welsberr
/
doclift
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Make doclift bundle paths portable

This commit is contained in:
welsberr 2026-04-23 10:27:33 -04:00
parent e725553562
commit 28aea13192
4 changed files with 30 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
src/doclift/convert.py
View File

@ -24,7 +24,11 @@ def _document_output_dir(out_root: Path, source_path: Path, title: str) -> Path:
return out_root / "documents" / f"{slugify(source_path.stem)}-{slugify(title)}"
def convert_doc(source_path: Path, out_root: Path, figure_assets: list | None = None) -> DocumentBundle:
def _relative_to_root(path: Path, root: Path) -> str:
return path.relative_to(root).as_posix()
def convert_doc(source_path: Path, source_root: Path, out_root: Path, figure_assets: list | None = None) -> DocumentBundle:
raw = run_catdoc(source_path)
cleaned = clean_text(raw)
title = extract_title(cleaned, source_path.stem)
@ -49,7 +53,8 @@ def convert_doc(source_path: Path, out_root: Path, figure_assets: list | None =
write_json(
tables_path,
{
"source_path": str(source_path),
"source_path": _relative_to_root(source_path, source_root),
"source_path_kind": "source_root_relative",
"table_references": table_refs,
"tables": [table.model_dump() for table in tables],
},
@ -57,7 +62,8 @@ def convert_doc(source_path: Path, out_root: Path, figure_assets: list | None =
write_json(
figures_path,
{
"source_path": str(source_path),
"source_path": _relative_to_root(source_path, source_root),
"source_path_kind": "source_root_relative",
"figure_references": figure_refs,
"related_assets": [asset.model_dump() for asset in related_assets],
},
@ -67,12 +73,14 @@ def convert_doc(source_path: Path, out_root: Path, figure_assets: list | None =
document_id=slugify(title),
title=title,
document_kind=document_kind,
source_path=str(source_path),
output_dir=str(doc_out),
markdown_path=str(markdown_path),
layout_path=str(layout_path),
tables_path=str(tables_path),
figures_path=str(figures_path),
source_path=_relative_to_root(source_path, source_root),
source_path_kind="source_root_relative",
output_dir=_relative_to_root(doc_out, out_root),
markdown_path=_relative_to_root(markdown_path, out_root),
layout_path=_relative_to_root(layout_path, out_root),
tables_path=_relative_to_root(tables_path, out_root),
figures_path=_relative_to_root(figures_path, out_root),
bundle_path_kind="bundle_root_relative",
table_count=len(tables),
figure_reference_count=len(figure_refs),
)
@ -81,9 +89,10 @@ def convert_doc(source_path: Path, out_root: Path, figure_assets: list | None =
def convert_directory(source_root: Path, out_root: Path, asset_root: Path | None = None) -> ConversionReport:
docs = sorted(path for path in source_root.rglob("*") if path.is_file() and path.suffix.lower() == ".doc")
figure_assets = collect_figure_assets(asset_root) if asset_root is not None else []
bundles = [convert_doc(path, out_root, figure_assets=figure_assets) for path in docs]
bundles = [convert_doc(path, source_root, out_root, figure_assets=figure_assets) for path in docs]
report = ConversionReport(
source_root=str(source_root),
source_root=source_root.name,
source_root_kind="source_label",
converter="catdoc_doc",
document_count=len(bundles),
documents=bundles,

2
src/doclift/legacy_doc.py
View File

@ -268,7 +268,7 @@ def collect_figure_assets(root: Path) -> list[FigureAsset]:
assets.append(
FigureAsset(
asset_id=slugify(relative),
path=str(path),
path=relative,
relative_path=relative,
name=path.name,
container=path.parent.name,

3
src/doclift/schemas.py
View File

@ -36,17 +36,20 @@ class DocumentBundle(BaseModel):
title: str
document_kind: str = "document"
source_path: str
source_path_kind: str = "source_root_relative"
output_dir: str
markdown_path: str
layout_path: str
tables_path: str
figures_path: str
bundle_path_kind: str = "bundle_root_relative"
table_count: int = 0
figure_reference_count: int = 0
class ConversionReport(BaseModel):
source_root: str
source_root_kind: str = "source_label"
converter: str
document_count: int = 0
documents: list[DocumentBundle] = Field(default_factory=list)

6
tests/test_convert.py
View File

@ -42,7 +42,13 @@ def test_convert_directory_writes_manifest_and_conversion_report(tmp_path: Path,
)
assert manifest["document_count"] == 1
assert manifest["source_root"] == "src"
assert manifest["documents"][0]["source_path"] == "sample.doc"
assert manifest["documents"][0]["markdown_path"] == "documents/sample-lecture-1-example-legacy-document/document.md"
assert conversion_report["summary"]["documents_with_tables"] == 1
assert conversion_report["summary"]["documents_with_figure_references"] == 1
assert figures_payload["source_path"] == "sample.doc"
assert figures_payload["source_path_kind"] == "source_root_relative"
assert figures_payload["figure_references"] == ["Fig. 5.1"]
assert len(figures_payload["related_assets"]) == 1
assert figures_payload["related_assets"][0]["path"] == "Fig. 5.1.bmp"