Apply some picky coding recommendations

readalongs/align.py

@@ -1,7 +1,6 @@
 """Main readalongs module for aligning text and audio."""
 
 import copy
-import io
 import os
 import shutil
 import sys
@@ -249,7 +248,7 @@ def read_noisedict(asr_config: soundswallower.Config) -> Set[str]:
 
     def load_noisedict(fdict):
         try:
-            with open(fdict, "rt", encoding="utf-8") as dictfh:
+            with open(fdict, encoding="utf-8") as dictfh:
                 noisewords = set()
                 for line in dictfh:
                     if line.startswith("##") or line.startswith(";;"):
@@ -364,15 +363,15 @@ def align_sequence(
     # Generate dictionary and FSG for the current sequence of words
     dict_data = make_dict(word_sequence.words, xml_path, unit=unit)
     if save_temps is not None:
-        dict_file = io.open(save_temps + ".dict" + i_suffix, "wb")
+        dict_file = open(save_temps + ".dict" + i_suffix, "wb")
     else:
         dict_file = PortableNamedTemporaryFile(prefix="readalongs_dict_", delete=True)
     dict_file.write(dict_data.encode("utf-8"))
     dict_file.close()
 
     fsg_data = make_fsg(word_sequence.words, xml_path)
     if save_temps is not None:
-        fsg_file = io.open(save_temps + ".fsg" + i_suffix, "wb")
+        fsg_file = open(save_temps + ".fsg" + i_suffix, "wb")
     else:
         fsg_file = PortableNamedTemporaryFile(prefix="readalongs_fsg_", delete=True)
     fsg_file.write(fsg_data.encode("utf-8"))

readalongs/align_utils.py

@@ -2,7 +2,6 @@
 Functions for saving alignments in various file formats.
 """
 
-import io
 from datetime import timedelta
 from typing import Any, Dict, Iterable, List, Optional, Sequence, Tuple, Union
 
@@ -399,7 +398,7 @@ def create_input_ras(**kwargs):
     try:
         if kwargs.get("input_file_name", False):
             filename = kwargs["input_file_name"]
-            with io.open(kwargs["input_file_name"], encoding="utf-8-sig") as f:
+            with open(kwargs["input_file_name"], encoding="utf-8-sig") as f:
                 text = f.readlines()
         elif kwargs.get("input_file_handle", False):
             filename = kwargs["input_file_handle"].name
@@ -418,10 +417,10 @@ def create_input_ras(**kwargs):
     save_temps = kwargs.get("save_temps", None)
     if kwargs.get("output_file", False):
         filename = kwargs["output_file"]
-        outfile = io.open(filename, "wb")
+        outfile = open(filename, "wb")
     elif save_temps is not None:
         filename = save_temps + ".input.readalong"
-        outfile = io.open(filename, "wb")
+        outfile = open(filename, "wb")
     else:
         outfile = PortableNamedTemporaryFile(
             prefix="readalongs_xml_", suffix=".readalong", delete=True

readalongs/api.py

@@ -166,7 +166,7 @@ def make_xml(
 
         make_xml_args = {param.name: param.default for param in cli.make_xml.params}
         try:
-            with open(plaintextfile, "r", encoding="utf-8-sig") as plaintextfile_handle:
+            with open(plaintextfile, encoding="utf-8-sig") as plaintextfile_handle:
                 make_xml_args.update(
                     plaintextfile=plaintextfile_handle,
                     xmlfile=xmlfile,

readalongs/cli.py

@@ -546,7 +546,7 @@ def make_xml(**kwargs):
             _, filename = create_input_ras(
                 input_file_handle=input_file, text_languages=languages
             )
-            with io.open(filename, encoding="utf-8-sig") as f:
+            with open(filename, encoding="utf-8-sig") as f:
                 sys.stdout.write(f.read())
         else:
             if not str(out_file).endswith(".readalong"):
@@ -564,7 +564,7 @@ def make_xml(**kwargs):
     except (RuntimeError, OSError) as e:
         raise click.UsageError(str(e)) from e
 
-    LOGGER.info("Wrote {}".format(out_file))
+    LOGGER.info(f"Wrote {out_file}")
 
 
 @cli.command(  # type: ignore  # quench spurious mypy error: "Command" has no attribute "command"
@@ -637,7 +637,7 @@ def tokenize(**kwargs):
         write_xml(sys.stdout.buffer, xml)
     else:
         save_xml(output_path, xml)
-    LOGGER.info("Wrote {}".format(output_path))
+    LOGGER.info(f"Wrote {output_path}")
 
 
 @cli.command(  # type: ignore  # quench spurious mypy error: "Command" has no attribute "command"
@@ -759,7 +759,7 @@ def g2p(**kwargs):
         write_xml(sys.stdout.buffer, xml)
     else:
         save_xml(output_path, xml)
-        LOGGER.info("Wrote {}".format(output_path))
+        LOGGER.info(f"Wrote {output_path}")
 
     if not valid:
         LOGGER.error(

readalongs/epub/create_epub.py

@@ -1,13 +1,11 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 ######################################################################
 #
 # create_epub.py
 #
 ######################################################################
 
-from __future__ import absolute_import, division, print_function, unicode_literals
 
 import os
 import shutil

readalongs/text/util.py

@@ -7,13 +7,10 @@
 # TODO: Add Google standard format docstrings
 ############################################
 
-import json
 import os
 import re
 import zipfile
-from collections import OrderedDict
 from datetime import datetime
-from io import TextIOWrapper
 from typing import IO, Union
 
 from lxml import etree
@@ -140,16 +137,10 @@ def parse_xml(xml_text: Union[str, bytes]) -> etree.ElementTree:
     )
 
 
-def load_xml_zip(zip_path, input_path) -> etree.ElementTree:
-    with zipfile.ZipFile(zip_path, "r") as fin_zip:
-        with fin_zip.open(input_path, "r") as fin:
-            return load_xml(fin)
-
-
 def write_xml(output_filelike, xml):
-    """Write XML to already opened file-like object"""
+    """Write XML to already opened binary-mode file-like object"""
     output_filelike.write(etree.tostring(xml, encoding="utf-8", xml_declaration=True))
-    output_filelike.write("\n".encode("utf-8"))
+    output_filelike.write(b"\n")
 
 
 def save_xml(output_path, xml):
@@ -163,27 +154,11 @@ def xml_to_string(xml) -> str:
     return etree.tostring(xml, encoding="utf-8", xml_declaration=True).decode()
 
 
-def save_xml_zip(zip_path, output_path, xml):
-    ensure_dirs(zip_path)
-    with zipfile.ZipFile(zip_path, "a", compression=zipfile.ZIP_DEFLATED) as fout_zip:
-        fout_zip.writestr(
-            output_path,
-            etree.tostring(xml, encoding="utf-8", xml_declaration=True) + "\n",
-        )
-
-
 def load_txt(input_path):
-    with open(input_path, "r", encoding="utf-8-sig") as fin:
+    with open(input_path, encoding="utf-8-sig") as fin:
         return fin.read()
 
 
-def load_txt_zip(zip_path, input_path):
-    with zipfile.ZipFile(zip_path, "r") as fin_zip:
-        with fin_zip.open(input_path, "r") as fin:
-            fin_utf8 = TextIOWrapper(fin, encoding="utf-8")
-            return fin_utf8.read()
-
-
 def save_txt(output_path, txt):
     ensure_dirs(output_path)
     with open(output_path, "w", encoding="utf-8") as fout:
@@ -196,31 +171,6 @@ def save_txt_zip(zip_path, output_path, txt):
         fout_zip.writestr(output_path, txt.encode("utf-8"))
 
 
-def load_json(input_path):
-    with open(input_path, "r", encoding="utf-8-sig") as fin:
-        return json.load(fin, object_pairs_hook=OrderedDict)
-
-
-def load_json_zip(zip_path, input_path):
-    with zipfile.ZipFile(zip_path, "r") as fin_zip:
-        with fin_zip.open(input_path, "r") as fin:
-            fin_utf8 = TextIOWrapper(fin, encoding="utf-8")
-            return json.loads(fin_utf8.read(), object_pairs_hook=OrderedDict)
-
-
-def save_json(output_path, obj):
-    ensure_dirs(output_path)
-    with open(output_path, "w", encoding="utf-8") as fout:
-        fout.write(unicode(json.dumps(obj, ensure_ascii=False, indent=4)))
-
-
-def save_json_zip(zip_path, output_path, obj):
-    ensure_dirs(zip_path)
-    txt = unicode(json.dumps(obj, ensure_ascii=False, indent=4))
-    with zipfile.ZipFile(zip_path, "a") as fout_zip:
-        fout_zip.writestr(output_path, txt.encode("utf-8"))
-
-
 def copy_file_to_zip(zip_path, origin_path, destination_path):
     ensure_dirs(zip_path)
     with zipfile.ZipFile(zip_path, "a", compression=zipfile.ZIP_DEFLATED) as fout_zip:
@@ -383,7 +333,7 @@ def save_readme_txt(
 ):
     # setup path for default WordPress upload directory
     today = datetime.now()
-    wp_upload_folder = "/wp-content/uploads/{:%Y/%m}/".format(today)
+    wp_upload_folder = f"/wp-content/uploads/{today:%Y/%m}/"
     with open(output_path, "w", encoding="utf-8") as fout:
         fout.write(
             TEMPLATE_README_TXT.format(

readalongs/waveform2svg/audio_util.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 ###################################################
 #
@@ -14,10 +13,8 @@
 #
 ###################################################
 
-from __future__ import absolute_import, division, print_function, unicode_literals
 
 import os
-from io import open
 
 import librosa  # type: ignore
 import numpy as np

readalongs/waveform2svg/make_all_svgs.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 ########################################################
 #
@@ -9,7 +8,6 @@
 #
 ########################################################
 
-from __future__ import absolute_import, division, print_function, unicode_literals
 
 import argparse
 

readalongs/waveform2svg/pitch2svg.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 ###################################################
 #
@@ -14,7 +13,6 @@
 #
 ###################################################
 
-from __future__ import absolute_import, division, print_function, unicode_literals
 
 import argparse
 from math import floor

readalongs/waveform2svg/waveform2svg.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 ###################################################
 #
@@ -11,7 +10,6 @@
 #
 ###################################################
 
-from __future__ import absolute_import, division, print_function, unicode_literals
 
 import argparse
 from math import ceil, floor

tests/basic_test_case.py

@@ -54,7 +54,7 @@ def setUp(self):
         else:
             # Alternative tempdir code keeps it after running, for manual inspection:
             tempdir_name = tempfile.mkdtemp(prefix=tempdir_prefix, dir=".")
-            print("tmpdir={}".format(tempdir_name))
+            print(f"tmpdir={tempdir_name}")
         self.tempdir = Path(tempdir_name)
 
     def tearDown(self):

tests/test_align_cli.py

@@ -89,7 +89,6 @@ def test_invoke_align(self) -> None:
         )
         with open(
             output / "tempfiles/output.tokenized.readalong",
-            "r",
             encoding="utf-8",
         ) as f:
             self.assertNotIn("\ufeff", f.read())
@@ -292,7 +291,7 @@ def test_align_english(self):
         tokenized_file = join(
             self.tempdir, "eng-output", "tempfiles", "eng-output.g2p.readalong"
         )
-        with open(tokenized_file, "r", encoding="utf8") as f:
+        with open(tokenized_file, encoding="utf8") as f:
             tok_output = f.read()
 
         self.assertIn(g2p_ref, tok_output)
@@ -616,7 +615,7 @@ def slurp_bin(filename):
                 return f.read()
 
         def slurp_text(filename, encoding):
-            with open(filename, "r", encoding=encoding) as f:
+            with open(filename, encoding=encoding) as f:
                 return f.read()
 
         base_file = write_file(self.tempdir / "add-bom-input.txt", "Random Text été")

tests/test_anchors.py

@@ -85,7 +85,7 @@ def test_anchors_align_modes(self):
             </body></doc>
         """
         xml_file = os.path.join(self.tempdir, "text-with-anchors.readalong")
-        with open(xml_file, "wt", encoding="utf8") as f:
+        with open(xml_file, "w", encoding="utf8") as f:
             print(xml_with_anchors, file=f)
         with self.assertLogs(LOGGER, level="INFO") as cm:
             with silence_c_stderr(), redirect_stderr(StringIO()):

tests/test_dtd.py

@@ -43,7 +43,7 @@ class TestDTD(TestCase):
     """Test the XML DTD"""
 
     def setUp(self):
-        with open(DTDPATH, "rt") as infh:
+        with open(DTDPATH) as infh:
             self.dtd = etree.DTD(infh)
 
     def test_valid_inputs(self):
@@ -96,7 +96,6 @@ def test_backwards_compatibility(self):
             os.path.join(
                 dirname(__file__), "..", "readalongs", "static", "read-along-1.0.dtd"
             ),
-            "rt",
         ) as dtdFile:
             dtd = etree.DTD(dtdFile)
             with open(

tests/test_force_align.py

@@ -133,7 +133,7 @@ def test_align_switch_am(self):
         with TemporaryDirectory(prefix="readalongs_am_") as tempdir:
             custom_am_path = os.path.join(tempdir, "en-us")
             shutil.copytree(get_model_path("en-us"), custom_am_path)
-            with open(os.path.join(custom_am_path, "noisedict"), "at") as fh:
+            with open(os.path.join(custom_am_path, "noisedict"), "a") as fh:
                 fh.write(";; here is a comment\n")
                 fh.write("[BOGUS] SIL\n")
             with redirect_stderr(StringIO()):

tests/test_g2p_cli.py

@@ -338,7 +338,7 @@ def test_align_with_preg2p(self):
                 _ = align_audio(
                     text_file, audio_file, save_temps=os.path.join(self.tempdir, "foo")
                 )
-        with open(os.path.join(self.tempdir, "foo.dict"), "r", encoding="utf8") as f:
+        with open(os.path.join(self.tempdir, "foo.dict"), encoding="utf8") as f:
             dict_file = f.read()
             self.assertIn("S AH S IY", dict_file)  # "ceci" in fra
             self.assertIn("DH IH S", dict_file)  # "this" in eng

tests/test_make_xml_cli.py

@@ -31,7 +31,7 @@ class TestMakeXMLCli(BasicTestCase):
     def setUp(self):
         super().setUp()
         self.empty_file = os.path.join(self.tempdir, "empty.txt")
-        with io.open(self.empty_file, "wb"):
+        with open(self.empty_file, "wb"):
             pass
 
     def test_invoke_prepare(self):