| 1 | #!/usr/bin/env python3 |
| 2 | |
| 3 | import argparse |
| 4 | import bisect |
| 5 | import json |
| 6 | import subprocess |
| 7 | import sys |
| 8 | import unicodedata |
| 9 | from dataclasses import dataclass |
| 10 | from pathlib import Path |
| 11 | |
| 12 | from _common import ( |
| 13 | COLLECTOR_SOURCES, |
| 14 | GITHUB_ACTIONS, |
| 15 | INTEGRATIONS_PATH, |
| 16 | REPO_PATH, |
| 17 | WARNINGS, |
| 18 | load_collectors, |
| 19 | load_yaml, |
| 20 | make_id, |
| 21 | make_validator, |
| 22 | ) |
| 23 | |
| 24 | TAXONOMY_PATH = INTEGRATIONS_PATH / 'taxonomy' |
| 25 | SECTIONS_PATH = TAXONOMY_PATH / 'sections.yaml' |
| 26 | ICONS_PATH = TAXONOMY_PATH / 'icons.yaml' |
| 27 | OUTPUT_PATH = INTEGRATIONS_PATH / 'taxonomy.json' |
| 28 | |
| 29 | SECTIONS_VALIDATOR = make_validator('./taxonomy_sections.json#') |
| 30 | COLLECTOR_TAXONOMY_VALIDATOR = make_validator('./taxonomy_collector.json#') |
| 31 | OUTPUT_VALIDATOR = make_validator('./taxonomy_output.json#') |
| 32 | |
| 33 | FATAL = 'fatal' |
| 34 | WARNING = 'warning' |
| 35 | |
| 36 | DISPLAY_KEYS = ( |
| 37 | 'title', |
| 38 | 'short_name', |
| 39 | 'icon', |
| 40 | 'priority', |
| 41 | 'families', |
| 42 | 'tooltip', |
| 43 | 'menu_pattern', |
| 44 | 'hide_sub_icon', |
| 45 | 'force_visibility', |
| 46 | 'fallback_icon', |
| 47 | 'include_grand_parents', |
| 48 | 'properties', |
| 49 | ) |
| 50 | |
| 51 | WIDGET_KEYS = ( |
| 52 | 'chart_library', |
| 53 | 'group_by', |
| 54 | 'group_by_label', |
| 55 | 'aggregation_method', |
| 56 | 'selected_dimensions', |
| 57 | 'dimensions_sort', |
| 58 | 'colors', |
| 59 | 'layout', |
| 60 | 'table_columns', |
| 61 | 'table_sort_by', |
| 62 | 'labels', |
| 63 | 'value_range', |
| 64 | 'eliminate_zero_dimensions', |
| 65 | 'context_items', |
| 66 | 'post_group_by', |
| 67 | 'show_post_aggregations', |
| 68 | 'grouping_method', |
| 69 | 'sparkline', |
| 70 | 'renderer', |
| 71 | ) |
| 72 | |
| 73 | SELECTOR_KEYS = ('context_prefix', 'context_prefix_exclude', 'collect_plugin') |
| 74 | SORTED_LIST_KEYS = set(SELECTOR_KEYS) |
| 75 | |
| 76 | ITEM_COPY_KEYS = { |
| 77 | 'owned_context': ('context', *DISPLAY_KEYS, 'single_node'), |
| 78 | 'group': ('id', *DISPLAY_KEYS, 'section_filters', 'dyncfg', 'single_node'), |
| 79 | 'flatten': ('id', *DISPLAY_KEYS, 'single_node'), |
| 80 | 'selector': ('id', *DISPLAY_KEYS, *SELECTOR_KEYS, 'single_node'), |
| 81 | 'context': ('id', *DISPLAY_KEYS, 'contexts', *WIDGET_KEYS, 'single_node'), |
| 82 | 'grid': ('id', *DISPLAY_KEYS, 'renderer', 'single_node'), |
| 83 | 'first_available': ('id', *DISPLAY_KEYS, 'single_node'), |
| 84 | 'view_switch': ('id',), |
| 85 | } |
| 86 | |
| 87 | PLACEMENT_COPY_KEYS = ( |
| 88 | 'short_name', |
| 89 | 'icon', |
| 90 | 'priority', |
| 91 | 'families', |
| 92 | 'tooltip', |
| 93 | 'menu_pattern', |
| 94 | 'hide_sub_icon', |
| 95 | 'force_visibility', |
| 96 | 'fallback_icon', |
| 97 | 'include_grand_parents', |
| 98 | 'properties', |
| 99 | 'single_node', |
| 100 | ) |
| 101 | |
| 102 | |
| 103 | @dataclass(frozen=True) |
| 104 | class Finding: |
| 105 | code: str |
| 106 | severity: str |
| 107 | path: Path |
| 108 | message: str |
| 109 | line: int | None = None |
| 110 | |
| 111 | def render(self): |
| 112 | location = str(self.path) |
| 113 | if GITHUB_ACTIONS: |
| 114 | line = f',line={self.line}' if self.line else '' |
| 115 | level = 'error' if self.severity == FATAL else 'warning' |
| 116 | return f'::{level} file={location}{line},title={self.code}::{self.message}' |
| 117 | |
| 118 | line = f':{self.line}' if self.line else '' |
| 119 | return f'{location}{line}: {self.severity.upper()} {self.code}: {self.message}' |
| 120 | |
| 121 | |
| 122 | def relpath(path): |
| 123 | try: |
| 124 | return path.relative_to(REPO_PATH).as_posix() |
| 125 | except ValueError: |
| 126 | return path.as_posix() |
| 127 | |
| 128 | |
| 129 | def normalize_title(value): |
| 130 | normalized = unicodedata.normalize('NFC', value or '') |
| 131 | return normalized.casefold() |
| 132 | |
| 133 | |
| 134 | def path_segment(section): |
| 135 | return section['id'].rsplit('.', 1)[-1] |
| 136 | |
| 137 | |
| 138 | def run_git(*args): |
| 139 | try: |
| 140 | return subprocess.check_output( |
| 141 | ['git', '-C', str(REPO_PATH), *args], |
| 142 | text=True, |
| 143 | stderr=subprocess.DEVNULL, |
| 144 | ).strip() |
| 145 | except (subprocess.CalledProcessError, FileNotFoundError): |
| 146 | return 'unknown' |
| 147 | |
| 148 | |
| 149 | def source_info(): |
| 150 | return { |
| 151 | 'netdata_commit': run_git('rev-parse', 'HEAD'), |
| 152 | 'generated_at': run_git('log', '-1', '--format=%cI'), |
| 153 | } |
| 154 | |
| 155 | |
| 156 | def discover_taxonomy_files(): |
| 157 | files = [] |
| 158 | for _, root, recursive in COLLECTOR_SOURCES: |
| 159 | if root.exists() and root.is_dir() and recursive: |
| 160 | files.extend(root.glob('*/taxonomy.yaml')) |
| 161 | elif root.exists() and root.is_file() and root.name == 'taxonomy.yaml': |
| 162 | files.append(root) |
| 163 | return sorted(set(files), key=lambda p: relpath(p)) |
| 164 | |
| 165 | |
| 166 | def validate_schema(validator, data, path, default_code, findings): |
| 167 | valid = True |
| 168 | for error in sorted(validator.iter_errors(data), key=lambda e: list(e.absolute_path)): |
| 169 | valid = False |
| 170 | code = default_code |
| 171 | absolute_path = [str(part) for part in error.absolute_path] |
| 172 | if 'single_node' in absolute_path: |
| 173 | code = 'TAX021' |
| 174 | elif error.validator == 'additionalProperties' and 'section_path' in error.message: |
| 175 | code = 'TAX028' |
| 176 | findings.append(Finding( |
| 177 | code=code, |
| 178 | severity=FATAL, |
| 179 | path=path, |
| 180 | message=f'{error.message} (schema path: {"/".join(str(p) for p in error.absolute_schema_path)})', |
| 181 | )) |
| 182 | return valid |
| 183 | |
| 184 | |
| 185 | def load_icons(findings): |
| 186 | data = load_yaml(ICONS_PATH) |
| 187 | if not data: |
| 188 | findings.append(Finding('TAX001', FATAL, ICONS_PATH, 'Unable to load taxonomy icon registry.')) |
| 189 | return set() |
| 190 | icons = data.get('icons', []) |
| 191 | seen = set() |
| 192 | for icon in icons: |
| 193 | if icon in seen: |
| 194 | findings.append(Finding('TAX028', FATAL, ICONS_PATH, f'Duplicate icon id: {icon}')) |
| 195 | seen.add(icon) |
| 196 | return seen |
| 197 | |
| 198 | |
| 199 | def load_sections(findings, icons): |
| 200 | data = load_yaml(SECTIONS_PATH) |
| 201 | if not data: |
| 202 | findings.append(Finding('TAX001', FATAL, SECTIONS_PATH, 'Unable to load taxonomy sections registry.')) |
| 203 | return [], {} |
| 204 | |
| 205 | if not validate_schema(SECTIONS_VALIDATOR, data, SECTIONS_PATH, 'TAX001', findings): |
| 206 | return [], {} |
| 207 | |
| 208 | sections = data['sections'] |
| 209 | by_id = {} |
| 210 | for section in sections: |
| 211 | section_id = section['id'] |
| 212 | if section_id in by_id: |
| 213 | findings.append(Finding('TAX006', FATAL, SECTIONS_PATH, f'Duplicate section id: {section_id}')) |
| 214 | by_id[section_id] = section |
| 215 | |
| 216 | for section in sections: |
| 217 | icon = section.get('icon') |
| 218 | if icon and icon not in icons: |
| 219 | findings.append(Finding('TAX028', FATAL, SECTIONS_PATH, f'Section {section["id"]} references unknown icon: {icon}')) |
| 220 | |
| 221 | parent_id = section.get('parent_id') |
| 222 | if parent_id and parent_id not in by_id: |
| 223 | findings.append(Finding('TAX028', FATAL, SECTIONS_PATH, f'Section {section["id"]} references unknown parent_id: {parent_id}')) |
| 224 | |
| 225 | deprecation = section.get('deprecation', {}) |
| 226 | replacement_id = deprecation.get('replacement_id') |
| 227 | if replacement_id and replacement_id not in by_id: |
| 228 | findings.append(Finding('TAX028', FATAL, SECTIONS_PATH, f'Section {section["id"]} references unknown replacement_id: {replacement_id}')) |
| 229 | |
| 230 | paths = {} |
| 231 | |
| 232 | def resolve_path(section_id, visiting): |
| 233 | if section_id in paths: |
| 234 | return paths[section_id] |
| 235 | if section_id in visiting: |
| 236 | findings.append(Finding('TAX028', FATAL, SECTIONS_PATH, f'Section parent cycle includes: {section_id}')) |
| 237 | return section_id |
| 238 | section = by_id[section_id] |
| 239 | parent_id = section.get('parent_id') |
| 240 | if not parent_id: |
| 241 | paths[section_id] = section_id |
| 242 | return section_id |
| 243 | paths[section_id] = f'{resolve_path(parent_id, visiting | {section_id})}.{path_segment(section)}' |
| 244 | return paths[section_id] |
| 245 | |
| 246 | for section_id in by_id: |
| 247 | resolve_path(section_id, set()) |
| 248 | |
| 249 | emitted = [] |
| 250 | for section in sorted(sections, key=lambda s: (s['section_order'], normalize_title(s['title']), s['id'])): |
| 251 | item = { |
| 252 | 'id': section['id'], |
| 253 | 'path': paths[section['id']], |
| 254 | 'title': section['title'], |
| 255 | 'section_order': section['section_order'], |
| 256 | 'status': section['status'], |
| 257 | } |
| 258 | for key in ('parent_id', 'short_name', 'icon', 'deprecation'): |
| 259 | if key in section: |
| 260 | item[key] = section[key] |
| 261 | extras = {k: v for k, v in section.items() if k.startswith('x_')} |
| 262 | if extras: |
| 263 | item['_extra'] = extras |
| 264 | emitted.append(item) |
| 265 | |
| 266 | return emitted, {section_id: (section, paths[section_id]) for section_id, section in by_id.items()} |
| 267 | |
| 268 | |
| 269 | def module_contexts(module): |
| 270 | contexts = [] |
| 271 | for scope in module.get('metrics', {}).get('scopes', []): |
| 272 | for metric in scope.get('metrics', []): |
| 273 | name = metric.get('name') |
| 274 | if name and name not in contexts: |
| 275 | contexts.append(name) |
| 276 | return contexts |
| 277 | |
| 278 | |
| 279 | def dynamic_declarations(module): |
| 280 | metrics = module.get('metrics', {}) |
| 281 | prefixes = {item['prefix'] for item in metrics.get('dynamic_context_prefixes', [])} |
| 282 | plugins = {item['plugin'] for item in metrics.get('dynamic_collect_plugins', [])} |
| 283 | return prefixes, plugins |
| 284 | |
| 285 | |
| 286 | def build_metadata_indexes(findings): |
| 287 | warning_start = len(WARNINGS) |
| 288 | modules = load_collectors() |
| 289 | for path, message in WARNINGS[warning_start:]: |
| 290 | findings.append(Finding('TAX001', FATAL, Path(path), message)) |
| 291 | |
| 292 | by_path_module = {} |
| 293 | context_to_modules = {} |
| 294 | contexts_by_plugin = {} |
| 295 | all_contexts = set() |
| 296 | |
| 297 | for module in modules: |
| 298 | src_path = Path(module['_src_path']) |
| 299 | meta = module['meta'] |
| 300 | key = (src_path, meta['plugin_name'], meta['module_name']) |
| 301 | by_path_module.setdefault(key, []).append(module) |
| 302 | |
| 303 | contexts = module_contexts(module) |
| 304 | contexts_by_plugin.setdefault(meta['plugin_name'], set()).update(contexts) |
| 305 | for context in contexts: |
| 306 | all_contexts.add(context) |
| 307 | context_to_modules.setdefault(context, set()).add(key) |
| 308 | |
| 309 | return { |
| 310 | 'modules': modules, |
| 311 | 'by_path_module': by_path_module, |
| 312 | 'context_to_modules': context_to_modules, |
| 313 | 'contexts_by_plugin': contexts_by_plugin, |
| 314 | 'all_contexts': sorted(all_contexts), |
| 315 | } |
| 316 | |
| 317 | |
| 318 | def prescan_removed_shapes(data, path, findings): |
| 319 | def walk(node): |
| 320 | if isinstance(node, dict): |
| 321 | if 'multi_node' in node and node.get('type') != 'view_switch': |
| 322 | findings.append(Finding('TAX022', FATAL, path, '`multi_node:` is accepted only inside `type: view_switch`.')) |
| 323 | for key, value in node.items(): |
| 324 | if key.endswith('_extend'): |
| 325 | findings.append(Finding('TAX023', FATAL, path, f'List-merge field `{key}:` is not accepted in taxonomy v1.')) |
| 326 | walk(value) |
| 327 | elif isinstance(node, list): |
| 328 | for item in node: |
| 329 | walk(item) |
| 330 | |
| 331 | walk(data) |
| 332 | |
| 333 | |
| 334 | def collector_ids(modules): |
| 335 | ids = [] |
| 336 | for module in modules: |
| 337 | ids.append(make_id(module['meta'])) |
| 338 | return sorted(ids) |
| 339 | |
| 340 | |
| 341 | def merged_module_contexts(modules): |
| 342 | contexts = set() |
| 343 | for module in modules: |
| 344 | contexts.update(module_contexts(module)) |
| 345 | return contexts |
| 346 | |
| 347 | |
| 348 | def merged_dynamic_declarations(modules, inline): |
| 349 | prefixes = set() |
| 350 | plugins = set() |
| 351 | for module in modules: |
| 352 | module_prefixes, module_plugins = dynamic_declarations(module) |
| 353 | prefixes.update(module_prefixes) |
| 354 | plugins.update(module_plugins) |
| 355 | |
| 356 | if inline: |
| 357 | prefixes.update(item['prefix'] for item in inline.get('dynamic_context_prefixes', [])) |
| 358 | plugins.update(item['plugin'] for item in inline.get('dynamic_collect_plugins', [])) |
| 359 | |
| 360 | return prefixes, plugins |
| 361 | |
| 362 | |
| 363 | def resolve_prefix(prefix, all_contexts): |
| 364 | start = bisect.bisect_left(all_contexts, prefix) |
| 365 | stop = bisect.bisect_left(all_contexts, prefix + chr(0x10ffff)) |
| 366 | return all_contexts[start:stop] |
| 367 | |
| 368 | |
| 369 | def is_context_prefix_declared(prefix, allowed_prefixes): |
| 370 | return any(prefix.startswith(allowed) for allowed in allowed_prefixes) |
| 371 | |
| 372 | |
| 373 | def ordered_union(*sequences): |
| 374 | seen = set() |
| 375 | result = [] |
| 376 | for sequence in sequences: |
| 377 | for item in sequence: |
| 378 | if item not in seen: |
| 379 | seen.add(item) |
| 380 | result.append(item) |
| 381 | return result |
| 382 | |
| 383 | |
| 384 | def ordered_dict_union(*sequences): |
| 385 | seen = set() |
| 386 | result = [] |
| 387 | for sequence in sequences: |
| 388 | for item in sequence: |
| 389 | key = json.dumps(item, sort_keys=True) |
| 390 | if key not in seen: |
| 391 | seen.add(key) |
| 392 | result.append(item) |
| 393 | return result |
| 394 | |
| 395 | |
| 396 | def node_label(node, fallback): |
| 397 | if isinstance(node, str): |
| 398 | return node |
| 399 | return node.get('id') or node.get('context') or node.get('title') or fallback |
| 400 | |
| 401 | |
| 402 | def validate_icons(node, path, icons, findings, label): |
| 403 | for key in ('icon', 'fallback_icon'): |
| 404 | icon = node.get(key) |
| 405 | if icon and icon not in icons: |
| 406 | findings.append(Finding('TAX028', FATAL, path, f'Item `{label}` references unknown {key}: {icon}')) |
| 407 | |
| 408 | |
| 409 | def validate_override(parent, path, findings): |
| 410 | if parent.get('type') == 'view_switch': |
| 411 | return |
| 412 | single_node = parent.get('single_node') |
| 413 | if single_node is None: |
| 414 | return |
| 415 | if not single_node: |
| 416 | findings.append(Finding('TAX024', WARNING, path, 'Empty `single_node:` block is equivalent to omitting it.')) |
| 417 | return |
| 418 | for key, value in single_node.items(): |
| 419 | if parent.get(key) == value: |
| 420 | findings.append(Finding('TAX025', WARNING, path, f'`single_node.{key}` is identical to the top-level value.')) |
| 421 | |
| 422 | |
| 423 | def copy_fields(node, output, keys): |
| 424 | for key in keys: |
| 425 | if key in node: |
| 426 | value = node[key] |
| 427 | if key in SORTED_LIST_KEYS: |
| 428 | value = sorted(value) |
| 429 | output[key] = value |
| 430 | |
| 431 | |
| 432 | def emit_extra(node, output): |
| 433 | extras = {k: v for k, v in node.items() if k.startswith('x_')} |
| 434 | if extras: |
| 435 | output['_extra'] = extras |
| 436 | |
| 437 | |
| 438 | def resolve_selectors(node, known_contexts, allowed_prefixes, allowed_plugins, metadata_indexes, path, findings): |
| 439 | resolved = set() |
| 440 | explicit = node.get('contexts', []) |
| 441 | prefixes = node.get('context_prefix', []) |
| 442 | excludes = node.get('context_prefix_exclude', []) |
| 443 | collect_plugins = node.get('collect_plugin', []) |
| 444 | |
| 445 | for context in explicit: |
| 446 | if context not in known_contexts: |
| 447 | findings.append(Finding('TAX003', FATAL, path, f'Unknown context for this collector: {context}')) |
| 448 | resolved.add(context) |
| 449 | |
| 450 | if excludes and not prefixes: |
| 451 | findings.append(Finding('TAX029', FATAL, path, '`context_prefix_exclude:` requires `context_prefix:` on the same node.')) |
| 452 | |
| 453 | for prefix in prefixes: |
| 454 | if not is_context_prefix_declared(prefix, allowed_prefixes): |
| 455 | findings.append(Finding('TAX031', FATAL, path, f'context_prefix `{prefix}` is not declared in metadata.yaml metrics.dynamic_context_prefixes.')) |
| 456 | for context in resolve_prefix(prefix, metadata_indexes['all_contexts']): |
| 457 | resolved.add(context) |
| 458 | |
| 459 | for exclude in excludes if prefixes else []: |
| 460 | if not any(exclude.startswith(prefix) for prefix in prefixes): |
| 461 | findings.append(Finding('TAX029', FATAL, path, f'context_prefix_exclude `{exclude}` is not covered by context_prefix.')) |
| 462 | for context in list(resolved): |
| 463 | if context.startswith(exclude): |
| 464 | resolved.remove(context) |
| 465 | |
| 466 | for plugin in collect_plugins: |
| 467 | if plugin not in allowed_plugins: |
| 468 | findings.append(Finding('TAX035', FATAL, path, f'collect_plugin `{plugin}` is not declared in metadata.yaml metrics.dynamic_collect_plugins.')) |
| 469 | resolved.update(metadata_indexes['contexts_by_plugin'].get(plugin, set())) |
| 470 | |
| 471 | for context in explicit: |
| 472 | if any(context.startswith(prefix) for prefix in prefixes): |
| 473 | findings.append(Finding('TAX034', WARNING, path, f'Context `{context}` is redundant because it is covered by context_prefix.')) |
| 474 | |
| 475 | return sorted(resolved) |
| 476 | |
| 477 | |
| 478 | def resolve_node_contexts(node, known_contexts, allowed_prefixes, allowed_plugins, metadata_indexes, path, findings): |
| 479 | return resolve_selectors(node, known_contexts, allowed_prefixes, allowed_plugins, metadata_indexes, path, findings) |
| 480 | |
| 481 | |
| 482 | def validate_literal_context(context, known_contexts, unresolved, path, findings): |
| 483 | known = context in known_contexts |
| 484 | if unresolved: |
| 485 | if known: |
| 486 | findings.append(Finding('TAX038', WARNING, path, f'Unresolved escape hatch is stale because context now exists: {context}')) |
| 487 | elif not known: |
| 488 | findings.append(Finding('TAX003', FATAL, path, f'Unknown context for this collector: {context}')) |
| 489 | return known |
| 490 | |
| 491 | |
| 492 | def resolve_context_references( |
| 493 | refs, |
| 494 | known_contexts, |
| 495 | allowed_prefixes, |
| 496 | allowed_plugins, |
| 497 | metadata_indexes, |
| 498 | path, |
| 499 | findings, |
| 500 | referenced_literals, |
| 501 | item_path): |
| 502 | referenced = [] |
| 503 | unresolved_references = [] |
| 504 | for ref in refs: |
| 505 | if isinstance(ref, str): |
| 506 | known = validate_literal_context(ref, known_contexts, unresolved=False, path=path, findings=findings) |
| 507 | referenced = ordered_union(referenced, [ref]) |
| 508 | referenced_literals.append((ref, item_path, path, False, known)) |
| 509 | continue |
| 510 | |
| 511 | if 'context' in ref: |
| 512 | context = ref['context'] |
| 513 | known = validate_literal_context(context, known_contexts, unresolved=True, path=path, findings=findings) |
| 514 | referenced = ordered_union(referenced, [context]) |
| 515 | referenced_literals.append((context, item_path, path, True, known)) |
| 516 | unresolved_references.append({ |
| 517 | 'context': context, |
| 518 | 'reason': ref['unresolved']['reason'], |
| 519 | 'owner': ref['unresolved']['owner'], |
| 520 | 'expires': ref['unresolved']['expires'], |
| 521 | 'item_path': item_path, |
| 522 | }) |
| 523 | continue |
| 524 | |
| 525 | resolved = resolve_selectors(ref, known_contexts, allowed_prefixes, allowed_plugins, metadata_indexes, path, findings) |
| 526 | referenced = ordered_union(referenced, resolved) |
| 527 | |
| 528 | return referenced, unresolved_references |
| 529 | |
| 530 | |
| 531 | def register_ownership(contexts, ownership, current, owner_kind, path, ownership_conflicts): |
| 532 | for context in contexts: |
| 533 | previous = ownership.get(context) |
| 534 | if previous and previous['owner'] != current: |
| 535 | code = 'TAX036' if 'selector' in {previous['kind'], owner_kind} else 'TAX033' |
| 536 | owners = tuple(sorted([previous['owner'], current])) |
| 537 | ownership_conflicts[(code, context, owners)] = { |
| 538 | 'path': path, |
| 539 | } |
| 540 | ownership[context] = { |
| 541 | 'owner': current, |
| 542 | 'kind': owner_kind, |
| 543 | } |
| 544 | |
| 545 | |
| 546 | def emit_ownership_conflicts(ownership_conflicts, findings): |
| 547 | for code, context, owners in sorted(ownership_conflicts): |
| 548 | findings.append(Finding( |
| 549 | code, |
| 550 | FATAL, |
| 551 | ownership_conflicts[(code, context, owners)]['path'], |
| 552 | f'Context `{context}` is owned by both {owners[0]} and {owners[1]}.', |
| 553 | )) |
| 554 | |
| 555 | |
| 556 | def emit_item( |
| 557 | node, |
| 558 | position, |
| 559 | known_contexts, |
| 560 | allowed_prefixes, |
| 561 | allowed_plugins, |
| 562 | metadata_indexes, |
| 563 | icons, |
| 564 | ownership, |
| 565 | ownership_conflicts, |
| 566 | referenced_literals, |
| 567 | owner_label, |
| 568 | path, |
| 569 | findings, |
| 570 | index): |
| 571 | if isinstance(node, str): |
| 572 | label = f'{owner_label}.{node}' |
| 573 | validate_literal_context(node, known_contexts, unresolved=False, path=path, findings=findings) |
| 574 | register_ownership([node], ownership, f'{relpath(path)}:{label}', 'literal', path, ownership_conflicts) |
| 575 | return { |
| 576 | 'type': 'owned_context', |
| 577 | 'context': node, |
| 578 | 'resolved_contexts': [node], |
| 579 | 'referenced_contexts': [], |
| 580 | 'unresolved_references': [], |
| 581 | } |
| 582 | |
| 583 | kind = node['type'] |
| 584 | label = f'{owner_label}.{node_label(node, str(index))}' |
| 585 | validate_icons(node, path, icons, findings, label) |
| 586 | validate_override(node, path, findings) |
| 587 | |
| 588 | output = {'type': kind} |
| 589 | copy_fields(node, output, ITEM_COPY_KEYS[kind]) |
| 590 | emit_extra(node, output) |
| 591 | |
| 592 | resolved_contexts = [] |
| 593 | referenced_contexts = [] |
| 594 | unresolved_references = [] |
| 595 | |
| 596 | if kind == 'owned_context': |
| 597 | context = node['context'] |
| 598 | validate_literal_context(context, known_contexts, unresolved=False, path=path, findings=findings) |
| 599 | resolved_contexts = [context] |
| 600 | register_ownership(resolved_contexts, ownership, f'{relpath(path)}:{label}', 'literal', path, ownership_conflicts) |
| 601 | |
| 602 | elif kind == 'selector': |
| 603 | resolved_contexts = resolve_selectors(node, known_contexts, allowed_prefixes, allowed_plugins, metadata_indexes, path, findings) |
| 604 | register_ownership(resolved_contexts, ownership, f'{relpath(path)}:{label}', 'selector', path, ownership_conflicts) |
| 605 | |
| 606 | elif kind in ('group', 'flatten'): |
| 607 | children = [] |
| 608 | for child_index, child in enumerate(node.get('items', [])): |
| 609 | emitted = emit_item( |
| 610 | child, |
| 611 | 'structural', |
| 612 | known_contexts, |
| 613 | allowed_prefixes, |
| 614 | allowed_plugins, |
| 615 | metadata_indexes, |
| 616 | icons, |
| 617 | ownership, |
| 618 | ownership_conflicts, |
| 619 | referenced_literals, |
| 620 | label, |
| 621 | path, |
| 622 | findings, |
| 623 | child_index, |
| 624 | ) |
| 625 | children.append(emitted) |
| 626 | resolved_contexts = ordered_union(resolved_contexts, emitted['resolved_contexts']) |
| 627 | referenced_contexts = ordered_union(referenced_contexts, emitted['referenced_contexts']) |
| 628 | unresolved_references = ordered_dict_union(unresolved_references, emitted['unresolved_references']) |
| 629 | output['items'] = children |
| 630 | |
| 631 | elif kind == 'context': |
| 632 | referenced_contexts, unresolved_references = resolve_context_references( |
| 633 | node['contexts'], |
| 634 | known_contexts, |
| 635 | allowed_prefixes, |
| 636 | allowed_plugins, |
| 637 | metadata_indexes, |
| 638 | path, |
| 639 | findings, |
| 640 | referenced_literals, |
| 641 | label, |
| 642 | ) |
| 643 | |
| 644 | elif kind == 'grid': |
| 645 | children = [] |
| 646 | for child_index, child in enumerate(node.get('items', [])): |
| 647 | emitted = emit_item( |
| 648 | child, |
| 649 | 'display', |
| 650 | known_contexts, |
| 651 | allowed_prefixes, |
| 652 | allowed_plugins, |
| 653 | metadata_indexes, |
| 654 | icons, |
| 655 | ownership, |
| 656 | ownership_conflicts, |
| 657 | referenced_literals, |
| 658 | label, |
| 659 | path, |
| 660 | findings, |
| 661 | child_index, |
| 662 | ) |
| 663 | children.append(emitted) |
| 664 | resolved_contexts = ordered_union(resolved_contexts, emitted['resolved_contexts']) |
| 665 | referenced_contexts = ordered_union(referenced_contexts, emitted['referenced_contexts']) |
| 666 | unresolved_references = ordered_dict_union(unresolved_references, emitted['unresolved_references']) |
| 667 | output['items'] = children |
| 668 | |
| 669 | elif kind == 'first_available': |
| 670 | children = [] |
| 671 | for child_index, child in enumerate(node.get('items', [])): |
| 672 | emitted = emit_item( |
| 673 | child, |
| 674 | 'display', |
| 675 | known_contexts, |
| 676 | allowed_prefixes, |
| 677 | allowed_plugins, |
| 678 | metadata_indexes, |
| 679 | icons, |
| 680 | ownership, |
| 681 | ownership_conflicts, |
| 682 | referenced_literals, |
| 683 | label, |
| 684 | path, |
| 685 | findings, |
| 686 | child_index, |
| 687 | ) |
| 688 | children.append(emitted) |
| 689 | resolved_contexts = ordered_union(resolved_contexts, emitted['resolved_contexts']) |
| 690 | referenced_contexts = ordered_union(referenced_contexts, emitted['referenced_contexts']) |
| 691 | unresolved_references = ordered_dict_union(unresolved_references, emitted['unresolved_references']) |
| 692 | output['items'] = children |
| 693 | |
| 694 | elif kind == 'view_switch': |
| 695 | branch_position = 'structural' if position == 'structural' else 'display' |
| 696 | for branch in ('multi_node', 'single_node'): |
| 697 | emitted = emit_item( |
| 698 | node[branch], |
| 699 | branch_position, |
| 700 | known_contexts, |
| 701 | allowed_prefixes, |
| 702 | allowed_plugins, |
| 703 | metadata_indexes, |
| 704 | icons, |
| 705 | ownership, |
| 706 | ownership_conflicts, |
| 707 | referenced_literals, |
| 708 | f'{label}.{branch}', |
| 709 | path, |
| 710 | findings, |
| 711 | 0, |
| 712 | ) |
| 713 | output[branch] = emitted |
| 714 | resolved_contexts = ordered_union(resolved_contexts, emitted['resolved_contexts']) |
| 715 | referenced_contexts = ordered_union(referenced_contexts, emitted['referenced_contexts']) |
| 716 | unresolved_references = ordered_dict_union(unresolved_references, emitted['unresolved_references']) |
| 717 | |
| 718 | if position != 'structural' and resolved_contexts: |
| 719 | findings.append(Finding('TAX001', FATAL, path, f'Item `{label}` owns contexts from a display-only position.')) |
| 720 | |
| 721 | output['resolved_contexts'] = resolved_contexts |
| 722 | output['referenced_contexts'] = referenced_contexts |
| 723 | output['unresolved_references'] = unresolved_references |
| 724 | return output |
| 725 | |
| 726 | |
| 727 | def emit_referenced_only_findings(referenced_literals, ownership, findings): |
| 728 | emitted = set() |
| 729 | rows = sorted(referenced_literals, key=lambda row: (row[0], row[1], relpath(row[2]))) |
| 730 | for context, item_path, path, unresolved, known in rows: |
| 731 | if unresolved or not known or context in ownership: |
| 732 | continue |
| 733 | key = (context, item_path, path) |
| 734 | if key in emitted: |
| 735 | continue |
| 736 | emitted.add(key) |
| 737 | findings.append(Finding( |
| 738 | 'TAX037', |
| 739 | FATAL, |
| 740 | path, |
| 741 | f'Context `{context}` is referenced by widget `{item_path}` but is not owned by any taxonomy item.', |
| 742 | )) |
| 743 | |
| 744 | |
| 745 | def process_taxonomy_file(path, sections, icons, metadata_indexes, ownership, findings, referenced_literals=None, ownership_conflicts=None): |
| 746 | if referenced_literals is None: |
| 747 | referenced_literals = [] |
| 748 | if ownership_conflicts is None: |
| 749 | ownership_conflicts = {} |
| 750 | |
| 751 | data = load_yaml(path) |
| 752 | if not data: |
| 753 | findings.append(Finding('TAX001', FATAL, path, 'Unable to load taxonomy file.')) |
| 754 | return [], [] |
| 755 | |
| 756 | prescan_removed_shapes(data, path, findings) |
| 757 | if not validate_schema(COLLECTOR_TAXONOMY_VALIDATOR, data, path, 'TAX001', findings): |
| 758 | return [], [] |
| 759 | |
| 760 | metadata_path = path.with_name('metadata.yaml') |
| 761 | identity = (metadata_path, data['plugin_name'], data['module_name']) |
| 762 | modules = metadata_indexes['by_path_module'].get(identity, []) |
| 763 | inline = data.get('inline_dynamic_declarations') |
| 764 | |
| 765 | if modules and inline: |
| 766 | findings.append(Finding('TAX029', FATAL, path, '`inline_dynamic_declarations:` is allowed only for collectors without metadata.yaml.')) |
| 767 | |
| 768 | known_contexts = merged_module_contexts(modules) |
| 769 | allowed_prefixes, allowed_plugins = merged_dynamic_declarations(modules, inline) |
| 770 | ids = collector_ids(modules) if modules else [f'{data["plugin_name"]}-{data["module_name"]}'] |
| 771 | |
| 772 | if 'taxonomy_optout' in data: |
| 773 | return [], [{ |
| 774 | 'collector_ids': ids, |
| 775 | 'plugin_name': data['plugin_name'], |
| 776 | 'module_name': data['module_name'], |
| 777 | 'source_path': relpath(path), |
| 778 | 'reason': data['taxonomy_optout']['reason'], |
| 779 | }] |
| 780 | |
| 781 | if not modules and not inline: |
| 782 | findings.append(Finding('TAX001', FATAL, path, 'No matching metadata.yaml module found and no inline_dynamic_declarations provided.')) |
| 783 | |
| 784 | emitted = [] |
| 785 | placement_keys = set() |
| 786 | |
| 787 | for placement in data['placements']: |
| 788 | placement_key = (placement['section_id'], placement['id']) |
| 789 | if placement_key in placement_keys: |
| 790 | findings.append(Finding('TAX006', FATAL, path, f'Duplicate placement in collector taxonomy: {placement["section_id"]}.{placement["id"]}')) |
| 791 | placement_keys.add(placement_key) |
| 792 | |
| 793 | section = sections.get(placement['section_id']) |
| 794 | if not section: |
| 795 | findings.append(Finding('TAX028', FATAL, path, f'Unknown section_id: {placement["section_id"]}')) |
| 796 | section_path = placement['section_id'] |
| 797 | else: |
| 798 | section_entry, section_path = section |
| 799 | if section_entry['status'] == 'deprecated': |
| 800 | findings.append(Finding('TAX028', FATAL, path, f'New placements cannot target deprecated section_id: {placement["section_id"]}')) |
| 801 | |
| 802 | validate_icons(placement, path, icons, findings, placement['id']) |
| 803 | validate_override(placement, path, findings) |
| 804 | |
| 805 | items = [] |
| 806 | resolved_contexts = [] |
| 807 | referenced_contexts = [] |
| 808 | unresolved_references = [] |
| 809 | for index, child in enumerate(placement['items']): |
| 810 | emitted_child = emit_item( |
| 811 | child, |
| 812 | 'structural', |
| 813 | known_contexts, |
| 814 | allowed_prefixes, |
| 815 | allowed_plugins, |
| 816 | metadata_indexes, |
| 817 | icons, |
| 818 | ownership, |
| 819 | ownership_conflicts, |
| 820 | referenced_literals, |
| 821 | placement['id'], |
| 822 | path, |
| 823 | findings, |
| 824 | index, |
| 825 | ) |
| 826 | items.append(emitted_child) |
| 827 | resolved_contexts = ordered_union(resolved_contexts, emitted_child['resolved_contexts']) |
| 828 | referenced_contexts = ordered_union(referenced_contexts, emitted_child['referenced_contexts']) |
| 829 | unresolved_references = ordered_dict_union(unresolved_references, emitted_child['unresolved_references']) |
| 830 | |
| 831 | item = { |
| 832 | 'collector_ids': ids, |
| 833 | 'plugin_name': data['plugin_name'], |
| 834 | 'module_name': data['module_name'], |
| 835 | 'source_path': relpath(path), |
| 836 | 'id': placement['id'], |
| 837 | 'section_id': placement['section_id'], |
| 838 | 'section_path': section_path, |
| 839 | 'title': placement['title'], |
| 840 | 'items': items, |
| 841 | 'resolved_contexts': resolved_contexts, |
| 842 | 'referenced_contexts': referenced_contexts, |
| 843 | 'unresolved_references': unresolved_references, |
| 844 | } |
| 845 | copy_fields(placement, item, PLACEMENT_COPY_KEYS) |
| 846 | emit_extra(placement, item) |
| 847 | emitted.append(item) |
| 848 | |
| 849 | return emitted, [] |
| 850 | |
| 851 | |
| 852 | def build_taxonomy(): |
| 853 | findings = [] |
| 854 | icons = load_icons(findings) |
| 855 | section_entries, sections = load_sections(findings, icons) |
| 856 | metadata_indexes = build_metadata_indexes(findings) |
| 857 | ownership = {} |
| 858 | ownership_conflicts = {} |
| 859 | referenced_literals = [] |
| 860 | placements = [] |
| 861 | opted_out_collectors = [] |
| 862 | |
| 863 | for path in discover_taxonomy_files(): |
| 864 | new_placements, new_optouts = process_taxonomy_file(path, sections, icons, metadata_indexes, ownership, findings, referenced_literals, ownership_conflicts) |
| 865 | placements.extend(new_placements) |
| 866 | opted_out_collectors.extend(new_optouts) |
| 867 | |
| 868 | emit_ownership_conflicts(ownership_conflicts, findings) |
| 869 | emit_referenced_only_findings(referenced_literals, ownership, findings) |
| 870 | |
| 871 | placements.sort(key=lambda item: ( |
| 872 | sections.get(item['section_id'], ({'section_order': 100000}, item['section_path']))[0]['section_order'], |
| 873 | item.get('priority', 1000), |
| 874 | normalize_title(item['title']), |
| 875 | item['id'], |
| 876 | item['source_path'], |
| 877 | )) |
| 878 | |
| 879 | taxonomy = { |
| 880 | 'taxonomy_schema_version': 1, |
| 881 | 'source': source_info(), |
| 882 | 'sections': section_entries, |
| 883 | 'placements': placements, |
| 884 | 'opted_out_collectors': sorted(opted_out_collectors, key=lambda item: (item['plugin_name'], item['module_name'], item['source_path'])), |
| 885 | } |
| 886 | |
| 887 | validate_schema(OUTPUT_VALIDATOR, taxonomy, OUTPUT_PATH, 'TAX001', findings) |
| 888 | return taxonomy, findings |
| 889 | |
| 890 | |
| 891 | def write_json(path, data): |
| 892 | path.write_text(json.dumps(data, indent=2, sort_keys=True) + '\n') |
| 893 | |
| 894 | |
| 895 | def main(): |
| 896 | parser = argparse.ArgumentParser(description='Generate Netdata collector taxonomy artifact.') |
| 897 | parser.add_argument('--check-only', action='store_true', help='Validate taxonomy sources without writing taxonomy.json.') |
| 898 | parser.add_argument('--output', type=Path, default=OUTPUT_PATH, help='Output JSON path.') |
| 899 | parser.add_argument('--findings-json', type=Path, help='Optional path for machine-readable findings.') |
| 900 | args = parser.parse_args() |
| 901 | |
| 902 | taxonomy, findings = build_taxonomy() |
| 903 | |
| 904 | for finding in findings: |
| 905 | print(finding.render(), file=sys.stderr) |
| 906 | |
| 907 | if args.findings_json: |
| 908 | write_json(args.findings_json, [ |
| 909 | { |
| 910 | 'code': finding.code, |
| 911 | 'severity': finding.severity, |
| 912 | 'path': relpath(finding.path), |
| 913 | 'line': finding.line, |
| 914 | 'message': finding.message, |
| 915 | } |
| 916 | for finding in findings |
| 917 | ]) |
| 918 | |
| 919 | if any(finding.severity == FATAL for finding in findings): |
| 920 | return 1 |
| 921 | |
| 922 | if not args.check_only: |
| 923 | write_json(args.output, taxonomy) |
| 924 | |
| 925 | return 0 |
| 926 | |
| 927 | |
| 928 | if __name__ == '__main__': |
| 929 | sys.exit(main()) |