Make some interfaces accepting of both str-paths and Path objects

ocrmypdf/exec/ghostscript.py

@@ -10,6 +10,7 @@ import sys
 from . import get_program
 from ..exceptions import SubprocessOutputError
 from PIL import Image
+from ..helpers import fspath
 
 
 @lru_cache(maxsize=1)
@@ -43,8 +44,8 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
     (xres, yres) even if those numbers are noninteger. The image's DPI will
      be overridden with the values in page_dpi.
     
-    :param input_file: 
-    :param output_file: 
+    :param input_file: pathlike
+    :param output_file: pathlike
     :param xres: resolution at which to rasterize page
     :param yres: 
     :param raster_device: 
@@ -69,7 +70,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
             '-dLastPage=%i' % pageno,
             '-o', tmp.name,
             '-r{0}x{1}'.format(str(int_res[0]), str(int_res[1])),
-            input_file
+            fspath(input_file)
         ]
 
         p = run(args_gs, stdout=PIPE, stderr=STDOUT,
@@ -95,9 +96,10 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
                 log.debug(
                     "Ghostscript: resize output image {} -> {}".format(
                         im.size, expected_size))
-                im.resize(expected_size).save(output_file, dpi=page_dpi)
+                im.resize(expected_size).save(
+                    fspath(output_file), dpi=page_dpi)
             else:
-                copy(tmp.name, output_file)
+                copy(tmp.name, fspath(output_file))
 
 
 def generate_pdfa(pdf_pages, output_file, compression, log,

ocrmypdf/helpers.py

@@ -79,10 +79,42 @@ def is_file_writable(test_file):
         return True
 
 
-@contextmanager
-def universal_open(p, *args, **kwargs):
-    "Work around Python 3.5's inability to open(pathlib.Path())"
-    try:
-        yield p.open(*args, **kwargs)
-    except AttributeError:
-        yield open(p, *args, **kwargs)
+if sys.version_info <= (3, 5):
+    def universal_open(p, *args, **kwargs):
+        "Work around Python 3.5's inability to open(pathlib.Path())"
+        try:
+            return p.open(*args, **kwargs)
+        except AttributeError:
+            return open(p, *args, **kwargs)
+
+
+    def fspath(path):
+        '''https://www.python.org/dev/peps/pep-0519/#os'''
+        if isinstance(path, (str, bytes)):
+            return path
+
+        # Work from the object's type to match method resolution of other magic
+        # methods.
+        path_type = type(path)
+        try:
+            path = path_type.__fspath__(path)
+        except AttributeError:
+            # Added for Python 3.5 support.
+            if isinstance(path, pathlib.Path):
+                return str(path)
+            elif hasattr(path_type, '__fspath__'):
+                raise
+        else:
+            if isinstance(path, (str, bytes)):
+                return path
+            else:
+                raise TypeError("expected __fspath__() to return str or bytes, "
+                                "not " + type(path).__name__)
+
+        raise TypeError(
+            "expected str, bytes, pathlib.Path or os.PathLike object, not "
+            + path_type.__name__)
+
+else:
+    universal_open = open
+    fspath = os.fspath

ocrmypdf/leptonica.py

@@ -14,6 +14,7 @@ from ctypes.util import find_library
 from .lib._leptonica import ffi
 from functools import lru_cache
 from enum import Enum
+from .helpers import fspath
 
 lept = ffi.dlopen(find_library('lept'))
 
@@ -208,26 +209,27 @@ class Pix:
             return 'P'
 
     @classmethod
-    def read(cls, filename):
+    def read(cls, path):
         """Load an image file into a PIX object.
 
         Leptonica can load TIFF, PNM (PBM, PGM, PPM), PNG, and JPEG.  If
         loading fails then the object will wrap a C null pointer.
         """
+        filename = fspath(path)
         with LeptonicaErrorTrap():
-            return cls(lept.pixRead(
-                filename.encode(sys.getfilesystemencoding())))
+            return cls(lept.pixRead(os.fsencode(filename)))
 
     def write_implied_format(
-            self, filename, jpeg_quality=0, jpeg_progressive=0):
+            self, path, jpeg_quality=0, jpeg_progressive=0):
         """Write pix to the filename, with the extension indicating format.
 
         jpeg_quality -- quality (iff JPEG; 1 - 100, 0 for default)
         jpeg_progressive -- (iff JPEG; 0 for baseline seq., 1 for progressive)
         """
+        filename = fspath(path)
         with LeptonicaErrorTrap():
             lept.pixWriteImpliedFormat(
-                filename.encode(sys.getfilesystemencoding()),
+                os.fsencode(filename),
                 self._pix, jpeg_quality, jpeg_progressive)
 
     def topil(self):

tests/test_main.py

@@ -77,8 +77,8 @@ def test_deskew(spoof_tesseract_noop, resources, outdir):
     deskewed_png = outdir / 'deskewed.png'
 
     ghostscript.rasterize_pdf(
-        str(deskewed_pdf),
-        str(deskewed_png),
+        deskewed_pdf,
+        deskewed_png,
         xres=150,
         yres=150,
         raster_device='pngmono',
@@ -116,8 +116,8 @@ def test_remove_background(spoof_tesseract_noop, resources, outdir):
     output_png = outdir / 'remove_bg.png'
 
     ghostscript.rasterize_pdf(
-        str(output_pdf),
-        str(output_png),
+        output_pdf,
+        output_png,
         xres=100,
         yres=100,
         raster_device='png16m',
@@ -270,9 +270,7 @@ def check_monochrome_correlation(
             print(png)
             return
         ghostscript.rasterize_pdf(
-            str(pdf),
-            str(png),
-            xres=100, yres=100,
+            pdf, png, xres=100, yres=100,
             raster_device='pngmono', log=gslog, pageno=pageno)
 
     rasterize(reference_pdf, reference_pageno, reference_png)