pre-commit: pyupgrade modernizing

.pre-commit-config.yaml

@@ -25,3 +25,8 @@ repos:
     rev: v1.17.0
     hooks:
       - id: setup-cfg-fmt
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.24.0
+    hooks:
+      - id: pyupgrade
+        args: ["--py36-plus"]

misc/webservice.py

@@ -37,7 +37,7 @@ app.secret_key = "secret"
 app.config['MAX_CONTENT_LENGTH'] = 50_000_000
 app.config.from_envvar("OCRMYPDF_WEBSERVICE_SETTINGS", silent=True)
 
-ALLOWED_EXTENSIONS = set(["pdf"])
+ALLOWED_EXTENSIONS = {"pdf"}
 
 
 def allowed_file(filename):

src/ocrmypdf/_exec/tesseract.py

@@ -117,7 +117,7 @@ def get_languages():
         if line.startswith('Error'):
             raise MissingDependencyError(lang_error(output))
     _header, *rest = output.splitlines()
-    return set(lang.strip() for lang in rest)
+    return {lang.strip() for lang in rest}
 
 
 def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:

src/ocrmypdf/_exec/unpaper.py

@@ -45,7 +45,7 @@ def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
                     im = im.convert(mode='1')
                 else:
                     im = im.convert(mode='RGB')
-            except IOError as e:
+            except OSError as e:
                 raise MissingDependencyError(
                     "Could not convert image with type " + im.mode
                 ) from e

src/ocrmypdf/_pipeline.py

@@ -48,7 +48,7 @@ def triage_image_file(input_file, output_file, options):
     log.info("Input file is not a PDF, checking if it is an image...")
     try:
         im = Image.open(input_file)
-    except EnvironmentError as e:
+    except OSError as e:
         # Recover the original filename
         log.error(str(e).replace(str(input_file), str(options.input_file)))
         raise UnsupportedImageFormatError() from e
@@ -135,7 +135,7 @@ def triage(original_filename, input_file, output_file, options):
             # Origin file is a pdf create a symlink with pdf extension
             safe_symlink(input_file, output_file)
             return output_file
-    except EnvironmentError as e:
+    except OSError as e:
         log.debug(f"Temporary file was at: {input_file}")
         msg = str(e).replace(str(input_file), original_filename)
         raise InputFileError(msg) from e
@@ -856,7 +856,7 @@ def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
             if frm != 1:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
-                with open(txt_file, 'r', encoding="utf-8") as in_:
+                with open(txt_file, encoding="utf-8") as in_:
                     txt = in_.read()
                     # Some OCR engines (e.g. Tesseract v4 alpha) add form feeds
                     # between pages, and some do not. For consistency, we ignore

src/ocrmypdf/_sync.py

@@ -421,7 +421,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
             try:
                 debug_log_handler.close()
                 log.removeHandler(debug_log_handler)
-            except EnvironmentError as e:
+            except OSError as e:
                 print(e, file=sys.stderr)
         cleanup_working_files(work_folder, options)
 

src/ocrmypdf/_validation.py

@@ -182,10 +182,10 @@ def _pages_from_ranges(ranges: str) -> Set[int]:
 
 def check_options_ocr_behavior(options):
     exclusive_options = sum(
-        [
+        
             (1 if opt else 0)
             for opt in (options.force_ocr, options.skip_text, options.redo_ocr)
-        ]
+        
     )
     if exclusive_options >= 2:
         raise BadArgsError("Choose only one of --force-ocr, --skip-text, --redo-ocr.")
@@ -302,7 +302,7 @@ def check_closed_streams(options):  # pragma: no cover
         if options.input_file == '-':
             log.error("Trying to read from stdin but stdin seems closed")
             return False
-        sys.stdin = open(os.devnull, 'r')
+        sys.stdin = open(os.devnull)
 
     if sys.stdout is None:
         if options.output_file == '-':

src/ocrmypdf/cli.py

@@ -22,7 +22,7 @@ def numeric(basetype: Type[T], min_: Optional[T] = None, max_: Optional[T] = Non
     def _numeric(string):
         value = basetype(string)
         if (min_ is not None and value < min_) or (max_ is not None and value > max_):
-            msg = "%r not in valid range %r" % (string, (min_, max_))
+            msg = f"{string!r} not in valid range {(min_, max_)!r}"
             raise argparse.ArgumentTypeError(msg)
         return value
 

src/ocrmypdf/helpers.py

@@ -189,7 +189,7 @@ def is_file_writable(test_file: os.PathLike) -> bool:
                 with suppress(OSError):
                     p.unlink()
             return True
-    except (EnvironmentError, RuntimeError) as e:
+    except (OSError, RuntimeError) as e:
         log.debug(e)
         log.error(str(e))
         return False
@@ -273,7 +273,7 @@ def deprecated(func):
     def new_func(*args, **kwargs):
         warnings.simplefilter('always', DeprecationWarning)  # turn off filter
         warnings.warn(
-            "Call to deprecated function {}.".format(func.__name__),
+            f"Call to deprecated function {func.__name__}.",
             category=DeprecationWarning,
             stacklevel=2,
         )

src/ocrmypdf/leptonica.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # © 2013-16: jbarlow83 from Github (https://github.com/jbarlow83)
 #
@@ -272,7 +271,7 @@ class LeptonicaObject:
         # Leptonica API uses double-pointers for its destroy APIs to prevent
         # dangling pointers. This means we need to put our single pointer,
         # cdata, in a temporary CDATA**.
-        pp = ffi.new('{} **'.format(cls.LEPTONICA_TYPENAME), cdata)
+        pp = ffi.new(f'{cls.LEPTONICA_TYPENAME} **', cdata)
         cls.cdata_destroy(pp)
 
 
@@ -844,7 +843,7 @@ class Box(LeptonicaObject):
 
     def __repr__(self):
         if self._cdata:
-            return '<leptonica.Box x={0} y={1} w={2} h={3}>'.format(
+            return '<leptonica.Box x={} y={} w={} h={}>'.format(
                 self.x, self.y, self.w, self.h
             )
         return '<leptonica.Box NULL>'
@@ -916,7 +915,7 @@ class Sel(LeptonicaObject):
         lines = [line.strip() for line in selstr.split('\n') if line.strip()]
         h = len(lines)
         w = len(lines[0])
-        lengths = set(len(line) for line in lines)
+        lengths = {len(line) for line in lines}
         if len(lengths) != 1:
             raise ValueError("All lines in selstr must be same length")
 

src/ocrmypdf/pdfinfo/layout.py

@@ -135,7 +135,7 @@ class LTStateAwareChar(LTChar):
         return self._text
 
     def __repr__(self):
-        return '<%s %s matrix=%s rendermode=%r font=%r adv=%s text=%r>' % (
+        return '<{} {} matrix={} rendermode={!r} font={!r} adv={} text={!r}>'.format(
             self.__class__.__name__,
             bbox2str(self.bbox),
             matrix2str(self.matrix),

tests/test_main.py

@@ -701,7 +701,7 @@ def test_sidecar_pagecount(resources, outpdf):
     pdfinfo = PdfInfo(resources / '3small.pdf')
     num_pages = len(pdfinfo)
 
-    with open(sidecar, 'r', encoding='utf-8') as f:
+    with open(sidecar, encoding='utf-8') as f:
         ocr_text = f.read()
 
     # There should a formfeed between each pair of pages, so the count of
@@ -722,7 +722,7 @@ def test_sidecar_nonempty(resources, outpdf):
         'tests/plugins/tesseract_cache.py',
     )
 
-    with open(sidecar, 'r', encoding='utf-8') as f:
+    with open(sidecar, encoding='utf-8') as f:
         ocr_text = f.read()
     assert 'the' in ocr_text