Add test to sanity check our pdf renderers

src/ocrmypdf/hocrtransform.py

@@ -219,6 +219,7 @@ class HocrTransform:
             chain(
                 self.hocr.iterfind(self._child_xpath('span', 'ocr_header')),
                 self.hocr.iterfind(self._child_xpath('span', 'ocr_line')),
+                self.hocr.iterfind(self._child_xpath('span', 'ocr_textfloat')),
             ),
             key=self.topdown_position,
         ):

tests/test_hocrtransform.py

@@ -15,20 +15,46 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+import re
+from io import StringIO
+from pathlib import Path
+
 import pytest
+from pdfminer.converter import TextConverter
+from pdfminer.layout import LAParams
+from pdfminer.pdfdocument import PDFDocument
+from pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManager
+from pdfminer.pdfpage import PDFPage
+from pdfminer.pdfparser import PDFParser
 from PIL import Image
 
 from ocrmypdf import hocrtransform
 from ocrmypdf._exec.tesseract import HOCR_TEMPLATE
 from ocrmypdf.helpers import check_pdf
 
+
+def text_from_pdf(filename):
+    output_string = StringIO()
+    with open(filename, 'rb') as in_file:
+        parser = PDFParser(in_file)
+        doc = PDFDocument(parser)
+        rsrcmgr = PDFResourceManager()
+        device = TextConverter(rsrcmgr, output_string, laparams=LAParams())
+        interpreter = PDFPageInterpreter(rsrcmgr, device)
+        for page in PDFPage.create_pages(doc):
+            interpreter.process_page(page)
+    return output_string.getvalue()
+
+
 # pylint: disable=redefined-outer-name
 
+check_ocrmypdf = pytest.helpers.check_ocrmypdf  # pylint: disable=no-member
+
 
 @pytest.fixture
 def blank_hocr(tmp_path):
     filename = tmp_path / "blank.hocr"
-    filename.write_text(HOCR_TEMPLATE)  # pylint: disable=E1101
+    filename.write_text(HOCR_TEMPLATE)
     return filename
 
 
@@ -42,3 +68,33 @@ def test_mono_image(blank_hocr, outdir):
     hocr.to_pdf(str(outdir / 'mono.pdf'), image_filename=str(outdir / 'mono.tif'))
 
     check_pdf(str(outdir / 'mono.pdf'))
+
+
+def test_hocrtransform_matches_sandwich(resources, outdir):
+    check_ocrmypdf(
+        resources / 'ccitt.pdf',
+        outdir / 'hocr.pdf',
+        '--pdf-renderer=hocr',
+        # '--plugin',
+        # 'tests/plugins/tesseract_cache.py',
+    )
+    check_ocrmypdf(
+        resources / 'ccitt.pdf',
+        outdir / 'tess.pdf',
+        '--pdf-renderer=sandwich',
+        # '--plugin',
+        # 'tests/plugins/tesseract_cache.py',
+    )
+
+    def clean(s):
+        s = re.sub(r'[ ]+', ' ', s)
+        s = re.sub(r'[ ]?[\n]+', r'\n', s)
+        return s
+
+    hocr_txt = clean(text_from_pdf(outdir / 'hocr.pdf'))
+    tess_txt = clean(text_from_pdf(outdir / 'tess.pdf'))
+
+    # Path('hocr.txt').write_text(hocr_txt)
+    # Path('tess.txt').write_text(tess_txt)
+
+    assert hocr_txt == tess_txt