More testing: JPEG

ocrmypdf/pdfa.py

@@ -67,8 +67,9 @@ def encode_text_string(s: str) -> str:
     From PDF 32000-1:2008 a string object may be included in hexademical form
     if it is enclosed in angle brackets.  For general Unicode the string should
     be UTF-16 (big endian) with byte order marks.  A non-hexademical
-    presentation is possible but this is preferable since it allows the output
-    Postscript file to be completely ASCII.
+    representation is doable but this is preferable since it allows the output
+    Postscript file to be completely ASCII and no escaping of Postscript
+    characters is necessary.
     '''
     if s == '':
         return ''

ocrmypdf/test/test_pageinfo.py

@@ -9,7 +9,9 @@ import os
 import sys
 import shutil
 from nose.tools import *
+from pkg_resources import Requirement, resource_filename
 
+req = Requirement.parse('ocrmypdf')
 
 TEST_OUTPUT = os.path.join(os.path.dirname(__file__), 'output')
 
@@ -93,3 +95,12 @@ def test_single_page_inline_image():
 
     pageinfo.pdf_get_all_pageinfo(filename)
 
+
+def test_jpeg():
+    filename = resource_filename(req, 'tests/resources/c02-22.pdf')
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+
+    pdfimage = pdfinfo[0]['images'][0]
+    assert pdfimage['enc'] == 'jpeg'
+

tests/resources/NOTE.rst

@@ -4,10 +4,14 @@ copyright reasons.
 Test files do not necessarily produce perfect (or even good) OCR
 results.
 
-+--------------+--------------------------------------------------------------------------------+
-| File         | Source                                                                         |
-+==============+================================================================================+
-| graph.pdf    | Wikimedia                                                                      |
-+--------------+--------------------------------------------------------------------------------+
-| c02-22.pdf   | Project Gutenberg: https://www.gutenberg.org/files/76/76-h/images/c02-22.jpg   |
-+--------------+--------------------------------------------------------------------------------+
++-------------------+--------------------------------------------------------------------------------+
+| File              | Source                                                                         |
++===================+================================================================================+
+| graph.pdf         | Wikimedia                                                                      |
++-------------------+--------------------------------------------------------------------------------+
+| c02-22.pdf        | Project Gutenberg: https://www.gutenberg.org/files/76/76-h/images/c02-22.jpg   |
++-------------------+--------------------------------------------------------------------------------+
+| LinnSequencer.jpg | Wikimedia: https://upload.wikimedia.org/wikipedia/en/b/b7/LinnSequencer_hardware_MIDI_sequencer_brochure_page_2_300dpi.jpg   |
++-------------------+--------------------------------------------------------------------------------+
+| congress.jpg      | http://www.baxleystamps.com/litho/meiji/courts_1871.jpg                        |
++-------------------+--------------------------------------------------------------------------------+