Merge v7.3.0 development

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',

src/ocrmypdf/exec/qpdf.py

@@ -19,6 +19,7 @@ from subprocess import CalledProcessError, STDOUT, PIPE, run
 from functools import lru_cache
 
 from . import  get_version
+from ..helpers import fspath
 
 
 @lru_cache(maxsize=1)
@@ -30,7 +31,7 @@ def check(input_file, log=None):
     args_qpdf = [
         'qpdf',
         '--check',
-        input_file
+        fspath(input_file)
     ]
 
     if log is None:

src/ocrmypdf/exec/tesseract.py

@@ -21,11 +21,11 @@ import shutil
 from functools import lru_cache
 from collections import namedtuple
 from textwrap import dedent
-from subprocess import CalledProcessError, TimeoutExpired, check_output, STDOUT
+from subprocess import CalledProcessError, TimeoutExpired, check_output, STDOUT, run, PIPE
 from contextlib import suppress
 
 from ..exceptions import MissingDependencyError, TesseractConfigError
-from ..helpers import page_number
+from ..helpers import page_number, fspath
 from . import get_version
 
 OrientationConfidence = namedtuple(
@@ -92,22 +92,33 @@ def psm():
 
 @lru_cache(maxsize=1)
 def languages():
+    def lang_error(output):
+        msg = dedent("""Tesseract failed to report available languages.
+        Output from Tesseract:
+        -----------
+        """)
+        msg += output
+        print(msg, file=sys.stderr)
+
     args_tess = [
         'tesseract',
         '--list-langs'
     ]
     try:
-        langs = check_output(
-                args_tess, universal_newlines=True, stderr=STDOUT)
+        proc = run(
+            args_tess, universal_newlines=True, stdout=PIPE, stderr=STDOUT,
+            check=True
+        )
+        output = proc.stdout
     except CalledProcessError as e:
-        msg = dedent("""Tesseract failed to report available languages.
-        Output from Tesseract:
-        -----------
-        """)
-        msg += e.output
-        print(msg, file=sys.stderr)
+        lang_error(e.output)
         raise MissingDependencyError from e
-    return set(lang.strip() for lang in langs.splitlines()[1:])
+
+    header, *rest = output.splitlines()
+    if not header.startswith('List of available languages'):
+        lang_error(output)
+        raise MissingDependencyError
+    return set(lang.strip() for lang in rest)
 
 
 def tess_base_args(langs, engine_mode):
@@ -124,7 +135,7 @@ def tess_base_args(langs, engine_mode):
 def get_orientation(input_file, engine_mode, timeout: float, log):
     args_tesseract = tess_base_args(['osd'], engine_mode) + [
         psm(), '0',
-        input_file,
+        fspath(input_file),
         'stdout'
     ]