From a036de318edb06dec44dc9163298dbd7ddce7882 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Thu, 30 Jul 2015 04:06:31 -0700
Subject: [PATCH] Replace mupdf and poppler with qpdf

Drop two dependencies and replace them with one that does the job of
both.  Smells like progress.

mupdf does PDF file repair and rendering
poppler does rendering and page splitting
qpdf does PDF file repair and page splitting
ghostscript does PDF file repair, rendering, and page splitting (sort of)

So we use qpdf.  Ghostscript's page splitting is supposed is less
efficient because it reprints the page (PDF -> Postscript -> PDF) and
possibly loses quality.  qpdf's library could be used to improve
performance.

This causes a slight performance regression:

py.test tests/test_main.py::test_maximum_options went from 187 seconds
up to 192.  This is likely due to O(n) serialized invocations of qpdf
compared to a single serialized call to pdfseparate.  Could improve on
this situation by using the example code in qpdf: pdf-split-pages.cc
or create marker files in split_pages() and then write a new @transform
function that would split pages on each CPU.  Probably not worth it,
overall, unless this causes problems on files with hundreds of pages.
---
 RELEASE_NOTES.rst |  4 +++-
 ocrmypdf/main.py  | 26 +++++++++++++++-----------
 setup.py          | 16 ++++------------
 3 files changed, 22 insertions(+), 24 deletions(-)

diff --git a/RELEASE_NOTES.rst b/RELEASE_NOTES.rst
index 7a53c3de..bdfcaff3 100644
--- a/RELEASE_NOTES.rst
+++ b/RELEASE_NOTES.rst
@@ -41,12 +41,14 @@ Changes
    - GNU parallel_
    - ImageMagick_
    - Python 2.7
+   - Poppler
+   - MuPDF_ tools
    - shell scripts
 
 -  Some new external dependencies are required:
 
-   - MuPDF_ tools
    - Ghostscript 9.14+
+   - qpdf 5.0.0+
    - Unpaper_ 6.1 (optional)
    - some automatically managed Python dependencies
   
diff --git a/ocrmypdf/main.py b/ocrmypdf/main.py
index b2574123..97b9c0da 100755
--- a/ocrmypdf/main.py
+++ b/ocrmypdf/main.py
@@ -17,7 +17,7 @@ import PyPDF2 as pypdf
 from PIL import Image
 
 from subprocess import Popen, check_call, PIPE, CalledProcessError, \
-    TimeoutExpired
+    TimeoutExpired, check_output
 try:
     from subprocess import DEVNULL
 except ImportError:
@@ -319,11 +319,10 @@ def repair_pdf(
         log,
         pdfinfo,
         pdfinfo_lock):
-    args_mutool = [
-        'mutool', 'clean',
-        input_file, output_file
+    args_qpdf = [
+        'qpdf', input_file, output_file
     ]
-    check_call(args_mutool)
+    check_call(args_qpdf)
 
     with pdfinfo_lock:
         pdfinfo.extend(pdf_get_all_pageinfo(output_file))
@@ -388,12 +387,17 @@ def split_pages(
     for oo in output_files:
         with suppress(FileNotFoundError):
             os.unlink(oo)
-    args_pdfseparate = [
-        'pdfseparate',
-        input_file,
-        os.path.join(work_folder, '%06d.page.pdf')
-    ]
-    check_call(args_pdfseparate)
+
+    pages = check_output(['qpdf', '--show-npages', input_file],
+                         universal_newlines=True, close_fds=True)
+
+    for n in range(int(pages)):
+        args_qpdf = [
+            'qpdf', input_file,
+            '--pages', input_file, '{0}'.format(n + 1), '--',
+            os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
+        ]
+        check_call(args_qpdf)
 
     from glob import glob
     for filename in glob(os.path.join(work_folder, '*.page.pdf')):
diff --git a/setup.py b/setup.py
index 4dff3f9d..ba3833f5 100644
--- a/setup.py
+++ b/setup.py
@@ -150,13 +150,6 @@ if command.startswith('install') or \
         package='unpaper',
         optional=True
     )
-    # Deprecated
-    check_external_program(
-        program='pdfseparate',
-        need_version='0.29.0',
-        package='poppler',
-        version_check_args=['-v']
-    )
     check_external_program(
         program='java',
         need_version='1.5.0',
@@ -164,11 +157,10 @@ if command.startswith('install') or \
         version_check_args=['-version']
     )
     check_external_program(
-        program='mutool',
-        need_version='1.7',
-        version_check_args=['-v'],
-        version_scrape_regex=re.compile(r'(\d+\.\d+[a-z]*)'),
-        package='mupdf-tools'
+        program='qpdf',
+        need_version='5.0.0',
+        package='qpdf',
+        version_check_args=['--version']
     )
 
 setup(