72 lines
2.5 KiB
Python
72 lines
2.5 KiB
Python
"""PDF→Text-Konvertierung: pymupdf4llm primär, pdftotext-Fallback, mtime-Cache."""
|
|
|
|
import os
|
|
import time
|
|
|
|
import fitz # PyMuPDF
|
|
import pytest
|
|
|
|
import blocks as blx
|
|
|
|
|
|
def _mini_pdf(path, text="Approximationsalgorithmen sind wichtig."):
|
|
doc = fitz.open()
|
|
page = doc.new_page()
|
|
page.insert_text((72, 72), text, fontsize=12)
|
|
doc.save(str(path))
|
|
doc.close()
|
|
|
|
|
|
def test_convert_writes_markdown_txt(tmp_path):
|
|
_mini_pdf(tmp_path / "skript.pdf")
|
|
blx._convert_pdfs(tmp_path)
|
|
out = (tmp_path / "skript.txt").read_text(encoding="utf-8")
|
|
assert "Approximationsalgorithmen" in out
|
|
|
|
|
|
def test_cache_skips_fresh_txt(tmp_path):
|
|
_mini_pdf(tmp_path / "a.pdf")
|
|
marker = tmp_path / "a.txt"
|
|
marker.write_text("MARKER", encoding="utf-8")
|
|
now = time.time() + 60
|
|
os.utime(marker, (now, now))
|
|
blx._convert_pdfs(tmp_path)
|
|
assert marker.read_text(encoding="utf-8") == "MARKER" # nicht neu konvertiert
|
|
|
|
|
|
def test_fallback_to_pdftotext(tmp_path, monkeypatch):
|
|
_mini_pdf(tmp_path / "b.pdf")
|
|
monkeypatch.setattr(blx, "_pdf_markdown", lambda p: None)
|
|
monkeypatch.setattr(blx, "_pdf_plaintext", lambda p: "fallback")
|
|
blx._convert_pdfs(tmp_path)
|
|
assert (tmp_path / "b.txt").read_text(encoding="utf-8") == "fallback"
|
|
|
|
|
|
def test_ocr_languages_from_tessdata(tmp_path, monkeypatch):
|
|
import pymupdf
|
|
|
|
monkeypatch.setattr(pymupdf, "get_tessdata", lambda: str(tmp_path))
|
|
assert blx._ocr_languages() is None # keine Sprachdaten → OCR aus
|
|
(tmp_path / "eng.traineddata").touch()
|
|
assert blx._ocr_languages() == "eng"
|
|
(tmp_path / "deu.traineddata").touch()
|
|
assert blx._ocr_languages() == "deu+eng"
|
|
monkeypatch.setattr(pymupdf, "get_tessdata", lambda: (_ for _ in ()).throw(RuntimeError()))
|
|
assert blx._ocr_languages() is None
|
|
|
|
|
|
def test_fidelity_guard_prefers_faithful_plaintext():
|
|
plain = "Definition. P = {L ⊆ Σ | A ∈ L} und ≤ sowie häufig über. " * 20
|
|
# Markdown verlor die Formeln (Symbole weg) → plain gewinnt
|
|
md_lossy = "Definition. und sowie h¨aufig ¨uber. " * 20
|
|
text, tool = blx._pick_conversion(md_lossy, plain)
|
|
assert tool == "pdftotext"
|
|
# Markdown treu (Symbole + Länge da) → md gewinnt
|
|
md_ok = "# Def\n" + plain
|
|
text, tool = blx._pick_conversion(md_ok, plain)
|
|
assert tool == "pymupdf4llm"
|
|
# nur eine Quelle verfügbar
|
|
assert blx._pick_conversion(None, plain)[1] == "pdftotext"
|
|
assert blx._pick_conversion(md_ok, None)[1] == "pymupdf4llm"
|
|
assert blx._pick_conversion(None, None) is None
|