Experimental change to use qpdf to merge files (disables Ghostscript)

All but one tests pass, test_input_file_not_a_pdf

Not sure if PyPDF2 metadata generation will mangle the first page.

ocrmypdf/main.py

@@ -1134,8 +1134,8 @@ def merge_pages_ghostscript(
 @active_if(options.output_type == 'pdf')
 @merge(
     input=[add_text_layer, render_hocr_debug_page, skip_page,
-           tesseract_ocr_and_render_pdf],
-    output=os.path.join(work_folder, 'merged_nometadata.pdf'),
+           tesseract_ocr_and_render_pdf, repair_pdf],
+    output=os.path.join(work_folder, 'merged.pdf'),
     extras=[_log, _pdfinfo, _pdfinfo_lock])
 def merge_pages_qpdf(
         input_files,
@@ -1144,6 +1144,10 @@ def merge_pages_qpdf(
         pdfinfo,
         pdfinfo_lock):
 
+    metadata_file = next(
+        (ii for ii in input_files if ii.endswith('.repaired.pdf')))
+    input_files.remove(metadata_file)
+
     def input_file_order(s):
         '''Sort order: All rendered pages followed
         by their debug page.'''
@@ -1154,10 +1158,27 @@ def merge_pages_qpdf(
 
     pdf_pages = sorted(input_files, key=input_file_order)
     log.debug("Final pages: " + "\n".join(pdf_pages))
+
+    reader_metadata = pypdf.PdfFileReader(metadata_file)
+    pdfmark = get_pdfmark(reader_metadata)
+    pdfmark['/Producer'] = 'qpdf ' + qpdf.version()
+
+    first_page = pypdf.PdfFileReader(pdf_pages[0])
+
+    writer = pypdf.PdfFileWriter()
+    writer.appendPagesFromReader(first_page)
+    writer.addMetadata(pdfmark)
+    writer_file = pdf_pages[0].replace('.pdf', '.metadata.pdf')
+    with open(writer_file, 'wb') as f:
+        writer.write(f)
+
+    pdf_pages[0] = writer_file
+
     qpdf.merge(pdf_pages, output_file)
 
 
-@active_if(options.output_type == 'pdf')
+#@active_if(options.output_type == 'pdf')
+@active_if(False)
 @merge(
     input=[merge_pages_qpdf, repair_pdf],
     output=os.path.join(work_folder, 'merged.pdf'),
@@ -1188,7 +1209,7 @@ def copy_metadata(
 
 
 @merge(
-    input=[merge_pages_ghostscript, copy_metadata],
+    input=[merge_pages_ghostscript, merge_pages_qpdf],
     output=options.output_file,
     extras=[_log, _pdfinfo, _pdfinfo_lock])
 def copy_final(

ocrmypdf/qpdf.py

@@ -2,12 +2,32 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from subprocess import CalledProcessError, check_output, STDOUT, check_call
+from functools import lru_cache
 import sys
 import os
+import re
 
 from . import ExitCode, get_program
 
 
+@lru_cache(maxsize=1)
+def version():
+    args_qpdf = [
+        get_program('qpdf'),
+        '--version'
+    ]
+    try:
+        versions = check_output(
+            args_qpdf, close_fds=True, universal_newlines=True,
+            stderr=STDOUT)
+    except CalledProcessError:
+        print("Could not find qpdf executable on system PATH.")
+        sys.exit(ExitCode.missing_dependency)
+
+    qpdf_version = re.match(r'qpdf version (.+)', versions).group(1)
+    return qpdf_version
+
+
 def check(input_file, log):
     args_qpdf = [
         get_program('qpdf'),
@@ -20,7 +40,7 @@ def check(input_file, log):
     except CalledProcessError as e:
         if e.returncode == 2:
             log.error("{0}: not a valid PDF, and could not repair it.".format(
-                    input_file))
+                input_file))
             log.error("Details:")
             log.error(e.output)
         elif e.returncode == 3: