Merge branch 'feature/pdfa-2' into develop

RELEASE_NOTES.rst

@@ -5,6 +5,14 @@ Please always read this file before installing the package
 
 Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
 
+
+Latest:
+=======
+
+-  Default output format is now PDF/A-2b instead of PDF/A-1b
+-  Python 3.5 and OS X El Capitan are now supported platforms - no changes were
+   needed to implement support
+
 v3.0:
 =====
 

ocrmypdf/ghostscript.py

@@ -44,7 +44,7 @@ def generate_pdfa(pdf_pages, output_file, threads=1):
             "-sDEVICE=pdfwrite",
             "-sColorConversionStrategy=/RGB",
             "-sProcessColorModel=DeviceRGB",
-            "-dPDFA",
+            "-dPDFA=2",
             "-sPDFACompatibilityPolicy=2",
             "-sOutputICCProfile=srgb.icc",
             "-sOutputFile=" + gs_pdf.name,

ocrmypdf/main.py

@@ -39,9 +39,7 @@ warnings.simplefilter('ignore', pypdf.utils.PdfReadWarning)
 
 
 BASEDIR = os.path.dirname(os.path.realpath(__file__))
-JHOVE_PATH = os.path.realpath(os.path.join(BASEDIR, 'jhove'))
-JHOVE_JAR = os.path.join(JHOVE_PATH, 'bin', 'JhoveApp.jar')
-JHOVE_CFG = os.path.join(JHOVE_PATH, 'conf', 'jhove.conf')
+VERSION = '3.0'
 
 
 # -------------
@@ -103,7 +101,7 @@ check_pil_encoder('zlib', 'PNG')
 parser = cmdline.get_argparse(
     prog="ocrmypdf",
     description="Generate searchable PDF file from an image-only PDF file.",
-    version='3.0',
+    version=VERSION,
     fromfile_prefix_chars='@',
     ignored_args=[
         'touch_files_only', 'recreate_database', 'checksum_file_name',
@@ -176,7 +174,7 @@ advanced.add_argument(
     '--tesseract-config', default=[], type=list, action='append',
     help="additional Tesseract configuration files")
 advanced.add_argument(
-    '--pdf-renderer', choices=['tesseract', 'hocr'], default='hocr',
+    '--pdf-renderer', choices=['auto', 'tesseract', 'hocr'], default='auto',
     help='choose OCR PDF renderer')
 advanced.add_argument(
     '--tesseract-timeout', default=180.0, type=float,
@@ -218,6 +216,8 @@ if not set(options.language).issubset(tesseract.languages()):
 # ----------
 # Arguments
 
+if options.pdf_renderer == 'auto':
+    options.pdf_renderer = 'hocr'
 
 if any((options.deskew, options.clean, options.clean_final)):
     try:
@@ -756,6 +756,11 @@ def generate_postscript_stub(
     if options.subject:
         pdfmark['subject'] = options.subject
 
+    pdfmark['creator'] = '{0} {1} / Tesseract OCR{2} {3}'.format(
+            parser.prog, VERSION,
+            '+PDF' if options.pdf_renderer == 'tesseract' else '',
+            tesseract.version())
+
     generate_pdfa_def(output_file, pdfmark)
 
 

ocrmypdf/pageinfo.py

@@ -104,6 +104,28 @@ def _find_page_images(page, pageinfo):
         yield image
 
 
+def _page_has_text(pdf, page):
+    # Simple test
+    text = page.extractText()
+    if text.strip() != '':
+        return True
+
+    # More nuanced test to deal with quirks of Tesseract PDF generation
+    # Check if there's a Glyphless font
+    try:
+        font = page['/Resources']['/Font']
+    except KeyError:
+        pass
+    else:
+        font_objects = list(font.keys())
+        for font_object in font_objects:
+            basefont = font[font_object]['/BaseFont']
+            if basefont.endswith('GlyphLessFont'):
+                return True
+
+    return False
+
+
 def _pdf_get_pageinfo(infile, page: int):
     pageinfo = {}
     pageinfo['pageno'] = page
@@ -112,8 +134,7 @@ def _pdf_get_pageinfo(infile, page: int):
     pdf = pypdf.PdfFileReader(infile)
     page = pdf.pages[page - 1]
 
-    text = page.extractText()
-    pageinfo['has_text'] = (text.strip() != '')
+    pageinfo['has_text'] = _page_has_text(pdf, page)
 
     width_pt = page['/MediaBox'][2] - page['/MediaBox'][0]
     height_pt = page['/MediaBox'][3] - page['/MediaBox'][1]

ocrmypdf/pdfa.py

@@ -27,6 +27,7 @@ def
   /Author <$author>
   /Subject <$subject>
   /Keywords <$keywords>
+  /Creator <$creator>
   /DOCINFO pdfmark
 
 % Define an ICC profile :
@@ -86,6 +87,7 @@ def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
                           title=pdfmark_utf16.get('title', ''),
                           author=pdfmark_utf16.get('author', ''),
                           subject=pdfmark_utf16.get('subject', ''),
+                          creator=pdfmark_utf16.get('creator', ''),
                           keywords=pdfmark_utf16.get('keywords', ''))
     return result