obsidian-plugin/lllin000_PaperForge
1
0
Fork 0
mirror of https://github.com/lllin000/PaperForge.git synced 2026-07-22 06:50:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: preserve OCR compatibility through renderer v2

Browse source
This commit is contained in:
Research Assistant 2026-06-05 10:42:20 +08:00
parent 22d189e69e
commit 635c50ab2e
2 changed files with 57 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
tests/test_ocr_redo.py
View file

@ -175,3 +175,31 @@ def test_ocr_redo_scan_finds_marked_papers(tmp_path):
assert "KEY_B" not in found
assert "KEY_C" in found
assert len(found) == 2
def test_ocr_redo_rebuilds_phase3_artifacts(tmp_path) -> None:
"""Verify postprocess_ocr_result produces render and health artifacts from Phase 3."""
import json as _json
from paperforge.worker.ocr import postprocess_ocr_result
vault = tmp_path / "vault"
vault.mkdir()
(vault / "paperforge.json").write_text(
_json.dumps({"vault_config": {"system_dir": "System", "resources_dir": "Resources"}}),
encoding="utf-8",
)
ocr_root = vault / "System" / "PaperForge" / "ocr"
ocr_root.mkdir(parents=True)
ocr_dir = ocr_root / "REDO003"
ocr_dir.mkdir()
(ocr_dir / "meta.json").write_text(
'{"zotero_key":"REDO003","ocr_status":"done","ocr_redo":true,"ocr_model":"PaddleOCR","source_pdf":""}',
encoding="utf-8",
)
postprocess_ocr_result(vault, "REDO003", [])
# Phase 3 artifacts should exist
assert (ocr_dir / "render" / "fulltext.md").exists(), "render/fulltext.md missing after redo"
assert (ocr_dir / "health" / "ocr_health.json").exists(), "health/ocr_health.json missing after redo"

29
tests/test_selection_sync_pdf.py
View file

@ -291,3 +291,32 @@ def test_sync_reads_enriched_meta_without_breaking_ocr_status(tmp_path: Path) ->
status, error = validate_ocr_meta(paths, meta)
assert status == "done"
assert error == ""
def test_postprocess_writes_compat_fulltext_at_top_level(tmp_path) -> None:
"""Phase 3 compatibility: top-level fulltext.md must still exist."""
import json as _json
from paperforge.worker.ocr import postprocess_ocr_result
vault = tmp_path / "vault"
vault.mkdir()
(vault / "paperforge.json").write_text(
_json.dumps({"vault_config": {"system_dir": "System", "resources_dir": "Resources"}}),
encoding="utf-8",
)
ocr_root = vault / "System" / "PaperForge" / "ocr"
ocr_root.mkdir(parents=True)
ocr_dir = ocr_root / "COMP001"
ocr_dir.mkdir()
(ocr_dir / "meta.json").write_text(
'{"zotero_key":"COMP001","ocr_status":"done","ocr_model":"PaddleOCR"}',
encoding="utf-8",
)
page_num, markdown_path, json_path, fulltext_md_path = postprocess_ocr_result(vault, "COMP001", [])
# Top-level fulltext.md must exist
assert (ocr_dir / "fulltext.md").exists(), "top-level fulltext.md missing"
# Returned path must resolve to the top-level fulltext.md
assert "fulltext.md" in fulltext_md_path, "returned path does not point to fulltext.md"