Convert many uses of str paths to Path

src/ocrmypdf/_concurrent.py

@@ -47,7 +47,7 @@ def log_listener(queue):
             logger = logging.getLogger(record.name)
             logger.handle(record)
         except Exception:  # pylint: disable=broad-except
-            import traceback
+            import traceback  # pylint: disable=import-outside-toplevel
 
             print("Logging problem", file=sys.stderr)
             traceback.print_exc(file=sys.stderr)

src/ocrmypdf/_graft.py

@@ -16,7 +16,6 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 import logging
-import os
 from contextlib import suppress
 from pathlib import Path
 
@@ -181,7 +180,7 @@ def _find_font(text, pdf_base):
 class OcrGrafter:
     def __init__(self, context):
         self.context = context
-        self.path_base = Path(context.origin).resolve()
+        self.path_base = context.origin
 
         self.pdf_base = pikepdf.open(self.path_base)
         self.font, self.font_key = None, None
@@ -264,12 +263,14 @@ class OcrGrafter:
         # {interim_count} is the opened file we were updateing
         # {interim_count - 1} can be deleted
         # {interim_count + 1} is the new file will produce and open
-        old_file = self.output_file + f'_working{self.interim_count - 1}.pdf'
+        old_file = self.output_file.with_suffix(f'.working{self.interim_count - 1}.pdf')
         if not self.context.options.keep_temporary_files:
             with suppress(FileNotFoundError):
-                os.unlink(old_file)
+                old_file.unlink()
 
-        next_file = self.output_file + f'_working{self.interim_count + 1}.pdf'
+        next_file = self.output_file.with_suffix(
+            f'.working{self.interim_count + 1}.pdf'
+        )
         self.pdf_base.save(next_file)
         self.pdf_base.close()
 

src/ocrmypdf/_jobcontext.py

@@ -19,6 +19,7 @@ import os
 import shutil
 import sys
 from functools import partial
+from pathlib import Path
 
 from ocrmypdf._plugin_manager import get_plugin_manager
 
@@ -26,10 +27,12 @@ from ocrmypdf._plugin_manager import get_plugin_manager
 class PdfContext:
     """Holds our context for a particular run of the pipeline"""
 
-    def __init__(self, options, work_folder, origin, pdfinfo, plugin_manager):
+    def __init__(
+        self, options, work_folder: Path, origin: Path, pdfinfo, plugin_manager
+    ):
         self.options = options
-        self.work_folder = work_folder
-        self.origin = origin
+        self.work_folder = Path(work_folder)
+        self.origin = Path(origin)
         self.pdfinfo = pdfinfo
         self.plugin_manager = plugin_manager
         if options:
@@ -39,8 +42,8 @@ class PdfContext:
         if self.name == '-':
             self.name = 'stdin'
 
-    def get_path(self, name):
-        return os.path.join(self.work_folder, name)
+    def get_path(self, name: str) -> Path:
+        return self.work_folder / name
 
     def get_page_contexts(self):
         npages = len(self.pdfinfo)
@@ -54,7 +57,7 @@ class PageContext:
     Must be pickable, so only store intrinsic/simple data elements
     """
 
-    def __init__(self, pdf_context, pageno):
+    def __init__(self, pdf_context: PdfContext, pageno):
         self.work_folder = pdf_context.work_folder
         self.origin = pdf_context.origin
         self.options = pdf_context.options
@@ -63,8 +66,8 @@ class PageContext:
         self.pageinfo = pdf_context.pdfinfo[pageno]
         self.plugin_manager = pdf_context.plugin_manager
 
-    def get_path(self, name):
-        return os.path.join(self.work_folder, "%06d_%s" % (self.pageno + 1, name))
+    def get_path(self, name: str) -> Path:
+        return self.work_folder / ("%06d_%s" % (self.pageno + 1, name))
 
     def __getstate__(self):
         state = self.__dict__.copy()

src/ocrmypdf/_pipeline.py

@@ -55,7 +55,7 @@ def triage_image_file(input_file, output_file, options):
         im = Image.open(input_file)
     except EnvironmentError as e:
         # Recover the original filename
-        log.error(str(e).replace(input_file, options.input_file))
+        log.error(str(e).replace(str(input_file), str(options.input_file)))
         raise UnsupportedImageFormatError() from e
 
     with im:
@@ -102,7 +102,10 @@ def triage_image_file(input_file, output_file, options):
             )
         with open(output_file, 'wb') as outf:
             img2pdf.convert(
-                input_file, layout_fun=layout_fun, with_pdfrw=False, outputstream=outf
+                os.fspath(input_file),
+                layout_fun=layout_fun,
+                with_pdfrw=False,
+                outputstream=outf,
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
@@ -139,7 +142,7 @@ def triage(original_filename, input_file, output_file, options):
             return output_file
     except EnvironmentError as e:
         log.debug(f"Temporary file was at: {input_file}")
-        msg = str(e).replace(input_file, original_filename)
+        msg = str(e).replace(str(input_file), original_filename)
         raise InputFileError(msg) from e
 
     triage_image_file(input_file, output_file, options)

src/ocrmypdf/_sync.py

@@ -304,7 +304,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
     if not plugin_manager:
         plugin_manager = get_plugin_manager([])
 
-    work_folder = mkdtemp(prefix="com.github.ocrmypdf.")
+    work_folder = Path(mkdtemp(prefix="com.github.ocrmypdf."))
     debug_log_handler = None
     if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
         'PYTEST_CURRENT_TEST', ''
@@ -317,10 +317,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
 
         # Triage image or pdf
         origin_pdf = triage(
-            original_filename,
-            start_input_file,
-            os.path.join(work_folder, 'origin.pdf'),
-            options,
+            original_filename, start_input_file, work_folder / 'origin.pdf', options
         )
 
         plugin_manager.hook.prepare(options=options)

src/ocrmypdf/_validation.py

@@ -376,17 +376,17 @@ def log_page_orientations(pdfinfo):
         log.info('Page orientations detected: %s', ' '.join(orientations))
 
 
-def create_input_file(options, work_folder):
+def create_input_file(options, work_folder: Path) -> (Path, str):
     if options.input_file == '-':
         # stdin
         log.info('reading file from standard input')
-        target = os.path.join(work_folder, 'stdin')
+        target = work_folder / 'stdin'
         with open(target, 'wb') as stream_buffer:
             copyfileobj(sys.stdin.buffer, stream_buffer)
         return target, "<stdin>"
     else:
         try:
-            target = os.path.join(work_folder, 'origin')
+            target = work_folder / 'origin'
             safe_symlink(options.input_file, target)
             return target, os.fspath(options.input_file)
         except FileNotFoundError:

src/ocrmypdf/exec/unpaper.py

@@ -24,6 +24,7 @@ import logging
 import os
 import shlex
 from functools import lru_cache
+from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError
 from tempfile import TemporaryDirectory
 
@@ -67,8 +68,8 @@ def run(input_file, output_file, dpi, mode_args):
                 "Failed to convert image to a supported format."
             ) from e
 
-        input_pnm = os.path.join(tmpdir, f'input{suffix}')
-        output_pnm = os.path.join(tmpdir, f'output{suffix}')
+        input_pnm = Path(tmpdir) / f'input{suffix}'
+        output_pnm = Path(tmpdir) / f'output{suffix}'
         im.save(input_pnm, format='PPM')
 
         # To prevent any shenanigans from accepting arbitrary parameters in
@@ -78,7 +79,7 @@ def run(input_file, output_file, dpi, mode_args):
         # 3) append absolute paths for the input and output file
         # This should ensure that a user cannot clobber some other file with
         # their unpaper arguments (whether intentionally or otherwise)
-        args_unpaper.extend([input_pnm, output_pnm])
+        args_unpaper.extend([os.fspath(input_pnm), os.fspath(output_pnm)])
         try:
             proc = external_run(
                 args_unpaper,

src/ocrmypdf/hocrtransform.py

@@ -29,9 +29,11 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 import argparse
+import os
 import re
 from collections import namedtuple
 from math import atan, cos, sin
+from pathlib import Path
 from xml.etree import ElementTree
 
 from reportlab.lib.units import inch
@@ -155,8 +157,8 @@ class HocrTransform:
 
     def to_pdf(
         self,
-        out_filename: str,
-        image_filename: str = None,
+        out_filename: Path,
+        image_filename: Path = None,
         show_bounding_boxes: bool = False,
         fontname: str = "Helvetica",
         invisible_text: bool = False,
@@ -173,7 +175,9 @@ class HocrTransform:
         # create the PDF file
         # page size in points (1/72 in.)
         pdf = Canvas(
-            out_filename, pagesize=(self.width, self.height), pageCompression=1
+            os.fspath(out_filename),
+            pagesize=(self.width, self.height),
+            pageCompression=1,
         )
 
         # draw bounding box for each paragraph
@@ -226,7 +230,9 @@ class HocrTransform:
             )
         # put the image on the page, scaled to fill the page
         if image_filename is not None:
-            pdf.drawImage(image_filename, 0, 0, width=self.width, height=self.height)
+            pdf.drawImage(
+                os.fspath(image_filename), 0, 0, width=self.width, height=self.height
+            )
 
         # finish up the page and save it
         pdf.showPage()

src/ocrmypdf/pdfinfo/info.py

@@ -820,9 +820,8 @@ class PdfInfo:
 
 
 def main():
-    # pylint: disable=import-outside-toplevel
-    import argparse
-    from pprint import pprint
+    import argparse  # pylint: disable=import-outside-toplevel
+    from pprint import pprint  # pylint: disable=import-outside-toplevel
 
     parser = argparse.ArgumentParser()
     parser.add_argument('infile')

tests/conftest.py

@@ -52,7 +52,7 @@ def is_macos():
 def running_in_docker():
     # Docker creates a file named /.dockerenv (newer versions) or
     # /.dockerinit (older) -- this is undocumented, not an offical test
-    return os.path.exists('/.dockerenv') or os.path.exists('/.dockerinit')
+    return Path('/.dockerenv').exists() or Path('/.dockerinit').exists()
 
 
 @pytest.helpers.register
@@ -69,9 +69,9 @@ def have_unpaper():
     return True
 
 
-TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
-SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
-PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
+TESTS_ROOT = Path(__file__).parent.resolve()
+SPOOF_PATH = TESTS_ROOT / 'spoof'
+PROJECT_ROOT = TESTS_ROOT
 OCRMYPDF = [sys.executable, '-m', 'ocrmypdf']
 
 
@@ -146,7 +146,7 @@ def spoof(tmp_path_factory, **kwargs):
     tmpdir.mkdir(parents=True)
 
     for replace_program, with_spoof in kwargs.items():
-        spoofer = Path(SPOOF_PATH) / with_spoof
+        spoofer = SPOOF_PATH / with_spoof
         if os.name != 'nt':
             spoofer.chmod(0o755)
             (tmpdir / replace_program).symlink_to(spoofer)
@@ -224,8 +224,8 @@ def check_ocrmypdf(input_file, output_file, *args, env=None):
     result = api.run_pipeline(options, plugin_manager=None, api=True)
 
     assert result == 0
-    assert os.path.exists(str(output_file)), "Output file not created"
-    assert os.stat(str(output_file)).st_size > 100, "PDF too small or empty"
+    assert output_file.exists(), "Output file not created"
+    assert output_file.stat().st_size > 100, "PDF too small or empty"
 
     return output_file
 

tests/test_main.py

@@ -210,7 +210,7 @@ def test_force_ocr_on_pdf_with_no_images(spoof_tesseract_crash, resources, no_ou
         resources / 'blank.pdf', no_outpdf, '--force-ocr', env=spoof_tesseract_crash
     )
     assert p.returncode == ExitCode.child_process_error
-    assert not os.path.exists(no_outpdf)
+    assert not no_outpdf.exists()
 
 
 @pytest.mark.skipif(
@@ -321,7 +321,7 @@ def test_tesseract_crash(renderer, spoof_tesseract_crash, resources, no_outpdf):
         env=spoof_tesseract_crash,
     )
     assert p.returncode == ExitCode.child_process_error
-    assert not os.path.exists(no_outpdf)
+    assert not no_outpdf.exists()
     assert "SubprocessOutputError" in err
 
 
@@ -330,7 +330,7 @@ def test_tesseract_crash_autorotate(spoof_tesseract_crash, resources, no_outpdf)
         resources / 'ccitt.pdf', no_outpdf, '-r', env=spoof_tesseract_crash
     )
     assert p.returncode == ExitCode.child_process_error
-    assert not os.path.exists(no_outpdf)
+    assert not no_outpdf.exists()
     assert "uncaught exception" in err
     print(out)
     print(err)