Fix issue #194 - --sidecar creates blank txt file

docs/release_notes.rst

@@ -5,6 +5,12 @@ OCRmyPDF uses `semantic versioning <http://semver.org/>`_ for its command line i
 
 The OCRmyPDF package itself does not contain a public API, although it is fairly stable and breaking changes are usually timed with a major release. A future release will clearly define the stable public API.
 
+v5.4.2
+------
+
+-   Fixed a regression from v5.4.1 that caused sidecar files to be created as empty files
+
+
 v5.4.1
 ------
 

ocrmypdf/pipeline.py

@@ -945,7 +945,7 @@ def merge_sidecars(
             if page_num != 0:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
-                with open(txt_file, 'r') as in_:
+                with open(txt_file, 'r', encoding="utf-8") as in_:
                     txt = in_.read()
                     # Tesseract v4 alpha started adding form feeds in 
                     # commit aa6eb6b
@@ -953,9 +953,9 @@ def merge_sidecars(
                     # for consistency just ignore its form feeds and insert our
                     # own
                     if txt.endswith('\f'):
-                        stream.write(in_.read()[:-1])
+                        stream.write(txt[:-1])
                     else:
-                        stream.write(in_.read())
+                        stream.write(txt)
             else:
                 stream.write('[OCR skipped on page {}]'.format(
                         page_num + 1))
@@ -964,7 +964,7 @@ def merge_sidecars(
         write_pages(sys.stdout)
         sys.stdout.flush()
     else:
-        with open(output_file, 'w', encoding='utf-8') as out:
+        with open(output_file, 'w', encoding="utf-8") as out:
             write_pages(out)
 
 

tests/test_main.py

@@ -805,7 +805,6 @@ def test_user_words(resources, outdir):
             '--image-dpi', 150,
             '--sidecar', sidecar_before
         )
-
         assert 'cromulent' not in sidecar_before.open().read()
 
     with word_list.open('w') as f:
@@ -984,6 +983,19 @@ def test_sidecar_pagecount(spoof_tesseract_cache, resources, outpdf):
         "Sidecar page count does not match PDF page count"
 
 
+def test_sidecar_nonempty(spoof_tesseract_cache, resources, outpdf):
+    sidecar = outpdf + '.txt'
+    check_ocrmypdf(
+        resources / 'ccitt.pdf', outpdf,
+        '--sidecar', sidecar,
+        env=spoof_tesseract_cache
+    )
+
+    with open(sidecar, 'r') as f:
+        ocr_text = f.read()
+    assert 'the' in ocr_text
+
+
 def test_pdfa_1(spoof_tesseract_cache, resources, outpdf):
     check_ocrmypdf(
         resources / 'ccitt.pdf', outpdf,