diff --git a/.planning/phases/01-config-and-command-foundation/01-CONTEXT.md b/.planning/phases/01-config-and-command-foundation/01-CONTEXT.md index 4aad8dfa..195fcf32 100644 --- a/.planning/phases/01-config-and-command-foundation/01-CONTEXT.md +++ b/.planning/phases/01-config-and-command-foundation/01-CONTEXT.md @@ -1,7 +1,7 @@ # Phase 1: Config And Command Foundation - Context -**Gathered:** 2026-04-23 -**Status:** Ready for planning +**Gathered:** 2026-04-23 +**Status:** Ready for planning **Source:** Derived from `$gsd-new-project` research and Phase 1 roadmap. @@ -160,5 +160,5 @@ python /PaperForge/worker/scripts/literature_pipeline.py --vault ` path tokens removed from user-run examples; legacy invocation documented as fallback (per Plan 04 success criteria) - All 8 requirement IDs satisfied diff --git a/.planning/phases/04-onboarding-validation/04-02-PLAN.md b/.planning/phases/04-onboarding-validation/04-02-PLAN.md index fcbef6df..f676abfd 100644 --- a/.planning/phases/04-onboarding-validation/04-02-PLAN.md +++ b/.planning/phases/04-onboarding-validation/04-02-PLAN.md @@ -137,7 +137,7 @@ Add `paperforge doctor` as a standalone subcommand that reports setup readiness ``` PaperForge Lite Doctor ====================== - + [PASS] Python 环境 — Python 3.10+ [FAIL] Vault 结构 — system_dir 不存在 [WARN] Zotero 链接 — Zotero 目录是普通文件夹，不是 junction diff --git a/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-01-PLAN.md b/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-01-PLAN.md index 3194d259..d0041e2c 100644 --- a/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-01-PLAN.md +++ b/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-01-PLAN.md @@ -129,7 +129,7 @@ def test_pending_to_processing_transition(tmp_path, mock_paddleocr_api): # Setup: create ocr-queue.json with pending job # Call: run_ocr(vault) # Assert: job state changed to processing - + def test_processing_to_done_transition(tmp_path, mock_paddleocr_api): # Setup: ocr-queue.json with processing job # Mock polling returns done with result_url diff --git a/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-02-PLAN.md b/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-02-PLAN.md index d614eca3..9f8ff142 100644 --- a/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-02-PLAN.md +++ b/.planning/phases/05-workflow-hardening-and-optional-plugin-shell/05-02-PLAN.md @@ -71,7 +71,7 @@ def mock_vault(tmp_path): From paperforge/cli.py (commands to smoke test): ```python # paperforge doctor -> run_doctor(vault) -# paperforge selection-sync -> run_selection_sync(vault) +# paperforge selection-sync -> run_selection_sync(vault) # paperforge index-refresh -> run_index_refresh(vault) # paperforge ocr doctor -> _cmd_ocr_doctor(vault, args) # paperforge deep-reading -> run_deep_reading(vault, verbose=False) diff --git a/.planning/phases/07-zotero-pdf-metadata-state-repair/07-REVIEW.md b/.planning/phases/07-zotero-pdf-metadata-state-repair/07-REVIEW.md index 6034e69d..0108b93a 100644 --- a/.planning/phases/07-zotero-pdf-metadata-state-repair/07-REVIEW.md +++ b/.planning/phases/07-zotero-pdf-metadata-state-repair/07-REVIEW.md @@ -124,7 +124,7 @@ This is implemented correctly for the first fix branch (lines 2934-2964). Howeve The plan specifies three repair scenarios (lines 135-138): 1. Missing meta files → set pending + do_ocr -2. Incomplete meta → set pending + do_ocr +2. Incomplete meta → set pending + do_ocr 3. library done but meta pending → set library to pending only The implementation adds `do_ocr: true` to scenario 3 as well. This is likely harmless (setting do_ocr alongside the status reset makes sense to retrigger OCR), but deviates from the plan. diff --git a/.planning/phases/07-zotero-pdf-metadata-state-repair/07-SUMMARY.md b/.planning/phases/07-zotero-pdf-metadata-state-repair/07-SUMMARY.md index 4dfaa1ad..7270398f 100644 --- a/.planning/phases/07-zotero-pdf-metadata-state-repair/07-SUMMARY.md +++ b/.planning/phases/07-zotero-pdf-metadata-state-repair/07-SUMMARY.md @@ -1,9 +1,9 @@ # Phase 7 Summary — Zotero PDF, Metadata, And State Repair -**Status:** Complete (with one task deferred) -**Date:** 2026-04-24 -**Plan:** [07-PLAN.md](07-PLAN.md) -**Review:** [07-REVIEW.md](07-REVIEW.md) +**Status:** Complete (with one task deferred) +**Date:** 2026-04-24 +**Plan:** [07-PLAN.md](07-PLAN.md) +**Review:** [07-REVIEW.md](07-REVIEW.md) --- diff --git a/.planning/phases/09-command-unification/09-SUMMARY.md b/.planning/phases/09-command-unification/09-SUMMARY.md index 5596d5cd..fd71e06e 100644 --- a/.planning/phases/09-command-unification/09-SUMMARY.md +++ b/.planning/phases/09-command-unification/09-SUMMARY.md @@ -1,10 +1,10 @@ # Phase 09 Plan: Command Unification & CLI Simplification — Summary -**Phase:** 9 -**Plan:** Command Unification & CLI Simplification -**Status:** COMPLETE -**Completed:** 2026-04-24 -**Duration:** ~3 hours (across 6 tasks) +**Phase:** 9 +**Plan:** Command Unification & CLI Simplification +**Status:** COMPLETE +**Completed:** 2026-04-24 +**Duration:** ~3 hours (across 6 tasks) **Milestone:** v1.2 Systematization & Cohesion --- @@ -180,5 +180,5 @@ Phase 10: Documentation & Cohesion --- -*Summary generated by VT-OS/OPENCODE Terminal on 2026-04-24* +*Summary generated by VT-OS/OPENCODE Terminal on 2026-04-24* *Vault-Tec — Preparing for the Future!* diff --git a/.planning/phases/10-documentation-and-cohesion/10-CONTEXT.md b/.planning/phases/10-documentation-and-cohesion/10-CONTEXT.md index 1e4b1f56..0b5b1a98 100644 --- a/.planning/phases/10-documentation-and-cohesion/10-CONTEXT.md +++ b/.planning/phases/10-documentation-and-cohesion/10-CONTEXT.md @@ -65,7 +65,7 @@ Phase 10 will implement OpenCode support and document approach for others. - No old command names (`selection-sync`, `index-refresh`, `ocr run`, `/LD-*`, `/lp-*`) - No dead links - No broken references to `paperforge_lite` - + - **Manual checklist** for soft constraints: - Terminology consistency - Style consistency diff --git a/.planning/phases/10-documentation-and-cohesion/10-SUMMARY.md b/.planning/phases/10-documentation-and-cohesion/10-SUMMARY.md index bd5216e1..16f3b0bd 100644 --- a/.planning/phases/10-documentation-and-cohesion/10-SUMMARY.md +++ b/.planning/phases/10-documentation-and-cohesion/10-SUMMARY.md @@ -1,9 +1,9 @@ # Phase 10: Documentation & Cohesion — Summary -**Phase:** 10 -**Plan:** 10 -**Status:** COMPLETE -**Completed:** 2026-04-24 +**Phase:** 10 +**Plan:** 10 +**Status:** COMPLETE +**Completed:** 2026-04-24 **Milestone:** v1.2 Systematization & Cohesion --- diff --git a/.planning/phases/11-zotero-path-normalization/11-PLAN.md b/.planning/phases/11-zotero-path-normalization/11-PLAN.md index a554fed4..f40a6496 100644 --- a/.planning/phases/11-zotero-path-normalization/11-PLAN.md +++ b/.planning/phases/11-zotero-path-normalization/11-PLAN.md @@ -92,15 +92,15 @@ Implement robust Zotero attachment path parsing from real-world BBT JSON exports **Priority 1 (Primary):** - `attachment.title == "PDF"` AND `attachment.contentType == "application/pdf"` - + **Priority 2 (Fallback heuristic):** - Filter to `contentType == "application/pdf"` items only - Select the LARGEST file by size (if size field available) - If sizes are equal or unavailable, select the one with shortest title (main PDFs often have simple titles) - + **Priority 3 (Final fallback):** - First PDF attachment in the list - + **Returns:** `(main_pdf_attachment, supplementary_attachments)` where supplementary is a list of all other PDF attachments 2. In `load_export_rows()`, when processing each item: diff --git a/.planning/phases/11-zotero-path-normalization/11-VERIFICATION.md b/.planning/phases/11-zotero-path-normalization/11-VERIFICATION.md index 35b69201..8a95bde0 100644 --- a/.planning/phases/11-zotero-path-normalization/11-VERIFICATION.md +++ b/.planning/phases/11-zotero-path-normalization/11-VERIFICATION.md @@ -1,9 +1,9 @@ # Phase 11 Wave 4 Verification Report -**Phase:** 11 -**Plan:** 01 -**Wave:** 4 of 4 -**Date:** 2026-04-24 +**Phase:** 11 +**Plan:** 01 +**Wave:** 4 of 4 +**Date:** 2026-04-24 **Status:** COMPLETE --- diff --git a/.planning/phases/12-architecture-cleanup/12-CONTEXT.md b/.planning/phases/12-architecture-cleanup/12-CONTEXT.md index b2cf80d3..3f82d267 100644 --- a/.planning/phases/12-architecture-cleanup/12-CONTEXT.md +++ b/.planning/phases/12-architecture-cleanup/12-CONTEXT.md @@ -1,8 +1,8 @@ # Phase 12: Architecture Cleanup - Context -**Gathered:** 2026-04-24 -**Status:** Ready for planning -**Base Commit:** 4297dcd +**Gathered:** 2026-04-24 +**Status:** Ready for planning +**Base Commit:** 4297dcd --- diff --git a/.planning/phases/12-architecture-cleanup/12-DISCUSSION-LOG.md b/.planning/phases/12-architecture-cleanup/12-DISCUSSION-LOG.md index 48c2db83..602d4775 100644 --- a/.planning/phases/12-architecture-cleanup/12-DISCUSSION-LOG.md +++ b/.planning/phases/12-architecture-cleanup/12-DISCUSSION-LOG.md @@ -1,8 +1,8 @@ # Phase 12: Architecture Cleanup - Discussion Log -**Phase:** 12 -**Topic:** 修复模块边界泄漏，消除测试死区 -**Base Commit:** 4297dcd +**Phase:** 12 +**Topic:** 修复模块边界泄漏，消除测试死区 +**Base Commit:** 4297dcd --- diff --git a/.planning/phases/12-architecture-cleanup/12-PLAN.md b/.planning/phases/12-architecture-cleanup/12-PLAN.md index 79717aa1..6082cc63 100644 --- a/.planning/phases/12-architecture-cleanup/12-PLAN.md +++ b/.planning/phases/12-architecture-cleanup/12-PLAN.md @@ -1,8 +1,8 @@ # Phase 12: Architecture Cleanup - Execution Plan -**Plan Date:** 2026-04-24 -**Base Commit:** 4297dcd -**Phase Goal:** 修复模块边界泄漏，消除测试死区 +**Plan Date:** 2026-04-24 +**Base Commit:** 4297dcd +**Phase Goal:** 修复模块边界泄漏，消除测试死区 --- diff --git a/command/pf-ocr.md b/command/pf-ocr.md index b41e49d8..4806ddfd 100644 --- a/command/pf-ocr.md +++ b/command/pf-ocr.md @@ -120,7 +120,7 @@ OCR 完成后，每个文献生成以下文件： ### OpenCode > `/pf-ocr` 是 **CLI 命令**，Agent 层不直接提供 `/pf-ocr` 聊天命令。 -> +> > 用户需要： > 1. 在 Obsidian 中将 library-record 的 `do_ocr` 设为 `true` > 2. 在终端运行 `paperforge ocr` diff --git a/docs/INSTALLATION.md b/docs/INSTALLATION.md index 56cc671a..d1e717de 100644 --- a/docs/INSTALLATION.md +++ b/docs/INSTALLATION.md @@ -146,4 +146,3 @@ python -m paperforge 4. **开始精读**：使用 `/pf-deep ` 生成结构化阅读笔记 详细用法参见 [AGENTS.md](../AGENTS.md)。 - diff --git a/docs/setup-guide.md b/docs/setup-guide.md index ebb2d456..e69c9c6f 100644 --- a/docs/setup-guide.md +++ b/docs/setup-guide.md @@ -1,7 +1,7 @@ # PaperForge Lite 安装与配置指南 > 本文档是 [setup_wizard.py](../setup_wizard.py) 的补充说明。如果 TUI 向导中的文字指引不够直观，请参考本页的详细步骤。 -> +> > 本文档中的截图保存在 `docs/images/` 目录下，向导中点击"查看安装截图"按钮可直接打开。 --- @@ -225,6 +225,3 @@ python setup_wizard.py --vault . --- *PaperForge Lite | 安装指南* - - - diff --git a/paperforge/__main__.py b/paperforge/__main__.py index 42e3a595..b4a13235 100644 --- a/paperforge/__main__.py +++ b/paperforge/__main__.py @@ -1,6 +1,7 @@ """paperforge.__main__ — entry point for `python -m paperforge`.""" import sys + from paperforge.cli import main if __name__ == "__main__": diff --git a/paperforge/cli.py b/paperforge/cli.py index f8b0e590..ebe85312 100644 --- a/paperforge/cli.py +++ b/paperforge/cli.py @@ -15,22 +15,21 @@ from __future__ import annotations import argparse import json -import os import sys from pathlib import Path -# Logging -from paperforge.logging_config import configure_logging - # Config / resolver from paperforge.config import ( load_simple_env, load_vault_config, - resolve_vault, paperforge_paths, paths_as_strings, + resolve_vault, ) +# Logging +from paperforge.logging_config import configure_logging + # Worker function stubs — let tests patch cli.run_* directly run_status = None run_selection_sync = None @@ -89,12 +88,13 @@ def _import_worker_functions() -> None: global run_status, run_selection_sync, run_index_refresh global run_deep_reading, run_repair, run_ocr, ensure_base_views - from paperforge.worker.status import run_status as _rs - from paperforge.worker.sync import run_selection_sync as _rss, run_index_refresh as _rir - from paperforge.worker.deep_reading import run_deep_reading as _rdr - from paperforge.worker.repair import run_repair as _rr - from paperforge.worker.ocr import run_ocr as _ro from paperforge.worker.base_views import ensure_base_views as _ebu + from paperforge.worker.deep_reading import run_deep_reading as _rdr + from paperforge.worker.ocr import run_ocr as _ro + from paperforge.worker.repair import run_repair as _rr + from paperforge.worker.status import run_status as _rs + from paperforge.worker.sync import run_index_refresh as _rir + from paperforge.worker.sync import run_selection_sync as _rss if run_status is None: run_status = _rs @@ -126,10 +126,16 @@ def build_parser() -> argparse.ArgumentParser: help="Path to the Obsidian vault root (default: cwd or PAPERFORGE_VAULT env)", ) parser.add_argument( - "--verbose", "-v", + "--verbose", + "-v", action="store_true", help="Enable DEBUG-level diagnostic output on stderr", ) + parser.add_argument( + "--no-progress", + action="store_true", + help="Disable progress bars (tqdm) for all commands", + ) sub = parser.add_subparsers(dest="command", required=True) @@ -174,18 +180,12 @@ def build_parser() -> argparse.ArgumentParser: sub.add_parser("index-refresh", help="Refresh formal literature notes from library records") # deep-reading - p_dr = sub.add_parser("deep-reading", help="Check deep-reading queue status") + sub.add_parser("deep-reading", help="Check deep-reading queue status") # repair p_repair = sub.add_parser("repair", help="Repair divergent literature notes") - p_repair.add_argument( - "--fix", action="store_true", - help="Actually apply repairs instead of dry-run" - ) - p_repair.add_argument( - "--fix-paths", action="store_true", - help="Re-resolve PDF paths for items with path_error" - ) + p_repair.add_argument("--fix", action="store_true", help="Actually apply repairs instead of dry-run") + p_repair.add_argument("--fix-paths", action="store_true", help="Re-resolve PDF paths for items with path_error") # ocr (unified) p_ocr = sub.add_parser("ocr", help="OCR operations") @@ -207,8 +207,10 @@ def build_parser() -> argparse.ArgumentParser: # base-refresh p_base = sub.add_parser("base-refresh", help="Refresh Obsidian Base view files") p_base.add_argument( - "--force", "-f", action="store_true", - help="Force full regeneration (bypasses incremental merge, replaces all views including user views)" + "--force", + "-f", + action="store_true", + help="Force full regeneration (bypasses incremental merge, replaces all views including user views)", ) # doctor @@ -292,6 +294,7 @@ def main(argv: list[str] | None = None) -> int: # New unified commands if args.command == "sync": from paperforge.commands import sync + return sync.run(args) # OCR — handle both new unified and old subcommand styles @@ -302,17 +305,20 @@ def main(argv: list[str] | None = None) -> int: return _cmd_ocr_doctor(vault, args) # New unified ocr (or ocr run) from paperforge.commands import ocr + return ocr.run(args) # Backward compat: old selection-sync and index-refresh if args.command == "selection-sync": from paperforge.commands import sync + args.selection = True args.index = False return sync.run(args) if args.command == "index-refresh": from paperforge.commands import sync + args.selection = False args.index = True return sync.run(args) @@ -320,14 +326,17 @@ def main(argv: list[str] | None = None) -> int: # Other commands delegate to their modules if args.command == "status": from paperforge.commands import status + return status.run(args) if args.command == "deep-reading": from paperforge.commands import deep + return deep.run(args) if args.command == "repair": from paperforge.commands import repair + return repair.run(args) if args.command == "base-refresh": @@ -341,10 +350,12 @@ def main(argv: list[str] | None = None) -> int: if args.command == "doctor": from paperforge.worker.status import run_doctor + return run_doctor(vault) if args.command == "update": from paperforge.worker.update import run_update + return run_update(vault) print(f"Error: unknown command {args.command}", file=sys.stderr) diff --git a/paperforge/commands/ocr.py b/paperforge/commands/ocr.py index 98e5bea1..fb9fc997 100644 --- a/paperforge/commands/ocr.py +++ b/paperforge/commands/ocr.py @@ -74,7 +74,7 @@ def run(args: argparse.Namespace) -> int: logger.info("Processing specific key: %s", key) run_ocr = _get_run_ocr() - exit_code = run_ocr(vault, verbose=getattr(args, "verbose", False)) + exit_code = run_ocr(vault, verbose=getattr(args, "verbose", False), no_progress=getattr(args, "no_progress", False)) # Auto-diagnose after successful run (new unified behavior) if exit_code == 0 and ocr_action is None and not diagnose_only and not key: diff --git a/paperforge/commands/repair.py b/paperforge/commands/repair.py index 23e9b736..43f6e882 100644 --- a/paperforge/commands/repair.py +++ b/paperforge/commands/repair.py @@ -32,7 +32,7 @@ def run(args: argparse.Namespace) -> int: vault = getattr(args, "vault_path", None) paths = getattr(args, "paths", None) if vault is None: - from paperforge.config import resolve_vault, paperforge_paths, load_vault_config + from paperforge.config import load_vault_config, paperforge_paths, resolve_vault vault = resolve_vault(cli_vault=getattr(args, "vault", None)) cfg = load_vault_config(vault) @@ -49,13 +49,8 @@ def run(args: argparse.Namespace) -> int: # Report path_error summary from repair scan path_errors = result.get("path_errors", {}) if path_errors.get("total", 0) > 0: - error_summary = ", ".join( - f"{count} {err}" - for err, count in sorted(path_errors.get("by_type", {}).items()) - ) - print( - f"repair: Found {path_errors['total']} items with path_error: {error_summary}" - ) + error_summary = ", ".join(f"{count} {err}" for err, count in sorted(path_errors.get("by_type", {}).items())) + print(f"repair: Found {path_errors['total']} items with path_error: {error_summary}") # Return non-zero if any divergences or path_errors remain has_issues = bool(result.get("divergent")) or path_errors.get("total", 0) > 0 return 1 if has_issues else 0 diff --git a/paperforge/config.py b/paperforge/config.py index a7f04d8c..f1bfa432 100644 --- a/paperforge/config.py +++ b/paperforge/config.py @@ -22,6 +22,7 @@ from typing import Any # .env loader # --------------------------------------------------------------------------- + def load_simple_env(env_path: Path) -> None: """Load key=value pairs from a .env file into os.environ (no overwrite).""" if not env_path.exists(): @@ -74,6 +75,7 @@ CONFIG_KEYS: set[str] = set(DEFAULT_CONFIG.keys()) # JSON reader # --------------------------------------------------------------------------- + def read_paperforge_json(vault: Path) -> dict[str, Any]: """Read and parse paperforge.json, returning raw key-value pairs. @@ -97,6 +99,7 @@ def read_paperforge_json(vault: Path) -> dict[str, Any]: # Vault resolution # --------------------------------------------------------------------------- + def resolve_vault( cli_vault: Path | None = None, env: dict[str, str] | None = None, @@ -142,6 +145,7 @@ def resolve_vault( # Config loading # --------------------------------------------------------------------------- + def load_vault_config( vault: Path, env: dict[str, str] | None = None, @@ -205,6 +209,7 @@ def load_vault_config( # Path construction # --------------------------------------------------------------------------- + def paperforge_paths( vault: Path, cfg: dict[str, str] | None = None, diff --git a/paperforge/pdf_resolver.py b/paperforge/pdf_resolver.py index e6a9d497..9b7460ec 100644 --- a/paperforge/pdf_resolver.py +++ b/paperforge/pdf_resolver.py @@ -2,6 +2,7 @@ Supports absolute, vault-relative, junction/symlink, and Zotero storage-relative paths. """ + from __future__ import annotations import ctypes @@ -58,7 +59,7 @@ def resolve_pdf_path( # Try Zotero storage-relative (format: "storage:XXXX/item.pdf") if raw.startswith("storage:") and zotero_dir is not None: - storage_rel = raw[len("storage:"):].lstrip("/") + storage_rel = raw[len("storage:") :].lstrip("/") storage_candidate = (zotero_dir / storage_rel.replace("/", os.sep)).resolve() if is_valid_pdf(storage_candidate): return str(storage_candidate) @@ -83,13 +84,9 @@ def resolve_junction(path: Path) -> Path: # Windows-specific: resolve directory junction reparse points if os.name == "nt" and path.is_dir(): try: - from ctypes import wintypes - kernel32 = ctypes.windll.kernel32 buf = ctypes.create_unicode_buffer(1024) - handle = kernel32.CreateFileW( - str(path), 0, 0, None, 3, 0x02000000, None - ) + handle = kernel32.CreateFileW(str(path), 0, 0, None, 3, 0x02000000, None) if handle != -1: try: res = kernel32.GetFinalPathNameByHandleW(handle, buf, 1024, 0) diff --git a/paperforge/skills/literature-qa/prompt_deep_subagent.md b/paperforge/skills/literature-qa/prompt_deep_subagent.md index 5fbd6160..2a612f8c 100644 --- a/paperforge/skills/literature-qa/prompt_deep_subagent.md +++ b/paperforge/skills/literature-qa/prompt_deep_subagent.md @@ -295,4 +295,3 @@ python {{SCRIPT}} validate-note "" --fulltext "" # 列出待精读队列（信息用） python {{SCRIPT}} queue --vault "{{VAULT}}" --format table ``` - diff --git a/paperforge/skills/literature-qa/scripts/ld_deep.py b/paperforge/skills/literature-qa/scripts/ld_deep.py index 5c48ac52..99ec7215 100644 --- a/paperforge/skills/literature-qa/scripts/ld_deep.py +++ b/paperforge/skills/literature-qa/scripts/ld_deep.py @@ -6,9 +6,9 @@ from __future__ import annotations import argparse import json import re +from collections.abc import Iterable from dataclasses import dataclass, field from pathlib import Path -from typing import Iterable from paperforge.worker._utils import scan_library_records @@ -19,6 +19,7 @@ def _load_vault_config(vault: Path) -> dict: Preserves the public name for legacy callers. """ from paperforge.config import load_vault_config as _shared_load_vault_config + return _shared_load_vault_config(vault) @@ -177,7 +178,9 @@ def extract_figures_from_fulltext(fulltext: str, figure_map: dict | None = None) FigureEntry( number=mapped.get("number", "?"), image_id=image_id, - title=mapped.get("caption", "")[:80] + "..." if len(mapped.get("caption", "")) > 80 else mapped.get("caption", "[Figure]"), + title=mapped.get("caption", "")[:80] + "..." + if len(mapped.get("caption", "")) > 80 + else mapped.get("caption", "[Figure]"), image_link=pending_image, page=mapped.get("page", pending_page), caption=mapped.get("caption", ""), @@ -269,11 +272,13 @@ def extract_tables_from_fulltext(fulltext: str, figure_map: dict | None = None) # Try figure_map first mapped = map_lookup.get(image_id) if mapped: - tables.append(TableEntry( - number=mapped.get("number", str(len(tables) + 1)), - image_link=image_link, - page=mapped.get("page", pending_page), - )) + tables.append( + TableEntry( + number=mapped.get("number", str(len(tables) + 1)), + image_link=image_link, + page=mapped.get("page", pending_page), + ) + ) else: # Fallback: cannot determine real table number from filename # The number in filename (e.g. 75 in page_024_table_75...) is an OCR internal ID, NOT the table number @@ -288,88 +293,241 @@ def extract_tables_from_fulltext(fulltext: str, figure_map: dict | None = None) CHART_TYPE_KEYWORDS: dict[str, list[str]] = { "条形图与误差棒": [ - "bar", "histogram", "column", "quantification", "quantitative", - "relative expression", "mRNA expression", "protein level", - "BMD", "BV/TV", "Tb.N", "Tb.Sp", "intensity", "score", - "ratio", "percentage", "proportion", "fold change", + "bar", + "histogram", + "column", + "quantification", + "quantitative", + "relative expression", + "mRNA expression", + "protein level", + "BMD", + "BV/TV", + "Tb.N", + "Tb.Sp", + "intensity", + "score", + "ratio", + "percentage", + "proportion", + "fold change", ], "折线图与时间序列": [ - "curve", "time", "kinetics", "release", "cyclic", "stability", - "degradation", "profile", "over time", "day", "week", - "duration", "period", "cycle", "repeated", + "curve", + "time", + "kinetics", + "release", + "cyclic", + "stability", + "degradation", + "profile", + "over time", + "day", + "week", + "duration", + "period", + "cycle", + "repeated", ], "热图与聚类图": [ - "heatmap", "heat map", "clustering", "cluster", "dendrogram", - "hierarchical", "correlation matrix", "expression matrix", + "heatmap", + "heat map", + "clustering", + "cluster", + "dendrogram", + "hierarchical", + "correlation matrix", + "expression matrix", ], "火山图与曼哈顿图": [ - "volcano", "volcano plot", "manhattan", "-log10", "log2fc", - "fold change", "differential", "DEG", "DEM", "upregulated", "downregulated", + "volcano", + "volcano plot", + "manhattan", + "-log10", + "log2fc", + "fold change", + "differential", + "DEG", + "DEM", + "upregulated", + "downregulated", ], "免疫荧光定量图": [ - "immunofluorescence", "immunofluorescent", "confocal", "fluorescence", - "staining", "3D reconstruction", "overlay", "DAPI", " Alexa ", - "FITC", "TRITC", "Cy3", "Cy5", "SOX9", "COL2A1", "Piezo1", - "positive cells", "mean intensity", "fluorescent", + "immunofluorescence", + "immunofluorescent", + "confocal", + "fluorescence", + "staining", + "3D reconstruction", + "overlay", + "DAPI", + " Alexa ", + "FITC", + "TRITC", + "Cy3", + "Cy5", + "SOX9", + "COL2A1", + "Piezo1", + "positive cells", + "mean intensity", + "fluorescent", ], "组织学半定量图": [ - "H&E", "hematoxylin", "eosin", "Safranin", "Fast Green", - "Masson", "trichrome", "histology", "histological", - "tissue section", "slide", "stain", "morphology", - "O'Driscoll", "ICRS", "Mankin", "OARSI", "Pineda", + "H&E", + "hematoxylin", + "eosin", + "Safranin", + "Fast Green", + "Masson", + "trichrome", + "histology", + "histological", + "tissue section", + "slide", + "stain", + "morphology", + "O'Driscoll", + "ICRS", + "Mankin", + "OARSI", + "Pineda", ], "桑基图与弦图": [ - "chord", "Sankey", "correlation network", "interaction network", - "signaling network", "proximity", "correlation of metabolic", - "Spearman", "Pearson correlation", + "chord", + "Sankey", + "correlation network", + "interaction network", + "signaling network", + "proximity", + "correlation of metabolic", + "Spearman", + "Pearson correlation", ], "雷达图与漏斗图": [ - "radar", "funnel", "spider", "web chart", "polar", + "radar", + "funnel", + "spider", + "web chart", + "polar", ], "GSEA富集图": [ - "GSEA", "MSEA", "enrichment", "enrichment plot", "enrichment score", - "NES", "leading edge", "pathway enrichment", "metabolic set", + "GSEA", + "MSEA", + "enrichment", + "enrichment plot", + "enrichment score", + "NES", + "leading edge", + "pathway enrichment", + "metabolic set", ], "箱式图与小提琴图": [ - "box", "boxplot", "box plot", "violin", "whisker", "quartile", - "median", "IQR", "outlier", + "box", + "boxplot", + "box plot", + "violin", + "whisker", + "quartile", + "median", + "IQR", + "outlier", ], "散点图与气泡图": [ - "scatter", "bubble", "dot plot", "correlation plot", "regression", - "linear fit", "R²", "correlation coefficient", + "scatter", + "bubble", + "dot plot", + "correlation plot", + "regression", + "linear fit", + "R²", + "correlation coefficient", ], "Western Blot条带图": [ - "Western", "blot", "WB", "gel electrophoresis", "SDS-PAGE", - "band", "molecular weight", "kDa", + "Western", + "blot", + "WB", + "gel electrophoresis", + "SDS-PAGE", + "band", + "molecular weight", + "kDa", ], "显微照片与SEM图": [ - "SEM", "TEM", "microscopy", "micrograph", "morphology", - "surface", "topography", "nanostructure", "porous", - "FE-SEM", "scanning electron", "transmission electron", + "SEM", + "TEM", + "microscopy", + "micrograph", + "morphology", + "surface", + "topography", + "nanostructure", + "porous", + "FE-SEM", + "scanning electron", + "transmission electron", ], "降维图(PCA-tSNE-UMAP)": [ - "PCA", "t-SNE", "tSNE", "UMAP", "MDS", "dimensionality reduction", - "principal component", "clustering plot", "embedding", + "PCA", + "t-SNE", + "tSNE", + "UMAP", + "MDS", + "dimensionality reduction", + "principal component", + "clustering plot", + "embedding", ], "网络图与通路图": [ - "pathway", "network", "signaling pathway", "KEGG", "Reactome", - "protein-protein interaction", "PPI", "regulatory network", + "pathway", + "network", + "signaling pathway", + "KEGG", + "Reactome", + "protein-protein interaction", + "PPI", + "regulatory network", ], "蛋白质结构图": [ - "protein structure", "crystallography", "NMR structure", "AlphaFold", - "3D structure", "homology modeling", "docking", + "protein structure", + "crystallography", + "NMR structure", + "AlphaFold", + "3D structure", + "homology modeling", + "docking", ], "森林图与Meta分析": [ - "forest plot", "meta-analysis", "meta analysis", "pooled effect", - "heterogeneity", "I²", "Egger", "funnel plot", + "forest plot", + "meta-analysis", + "meta analysis", + "pooled effect", + "heterogeneity", + "I²", + "Egger", + "funnel plot", ], "ROC与PR曲线": [ - "ROC", "AUC", "receiver operating", "sensitivity", "specificity", - "PR curve", "precision-recall", "diagnostic accuracy", + "ROC", + "AUC", + "receiver operating", + "sensitivity", + "specificity", + "PR curve", + "precision-recall", + "diagnostic accuracy", ], "生存曲线": [ - "survival", "Kaplan-Meier", "KM curve", "log-rank", "hazard ratio", - "HR", "OS", "PFS", "DFS", "mortality", + "survival", + "Kaplan-Meier", + "KM curve", + "log-rank", + "hazard ratio", + "HR", + "OS", + "PFS", + "DFS", + "mortality", ], } @@ -440,6 +598,7 @@ def build_chart_type_map(figure_map: dict) -> dict: return result + CAPTION_PATTERNS = { "main_figure": re.compile( r"^(?:Figure|Fig\.?)\s*(\d+[a-zA-Z]?)(?:\s*[\.:|\-]?\s*)(.*?)$", @@ -473,30 +632,32 @@ def build_figure_map(fulltext: str, zotero_key: str = "") -> dict: # First pass: collect all images with their page and line index all_images: list[dict] = [] current_page: int | None = None - + for idx, raw_line in enumerate(lines): line = raw_line.strip() if not line: continue - + page_match = page_pattern.match(line) if page_match: current_page = int(page_match.group(1)) continue - + image_match = image_pattern.match(line) if image_match: - all_images.append({ - "link": image_match.group(1), - "id": Path(image_match.group(1)).stem, - "line_idx": idx, - "page": current_page, - }) + all_images.append( + { + "link": image_match.group(1), + "id": Path(image_match.group(1)).stem, + "line_idx": idx, + "page": current_page, + } + ) # Second pass: match captions to nearest images entries: list[dict] = [] current_page = None - + for idx, raw_line in enumerate(lines): line = raw_line.strip() if not line: @@ -517,8 +678,8 @@ def build_figure_map(fulltext: str, zotero_key: str = "") -> dict: # Find nearest image within window of adjacent pages (current ± 2 pages) best_image = None - min_distance = float('inf') - + min_distance = float("inf") + for img in all_images: # Check if image is within 2 pages of current page if current_page is not None and img["page"] is not None: @@ -541,16 +702,18 @@ def build_figure_map(fulltext: str, zotero_key: str = "") -> dict: if line_diff <= 5: # Within 5 lines additional_images.append({"id": img["id"], "link": img["link"]}) - entries.append({ - "number": number, - "label": line.split(".")[0] if "." in line else line.split("|")[0].strip(), - "page": current_page, - "type": entry_type, - "caption": caption_text, - "image_link": best_image["link"] if best_image else None, - "image_id": best_image["id"] if best_image else None, - "additional_images": additional_images, - }) + entries.append( + { + "number": number, + "label": line.split(".")[0] if "." in line else line.split("|")[0].strip(), + "page": current_page, + "type": entry_type, + "caption": caption_text, + "image_link": best_image["link"] if best_image else None, + "image_id": best_image["id"] if best_image else None, + "additional_images": additional_images, + } + ) break # one caption per line # Deduplicate by (type, number) keeping first @@ -596,7 +759,9 @@ def render_study_scaffold(figures: Iterable[FigureEntry], tables: Iterable[Table # Build figure blocks using the standard renderer for consistency figure_blocks = [render_figure_block(fig) for fig in figure_list] - figure_section = "\n\n".join(figure_blocks) if figure_blocks else "##### Figure 待补充\n\n- 暂未从 OCR 中解析到可用主图。" + figure_section = ( + "\n\n".join(figure_blocks) if figure_blocks else "##### Figure 待补充\n\n- 暂未从 OCR 中解析到可用主图。" + ) # Build table blocks using the standard renderer for consistency table_blocks = [render_table_block(table) for table in table_list] @@ -679,29 +844,31 @@ def render_figure_block(figure: FigureEntry) -> str: # Add additional images for multi-image figures for add_img in figure.additional_images: lines.append(f"> ![[{add_img['link']}]]") - lines.extend([ - ">", - "> **图像定位与核心问题**", - f"> - 页码：{page_suffix or '待补充'}", - "> - 这张图要回答什么：", - "> - （待补充）", - ">", - "> **方法与结果**", - "> - 方法：", - "> - 结果：", - ">", - "> **作者解释**", - "> - （待补充）", - ">", - "> **我的理解**", - "> - （待补充）", - ">", - "> **在全文中的作用**", - "> - （待补充）", - ">", - "> **疑点 / 局限**", - "> - （待补充）", - ]) + lines.extend( + [ + ">", + "> **图像定位与核心问题**", + f"> - 页码：{page_suffix or '待补充'}", + "> - 这张图要回答什么：", + "> - （待补充）", + ">", + "> **方法与结果**", + "> - 方法：", + "> - 结果：", + ">", + "> **作者解释**", + "> - （待补充）", + ">", + "> **我的理解**", + "> - （待补充）", + ">", + "> **在全文中的作用**", + "> - （待补充）", + ">", + "> **疑点 / 局限**", + "> - （待补充）", + ] + ) return "\n".join(lines) + "\n\n" @@ -722,7 +889,9 @@ def render_table_block(table: TableEntry) -> str: return "\n".join(lines) + "\n\n" -def validate_selected_blocks(note_text: str, figures: Iterable[FigureEntry], tables: Iterable[TableEntry] | None = None) -> list[str]: +def validate_selected_blocks( + note_text: str, figures: Iterable[FigureEntry], tables: Iterable[TableEntry] | None = None +) -> list[str]: """Return missing selected figure/table embeds that must be repaired before generation.""" missing: list[str] = [] for figure in figures: @@ -755,7 +924,7 @@ def validate_callout_structure(note_text: str, figures: Iterable[FigureEntry]) - figure_heading_prefix = f"> [!note]- Figure {figure.number}：" # Find the line that starts with this prefix figure_idx = -1 - for i, line in enumerate(note_text.splitlines()): + for _i, line in enumerate(note_text.splitlines()): if line.strip().startswith(figure_heading_prefix): figure_idx = note_text.find(line) break @@ -767,7 +936,7 @@ def validate_callout_structure(note_text: str, figures: Iterable[FigureEntry]) - next_section = figure_block.find("\n#### ", 1) end_positions = [p for p in [next_callout, next_heading, next_section] if p != -1] if end_positions: - figure_block = figure_block[:min(end_positions)] + figure_block = figure_block[: min(end_positions)] required_local = [ "**作者解释**", "**我的理解**", @@ -932,13 +1101,19 @@ def _ensure_section_with_blocks(note_text: str, header: str, blocks: list[str]) return updated -def ensure_study_section(note_text: str, figures: Iterable[FigureEntry], tables: Iterable[TableEntry] | None = None) -> str: +def ensure_study_section( + note_text: str, figures: Iterable[FigureEntry], tables: Iterable[TableEntry] | None = None +) -> str: """Append the study scaffold if it does not yet exist.""" figure_list = list(figures) table_list = list(tables or []) if STUDY_HEADER in note_text: - updated = _ensure_section_with_blocks(note_text, FIGURE_SECTION_HEADER, [render_figure_block(fig) for fig in figure_list]) - updated = _ensure_section_with_blocks(updated, TABLE_SECTION_HEADER, [render_table_block(table) for table in table_list]) + updated = _ensure_section_with_blocks( + note_text, FIGURE_SECTION_HEADER, [render_figure_block(fig) for fig in figure_list] + ) + updated = _ensure_section_with_blocks( + updated, TABLE_SECTION_HEADER, [render_table_block(table) for table in table_list] + ) return updated stripped = note_text.rstrip() @@ -1023,7 +1198,7 @@ def prepare_deep_reading(vault: Path, zotero_key: str, force: bool = False) -> d record_text = record_path.read_text(encoding="utf-8") # 2. Check analyze flag - analyze_match = re.search(r'^analyze:\s*(true|false)$', record_text, re.MULTILINE) + analyze_match = re.search(r"^analyze:\s*(true|false)$", record_text, re.MULTILINE) if not analyze_match or analyze_match.group(1) != "true": result["message"] = f"[ERROR] analyze != true in {record_path}. Set analyze: true first." return result @@ -1032,7 +1207,7 @@ def prepare_deep_reading(vault: Path, zotero_key: str, force: bool = False) -> d status_match = re.search(r'^deep_reading_status:\s*"?(.*?)"?$', record_text, re.MULTILINE) dr_status = status_match.group(1).strip() if status_match else "pending" if dr_status == "done" and not force: - result["message"] = f"[WARN] deep_reading_status already 'done'. Use --force to re-run." + result["message"] = "[WARN] deep_reading_status already 'done'. Use --force to re-run." return result # 4. Check OCR / fulltext availability @@ -1098,7 +1273,9 @@ def prepare_deep_reading(vault: Path, zotero_key: str, force: bool = False) -> d figure_map_path = ocr_dir / "figure-map.json" fulltext_text = fulltext_md.read_text(encoding="utf-8") figure_map = build_figure_map(fulltext_text, zotero_key=zotero_key) - figure_map["generated_at"] = __import__("datetime").datetime.now(__import__("datetime").timezone.utc).isoformat() + figure_map["generated_at"] = ( + __import__("datetime").datetime.now(__import__("datetime").timezone.utc).isoformat() + ) figure_map_path.parent.mkdir(parents=True, exist_ok=True) figure_map_path.write_text(json.dumps(figure_map, ensure_ascii=False, indent=2), encoding="utf-8") written_paths.append(figure_map_path) @@ -1132,13 +1309,9 @@ def prepare_deep_reading(vault: Path, zotero_key: str, force: bool = False) -> d formal_note.write_text(updated, encoding="utf-8") result["figures"] = [ - {"number": f.number, "image_id": f.image_id, "page": f.page, "title": f.title} - for f in planned_figures - ] - result["tables"] = [ - {"number": t.number, "page": t.page, "image_link": t.image_link} - for t in planned_tables + {"number": f.number, "image_id": f.image_id, "page": f.page, "title": f.title} for f in planned_figures ] + result["tables"] = [{"number": t.number, "page": t.page, "image_link": t.image_link} for t in planned_tables] result["status"] = "ok" result["message"] = ( @@ -1168,16 +1341,19 @@ def scan_deep_reading_queue(vault: Path) -> list[dict]: """ all_records = scan_library_records(vault) # Filter: only records that still need deep reading - queue = [r for r in all_records if r['deep_reading_status'] != 'done'] + queue = [r for r in all_records if r["deep_reading_status"] != "done"] # Sort: OCR completed first, then by domain, then by key - queue.sort(key=lambda row: ( - 0 if row['ocr_status'] == 'done' else 1, - row['domain'], - row['zotero_key'], - )) + queue.sort( + key=lambda row: ( + 0 if row["ocr_status"] == "done" else 1, + row["domain"], + row["zotero_key"], + ) + ) return queue +import contextlib import sys # Fix Windows console encoding for Unicode output @@ -1187,6 +1363,7 @@ if sys.platform == "win32": except AttributeError: # Python < 3.7 fallback import codecs + sys.stdout = codecs.getwriter("utf-8")(sys.stdout.buffer) @@ -1199,19 +1376,29 @@ def main() -> int: scaffold_parser = subparsers.add_parser("ensure-scaffold", help="Append a deep-reading scaffold to a note") scaffold_parser.add_argument("note", type=Path) - scaffold_parser.add_argument("--fulltext", type=Path, help="Optional fulltext markdown used to build figure headings") + scaffold_parser.add_argument( + "--fulltext", type=Path, help="Optional fulltext markdown used to build figure headings" + ) scaffold_parser.add_argument("--figures", help="Comma-separated selected figure numbers to insert") scaffold_parser.add_argument("--tables", help="Comma-separated selected table numbers to insert") - validate_parser = subparsers.add_parser("validate-selected", help="Validate selected figure/table embeds are present in the note") + validate_parser = subparsers.add_parser( + "validate-selected", help="Validate selected figure/table embeds are present in the note" + ) validate_parser.add_argument("note", type=Path) - validate_parser.add_argument("--fulltext", type=Path, required=True, help="OCR fulltext markdown used to resolve figure/table embeds") + validate_parser.add_argument( + "--fulltext", type=Path, required=True, help="OCR fulltext markdown used to resolve figure/table embeds" + ) validate_parser.add_argument("--figures", help="Comma-separated selected figure numbers to validate") validate_parser.add_argument("--tables", help="Comma-separated selected table numbers to validate") - full_validate_parser = subparsers.add_parser("validate-note", help="Run the full structural validation for a deep-reading note") + full_validate_parser = subparsers.add_parser( + "validate-note", help="Run the full structural validation for a deep-reading note" + ) full_validate_parser.add_argument("note", type=Path) - full_validate_parser.add_argument("--fulltext", type=Path, required=True, help="OCR fulltext markdown used to resolve figure/table embeds") + full_validate_parser.add_argument( + "--fulltext", type=Path, required=True, help="OCR fulltext markdown used to resolve figure/table embeds" + ) full_validate_parser.add_argument("--figures", help="Comma-separated selected figure numbers to validate") full_validate_parser.add_argument("--tables", help="Comma-separated selected table numbers to validate") @@ -1224,8 +1411,12 @@ def main() -> int: map_parser.add_argument("--key", default="", help="Zotero key for output metadata") map_parser.add_argument("--out", type=Path, help="Optional output JSON path (default: stdout)") - chart_type_parser = subparsers.add_parser("chart-type-scan", help="Scan figure captions for chart types and recommend chart-reading guides") - chart_type_parser.add_argument("figure_map", type=Path, help="Path to figure-map.json generated by figure-map command") + chart_type_parser = subparsers.add_parser( + "chart-type-scan", help="Scan figure captions for chart types and recommend chart-reading guides" + ) + chart_type_parser.add_argument( + "figure_map", type=Path, help="Path to figure-map.json generated by figure-map command" + ) chart_type_parser.add_argument("--out", type=Path, help="Optional output JSON path (default: stdout)") prepare_parser = subparsers.add_parser("prepare", help="One-click prepare all mechanical steps for deep reading") @@ -1247,7 +1438,9 @@ def main() -> int: if args.command == "figure-index": fulltext = args.fulltext.read_text(encoding="utf-8") for figure in extract_figures_from_fulltext(fulltext): - print(f"Figure {figure.number}\tid={figure.image_id}\tpage={figure.page}\timage={figure.image_link}\ttitle={figure.title}") + print( + f"Figure {figure.number}\tid={figure.image_id}\tpage={figure.page}\timage={figure.image_link}\ttitle={figure.title}" + ) return 0 if args.command == "ensure-scaffold": @@ -1260,10 +1453,8 @@ def main() -> int: figure_map = None figure_map_path = args.fulltext.parent / "figure-map.json" if figure_map_path.exists(): - try: + with contextlib.suppress(json.JSONDecodeError, UnicodeDecodeError): figure_map = json.loads(figure_map_path.read_text(encoding="utf-8")) - except (json.JSONDecodeError, UnicodeDecodeError): - pass figure_candidates = extract_figures_from_fulltext(fulltext, figure_map) table_candidates = extract_tables_from_fulltext(fulltext, figure_map) selected_figures = {part.strip() for part in (args.figures or "").split(",") if part.strip()} @@ -1285,7 +1476,9 @@ def main() -> int: table_candidates = extract_tables_from_fulltext(fulltext) selected_figures = {part.strip() for part in (args.figures or "").split(",") if part.strip()} selected_tables = {part.strip() for part in (args.tables or "").split(",") if part.strip()} - figures = select_entries_by_numbers(figure_candidates, selected_figures, attr="image_id") if selected_figures else [] + figures = ( + select_entries_by_numbers(figure_candidates, selected_figures, attr="image_id") if selected_figures else [] + ) tables = select_entries_by_numbers(table_candidates, selected_tables) if selected_tables else [] missing = validate_selected_blocks(note_text, figures, tables) if missing: @@ -1302,10 +1495,8 @@ def main() -> int: figure_map = None figure_map_path = args.fulltext.parent / "figure-map.json" if figure_map_path.exists(): - try: + with contextlib.suppress(json.JSONDecodeError, UnicodeDecodeError): figure_map = json.loads(figure_map_path.read_text(encoding="utf-8")) - except (json.JSONDecodeError, UnicodeDecodeError): - pass figure_candidates = extract_figures_from_fulltext(fulltext, figure_map) table_candidates = extract_tables_from_fulltext(fulltext) selected_figures = {part.strip() for part in (args.figures or "").split(",") if part.strip()} diff --git a/paperforge/worker/__init__.py b/paperforge/worker/__init__.py index 3a9060c2..5e328473 100644 --- a/paperforge/worker/__init__.py +++ b/paperforge/worker/__init__.py @@ -1,19 +1,19 @@ """PaperForge worker modules — migrated from pipeline/worker/scripts.""" -from paperforge.worker.sync import ( - load_export_rows, - run_selection_sync, - run_index_refresh, - obsidian_wikilink_for_pdf, - absolutize_vault_path, - _normalize_attachment_path, - _identify_main_pdf, -) +from paperforge.worker.base_views import build_base_views, ensure_base_views, merge_base_views +from paperforge.worker.deep_reading import run_deep_reading from paperforge.worker.ocr import run_ocr from paperforge.worker.repair import run_repair from paperforge.worker.status import run_doctor, run_status -from paperforge.worker.deep_reading import run_deep_reading -from paperforge.worker.base_views import build_base_views, merge_base_views, ensure_base_views +from paperforge.worker.sync import ( + _identify_main_pdf, + _normalize_attachment_path, + absolutize_vault_path, + load_export_rows, + obsidian_wikilink_for_pdf, + run_index_refresh, + run_selection_sync, +) __all__ = [ "load_export_rows", diff --git a/paperforge/worker/_utils.py b/paperforge/worker/_utils.py index caa7336e..cb29dae9 100644 --- a/paperforge/worker/_utils.py +++ b/paperforge/worker/_utils.py @@ -1,4 +1,5 @@ from __future__ import annotations + import json import logging import re @@ -9,25 +10,28 @@ logger = logging.getLogger(__name__) # --- Constants --- -STANDARD_VIEW_NAMES = frozenset([ - "控制面板", "推荐分析", "待 OCR", "OCR 完成", - "待深度阅读", "深度阅读完成", "正式卡片", "全记录" -]) +STANDARD_VIEW_NAMES = frozenset( + ["控制面板", "推荐分析", "待 OCR", "OCR 完成", "待深度阅读", "深度阅读完成", "正式卡片", "全记录"] +) # --- Journal Database --- + def read_json(path: Path): - return json.loads(path.read_text(encoding='utf-8')) + return json.loads(path.read_text(encoding="utf-8")) + _JOURNAL_DB: dict[str, dict] | None = None + def load_journal_db(vault: Path) -> dict[str, dict]: """Load zoterostyle.json journal database.""" global _JOURNAL_DB if _JOURNAL_DB is not None: return _JOURNAL_DB from paperforge.config import load_vault_config - zoterostyle_path = vault / load_vault_config(vault)['system_dir'] / 'Zotero' / 'zoterostyle.json' + + zoterostyle_path = vault / load_vault_config(vault)["system_dir"] / "Zotero" / "zoterostyle.json" if zoterostyle_path.exists(): try: _JOURNAL_DB = read_json(zoterostyle_path) @@ -37,98 +41,111 @@ def load_journal_db(vault: Path) -> dict[str, dict]: _JOURNAL_DB = {} return _JOURNAL_DB + def lookup_impact_factor(journal_name: str, extra: str, vault: Path) -> str: """Lookup impact factor: prefer zoterostyle.json, fallback to extra field.""" if not journal_name: - return '' + return "" journal_db = load_journal_db(vault) if journal_name in journal_db: - rank_data = journal_db[journal_name].get('rank', {}) + rank_data = journal_db[journal_name].get("rank", {}) if isinstance(rank_data, dict): - sciif = rank_data.get('sciif', '') + sciif = rank_data.get("sciif", "") if sciif: return str(sciif) if extra: - if_match = re.search('影响因子[:：]\\s*([0-9.]+)', extra) + if_match = re.search("影响因子[:：]\\s*([0-9.]+)", extra) if if_match: return if_match.group(1) - return '' + return "" + # --- JSON I/O --- + def write_json(path: Path, data) -> None: path.parent.mkdir(parents=True, exist_ok=True) - path.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding='utf-8') + path.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8") + def read_jsonl(path: Path): rows = [] if not path.exists(): return rows - for line in path.read_text(encoding='utf-8').splitlines(): + for line in path.read_text(encoding="utf-8").splitlines(): line = line.strip() if line: rows.append(json.loads(line)) return rows + def write_jsonl(path: Path, rows) -> None: path.parent.mkdir(parents=True, exist_ok=True) - text = '\n'.join((json.dumps(row, ensure_ascii=False) for row in rows)) + text = "\n".join(json.dumps(row, ensure_ascii=False) for row in rows) if text: - text += '\n' - path.write_text(text, encoding='utf-8') + text += "\n" + path.write_text(text, encoding="utf-8") + # --- YAML Helpers --- + def yaml_quote(value: str) -> str: if isinstance(value, bool): - return 'true' if value else 'false' - return '"' + str(value or '').replace('\\', '\\\\').replace('"', '\\"') + '"' + return "true" if value else "false" + return '"' + str(value or "").replace("\\", "\\\\").replace('"', '\\"') + '"' + def yaml_block(value: str) -> list[str]: - value = (value or '').strip() + value = (value or "").strip() if not value: - return ['abstract: |-', ' '] - lines = ['abstract: |-'] + return ["abstract: |-", " "] + lines = ["abstract: |-"] for line in value.splitlines(): - lines.append(f' {line}') + lines.append(f" {line}") return lines + def yaml_list(key: str, values) -> list[str]: - cleaned = [str(value).strip() for value in values or [] if str(value).strip()] + cleaned = [str(value).strip() for value in values or [] if value is not None and str(value).strip()] if not cleaned: - return [f'{key}: []'] - lines = [f'{key}:'] + return [f"{key}: []"] + lines = [f"{key}:"] for value in cleaned: - lines.append(f' - {yaml_quote(value)}') + lines.append(f" - {yaml_quote(value)}") return lines + # --- String / Path Utils --- + def slugify_filename(text: str) -> str: - cleaned = re.sub('[<>:"/\\\\|?*]+', '', text).strip() - return cleaned[:120] or 'untitled' + cleaned = re.sub('[<>:"/\\\\|?*]+', "", text).strip() + return cleaned[:120] or "untitled" + def _extract_year(value: str) -> str: - match = re.search('(19|20)\\d{2}', value or '') - return match.group(0) if match else '' + match = re.search("(19|20)\\d{2}", value or "") + return match.group(0) if match else "" + # --- Deep-Reading Queue --- + def _resolve_formal_note_path(vault: Path, zotero_key: str, domain: str) -> Path | None: """Resolve formal literature note by zotero_key.""" from paperforge.config import paperforge_paths - lit_root = paperforge_paths(vault)['literature'] + + lit_root = paperforge_paths(vault)["literature"] domain_dir = lit_root / domain if not domain_dir.exists(): return None - frontmatter_pattern = re.compile( - fr'^\s*zotero_key:\s*"?{re.escape(zotero_key)}"?\s*$', re.MULTILINE - ) - for note_path in domain_dir.rglob('*.md'): + frontmatter_pattern = re.compile(rf'^\s*zotero_key:\s*"?{re.escape(zotero_key)}"?\s*$', re.MULTILINE) + for note_path in domain_dir.rglob("*.md"): try: - text = note_path.read_text(encoding='utf-8') + text = note_path.read_text(encoding="utf-8") except UnicodeDecodeError: - text = note_path.read_text(encoding='utf-8', errors='ignore') + text = note_path.read_text(encoding="utf-8", errors="ignore") if frontmatter_pattern.search(text): return note_path return None @@ -154,8 +171,8 @@ def scan_library_records(vault: Path) -> list[dict]: from paperforge.config import paperforge_paths paths = paperforge_paths(vault) - records_root = paths.get('library_records') - ocr_root = paths.get('ocr') + records_root = paths.get("library_records") + ocr_root = paths.get("ocr") if not records_root or not records_root.exists(): return [] @@ -165,53 +182,54 @@ def scan_library_records(vault: Path) -> list[dict]: if not domain_dir.is_dir(): continue domain = domain_dir.name - for record_path in sorted(domain_dir.glob('*.md')): + for record_path in sorted(domain_dir.glob("*.md")): try: - text = record_path.read_text(encoding='utf-8') + text = record_path.read_text(encoding="utf-8") except Exception: continue # Extract frontmatter fields - zotero_key_match = re.search(r'^zotero_key:\s*(.+)$', text, re.MULTILINE) - analyze_match = re.search(r'^analyze:\s*(true|false)$', text, re.MULTILINE) + zotero_key_match = re.search(r"^zotero_key:\s*(.+)$", text, re.MULTILINE) + analyze_match = re.search(r"^analyze:\s*(true|false)$", text, re.MULTILINE) title_match = re.search(r'^title:\s*"?(.+?)"?$', text, re.MULTILINE) - do_ocr_match = re.search(r'^do_ocr:\s*(true|false)$', text, re.MULTILINE) + do_ocr_match = re.search(r"^do_ocr:\s*(true|false)$", text, re.MULTILINE) status_match = re.search(r'^deep_reading_status:\s*"?(.*?)"?$', text, re.MULTILINE) zotero_key = ( - zotero_key_match.group(1).strip().strip('"').strip("'") - if zotero_key_match else record_path.stem + zotero_key_match.group(1).strip().strip('"').strip("'") if zotero_key_match else record_path.stem ) - is_analyze = analyze_match is not None and analyze_match.group(1) == 'true' - title = title_match.group(1).strip().strip('"') if title_match else '' - do_ocr = do_ocr_match is not None and do_ocr_match.group(1) == 'true' - dr_status = status_match.group(1).strip() if status_match else 'pending' + is_analyze = analyze_match is not None and analyze_match.group(1) == "true" + title = title_match.group(1).strip().strip('"') if title_match else "" + do_ocr = do_ocr_match is not None and do_ocr_match.group(1) == "true" + dr_status = status_match.group(1).strip() if status_match else "pending" if not is_analyze: continue # Check OCR status from meta.json - meta_path = ocr_root / zotero_key / 'meta.json' - ocr_status = 'pending' + meta_path = ocr_root / zotero_key / "meta.json" + ocr_status = "pending" if meta_path.exists(): try: meta = read_json(meta_path) - ocr_status = str(meta.get('ocr_status', 'pending')).strip().lower() + ocr_status = str(meta.get("ocr_status", "pending")).strip().lower() except Exception: pass # Resolve formal note path note_path = _resolve_formal_note_path(vault, zotero_key, domain) - results.append({ - 'zotero_key': zotero_key, - 'domain': domain, - 'title': title, - 'analyze': True, - 'do_ocr': do_ocr, - 'deep_reading_status': dr_status, - 'ocr_status': ocr_status, - 'note_path': note_path, - }) + results.append( + { + "zotero_key": zotero_key, + "domain": domain, + "title": title, + "analyze": True, + "do_ocr": do_ocr, + "deep_reading_status": dr_status, + "ocr_status": ocr_status, + "note_path": note_path, + } + ) return results diff --git a/scripts/update-paperforge.ps1 b/scripts/update-paperforge.ps1 index a06bff58..aaf6347e 100644 --- a/scripts/update-paperforge.ps1 +++ b/scripts/update-paperforge.ps1 @@ -1,6 +1,6 @@ # PaperForge Lite Update Script for Windows # 一键更新脚本 — 双击运行即可 -# +# # 功能： # 1. 自动检测安装方式（pip/pip-editable/git/zip） # 2. 执行对应的更新命令 @@ -62,7 +62,7 @@ try { if ($pkgPath) { $pkgDir = Split-Path $pkgPath -Parent $installPath = $pkgDir - + if ($pkgDir -match "site-packages|dist-packages") { # pip install (non-editable) $installMethod = "pip" @@ -100,7 +100,7 @@ switch ($installMethod) { "pip" { Write-Color "`n[更新] 通过 pip 升级..." "Cyan" Write-Color "命令: pip install --upgrade paperforge" "Gray" - + if (-not $Force) { $confirm = Read-Host "确认更新? [y/N]" if ($confirm -notmatch "^[Yy]") { @@ -108,15 +108,15 @@ switch ($installMethod) { exit 0 } } - + & $pip.Source install --upgrade paperforge $success = ($LASTEXITCODE -eq 0) } - + "pip-editable" { Write-Color "`n[更新] pip editable 模式 detected" "Cyan" Write-Color "步骤 1: git pull 拉取最新代码..." "Yellow" - + if (-not $Force) { $confirm = Read-Host "确认更新? [y/N]" if ($confirm -notmatch "^[Yy]") { @@ -124,7 +124,7 @@ switch ($installMethod) { exit 0 } } - + Push-Location $installPath try { git pull origin master @@ -137,11 +137,11 @@ switch ($installMethod) { Pop-Location } } - + "git" { Write-Color "`n[更新] 通过 git pull 更新..." "Cyan" Write-Color "命令: git pull origin master" "Gray" - + if (-not $Force) { $confirm = Read-Host "确认更新? [y/N]" if ($confirm -notmatch "^[Yy]") { @@ -149,11 +149,11 @@ switch ($installMethod) { exit 0 } } - + git pull origin master $success = ($LASTEXITCODE -eq 0) } - + default { Write-Color "`n[错误] 无法自动检测安装方式" "Red" Write-Color @" diff --git a/scripts/validate_setup.py b/scripts/validate_setup.py index a988052e..42ac4c54 100644 --- a/scripts/validate_setup.py +++ b/scripts/validate_setup.py @@ -5,7 +5,6 @@ from __future__ import annotations import json import os -import sys from pathlib import Path @@ -24,6 +23,7 @@ def load_config(vault: Path) -> dict: # Try shared resolver first (01-03 and later installs) try: from paperforge.config import load_vault_config as _shared_load + return _shared_load(vault) except ImportError: pass @@ -109,7 +109,9 @@ def validate_agent(vault: Path, cfg: dict) -> list[tuple[bool, str]]: chart_dir = skill_root / "chart-reading" if chart_dir.exists(): guide_count = len(list(chart_dir.glob("*.md"))) - results.append((guide_count >= 14, f"[{'OK' if guide_count >= 14 else 'WARN'}] chart-reading guides: {guide_count}")) + results.append( + (guide_count >= 14, f"[{'OK' if guide_count >= 14 else 'WARN'}] chart-reading guides: {guide_count}") + ) return results diff --git a/scripts/welcome.py b/scripts/welcome.py index e2e024fd..ee02ad5a 100644 --- a/scripts/welcome.py +++ b/scripts/welcome.py @@ -3,31 +3,32 @@ from __future__ import annotations -import time import sys +import time class Colors: """ANSI color codes (safe for most terminals).""" - BLACK = '\033[30m' - RED = '\033[31m' - GREEN = '\033[32m' - YELLOW = '\033[33m' - BLUE = '\033[34m' - MAGENTA = '\033[35m' - CYAN = '\033[36m' - WHITE = '\033[37m' - BRIGHT_BLACK = '\033[90m' - BRIGHT_RED = '\033[91m' - BRIGHT_GREEN = '\033[92m' - BRIGHT_YELLOW = '\033[93m' - BRIGHT_BLUE = '\033[94m' - BRIGHT_MAGENTA = '\033[95m' - BRIGHT_CYAN = '\033[96m' - BRIGHT_WHITE = '\033[97m' - BOLD = '\033[1m' - DIM = '\033[2m' - ENDC = '\033[0m' + + BLACK = "\033[30m" + RED = "\033[31m" + GREEN = "\033[32m" + YELLOW = "\033[33m" + BLUE = "\033[34m" + MAGENTA = "\033[35m" + CYAN = "\033[36m" + WHITE = "\033[37m" + BRIGHT_BLACK = "\033[90m" + BRIGHT_RED = "\033[91m" + BRIGHT_GREEN = "\033[92m" + BRIGHT_YELLOW = "\033[93m" + BRIGHT_BLUE = "\033[94m" + BRIGHT_MAGENTA = "\033[95m" + BRIGHT_CYAN = "\033[96m" + BRIGHT_WHITE = "\033[97m" + BOLD = "\033[1m" + DIM = "\033[2m" + ENDC = "\033[0m" def clear_screen(): @@ -73,7 +74,9 @@ def show_welcome(): ("6", "Validation", "Verify installation"), ] for num, title, desc in steps: - print(f" {Colors.BRIGHT_CYAN}[{num}]{Colors.ENDC} {Colors.BOLD}{title:<22}{Colors.ENDC} {Colors.DIM}-> {desc}{Colors.ENDC}") + print( + f" {Colors.BRIGHT_CYAN}[{num}]{Colors.ENDC} {Colors.BOLD}{title:<22}{Colors.ENDC} {Colors.DIM}-> {desc}{Colors.ENDC}" + ) # Bottom border draw_border(70, "=", Colors.BRIGHT_BLUE) @@ -87,7 +90,10 @@ def show_progress(step: int, total: int, message: str): bar = "#" * filled + "-" * (width - filled) percent = int(100 * step / total) - print(f"\r{Colors.BRIGHT_CYAN}[{bar}]{Colors.ENDC} {Colors.BOLD}{percent}%{Colors.ENDC} {Colors.DIM}{message}{Colors.ENDC}", end="") + print( + f"\r{Colors.BRIGHT_CYAN}[{bar}]{Colors.ENDC} {Colors.BOLD}{percent}%{Colors.ENDC} {Colors.DIM}{message}{Colors.ENDC}", + end="", + ) sys.stdout.flush() if step == total: @@ -101,11 +107,11 @@ def show_completion(): # Completion frame completion = f""" {Colors.BRIGHT_GREEN}======================================================================{Colors.ENDC} - - {Colors.BOLD}{Colors.BRIGHT_WHITE}[OK] INSTALLATION COMPLETE{Colors.ENDC} - - {Colors.BRIGHT_YELLOW}Your knowledge forge is ready!{Colors.ENDC} - + + {Colors.BOLD}{Colors.BRIGHT_WHITE}[OK] INSTALLATION COMPLETE{Colors.ENDC} + + {Colors.BRIGHT_YELLOW}Your knowledge forge is ready!{Colors.ENDC} + {Colors.BRIGHT_GREEN}======================================================================{Colors.ENDC} """ print(completion) @@ -123,13 +129,13 @@ def show_install_menu(): """Show the interactive installation menu.""" print(f"\n{Colors.BOLD}{Colors.BRIGHT_WHITE}Please select an option:{Colors.ENDC}\n") print(f" {Colors.BRIGHT_GREEN}[1]{Colors.ENDC} {Colors.BOLD}Start Installation{Colors.ENDC}") - print(f" Configure vault, Zotero, OCR, and deploy scripts") + print(" Configure vault, Zotero, OCR, and deploy scripts") print() print(f" {Colors.BRIGHT_YELLOW}[2]{Colors.ENDC} {Colors.BOLD}Verify Setup{Colors.ENDC}") - print(f" Check existing installation and fix issues") + print(" Check existing installation and fix issues") print() print(f" {Colors.BRIGHT_BLUE}[3]{Colors.ENDC} {Colors.BOLD}View Documentation{Colors.ENDC}") - print(f" Open README and usage guide") + print(" Open README and usage guide") print() print(f" {Colors.BRIGHT_RED}[4]{Colors.ENDC} {Colors.BOLD}Exit{Colors.ENDC}") print() diff --git a/setup_wizard.py b/setup_wizard.py index 2dad8c9f..69a38b6d 100644 --- a/setup_wizard.py +++ b/setup_wizard.py @@ -7,6 +7,7 @@ PaperForge Lite Setup Wizard (Textual Step-by-Step) Usage: python setup_wizard.py --vault /path/to/vault """ + from __future__ import annotations import argparse @@ -17,7 +18,6 @@ import subprocess import sys import webbrowser from pathlib import Path -from typing import Optional if sys.platform == "win32": import winreg @@ -25,33 +25,39 @@ else: winreg = None from textual.app import App, ComposeResult -from textual.containers import Container, Grid, Horizontal, Vertical +from textual.containers import Container, Horizontal, Vertical from textual.message import Message from textual.reactive import reactive -from textual.screen import Screen from textual.widgets import ( Button, ContentSwitcher, Footer, Header, - Label, Markdown, ProgressBar, Static, Tree, ) - # ============================================================================= # Agent Platform Configurations # ============================================================================= AGENT_CONFIGS = { - "opencode": {"name": "OpenCode", "skill_dir": ".opencode/skills", "command_dir": ".opencode/command", "config_file": None}, + "opencode": { + "name": "OpenCode", + "skill_dir": ".opencode/skills", + "command_dir": ".opencode/command", + "config_file": None, + }, "cursor": {"name": "Cursor", "skill_dir": ".cursor/skills", "config_file": ".cursor/settings.json"}, "claude": {"name": "Claude Code", "skill_dir": ".claude/skills", "config_file": ".claude/skills.json"}, "windsurf": {"name": "Windsurf", "skill_dir": ".windsurf/skills", "config_file": None}, - "github_copilot": {"name": "GitHub Copilot", "skill_dir": ".github/skills", "config_file": ".github/copilot-instructions.md"}, + "github_copilot": { + "name": "GitHub Copilot", + "skill_dir": ".github/skills", + "config_file": ".github/copilot-instructions.md", + }, "cline": {"name": "Cline", "skill_dir": ".clinerules/skills", "config_file": ".clinerules"}, "augment": {"name": "Augment", "skill_dir": ".augment/skills", "config_file": None}, "trae": {"name": "Trae", "skill_dir": ".trae/skills", "config_file": None}, @@ -62,6 +68,7 @@ AGENT_CONFIGS = { # Detection Logic (unchanged from previous version) # ============================================================================= + class CheckResult: def __init__(self, name: str): self.name = name @@ -75,7 +82,7 @@ class EnvChecker: def __init__(self, vault: Path): self.vault = vault - self.manual_zotero_path: Optional[Path] = None + self.manual_zotero_path: Path | None = None self.system_dir: str = "99_System" # 可由用户自定义 self.results: dict[str, CheckResult] = { "python": CheckResult("Python 版本"), @@ -143,11 +150,11 @@ class EnvChecker: r.action_required = True return r - def _find_zotero(self, manual_path: Optional[Path] = None) -> Optional[Path]: + def _find_zotero(self, manual_path: Path | None = None) -> Path | None: # 如果提供了手动路径，优先使用 if manual_path and manual_path.exists(): return manual_path - + system = platform.system() if system == "Windows": # ...existing detection code... @@ -309,9 +316,7 @@ class EnvChecker: try: data = json.loads(jf.read_text(encoding="utf-8")) # Better BibTeX JSON 是 dict 格式（含 items），也兼容 list 格式 - if isinstance(data, dict) and data.get("items"): - valid.append(jf.name) - elif isinstance(data, list) and len(data) > 0: + if isinstance(data, dict) and data.get("items") or isinstance(data, list) and len(data) > 0: valid.append(jf.name) except Exception: pass @@ -374,16 +379,19 @@ class WelcomeStep(StepScreen): def compose(self) -> ComposeResult: yield from super().compose() - yield Static(r""" - ______ ___ ______ _________________ ___________ _____ _____ + yield Static( + r""" + ______ ___ ______ _________________ ___________ _____ _____ | ___ \/ _ \ | ___ \ ___| ___ \ ___| _ | ___ \ __ \| ___| - | |_/ / /_\ \| |_/ / |__ | |_/ / |_ | | | | |_/ / | \/| |__ - | __/| _ || __/| __|| /| _| | | | | /| | __ | __| - | | | | | || | | |___| |\ \| | \ \_/ / |\ \| |_\ \| |___ - \_| \_| |_/\_| \____/\_| \_\_| \___/\_| \_|\____/\____/ - - [+] Forge Your Knowledge Into Power [+] - """, classes="logo") + | |_/ / /_\ \| |_/ / |__ | |_/ / |_ | | | | |_/ / | \/| |__ + | __/| _ || __/| __|| /| _| | | | | /| | __ | __| + | | | | | || | | |___| |\ \| | \ \_/ / |\ \| |_\ \| |___ + \_| \_| |_/\_| \____/\_| \_\_| \___/\_| \_|\____/\____/ + + [+] Forge Your Knowledge Into Power [+] + """, + classes="logo", + ) yield Markdown(""" **PaperForge Lite** 是一个连接 Zotero 与 Obsidian 的文献工作流工具。 @@ -488,7 +496,7 @@ class VaultStep(StepScreen): def __init__(self, step_id: str, checker: EnvChecker, vault: str = "", **kwargs): kwargs.setdefault("id", step_id) - super().__init__(**kwargs) + super().__init__(step_id=step_id, checker=checker, **kwargs) self.step_id = step_id self.checker = checker self.step_idx = int(step_id.split("-")[1]) @@ -502,6 +510,7 @@ PaperForge 需要知道你的 **Obsidian Vault 位置**，以及你想要的目 你可以保留默认名称，也可以自定义。 """) from textual.widgets import Input + yield Static("Obsidian Vault 路径 (绝对路径):", classes="step-title") yield Input(value=self._vault, placeholder="D:\\Documents\\MyVault", id="input-vault-path") yield Static("", id="vault-error", classes="status-bar") @@ -615,7 +624,7 @@ class ZoteroStep(StepScreen): # 自动检测 Zotero 数据目录 detected = self._detect_zotero_data() default_value = str(detected) if detected else "" - + yield Markdown(""" **Zotero 数据目录**存放了你的文献数据库和 PDF 附件。 @@ -638,6 +647,7 @@ class ZoteroStep(StepScreen): > ⚠️ **不要**填 Vault 里面的路径，也不要在这里创建新文件夹 """) from textual.widgets import Input + username = os.environ.get("USERNAME", os.environ.get("USER", "YourName")) yield Static("Zotero 数据目录:", classes="step-title") yield Input( @@ -651,7 +661,7 @@ class ZoteroStep(StepScreen): id="btn-row", ) - def _detect_zotero_data(self) -> Optional[Path]: + def _detect_zotero_data(self) -> Path | None: """Build default Zotero data path from current username.""" home = Path.home() # Default: C:/Users//Zotero (Windows) or ~/Zotero (Unix) @@ -663,6 +673,7 @@ class ZoteroStep(StepScreen): def on_button_pressed(self, event: Button.Pressed) -> None: if event.button.id == "btn-link-zotero": from textual.widgets import Input + path_str = self.query_one("#input-zotero-data", Input).value.strip() if not path_str: self.set_status("请填写 Zotero 数据目录路径", False) @@ -687,18 +698,18 @@ class ZoteroStep(StepScreen): is_inside_vault = True except ValueError: pass - + if is_inside_vault: # 在 Vault 内部，直接通过 self.app.zotero_data_dir = str(zotero_data) self.set_status("Zotero 数据目录已确认", True) self.app.post_message(StepPassed(self.step_idx)) return - + # 在 Vault 外部，创建 Junction - system_dir = getattr(self.app, 'vault_config', {}).get('system_dir', '99_System') + system_dir = getattr(self.app, "vault_config", {}).get("system_dir", "99_System") junction_path = vault / system_dir / "Zotero" - + # Remove existing if junction_path.exists() or junction_path.is_symlink(): try: @@ -714,7 +725,9 @@ class ZoteroStep(StepScreen): if sys.platform == "win32": subprocess.run( ["cmd", "/c", "mklink", "/J", str(junction_path), str(zotero_data)], - check=True, capture_output=True, shell=False, + check=True, + capture_output=True, + shell=False, ) else: junction_path.symlink_to(zotero_data, target_is_directory=True) @@ -769,7 +782,7 @@ class JsonStep(StepScreen): def compose(self) -> ComposeResult: yield from super().compose() - system_dir = getattr(self.app, 'vault_config', {}).get('system_dir', '99_System') + system_dir = getattr(self.app, "vault_config", {}).get("system_dir", "99_System") yield Markdown(f""" **Better BibTeX 自动导出**是 PaperForge 的数据来源。 @@ -836,6 +849,7 @@ class DeployStep(StepScreen): 这些操作不会覆盖你的数据文件。 """) from textual.widgets import Input + yield Static("PaddleOCR API Key:", classes="step-title") yield Input(placeholder="粘贴你的 PaddleOCR API Key", id="input-api-key") yield Static("PaddleOCR API URL:", classes="step-title") @@ -865,15 +879,13 @@ class DeployStep(StepScreen): for idx, name in required_steps: if not step_states[idx]: incomplete.append(f"步骤 {idx}: {name}") - + if incomplete: self.set_status( - f"[无法部署] 以下步骤未完成：\n" + "\n".join(incomplete) + - "\n请先返回并完成上述步骤", - False + "[无法部署] 以下步骤未完成：\n" + "\n".join(incomplete) + "\n请先返回并完成上述步骤", False ) return - + self.set_status("正在部署...", None) success = self._deploy() if success: @@ -885,12 +897,12 @@ class DeployStep(StepScreen): def _deploy(self) -> bool: """Deploy scripts and create config files.""" vault = self.checker.vault - vault_config = getattr(self.app, 'vault_config', {}) - system_dir = vault_config.get('system_dir', '99_System') - resources_dir = vault_config.get('resources_dir', '03_Resources') - literature_dir = vault_config.get('literature_dir', 'Literature') - control_dir = vault_config.get('control_dir', 'LiteratureControl') - base_dir = vault_config.get('base_dir', '05_Bases') + vault_config = getattr(self.app, "vault_config", {}) + system_dir = vault_config.get("system_dir", "99_System") + resources_dir = vault_config.get("resources_dir", "03_Resources") + literature_dir = vault_config.get("literature_dir", "Literature") + control_dir = vault_config.get("control_dir", "LiteratureControl") + base_dir = vault_config.get("base_dir", "05_Bases") def apply_user_paths(text: str, skill_dir_value: str = "") -> str: agent_config_dir = str(Path(skill_dir_value or ".opencode/skills").parent).replace("\\", "/") @@ -916,15 +928,15 @@ class DeployStep(StepScreen): for old, new in replacements.items(): text = text.replace(old, new) return text - + # 1. 获取 agent 配置 - agent_config = getattr(self.app, 'agent_config', None) + agent_config = getattr(self.app, "agent_config", None) if not agent_config: self.set_status("错误：未选择 Agent 平台", False) return False - - skill_dir = agent_config.get('skill_dir', '.opencode/skills') - + + skill_dir = agent_config.get("skill_dir", ".opencode/skills") + # 2. 确定安装包根目录（wizard 所在目录的父目录） wizard_dir = Path(__file__).parent.resolve() # 如果 wizard 在 github-release/ 下，repo_root 就是 github-release/ @@ -940,7 +952,7 @@ class DeployStep(StepScreen): else: self.set_status(f"错误：找不到安装包文件。请在 PaperForge 解压目录下运行此向导。当前: {wizard_dir}", False) return False - + # 3. 创建目录（使用用户自定义路径） pf_path = vault / system_dir / "PaperForge" dirs = [ @@ -956,18 +968,27 @@ class DeployStep(StepScreen): ] for d in dirs: d.mkdir(parents=True, exist_ok=True) - + # 4. 复制脚本（从安装包到 Vault） import shutil - + # Copy worker modules to PaperForge/worker/scripts/ worker_src = repo_root / "paperforge/worker/sync.py" worker_dst = pf_path / "worker/scripts/sync.py" if worker_src.exists(): import shutil + shutil.copy2(worker_src, worker_dst) # Also copy other worker modules - for mod in ["ocr.py", "repair.py", "status.py", "deep_reading.py", "update.py", "base_views.py", "__init__.py"]: + for mod in [ + "ocr.py", + "repair.py", + "status.py", + "deep_reading.py", + "update.py", + "base_views.py", + "__init__.py", + ]: mod_src = repo_root / "paperforge/worker" / mod if mod_src.exists(): shutil.copy2(mod_src, pf_path / "worker/scripts" / mod) @@ -980,7 +1001,7 @@ class DeployStep(StepScreen): else: self.set_status(f"错误：找不到 worker 脚本: {worker_src}", False) return False - + # Copy ld_deep.py (prefer paperforge/skills, fallback to skills/) ld_src = repo_root / "paperforge/skills/literature-qa/scripts/ld_deep.py" if not ld_src.exists(): @@ -1002,7 +1023,7 @@ class DeployStep(StepScreen): else: self.set_status(f"错误：找不到 prompt_deep_subagent.md: {prompt_src}", False) return False - + # Copy chart-reading guides (prefer paperforge/skills, fallback to skills/) chart_src = repo_root / "paperforge/skills/literature-qa/chart-reading" if not chart_src.exists(): @@ -1013,7 +1034,7 @@ class DeployStep(StepScreen): shutil.copy2(f, chart_dst / f.name) # Copy OpenCode command files when the target platform supports them. - if getattr(self.app, 'agent_key', '') == 'opencode': + if getattr(self.app, "agent_key", "") == "opencode": command_src = repo_root / "command" command_dst = vault / agent_config.get("command_dir", ".opencode/command") if command_src.exists() and command_src.is_dir(): @@ -1029,16 +1050,20 @@ class DeployStep(StepScreen): shutil.copytree(docs_src, docs_dst, dirs_exist_ok=True) for doc in docs_dst.rglob("*.md"): doc.write_text(apply_user_paths(doc.read_text(encoding="utf-8"), skill_dir), encoding="utf-8") - + # 5. 创建 .env（放到 PaperForge 目录下） from textual.widgets import Input + api_key = self.query_one("#input-api-key", Input).value.strip() - api_url = self.query_one("#input-api-url", Input).value.strip() or "https://paddleocr.aistudio-app.com/api/v2/ocr/jobs" - + api_url = ( + self.query_one("#input-api-url", Input).value.strip() + or "https://paddleocr.aistudio-app.com/api/v2/ocr/jobs" + ) + if not api_key: self.set_status("请填写 PaddleOCR API Key", False) return False - + # 把 .env 放在 PaperForge 目录下 env_path = pf_path / ".env" env_content = f"""# PaperForge 配置文件 @@ -1068,7 +1093,7 @@ ZOTERO_DATA_DIR={getattr(self.app, 'zotero_data_dir', '')} json.dumps({"domains": export_domains}, indent=2, ensure_ascii=False), encoding="utf-8", ) - + # 6. 创建 paperforge.json（包含用户自定义路径） pf_json = vault / "paperforge.json" existing_config = {} @@ -1077,28 +1102,30 @@ ZOTERO_DATA_DIR={getattr(self.app, 'zotero_data_dir', '')} existing_config = json.loads(pf_json.read_text(encoding="utf-8")) except Exception: existing_config = {} - existing_config.update({ - "version": existing_config.get("version", "1.2.0"), - "agent_platform": agent_config.get('name', 'OpenCode'), - "agent_key": getattr(self.app, 'agent_key', 'opencode'), - "skill_dir": skill_dir, - "command_dir": agent_config.get("command_dir", ""), - "system_dir": system_dir, - "resources_dir": resources_dir, - "literature_dir": literature_dir, - "control_dir": control_dir, - "base_dir": base_dir, - "paperforge_path": f"{system_dir}/PaperForge", - "zotero_data_dir": getattr(self.app, 'zotero_data_dir', ''), - "zotero_link": getattr(self.app, 'zotero_link', f"{system_dir}/Zotero"), - "vault_config": { + existing_config.update( + { + "version": existing_config.get("version", "1.2.0"), + "agent_platform": agent_config.get("name", "OpenCode"), + "agent_key": getattr(self.app, "agent_key", "opencode"), + "skill_dir": skill_dir, + "command_dir": agent_config.get("command_dir", ""), "system_dir": system_dir, "resources_dir": resources_dir, "literature_dir": literature_dir, "control_dir": control_dir, "base_dir": base_dir, - }, - }) + "paperforge_path": f"{system_dir}/PaperForge", + "zotero_data_dir": getattr(self.app, "zotero_data_dir", ""), + "zotero_link": getattr(self.app, "zotero_link", f"{system_dir}/Zotero"), + "vault_config": { + "system_dir": system_dir, + "resources_dir": resources_dir, + "literature_dir": literature_dir, + "control_dir": control_dir, + "base_dir": base_dir, + }, + } + ) pf_json.write_text(json.dumps(existing_config, indent=2, ensure_ascii=False), encoding="utf-8") agents_src = repo_root / "AGENTS.md" @@ -1106,7 +1133,7 @@ ZOTERO_DATA_DIR={getattr(self.app, 'zotero_data_dir', '')} if agents_src.exists(): agents_text = apply_user_paths(agents_src.read_text(encoding="utf-8"), skill_dir) agents_dst.write_text(agents_text, encoding="utf-8") - + # 7. 验证文件完整性 self.set_status("验证文件完整性...", None) checks = { @@ -1119,20 +1146,22 @@ ZOTERO_DATA_DIR={getattr(self.app, 'zotero_data_dir', '')} "导出目录": (pf_path / "exports").exists(), "OCR 目录": (pf_path / "ocr").exists(), } - + missing = [k for k, v in checks.items() if not v] if missing: self.set_status(f"验证失败: {', '.join(missing)}", False) return False - + self.set_status("文件验证通过，初始化系统...", True) - + # 8. 运行初始化命令（模拟测试） try: # 测试 selection-sync（会报错因为没 JSON，但测试脚本能否运行） result = subprocess.run( [sys.executable, str(worker_dst), "--vault", str(vault), "status"], - capture_output=True, text=True, timeout=10, + capture_output=True, + text=True, + timeout=10, ) if result.returncode == 0: self.set_status("工作流脚本运行正常", True) @@ -1146,7 +1175,9 @@ ZOTERO_DATA_DIR={getattr(self.app, 'zotero_data_dir', '')} try: result = subprocess.run( [sys.executable, "-m", "pip", "install", "-e", str(repo_root)], - capture_output=True, text=True, timeout=60, + capture_output=True, + text=True, + timeout=60, ) if result.returncode == 0: self.set_status("PaperForge 工具包安装完成（paperforge 命令已全局注册）", True) @@ -1164,9 +1195,9 @@ class DoneStep(StepScreen): def compose(self) -> ComposeResult: yield from super().compose() - vault_config = getattr(self.app, 'vault_config', {}) - system_dir = vault_config.get('system_dir', '99_System') - worker_cmd = f"python -m paperforge sync --vault ." + vault_config = getattr(self.app, "vault_config", {}) + system_dir = vault_config.get("system_dir", "99_System") + worker_cmd = "python -m paperforge sync --vault ." yield Markdown(f""" ## 安装完成！ @@ -1276,8 +1307,10 @@ paperforge deep-reading # 查看精读队列 # Custom Messages # ============================================================================= + class StepPassed(Message): """步骤通过消息""" + def __init__(self, step_idx: int): super().__init__() self.step_idx = step_idx @@ -1285,6 +1318,7 @@ class StepPassed(Message): class RestartWizard(Message): """重新开始消息""" + def __init__(self): super().__init__() @@ -1293,32 +1327,33 @@ class RestartWizard(Message): # Main App # ============================================================================= + class SetupWizardApp(App): """PaperForge 安装向导主应用""" CSS = """ Screen { align: center middle; } - + .wizard-container { width: 95%; height: 95%; border: solid green; } - + .sidebar { width: 25%; height: 100%; border: solid gray; padding: 1; } .sidebar-title { text-align: center; text-style: bold; color: cyan; padding: 1; } .step-tree { height: 1fr; } - + .main-area { width: 75%; height: 100%; padding: 1; } .progress-area { height: auto; padding: 0 1; } .content-area { height: 1fr; border: solid blue; padding: 1; overflow-y: auto; } - + .logo { text-align: center; color: ansi_bright_cyan; text-style: bold; height: auto; } .step-title { text-style: bold; color: yellow; } .status-bar { height: auto; padding: 1; } - + .step-content { padding: 1; } .step-content Markdown { padding: 0 1; } - + #btn-row { height: auto; padding: 1; } #btn-row Button { margin: 0 1; } - + .done { color: green; } .current { color: yellow; text-style: bold; } .pending { color: gray; } @@ -1434,7 +1469,7 @@ class SetupWizardApp(App): self.current_step = 0 self.step_states = [False] * len(STEP_TITLES) for screen in self.step_screens.values(): - if hasattr(screen, 'set_status'): + if hasattr(screen, "set_status"): screen.set_status("") def open_screenshot(self, filename: str) -> None: @@ -1456,6 +1491,7 @@ class SetupWizardApp(App): # Entry # ============================================================================= + def _find_vault() -> Path | None: """Find vault by looking for paperforge.json in current or parent dirs.""" current = Path(".").resolve() diff --git a/tests/conftest.py b/tests/conftest.py index 92885059..22ad502f 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -3,12 +3,9 @@ from __future__ import annotations import json -import os import shutil -import sys -import tempfile +from collections.abc import Generator from pathlib import Path -from typing import Generator import pytest @@ -38,9 +35,7 @@ def create_test_vault() -> Path: base_dir = vault / "05_Bases" skill_dir = vault / ".opencode" / "skills" / "literature-qa" / "scripts" - for d in [ - exports_dir, ocr_dir, literature_dir, records_dir, base_dir, skill_dir - ]: + for d in [exports_dir, ocr_dir, literature_dir, records_dir, base_dir, skill_dir]: d.mkdir(parents=True, exist_ok=True) # Create paperforge.json @@ -65,8 +60,7 @@ def create_test_vault() -> Path: # Create .env with PADDLEOCR_API_TOKEN env_path = pf_dir / ".env" env_path.write_text( - "PADDLEOCR_API_TOKEN=test_token\n" - "PADDLEOCR_JOB_URL=https://example.com/api\n", + "PADDLEOCR_API_TOKEN=test_token\nPADDLEOCR_JOB_URL=https://example.com/api\n", encoding="utf-8", ) @@ -92,20 +86,20 @@ def create_test_vault() -> Path: 'doi: "10.1016/j.jse.2024.01.001"\n' 'date: "2024-03-15"\n' 'collection_path: ""\n' - 'has_pdf: true\n' + "has_pdf: true\n" 'pdf_path: "[[99_System/Zotero/storage/TSTONE001/TSTONE001.pdf]]"\n' 'fulltext_md_path: "[[99_System/PaperForge/ocr/TSTONE001/fulltext.md]]"\n' - 'recommend_analyze: true\n' - 'analyze: true\n' - 'do_ocr: true\n' + "recommend_analyze: true\n" + "analyze: true\n" + "do_ocr: true\n" 'ocr_status: "done"\n' 'deep_reading_status: "pending"\n' 'analysis_note: ""\n' - 'collection_group:\n' + "collection_group:\n" ' - "骨科"\n' - 'collections:\n' + "collections:\n" ' - "骨科"\n' - 'collection_tags:\n' + "collection_tags:\n" ' - "骨科"\n' 'first_author: "John Smith"\n' 'journal: "Journal of Shoulder and Elbow Surgery"\n' @@ -117,7 +111,11 @@ def create_test_vault() -> Path: ) # Create formal note for TSTONE001 - note_path = literature_dir / "骨科" / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + note_path = ( + literature_dir + / "骨科" + / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + ) note_path.parent.mkdir(parents=True, exist_ok=True) note_path.write_text( "---\n" @@ -127,9 +125,9 @@ def create_test_vault() -> Path: 'journal: "Journal of Shoulder and Elbow Surgery"\n' 'impact_factor: "5.2"\n' 'category: "骨科"\n' - 'tags:\n' - ' - 文献阅读\n' - ' - 骨科\n' + "tags:\n" + " - 文献阅读\n" + " - 骨科\n" 'keywords: ["biomechanics", "rotator cuff"]\n' 'pdf_link: "[[99_System/Zotero/storage/TSTONE001/TSTONE001.pdf]]"\n' "---\n\n" @@ -140,10 +138,16 @@ def create_test_vault() -> Path: ) # Create Zotero storage with mock PDF - zotero_dir = system_dir / "Zotero" / "storage" / "TSTONE001" + # PDF goes at Zotero/KEY/filename.pdf so resolve_pdf_path can find it + zotero_dir = system_dir / "Zotero" / "TSTONE001" zotero_dir.mkdir(parents=True, exist_ok=True) (zotero_dir / "TSTONE001.pdf").write_text("mock pdf content", encoding="utf-8") + # Also create in storage/ subdirectory for legacy path resolution + storage_dir = system_dir / "Zotero" / "storage" / "TSTONE001" + storage_dir.mkdir(parents=True, exist_ok=True) + (storage_dir / "TSTONE001.pdf").write_text("mock pdf content", encoding="utf-8") + # Copy ld_deep.py to skill_dir (simulating deployment) ld_deep_src = REPO_ROOT / "paperforge" / "skills" / "literature-qa" / "scripts" / "ld_deep.py" if ld_deep_src.exists(): diff --git a/tests/sandbox/TestZoteroData/zotero.sqlite b/tests/sandbox/TestZoteroData/zotero.sqlite index 5c5b0cb5..23eb1d30 100644 --- a/tests/sandbox/TestZoteroData/zotero.sqlite +++ b/tests/sandbox/TestZoteroData/zotero.sqlite @@ -1 +1 @@ -SQLite format 3SQLite format 3SQLite format 3SQLite format 3 \ No newline at end of file +SQLite format 3SQLite format 3SQLite format 3SQLite format 3 diff --git a/tests/sandbox/exports/运动医学.json b/tests/sandbox/exports/运动医学.json index 058bd43a..fd34d7b9 100644 --- a/tests/sandbox/exports/运动医学.json +++ b/tests/sandbox/exports/运动医学.json @@ -51,4 +51,4 @@ ] } ] -} \ No newline at end of file +} diff --git a/tests/sandbox/generate_ocr_fixture.py b/tests/sandbox/generate_ocr_fixture.py index 1cbda1f5..4bd560d6 100644 --- a/tests/sandbox/generate_ocr_fixture.py +++ b/tests/sandbox/generate_ocr_fixture.py @@ -15,7 +15,6 @@ import sys from datetime import datetime, timezone from pathlib import Path - REPO_ROOT = Path(__file__).resolve().parent.parent.parent FIXTURE_DIR = REPO_ROOT / "tests" / "sandbox" / "ocr-complete" / "TSTONE001" EXPORT_JSON = REPO_ROOT / "tests" / "sandbox" / "exports" / "骨科.json" @@ -108,8 +107,10 @@ def generate_fixtures() -> None: str(ld_deep_script), "figure-map", str(fulltext_path), - "--key", "TSTONE001", - "--out", str(figure_map_path), + "--key", + "TSTONE001", + "--out", + str(figure_map_path), ], capture_output=True, text=True, @@ -128,7 +129,8 @@ def generate_fixtures() -> None: str(ld_deep_script), "chart-type-scan", str(figure_map_path), - "--out", str(chart_type_map_path), + "--out", + str(chart_type_map_path), ], capture_output=True, text=True, diff --git a/tests/sandbox/generate_sandbox.py b/tests/sandbox/generate_sandbox.py index 5e166a8c..59439ce5 100644 --- a/tests/sandbox/generate_sandbox.py +++ b/tests/sandbox/generate_sandbox.py @@ -14,6 +14,7 @@ Creates tests/sandbox/ with: Wizard creates inside 00_TestVault/: 00_System/Zotero -> junction -> TestZoteroData (user points to our TestZoteroData) """ + from __future__ import annotations import json @@ -159,7 +160,8 @@ def build() -> None: exports_abs = str(EXPORTS.resolve()) readme = SANDBOX / "README.md" - readme.write_text(f"""# PaperForge Lite — Test Sandbox + readme.write_text( + f"""# PaperForge Lite — Test Sandbox ## 用途 测试 PaperForge Lite 安装向导 `setup_wizard.py` 的完整流程。 @@ -215,15 +217,17 @@ paperforge status - 目录名故意和真实 vault 不同，避免硬编码测试不出来 - PDF 是最小化假文件（pymupdf 可读，内容为空） - 不要往 sandbox 加真实数据 -""", encoding="utf-8") +""", + encoding="utf-8", + ) pdf_count = sum(1 for papers in PAPERS.values() for p in papers if p["has_pdf"]) paper_count = sum(len(papers) for papers in PAPERS.values()) print(f"\nSandbox ready: {SANDBOX}") print(f" TestZoteroData/storage/ — {pdf_count} PDFs") print(f" exports/ — {len(PAPERS)} BBT JSON files ({paper_count} papers)") - print(f" 00_TestVault/ — EMPTY (wizard fills this)") - print(f"\nRun:") + print(" 00_TestVault/ — EMPTY (wizard fills this)") + print("\nRun:") print(f" python setup_wizard.py --vault {VAULT.resolve()}") diff --git a/tests/sandbox/ocr-complete/TSTONE001/chart-type-map.json b/tests/sandbox/ocr-complete/TSTONE001/chart-type-map.json index ac621709..097f98fb 100644 --- a/tests/sandbox/ocr-complete/TSTONE001/chart-type-map.json +++ b/tests/sandbox/ocr-complete/TSTONE001/chart-type-map.json @@ -66,4 +66,4 @@ "recommended_guides": [] } ] -} \ No newline at end of file +} diff --git a/tests/sandbox/ocr-complete/TSTONE001/figure-map.json b/tests/sandbox/ocr-complete/TSTONE001/figure-map.json index f1ff8921..950646a9 100644 --- a/tests/sandbox/ocr-complete/TSTONE001/figure-map.json +++ b/tests/sandbox/ocr-complete/TSTONE001/figure-map.json @@ -77,4 +77,4 @@ ], "supplementary_figures": [], "supplementary_tables": [] -} \ No newline at end of file +} diff --git a/tests/sandbox/ocr-complete/TSTONE001/json/result.json b/tests/sandbox/ocr-complete/TSTONE001/json/result.json new file mode 100644 index 00000000..a85aab82 --- /dev/null +++ b/tests/sandbox/ocr-complete/TSTONE001/json/result.json @@ -0,0 +1,26 @@ +{ + "pages": [ + { + "page_num": 1, + "markdown": "Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair\n\nJohn Smith, Jane Doe\nJournal of Shoulder and Elbow Surgery, 2024\n\n## Abstract\n\nThis study compares the biomechanical properties of various suture anchor configurations used in rotator cuff repair surgery.\n\n## Introduction\n\nRotator cuff tears are a common shoulder pathology. Surgical repair using suture anchors remains the gold standard treatment." + }, + { + "page_num": 2, + "markdown": "## Methods\n\n### Patient Demographics\n\nTable 1: Patient demographics and baseline characteristics (n=45).\n\n### Biomechanical Testing\n\nFigure 2: Biomechanical testing setup. (A) Custom loading fixture. (B) Cyclic loading protocol.\n\n## Results\n\n### Load to Failure\n\nFigure 3: Load to failure comparison. Error bars represent standard deviation. *p < 0.05 vs single row." + }, + { + "page_num": 3, + "markdown": "### Stiffness Analysis\n\nFigure 4: Stiffness comparison between repair techniques.\n\nTable 2: Biomechanical properties summary.\n\n## Discussion\n\nThe double row technique demonstrated significantly higher load to failure compared to single row repair.\n\n## Conclusion\n\nDouble row suture anchor fixation provides superior biomechanical properties for rotator cuff repair." + } + ], + "figures": [ + {"page": 1, "filename": "page_001_fig_01.png", "caption": "Overview of suture anchor placement techniques."}, + {"page": 2, "filename": "page_002_fig_02.png", "caption": "Biomechanical testing setup."}, + {"page": 3, "filename": "page_003_fig_03.png", "caption": "Load to failure comparison."}, + {"page": 3, "filename": "page_003_fig_04.png", "caption": "Stiffness comparison between repair techniques."} + ], + "tables": [ + {"page": 2, "filename": "page_002_table_01.png", "caption": "Patient demographics and baseline characteristics."}, + {"page": 3, "filename": "page_003_table_02.png", "caption": "Biomechanical properties summary."} + ] +} diff --git a/tests/sandbox/ocr-complete/TSTONE001/meta.json b/tests/sandbox/ocr-complete/TSTONE001/meta.json index 057f2a0c..521be293 100644 --- a/tests/sandbox/ocr-complete/TSTONE001/meta.json +++ b/tests/sandbox/ocr-complete/TSTONE001/meta.json @@ -3,4 +3,4 @@ "ocr_status": "done", "page_count": 3, "generated_at": "2026-04-24T05:04:53.026897+00:00" -} \ No newline at end of file +} diff --git a/tests/test_base_preservation.py b/tests/test_base_preservation.py index a646212a..02d44221 100644 --- a/tests/test_base_preservation.py +++ b/tests/test_base_preservation.py @@ -1,13 +1,12 @@ """Tests for incremental merge and user-view preservation (Phase 3, Plan 02).""" + import pytest -from pathlib import Path + from paperforge.worker.base_views import ( + PAPERFORGE_VIEW_PREFIX, + build_base_views, ensure_base_views, merge_base_views, - build_base_views, - substitute_config_placeholders, - PAPERFORGE_VIEW_PREFIX, - STANDARD_VIEW_NAMES, ) from paperforge.worker.sync import slugify_filename @@ -46,13 +45,16 @@ class TestIncrementalMerge: content = domain_base.read_text(encoding="utf-8") assert content.count("type: table") == 8 - user_custom = content + ''' + user_custom = ( + content + + """ - type: table name: "My Custom Dashboard" order: - title - year -''' +""" + ) domain_base.write_text(user_custom, encoding="utf-8") ensure_base_views(self.vault, self.paths, self.config, force=False) @@ -84,12 +86,15 @@ class TestIncrementalMerge: ensure_base_views(self.vault, self.paths, self.config, force=False) content1 = domain_base.read_text(encoding="utf-8") - user_custom = content1 + ''' + user_custom = ( + content1 + + """ - type: table name: "My Custom View" order: - title -''' +""" + ) domain_base.write_text(user_custom, encoding="utf-8") ensure_base_views(self.vault, self.paths, self.config, force=True) @@ -106,15 +111,14 @@ class TestIncrementalMerge: content1 = domain_base.read_text(encoding="utf-8") modified = content1.replace( - 'filter: \'ocr_status = "done"\'', - 'filter: \'ocr_status = "done" AND has_pdf = true\'' + "filter: 'ocr_status = \"done\"'", "filter: 'ocr_status = \"done\" AND has_pdf = true'" ) domain_base.write_text(modified, encoding="utf-8") ensure_base_views(self.vault, self.paths, self.config, force=False) refreshed = domain_base.read_text(encoding="utf-8") - assert 'filter: \'ocr_status = "done"\'' in refreshed + assert "filter: 'ocr_status = \"done\"'" in refreshed assert "has_pdf = true" not in refreshed def test_new_domain_base_is_created_on_first_run(self): @@ -202,7 +206,7 @@ class TestLiteratureHubBase: class TestMergeBaseViews: def test_merge_base_views_preserves_user_views(self): """merge_base_views preserves views without PAPERFORGE_VIEW_PREFIX.""" - existing = ''' + existing = """ filters: and: - file.inFolder("骨科") @@ -221,7 +225,7 @@ views: name: "My Custom View" order: - title -''' +""" views = build_base_views("骨科") result = merge_base_views(existing, views) @@ -240,7 +244,7 @@ views: def test_merge_base_views_unknown_placeholder_unchanged(self): """Unknown placeholders in content are left unchanged after merge.""" - existing = ''' + existing = """ filters: and: - file.inFolder("骨科") @@ -249,7 +253,7 @@ views: name: "控制面板" order: - file.name -''' +""" views = build_base_views("骨科") result = merge_base_views(existing, views) diff --git a/tests/test_base_views.py b/tests/test_base_views.py index e18018e9..651725c8 100644 --- a/tests/test_base_views.py +++ b/tests/test_base_views.py @@ -1,6 +1,5 @@ """Tests for the 8-view Base generation system (Phase 3, Plan 01).""" -import pytest -from pathlib import Path + from paperforge.worker.base_views import ( build_base_views, substitute_config_placeholders, @@ -15,10 +14,7 @@ class TestBuildBaseViews: def test_all_view_names_present(self): views = build_base_views("骨科") names = [v["name"] for v in views] - expected = [ - "控制面板", "推荐分析", "待 OCR", "OCR 完成", - "待深度阅读", "深度阅读完成", "正式卡片", "全记录" - ] + expected = ["控制面板", "推荐分析", "待 OCR", "OCR 完成", "待深度阅读", "深度阅读完成", "正式卡片", "全记录"] assert names == expected def test_each_view_has_required_keys(self): @@ -38,7 +34,7 @@ class TestBuildBaseViews: def test_pending_ocr_filter(self): views = build_base_views("骨科") pending = next(v for v in views if v["name"] == "待 OCR") - assert 'do_ocr = true' in pending["filter"] + assert "do_ocr = true" in pending["filter"] assert 'ocr_status = "pending"' in pending["filter"] def test_ocr_done_filter(self): @@ -61,10 +57,7 @@ class TestSubstituteConfigPlaceholders: vault.mkdir() lib_rec = vault / "03_Resources" / "LiteratureControl" / "library-records" lib_rec.mkdir(parents=True) - result = substitute_config_placeholders( - content, - {"library_records": lib_rec, "vault": vault} - ) + result = substitute_config_placeholders(content, {"library_records": lib_rec, "vault": vault}) assert "${LIBRARY_RECORDS}" not in result assert "03_Resources/LiteratureControl/library-records" in result @@ -77,8 +70,7 @@ class TestSubstituteConfigPlaceholders: lib_rec.mkdir() lit.mkdir() result = substitute_config_placeholders( - content, - {"library_records": lib_rec, "literature": lit, "vault": vault} + content, {"library_records": lib_rec, "literature": lit, "vault": vault} ) assert "${LIBRARY_RECORDS}" not in result assert "${LITERATURE}" not in result @@ -94,8 +86,5 @@ class TestSubstituteConfigPlaceholders: vault.mkdir() lib_rec = vault / "LR" lib_rec.mkdir() - result = substitute_config_placeholders( - content, - {"library_records": lib_rec, "vault": vault} - ) + result = substitute_config_placeholders(content, {"library_records": lib_rec, "vault": vault}) assert "\\" not in result # Should use forward slash diff --git a/tests/test_cli_paths.py b/tests/test_cli_paths.py index 19079848..9ccce7bd 100644 --- a/tests/test_cli_paths.py +++ b/tests/test_cli_paths.py @@ -4,7 +4,6 @@ import io import json from contextlib import redirect_stdout -from pathlib import Path import pytest diff --git a/tests/test_cli_worker_dispatch.py b/tests/test_cli_worker_dispatch.py index b2a7251a..75b94eee 100644 --- a/tests/test_cli_worker_dispatch.py +++ b/tests/test_cli_worker_dispatch.py @@ -1,11 +1,11 @@ # Tests for paperforge CLI worker dispatch # These tests prove the locked command surface without invoking real workers. -import pytest import json -import sys from pathlib import Path -from unittest.mock import patch, MagicMock +from unittest.mock import patch + +import pytest # ---------------------------------------------------------------------- # Worker function stubs — capture calls for assertion @@ -33,7 +33,7 @@ def stub_run_deep_reading(vault: Path, verbose: bool = False) -> int: return 0 -def stub_run_ocr(vault: Path, verbose: bool = False) -> int: +def stub_run_ocr(vault: Path, verbose: bool = False, no_progress: bool = False) -> int: CAPTURED_CALLS.append(("run_ocr", vault)) return 0 @@ -69,7 +69,9 @@ def mock_vault(tmp_path): def test_status_dispatch(clean_captured, mock_vault): """main(['--vault', vault, 'status']) calls run_status.""" import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch.object(cli, "run_status", stub_run_status): @@ -82,7 +84,9 @@ def test_status_dispatch(clean_captured, mock_vault): def test_selection_sync_dispatch(clean_captured, mock_vault): """main(['--vault', vault, 'selection-sync']) calls run_selection_sync.""" import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch.object(cli, "run_selection_sync", stub_run_selection_sync): @@ -95,7 +99,9 @@ def test_selection_sync_dispatch(clean_captured, mock_vault): def test_index_refresh_dispatch(clean_captured, mock_vault): """main(['--vault', vault, 'index-refresh']) calls run_index_refresh.""" import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch.object(cli, "run_index_refresh", stub_run_index_refresh): @@ -108,7 +114,9 @@ def test_index_refresh_dispatch(clean_captured, mock_vault): def test_deep_reading_dispatch(clean_captured, mock_vault): """main(['--vault', vault, 'deep-reading']) calls run_deep_reading.""" import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch.object(cli, "run_deep_reading", stub_run_deep_reading): @@ -121,7 +129,9 @@ def test_deep_reading_dispatch(clean_captured, mock_vault): def test_ocr_run_dispatch(clean_captured, mock_vault): """main(['--vault', vault, 'ocr', 'run']) calls run_ocr.""" import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch.object(cli, "run_ocr", stub_run_ocr): @@ -134,7 +144,9 @@ def test_ocr_run_dispatch(clean_captured, mock_vault): def test_ocr_alias_dispatch(clean_captured, mock_vault): """main(['--vault', vault, 'ocr']) calls run_ocr (alias for 'ocr run').""" import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch.object(cli, "run_ocr", stub_run_ocr): @@ -147,7 +159,9 @@ def test_ocr_alias_dispatch(clean_captured, mock_vault): def test_ocr_doctor_dispatch(clean_captured, mock_vault): """main(['--vault', vault, 'ocr', 'doctor']) calls _cmd_ocr_doctor.""" import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch.object(cli, "_cmd_ocr_doctor", lambda vault, args: 0): diff --git a/tests/test_command_docs.py b/tests/test_command_docs.py index db745139..5bcfaa5e 100644 --- a/tests/test_command_docs.py +++ b/tests/test_command_docs.py @@ -1,4 +1,3 @@ -# -*- coding: utf-8 -*- """ Test suite for PaperForge Lite command documentation. @@ -8,11 +7,11 @@ instead of unresolved token paths. Scope: User-run command examples in markdown files. Excluded: Architecture diagrams, frontmatter field examples in AGENTS.md. """ + from __future__ import annotations import re from pathlib import Path -from typing import Optional import pytest @@ -59,6 +58,7 @@ def code_block_lines(content: str) -> list[str]: # Fixtures # --------------------------------------------------------------------------- + @pytest.fixture def command_docs() -> dict[str, Path]: base = REPO_ROOT / "command" @@ -85,6 +85,7 @@ def user_facing_docs() -> dict[str, Path]: # Task 1 tests — stable commands present # --------------------------------------------------------------------------- + class TestStableCommandsPresent: """Verify command docs contain stable paperforge commands.""" @@ -107,10 +108,9 @@ class TestStableCommandsPresent: code_lines = code_block_lines(content) # Join all lines for substring search combined = "\n".join(code_lines) - assert expected_cmd in combined, ( - f"[{doc_key}] Expected stable command '{expected_cmd}' " - f"not found in code blocks. Code lines:\n{code_lines}" - ) + assert ( + expected_cmd in combined + ), f"[{doc_key}] Expected stable command '{expected_cmd}' not found in code blocks. Code lines:\n{code_lines}" def test_pf_deep_mentions_paperforge_deep_reading( self, @@ -118,9 +118,9 @@ class TestStableCommandsPresent: ) -> None: """pf-deep.md must mention 'paperforge deep-reading' for queue preflight.""" content = read_fileutf8(command_docs["pf-deep"]) - assert "paperforge deep-reading" in content, ( - "pf-deep.md must mention 'paperforge deep-reading' for queue preflight" - ) + assert ( + "paperforge deep-reading" in content + ), "pf-deep.md must mention 'paperforge deep-reading' for queue preflight" def test_pf_deep_mentions_paperforge_paths_json( self, @@ -128,16 +128,16 @@ class TestStableCommandsPresent: ) -> None: """pf-deep.md must reference 'paperforge paths --json' for path resolution.""" content = read_fileutf8(command_docs["pf-deep"]) - assert "paperforge paths --json" in content or "paperforge paths" in content, ( - "pf-deep.md must reference 'paperforge paths' or 'paperforge paths --json' " - "for script path discovery" - ) + assert ( + "paperforge paths --json" in content or "paperforge paths" in content + ), "pf-deep.md must reference 'paperforge paths' or 'paperforge paths --json' for script path discovery" # --------------------------------------------------------------------------- # Task 1 tests — unresolved tokens absent from user-run examples # --------------------------------------------------------------------------- + class TestUnresolvedTokensAbsentFromUserRunExamples: """ Limit unresolved-token rejection to user-run command examples. @@ -180,10 +180,9 @@ class TestUnresolvedTokensAbsentFromUserRunExamples: code_lines = code_block_lines(content) combined = "\n".join(code_lines) match = self.LEGACY_PYTHON_LITERATURE_PIPELINE.search(combined) - assert match is None, ( - f"[README] Found legacy unresolved token path in code blocks: {match.group(0)!r}\n" - f"Code lines:\n{code_lines}" - ) + assert ( + match is None + ), f"[README] Found legacy unresolved token path in code blocks: {match.group(0)!r}\nCode lines:\n{code_lines}" def test_installation_no_legacy_python_literature_pipeline_in_examples( self, @@ -204,6 +203,7 @@ class TestUnresolvedTokensAbsentFromUserRunExamples: # Task 1 tests — paperforge paths/status examples in user-facing docs # --------------------------------------------------------------------------- + class TestPaperforgeCommandExamplesInUserDocs: """README, INSTALLATION, setup-guide must show stable paperforge command examples.""" @@ -223,16 +223,16 @@ class TestPaperforgeCommandExamplesInUserDocs: ) -> None: """User-facing docs must contain at least one 'paperforge status' or 'paperforge paths' example.""" content = read_fileutf8(user_facing_docs[doc_key]) - assert re.search(pattern, content), ( - f"[{doc_key}] Expected to find stable paperforge command pattern {pattern!r} " - f"in user-facing documentation." - ) + assert re.search( + pattern, content + ), f"[{doc_key}] Expected to find stable paperforge command pattern {pattern!r} in user-facing documentation." # --------------------------------------------------------------------------- # New tests — unified commands present in user-facing docs # --------------------------------------------------------------------------- + class TestUnifiedCommandsInUserDocs: """AGENTS.md, README must reference new unified commands, not old ones.""" @@ -296,9 +296,7 @@ class TestUnifiedCommandsInUserDocs: if "命令迁移说明" in line or "迁移" in line.lower() or "migration" in line.lower(): migration_started = True if "paperforge ocr run" in line and not migration_started: - pytest.fail( - f"[{doc_key}] Found old command 'paperforge ocr run' outside migration section: {line}" - ) + pytest.fail(f"[{doc_key}] Found old command 'paperforge ocr run' outside migration section: {line}") # --------------------------------------------------------------------------- diff --git a/tests/test_config.py b/tests/test_config.py index db4eae04..62c3fc87 100644 --- a/tests/test_config.py +++ b/tests/test_config.py @@ -6,19 +6,19 @@ These tests prove: - CONF-03: All consumers use the same resolver - CONF-04: Top-level and nested paperforge.json keys are both honored """ + from __future__ import annotations import json -import os from pathlib import Path import pytest - # --------------------------------------------------------------------------- # Fixtures # --------------------------------------------------------------------------- + @pytest.fixture def minimal_vault(tmp_path: Path) -> Path: """A vault with no paperforge.json.""" @@ -32,15 +32,18 @@ def vault_with_nested_config(tmp_path: Path) -> Path: vault.mkdir() pf = vault / "paperforge.json" pf.write_text( - json.dumps({ - "vault_config": { - "system_dir": "CustomSystem", - "resources_dir": "CustomResources", - "literature_dir": "CustomLiterature", - "control_dir": "CustomControl", - "base_dir": "CustomBases", - } - }, ensure_ascii=False), + json.dumps( + { + "vault_config": { + "system_dir": "CustomSystem", + "resources_dir": "CustomResources", + "literature_dir": "CustomLiterature", + "control_dir": "CustomControl", + "base_dir": "CustomBases", + } + }, + ensure_ascii=False, + ), encoding="utf-8", ) return vault @@ -53,18 +56,21 @@ def vault_with_top_level_config(tmp_path: Path) -> Path: vault.mkdir() pf = vault / "paperforge.json" pf.write_text( - json.dumps({ - "vault_config": { - "system_dir": "NestedSystem", - "resources_dir": "NestedResources", + json.dumps( + { + "vault_config": { + "system_dir": "NestedSystem", + "resources_dir": "NestedResources", + }, + # Legacy top-level keys — these take precedence per CONF-04 + "system_dir": "LegacySystem", + "resources_dir": "LegacyResources", + "literature_dir": "LegacyLiterature", + "control_dir": "LegacyControl", + "base_dir": "LegacyBases", }, - # Legacy top-level keys — these take precedence per CONF-04 - "system_dir": "LegacySystem", - "resources_dir": "LegacyResources", - "literature_dir": "LegacyLiterature", - "control_dir": "LegacyControl", - "base_dir": "LegacyBases", - }, ensure_ascii=False), + ensure_ascii=False, + ), encoding="utf-8", ) return vault @@ -108,40 +114,48 @@ def env_dict() -> dict[str, str]: # DEFAULT_CONFIG tests — truths from must_haves # --------------------------------------------------------------------------- + def test_default_system_dir_is_99_System(): """Built-in default for system_dir must be '99_System'.""" from paperforge.config import DEFAULT_CONFIG + assert DEFAULT_CONFIG["system_dir"] == "99_System" def test_default_resources_dir_is_03_Resources(): """Built-in default for resources_dir must be '03_Resources'.""" from paperforge.config import DEFAULT_CONFIG + assert DEFAULT_CONFIG["resources_dir"] == "03_Resources" def test_default_literature_dir(): from paperforge.config import DEFAULT_CONFIG + assert DEFAULT_CONFIG["literature_dir"] == "Literature" def test_default_control_dir(): from paperforge.config import DEFAULT_CONFIG + assert DEFAULT_CONFIG["control_dir"] == "LiteratureControl" def test_default_base_dir(): from paperforge.config import DEFAULT_CONFIG + assert DEFAULT_CONFIG["base_dir"] == "05_Bases" def test_default_skill_dir(): from paperforge.config import DEFAULT_CONFIG + assert DEFAULT_CONFIG["skill_dir"] == ".opencode/skills" def test_default_command_dir(): from paperforge.config import DEFAULT_CONFIG + assert DEFAULT_CONFIG["command_dir"] == ".opencode/command" @@ -149,9 +163,11 @@ def test_default_command_dir(): # ENV_KEYS coverage — CONF-01 # --------------------------------------------------------------------------- + def test_env_keys_has_all_required_overrides(): """All PAPERFORGE_* env vars must be registered in ENV_KEYS.""" from paperforge.config import ENV_KEYS + required = { "PAPERFORGE_VAULT", "PAPERFORGE_SYSTEM_DIR", @@ -170,6 +186,7 @@ def test_env_keys_has_all_required_overrides(): # load_vault_config precedence — CONF-01, CONF-04 # --------------------------------------------------------------------------- + def test_env_overrides_nested_json(env_dict): """PAPERFORGE_SYSTEM_DIR overrides nested vault_config.system_dir (CONF-01).""" from paperforge.config import load_vault_config @@ -186,12 +203,13 @@ def test_env_overrides_nested_json(env_dict): env_dict["PAPERFORGE_SYSTEM_DIR"] = "EnvSystem" cfg = load_vault_config(vault, env=env_dict) - assert cfg["system_dir"] == "EnvSystem", ( - f"Expected 'EnvSystem' from PAPERFORGE_SYSTEM_DIR, got '{cfg['system_dir']}'" - ) + assert ( + cfg["system_dir"] == "EnvSystem" + ), f"Expected 'EnvSystem' from PAPERFORGE_SYSTEM_DIR, got '{cfg['system_dir']}'" # Cleanup import shutil + shutil.rmtree(vault, ignore_errors=True) @@ -207,11 +225,12 @@ def test_explicit_overrides_win_over_env(env_dict): overrides = {"system_dir": "OverrideSystem"} cfg = load_vault_config(vault, env=env_dict, overrides=overrides) - assert cfg["system_dir"] == "OverrideSystem", ( - f"Expected 'OverrideSystem' from explicit override, got '{cfg['system_dir']}'" - ) + assert ( + cfg["system_dir"] == "OverrideSystem" + ), f"Expected 'OverrideSystem' from explicit override, got '{cfg['system_dir']}'" import shutil + shutil.rmtree(vault, ignore_errors=True) @@ -237,17 +256,17 @@ def test_top_level_keys_override_nested_for_backward_compat(tmp_path: Path): vault = tmp_path / "vault_legacy" vault.mkdir() (vault / "paperforge.json").write_text( - json.dumps({ - "vault_config": {"system_dir": "NestedSystem"}, - "system_dir": "LegacySystem", - }), + json.dumps( + { + "vault_config": {"system_dir": "NestedSystem"}, + "system_dir": "LegacySystem", + } + ), encoding="utf-8", ) cfg = load_vault_config(vault) - assert cfg["system_dir"] == "LegacySystem", ( - f"Expected 'LegacySystem' from top-level key, got '{cfg['system_dir']}'" - ) + assert cfg["system_dir"] == "LegacySystem", f"Expected 'LegacySystem' from top-level key, got '{cfg['system_dir']}'" def test_defaults_used_when_no_json(tmp_path: Path): @@ -266,6 +285,7 @@ def test_defaults_used_when_no_json(tmp_path: Path): # paperforge_paths key inventory — CONF-02, CONF-03 # --------------------------------------------------------------------------- + def test_paperforge_paths_returns_exact_keys(tmp_path: Path): """paperforge_paths() must return exactly the required user-facing keys.""" from paperforge.config import paperforge_paths @@ -369,11 +389,13 @@ def test_paperforge_paths_includes_ld_deep_script(tmp_path: Path): # paths_as_strings — JSON serializable output # --------------------------------------------------------------------------- + def test_paths_as_strings_returns_string_values(): """paths_as_strings must return dict[str, str] with all values as strings.""" - from paperforge.config import paths_as_strings from pathlib import Path + from paperforge.config import paths_as_strings + paths = { "vault": Path("/some/vault"), "system": Path("/some/vault/99_System"), @@ -404,6 +426,7 @@ def test_paths_as_strings_returns_string_values(): # resolve_vault precedence # --------------------------------------------------------------------------- + def test_resolve_vault_precedence_explicit_first(tmp_path: Path): """resolve_vault returns explicit cli_vault first.""" from paperforge.config import resolve_vault diff --git a/tests/test_doctor.py b/tests/test_doctor.py index c3e4a5eb..b1a2f49c 100644 --- a/tests/test_doctor.py +++ b/tests/test_doctor.py @@ -1,9 +1,9 @@ -import pytest import json -import sys from pathlib import Path from unittest.mock import patch +import pytest + def stub_run_doctor(vault: Path) -> int: return 0 @@ -11,7 +11,9 @@ def stub_run_doctor(vault: Path) -> int: def test_doctor_command_exists(clean_captured, mock_vault): import importlib + import paperforge.cli as cli + importlib.reload(cli) with patch("paperforge.worker.status.run_doctor", stub_run_doctor): @@ -22,17 +24,21 @@ def test_doctor_command_exists(clean_captured, mock_vault): def test_doctor_python_check(): - from paperforge.worker.status import run_doctor import inspect + + from paperforge.worker.status import run_doctor + sig = inspect.signature(run_doctor) assert "vault" in sig.parameters def test_doctor_returns_int(): - from paperforge.worker.status import run_doctor import inspect - sig = inspect.signature(run_doctor) - assert sig.return_annotation in (int, "int") or True + + from paperforge.worker.status import run_doctor + + inspect.signature(run_doctor) + assert True @pytest.fixture @@ -57,6 +63,7 @@ def mock_vault(tmp_path): def test_doctor_on_empty_vault(tmp_path, capsys): from paperforge.worker.status import run_doctor + pf_cfg = { "system_dir": "99_System", "resources_dir": "03_Resources", diff --git a/tests/test_ld_deep_config.py b/tests/test_ld_deep_config.py index 9f5e19cb..ea2e336e 100644 --- a/tests/test_ld_deep_config.py +++ b/tests/test_ld_deep_config.py @@ -1,12 +1,13 @@ """Test compatibility: ld_deep uses shared resolver for path construction.""" + from __future__ import annotations import json import sys +from importlib.util import module_from_spec, spec_from_file_location from pathlib import Path import pytest -from importlib.util import spec_from_file_location, module_from_spec # Pre-load ld_deep so its functions are available _REPO_ROOT = Path(__file__).parent.parent @@ -28,7 +29,7 @@ def tmp_vault(tmp_path: Path) -> Path: (paperforge / "ocr").mkdir(parents=True) resources = tmp_path / "03_Resources" - literature = resources / "Literature" + resources / "Literature" control = resources / "LiteratureControl" (control / "library-records").mkdir(parents=True) @@ -58,19 +59,20 @@ class TestDeepLoadVaultConfig: def test_load_vault_config_keys(self, tmp_vault: Path) -> None: """_load_vault_config returns same keys as shared resolver.""" - from paperforge.config import load_vault_config as shared_load import ld_deep + from paperforge.config import load_vault_config as shared_load + shared_cfg = shared_load(tmp_vault) ld_cfg = ld_deep._load_vault_config(tmp_vault) - assert set(ld_cfg.keys()) == set(shared_cfg.keys()), ( - f"Key mismatch: ld_deep={set(ld_cfg.keys())} vs shared={set(shared_cfg.keys())}" - ) + assert set(ld_cfg.keys()) == set( + shared_cfg.keys() + ), f"Key mismatch: ld_deep={set(ld_cfg.keys())} vs shared={set(shared_cfg.keys())}" for key in shared_cfg: - assert ld_cfg.get(key) == shared_cfg.get(key), ( - f"Key '{key}' differs: ld_deep={ld_cfg.get(key)!r} vs shared={shared_cfg.get(key)!r}" - ) + assert ld_cfg.get(key) == shared_cfg.get( + key + ), f"Key '{key}' differs: ld_deep={ld_cfg.get(key)!r} vs shared={shared_cfg.get(key)!r}" def test_env_override_respected(self, tmp_vault: Path, monkeypatch) -> None: """PAPERFORGE_SYSTEM_DIR env var is respected.""" @@ -93,13 +95,12 @@ class TestDeepPaperforgePaths: for key in ["ocr", "records", "literature"]: assert key in paths, f"Missing expected key: {key}" - def test_paperforge_paths_values_match_shared_resolver( - self, tmp_vault: Path - ) -> None: + def test_paperforge_paths_values_match_shared_resolver(self, tmp_vault: Path) -> None: """Values for ocr, records, literature match paperforge_paths().""" - from paperforge.config import paperforge_paths as shared_paths import ld_deep + from paperforge.config import paperforge_paths as shared_paths + shared = shared_paths(tmp_vault) ld_paths = ld_deep._paperforge_paths(tmp_vault) diff --git a/tests/test_ocr_classify.py b/tests/test_ocr_classify.py index 0c9554f9..b6a382f4 100644 --- a/tests/test_ocr_classify.py +++ b/tests/test_ocr_classify.py @@ -2,12 +2,12 @@ Maps exceptions to (state, suggestion) pairs per the D-03 taxonomy. """ + from __future__ import annotations import json from unittest.mock import MagicMock -import pytest import requests from paperforge.ocr_diagnostics import classify_error diff --git a/tests/test_ocr_doctor.py b/tests/test_ocr_doctor.py index f28db03f..a9e5f2f2 100644 --- a/tests/test_ocr_doctor.py +++ b/tests/test_ocr_doctor.py @@ -2,9 +2,7 @@ import json import os -from unittest.mock import patch, MagicMock - -import pytest +from unittest.mock import MagicMock, patch from paperforge.ocr_diagnostics import ocr_doctor @@ -123,15 +121,17 @@ def test_l4_live_success(): delete_resp = MagicMock() delete_resp.status_code = 204 - with patch.dict(os.environ, env, clear=True): - with patch( + with ( + patch.dict(os.environ, env, clear=True), + patch( "paperforge.ocr_diagnostics.requests.get", side_effect=[get_resp] + [poll_resp] * 10, - ): - with patch("paperforge.ocr_diagnostics.requests.post", return_value=post_resp): - with patch("paperforge.ocr_diagnostics.requests.delete", return_value=delete_resp): - with patch("paperforge.ocr_diagnostics.time.sleep"): - result = ocr_doctor(config=None, live=True) + ), + patch("paperforge.ocr_diagnostics.requests.post", return_value=post_resp), + ): + with patch("paperforge.ocr_diagnostics.requests.delete", return_value=delete_resp): + with patch("paperforge.ocr_diagnostics.time.sleep"): + result = ocr_doctor(config=None, live=True) assert result["level"] == 4 assert result["passed"] is True @@ -153,15 +153,17 @@ def test_l4_live_failure(): delete_resp = MagicMock() delete_resp.status_code = 204 - with patch.dict(os.environ, env, clear=True): - with patch( + with ( + patch.dict(os.environ, env, clear=True), + patch( "paperforge.ocr_diagnostics.requests.get", side_effect=[get_resp] + [poll_resp] * 10, - ): - with patch("paperforge.ocr_diagnostics.requests.post", return_value=post_resp): - with patch("paperforge.ocr_diagnostics.requests.delete", return_value=delete_resp): - with patch("paperforge.ocr_diagnostics.time.sleep"): - result = ocr_doctor(config=None, live=True) + ), + patch("paperforge.ocr_diagnostics.requests.post", return_value=post_resp), + ): + with patch("paperforge.ocr_diagnostics.requests.delete", return_value=delete_resp): + with patch("paperforge.ocr_diagnostics.time.sleep"): + result = ocr_doctor(config=None, live=True) assert result["level"] == 4 assert result["passed"] is False diff --git a/tests/test_ocr_preflight.py b/tests/test_ocr_preflight.py index f210471e..08947fca 100644 --- a/tests/test_ocr_preflight.py +++ b/tests/test_ocr_preflight.py @@ -3,13 +3,12 @@ Verifies that missing PDFs are caught before API submission and produce ocr_status: nopdf. """ + from __future__ import annotations from pathlib import Path from unittest.mock import MagicMock, patch -import pytest - class TestOcrPreflight: """Tests for PDF preflight behavior in run_ocr().""" @@ -36,59 +35,51 @@ class TestOcrPreflight: mock_paths["exports"].mkdir() mock_paths["ocr"].mkdir() - with patch( - "paperforge.worker.ocr.pipeline_paths", - return_value=mock_paths, - ): - with patch( + with ( + patch( + "paperforge.worker.ocr.pipeline_paths", + return_value=mock_paths, + ), + patch( "paperforge.worker.ocr.load_control_actions", return_value={"ABC123": {"do_ocr": True}}, - ): - with patch( - "paperforge.worker.ocr.load_export_rows", - return_value=[ - { - "key": "ABC123", - "attachments": [], - "title": "No PDF Paper", - } - ], - ): - with patch( - "paperforge.worker.ocr.sync_ocr_queue", - return_value=[ - { - "zotero_key": "ABC123", - "has_pdf": False, - "pdf_path": "", - } - ], - ): - with patch( - "paperforge.worker.ocr.ensure_ocr_meta", - return_value={}, - ): - with patch( - "paperforge.worker.ocr.write_json" - ) as mock_write: - with patch( - "paperforge.worker.sync.run_selection_sync" - ): - with patch( - "paperforge.worker.sync.run_index_refresh" - ): - from paperforge.worker.ocr import ( - run_ocr, - ) + ), + patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": "ABC123", + "attachments": [], + "title": "No PDF Paper", + } + ], + ), + patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + { + "zotero_key": "ABC123", + "has_pdf": False, + "pdf_path": "", + } + ], + ), + patch( + "paperforge.worker.ocr.ensure_ocr_meta", + return_value={}, + ), + patch("paperforge.worker.ocr.write_json") as mock_write, + patch("paperforge.worker.sync.run_selection_sync"), + patch("paperforge.worker.sync.run_index_refresh"), + ): + from paperforge.worker.ocr import ( + run_ocr, + ) - run_ocr(vault) + run_ocr(vault) calls = mock_write.call_args_list - assert any( - call[0][1].get("ocr_status") == "nopdf" - for call in calls - if isinstance(call[0][1], dict) - ) + assert any(call[0][1].get("ocr_status") == "nopdf" for call in calls if isinstance(call[0][1], dict)) def test_missing_pdf_file_sets_nopdf(self, tmp_path: Path) -> None: """has_pdf=True but file missing -> ocr_status: nopdf.""" @@ -97,64 +88,56 @@ class TestOcrPreflight: mock_paths["exports"].mkdir() mock_paths["ocr"].mkdir() - with patch( - "paperforge.worker.ocr.pipeline_paths", - return_value=mock_paths, - ): - with patch( + with ( + patch( + "paperforge.worker.ocr.pipeline_paths", + return_value=mock_paths, + ), + patch( "paperforge.worker.ocr.load_control_actions", return_value={"ABC123": {"do_ocr": True}}, - ): - with patch( - "paperforge.worker.ocr.load_export_rows", - return_value=[ - { - "key": "ABC123", - "attachments": [ - { - "contentType": "application/pdf", - "path": str(tmp_path / "nonexistent.pdf"), - } - ], - "title": "Missing PDF Paper", - } - ], - ): - with patch( - "paperforge.worker.ocr.sync_ocr_queue", - return_value=[ + ), + patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": "ABC123", + "attachments": [ { - "zotero_key": "ABC123", - "has_pdf": True, - "pdf_path": str(tmp_path / "nonexistent.pdf"), + "contentType": "application/pdf", + "path": str(tmp_path / "nonexistent.pdf"), } ], - ): - with patch( - "paperforge.worker.ocr.ensure_ocr_meta", - return_value={}, - ): - with patch( - "paperforge.worker.ocr.write_json" - ) as mock_write: - with patch( - "paperforge.worker.sync.run_selection_sync" - ): - with patch( - "paperforge.worker.sync.run_index_refresh" - ): - from paperforge.worker.ocr import ( - run_ocr, - ) + "title": "Missing PDF Paper", + } + ], + ), + patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + { + "zotero_key": "ABC123", + "has_pdf": True, + "pdf_path": str(tmp_path / "nonexistent.pdf"), + } + ], + ), + patch( + "paperforge.worker.ocr.ensure_ocr_meta", + return_value={}, + ), + patch("paperforge.worker.ocr.write_json") as mock_write, + patch("paperforge.worker.sync.run_selection_sync"), + patch("paperforge.worker.sync.run_index_refresh"), + ): + from paperforge.worker.ocr import ( + run_ocr, + ) - run_ocr(vault) + run_ocr(vault) calls = mock_write.call_args_list - assert any( - call[0][1].get("ocr_status") == "nopdf" - for call in calls - if isinstance(call[0][1], dict) - ) + assert any(call[0][1].get("ocr_status") == "nopdf" for call in calls if isinstance(call[0][1], dict)) def test_valid_pdf_proceeds(self, tmp_path: Path) -> None: """Valid resolved PDF -> proceeds to API submission with resolved path.""" @@ -165,68 +148,57 @@ class TestOcrPreflight: mock_paths["exports"].mkdir() mock_paths["ocr"].mkdir() - with patch( - "paperforge.worker.ocr.pipeline_paths", - return_value=mock_paths, - ): - with patch( + with ( + patch( + "paperforge.worker.ocr.pipeline_paths", + return_value=mock_paths, + ), + patch( "paperforge.worker.ocr.load_control_actions", return_value={"ABC123": {"do_ocr": True}}, - ): - with patch( - "paperforge.worker.ocr.load_export_rows", - return_value=[ - { - "key": "ABC123", - "attachments": [ - { - "contentType": "application/pdf", - "path": str(pdf), - } - ], - "title": "Valid PDF Paper", - } - ], - ): - with patch( - "paperforge.worker.ocr.sync_ocr_queue", - return_value=[ + ), + patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": "ABC123", + "attachments": [ { - "zotero_key": "ABC123", - "has_pdf": True, - "pdf_path": str(pdf), + "contentType": "application/pdf", + "path": str(pdf), } ], - ): - with patch( - "paperforge.worker.ocr.ensure_ocr_meta", - return_value={}, - ): - with patch( - "paperforge.worker.ocr.write_json" - ): - with patch("builtins.open") as mock_open: - with patch( - "paperforge.worker.ocr.requests.post" - ) as mock_post: - mock_post.return_value = MagicMock() - mock_post.return_value.json.return_value = { - "data": {"jobId": "123"} - } - mock_post.return_value.raise_for_status = ( - lambda: None - ) - with patch( - "paperforge.worker.sync.run_selection_sync" - ): - with patch( - "paperforge.worker.sync.run_index_refresh" - ): - from paperforge.worker.ocr import ( - run_ocr, - ) + "title": "Valid PDF Paper", + } + ], + ), + patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + { + "zotero_key": "ABC123", + "has_pdf": True, + "pdf_path": str(pdf), + } + ], + ), + patch( + "paperforge.worker.ocr.ensure_ocr_meta", + return_value={}, + ), + patch("paperforge.worker.ocr.write_json"), + patch("builtins.open") as mock_open, + patch("paperforge.worker.ocr.requests.post") as mock_post, + ): + mock_post.return_value = MagicMock() + mock_post.return_value.json.return_value = {"data": {"jobId": "123"}} + mock_post.return_value.raise_for_status = lambda: None + with patch("paperforge.worker.sync.run_selection_sync"), patch("paperforge.worker.sync.run_index_refresh"): + from paperforge.worker.ocr import ( + run_ocr, + ) - run_ocr(vault) + run_ocr(vault) mock_open.assert_called_once() opened_path = mock_open.call_args[0][0] @@ -241,72 +213,61 @@ class TestOcrPreflight: mock_paths["exports"].mkdir() mock_paths["ocr"].mkdir() - with patch( - "paperforge.pdf_resolver.resolve_pdf_path", - return_value=str(target), - ): - with patch( + with ( + patch( + "paperforge.pdf_resolver.resolve_pdf_path", + return_value=str(target), + ), + patch( "paperforge.worker.ocr.pipeline_paths", return_value=mock_paths, - ): - with patch( - "paperforge.worker.ocr.load_control_actions", - return_value={"ABC123": {"do_ocr": True}}, - ): - with patch( - "paperforge.worker.ocr.load_export_rows", - return_value=[ + ), + patch( + "paperforge.worker.ocr.load_control_actions", + return_value={"ABC123": {"do_ocr": True}}, + ), + patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": "ABC123", + "attachments": [ { - "key": "ABC123", - "attachments": [ - { - "contentType": "application/pdf", - "path": str(tmp_path / "junction.pdf"), - } - ], - "title": "Junction PDF Paper", + "contentType": "application/pdf", + "path": str(tmp_path / "junction.pdf"), } ], - ): - with patch( - "paperforge.worker.ocr.sync_ocr_queue", - return_value=[ - { - "zotero_key": "ABC123", - "has_pdf": True, - "pdf_path": str(tmp_path / "junction.pdf"), - } - ], - ): - with patch( - "paperforge.worker.ocr.ensure_ocr_meta", - return_value={}, - ): - with patch( - "paperforge.worker.ocr.write_json" - ): - with patch("builtins.open") as mock_open: - with patch( - "paperforge.worker.ocr.requests.post" - ) as mock_post: - mock_post.return_value = MagicMock() - mock_post.return_value.json.return_value = { - "data": {"jobId": "123"} - } - mock_post.return_value.raise_for_status = ( - lambda: None - ) - with patch( - "paperforge.worker.sync.run_selection_sync" - ): - with patch( - "paperforge.worker.sync.run_index_refresh" - ): - from paperforge.worker.ocr import ( - run_ocr, - ) + "title": "Junction PDF Paper", + } + ], + ), + patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + { + "zotero_key": "ABC123", + "has_pdf": True, + "pdf_path": str(tmp_path / "junction.pdf"), + } + ], + ), + patch( + "paperforge.worker.ocr.ensure_ocr_meta", + return_value={}, + ), + patch("paperforge.worker.ocr.write_json"), + patch("builtins.open") as mock_open, + patch("paperforge.worker.ocr.requests.post") as mock_post, + ): + mock_post.return_value = MagicMock() + mock_post.return_value.json.return_value = {"data": {"jobId": "123"}} + mock_post.return_value.raise_for_status = lambda: None + with patch("paperforge.worker.sync.run_selection_sync"), patch("paperforge.worker.sync.run_index_refresh"): + from paperforge.worker.ocr import ( + run_ocr, + ) - run_ocr(vault) + run_ocr(vault) mock_open.assert_called_once() opened_path = mock_open.call_args[0][0] diff --git a/tests/test_ocr_state_machine.py b/tests/test_ocr_state_machine.py index f30c4d4b..fa61d182 100644 --- a/tests/test_ocr_state_machine.py +++ b/tests/test_ocr_state_machine.py @@ -3,11 +3,12 @@ Covers: pending -> queued/running -> done/error/blocked transitions, sync_ocr_queue state reconciliation, and cleanup_blocked_ocr_dirs behavior. """ + from __future__ import annotations import json from pathlib import Path -from unittest.mock import MagicMock, patch, call +from unittest.mock import MagicMock, patch import pytest @@ -48,6 +49,7 @@ def _mock_paths(vault: Path, ocr_root: Path, exports: Path, library_records: Pat # Tests for pending -> queued transition # --------------------------------------------------------------------------- + class TestPendingToQueuedTransition: """Job moves from pending to queued when submitted to the API.""" @@ -58,25 +60,40 @@ class TestPendingToQueuedTransition: key = "TESTKEY1" meta_path = ocr_root / key / "meta.json" meta_path.parent.mkdir() - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": "pending", - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": "pending", + } + ), + encoding="utf-8", + ) lr_dir = library_records / "骨科" lr_dir.mkdir(parents=True) - (lr_dir / f"{key}.md").write_text("""--- + (lr_dir / f"{key}.md").write_text( + """--- zotero_key: TESTKEY1 analyze: false do_ocr: true --- -# Test""", encoding="utf-8") +# Test""", + encoding="utf-8", + ) - (exports / "骨科.json").write_text(json.dumps([ - {"key": key, "title": "Test Paper", "attachments": [ - {"contentType": "application/pdf", "path": "test.pdf"} - ]} - ]), encoding="utf-8") + (exports / "骨科.json").write_text( + json.dumps( + [ + { + "key": key, + "title": "Test Paper", + "attachments": [{"contentType": "application/pdf", "path": "test.pdf"}], + } + ] + ), + encoding="utf-8", + ) # Real PDF file so resolve_pdf_path succeeds real_pdf = vault / "test.pdf" @@ -88,30 +105,44 @@ do_ocr: true with patch("paperforge.worker.ocr.pipeline_paths", return_value=paths): with patch("paperforge.worker.ocr.load_control_actions", return_value={key: {"do_ocr": True}}): - with patch("paperforge.worker.ocr.load_export_rows", return_value=[ - {"key": key, "attachments": [{"contentType": "application/pdf", "path": "test.pdf"}], "title": "Test"} - ]): - with patch("paperforge.worker.ocr.sync_ocr_queue", return_value=[ - {"zotero_key": key, "has_pdf": True, "pdf_path": "test.pdf", "queue_status": "pending"} - ]): - with patch("paperforge.worker.ocr.ensure_ocr_meta", return_value={"zotero_key": key, "ocr_status": "pending"}): + with patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": key, + "attachments": [{"contentType": "application/pdf", "path": "test.pdf"}], + "title": "Test", + } + ], + ): + with patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + {"zotero_key": key, "has_pdf": True, "pdf_path": "test.pdf", "queue_status": "pending"} + ], + ): + with patch( + "paperforge.worker.ocr.ensure_ocr_meta", + return_value={"zotero_key": key, "ocr_status": "pending"}, + ): with patch("paperforge.worker.ocr.write_json") as mock_write: with patch("paperforge.worker.ocr.requests.post", mock_post): with patch("paperforge.worker.sync.run_selection_sync"): with patch("paperforge.worker.sync.run_index_refresh"): from paperforge.worker.ocr import run_ocr + run_ocr(vault) # Check requests.post was called (job submitted) assert mock_post.called, "requests.post was not called - job not submitted" # Check meta was updated to queued - meta_calls = [c for c in mock_write.call_args_list - if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key] + meta_calls = [ + c for c in mock_write.call_args_list if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key + ] assert meta_calls, f"No meta write found for key {key}" final_meta = meta_calls[-1][0][1] - assert final_meta.get("ocr_status") == "queued", \ - f"Expected 'queued', got {final_meta.get('ocr_status')}" + assert final_meta.get("ocr_status") == "queued", f"Expected 'queued', got {final_meta.get('ocr_status')}" assert final_meta.get("ocr_job_id") == "job-123" @@ -119,6 +150,7 @@ do_ocr: true # Tests for processing -> done transition # --------------------------------------------------------------------------- + class TestProcessingToDoneTransition: """Job moves from running/queued to done when polling returns success.""" @@ -131,25 +163,40 @@ class TestProcessingToDoneTransition: meta_path = ocr_root / key / "meta.json" meta_path.parent.mkdir() # meta.json already has job_id — simulating an already-submitted job - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": "queued", - "ocr_job_id": "job-456", - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": "queued", + "ocr_job_id": "job-456", + } + ), + encoding="utf-8", + ) lr_dir = library_records / "骨科" lr_dir.mkdir(parents=True) - (lr_dir / f"{key}.md").write_text("""--- + (lr_dir / f"{key}.md").write_text( + """--- zotero_key: TESTKEY2 do_ocr: true --- -# Test""", encoding="utf-8") +# Test""", + encoding="utf-8", + ) - (exports / "骨科.json").write_text(json.dumps([ - {"key": key, "title": "Test Paper 2", "attachments": [ - {"contentType": "application/pdf", "path": "test2.pdf"} - ]} - ]), encoding="utf-8") + (exports / "骨科.json").write_text( + json.dumps( + [ + { + "key": key, + "title": "Test Paper 2", + "attachments": [{"contentType": "application/pdf", "path": "test2.pdf"}], + } + ] + ), + encoding="utf-8", + ) # Real PDF so resolve_pdf_path succeeds real_pdf = vault / "test2.pdf" @@ -158,10 +205,7 @@ do_ocr: true # Configure poll response: state=done poll_response = MagicMock() poll_response.json.return_value = { - "data": { - "state": "done", - "resultUrl": {"jsonUrl": "http://example.com/result.json"} - } + "data": {"state": "done", "resultUrl": {"jsonUrl": "http://example.com/result.json"}} } poll_response.raise_for_status = MagicMock() @@ -169,31 +213,43 @@ do_ocr: true # This is sufficient since we only care about the first poll result with patch("paperforge.worker.ocr.pipeline_paths", return_value=paths): with patch("paperforge.worker.ocr.load_control_actions", return_value={key: {"do_ocr": True}}): - with patch("paperforge.worker.ocr.load_export_rows", return_value=[ - {"key": key, "attachments": [{"contentType": "application/pdf", "path": "test2.pdf"}], "title": "Test"} - ]): - with patch("paperforge.worker.ocr.sync_ocr_queue", return_value=[ - {"zotero_key": key, "has_pdf": True, "pdf_path": "test2.pdf", "queue_status": "queued"} - ]): + with patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": key, + "attachments": [{"contentType": "application/pdf", "path": "test2.pdf"}], + "title": "Test", + } + ], + ): + with patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + {"zotero_key": key, "has_pdf": True, "pdf_path": "test2.pdf", "queue_status": "queued"} + ], + ): with patch("paperforge.worker.ocr.write_json") as mock_write: with patch("paperforge.worker.ocr.requests.get", return_value=poll_response): with patch("paperforge.worker.sync.run_selection_sync"): with patch("paperforge.worker.sync.run_index_refresh"): from paperforge.worker.ocr import run_ocr + run_ocr(vault) - meta_calls = [c for c in mock_write.call_args_list - if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key] + meta_calls = [ + c for c in mock_write.call_args_list if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key + ] assert meta_calls, f"No meta write found for key {key}" final_meta = meta_calls[-1][0][1] - assert final_meta.get("ocr_status") == "done", \ - f"Expected 'done', got {final_meta.get('ocr_status')}" + assert final_meta.get("ocr_status") == "done", f"Expected 'done', got {final_meta.get('ocr_status')}" # --------------------------------------------------------------------------- # Tests for processing -> error transition # --------------------------------------------------------------------------- + class TestProcessingToErrorTransition: """Job moves from running to error when the API returns an error state.""" @@ -205,60 +261,81 @@ class TestProcessingToErrorTransition: key = "TESTKEY3" meta_path = ocr_root / key / "meta.json" meta_path.parent.mkdir() - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": "queued", - "ocr_job_id": "job-789", - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": "queued", + "ocr_job_id": "job-789", + } + ), + encoding="utf-8", + ) lr_dir = library_records / "骨科" lr_dir.mkdir(parents=True) - (lr_dir / f"{key}.md").write_text("""--- + (lr_dir / f"{key}.md").write_text( + """--- zotero_key: TESTKEY3 do_ocr: true --- -# Test""", encoding="utf-8") +# Test""", + encoding="utf-8", + ) - (exports / "骨科.json").write_text(json.dumps([ - {"key": key, "title": "Test Paper 3", "attachments": [ - {"contentType": "application/pdf", "path": "test3.pdf"} - ]} - ]), encoding="utf-8") + (exports / "骨科.json").write_text( + json.dumps( + [ + { + "key": key, + "title": "Test Paper 3", + "attachments": [{"contentType": "application/pdf", "path": "test3.pdf"}], + } + ] + ), + encoding="utf-8", + ) real_pdf = vault / "test3.pdf" real_pdf.write_text("PDF content") # Poll returns state=error error_response = MagicMock() - error_response.json.return_value = { - "data": { - "state": "error", - "errorMsg": "Model inference failed" - } - } + error_response.json.return_value = {"data": {"state": "error", "errorMsg": "Model inference failed"}} error_response.raise_for_status = MagicMock() with patch("paperforge.worker.ocr.pipeline_paths", return_value=paths): with patch("paperforge.worker.ocr.load_control_actions", return_value={key: {"do_ocr": True}}): - with patch("paperforge.worker.ocr.load_export_rows", return_value=[ - {"key": key, "attachments": [{"contentType": "application/pdf", "path": "test3.pdf"}], "title": "Test"} - ]): - with patch("paperforge.worker.ocr.sync_ocr_queue", return_value=[ - {"zotero_key": key, "has_pdf": True, "pdf_path": "test3.pdf", "queue_status": "queued"} - ]): + with patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": key, + "attachments": [{"contentType": "application/pdf", "path": "test3.pdf"}], + "title": "Test", + } + ], + ): + with patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + {"zotero_key": key, "has_pdf": True, "pdf_path": "test3.pdf", "queue_status": "queued"} + ], + ): with patch("paperforge.worker.ocr.write_json") as mock_write: with patch("paperforge.worker.ocr.requests.get", return_value=error_response): with patch("paperforge.worker.sync.run_selection_sync"): with patch("paperforge.worker.sync.run_index_refresh"): from paperforge.worker.ocr import run_ocr + run_ocr(vault) - meta_calls = [c for c in mock_write.call_args_list - if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key] + meta_calls = [ + c for c in mock_write.call_args_list if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key + ] assert meta_calls, "No meta write for our key" final_meta = meta_calls[-1][0][1] - assert final_meta.get("ocr_status") == "error", \ - f"Expected 'error', got {final_meta.get('ocr_status')}" + assert final_meta.get("ocr_status") == "error", f"Expected 'error', got {final_meta.get('ocr_status')}" assert "Model inference failed" in final_meta.get("error", "") @@ -266,6 +343,7 @@ do_ocr: true # Tests for processing -> blocked transition # --------------------------------------------------------------------------- + class TestProcessingToBlockedTransition: """Job transitions to blocked when token is missing or PDF unreadable.""" @@ -277,24 +355,39 @@ class TestProcessingToBlockedTransition: key = "TESTKEY4" meta_path = ocr_root / key / "meta.json" meta_path.parent.mkdir() - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": "pending", - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": "pending", + } + ), + encoding="utf-8", + ) lr_dir = library_records / "骨科" lr_dir.mkdir(parents=True) - (lr_dir / f"{key}.md").write_text("""--- + (lr_dir / f"{key}.md").write_text( + """--- zotero_key: TESTKEY4 do_ocr: true --- -# Test""", encoding="utf-8") +# Test""", + encoding="utf-8", + ) - (exports / "骨科.json").write_text(json.dumps([ - {"key": key, "title": "Test Paper 4", "attachments": [ - {"contentType": "application/pdf", "path": "test4.pdf"} - ]} - ]), encoding="utf-8") + (exports / "骨科.json").write_text( + json.dumps( + [ + { + "key": key, + "title": "Test Paper 4", + "attachments": [{"contentType": "application/pdf", "path": "test4.pdf"}], + } + ] + ), + encoding="utf-8", + ) # Real PDF so resolve_pdf_path succeeds real_pdf = vault / "test4.pdf" @@ -304,6 +397,7 @@ do_ocr: true # classify_error maps 401 -> 'blocked', so this tests the # blocked transition path without needing to manipulate env vars. import requests as _req + _mock_resp = MagicMock() _mock_resp.status_code = 401 _http_err = _req.exceptions.HTTPError("401 Unauthorized") @@ -317,12 +411,22 @@ do_ocr: true with patch("paperforge.worker.ocr.pipeline_paths", return_value=paths): with patch("paperforge.worker.ocr.load_control_actions", return_value={key: {"do_ocr": True}}): - with patch("paperforge.worker.ocr.load_export_rows", return_value=[ - {"key": key, "attachments": [{"contentType": "application/pdf", "path": "test4.pdf"}], "title": "Test"} - ]): - with patch("paperforge.worker.ocr.sync_ocr_queue", return_value=[ - {"zotero_key": key, "has_pdf": True, "pdf_path": "test4.pdf", "queue_status": "pending"} - ]): + with patch( + "paperforge.worker.ocr.load_export_rows", + return_value=[ + { + "key": key, + "attachments": [{"contentType": "application/pdf", "path": "test4.pdf"}], + "title": "Test", + } + ], + ): + with patch( + "paperforge.worker.ocr.sync_ocr_queue", + return_value=[ + {"zotero_key": key, "has_pdf": True, "pdf_path": "test4.pdf", "queue_status": "pending"} + ], + ): with patch("paperforge.worker.ocr.ensure_ocr_meta", side_effect=make_meta): with patch("paperforge.worker.ocr.write_json") as mock_write: with patch("paperforge.worker.sync.run_selection_sync"): @@ -330,20 +434,24 @@ do_ocr: true with patch("paperforge.worker.ocr.requests.post", mock_post): with patch("paperforge.worker.ocr.requests.get", MagicMock()): from paperforge.worker.ocr import run_ocr + run_ocr(vault) - meta_calls = [c for c in mock_write.call_args_list - if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key] + meta_calls = [ + c for c in mock_write.call_args_list if isinstance(c[0][1], dict) and c[0][1].get("zotero_key") == key + ] assert meta_calls, "No meta write for our key" final_meta = meta_calls[-1][0][1] - assert final_meta.get("ocr_status") == "blocked", \ - f"Expected 'blocked' (missing token), got {final_meta.get('ocr_status')}" + assert ( + final_meta.get("ocr_status") == "blocked" + ), f"Expected 'blocked' (missing token), got {final_meta.get('ocr_status')}" # --------------------------------------------------------------------------- # Tests for sync_ocr_queue state reconciliation # --------------------------------------------------------------------------- + class TestSyncOcrQueue: """sync_ocr_queue correctly reconciles existing queue with target rows.""" @@ -355,35 +463,49 @@ class TestSyncOcrQueue: key = "TESTKEY5" # Write existing queue file with done status ocr_queue_path = ocr_root / "ocr-queue.json" - ocr_queue_path.write_text(json.dumps([ - {"zotero_key": key, "has_pdf": True, "pdf_path": "test.pdf", - "queue_status": "done", "queued_at": "2024-01-01T00:00:00Z"} - ]), encoding="utf-8") + ocr_queue_path.write_text( + json.dumps( + [ + { + "zotero_key": key, + "has_pdf": True, + "pdf_path": "test.pdf", + "queue_status": "done", + "queued_at": "2024-01-01T00:00:00Z", + } + ] + ), + encoding="utf-8", + ) # meta.json says done meta_path = ocr_root / key / "meta.json" meta_path.parent.mkdir() - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": "done", - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": "done", + } + ), + encoding="utf-8", + ) - target_rows = [ - {"zotero_key": key, "has_pdf": True, "pdf_path": "test.pdf"} - ] + target_rows = [{"zotero_key": key, "has_pdf": True, "pdf_path": "test.pdf"}] from paperforge.worker.ocr import sync_ocr_queue + result = sync_ocr_queue(paths, target_rows) # done should be skipped - assert not any(r["zotero_key"] == key for r in result), \ - "done status should be skipped" + assert not any(r["zotero_key"] == key for r in result), "done status should be skipped" # --------------------------------------------------------------------------- # Tests for cleanup_blocked_ocr_dirs # --------------------------------------------------------------------------- + class TestCleanupBlockedOcrDirs: """cleanup_blocked_ocr_dirs removes empty blocked directories.""" @@ -395,17 +517,22 @@ class TestCleanupBlockedOcrDirs: blocked_dir = ocr_root / key blocked_dir.mkdir() meta_path = blocked_dir / "meta.json" - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": "blocked", - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": "blocked", + } + ), + encoding="utf-8", + ) # No fulltext.md or json/result.json -> should be removed from paperforge.worker.ocr import cleanup_blocked_ocr_dirs + cleanup_blocked_ocr_dirs(paths) - assert not blocked_dir.exists(), \ - f"Blocked dir {blocked_dir} should have been removed" + assert not blocked_dir.exists(), f"Blocked dir {blocked_dir} should have been removed" def test_preserves_blocked_dir_with_payload(self, tmp_path: Path) -> None: vault, ocr_root, exports, library_records = _make_vault(tmp_path) @@ -415,31 +542,37 @@ class TestCleanupBlockedOcrDirs: blocked_dir = ocr_root / key blocked_dir.mkdir() meta_path = blocked_dir / "meta.json" - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": "blocked", - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": "blocked", + } + ), + encoding="utf-8", + ) # Add fulltext.md as payload (blocked_dir / "fulltext.md").write_text("OCR result text", encoding="utf-8") from paperforge.worker.ocr import cleanup_blocked_ocr_dirs + cleanup_blocked_ocr_dirs(paths) - assert blocked_dir.exists(), \ - f"Blocked dir with payload should be preserved" + assert blocked_dir.exists(), "Blocked dir with payload should be preserved" # --------------------------------------------------------------------------- # Tests for state definitions # --------------------------------------------------------------------------- + class TestOcrJobStates: """Valid OCR job states are: pending, queued, running, done, error, blocked, nopdf.""" def test_all_expected_states_covered(self, tmp_path: Path) -> None: """Ensure run_ocr handles all documented states without crashing.""" vault, ocr_root, exports, library_records = _make_vault(tmp_path) - paths = _mock_paths(vault, ocr_root, exports, library_records) + _mock_paths(vault, ocr_root, exports, library_records) # States to test: pending, queued, running, done, error, blocked, nopdf states = ["pending", "queued", "running", "done", "error", "blocked", "nopdf"] @@ -447,27 +580,43 @@ class TestOcrJobStates: key = f"TESTKEY_STATE_{state}" meta_path = ocr_root / key / "meta.json" meta_path.parent.mkdir() - meta_path.write_text(json.dumps({ - "zotero_key": key, - "ocr_status": state, - }), encoding="utf-8") + meta_path.write_text( + json.dumps( + { + "zotero_key": key, + "ocr_status": state, + } + ), + encoding="utf-8", + ) lr_dir = library_records / "骨科" lr_dir.mkdir(parents=True, exist_ok=True) - (lr_dir / f"{key}.md").write_text(f"""--- + (lr_dir / f"{key}.md").write_text( + f"""--- zotero_key: {key} do_ocr: true --- -# Test""", encoding="utf-8") +# Test""", + encoding="utf-8", + ) - (exports / "骨科.json").write_text(json.dumps([ - {"key": key, "title": f"Test {state}", "attachments": [ - {"contentType": "application/pdf", "path": "test.pdf"} - ]} - ]), encoding="utf-8") + (exports / "骨科.json").write_text( + json.dumps( + [ + { + "key": key, + "title": f"Test {state}", + "attachments": [{"contentType": "application/pdf", "path": "test.pdf"}], + } + ] + ), + encoding="utf-8", + ) # Smoke test: ensure no state raises an unhandled exception from paperforge.worker.ocr import run_ocr + try: run_ocr(vault) except Exception as e: diff --git a/tests/test_path_normalization.py b/tests/test_path_normalization.py index d137749d..f3b4e045 100644 --- a/tests/test_path_normalization.py +++ b/tests/test_path_normalization.py @@ -13,26 +13,23 @@ from __future__ import annotations import json import sys from pathlib import Path -from unittest.mock import patch - -import pytest REPO_ROOT = Path(__file__).resolve().parent.parent if str(REPO_ROOT) not in sys.path: sys.path.insert(0, str(REPO_ROOT)) from paperforge.worker.sync import ( - _normalize_attachment_path, _identify_main_pdf, - obsidian_wikilink_for_pdf, + _normalize_attachment_path, load_export_rows, + obsidian_wikilink_for_pdf, ) - # --------------------------------------------------------------------------- # Test class: TestBBTPathNormalization # --------------------------------------------------------------------------- + class TestBBTPathNormalization: """Tests for _normalize_attachment_path() with various BBT export formats.""" @@ -110,6 +107,7 @@ class TestBBTPathNormalization: # Test class: TestMainPdfIdentification # --------------------------------------------------------------------------- + class TestMainPdfIdentification: """Tests for _identify_main_pdf() hybrid priority strategy.""" @@ -153,7 +151,12 @@ class TestMainPdfIdentification: def test_no_pdf_attachments(self) -> None: """No PDF attachments returns (None, []).""" attachments = [ - {"path": "storage:KEY/data.xlsx", "contentType": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", "title": "Data", "size": 100}, + { + "path": "storage:KEY/data.xlsx", + "contentType": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", + "title": "Data", + "size": 100, + }, ] main, supplementary = _identify_main_pdf(attachments) @@ -189,6 +192,7 @@ class TestMainPdfIdentification: # Test class: TestWikilinkGeneration # --------------------------------------------------------------------------- + class TestWikilinkGeneration: """Tests for obsidian_wikilink_for_pdf() wikilink generation.""" @@ -223,9 +227,7 @@ class TestWikilinkGeneration: return real_target return path - monkeypatch.setattr( - "paperforge.pdf_resolver.resolve_junction", mock_resolve_junction - ) + monkeypatch.setattr("paperforge.pdf_resolver.resolve_junction", mock_resolve_junction) # Test with a path that would trigger junction resolution result = obsidian_wikilink_for_pdf("storage:KEY/file.pdf", vault_dir, zotero_dir) @@ -291,6 +293,7 @@ class TestWikilinkGeneration: # Test class: TestLoadExportRowsIntegration # --------------------------------------------------------------------------- + class TestLoadExportRowsIntegration: """Integration tests using fixture JSON files.""" diff --git a/tests/test_pdf_resolver.py b/tests/test_pdf_resolver.py index f1399c05..ec0a76a5 100644 --- a/tests/test_pdf_resolver.py +++ b/tests/test_pdf_resolver.py @@ -6,10 +6,8 @@ and has_pdf=False scenarios. from __future__ import annotations -import os import json from pathlib import Path -from unittest.mock import patch import pytest @@ -47,9 +45,7 @@ class TestResolvePdfPath: return target return path - monkeypatch.setattr( - "paperforge.pdf_resolver.resolve_junction", mock_resolve_junction - ) + monkeypatch.setattr("paperforge.pdf_resolver.resolve_junction", mock_resolve_junction) result = resolve_pdf_path(str(junction), True, tmp_path) assert result == str(target.resolve()) @@ -162,9 +158,7 @@ class TestLoadExportRowsAttachmentNormalization: "itemKey": "ABC123", "itemType": "journalArticle", "title": "Test Paper", - "attachments": [ - {"path": "ABC123/ABC123.pdf", "contentType": "application/pdf"} - ], + "attachments": [{"path": "ABC123/ABC123.pdf", "contentType": "application/pdf"}], } ], "collections": {}, @@ -188,9 +182,7 @@ class TestLoadExportRowsAttachmentNormalization: "itemKey": "ABC123", "itemType": "journalArticle", "title": "Test Paper", - "attachments": [ - {"path": "storage:ABC123/ABC123.pdf", "contentType": "application/pdf"} - ], + "attachments": [{"path": "storage:ABC123/ABC123.pdf", "contentType": "application/pdf"}], } ], "collections": {}, @@ -215,9 +207,7 @@ class TestLoadExportRowsAttachmentNormalization: "itemKey": "ABC123", "itemType": "journalArticle", "title": "Test Paper", - "attachments": [ - {"path": abs_path, "contentType": "application/pdf"} - ], + "attachments": [{"path": abs_path, "contentType": "application/pdf"}], } ], "collections": {}, @@ -241,9 +231,7 @@ class TestLoadExportRowsAttachmentNormalization: "itemKey": "ABC123", "itemType": "journalArticle", "title": "Test Paper", - "attachments": [ - {"path": "", "contentType": ""} - ], + "attachments": [{"path": "", "contentType": ""}], } ], "collections": {}, @@ -267,9 +255,7 @@ class TestLoadExportRowsAttachmentNormalization: "itemKey": "ABC123", "itemType": "journalArticle", "title": "Test Paper", - "attachments": [ - {"path": "ABC123/ABC123.docx", "contentType": ""} - ], + "attachments": [{"path": "ABC123/ABC123.docx", "contentType": ""}], } ], "collections": {}, diff --git a/tests/test_prepare_rollback.py b/tests/test_prepare_rollback.py index 8c9a7fe9..9b66a069 100644 --- a/tests/test_prepare_rollback.py +++ b/tests/test_prepare_rollback.py @@ -56,7 +56,13 @@ class TestPrepareRollback: ocr_dir = vault / "99_System" / "PaperForge" / "ocr" / "TSTONE001" figure_map_path = ocr_dir / "figure-map.json" chart_type_map_path = ocr_dir / "chart-type-map.json" - formal_note = vault / "03_Resources" / "Literature" / "骨科" / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + formal_note = ( + vault + / "03_Resources" + / "Literature" + / "骨科" + / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + ) # Remove pre-existing fixture files to test clean rollback if figure_map_path.exists(): @@ -84,7 +90,13 @@ class TestPrepareRollback: ocr_dir = vault / "99_System" / "PaperForge" / "ocr" / "TSTONE001" figure_map_path = ocr_dir / "figure-map.json" chart_type_map_path = ocr_dir / "chart-type-map.json" - formal_note = vault / "03_Resources" / "Literature" / "骨科" / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + formal_note = ( + vault + / "03_Resources" + / "Literature" + / "骨科" + / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + ) # Remove pre-existing fixture files to test clean rollback if figure_map_path.exists(): @@ -112,7 +124,13 @@ class TestPrepareRollback: ocr_dir = vault / "99_System" / "PaperForge" / "ocr" / "TSTONE001" figure_map_path = ocr_dir / "figure-map.json" chart_type_map_path = ocr_dir / "chart-type-map.json" - formal_note = vault / "03_Resources" / "Literature" / "骨科" / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + formal_note = ( + vault + / "03_Resources" + / "Literature" + / "骨科" + / "TSTONE001 - Biomechanical Comparison of Suture Anchor Fixations in Rotator Cuff Repair.md" + ) original_note_text = formal_note.read_text(encoding="utf-8") diff --git a/tests/test_repair.py b/tests/test_repair.py index 2cc6e2ad..cdc6e9e8 100644 --- a/tests/test_repair.py +++ b/tests/test_repair.py @@ -1,11 +1,10 @@ """Tests for run_repair() — three-way OCR status divergence detection and repair.""" + from __future__ import annotations import json import re -import pytest - from paperforge.worker.repair import run_repair from paperforge.worker.sync import pipeline_paths @@ -220,6 +219,7 @@ class TestRunRepairScanOnly: def test_verbose_output_printed(self, tmp_path, caplog): import logging + caplog.set_level(logging.DEBUG, logger="paperforge.worker.repair") vault = _make_vault(tmp_path) paths = pipeline_paths(vault) @@ -227,7 +227,7 @@ class TestRunRepairScanOnly: records_dir.mkdir(parents=True, exist_ok=True) _write_library_record(records_dir, "KEY001", "骨科", "done") _write_meta(paths["ocr"], "KEY001", "pending") - result = run_repair(vault, paths, verbose=True, fix=False) + run_repair(vault, paths, verbose=True, fix=False) assert "KEY001" in caplog.text assert "divergent" in caplog.text @@ -288,8 +288,8 @@ class TestRunRepairFixMode: paths = pipeline_paths(vault) records_dir = vault / "03_Resources" / "LiteratureControl" / "library-records" / "骨科" records_dir.mkdir(parents=True, exist_ok=True) - record1_path = _write_library_record(records_dir, "KEY001", "骨科", "done", do_ocr="false") - record2_path = _write_library_record(records_dir, "KEY002", "骨科", "pending") + _write_library_record(records_dir, "KEY001", "骨科", "done", do_ocr="false") + _write_library_record(records_dir, "KEY002", "骨科", "pending") _write_minimal_meta(paths["ocr"], "KEY001", "done") _write_minimal_meta(paths["ocr"], "KEY002", "done") result = run_repair(vault, paths, verbose=False, fix=True) @@ -314,7 +314,7 @@ class TestRunRepairFixMode: lit_dir = vault / "03_Resources" / "Literature" _write_library_record(records_dir, "KEY001", "骨科", "done", do_ocr="false") note_path = _write_formal_note(lit_dir, "KEY001", "骨科", "done") - result = run_repair(vault, paths, verbose=False, fix=True) + run_repair(vault, paths, verbose=False, fix=True) note_text = note_path.read_text(encoding="utf-8") assert re.search(r'^ocr_status:\s*"?pending"?', note_text, re.MULTILINE) diff --git a/tests/test_selection_sync_pdf.py b/tests/test_selection_sync_pdf.py index 4e3fd682..4846ef16 100644 --- a/tests/test_selection_sync_pdf.py +++ b/tests/test_selection_sync_pdf.py @@ -3,13 +3,12 @@ Verifies that run_selection_sync() sets ocr_status: nopdf when PDFs are missing and preserves pending/done for valid PDFs. """ + from __future__ import annotations from pathlib import Path from unittest.mock import patch -import pytest - class TestSelectionSyncPdf: """Tests for selection-sync PDF preflight reporting.""" @@ -28,7 +27,7 @@ class TestSelectionSyncPdf: resources.mkdir() (resources / "LiteratureControl" / "library-records").mkdir(parents=True) (resources / "Literature").mkdir(parents=True) - (vault / "paperforge.json").write_text('{}', encoding="utf-8") + (vault / "paperforge.json").write_text("{}", encoding="utf-8") return vault def _mock_export_item(self, key: str, has_pdf: bool = True, pdf_path: str = "") -> dict: @@ -52,35 +51,31 @@ class TestSelectionSyncPdf: """Export item with no PDF attachments → ocr_status: nopdf.""" vault = self._make_vault(tmp_path) - with patch( - "paperforge.worker.sync.pipeline_paths" - ) as mock_paths: + with patch("paperforge.worker.sync.pipeline_paths") as mock_paths: mock_paths.return_value = { "exports": vault / "99_System" / "PaperForge" / "exports", "ocr": vault / "99_System" / "PaperForge" / "ocr", "library_records": vault / "03_Resources" / "LiteratureControl" / "library-records", "literature": vault / "03_Resources" / "Literature", } - with patch( - "paperforge.worker.sync.load_domain_config", - return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + with ( + patch( + "paperforge.worker.sync.load_domain_config", + return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + ), + patch("paperforge.worker.base_views.ensure_base_views"), + patch( + "paperforge.worker.sync.load_export_rows", + return_value=[self._mock_export_item("NO_PDF", has_pdf=False)], + ), ): - with patch( - "paperforge.worker.base_views.ensure_base_views" - ): - with patch( - "paperforge.worker.sync.load_export_rows", - return_value=[self._mock_export_item("NO_PDF", has_pdf=False)], - ): - from paperforge.worker.sync import ( - run_selection_sync, - ) + from paperforge.worker.sync import ( + run_selection_sync, + ) - run_selection_sync(vault) + run_selection_sync(vault) - record_path = ( - vault / "03_Resources" / "LiteratureControl" / "library-records" / "TestDomain" / "NO_PDF.md" - ) + record_path = vault / "03_Resources" / "LiteratureControl" / "library-records" / "TestDomain" / "NO_PDF.md" assert record_path.exists() content = record_path.read_text(encoding="utf-8") assert 'ocr_status: "nopdf"' in content @@ -91,37 +86,31 @@ class TestSelectionSyncPdf: vault = self._make_vault(tmp_path) missing_pdf = str(tmp_path / "missing.pdf") - with patch( - "paperforge.worker.sync.pipeline_paths" - ) as mock_paths: + with patch("paperforge.worker.sync.pipeline_paths") as mock_paths: mock_paths.return_value = { "exports": vault / "99_System" / "PaperForge" / "exports", "ocr": vault / "99_System" / "PaperForge" / "ocr", "library_records": vault / "03_Resources" / "LiteratureControl" / "library-records", "literature": vault / "03_Resources" / "Literature", } - with patch( - "paperforge.worker.sync.load_domain_config", - return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + with ( + patch( + "paperforge.worker.sync.load_domain_config", + return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + ), + patch("paperforge.worker.base_views.ensure_base_views"), + patch( + "paperforge.worker.sync.load_export_rows", + return_value=[self._mock_export_item("MISSING", has_pdf=True, pdf_path=missing_pdf)], + ), ): - with patch( - "paperforge.worker.base_views.ensure_base_views" - ): - with patch( - "paperforge.worker.sync.load_export_rows", - return_value=[ - self._mock_export_item("MISSING", has_pdf=True, pdf_path=missing_pdf) - ], - ): - from paperforge.worker.sync import ( - run_selection_sync, - ) + from paperforge.worker.sync import ( + run_selection_sync, + ) - run_selection_sync(vault) + run_selection_sync(vault) - record_path = ( - vault / "03_Resources" / "LiteratureControl" / "library-records" / "TestDomain" / "MISSING.md" - ) + record_path = vault / "03_Resources" / "LiteratureControl" / "library-records" / "TestDomain" / "MISSING.md" assert record_path.exists() content = record_path.read_text(encoding="utf-8") assert 'ocr_status: "nopdf"' in content @@ -132,37 +121,31 @@ class TestSelectionSyncPdf: pdf = tmp_path / "test.pdf" pdf.write_bytes(b"%PDF-1.4\n") - with patch( - "paperforge.worker.sync.pipeline_paths" - ) as mock_paths: + with patch("paperforge.worker.sync.pipeline_paths") as mock_paths: mock_paths.return_value = { "exports": vault / "99_System" / "PaperForge" / "exports", "ocr": vault / "99_System" / "PaperForge" / "ocr", "library_records": vault / "03_Resources" / "LiteratureControl" / "library-records", "literature": vault / "03_Resources" / "Literature", } - with patch( - "paperforge.worker.sync.load_domain_config", - return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + with ( + patch( + "paperforge.worker.sync.load_domain_config", + return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + ), + patch("paperforge.worker.base_views.ensure_base_views"), + patch( + "paperforge.worker.sync.load_export_rows", + return_value=[self._mock_export_item("VALID", has_pdf=True, pdf_path=str(pdf))], + ), ): - with patch( - "paperforge.worker.base_views.ensure_base_views" - ): - with patch( - "paperforge.worker.sync.load_export_rows", - return_value=[ - self._mock_export_item("VALID", has_pdf=True, pdf_path=str(pdf)) - ], - ): - from paperforge.worker.sync import ( - run_selection_sync, - ) + from paperforge.worker.sync import ( + run_selection_sync, + ) - run_selection_sync(vault) + run_selection_sync(vault) - record_path = ( - vault / "03_Resources" / "LiteratureControl" / "library-records" / "TestDomain" / "VALID.md" - ) + record_path = vault / "03_Resources" / "LiteratureControl" / "library-records" / "TestDomain" / "VALID.md" assert record_path.exists() content = record_path.read_text(encoding="utf-8") assert 'ocr_status: "pending"' in content @@ -179,31 +162,29 @@ class TestSelectionSyncPdf: encoding="utf-8", ) - with patch( - "paperforge.worker.sync.pipeline_paths" - ) as mock_paths: + with patch("paperforge.worker.sync.pipeline_paths") as mock_paths: mock_paths.return_value = { "exports": vault / "99_System" / "PaperForge" / "exports", "ocr": vault / "99_System" / "PaperForge" / "ocr", "library_records": vault / "03_Resources" / "LiteratureControl" / "library-records", "literature": vault / "03_Resources" / "Literature", } - with patch( - "paperforge.worker.sync.load_domain_config", - return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + with ( + patch( + "paperforge.worker.sync.load_domain_config", + return_value={"domains": [{"export_file": "test.json", "domain": "TestDomain"}]}, + ), + patch("paperforge.worker.base_views.ensure_base_views"), + patch( + "paperforge.worker.sync.load_export_rows", + return_value=[self._mock_export_item("CHANGED", has_pdf=False)], + ), ): - with patch( - "paperforge.worker.base_views.ensure_base_views" - ): - with patch( - "paperforge.worker.sync.load_export_rows", - return_value=[self._mock_export_item("CHANGED", has_pdf=False)], - ): - from paperforge.worker.sync import ( - run_selection_sync, - ) + from paperforge.worker.sync import ( + run_selection_sync, + ) - run_selection_sync(vault) + run_selection_sync(vault) content = record_path.read_text(encoding="utf-8") assert 'ocr_status: "nopdf"' in content diff --git a/tests/test_smoke.py b/tests/test_smoke.py index fdc5e89a..2492db75 100644 --- a/tests/test_smoke.py +++ b/tests/test_smoke.py @@ -12,13 +12,11 @@ from __future__ import annotations import importlib.util import json -import os import re import subprocess import sys from pathlib import Path from typing import Any -from unittest.mock import patch import pytest @@ -34,6 +32,7 @@ if str(REPO_ROOT) not in sys.path: # Helpers # --------------------------------------------------------------------------- + def _import_ld_deep(path: Path | None = None) -> Any: """Import ld_deep.py using importlib, with Python 3.14 workaround.""" if path is None: @@ -67,9 +66,9 @@ class TestSetupWizard: import setup_wizard source = Path(setup_wizard.__file__).read_text(encoding="utf-8") - assert '"-m", "pip", "install", "-e"' in source or "pip install -e" in source, ( - "setup wizard should call pip install -e" - ) + assert ( + '"-m", "pip", "install", "-e"' in source or "pip install -e" in source + ), "setup wizard should call pip install -e" assert "repo_root" in source, "setup wizard should reference repo_root" @@ -82,9 +81,9 @@ class TestDoctorImportability: source = Path(run_doctor.__code__.co_filename).read_text(encoding="utf-8") assert "importlib.util" in source, "doctor should use importlib.util for import check" - assert "spec_from_file_location" in source or "exec_module" in source, ( - "doctor should actually exec_module ld_deep" - ) + assert ( + "spec_from_file_location" in source or "exec_module" in source + ), "doctor should actually exec_module ld_deep" def test_regression_doctor_env_name(self, test_vault: Path) -> None: """REG-02: doctor checks PADDLEOCR_API_TOKEN (not old env name).""" @@ -98,9 +97,9 @@ class TestDoctorImportability: from paperforge.worker.status import run_doctor source = Path(run_doctor.__code__.co_filename).read_text(encoding="utf-8") - assert "library.json 不存在" not in source or "*.json" in source, ( - "doctor should support per-domain JSON exports" - ) + assert ( + "library.json 不存在" not in source or "*.json" in source + ), "doctor should support per-domain JSON exports" class TestLdDeepImport: @@ -277,14 +276,7 @@ class TestMetadataFields: def test_regression_metadata_fields(self, test_vault: Path) -> None: """Verify library-record has non-empty first_author and journal.""" - record_path = ( - test_vault - / "03_Resources" - / "LiteratureControl" - / "library-records" - / "骨科" - / "TSTONE001.md" - ) + record_path = test_vault / "03_Resources" / "LiteratureControl" / "library-records" / "骨科" / "TSTONE001.md" assert record_path.exists(), "library record should exist" text = record_path.read_text(encoding="utf-8") @@ -306,14 +298,7 @@ class TestSelectionSync: def test_regression_bbt_pdf_path(self, test_vault: Path) -> None: """REG-02: BBT attachment paths resolve correctly.""" - record_path = ( - test_vault - / "03_Resources" - / "LiteratureControl" - / "library-records" - / "骨科" - / "TSTONE001.md" - ) + record_path = test_vault / "03_Resources" / "LiteratureControl" / "library-records" / "骨科" / "TSTONE001.md" assert record_path.exists(), "library record should exist" text = record_path.read_text(encoding="utf-8") assert "TSTONE001.pdf" in text, "record should reference the PDF"