From 9a4493f211125e0b9d101059c2a255a89af3c791 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Fri, 18 Jan 2019 05:33:28 -0800
Subject: [PATCH] Add --unpaper-args

Needs test code and stricter validation
---
 src/ocrmypdf/__main__.py     | 18 ++++++++++++++++
 src/ocrmypdf/_pipeline.py    |  2 +-
 src/ocrmypdf/exec/unpaper.py | 41 ++++++++++++++++++++----------------
 3 files changed, 42 insertions(+), 19 deletions(-)

diff --git a/src/ocrmypdf/__main__.py b/src/ocrmypdf/__main__.py
index c2cb06bb..f7a9047f 100755
--- a/src/ocrmypdf/__main__.py
+++ b/src/ocrmypdf/__main__.py
@@ -278,6 +278,13 @@ preprocessing.add_argument(
     help="Clean page as above, and incorporate the cleaned image in the final "
     "PDF.  Might remove desired content.",
 )
+preprocessing.add_argument(
+    '--unpaper-args',
+    type=str,
+    default=None,
+    help="A quoted string of arguments to pass to unpaper. Requires --clean. "
+    "Example: --unpaper-args '--layout double'.",
+)
 preprocessing.add_argument(
     '--oversample',
     metavar='DPI',
@@ -623,12 +630,23 @@ def _optional_program_recommended(name, version_fn, min_version, for_argument):
 
 
 def check_options_preprocessing(options, log):
+    if options.unpaper_args and not options.clean:
+        raise argparse.ArgumentError(
+            None, "--clean is required for --unpaper-args"
+        )
     if any((options.clean, options.clean_final)):
         from .exec import unpaper
 
         _optional_program_required(
             'unpaper', unpaper.version, '6.1', '--clean, --clean-final'
         )
+        try:
+            if options.unpaper_args:
+                options.unpaper_args = unpaper.validate_custom_args(
+                    options.unpaper_args
+                )
+        except Exception as e:
+            raise argparse.ArgumentError(None, str(e))
 
 
 def check_options_ocr_behavior(options, log):
diff --git a/src/ocrmypdf/_pipeline.py b/src/ocrmypdf/_pipeline.py
index 4fe52970..abe90f9c 100644
--- a/src/ocrmypdf/_pipeline.py
+++ b/src/ocrmypdf/_pipeline.py
@@ -566,7 +566,7 @@ def preprocess_clean(input_file, output_file, log, context):
     pageinfo = get_pageinfo(input_file, context)
     dpi = get_page_square_dpi(pageinfo, options)
 
-    unpaper.clean(input_file, output_file, dpi, log)
+    unpaper.clean(input_file, output_file, dpi, log, options.unpaper_args)
 
 
 def select_ocr_image(infiles, output_file, log, context):
diff --git a/src/ocrmypdf/exec/unpaper.py b/src/ocrmypdf/exec/unpaper.py
index 87104f99..cf53fd8a 100644
--- a/src/ocrmypdf/exec/unpaper.py
+++ b/src/ocrmypdf/exec/unpaper.py
@@ -19,6 +19,7 @@
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
 
 import os
+import shlex
 import sys
 from functools import lru_cache
 from subprocess import STDOUT, CalledProcessError, check_output
@@ -86,21 +87,25 @@ def run(input_file, output_file, dpi, log, mode_args):
             Image.open(output_pnm.name).save(output_file, dpi=(dpi, dpi))
 
 
-def clean(input_file, output_file, dpi, log):
-    run(
-        input_file,
-        output_file,
-        dpi,
-        log,
-        [
-            '--layout',
-            'none',
-            '--mask-scan-size',
-            '100',  # don't blank out narrow columns
-            '--no-border-align',  # don't align visible content to borders
-            '--no-mask-center',  # don't center visible content within page
-            '--no-grayfilter',  # don't remove light gray areas
-            '--no-blackfilter',  # don't remove solid black areas
-            '--no-deskew',  # don't deskew
-        ],
-    )
+def validate_custom_args(args: str):
+    unpaper_args = shlex.split(args)
+    if any('/' in arg for arg in unpaper_args):
+        raise ValueError('No filenames allowed in --unpaper-args')
+    return unpaper_args
+
+
+def clean(input_file, output_file, dpi, log, unpaper_args=None):
+    default_args = [
+        '--layout',
+        'none',
+        '--mask-scan-size',
+        '100',  # don't blank out narrow columns
+        '--no-border-align',  # don't align visible content to borders
+        '--no-mask-center',  # don't center visible content within page
+        '--no-grayfilter',  # don't remove light gray areas
+        '--no-blackfilter',  # don't remove solid black areas
+        '--no-deskew',  # don't deskew
+    ]
+    if not unpaper_args:
+        unpaper_args = default_args
+    run(input_file, output_file, dpi, log, unpaper_args)