.as_posix()
def duplicate_ids(ids: list[str]) -> list[dict]:
counts: dict[str, int] = {}
for item in ids:
counts[item] = counts.get(item, 0) + 1
return [{"id": item, "count": count} for item, count in sorted(counts.items()) if count > 1]
def image_record(path: Path, docs_root: Path) -> dict:
suffix = path.suffix.lower()
record = {
"path": relative(path, docs_root),
"exists": path.exists(),
"bytes": path.stat().st_size if path.exists() else 0,
}
if not path.exists():
return record
if suffix in IMAGE_SUFFIXES:
with Image.open(path) as image:
record.update({
"width": int(image.width),
"height": int(image.height),
"format": image.format,
})
elif suffix == ".svg":
text = path.read_text(encoding="utf-8", errors="ignore")
viewbox = re.search(r'viewBox=["\']([^"\']+)["\']', text)
record["format"] = "SVG"
record["has_viewbox"] = bool(viewbox)
return record
def validate(docs_root: Path, site_base: str) -> dict:
html_files = sorted(docs_root.glob("*.html"))
parsers = {path: parse_html(path) for path in html_files}
anchors_by_file = {path: set(parser.ids) for path, parser in parsers.items()}
missing_targets = []
missing_anchors = []
local_references = []
external_reference_count = 0
image_paths: set[Path] = set()
for path, parser in parsers.items():
text = path.read_text(encoding="utf-8", errors="ignore")
external_reference_count += len(re.findall(r'https?://', text))
for ref in parser.references:
target = resolve_reference(docs_root, path, ref.path_part, site_base)
target_rel = relative(target, docs_root)
source_rel = relative(ref.source, docs_root)
local_references.append({
"source": source_rel,
"tag": ref.tag,
"attr": ref.attr,
"raw": ref.raw,
"target": target_rel,
"fragment": ref.fragment,
})
if not target.exists():
missing_targets.append({
"source": source_rel,
"raw": ref.raw,
"target": target_rel,
})
continue
if ref.tag == "img" and ref.attr == "src":
image_paths.add(target)
if ref.fragment:
anchor_target = target if target.suffix.lower() == ".html" else path
if ref.path_part and target.suffix.lower() != ".html":
continue
anchors = anchors_by_file.get(anchor_target)
if anchors is None and anchor_target.exists() and anchor_target.suffix.lower() == ".html":
anchors = set(parse_html(anchor_target).ids)
anchors_by_file[anchor_target] = anchors
if anchors is not None and ref.fragment not in anchors:
missing_anchors.append({
"source": source_rel,
"raw": ref.raw,
"target": relative(anchor_target, docs_root),
"fragment": ref.fragment,
})
json_records = []
invalid_json = []
for path in sorted((docs_root / "data").glob("*.json")):
rel_path = relative(path, docs_root)
try:
payload = json.loads(path.read_text(encoding="utf-8"))
except json.JSONDecodeError as exc:
invalid_json.append({"path": rel_path, "error": str(exc)})
continue
json_records.append({
"path": rel_path,
"bytes": path.stat().st_size,
"top_level_type": type(payload).__name__,
})
images = []
invalid_images = []
for path in sorted(image_paths):
try:
record = image_record(path, docs_root)
images.append(record)
if not record.get("exists") or record.get("bytes", 0) <= 0:
invalid_images.append(record)
if path.suffix.lower() in IMAGE_SUFFIXES and (record.get("width", 0) <= 0 or record.get("height", 0) <= 0):
invalid_images.append(record)
if path.suffix.lower() == ".svg" and not record.get("has_viewbox"):
invalid_images.append(record)
except Exception as exc: # noqa: BLE001 - report image validation failures.
invalid_images.append({"path": relative(path, docs_root), "error": str(exc)})
duplicate_id_records = [
{"path": relative(path, docs_root), "duplicates": duplicate_ids(parser.ids)}
for path, parser in parsers.items()
]
duplicate_id_records = [item for item in duplicate_id_records if item["duplicates"]]
semantic_checks = []
semantic_layout_failures = []
index_path = docs_root / "index.html"
index_text = index_path.read_text(encoding="utf-8", errors="ignore") if index_path.exists() else ""
roadmap_payload = None
roadmap_json_error = None
roadmap_path = docs_root / "data/research_roadmap.json"
try:
roadmap_payload = json.loads(roadmap_path.read_text(encoding="utf-8"))
except Exception as exc: # noqa: BLE001 - report malformed/missing roadmap data.
roadmap_json_error = str(exc)
def section_pos(section_id: str) -> int:
match = re.search(rf'<section\b[^>]*\bid="{re.escape(section_id)}"', index_text)
return match.start() if match else -1
suite_start = section_pos("suite")
suite_end = section_pos("pipeline")
suite_text = index_text[suite_start:suite_end] if suite_start >= 0 and suite_end > suite_start else ""
overview_pos = section_pos("overview")
protocol_pos = section_pos("protocol")
evidence_pos = section_pos("evidence")
dataset_start = section_pos("dataset-card")
dataset_end = section_pos("suite")
dataset_text = index_text[dataset_start:dataset_end] if dataset_start >= 0 and dataset_end > dataset_start else ""
roadmap_page = docs_root / "research_roadmap.html"
roadmap_page_text = roadmap_page.read_text(encoding="utf-8", errors="ignore") if roadmap_page.exists() else ""
semantic_rules = [
(
"project_tabs_have_five_groups",
'data-tab-key=',
None,
"The long research page should be grouped into five top-level tabs.",
),
(
"project_sections_are_assigned_to_tabs",
'data-project-tab=',
None,
"Every major research section should be assigned to a tab group.",
),
(
"project_hash_router_preserves_deep_links",
'activateTabForHash',
None,
"Deep links should open the correct tab instead of landing on hidden content.",
),
(
"project_tabs_use_accessible_roles",
'role="tab"',
None,
"The tabbed research dashboard should expose tablist/tab semantics.",
),
(
"project_sections_are_labeled_tabpanels",
'role="tabpanel"',
None,
"Every tabbed research section should expose a labeled panel role.",
),
(
"project_tabs_update_selected_state",
'aria-selected',
None,
"Tab activation should update selected state for assistive technology.",
),
(
"project_tabs_support_keyboard_navigation",
'moveProjectTabFocus',
None,
"Keyboard users should be able to switch project tabs with arrow, Home, and End keys.",
),
(
"project_overview_precedes_progress_ledger",
'<section id="overview">',
'<section id="evidence">',
"The project overview should appear before the deeper progress ledger.",
),
(
"project_status_links_json",
'data/project_status.json',
None,
"The website should expose the machine-readable project status.",
),
(
"roadmap_links_json",
'data/research_roadmap.json',
None,
"The website should expose the machine-readable research roadmap.",
),
(
"interactive_roadmap_page_linked",
'research_roadmap.html',
None,
"The project site should link to the dedicated interactive research roadmap page.",
),
(
"interactive_roadmap_links_json",
'data/research_roadmap_interactive.json',
None,
"The project site should expose the machine-readable interactive roadmap contract.",
),
(
"interactive_roadmap_loads_generated_json",
'data/research_roadmap_interactive.json',
None,
"The interactive roadmap page should load the generated roadmap JSON contract.",
),
(
"interactive_roadmap_tracks_four_directions",
'Research tracks',
None,
"The interactive roadmap page should expose the four research-track control surface.",
),
(
"rendered_site_check_links_json",
'data/rendered_site_check.json',
None,
"The website should expose the browser-level rendered website check.",
),
(
"roadmap_html_matches_json_phases",
"",
None,
"The roadmap section should show every stage defined in research_roadmap.json.",
),
(
"roadmap_status_chips_match_json",
"",
None,
"The roadmap status chips should match the phase statuses in research_roadmap.json.",
),
(
"evaluation_protocol_between_overview_and_progress",
'<section id="protocol">',
'<section id="evidence">',
"The evaluation protocol should appear before the deeper evidence ledger.",
),
(
"evaluation_protocol_links_json",
'data/evaluation_protocol.json',
None,
"The website should expose the machine-readable evaluation protocol.",
),
(
"figure_index_links_json",
'data/figure_index.json',
None,
"The website should expose the machine-readable figure index.",
),
(
"suite_task_map_precedes_modality_atlas",
'<div class="figure-pan" id="task-suite-map">',
'<div class="modality-atlas-panel"',
"The Suite anchor should show the full 12-task map before the modality atlas.",
),
(
"suite_modality_atlas_contains_seven_cards",
'class="atlas-card',
None,
"The modality atlas should expose seven sample modalities.",
),
(
"dataset_card_section_mentions_sample_license",
'cc-by-nc-4.0',
None,
"The dataset-card section should preserve the public sample card license.",
),
(
"dataset_card_section_mentions_api_episode_listing",
'12,103 episode folders',
None,
"The dataset-card section should distinguish HF API listing metadata from local data possession.",
),
(
"dataset_card_section_links_source_alignment_audit",
'data/source_alignment_audit.json',
None,
"The dataset-card section should expose the generated source-alignment report.",
),
(
"task_player_surface_present",
'id="taskPlayer"',
None,
"The website should expose the interactive task walkthrough/player.",
),
(
"task_player_uses_walkthrough_json",
'data/task_walkthroughs.json',
None,
"The task player and task cards should read the generated walkthrough JSON.",
),
(
"task_cards_use_human_research_names",
'Action Recognition',
None,
"The public task surface should use readable research task names.",
),
]
for name, marker, after_marker, reason in semantic_rules:
if name == "project_tabs_have_five_groups":
tab_count = index_text.count(marker)
passed = tab_count == 5
detail = {"tab_count": tab_count}
elif name == "project_sections_are_assigned_to_tabs":
section_count = index_text.count(marker)
passed = section_count >= 19
detail = {"section_count": section_count}
elif name == "project_hash_router_preserves_deep_links":
marker_count = index_text.count(marker)
passed = marker_count >= 2 and "sectionTabMap" in index_text
detail = {"marker_count": marker_count, "has_section_tab_map": "sectionTabMap" in index_text}
elif name == "project_tabs_use_accessible_roles":
tab_role_count = index_text.count(marker)
project_tab_count = index_text.count("data-tab-key=")
nested_tab_count = index_text.count("data-panel-target=")
passed = (
'role="tablist"' in index_text
and project_tab_count == 5
and nested_tab_count >= 4
and tab_role_count >= project_tab_count + nested_tab_count
)
detail = {
"tab_role_count": tab_role_count,
"project_tab_count": project_tab_count,
"nested_tab_count": nested_tab_count,
"has_tablist": 'role="tablist"' in index_text,
}
elif name == "project_sections_are_labeled_tabpanels":
panel_count = index_text.count(marker)
passed = panel_count >= 19 and index_text.count('aria-labelledby="tab-') >= 19
detail = {
"panel_count": panel_count,
"labeled_panel_count": index_text.count('aria-labelledby="tab-'),
}
elif name == "project_tabs_update_selected_state":
selected_count = index_text.count(marker)
passed = selected_count >= 6 and 'setAttribute("aria-selected"' in index_text
detail = {
"selected_count": selected_count,
"updates_selected_state": 'setAttribute("aria-selected"' in index_text,
}
elif name == "project_tabs_support_keyboard_navigation":
marker_count = index_text.count(marker)
passed = marker_count >= 2 and "ArrowRight" in index_text and "Home" in index_text and "End" in index_text
detail = {
"marker_count": marker_count,
"has_arrow_navigation": "ArrowRight" in index_text and "ArrowLeft" in index_text,
"has_home_end_navigation": "Home" in index_text and "End" in index_text,
}
elif name == "roadmap_html_matches_json_phases":
phase_names = [str(phase.get("name", "")) for phase in (roadmap_payload or {}).get("phases", [])]
missing_names = [phase for phase in phase_names if phase and phase not in index_text]
passed = bool(phase_names) and not missing_names and not roadmap_json_error
detail = {
"phase_count": len(phase_names),
"missing_phase_names": missing_names,
"roadmap_json_error": roadmap_json_error,
}
elif name == "roadmap_status_chips_match_json":
statuses = [str(phase.get("status", "")).lower() for phase in (roadmap_payload or {}).get("phases", [])]
missing_statuses = sorted({status for status in statuses if status and f'data-status="{status}"' not in index_text})
passed = bool(statuses) and not missing_statuses and not roadmap_json_error
detail = {
"phase_count": len(statuses),
"statuses": statuses,
"missing_statuses": missing_statuses,
"roadmap_json_error": roadmap_json_error,
}
elif name == "suite_modality_atlas_contains_seven_cards":
card_count = len(re.findall(r'class="atlas-card(?:\s|")', suite_text))
passed = card_count == 7
detail = {"card_count": card_count}
elif name.startswith("dataset_card_section_"):
marker_count = dataset_text.count(marker)
passed = marker_count >= 1
detail = {"marker_count": marker_count}
elif name == "project_overview_precedes_progress_ledger":
passed = overview_pos >= 0 and evidence_pos >= 0 and overview_pos < evidence_pos
detail = {"overview_index": overview_pos, "evidence_index": evidence_pos}
elif name == "evaluation_protocol_between_overview_and_progress":
passed = overview_pos >= 0 and protocol_pos >= 0 and evidence_pos >= 0 and overview_pos < protocol_pos < evidence_pos
detail = {"overview_index": overview_pos, "protocol_index": protocol_pos, "evidence_index": evidence_pos}
elif name in {
"project_status_links_json",
"roadmap_links_json",
"interactive_roadmap_page_linked",
"interactive_roadmap_links_json",
"rendered_site_check_links_json",
"figure_index_links_json",
"task_player_surface_present",
"task_player_uses_walkthrough_json",
"task_cards_use_human_research_names",
}:
marker_count = index_text.count(marker)
passed = marker_count >= 1
detail = {"marker_count": marker_count}
elif name in {
"interactive_roadmap_loads_generated_json",
"interactive_roadmap_tracks_four_directions",
}:
marker_count = roadmap_page_text.count(marker)
passed = marker_count >= 1 and roadmap_page.exists()
detail = {"marker_count": marker_count, "page_exists": roadmap_page.exists()}
elif name == "evaluation_protocol_links_json":
marker_count = index_text.count(marker)
passed = marker_count >= 1
detail = {"marker_count": marker_count}
else:
marker_pos = suite_text.find(marker)
after_pos = suite_text.find(after_marker or "")
passed = marker_pos >= 0 and after_pos >= 0 and marker_pos < after_pos
detail = {"first_marker_index": marker_pos, "second_marker_index": after_pos}
check = {"name": name, "status": "pass" if passed else "fail", "reason": reason, **detail}
semantic_checks.append(check)
if not passed:
semantic_layout_failures.append(check)
failures = {
"missing_targets": missing_targets,
"missing_anchors": missing_anchors,
"duplicate_ids": duplicate_id_records,
"invalid_json": invalid_json,
"invalid_images": invalid_images,
"semantic_layout": semantic_layout_failures,
}
failure_count = sum(len(items) for items in failures.values())
return {
"status": "pass" if failure_count == 0 else "fail",
"generated_at_utc": datetime.now(timezone.utc).isoformat(timespec="seconds"),
"docs_root": relative(docs_root, ROOT),
"site_base": site_base,
"summary": {
"html_pages": len(html_files),
"local_references": len(local_references),
"external_reference_count": external_reference_count,
"json_files": len(json_records),
"image_assets_referenced": len(images),
"failure_count": failure_count,
},
"failures": failures,
"semantic_checks": semantic_checks,
"html_pages": [
{
"path": relative(path, docs_root),
"id_count": len(parser.ids),
"reference_count": len(parser.references),
"image_count": len(parser.images),
}
for path, parser in parsers.items()
],
"json_files": json_records,
"images": images,
}
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--docs-root", type=Path, default=DEFAULT_DOCS)
parser.add_argument("--output", type=Path, default=DEFAULT_OUTPUT)
parser.add_argument("--site-base", default=DEFAULT_SITE_BASE)
args = parser.parse_args()
report = validate(args.docs_root.resolve(), args.site_base)
args.output.parent.mkdir(parents=True, exist_ok=True)
args.output.write_text(json.dumps(report, indent=2) + "\n", encoding="utf-8")
print(f"{report['status'].upper()}: wrote {args.output}")
if report["status"] != "pass":
for kind, items in report["failures"].items():
for item in items[:20]:
print(f"- {kind}: {item}")
return 1
return 0
if __name__ == "__main__":
raise SystemExit(main())
|