Test case: true type font without Unicode mapping

src/ocrmypdf/pdfinfo/__init__.py

@@ -588,12 +588,12 @@ def _pdf_get_pageinfo(pdf, pageno: int, infile, xmltext):
     return pageinfo
 
 
-def _pdf_get_all_pageinfo(infile, detailed_page_analysis, log=None):
+def _pdf_get_all_pageinfo(infile, detailed_analysis=False, log=None):
     if not log:
         log = Mock()
 
     pdf = pikepdf.open(infile)
-    if detailed_page_analysis:
+    if detailed_analysis:
         pages_xml = None
     else:
         pages_xml = ghosttext.extract_text_xml(infile, pdf, pageno=None, log=log)
@@ -601,17 +601,18 @@ def _pdf_get_all_pageinfo(infile, detailed_page_analysis, log=None):
     pages = []
     for n in range(len(pdf.pages)):
         page_xml = pages_xml[n] if pages_xml else None
-        page = PageInfo(pdf, n, infile, page_xml)
+        page = PageInfo(pdf, n, infile, page_xml, detailed_analysis)
         pages.append(page)
 
     return pages, pdf
 
 
 class PageInfo:
-    def __init__(self, pdf, pageno, infile, xmltext):
+    def __init__(self, pdf, pageno, infile, xmltext, detailed_analysis=False):
         self._pageno = pageno
         self._infile = infile
         self._pageinfo = _pdf_get_pageinfo(pdf, pageno, infile, xmltext)
+        self._detailed_analysis = detailed_analysis
 
     @property
     def pageno(self):
@@ -623,6 +624,8 @@ class PageInfo:
 
     @property
     def has_corrupt_text(self):
+        if not self._detailed_analysis:
+            raise NotImplementedError('Did not do detailed analysis')
         return any(tbox.is_corrupt for tbox in self._pageinfo['textboxes'])
 
     @property

tests/resources/README.rst

@@ -139,6 +139,11 @@ licensed under the specified license.
         - @jbarlow83
         - @jbarlow83
         - CC-BY-SA 4.0
+    *   - truetype_font_nomapping.pdf
+        - example of a PDF with an embedded subsetted TrueType font with no Unicode mapping
+        - @jbarlow83
+        - @jbarlow83
+        - CC-BY-SA 4.0
     *   - trivial.pdf
         - smallest possible valid PDF-1.3 with all required fields
         - @jbarlow83

tests/test_pdfinfo.py

@@ -183,3 +183,13 @@ def test_ocr_detection(resources):
     pdf = pdfinfo.PdfInfo(filename)
     assert not pdf[0].has_vector
     assert pdf[0].has_text
+
+
+def test_corrupt_font_detection(resources):
+    filename = resources / 'truetype_font_nomapping.pdf'
+    with pytest.raises(NotImplementedError):
+        pdf = pdfinfo.PdfInfo(filename)
+        pdf[0].has_corrupt_text
+
+    pdf = pdfinfo.PdfInfo(filename, detailed_page_analysis=True)
+    assert pdf[0].has_corrupt_text