| 1 | #!/usr/bin/env python3 |
| 2 | """PPT Master project-management CLI implementation. |
| 3 | |
| 4 | Usage: |
| 5 | python3 scripts/project_manager.py init <project_name> [--format ppt169] [--dir <path>] [--quick-generate] |
| 6 | python3 scripts/project_manager.py import-sources <project_path> <source1> [<source2> ...] [--move | --copy] |
| 7 | python3 scripts/project_manager.py scaffold-spec <project_path> |
| 8 | python3 scripts/project_manager.py scaffold-lock <project_path> |
| 9 | python3 scripts/project_manager.py validate <project_path> |
| 10 | python3 scripts/project_manager.py info <project_path> |
| 11 | python3 scripts/project_manager.py page-context <project_path> P07 [--record-usage] |
| 12 | python3 scripts/project_manager.py page-context-report <project_path> |
| 13 | |
| 14 | Examples: |
| 15 | python3 scripts/project_manager.py init demo --format ppt169 |
| 16 | python3 scripts/project_manager.py validate projects/demo |
| 17 | |
| 18 | Dependencies: |
| 19 | Standard library plus local PPT Master project and source-conversion modules. |
| 20 | """ |
| 21 | |
| 22 | from __future__ import annotations |
| 23 | |
| 24 | import argparse |
| 25 | import filecmp |
| 26 | import json |
| 27 | import os |
| 28 | import re |
| 29 | import shutil |
| 30 | import subprocess |
| 31 | import sys |
| 32 | import tempfile |
| 33 | from datetime import datetime |
| 34 | from pathlib import Path |
| 35 | from urllib.parse import urlparse |
| 36 | |
| 37 | from .page_context import ( |
| 38 | build_page_context, |
| 39 | page_context_usage_report, |
| 40 | record_page_context_usage, |
| 41 | render_page_context, |
| 42 | ) |
| 43 | from .paths import ( |
| 44 | PROJECTS_ROOT, |
| 45 | REPO_ROOT, |
| 46 | SCRIPTS_DIR, |
| 47 | SOURCE_TO_MD_DIR, |
| 48 | ) |
| 49 | from .project_specs import scaffold_project_artifact, validate_project_artifacts |
| 50 | |
| 51 | if str(SCRIPTS_DIR) not in sys.path: |
| 52 | sys.path.insert(0, str(SCRIPTS_DIR)) |
| 53 | |
| 54 | from attribution_guard import require_skill_integrity # noqa: E402 |
| 55 | from workflow_log import append_note # noqa: E402 |
| 56 | |
| 57 | try: |
| 58 | from project_utils import ( |
| 59 | CANVAS_FORMATS, |
| 60 | get_project_info as get_project_info_common, |
| 61 | normalize_canvas_format, |
| 62 | validate_project_structure, |
| 63 | validate_svg_viewbox, |
| 64 | ) |
| 65 | except ImportError: |
| 66 | tools_dir = SCRIPTS_DIR |
| 67 | if str(tools_dir) not in sys.path: |
| 68 | sys.path.insert(0, str(tools_dir)) |
| 69 | from project_utils import ( # type: ignore |
| 70 | CANVAS_FORMATS, |
| 71 | get_project_info as get_project_info_common, |
| 72 | normalize_canvas_format, |
| 73 | validate_project_structure, |
| 74 | validate_svg_viewbox, |
| 75 | ) |
| 76 | |
| 77 | TOOLS_DIR = SCRIPTS_DIR |
| 78 | SOURCE_TO_MD_TOOLS_DIR = SOURCE_TO_MD_DIR |
| 79 | if str(SOURCE_TO_MD_TOOLS_DIR) not in sys.path: |
| 80 | sys.path.insert(0, str(SOURCE_TO_MD_TOOLS_DIR)) |
| 81 | |
| 82 | from _dispatcher import ( # noqa: E402 |
| 83 | DOC_SUFFIXES, |
| 84 | EXCEL_SUFFIXES, |
| 85 | LEGACY_EXCEL_SUFFIXES, |
| 86 | PDF_SUFFIXES, |
| 87 | PRESENTATION_SUFFIXES, |
| 88 | build_conversion_command, |
| 89 | ) |
| 90 | |
| 91 | SOURCE_DIRNAME = "sources" |
| 92 | TEXT_SOURCE_SUFFIXES = {".md", ".markdown", ".txt"} |
| 93 | TABLE_TEXT_SUFFIXES = {".csv", ".tsv"} |
| 94 | BITMAP_IMAGE_SUFFIXES = { |
| 95 | ".png", ".jpg", ".jpeg", ".gif", ".webp", ".bmp", ".tiff", ".tif", |
| 96 | } |
| 97 | IMAGE_ASSET_SUFFIXES = BITMAP_IMAGE_SUFFIXES | { |
| 98 | ".emf", ".wmf", ".svg", |
| 99 | } |
| 100 | |
| 101 | |
| 102 | def _validate_image_manifest( |
| 103 | payload: object, |
| 104 | path: Path, |
| 105 | ) -> list[dict]: |
| 106 | """Require a safe, case-insensitively unique image manifest payload.""" |
| 107 | if not isinstance(payload, list): |
| 108 | raise RuntimeError( |
| 109 | f"Image manifest must be a JSON array: {path}" |
| 110 | ) |
| 111 | |
| 112 | seen_filenames: dict[str, str] = {} |
| 113 | for index, item in enumerate(payload): |
| 114 | if not isinstance(item, dict): |
| 115 | raise RuntimeError( |
| 116 | f"Existing image manifest item {index} must be an object: {path}" |
| 117 | ) |
| 118 | filename = item.get("filename") |
| 119 | if ( |
| 120 | not isinstance(filename, str) |
| 121 | or not filename.strip() |
| 122 | or filename in {".", ".."} |
| 123 | or "/" in filename |
| 124 | or "\\" in filename |
| 125 | or ":" in filename |
| 126 | or Path(filename).is_absolute() |
| 127 | or Path(filename).name != filename |
| 128 | ): |
| 129 | raise RuntimeError( |
| 130 | f"Image manifest item {index} has no safe bare filename: {path}" |
| 131 | ) |
| 132 | normalized_filename = filename.casefold() |
| 133 | if normalized_filename in seen_filenames: |
| 134 | raise RuntimeError( |
| 135 | f"Image manifest filename {filename!r} conflicts with " |
| 136 | f"{seen_filenames[normalized_filename]!r} (case-insensitive): {path}" |
| 137 | ) |
| 138 | seen_filenames[normalized_filename] = filename |
| 139 | return payload |
| 140 | |
| 141 | |
| 142 | def _read_existing_image_manifest(path: Path) -> list[dict]: |
| 143 | """Load an existing project image manifest or fail closed on corruption.""" |
| 144 | if not path.exists(): |
| 145 | return [] |
| 146 | if not path.is_file(): |
| 147 | raise RuntimeError(f"Existing image manifest is not a regular file: {path}") |
| 148 | try: |
| 149 | payload = json.loads(path.read_text(encoding="utf-8")) |
| 150 | except (OSError, json.JSONDecodeError) as exc: |
| 151 | raise RuntimeError( |
| 152 | f"Existing image manifest is unreadable: {path} ({exc}); " |
| 153 | "repair or restore it before importing more assets" |
| 154 | ) from exc |
| 155 | return _validate_image_manifest(payload, path) |
| 156 | |
| 157 | |
| 158 | def _write_json_atomic(path: Path, payload: object) -> None: |
| 159 | """Write JSON through a same-directory temporary file and atomic rename.""" |
| 160 | fd, temp_name = tempfile.mkstemp( |
| 161 | prefix=f"{path.stem}.", |
| 162 | suffix=".tmp", |
| 163 | dir=str(path.parent), |
| 164 | ) |
| 165 | try: |
| 166 | with os.fdopen(fd, "w", encoding="utf-8") as handle: |
| 167 | json.dump(payload, handle, ensure_ascii=False, indent=2) |
| 168 | handle.write("\n") |
| 169 | os.replace(temp_name, path) |
| 170 | except Exception: |
| 171 | try: |
| 172 | os.unlink(temp_name) |
| 173 | except OSError: |
| 174 | pass |
| 175 | raise |
| 176 | |
| 177 | |
| 178 | def is_url(value: str) -> bool: |
| 179 | """Return whether a string looks like an HTTP(S) URL.""" |
| 180 | parsed = urlparse(value) |
| 181 | return parsed.scheme in {"http", "https"} and bool(parsed.netloc) |
| 182 | |
| 183 | |
| 184 | def sanitize_name(value: str) -> str: |
| 185 | """Sanitize a user-facing name into a filesystem-safe token.""" |
| 186 | safe = "".join(ch if ch.isalnum() or ch in "-_." else "_" for ch in value.strip()) |
| 187 | safe = safe.strip("._") |
| 188 | while "__" in safe: |
| 189 | safe = safe.replace("__", "_") |
| 190 | return safe[:120] or "source" |
| 191 | |
| 192 | |
| 193 | def derive_url_basename(url: str) -> str: |
| 194 | """Derive a stable base filename from a URL.""" |
| 195 | parsed = urlparse(url) |
| 196 | parts = [sanitize_name(parsed.netloc)] |
| 197 | if parsed.path and parsed.path != "/": |
| 198 | path_part = sanitize_name(parsed.path.strip("/").replace("/", "_")) |
| 199 | if path_part: |
| 200 | parts.append(path_part) |
| 201 | return "_".join(part for part in parts if part) or "web_source" |
| 202 | |
| 203 | |
| 204 | def is_within_path(path: Path, parent: Path) -> bool: |
| 205 | """Return whether `path` resolves inside `parent`.""" |
| 206 | try: |
| 207 | path.resolve().relative_to(parent.resolve()) |
| 208 | return True |
| 209 | except ValueError: |
| 210 | return False |
| 211 | |
| 212 | |
| 213 | def _has_usable_import(summary: dict[str, list[str]]) -> bool: |
| 214 | """Return whether import-sources produced at least one usable source artifact.""" |
| 215 | return any( |
| 216 | summary.get(key) |
| 217 | for key in ("archived", "markdown", "assets", "images", "analysis") |
| 218 | ) |
| 219 | |
| 220 | |
| 221 | class ProjectManager: |
| 222 | """Create, inspect, validate, and populate project folders.""" |
| 223 | |
| 224 | CANVAS_FORMATS = CANVAS_FORMATS |
| 225 | |
| 226 | def __init__(self, base_dir: str | Path | None = None) -> None: |
| 227 | self.base_dir = Path(base_dir) if base_dir is not None else Path.cwd() / "projects" |
| 228 | |
| 229 | def scaffold_artifact(self, project_path: str, artifact: str) -> str: |
| 230 | """Delegate deterministic Markdown scaffold rendering.""" |
| 231 | return scaffold_project_artifact(Path(project_path), artifact) |
| 232 | |
| 233 | def init_project( |
| 234 | self, |
| 235 | project_name: str, |
| 236 | canvas_format: str = "ppt169", |
| 237 | base_dir: str | None = None, |
| 238 | *, |
| 239 | quick_generate: bool = False, |
| 240 | ) -> str: |
| 241 | base_path = Path(base_dir) if base_dir else self.base_dir |
| 242 | |
| 243 | if ( |
| 244 | not project_name |
| 245 | or project_name in {".", ".."} |
| 246 | or Path(project_name).is_absolute() |
| 247 | or "/" in project_name |
| 248 | or "\\" in project_name |
| 249 | ): |
| 250 | raise ValueError( |
| 251 | "Project name must be a single, non-absolute path component" |
| 252 | ) |
| 253 | |
| 254 | normalized_format = normalize_canvas_format(canvas_format) |
| 255 | if normalized_format not in self.CANVAS_FORMATS: |
| 256 | available = ", ".join(sorted(self.CANVAS_FORMATS.keys())) |
| 257 | raise ValueError( |
| 258 | f"Unsupported canvas format: {canvas_format} " |
| 259 | f"(available: {available}; common alias: xhs -> xiaohongshu)" |
| 260 | ) |
| 261 | |
| 262 | date_str = datetime.now().strftime("%Y%m%d") |
| 263 | # A name already carrying a `_<format>_<YYYYMMDD>` suffix (e.g. a full |
| 264 | # project dir name pasted back into init) is used as-is — re-appending |
| 265 | # would produce `name_ppt169_20260101_ppt169_20260102`. |
| 266 | if re.search(rf"_{re.escape(normalized_format)}_\d{{8}}$", project_name): |
| 267 | project_dir_name = project_name |
| 268 | else: |
| 269 | project_dir_name = f"{project_name}_{normalized_format}_{date_str}" |
| 270 | project_path = base_path / project_dir_name |
| 271 | |
| 272 | if not is_within_path(project_path, base_path): |
| 273 | raise ValueError( |
| 274 | f"Project directory must stay within the base directory: {base_path}" |
| 275 | ) |
| 276 | if project_path.exists(): |
| 277 | raise FileExistsError(f"Project directory already exists: {project_path}") |
| 278 | |
| 279 | project_dirs = ( |
| 280 | ("svg_output",) |
| 281 | if quick_generate |
| 282 | else ( |
| 283 | "svg_output", |
| 284 | "svg_final", |
| 285 | "images", |
| 286 | "icons", |
| 287 | "notes", |
| 288 | "templates", |
| 289 | "live_preview", |
| 290 | SOURCE_DIRNAME, |
| 291 | "analysis", |
| 292 | "validation", |
| 293 | "exports", |
| 294 | ) |
| 295 | ) |
| 296 | for rel_path in project_dirs: |
| 297 | (project_path / rel_path).mkdir(parents=True, exist_ok=True) |
| 298 | |
| 299 | canvas_info = self.CANVAS_FORMATS[normalized_format] |
| 300 | if not quick_generate: |
| 301 | readme_path = project_path / "README.md" |
| 302 | readme_path.write_text( |
| 303 | ( |
| 304 | f"# {project_name}\n\n" |
| 305 | f"- Canvas format: {normalized_format}\n" |
| 306 | f"- Created: {date_str}\n\n" |
| 307 | "## Directories\n\n" |
| 308 | "- `svg_output/`: raw SVG output\n" |
| 309 | "- `svg_final/`: self-contained SVG visual preview; may be inserted manually as an SVG image, but PowerPoint Convert to Shape is unsupported\n" |
| 310 | "- `images/`: runtime image pool; converter assets keep their original short filenames when possible\n" |
| 311 | "- `icons/`: project icon set — selected library icons copied in (via icon_sync.py) plus any custom icons you add; embedded from here at export\n" |
| 312 | "- `notes/`: speaker notes\n" |
| 313 | "- `templates/`: project templates\n" |
| 314 | "- `live_preview/`: browser preview runtime files and history (lock.json, server.log, edits.jsonl, annotations.jsonl)\n" |
| 315 | "- `sources/`: source materials and normalized markdown\n" |
| 316 | "- `analysis/`: machine-extracted intermediate analysis (PPTX intake, image_analysis.csv) — the pipeline's canonical must-read source/asset facts\n" |
| 317 | "- `validation/`: cold workflow audit log, SVG quality reports, and PPTX postflight audit reports\n" |
| 318 | "- `exports/`: final native DrawingML pptx deliverables only (timestamped); `_native_charts_tables.pptx` name with `--native-charts-and-tables`, `_narrated.pptx` name when narration audio is embedded\n" |
| 319 | "- `backup/<timestamp>/`: svg_output/ archive (always written in default-flow mode; safe to delete old timestamps)\n" |
| 320 | ), |
| 321 | encoding="utf-8", |
| 322 | ) |
| 323 | |
| 324 | print(f"Project created: {project_path}") |
| 325 | print(f"Canvas: {canvas_info['name']} ({canvas_info['dimensions']})") |
| 326 | return str(project_path) |
| 327 | |
| 328 | def _source_dir(self, project_path: Path) -> Path: |
| 329 | sources_dir = project_path / SOURCE_DIRNAME |
| 330 | sources_dir.mkdir(parents=True, exist_ok=True) |
| 331 | return sources_dir |
| 332 | |
| 333 | def _analysis_dir(self, project_path: Path) -> Path: |
| 334 | analysis_dir = project_path / "analysis" |
| 335 | analysis_dir.mkdir(parents=True, exist_ok=True) |
| 336 | return analysis_dir |
| 337 | |
| 338 | def _ensure_unique_path(self, path: Path) -> Path: |
| 339 | if not path.exists(): |
| 340 | return path |
| 341 | |
| 342 | suffix = path.suffix |
| 343 | stem = path.stem |
| 344 | counter = 2 |
| 345 | while True: |
| 346 | candidate = path.with_name(f"{stem}_{counter}{suffix}") |
| 347 | if not candidate.exists(): |
| 348 | return candidate |
| 349 | counter += 1 |
| 350 | |
| 351 | def _copy_or_move_file(self, source: Path, destination: Path, move: bool) -> Path: |
| 352 | try: |
| 353 | if source.resolve() == destination.resolve(): |
| 354 | return destination |
| 355 | except FileNotFoundError: |
| 356 | pass |
| 357 | |
| 358 | destination = self._ensure_unique_path(destination) |
| 359 | if move: |
| 360 | shutil.move(str(source), str(destination)) |
| 361 | else: |
| 362 | shutil.copy2(source, destination) |
| 363 | return destination |
| 364 | |
| 365 | def _copy_or_move_tree(self, source: Path, destination: Path, move: bool) -> Path: |
| 366 | try: |
| 367 | if source.resolve() == destination.resolve(): |
| 368 | return destination |
| 369 | except FileNotFoundError: |
| 370 | pass |
| 371 | |
| 372 | destination = self._ensure_unique_path(destination) |
| 373 | if move: |
| 374 | shutil.move(str(source), str(destination)) |
| 375 | else: |
| 376 | shutil.copytree(source, destination) |
| 377 | return destination |
| 378 | |
| 379 | def _run_tool(self, args: list[str]) -> None: |
| 380 | child_env = os.environ.copy() |
| 381 | child_env["PYTHONUTF8"] = "1" |
| 382 | child_env["PYTHONIOENCODING"] = "utf-8:replace" |
| 383 | try: |
| 384 | result = subprocess.run( |
| 385 | args, |
| 386 | cwd=REPO_ROOT, |
| 387 | check=True, |
| 388 | capture_output=True, |
| 389 | text=True, |
| 390 | encoding="utf-8", |
| 391 | errors="replace", |
| 392 | env=child_env, |
| 393 | ) |
| 394 | except FileNotFoundError as exc: |
| 395 | raise RuntimeError(f"Missing executable: {args[0]}") from exc |
| 396 | except subprocess.CalledProcessError as exc: |
| 397 | details = (exc.stderr or exc.stdout or "").strip() |
| 398 | raise RuntimeError(details or "tool execution failed") from exc |
| 399 | |
| 400 | if result.stdout.strip(): |
| 401 | print(result.stdout.strip()) |
| 402 | |
| 403 | def _import_pdf(self, pdf_path: Path, markdown_path: Path) -> None: |
| 404 | route = build_conversion_command( |
| 405 | str(pdf_path), |
| 406 | markdown_path, |
| 407 | forced_type="pdf", |
| 408 | ) |
| 409 | self._run_tool(route.command) |
| 410 | |
| 411 | def _import_doc(self, doc_path: Path, markdown_path: Path) -> None: |
| 412 | route = build_conversion_command( |
| 413 | str(doc_path), |
| 414 | markdown_path, |
| 415 | forced_type="doc", |
| 416 | ) |
| 417 | self._run_tool(route.command) |
| 418 | |
| 419 | def _import_presentation(self, presentation_path: Path, markdown_path: Path) -> None: |
| 420 | route = build_conversion_command( |
| 421 | str(presentation_path), |
| 422 | markdown_path, |
| 423 | forced_type="pptx", |
| 424 | ) |
| 425 | self._run_tool(route.command) |
| 426 | |
| 427 | def _import_pptx_intake(self, presentation_path: Path, project_dir: Path) -> Path: |
| 428 | # Multi-deck intake: each PPTX writes its own `<stem>.identity.json` / |
| 429 | # `<stem>.slide_library.json` and is merged into the single multi-deck |
| 430 | # index `analysis/source_profile.json` (one entry per source deck). |
| 431 | analysis_dir = self._analysis_dir(project_dir) |
| 432 | self._run_tool( |
| 433 | [ |
| 434 | sys.executable, |
| 435 | str(TOOLS_DIR / "pptx_intake.py"), |
| 436 | str(presentation_path), |
| 437 | "-o", |
| 438 | str(analysis_dir), |
| 439 | ] |
| 440 | ) |
| 441 | return analysis_dir |
| 442 | |
| 443 | def _import_excel(self, excel_path: Path, markdown_path: Path) -> None: |
| 444 | route = build_conversion_command( |
| 445 | str(excel_path), |
| 446 | markdown_path, |
| 447 | forced_type="excel", |
| 448 | ) |
| 449 | self._run_tool(route.command) |
| 450 | |
| 451 | def _import_url( |
| 452 | self, |
| 453 | url: str, |
| 454 | markdown_path: Path, |
| 455 | ) -> None: |
| 456 | route = build_conversion_command( |
| 457 | url, |
| 458 | markdown_path, |
| 459 | forced_type="web", |
| 460 | ) |
| 461 | self._run_tool(route.command) |
| 462 | |
| 463 | def _is_valid_imported_url_markdown(self, markdown_path: Path) -> bool: |
| 464 | """Return whether web_to_md produced a usable Markdown source.""" |
| 465 | if not markdown_path.is_file(): |
| 466 | return False |
| 467 | content = markdown_path.read_text(encoding="utf-8", errors="replace") |
| 468 | if "[Failed URLs]:" in content: |
| 469 | return False |
| 470 | return bool(content.strip()) |
| 471 | |
| 472 | def _archive_url_record(self, sources_dir: Path, url: str) -> Path: |
| 473 | file_path = self._ensure_unique_path(sources_dir / f"{derive_url_basename(url)}.url.txt") |
| 474 | file_path.write_text( |
| 475 | f"URL: {url}\nImported: {datetime.now().isoformat(timespec='seconds')}\n", |
| 476 | encoding="utf-8", |
| 477 | ) |
| 478 | return file_path |
| 479 | |
| 480 | def _normalize_text_source(self, source_path: Path, sources_dir: Path) -> Path: |
| 481 | target = self._ensure_unique_path(sources_dir / f"{source_path.stem}.md") |
| 482 | content = source_path.read_text(encoding="utf-8", errors="replace") |
| 483 | target.write_text(content, encoding="utf-8") |
| 484 | return target |
| 485 | |
| 486 | def _canonicalize_markdown_content(self, content: str) -> str: |
| 487 | canonical = content.replace("\r\n", "\n") |
| 488 | canonical = re.sub(r"(?m)^(\s*Crawled:\s+).*$", r"\1__IGNORED__", canonical) |
| 489 | canonical = re.sub(r"(?m)^(\s*Imported:\s+).*$", r"\1__IGNORED__", canonical) |
| 490 | canonical = re.sub(r"([^\s\]()/]+_files)/", "__ASSET_DIR__/", canonical) |
| 491 | return canonical.strip() |
| 492 | |
| 493 | def _find_equivalent_markdown(self, source_path: Path, sources_dir: Path) -> Path | None: |
| 494 | source_content = source_path.read_text(encoding="utf-8", errors="replace") |
| 495 | canonical_source = self._canonicalize_markdown_content(source_content) |
| 496 | |
| 497 | for existing in sorted(sources_dir.iterdir()): |
| 498 | if existing.suffix.lower() not in {".md", ".markdown"}: |
| 499 | continue |
| 500 | try: |
| 501 | if existing.resolve() == source_path.resolve(): |
| 502 | continue |
| 503 | except FileNotFoundError: |
| 504 | pass |
| 505 | |
| 506 | existing_content = existing.read_text(encoding="utf-8", errors="replace") |
| 507 | if self._canonicalize_markdown_content(existing_content) == canonical_source: |
| 508 | return existing |
| 509 | |
| 510 | return None |
| 511 | |
| 512 | def _companion_asset_dir(self, source_path: Path) -> Path | None: |
| 513 | candidate = source_path.with_name(f"{source_path.stem}_files") |
| 514 | if candidate.exists() and candidate.is_dir(): |
| 515 | return candidate |
| 516 | return None |
| 517 | |
| 518 | def _rewrite_markdown_asset_refs( |
| 519 | self, |
| 520 | markdown_path: Path, |
| 521 | original_asset_dirname: str, |
| 522 | imported_asset_dirname: str, |
| 523 | ) -> None: |
| 524 | if original_asset_dirname == imported_asset_dirname: |
| 525 | return |
| 526 | |
| 527 | content = markdown_path.read_text(encoding="utf-8", errors="replace") |
| 528 | updated = content.replace(f"{original_asset_dirname}/", f"{imported_asset_dirname}/") |
| 529 | if updated != content: |
| 530 | markdown_path.write_text(updated, encoding="utf-8") |
| 531 | |
| 532 | def _merge_image_manifest(self, source_items: list[dict], destination_manifest: Path) -> None: |
| 533 | """Merge per-source manifest items into the project-level manifest, keyed by filename.""" |
| 534 | _validate_image_manifest(source_items, destination_manifest) |
| 535 | existing_data = _read_existing_image_manifest(destination_manifest) |
| 536 | |
| 537 | new_by_filename: dict[str, dict] = {} |
| 538 | new_order: list[str] = [] |
| 539 | for item in source_items: |
| 540 | filename = item.get("filename") |
| 541 | if not isinstance(filename, str): |
| 542 | continue |
| 543 | normalized_filename = filename.casefold() |
| 544 | if normalized_filename not in new_by_filename: |
| 545 | new_order.append(normalized_filename) |
| 546 | new_by_filename[normalized_filename] = item |
| 547 | |
| 548 | merged: list[dict] = [] |
| 549 | seen: set[str] = set() |
| 550 | for item in existing_data: |
| 551 | if not isinstance(item, dict): |
| 552 | continue |
| 553 | filename = item.get("filename") |
| 554 | if not isinstance(filename, str): |
| 555 | continue |
| 556 | normalized_filename = filename.casefold() |
| 557 | if normalized_filename in new_by_filename: |
| 558 | merged.append(new_by_filename[normalized_filename]) |
| 559 | else: |
| 560 | merged.append(item) |
| 561 | seen.add(normalized_filename) |
| 562 | |
| 563 | for normalized_filename in new_order: |
| 564 | if normalized_filename not in seen: |
| 565 | merged.append(new_by_filename[normalized_filename]) |
| 566 | |
| 567 | _validate_image_manifest(merged, destination_manifest) |
| 568 | _write_json_atomic(destination_manifest, merged) |
| 569 | |
| 570 | @staticmethod |
| 571 | def _namespace_from_asset_dir(asset_dir: Path) -> str: |
| 572 | """Derive a per-source namespace from a `<stem>_files` companion directory name.""" |
| 573 | name = asset_dir.name |
| 574 | suffix = "_files" |
| 575 | return name[:-len(suffix)] if name.endswith(suffix) else name |
| 576 | |
| 577 | def _image_destination_name( |
| 578 | self, |
| 579 | images_dir: Path, |
| 580 | source_file: Path, |
| 581 | namespace: str, |
| 582 | existing_manifest: dict[str, dict], |
| 583 | occupied_names: set[str], |
| 584 | ) -> str: |
| 585 | """Return a short unique image filename for the runtime image pool.""" |
| 586 | candidate = images_dir / source_file.name |
| 587 | if candidate.name.casefold() not in occupied_names: |
| 588 | return source_file.name |
| 589 | try: |
| 590 | meta = existing_manifest.get(candidate.name, {}) |
| 591 | if ( |
| 592 | meta.get("source_namespace") == namespace |
| 593 | and candidate.is_file() |
| 594 | and filecmp.cmp(source_file, candidate, shallow=False) |
| 595 | ): |
| 596 | return candidate.name |
| 597 | except OSError: |
| 598 | pass |
| 599 | |
| 600 | stem = source_file.stem |
| 601 | suffix = source_file.suffix |
| 602 | counter = 2 |
| 603 | while True: |
| 604 | candidate = images_dir / f"{stem}_{counter}{suffix}" |
| 605 | if candidate.name.casefold() not in occupied_names: |
| 606 | return candidate.name |
| 607 | try: |
| 608 | meta = existing_manifest.get(candidate.name, {}) |
| 609 | if ( |
| 610 | meta.get("source_namespace") == namespace |
| 611 | and candidate.is_file() |
| 612 | and filecmp.cmp(source_file, candidate, shallow=False) |
| 613 | ): |
| 614 | return candidate.name |
| 615 | except OSError: |
| 616 | pass |
| 617 | counter += 1 |
| 618 | |
| 619 | def _propagate_image_assets(self, asset_dir: Path, project_dir: Path) -> None: |
| 620 | """Copy converter-generated image assets and manifest into project images/. |
| 621 | |
| 622 | Filenames are preserved when possible because source Markdown commonly |
| 623 | uses short names that are meaningful in context. Only real collisions |
| 624 | receive a compact numeric suffix. |
| 625 | """ |
| 626 | manifest_path = asset_dir / "image_manifest.json" |
| 627 | if not manifest_path.is_file(): |
| 628 | return |
| 629 | |
| 630 | try: |
| 631 | source_payload = json.loads(manifest_path.read_text(encoding="utf-8")) |
| 632 | except (OSError, json.JSONDecodeError) as exc: |
| 633 | print(f"[WARN] Cannot read image manifest {manifest_path}: {exc}") |
| 634 | return |
| 635 | try: |
| 636 | source_data = _validate_image_manifest(source_payload, manifest_path) |
| 637 | except RuntimeError as exc: |
| 638 | print(f"[WARN] {exc}") |
| 639 | return |
| 640 | |
| 641 | images_dir = project_dir / "images" |
| 642 | namespace = self._namespace_from_asset_dir(asset_dir) |
| 643 | destination_manifest = images_dir / "image_manifest.json" |
| 644 | existing_data = _read_existing_image_manifest(destination_manifest) |
| 645 | images_dir.mkdir(parents=True, exist_ok=True) |
| 646 | |
| 647 | existing_manifest = { |
| 648 | item["filename"]: item |
| 649 | for item in existing_data |
| 650 | } |
| 651 | occupied_names = { |
| 652 | path.name.casefold() |
| 653 | for path in images_dir.iterdir() |
| 654 | if path.is_file() |
| 655 | } |
| 656 | rename_map: dict[str, str] = {} |
| 657 | |
| 658 | copied_count = 0 |
| 659 | for source_file in sorted(asset_dir.iterdir()): |
| 660 | if not source_file.is_file(): |
| 661 | continue |
| 662 | if source_file.suffix.lower() not in IMAGE_ASSET_SUFFIXES: |
| 663 | continue |
| 664 | new_name = self._image_destination_name( |
| 665 | images_dir, |
| 666 | source_file, |
| 667 | namespace, |
| 668 | existing_manifest, |
| 669 | occupied_names, |
| 670 | ) |
| 671 | destination = images_dir / new_name |
| 672 | if source_file.resolve() != destination.resolve(): |
| 673 | shutil.copy2(source_file, destination) |
| 674 | occupied_names.add(new_name.casefold()) |
| 675 | rename_map[source_file.name] = new_name |
| 676 | copied_count += 1 |
| 677 | |
| 678 | rebased_items: list[dict] = [] |
| 679 | for item in source_data: |
| 680 | if not isinstance(item, dict): |
| 681 | continue |
| 682 | original = item.get("filename") |
| 683 | if not isinstance(original, str): |
| 684 | continue |
| 685 | new_item = dict(item) |
| 686 | new_item["filename"] = rename_map.get(original, original) |
| 687 | new_item["source_namespace"] = namespace |
| 688 | rebased_items.append(new_item) |
| 689 | |
| 690 | self._merge_image_manifest(rebased_items, images_dir / "image_manifest.json") |
| 691 | print( |
| 692 | f"Propagated {copied_count} image asset(s) + manifest " |
| 693 | f"from {asset_dir} → images/ (namespace: {namespace})" |
| 694 | ) |
| 695 | |
| 696 | def _propagate_companion_image_assets(self, markdown_path: Path, project_dir: Path) -> None: |
| 697 | asset_dir = markdown_path.with_name(f"{markdown_path.stem}_files") |
| 698 | if asset_dir.is_dir(): |
| 699 | self._propagate_image_assets(asset_dir, project_dir) |
| 700 | |
| 701 | def _import_markdown_with_assets( |
| 702 | self, |
| 703 | source_path: Path, |
| 704 | sources_dir: Path, |
| 705 | move: bool, |
| 706 | ) -> tuple[Path, Path | None, str | None]: |
| 707 | archived_markdown = self._copy_or_move_file( |
| 708 | source_path, |
| 709 | sources_dir / source_path.name, |
| 710 | move=move, |
| 711 | ) |
| 712 | |
| 713 | profile_src = source_path.with_name(f"{source_path.stem}.conversion_profile.json") |
| 714 | if profile_src.is_file(): |
| 715 | self._copy_or_move_file( |
| 716 | profile_src, |
| 717 | sources_dir / f"{archived_markdown.stem}.conversion_profile.json", |
| 718 | move=move, |
| 719 | ) |
| 720 | |
| 721 | asset_dir = self._companion_asset_dir(source_path) |
| 722 | if asset_dir is None: |
| 723 | return archived_markdown, None, None |
| 724 | |
| 725 | imported_asset_dir = self._copy_or_move_tree( |
| 726 | asset_dir, |
| 727 | sources_dir / f"{archived_markdown.stem}_files", |
| 728 | move=move, |
| 729 | ) |
| 730 | self._rewrite_markdown_asset_refs( |
| 731 | archived_markdown, |
| 732 | original_asset_dirname=asset_dir.name, |
| 733 | imported_asset_dirname=imported_asset_dir.name, |
| 734 | ) |
| 735 | |
| 736 | note = None |
| 737 | if archived_markdown.stem != source_path.stem: |
| 738 | note = ( |
| 739 | f"{source_path}: renamed imported markdown to {archived_markdown.name} " |
| 740 | f"and rewrote asset references to {imported_asset_dir.name}/" |
| 741 | ) |
| 742 | return archived_markdown, imported_asset_dir, note |
| 743 | |
| 744 | def import_sources( |
| 745 | self, |
| 746 | project_path: str, |
| 747 | source_items: list[str], |
| 748 | move: bool = False, |
| 749 | copy: bool = False, |
| 750 | ) -> dict[str, list[str]]: |
| 751 | if move and copy: |
| 752 | raise ValueError("--move and --copy are mutually exclusive") |
| 753 | project_dir = Path(project_path) |
| 754 | if not project_dir.exists() or not project_dir.is_dir(): |
| 755 | raise FileNotFoundError(f"Project directory not found: {project_dir}") |
| 756 | if not source_items: |
| 757 | raise ValueError("At least one source path or URL is required") |
| 758 | |
| 759 | sources_dir = self._source_dir(project_dir) |
| 760 | summary: dict[str, list[str]] = { |
| 761 | "archived": [], |
| 762 | "url_records": [], |
| 763 | "markdown": [], |
| 764 | "assets": [], |
| 765 | "images": [], |
| 766 | "analysis": [], |
| 767 | "notes": [], |
| 768 | "skipped": [], |
| 769 | } |
| 770 | |
| 771 | expanded_items: list[str] = [] |
| 772 | supplied_dirs: list[Path] = [] |
| 773 | for item in source_items: |
| 774 | if is_url(item): |
| 775 | expanded_items.append(item) |
| 776 | continue |
| 777 | item_path = Path(item) |
| 778 | if item_path.is_dir(): |
| 779 | supplied_dirs.append(item_path) |
| 780 | directory_files = sorted( |
| 781 | path for path in item_path.iterdir() if path.is_file() |
| 782 | ) |
| 783 | if directory_files: |
| 784 | expanded_items.extend(str(path) for path in directory_files) |
| 785 | summary["notes"].append( |
| 786 | f"{item}: expanded directory into {len(directory_files)} file(s)" |
| 787 | ) |
| 788 | else: |
| 789 | summary["skipped"].append(f"{item}: directory contains no files") |
| 790 | continue |
| 791 | expanded_items.append(item) |
| 792 | |
| 793 | explicit_markdown_stems = { |
| 794 | Path(item).stem |
| 795 | for item in expanded_items |
| 796 | if not is_url(item) |
| 797 | and Path(item).exists() |
| 798 | and Path(item).is_file() |
| 799 | and Path(item).suffix.lower() in {".md", ".markdown"} |
| 800 | } |
| 801 | |
| 802 | for item in expanded_items: |
| 803 | if is_url(item): |
| 804 | markdown_path = self._ensure_unique_path( |
| 805 | sources_dir / f"{derive_url_basename(item)}.md" |
| 806 | ) |
| 807 | try: |
| 808 | self._import_url(item, markdown_path) |
| 809 | except Exception as exc: # pragma: no cover - summary path |
| 810 | archived = self._archive_url_record(sources_dir, item) |
| 811 | summary["url_records"].append(str(archived)) |
| 812 | summary["skipped"].append(f"{item}: {exc}") |
| 813 | continue |
| 814 | |
| 815 | if not self._is_valid_imported_url_markdown(markdown_path): |
| 816 | markdown_path.unlink(missing_ok=True) |
| 817 | archived = self._archive_url_record(sources_dir, item) |
| 818 | summary["url_records"].append(str(archived)) |
| 819 | summary["skipped"].append(f"{item}: URL conversion produced no usable Markdown") |
| 820 | continue |
| 821 | |
| 822 | summary["markdown"].append(str(markdown_path)) |
| 823 | self._propagate_companion_image_assets(markdown_path, project_dir) |
| 824 | continue |
| 825 | |
| 826 | source_path = Path(item) |
| 827 | if not source_path.exists(): |
| 828 | summary["skipped"].append(f"{item}: path not found") |
| 829 | continue |
| 830 | if source_path.is_dir(): |
| 831 | summary["skipped"].append(f"{item}: directories are not supported") |
| 832 | continue |
| 833 | |
| 834 | inside_projects = is_within_path(source_path, PROJECTS_ROOT) |
| 835 | if copy: |
| 836 | effective_move = False |
| 837 | elif inside_projects: |
| 838 | effective_move = True |
| 839 | else: |
| 840 | effective_move = False |
| 841 | if move and not inside_projects: |
| 842 | print( |
| 843 | f"note: {source_path} is outside {PROJECTS_ROOT}; copied " |
| 844 | f"(not moved). Only sources under projects/ may be moved.", |
| 845 | file=sys.stderr, |
| 846 | ) |
| 847 | elif inside_projects and not move and not copy: |
| 848 | print( |
| 849 | f"note: {source_path} is under projects/; moved into the target " |
| 850 | f"project. Pass --copy to preserve it.", |
| 851 | file=sys.stderr, |
| 852 | ) |
| 853 | suffix = source_path.suffix.lower() |
| 854 | |
| 855 | if suffix in {".md", ".markdown"}: |
| 856 | duplicate_markdown = self._find_equivalent_markdown(source_path, sources_dir) |
| 857 | if duplicate_markdown is not None: |
| 858 | summary["markdown"].append(str(duplicate_markdown)) |
| 859 | self._propagate_companion_image_assets(duplicate_markdown, project_dir) |
| 860 | summary["notes"].append( |
| 861 | f"{item}: skipped duplicate markdown import because equivalent content already exists as {duplicate_markdown.name}" |
| 862 | ) |
| 863 | continue |
| 864 | |
| 865 | archived_markdown, asset_dir, note = self._import_markdown_with_assets( |
| 866 | source_path, |
| 867 | sources_dir, |
| 868 | move=effective_move, |
| 869 | ) |
| 870 | summary["archived"].append(str(archived_markdown)) |
| 871 | summary["markdown"].append(str(archived_markdown)) |
| 872 | if asset_dir is not None: |
| 873 | summary["assets"].append(str(asset_dir)) |
| 874 | self._propagate_image_assets(asset_dir, project_dir) |
| 875 | if note: |
| 876 | summary["notes"].append(note) |
| 877 | continue |
| 878 | |
| 879 | archived_path = self._copy_or_move_file( |
| 880 | source_path, |
| 881 | sources_dir / source_path.name, |
| 882 | move=effective_move, |
| 883 | ) |
| 884 | summary["archived"].append(str(archived_path)) |
| 885 | |
| 886 | if suffix in BITMAP_IMAGE_SUFFIXES: |
| 887 | images_dir = project_dir / "images" |
| 888 | images_dir.mkdir(parents=True, exist_ok=True) |
| 889 | image_path = self._ensure_unique_path(images_dir / archived_path.name) |
| 890 | shutil.copy2(archived_path, image_path) |
| 891 | summary["images"].append(str(image_path)) |
| 892 | if image_path.name != archived_path.name: |
| 893 | summary["notes"].append( |
| 894 | f"{item}: copied runtime image as {image_path.name} " |
| 895 | "to avoid a filename collision" |
| 896 | ) |
| 897 | elif suffix in PDF_SUFFIXES: |
| 898 | canonical_markdown_path = sources_dir / f"{archived_path.stem}.md" |
| 899 | if archived_path.stem in explicit_markdown_stems: |
| 900 | summary["notes"].append( |
| 901 | f"{item}: skipped PDF auto-conversion because a same-stem Markdown source was provided" |
| 902 | ) |
| 903 | continue |
| 904 | if canonical_markdown_path.exists(): |
| 905 | summary["markdown"].append(str(canonical_markdown_path)) |
| 906 | self._propagate_companion_image_assets(canonical_markdown_path, project_dir) |
| 907 | summary["notes"].append( |
| 908 | f"{item}: skipped PDF auto-conversion because {canonical_markdown_path.name} already exists" |
| 909 | ) |
| 910 | continue |
| 911 | markdown_path = canonical_markdown_path |
| 912 | try: |
| 913 | self._import_pdf(archived_path, markdown_path) |
| 914 | summary["markdown"].append(str(markdown_path)) |
| 915 | self._propagate_companion_image_assets(markdown_path, project_dir) |
| 916 | except Exception as exc: # pragma: no cover - summary path |
| 917 | summary["skipped"].append(f"{item}: PDF conversion failed ({exc})") |
| 918 | elif suffix in PRESENTATION_SUFFIXES: |
| 919 | canonical_markdown_path = sources_dir / f"{archived_path.stem}.md" |
| 920 | try: |
| 921 | intake_dir = self._import_pptx_intake(archived_path, project_dir) |
| 922 | intake_str = str(intake_dir) |
| 923 | if intake_str not in summary["analysis"]: |
| 924 | summary["analysis"].append(intake_str) |
| 925 | except Exception as exc: # pragma: no cover - summary path |
| 926 | summary["notes"].append(f"{item}: PPTX intake analysis failed ({exc})") |
| 927 | if archived_path.stem in explicit_markdown_stems: |
| 928 | summary["notes"].append( |
| 929 | f"{item}: skipped presentation auto-conversion because a same-stem Markdown source was provided" |
| 930 | ) |
| 931 | continue |
| 932 | if canonical_markdown_path.exists(): |
| 933 | summary["markdown"].append(str(canonical_markdown_path)) |
| 934 | self._propagate_companion_image_assets(canonical_markdown_path, project_dir) |
| 935 | summary["notes"].append( |
| 936 | f"{item}: skipped presentation auto-conversion because {canonical_markdown_path.name} already exists" |
| 937 | ) |
| 938 | continue |
| 939 | markdown_path = canonical_markdown_path |
| 940 | try: |
| 941 | self._import_presentation(archived_path, markdown_path) |
| 942 | summary["markdown"].append(str(markdown_path)) |
| 943 | self._propagate_companion_image_assets(markdown_path, project_dir) |
| 944 | except Exception as exc: # pragma: no cover - summary path |
| 945 | summary["skipped"].append(f"{item}: presentation conversion failed ({exc})") |
| 946 | elif suffix in EXCEL_SUFFIXES: |
| 947 | canonical_markdown_path = sources_dir / f"{archived_path.stem}.md" |
| 948 | if archived_path.stem in explicit_markdown_stems: |
| 949 | summary["notes"].append( |
| 950 | f"{item}: skipped Excel auto-conversion because a same-stem Markdown source was provided" |
| 951 | ) |
| 952 | continue |
| 953 | if canonical_markdown_path.exists(): |
| 954 | summary["markdown"].append(str(canonical_markdown_path)) |
| 955 | self._propagate_companion_image_assets(canonical_markdown_path, project_dir) |
| 956 | summary["notes"].append( |
| 957 | f"{item}: skipped Excel auto-conversion because {canonical_markdown_path.name} already exists" |
| 958 | ) |
| 959 | continue |
| 960 | markdown_path = canonical_markdown_path |
| 961 | try: |
| 962 | self._import_excel(archived_path, markdown_path) |
| 963 | summary["markdown"].append(str(markdown_path)) |
| 964 | self._propagate_companion_image_assets(markdown_path, project_dir) |
| 965 | except Exception as exc: # pragma: no cover - summary path |
| 966 | summary["skipped"].append(f"{item}: Excel conversion failed ({exc})") |
| 967 | elif suffix in LEGACY_EXCEL_SUFFIXES: |
| 968 | summary["notes"].append( |
| 969 | f"{item}: archived only; legacy .xls is not converted automatically. " |
| 970 | "Resave as .xlsx to generate Markdown." |
| 971 | ) |
| 972 | elif suffix in TABLE_TEXT_SUFFIXES: |
| 973 | summary["notes"].append( |
| 974 | f"{item}: archived as a plain-text table source; no Markdown conversion needed" |
| 975 | ) |
| 976 | elif suffix in DOC_SUFFIXES: |
| 977 | canonical_markdown_path = sources_dir / f"{archived_path.stem}.md" |
| 978 | if archived_path.stem in explicit_markdown_stems: |
| 979 | summary["notes"].append( |
| 980 | f"{item}: skipped document auto-conversion because a same-stem Markdown source was provided" |
| 981 | ) |
| 982 | continue |
| 983 | if canonical_markdown_path.exists(): |
| 984 | summary["markdown"].append(str(canonical_markdown_path)) |
| 985 | self._propagate_companion_image_assets(canonical_markdown_path, project_dir) |
| 986 | summary["notes"].append( |
| 987 | f"{item}: skipped document auto-conversion because {canonical_markdown_path.name} already exists" |
| 988 | ) |
| 989 | continue |
| 990 | markdown_path = canonical_markdown_path |
| 991 | try: |
| 992 | self._import_doc(archived_path, markdown_path) |
| 993 | summary["markdown"].append(str(markdown_path)) |
| 994 | self._propagate_companion_image_assets(markdown_path, project_dir) |
| 995 | except Exception as exc: # pragma: no cover - summary path |
| 996 | summary["skipped"].append(f"{item}: document conversion failed ({exc})") |
| 997 | elif suffix == ".txt": |
| 998 | markdown_path = self._normalize_text_source(archived_path, sources_dir) |
| 999 | summary["markdown"].append(str(markdown_path)) |
| 1000 | else: |
| 1001 | summary["notes"].append(f"{item}: archived only, no automatic conversion") |
| 1002 | |
| 1003 | # Cleanup: only a projects-local source directory may be removed after |
| 1004 | # its files move into the target project. Every other location is copied |
| 1005 | # and remains untouched, even when the caller passes --move. |
| 1006 | for directory in supplied_dirs: |
| 1007 | if copy or not is_within_path(directory, PROJECTS_ROOT): |
| 1008 | continue |
| 1009 | if directory.is_dir() and not any(directory.iterdir()): |
| 1010 | try: |
| 1011 | directory.rmdir() |
| 1012 | except OSError: |
| 1013 | continue |
| 1014 | summary["notes"].append( |
| 1015 | f"{directory}: removed empty source directory after import" |
| 1016 | ) |
| 1017 | |
| 1018 | return summary |
| 1019 | |
| 1020 | def validate_project(self, project_path: str) -> tuple[bool, list[str], list[str]]: |
| 1021 | project_path_obj = Path(project_path) |
| 1022 | _, errors, warnings = validate_project_structure( |
| 1023 | str(project_path_obj), |
| 1024 | validate_communication=False, |
| 1025 | ) |
| 1026 | |
| 1027 | if project_path_obj.exists() and project_path_obj.is_dir(): |
| 1028 | project_info = get_project_info_common(str(project_path_obj)) |
| 1029 | artifact_errors, artifact_warnings = validate_project_artifacts( |
| 1030 | project_path_obj, |
| 1031 | project_info, |
| 1032 | ) |
| 1033 | errors.extend(artifact_errors) |
| 1034 | warnings.extend(artifact_warnings) |
| 1035 | |
| 1036 | if project_path_obj.exists() and project_path_obj.is_dir(): |
| 1037 | info = get_project_info_common(str(project_path_obj)) |
| 1038 | if info.get("svg_files"): |
| 1039 | svg_files = [project_path_obj / "svg_output" / name for name in info["svg_files"]] |
| 1040 | expected_format = info.get("format") |
| 1041 | if expected_format == "unknown": |
| 1042 | expected_format = None |
| 1043 | warnings.extend(validate_svg_viewbox(svg_files, expected_format)) |
| 1044 | |
| 1045 | return not errors, list(dict.fromkeys(errors)), warnings |
| 1046 | |
| 1047 | def get_project_info(self, project_path: str) -> dict[str, object]: |
| 1048 | shared = get_project_info_common(project_path) |
| 1049 | return { |
| 1050 | "name": shared.get("name", Path(project_path).name), |
| 1051 | "path": shared.get("path", str(project_path)), |
| 1052 | "exists": shared.get("exists", False), |
| 1053 | "svg_count": shared.get("svg_count", 0), |
| 1054 | "has_spec": shared.get("has_spec", False), |
| 1055 | "has_source": shared.get("has_source", False), |
| 1056 | "source_count": shared.get("source_count", 0), |
| 1057 | "canvas_format": shared.get("format_name", "Unknown"), |
| 1058 | "create_date": shared.get("date_formatted", "Unknown"), |
| 1059 | } |
| 1060 | |
| 1061 | |
| 1062 | def build_parser() -> argparse.ArgumentParser: |
| 1063 | """Build the command-line parser.""" |
| 1064 | parser = argparse.ArgumentParser( |
| 1065 | description="PPT Master project management helpers.", |
| 1066 | formatter_class=argparse.RawDescriptionHelpFormatter, |
| 1067 | epilog="""Examples: |
| 1068 | python3 scripts/project_manager.py init demo --format ppt169 |
| 1069 | python3 scripts/project_manager.py import-sources projects/demo file.md |
| 1070 | python3 scripts/project_manager.py scaffold-spec projects/demo_ppt169_20260718 |
| 1071 | python3 scripts/project_manager.py scaffold-lock projects/demo_ppt169_20260718 |
| 1072 | python3 scripts/project_manager.py validate projects/demo |
| 1073 | python3 scripts/project_manager.py info projects/demo |
| 1074 | python3 scripts/project_manager.py page-context projects/demo P07 --record-usage |
| 1075 | python3 scripts/project_manager.py page-context-report projects/demo |
| 1076 | """, |
| 1077 | ) |
| 1078 | subparsers = parser.add_subparsers(dest="command", required=True) |
| 1079 | |
| 1080 | init = subparsers.add_parser("init", help="Create a project directory") |
| 1081 | init.add_argument("project_name", help="Project name") |
| 1082 | init.add_argument("--format", default="ppt169", help="Canvas format (default: ppt169)") |
| 1083 | init.add_argument("--dir", default=None, help="Base directory for the project") |
| 1084 | init.add_argument( |
| 1085 | "--quick-generate", |
| 1086 | action="store_true", |
| 1087 | help=( |
| 1088 | "Create svg_output plus the validation workflow audit log and " |
| 1089 | "omit README.md" |
| 1090 | ), |
| 1091 | ) |
| 1092 | |
| 1093 | import_sources = subparsers.add_parser( |
| 1094 | "import-sources", |
| 1095 | help="Import source files or URLs into a project", |
| 1096 | ) |
| 1097 | import_sources.add_argument("project_path", help="Project directory") |
| 1098 | import_sources.add_argument("sources", nargs="+", help="Source files, directories, or URLs") |
| 1099 | mode = import_sources.add_mutually_exclusive_group() |
| 1100 | mode.add_argument( |
| 1101 | "--move", |
| 1102 | action="store_true", |
| 1103 | help="Move local sources under projects/; sources elsewhere are copied", |
| 1104 | ) |
| 1105 | mode.add_argument("--copy", action="store_true", help="Copy local source files") |
| 1106 | |
| 1107 | scaffold_spec = subparsers.add_parser( |
| 1108 | "scaffold-spec", |
| 1109 | help="Create design_spec.md from the versioned scaffold", |
| 1110 | ) |
| 1111 | scaffold_spec.add_argument("project_path", help="Project directory") |
| 1112 | |
| 1113 | scaffold_lock = subparsers.add_parser( |
| 1114 | "scaffold-lock", |
| 1115 | help="Create spec_lock.md from the versioned scaffold", |
| 1116 | ) |
| 1117 | scaffold_lock.add_argument("project_path", help="Project directory") |
| 1118 | |
| 1119 | validate = subparsers.add_parser("validate", help="Validate a project directory") |
| 1120 | validate.add_argument("project_path", help="Project directory") |
| 1121 | |
| 1122 | info = subparsers.add_parser("info", help="Print project metadata") |
| 1123 | info.add_argument("project_path", help="Project directory") |
| 1124 | |
| 1125 | page_context = subparsers.add_parser( |
| 1126 | "page-context", |
| 1127 | help="Print one deterministic per-page execution view", |
| 1128 | ) |
| 1129 | page_context.add_argument("project_path", help="Project directory") |
| 1130 | page_context.add_argument("page", help="Positive page key such as P07") |
| 1131 | page_context.add_argument( |
| 1132 | "--bundle", |
| 1133 | action="store_true", |
| 1134 | help="Deprecated compatibility flag; output remains compact", |
| 1135 | ) |
| 1136 | page_context.add_argument( |
| 1137 | "--pretty", |
| 1138 | action="store_true", |
| 1139 | help="Pretty-print the page-context JSON payload", |
| 1140 | ) |
| 1141 | page_context.add_argument( |
| 1142 | "--record-usage", |
| 1143 | action="store_true", |
| 1144 | help="Write compact-output token telemetry under analysis/page-context/", |
| 1145 | ) |
| 1146 | |
| 1147 | page_context_report = subparsers.add_parser( |
| 1148 | "page-context-report", |
| 1149 | help="Summarize fresh per-page context telemetry", |
| 1150 | ) |
| 1151 | page_context_report.add_argument("project_path", help="Project directory") |
| 1152 | return parser |
| 1153 | |
| 1154 | |
| 1155 | def main(argv: list[str] | None = None) -> int: |
| 1156 | """Run the CLI entry point.""" |
| 1157 | require_skill_integrity() |
| 1158 | parser = build_parser() |
| 1159 | args = parser.parse_args(argv) |
| 1160 | manager = ProjectManager() |
| 1161 | |
| 1162 | try: |
| 1163 | if args.command == "init": |
| 1164 | project_path = manager.init_project( |
| 1165 | args.project_name, |
| 1166 | args.format, |
| 1167 | base_dir=args.dir, |
| 1168 | quick_generate=args.quick_generate, |
| 1169 | ) |
| 1170 | print(f"[OK] Project initialized: {project_path}") |
| 1171 | print("Next:") |
| 1172 | if args.quick_generate: |
| 1173 | print("1. Generate SVG files into svg_output/") |
| 1174 | print("2. Run the Quick Generate final checker and exporter") |
| 1175 | profile = "quick" |
| 1176 | else: |
| 1177 | print("1. Put source files into sources/ (or use import-sources)") |
| 1178 | print("2. Save your design spec to the project root") |
| 1179 | print("3. Generate SVG files into svg_output/") |
| 1180 | profile = "default" |
| 1181 | try: |
| 1182 | append_note( |
| 1183 | project_path, |
| 1184 | f"Project initialized: profile={profile}; " |
| 1185 | f"canvas={args.format}; path={project_path}", |
| 1186 | ) |
| 1187 | except OSError as exc: |
| 1188 | print( |
| 1189 | f"[WARN] Workflow audit unavailable: {exc}", |
| 1190 | file=sys.stderr, |
| 1191 | ) |
| 1192 | return 0 |
| 1193 | |
| 1194 | if args.command == "import-sources": |
| 1195 | summary = manager.import_sources( |
| 1196 | args.project_path, |
| 1197 | args.sources, |
| 1198 | move=args.move, |
| 1199 | copy=args.copy, |
| 1200 | ) |
| 1201 | import_complete = _has_usable_import(summary) |
| 1202 | if import_complete: |
| 1203 | print(f"[OK] Imported sources into: {args.project_path}") |
| 1204 | else: |
| 1205 | print( |
| 1206 | f"[ERROR] No usable sources imported into: {args.project_path}", |
| 1207 | file=sys.stderr, |
| 1208 | ) |
| 1209 | if summary["archived"]: |
| 1210 | print("\nArchived originals:") |
| 1211 | for item in summary["archived"]: |
| 1212 | print(f" - {item}") |
| 1213 | if summary["url_records"]: |
| 1214 | print("\nArchived URL records:") |
| 1215 | for item in summary["url_records"]: |
| 1216 | print(f" - {item}") |
| 1217 | if summary["markdown"]: |
| 1218 | print("\nNormalized markdown:") |
| 1219 | for item in summary["markdown"]: |
| 1220 | print(f" - {item}") |
| 1221 | if summary["assets"]: |
| 1222 | print("\nImported asset directories:") |
| 1223 | for item in summary["assets"]: |
| 1224 | print(f" - {item}") |
| 1225 | if summary["images"]: |
| 1226 | print("\nRuntime image copies:") |
| 1227 | for item in summary["images"]: |
| 1228 | print(f" - {item}") |
| 1229 | if summary["analysis"]: |
| 1230 | print("\nAnalysis artifacts:") |
| 1231 | for item in summary["analysis"]: |
| 1232 | print(f" - {item}") |
| 1233 | if summary["notes"]: |
| 1234 | print("\nNotes:") |
| 1235 | for item in summary["notes"]: |
| 1236 | print(f" - {item}") |
| 1237 | if summary["skipped"]: |
| 1238 | print("\nSkipped:") |
| 1239 | for item in summary["skipped"]: |
| 1240 | print(f" - {item}") |
| 1241 | return 0 if import_complete else 1 |
| 1242 | |
| 1243 | if args.command == "scaffold-spec": |
| 1244 | artifact_path = manager.scaffold_artifact(args.project_path, "design_spec") |
| 1245 | print(f"[OK] Design spec scaffold created: {artifact_path}") |
| 1246 | return 0 |
| 1247 | |
| 1248 | if args.command == "scaffold-lock": |
| 1249 | artifact_path = manager.scaffold_artifact(args.project_path, "spec_lock") |
| 1250 | print(f"[OK] Execution lock scaffold created: {artifact_path}") |
| 1251 | return 0 |
| 1252 | |
| 1253 | if args.command == "validate": |
| 1254 | project_path = args.project_path |
| 1255 | is_valid, errors, warnings = manager.validate_project(project_path) |
| 1256 | |
| 1257 | print(f"\nProject validation: {project_path}") |
| 1258 | print("=" * 60) |
| 1259 | |
| 1260 | if errors: |
| 1261 | print("\n[ERROR]") |
| 1262 | for error in errors: |
| 1263 | print(f" - {error}") |
| 1264 | |
| 1265 | if warnings: |
| 1266 | print("\n[WARN]") |
| 1267 | for warning in warnings: |
| 1268 | print(f" - {warning}") |
| 1269 | |
| 1270 | if is_valid and not warnings: |
| 1271 | print("\n[OK] Project structure is complete.") |
| 1272 | elif is_valid: |
| 1273 | print("\n[OK] Project structure is valid, with warnings.") |
| 1274 | else: |
| 1275 | print("\n[ERROR] Project structure is invalid.") |
| 1276 | return 1 |
| 1277 | return 0 |
| 1278 | |
| 1279 | if args.command == "info": |
| 1280 | project_path = args.project_path |
| 1281 | info = manager.get_project_info(project_path) |
| 1282 | |
| 1283 | print(f"\nProject info: {info['name']}") |
| 1284 | print("=" * 60) |
| 1285 | print(f"Path: {info['path']}") |
| 1286 | print(f"Exists: {'Yes' if info['exists'] else 'No'}") |
| 1287 | print(f"SVG files: {info['svg_count']}") |
| 1288 | print(f"Design spec: {'Yes' if info['has_spec'] else 'No'}") |
| 1289 | print(f"Source materials: {'Yes' if info['has_source'] else 'No'}") |
| 1290 | print(f"Source count: {info['source_count']}") |
| 1291 | print(f"Canvas format: {info['canvas_format']}") |
| 1292 | print(f"Created: {info['create_date']}") |
| 1293 | return 0 |
| 1294 | |
| 1295 | if args.command == "page-context": |
| 1296 | result = build_page_context(args.project_path, args.page) |
| 1297 | output, measured_reads = render_page_context( |
| 1298 | result, |
| 1299 | bundle=args.bundle, |
| 1300 | pretty=args.pretty, |
| 1301 | ) |
| 1302 | if args.record_usage: |
| 1303 | _usage_path, token_status = record_page_context_usage( |
| 1304 | result, |
| 1305 | output, |
| 1306 | measured_reads, |
| 1307 | ) |
| 1308 | if token_status != "exact": |
| 1309 | print( |
| 1310 | "[WARN] tiktoken/o200k_base unavailable; recorded bytes " |
| 1311 | "and hashes without token counts", |
| 1312 | file=sys.stderr, |
| 1313 | ) |
| 1314 | print(output, end="") |
| 1315 | return 0 |
| 1316 | |
| 1317 | if args.command == "page-context-report": |
| 1318 | report = page_context_usage_report(args.project_path) |
| 1319 | print(json.dumps(report, ensure_ascii=False, indent=2)) |
| 1320 | return 0 |
| 1321 | |
| 1322 | parser.error(f"Unknown command: {args.command}") |
| 1323 | except Exception as exc: |
| 1324 | print(f"[ERROR] {exc}") |
| 1325 | return 1 |
| 1326 |