From fa48205bb8fa74484f542ea1f9ba6ef02f5c2135 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Thu, 18 Oct 2018 21:46:08 -0700
Subject: [PATCH] Add feature to remove vector graphics objects

---
 src/ocrmypdf/__main__.py         | 5 +++++
 src/ocrmypdf/_pipeline.py        | 3 ++-
 src/ocrmypdf/exec/ghostscript.py | 5 ++++-
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/src/ocrmypdf/__main__.py b/src/ocrmypdf/__main__.py
index 3e69effd..175118d4 100755
--- a/src/ocrmypdf/__main__.py
+++ b/src/ocrmypdf/__main__.py
@@ -244,6 +244,11 @@ preprocessing.add_argument(
     '--oversample', metavar='DPI', type=numeric(int, 0, 5000), default=0,
     help="Oversample images to at least the specified DPI, to improve OCR "
          "results slightly")
+preprocessing.add_argument(
+    '--remove-vectors', action='store_true',
+    help="EXPERIMENTAL. Remove any vector graphics objects from the PDF, "
+         "including text rendered as curves. Useful when these objects "
+         "interfere with OCR.")
 
 ocrsettings = parser.add_argument_group(
     "OCR options",
diff --git a/src/ocrmypdf/_pipeline.py b/src/ocrmypdf/_pipeline.py
index e114d6b6..5bb057d6 100644
--- a/src/ocrmypdf/_pipeline.py
+++ b/src/ocrmypdf/_pipeline.py
@@ -493,7 +493,8 @@ def rasterize_with_ghostscript(
     ghostscript.rasterize_pdf(
         input_file, output_file, xres=canvas_dpi, yres=canvas_dpi,
         raster_device=device, log=log, page_dpi=(page_dpi, page_dpi),
-        pageno=page_number(input_file), rotation=correction)
+        pageno=page_number(input_file), rotation=correction,
+        filter_vector=options.remove_vectors)
 
 
 def preprocess_remove_background(
diff --git a/src/ocrmypdf/exec/ghostscript.py b/src/ocrmypdf/exec/ghostscript.py
index 60a0f3c6..d1abfe96 100644
--- a/src/ocrmypdf/exec/ghostscript.py
+++ b/src/ocrmypdf/exec/ghostscript.py
@@ -101,7 +101,7 @@ def extract_text(input_file, pageno=1):
 
 
 def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
-                  pageno=1, page_dpi=None, rotation=None):
+                  pageno=1, page_dpi=None, rotation=None, filter_vector=False):
     """Rasterize one page of a PDF at resolution (xres, yres) in canvas units.
 
     The image is sized to match the integer pixels dimensions implied by
@@ -116,6 +116,8 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
     :param log:
     :param pageno: page number to rasterize (beginning at page 1)
     :param page_dpi: resolution tuple (x, y) overriding output image DPI
+    :param rotation: 0, 90, 180, 270: clockwise angle to rotate page
+    :param filter_vector: if True, remove vector graphics objects
     :return:
     """
     res = xres, yres
@@ -134,6 +136,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
             '-dFirstPage=%i' % pageno,
             '-dLastPage=%i' % pageno,
             '-r{0}x{1}'.format(str(int_res[0]), str(int_res[1])),
+        ] + (['-dFILTERVECTOR'] if filter_vector else []) + [
             '-o', tmp.name,
             '-dAutoRotatePages=/None',  # Probably has no effect on raster
             '-f',