From fbf06741896fac650f936738162f9554b82fc594 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Sun, 15 Oct 2023 00:49:58 -0700
Subject: [PATCH] hocr_to_ocr_pdf: handle missing hocr json file

---
 src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py |  6 +++++-
 tests/test_api.py                          | 12 +++++++++---
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py b/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
index f3b5d47a..c13097dc 100644
--- a/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
+++ b/src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py
@@ -39,7 +39,11 @@ log = logging.getLogger(__name__)
 
 
 def exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
-    hocr_result = HOCRResult.from_json(page_context.get_path('hocr.json').read_text())
+    hocr_json = page_context.get_path('hocr.json')
+    if not hocr_json.exists():
+        # No hOCR file, so no OCR was performed on this page.
+        return HOCRResult(pageno=page_context.pageno)
+    hocr_result = HOCRResult.from_json(hocr_json.read_text())
     hocr_result.textpdf = render_hocr_page(
         page_context.get_path('ocr_hocr.hocr'), page_context
     )
diff --git a/tests/test_api.py b/tests/test_api.py
index d7a0a200..4e92c719 100644
--- a/tests/test_api.py
+++ b/tests/test_api.py
@@ -7,6 +7,7 @@ from io import BytesIO
 from pathlib import Path
 
 import pytest
+from pdfminer.high_level import extract_text
 
 import ocrmypdf
 
@@ -27,7 +28,7 @@ def test_stream_api(resources: Path):
     assert b'%PDF' in out.read(1024)
 
 
-def test_hocr_api(resources: Path, outdir: Path):
+def test_hocr_api_multipage(resources: Path, outdir: Path, outpdf: Path):
     ocrmypdf.pdf_to_hocr(
         resources / 'multipage.pdf',
         outdir,
@@ -37,9 +38,11 @@ def test_hocr_api(resources: Path, outdir: Path):
     )
     assert (outdir / '000001_ocr_hocr.hocr').exists()
     assert (outdir / '000006_ocr_hocr.hocr').exists()
-
     assert not (outdir / '000004_ocr_hocr.hocr').exists()
 
+    ocrmypdf.hocr_to_ocr_pdf(outdir, outpdf)
+    assert outpdf.exists()
+
 
 def test_hocr_to_pdf_api(resources: Path, outdir: Path, outpdf: Path):
     ocrmypdf.pdf_to_hocr(
@@ -54,4 +57,7 @@ def test_hocr_to_pdf_api(resources: Path, outdir: Path, outpdf: Path):
     mangled = hocr.replace('the', 'hocr')
     (outdir / '000001_ocr_hocr.hocr').write_text(mangled, encoding='utf-8')
 
-    ocrmypdf.hocr_to_ocr_pdf(outdir, outpdf)
+    ocrmypdf.hocr_to_ocr_pdf(outdir, outpdf, optimize=0)
+
+    text = extract_text(outpdf)
+    assert 'hocr' in text and 'the' not in text