Sort imports with isort

setup.cfg

@@ -14,5 +14,12 @@ testpaths = tests
 filterwarnings =
 	ignore:.*XMLParser.*:DeprecationWarning
 
+[isort]
+multi_line_output=3
+include_trailing_comma=True
+force_grid_wrap=0
+use_parentheses=True
+line_length=88
+
 [metadata]
 license_file = LICENSE

src/ocrmypdf/__main__.py

@@ -16,40 +16,37 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from tempfile import mkdtemp
-from pathlib import Path
-import sys
+import argparse
+import atexit
+import logging
 import os
 import re
-import atexit
+import sys
 import textwrap
-import logging
-import argparse
+from pathlib import Path
+from tempfile import mkdtemp
 
 import PIL
-
-import ruffus.ruffus_exceptions as ruffus_exceptions
 import ruffus.cmdline as cmdline
 import ruffus.proxy_logger as proxy_logger
+import ruffus.ruffus_exceptions as ruffus_exceptions
 
+from . import PROGRAM_NAME, VERSION
+from . import exceptions as ocrmypdf_exceptions
 from ._jobcontext import JobContext, JobContextManager, cleanup_working_files
 from ._pipeline import build_pipeline
-from .pdfa import file_claims_pdfa
-from .helpers import re_symlink, is_file_writable, available_cpu_count
-from .exec import tesseract, qpdf, ghostscript
-from . import PROGRAM_NAME, VERSION
-
+from ._unicodefun import verify_python3_env
 from .exceptions import (
+    BadArgsError,
     ExitCode,
     ExitCodeException,
-    MissingDependencyError,
     InputFileError,
-    BadArgsError,
+    MissingDependencyError,
     OutputFileAccessError,
 )
-from . import exceptions as ocrmypdf_exceptions
-from ._unicodefun import verify_python3_env
-
+from .exec import ghostscript, qpdf, tesseract
+from .helpers import available_cpu_count, is_file_writable, re_symlink
+from .pdfa import file_claims_pdfa
 
 # -------------
 # External dependencies

src/ocrmypdf/_jobcontext.py

@@ -15,10 +15,10 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+import shutil
+import sys
 from contextlib import suppress
 from multiprocessing.managers import SyncManager
-import sys
-import shutil
 
 from .pdfinfo import PdfInfo
 

src/ocrmypdf/_pipeline.py

@@ -15,39 +15,36 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from contextlib import suppress
-from shutil import copyfileobj, copyfile
-from pathlib import Path
-from datetime import datetime, timezone
-import sys
 import os
 import re
+import sys
+from contextlib import suppress
+from datetime import datetime, timezone
+from pathlib import Path
+from shutil import copyfile, copyfileobj
 
 import img2pdf
-import pikepdf
-
 from PIL import Image
-from ruffus import formatter, regex, Pipeline, suffix
+from ruffus import Pipeline, formatter, regex, suffix
 
+import pikepdf
 from pikepdf.models.metadata import encode_pdf_date
 
-from .hocrtransform import HocrTransform
-from .pdfinfo import PdfInfo, Colorspace
-from .pdfa import generate_pdfa_ps
-from .helpers import re_symlink, is_iterable_notstr, page_number, flatten_groups
-from .exec import ghostscript, tesseract
-from .exceptions import (
-    UnsupportedImageFormatError,
-    DpiError,
-    PriorOcrFoundError,
-    InputFileError,
-    EncryptedPdfError,
-)
-from . import leptonica
-from . import PROGRAM_NAME, VERSION
-from .optimize import optimize
+from . import PROGRAM_NAME, VERSION, leptonica
 from ._weave import weave_layers
-
+from .exceptions import (
+    DpiError,
+    EncryptedPdfError,
+    InputFileError,
+    PriorOcrFoundError,
+    UnsupportedImageFormatError,
+)
+from .exec import ghostscript, tesseract
+from .helpers import flatten_groups, is_iterable_notstr, page_number, re_symlink
+from .hocrtransform import HocrTransform
+from .optimize import optimize
+from .pdfa import generate_pdfa_ps
+from .pdfinfo import Colorspace, PdfInfo
 
 VECTOR_PAGE_DPI = 400
 

src/ocrmypdf/_unicodefun.py

@@ -33,9 +33,9 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 
+import codecs
 import os
 import sys
-import codecs
 
 
 def verify_python3_env():  # pragma: no cover

src/ocrmypdf/_weave.py

@@ -15,13 +15,13 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from pathlib import Path
 from itertools import groupby
+from pathlib import Path
 
 import pikepdf
 
-from .helpers import flatten_groups, page_number
 from .exec import tesseract
+from .helpers import flatten_groups, page_number
 
 
 def _update_page_resources(*, page, font, font_key, procset):

src/ocrmypdf/exec/ghostscript.py

@@ -15,15 +15,17 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from tempfile import NamedTemporaryFile
-from subprocess import run, PIPE, STDOUT
-from shutil import copy
-from functools import lru_cache
 import re
+from functools import lru_cache
+from os import fspath
+from shutil import copy
+from subprocess import PIPE, STDOUT, run
+from tempfile import NamedTemporaryFile
+
 from PIL import Image
+
 from . import get_version
 from ..exceptions import SubprocessOutputError
-from os import fspath
 
 
 @lru_cache(maxsize=1)

src/ocrmypdf/exec/jbig2enc.py

@@ -15,8 +15,8 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from subprocess import run, PIPE
 from functools import lru_cache
+from subprocess import PIPE, run
 
 from . import get_version
 from ..exceptions import MissingDependencyError

src/ocrmypdf/exec/pngquant.py

@@ -15,8 +15,8 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from subprocess import run
 from functools import lru_cache
+from subprocess import run
 
 from . import get_version
 from ..exceptions import MissingDependencyError

src/ocrmypdf/exec/qpdf.py

@@ -15,11 +15,11 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from subprocess import CalledProcessError, STDOUT, PIPE, run
 from functools import lru_cache
+from os import fspath
+from subprocess import PIPE, STDOUT, CalledProcessError, run
 
 from . import get_version
-from os import fspath
 
 
 @lru_cache(maxsize=1)

src/ocrmypdf/exec/tesseract.py

@@ -15,26 +15,26 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-import sys
 import os
 import shutil
-from functools import lru_cache
+import sys
 from collections import namedtuple
-from textwrap import dedent
+from contextlib import suppress
+from functools import lru_cache
+from os import fspath
 from subprocess import (
+    PIPE,
+    STDOUT,
     CalledProcessError,
     TimeoutExpired,
     check_output,
-    STDOUT,
     run,
-    PIPE,
 )
-from contextlib import suppress
-from os import fspath
+from textwrap import dedent
 
+from . import get_version
 from ..exceptions import MissingDependencyError, TesseractConfigError
 from ..helpers import page_number
-from . import get_version
 
 OrientationConfidence = namedtuple('OrientationConfidence', ('angle', 'confidence'))
 

src/ocrmypdf/exec/unpaper.py

@@ -18,14 +18,14 @@
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
 
-from subprocess import CalledProcessError, STDOUT, check_output
-from tempfile import NamedTemporaryFile
-import sys
 import os
+import sys
 from functools import lru_cache
-from ..exceptions import MissingDependencyError
-from . import get_version
+from subprocess import STDOUT, CalledProcessError, check_output
+from tempfile import NamedTemporaryFile
 
+from . import get_version
+from ..exceptions import MissingDependencyError
 
 try:
     from PIL import Image

src/ocrmypdf/helpers.py

@@ -15,14 +15,14 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from functools import partial, wraps
+import multiprocessing
+import os
+import sys
+import warnings
 from collections.abc import Iterable
 from contextlib import suppress
+from functools import partial, wraps
 from pathlib import Path
-import sys
-import os
-import multiprocessing
-import warnings
 
 
 def re_symlink(input_file, soft_link_name, log=None):

src/ocrmypdf/hocrtransform.py

@@ -28,14 +28,14 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
-from reportlab.pdfgen.canvas import Canvas
-from reportlab.lib.units import inch
-from xml.etree import ElementTree
-from collections import namedtuple
-from math import atan, sin, cos
-import re
 import argparse
+import re
+from collections import namedtuple
+from math import atan, cos, sin
+from xml.etree import ElementTree
 
+from reportlab.lib.units import inch
+from reportlab.pdfgen.canvas import Canvas
 
 Rect = namedtuple('Rect', ['x1', 'y1', 'x2', 'y2'])
 

src/ocrmypdf/leptonica.py

@@ -20,20 +20,20 @@
 #
 # Python FFI wrapper for Leptonica library
 
-from collections.abc import Sequence
-from contextlib import suppress
-from ctypes.util import find_library
-from functools import lru_cache
-from io import BytesIO
-from tempfile import TemporaryFile
 import argparse
 import logging
 import os
 import sys
 import warnings
+from collections.abc import Sequence
+from contextlib import suppress
+from ctypes.util import find_library
+from functools import lru_cache
+from io import BytesIO
+from os import fspath
+from tempfile import TemporaryFile
 
 from .lib._leptonica import ffi
-from os import fspath
 
 # pylint: disable=protected-access
 

src/ocrmypdf/optimize.py

@@ -15,21 +15,21 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from pathlib import Path
 import concurrent.futures
-from collections import defaultdict
 import logging
 import sys
+from collections import defaultdict
 from os import fspath
+from pathlib import Path
 
 from PIL import Image
 
 import pikepdf
 
-from ._jobcontext import JobContext
 from . import leptonica
+from ._jobcontext import JobContext
+from .exec import jbig2enc, pngquant
 from .helpers import re_symlink
-from .exec import pngquant, jbig2enc
 
 DEFAULT_JPEG_QUALITY = 75
 DEFAULT_PNG_QUALITY = 70

src/ocrmypdf/pdfa.py

@@ -31,22 +31,19 @@ Ghostscript's handling of pdfmark.
 
 """
 
+import os
 from binascii import hexlify
 from pathlib import Path
 from string import Template
+
 import pkg_resources
-import os
 
 import pikepdf
-
-from pikepdf.models.metadata import (
-    encode_pdf_date as _encode_date,
-    decode_pdf_date as _decode_date,
-)
+from pikepdf.models.metadata import decode_pdf_date as _decode_date
+from pikepdf.models.metadata import encode_pdf_date as _encode_date
 
 from .helpers import deprecated
 
-
 ICC_PROFILE_RELPATH = 'data/sRGB.icc'
 
 SRGB_ICC_PROFILE = pkg_resources.resource_filename('ocrmypdf', ICC_PROFILE_RELPATH)

src/ocrmypdf/pdfinfo/layout.py

@@ -38,9 +38,9 @@ from pdfminer.pdfdocument import PDFTextExtractionNotAllowed
 from pdfminer.pdffont import (
     PDFCIDFont,
     PDFFont,
+    PDFSimpleFont,
     PDFType3Font,
     PDFUnicodeNotDefined,
-    PDFSimpleFont,
 )
 from pdfminer.pdfpage import PDFPage
 from pdfminer.utils import bbox2str, fsplit, matrix2str

tests/conftest.py

@@ -15,14 +15,15 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-import sys
 import os
 import platform
+import sys
 from pathlib import Path
-from subprocess import Popen, PIPE
+from subprocess import PIPE, Popen
+
+import pytest
 
 pytest_plugins = ['helpers_namespace']
-import pytest
 
 try:
     from pytest_cov.embed import cleanup_on_sigterm

tests/spoof/gs_feature_elision.py

@@ -21,10 +21,11 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 
-import sys
 import os
+import sys
 from subprocess import check_call
 
+
 """Replicate one type of Ghostscript feature elision warning during
 PDF/A creation."""
 

tests/spoof/gs_pdfa_failure.py

@@ -20,8 +20,9 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
-import sys
 import os
+import sys
+
 
 """Replicate Ghostscript PDF/A conversion failure by suppressing some
 arguments"""

tests/spoof/gs_raster_failure.py

@@ -21,8 +21,8 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 
-import sys
 import os
+import sys
 
 """Replicate Ghostscript raster failure while allowing rendering"""
 

tests/spoof/gs_render_failure.py

@@ -22,8 +22,8 @@
 
 """Replicate Ghostscript render failure while allowing rasterizing"""
 
-import sys
 import os
+import sys
 
 
 def real_ghostscript(argv):

tests/spoof/tesseract_badutf8.py

@@ -21,10 +21,10 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 import sys
+
 import img2pdf
 from PIL import Image
 
-
 """Tesseract bad utf8 spoof
 
 In 'hocr' mode or 'pdf' mode, return error code 1 and some non-Unicode

tests/spoof/tesseract_big_image_error.py

@@ -23,7 +23,6 @@
 
 import sys
 
-
 VERSION_STRING = '''tesseract 4.0.0
  leptonica-1.77.0
   libjpeg 9c : libpng 1.6.35 : libtiff 4.0.10 : zlib 1.2.11 : libopenjp2 2.3.0

tests/spoof/tesseract_cache.py

@@ -49,15 +49,15 @@ Assumes Tesseract 4.0.0-alpha or higher.
 
 """
 
-from pathlib import Path
-import sys
-import os
-import shutil
-import subprocess
 import argparse
 import json
+import os
 import platform
 import re
+import shutil
+import subprocess
+import sys
+from pathlib import Path
 
 if '_OCRMYPDF_SAVE_PATH' in os.environ:
     os.environ['PATH'] = os.environ['_OCRMYPDF_SAVE_PATH']

tests/spoof/tesseract_crash.py

@@ -20,10 +20,9 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
-import sys
 import os
 import signal
-
+import sys
 
 VERSION_STRING = '''tesseract 4.0.0
  leptonica-1.77.0

tests/spoof/tesseract_noop.py

@@ -32,11 +32,11 @@ In orientation check mode, report the orientation is upright.
 """
 
 import sys
+
 import img2pdf
 import PyPDF2 as pypdf
 from PIL import Image
 
-
 VERSION_STRING = '''tesseract 4.0.0
  leptonica-1.77.0
   libjpeg 9c : libpng 1.6.35 : libtiff 4.0.10 : zlib 1.2.11 : libopenjp2 2.3.0

tests/test_hocrtransform.py

@@ -15,12 +15,14 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from ocrmypdf import hocrtransform
-from ocrmypdf.exec.tesseract import HOCR_TEMPLATE
-from ocrmypdf.exec import qpdf
-from PIL import Image
 from pathlib import Path
+
 import pytest
+from PIL import Image
+
+from ocrmypdf import hocrtransform
+from ocrmypdf.exec import qpdf
+from ocrmypdf.exec.tesseract import HOCR_TEMPLATE
 
 # pylint: disable=redefined-outer-name
 

tests/test_main.py

@@ -15,23 +15,23 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from subprocess import Popen, PIPE, DEVNULL
-from pathlib import Path
-from math import isclose
+import logging
 import os
 import shutil
 import sys
-import logging
+from math import isclose
+from pathlib import Path
+from subprocess import DEVNULL, PIPE, Popen
 
-from PIL import Image
 import PIL
 import pytest
+from PIL import Image
 
-from ocrmypdf.pdfinfo import PdfInfo, Colorspace, Encoding
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 from ocrmypdf.exec import ghostscript, qpdf, tesseract
-from ocrmypdf.pdfa import file_claims_pdfa
 from ocrmypdf.leptonica import Pix
+from ocrmypdf.pdfa import file_claims_pdfa
+from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 
 # pytest.helpers is dynamic
 # pylint: disable=no-member,redefined-outer-name

tests/test_metadata.py

@@ -16,21 +16,20 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 
-import pytest
-
+import datetime
 from datetime import timezone
+from os import fspath
 from pathlib import Path
 from shutil import copyfile
-from unittest.mock import patch, MagicMock
-import datetime
-from os import fspath
+from unittest.mock import MagicMock, patch
+
+import pytest
 
 import pikepdf
-from pikepdf.models.metadata import decode_pdf_date
-
 from ocrmypdf.exceptions import ExitCode
-from ocrmypdf.pdfa import file_claims_pdfa, generate_pdfa_ps, SRGB_ICC_PROFILE
 from ocrmypdf.exec import ghostscript
+from ocrmypdf.pdfa import SRGB_ICC_PROFILE, file_claims_pdfa, generate_pdfa_ps
+from pikepdf.models.metadata import decode_pdf_date
 
 try:
     import fitz

tests/test_multiprocessing.py

@@ -14,11 +14,12 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from ocrmypdf.pdfinfo import PdfInfo, PageInfo
-from ocrmypdf._jobcontext import JobContext, JobContextManager
 from multiprocessing import Process
 from multiprocessing.managers import BaseProxy
 
+from ocrmypdf._jobcontext import JobContext, JobContextManager
+from ocrmypdf.pdfinfo import PageInfo, PdfInfo
+
 
 def test_jobcontext_proxy(resources):
     # Prove that managers are set up correctly to share state among processes

tests/test_optimize.py

@@ -15,20 +15,17 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from pathlib import Path
+import logging
 from os import fspath
+from pathlib import Path
 
 import pytest
-import logging
-
 from PIL import Image
 
 import pikepdf
-
 from ocrmypdf import optimize as opt
-from ocrmypdf.exec.ghostscript import rasterize_pdf
 from ocrmypdf.exec import jbig2enc, pngquant
-
+from ocrmypdf.exec.ghostscript import rasterize_pdf
 
 check_ocrmypdf = pytest.helpers.check_ocrmypdf
 

tests/test_pdfinfo.py

@@ -15,20 +15,22 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from ocrmypdf import pdfinfo
-from reportlab.pdfgen.canvas import Canvas
-from PIL import Image
-from tempfile import NamedTemporaryFile
-from math import isclose
-from ocrmypdf.pdfinfo import Colorspace, Encoding
-from contextlib import suppress
 import os
-import shutil
-import pytest
-import img2pdf
-import sys
-import pikepdf
 import pickle
+import shutil
+import sys
+from contextlib import suppress
+from math import isclose
+from tempfile import NamedTemporaryFile
+
+import img2pdf
+import pytest
+from PIL import Image
+from reportlab.pdfgen.canvas import Canvas
+
+import pikepdf
+from ocrmypdf import pdfinfo
+from ocrmypdf.pdfinfo import Colorspace, Encoding
 
 
 def test_single_page_text(outdir):

tests/test_rotation.py

@@ -17,18 +17,17 @@
 
 import logging
 from io import BytesIO
-from unittest.mock import Mock
 from os import fspath
+from unittest.mock import Mock
 
-from PIL import Image
-import pytest
 import img2pdf
+import pytest
+from PIL import Image
+
 import pikepdf
-
 from ocrmypdf import leptonica
-from ocrmypdf.pdfinfo import PdfInfo
 from ocrmypdf.exec import ghostscript, tesseract
-
+from ocrmypdf.pdfinfo import PdfInfo
 
 # pytest.helpers is dynamic
 # pylint: disable=no-member

tests/test_tess4.py

@@ -15,10 +15,10 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from os import fspath
-import sys
 import os
+import sys
 from contextlib import contextmanager
+from os import fspath
 from pathlib import Path
 
 import PyPDF2 as pypdf

tests/test_unpaper.py

@@ -16,7 +16,9 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 from pathlib import Path
+
 import pytest
+
 from ocrmypdf.exceptions import ExitCode
 
 # pytest.helpers is dynamic

tests/test_userunit.py

@@ -15,19 +15,20 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
+import logging
 import os
 import shutil
-import pytest
-from ocrmypdf.pdfinfo import PdfInfo, Colorspace, Encoding
-import PyPDF2 as pypdf
-from ocrmypdf.exceptions import ExitCode
-from ocrmypdf import leptonica
-from ocrmypdf.pdfa import file_claims_pdfa
-from ocrmypdf.exec import ghostscript
-import logging
 from math import isclose
+from subprocess import DEVNULL, PIPE, Popen, check_call, check_output
 
+import PyPDF2 as pypdf
+import pytest
+
+from ocrmypdf import leptonica
+from ocrmypdf.exceptions import ExitCode
+from ocrmypdf.exec import ghostscript
+from ocrmypdf.pdfa import file_claims_pdfa
+from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 
 check_ocrmypdf = pytest.helpers.check_ocrmypdf
 run_ocrmypdf = pytest.helpers.run_ocrmypdf