Cleanup unused imports

.gitignore

@@ -8,6 +8,7 @@ tasks.py
 .ruffus_history.sqlite
 .idea/
 .pytest_cache/
+.pylintrc
 
 # Package building
 *.egg-info/

src/ocrmypdf/__main__.py

@@ -22,7 +22,6 @@ from pathlib import Path
 import sys
 import os
 import re
-import multiprocessing
 import atexit
 import textwrap
 import logging

src/ocrmypdf/exec/ghostscript.py

@@ -16,14 +16,13 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 from tempfile import NamedTemporaryFile
-from subprocess import run, PIPE, STDOUT, CalledProcessError
+from subprocess import run, PIPE, STDOUT
 from shutil import copy
 from functools import lru_cache
 import re
-import sys
 from PIL import Image
 from . import get_version
-from ..exceptions import SubprocessOutputError, MissingDependencyError
+from ..exceptions import SubprocessOutputError
 from ..helpers import fspath
 
 

src/ocrmypdf/exec/qpdf.py

@@ -17,15 +17,10 @@
 
 from subprocess import CalledProcessError, STDOUT, PIPE, run
 from functools import lru_cache
-import sys
-import os
-import re
-import resource
 
 from ..exceptions import InputFileError, SubprocessOutputError, \
-    MissingDependencyError, EncryptedPdfError
+    EncryptedPdfError
 from . import  get_version
-from ..helpers import re_symlink
 
 
 @lru_cache(maxsize=1)

src/ocrmypdf/exec/tesseract.py

@@ -17,13 +17,11 @@
 
 import sys
 import os
-import re
 import shutil
 from functools import lru_cache
 from collections import namedtuple
 from textwrap import dedent
-from subprocess import PIPE, CalledProcessError, \
-    TimeoutExpired, check_output, STDOUT
+from subprocess import CalledProcessError, TimeoutExpired, check_output, STDOUT
 from contextlib import suppress
 
 from ..exceptions import MissingDependencyError, TesseractConfigError

src/ocrmypdf/helpers.py

@@ -17,7 +17,7 @@
 
 from functools import partial
 from collections.abc import Iterable
-from contextlib import suppress, contextmanager
+from contextlib import suppress
 from pathlib import Path
 import sys
 import os

src/ocrmypdf/hocrtransform.py

@@ -16,10 +16,10 @@
 # distribute, sublicense, and/or sell copies of the Software, and to
 # permit persons to whom the Software is furnished to do so, subject to
 # the following conditions:
-# 
+#
 # The above copyright notice and this permission notice shall be included
 # in all copies or substantial portions of the Software.
-# 
+#
 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
 # OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
@@ -31,7 +31,6 @@
 from reportlab.pdfgen.canvas import Canvas
 from reportlab.lib.units import inch
 from xml.etree import ElementTree
-from PIL import Image
 from collections import namedtuple
 from math import atan, sin, cos
 import re

src/ocrmypdf/leptonica.py

@@ -27,9 +27,9 @@ import logging
 import warnings
 from tempfile import TemporaryFile
 from ctypes.util import find_library
-from .lib._leptonica import ffi
 from functools import lru_cache
-from enum import Enum
+
+from .lib._leptonica import ffi
 from .helpers import fspath
 
 lept = ffi.dlopen(find_library('lept'))
@@ -635,4 +635,4 @@ if __name__ == '__main__':
     parser_deskew.set_defaults(func=deskew)
 
     args = parser.parse_args()
-    args.func(args)
+    args.func(args)

src/ocrmypdf/optimize.py

@@ -16,14 +16,11 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 from pathlib import Path
-from subprocess import CalledProcessError
 import concurrent.futures
 from collections import defaultdict, namedtuple
-import struct
 import logging
 import sys
 
-from io import BytesIO
 from PIL import Image
 
 import pikepdf

src/ocrmypdf/pdfinfo.py

@@ -16,17 +16,12 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from subprocess import Popen, PIPE
 from decimal import Decimal
 from math import hypot, isclose
 import re
-import sys
 from collections import namedtuple
-from collections.abc import MutableMapping, Mapping
-import warnings
 from pathlib import Path
 from enum import Enum
-from contextlib import contextmanager
 
 from .exec import ghostscript
 from .helpers import fspath

src/ocrmypdf/pipeline.py

@@ -22,7 +22,6 @@ from datetime import datetime, timezone
 
 import sys
 import os
-import shutil
 import re
 
 import img2pdf
@@ -32,11 +31,11 @@ from PIL import Image
 from ruffus import formatter, regex, Pipeline, suffix
 
 from .hocrtransform import HocrTransform
-from .pdfinfo import PdfInfo, Encoding, Colorspace
+from .pdfinfo import PdfInfo, Colorspace
 from .pdfa import generate_pdfa_ps, encode_pdf_date
 from .helpers import re_symlink, is_iterable_notstr, page_number, flatten_groups
 from .exec import ghostscript, tesseract, qpdf
-from .exceptions import PdfMergeFailedError, UnsupportedImageFormatError, \
+from .exceptions import UnsupportedImageFormatError, \
     DpiError, PriorOcrFoundError, InputFileError
 from . import leptonica
 from . import PROGRAM_NAME, VERSION

tests/spoof/tesseract_cache.py

@@ -20,18 +20,6 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
-
-from pathlib import Path
-import sys
-import os
-import shutil
-import subprocess
-import argparse
-import json
-import platform
-import re
-
-
 """Cache output of tesseract to speed up test suite
 
 The cache is keyed by an environment variable that slips the input test file
@@ -66,6 +54,16 @@ given.
 
 """
 
+from pathlib import Path
+import sys
+import os
+import shutil
+import subprocess
+import argparse
+import json
+import platform
+import re
+
 if '_OCRMYPDF_SAVE_PATH' in os.environ:
     os.environ['PATH'] = os.environ['_OCRMYPDF_SAVE_PATH']
 

tests/spoof/tesseract_noop.py

@@ -20,12 +20,6 @@
 # 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 img2pdf
-import PyPDF2 as pypdf
-from PIL import Image
-
-
 """Tesseract no-op spoof
 
 To quickly run tests where getting OCR output is not necessary.
@@ -37,6 +31,11 @@ In 'pdf' mode, convert the image to PDF using another program.
 In orientation check mode, report the orientation is upright.
 """
 
+import sys
+import img2pdf
+import PyPDF2 as pypdf
+from PIL import Image
+
 
 VERSION_STRING = '''tesseract 3.05.01
  leptonica-1.72

tests/test_hocrtransform.py

@@ -18,17 +18,11 @@
 from ocrmypdf import hocrtransform
 from ocrmypdf.exec.tesseract import HOCR_TEMPLATE
 from ocrmypdf.exec import qpdf
-from reportlab.pdfgen.canvas import Canvas
 from PIL import Image
-from tempfile import NamedTemporaryFile
-from contextlib import suppress
 from pathlib import Path
-import os
-import shutil
 import pytest
-import img2pdf
-import pytest
-import sys
+
+# pylint: disable=redefined-outer-name
 
 
 @pytest.fixture

tests/test_main.py

@@ -34,8 +34,7 @@ from ocrmypdf.pdfa import file_claims_pdfa
 from ocrmypdf.leptonica import Pix
 
 # pytest.helpers is dynamic
-# pylint: disable=no-member
-# pylint: disable=w0612
+# pylint: disable=no-member,redefined-outer-name
 
 check_ocrmypdf = pytest.helpers.check_ocrmypdf
 run_ocrmypdf = pytest.helpers.run_ocrmypdf

tests/test_optimize.py

@@ -19,8 +19,6 @@ from pathlib import Path
 
 import pytest
 
-import pikepdf
-
 from ocrmypdf import optimize as opt