From 568bf7749e1b48cd84132122cf992db1d9f5038b Mon Sep 17 00:00:00 2001 From: Audiobook Producer Date: Sun, 18 Oct 2026 01:57:44 -0500 Subject: [PATCH] warnings.log: one line per entry; longer OCR error text --- _pipeline/bookio.py | 3 ++- _pipeline/ingest.py | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/_pipeline/bookio.py b/_pipeline/bookio.py index 39a64f9..ed8de78 100644 --- a/_pipeline/bookio.py +++ b/_pipeline/bookio.py @@ -30,7 +30,8 @@ def write_warnings(book_dir, stage, entries): if os.path.exists(path): with open(path, encoding="utf-8") as f: keep = [ln for ln in f.read().splitlines() if ln and not ln.startswith(stage + " |")] - lines = keep + ["%s | %s | %s | %s" % (stage, k, w, m) for k, w, m in entries] + one = lambda t: " / ".join(str(t).split("\n")).strip() # one entry = one line + lines = keep + ["%s | %s | %s | %s" % (stage, k, one(w), one(m)) for k, w, m in entries] with open(path, "w", encoding="utf-8") as f: f.write("\n".join(lines) + ("\n" if lines else "")) diff --git a/_pipeline/ingest.py b/_pipeline/ingest.py index 9489990..b3abe43 100644 --- a/_pipeline/ingest.py +++ b/_pipeline/ingest.py @@ -108,5 +108,5 @@ def ocr_if_needed(cfg, book_dir, book): src = os.path.join(book_dir, book["source_pdf"]) r = subprocess.run(["ocrmypdf", "--skip-text", "-l", cfg["ocr"]["language"], src, out], capture_output=True, text=True) if r.returncode != 0: - return [("ocr-failed", where, "ocrmypdf exit %d: %s" % (r.returncode, (r.stderr.strip()[:300] + " ... " + r.stderr.strip()[-300:]) if len(r.stderr) > 650 else r.stderr.strip()))] + return [("ocr-failed", where, "ocrmypdf exit %d: %s" % (r.returncode, (r.stderr.strip()[:700] + " ... " + r.stderr.strip()[-500:]) if len(r.stderr) > 1250 else r.stderr.strip()))] return [("ocr", where, "OCR applied to a scratch copy; original untouched")]