Add Markdown recheck command

This commit is contained in:
NINI
2026-05-11 01:00:26 +09:00
parent b69c03c206
commit 03927a26a1
9 changed files with 276 additions and 11 deletions
+29 -2
View File
@@ -16,8 +16,9 @@ from pdf2md.mineru_adapter import MinerUAdapterResult
class FakeAdapter:
def __init__(self, *, succeeded: bool = True) -> None:
def __init__(self, *, succeeded: bool = True, raw_markdown: str | None = None) -> None:
self.succeeded = succeeded
self.raw_markdown = raw_markdown
self.calls: list[Path] = []
self.options: list[object] = []
@@ -33,7 +34,7 @@ class FakeAdapter:
command=("mineru", "-p", str(input_path), "-o", str(output_dir)),
input_pdf=input_path,
work_dir=output_dir,
raw_markdown=f"# {input_path.stem}\n" if self.succeeded else None,
raw_markdown=(self.raw_markdown or f"# {input_path.stem}\n") if self.succeeded else None,
raw_structured={"pages": 1},
asset_paths=(),
warnings=() if self.succeeded else (warning,),
@@ -188,6 +189,32 @@ def test_cli_failure_summary_returns_nonzero(tmp_path: Path, capsys) -> None:
assert not (tmp_path / "out" / "paper.md").exists()
def test_cli_recheck_markdown_regenerates_adjacent_metadata_and_report(tmp_path: Path, capsys) -> None:
pdf = make_pdf(tmp_path, "paper.pdf")
out = tmp_path / "out"
adapter = FakeAdapter(raw_markdown="Inline \\(bad_math\\)\n")
assert (
main(
["convert", str(pdf), "--out", str(out)],
adapter=adapter,
clock=fixed_clock,
math_checker=lambda _: False,
)
== 0
)
capsys.readouterr()
markdown_path = out / "paper.md"
markdown_path.write_text("Inline $x_i$\n", encoding="utf-8")
exit_code = main(["recheck", str(markdown_path)], clock=fixed_clock, math_checker=lambda _: True)
captured = capsys.readouterr()
assert exit_code == 0
assert "rechecked:" in captured.out
assert "warnings: 0" in captured.out
assert "- Final status: `success`" in (out / "paper.report.md").read_text(encoding="utf-8")
def test_cli_preflight_conflict_fails_before_conversion(tmp_path: Path, capsys) -> None:
pdf = make_pdf(tmp_path, "paper.pdf")
out = tmp_path / "out"
+28 -1
View File
@@ -9,7 +9,7 @@ import pytest
from pypdf import PdfWriter
import pdf2md.conversion as conversion_module
from pdf2md.conversion import BatchConversionResult, convert_input, convert_pdf
from pdf2md.conversion import BatchConversionResult, convert_input, convert_pdf, recheck_markdown
from pdf2md.ir import WarningCode, WarningRecord, WarningSeverity
from pdf2md.mineru_adapter import MinerUAdapterResult, StrictLocalViolationError
from pdf2md.paths import OutputConflictError
@@ -230,6 +230,33 @@ def test_convert_pdf_records_math_checker_failures_in_metadata_and_report(tmp_pa
assert "`MATH_RENDER_FAILED`" in report
def test_recheck_markdown_regenerates_metadata_and_report_from_current_markdown(tmp_path: Path) -> None:
pdf = make_pdf(tmp_path)
adapter = FakeAdapter(raw_markdown="Inline \\(bad_math\\)\n")
result = convert_pdf(pdf, tmp_path / "out", adapter=adapter, math_checker=lambda _: False, clock=fixed_clock)
result.markdown_path.write_text("Inline $x_i$\n", encoding="utf-8")
rechecked = recheck_markdown(result.markdown_path, math_checker=lambda _: True, clock=fixed_clock)
assert rechecked.final_status == "success"
assert rechecked.warning_count == 0
assert rechecked.markdown_path == result.markdown_path
assert rechecked.metadata_path == result.metadata_path
assert rechecked.report_path == result.report_path
metadata = json.loads(result.metadata_path.read_text(encoding="utf-8"))
assert metadata["source_sha256"] == hashlib.sha256(pdf.read_bytes()).hexdigest()
assert metadata["created_at"] == "2026-05-08T00:00:00Z"
assert metadata["summary"]["pages_processed"] == 1
assert metadata["summary"]["inline_formula_count"] == 1
assert metadata["summary"]["math_render_error_count"] == 0
assert metadata["summary"]["warning_count"] == 0
assert metadata["warnings"] == []
report = result.report_path.read_text(encoding="utf-8")
assert "- Final status: `success`" in report
assert "- Math render error count: 0" in report
assert "- None" in report
def test_convert_pdf_records_unavailable_math_checker_for_math_output(tmp_path: Path, monkeypatch) -> None:
pdf = make_pdf(tmp_path)
adapter = FakeAdapter(raw_markdown="Inline \\(x\\)\n")
+1
View File
@@ -6,3 +6,4 @@ import pdf2md
def test_package_imports() -> None:
assert pdf2md.__version__ == "0.1.0"
assert callable(pdf2md.convert_pdf)
assert callable(pdf2md.recheck_markdown)