style: apply a number of pylint recommendations

.pylintrc

@@ -1,2 +1,8 @@
 [MASTER]
-disable=no-else-return # I find the "unecessary" else makes code more readable
+disable=
+    # We use isort for sorting our imports, so nevermind what pylint thinks
+    wrong-import-order,
+    # I find the "unnecessary" else makes code more readable
+    no-else-return,
+    # We use single letter e for exception, f for file handles
+    invalid-name

g2p/api.py

@@ -140,10 +140,10 @@ def get(self):
 def update_docs():
     """Update the swagger documentation with all nodes from the network"""
     swagger_path = os.path.join(os.path.dirname(static_file), "swagger.json")
-    with open(swagger_path) as f:
+    with open(swagger_path, encoding="utf-8-sig") as f:
         data = json.load(f)
     data["components"]["schemas"]["Langs"]["enum"] = sorted(LANGS_NETWORK.nodes)
-    with open(swagger_path, "w", newline="\n") as f:
+    with open(swagger_path, "w", encoding="utf-8", newline="\n") as f:
         f.write(json.dumps(data))
     LOGGER.info("Updated API documentation")
 

g2p/app.py

@@ -79,6 +79,7 @@ def network_to_echart(write_to_file: bool = False, layout: bool = False):
         with open(
             os.path.join(os.path.dirname(static_file), "languages-network.json"),
             "w",
+            encoding="utf-8",
             newline="\n",
         ) as f:
             f.write(json.dumps({"nodes": nodes, "edges": edges}) + "\n")

g2p/cli.py

@@ -1,3 +1,6 @@
+"""
+Command line interface to the g2p system
+"""
 import json
 import os
 import pprint
@@ -314,7 +317,7 @@ def generate_mapping(  # noqa: C901
 
     if list_dummy:
         # --list-dummy mode
-        print("Dummy phone inventory: {}".format(DUMMY_INVENTORY))
+        print(f"Dummy phone inventory: {DUMMY_INVENTORY}")
 
     elif ipa or dummy:
         # --ipa and --dummy modes

g2p/mappings/__init__.py

@@ -185,6 +185,7 @@ def find_mapping_by_id(map_id: str):
 
     @staticmethod
     def mapping_type(name):
+        """Return the type of a mapping given its name"""
         if is_ipa(name):
             return "IPA"
         elif is_xsampa(name):
@@ -211,6 +212,7 @@ def _string_to_pua(string: str, offset: int) -> str:
         return intermediate_char * len(string)
 
     def index(self, item):
+        """Find the location of an item in self"""
         return self.mapping.index(item)
 
     def inventory(self, in_or_out: str = "in"):
@@ -259,7 +261,7 @@ def sorted_rule_items(rule: dict):
             for io in self.mapping
         ]
 
-    def process_kwargs(self, mapping):
+    def process_kwargs(self, mapping):  # noqa: C901
         """Apply kwargs in the order they are provided. kwargs are ordered as of python 3.6"""
 
         if "as_is" in self.kwargs:
@@ -364,7 +366,8 @@ def rule_to_regex(self, rule: dict) -> Union[Pattern, None]:
         # Prevent null input. See, https://github.com/roedoejet/g2p/issues/24
         if not rule["in"]:
             LOGGER.warning(
-                f'Rule with input \'{rule["in"]}\' and output \'{rule["out"]}\' has no input. This is disallowed. Please check your mapping file for rules with null inputs.'
+                f'Rule with input \'{rule["in"]}\' and output \'{rule["out"]}\' has no input. '
+                "This is disallowed. Please check your mapping file for rules with null inputs."
             )
             return None
         if "context_before" in rule and rule["context_before"]:
@@ -459,7 +462,7 @@ def mapping_to_file(self, output_path: str = GEN_DIR, file_type: str = "json"):
         """Write mapping to file"""
 
         if not os.path.isdir(output_path):
-            raise Exception("Path %s is not a directory", output_path)
+            raise Exception(f"Path {output_path} is not a directory")
         fn = os.path.join(
             output_path,
             self.kwargs.get("in_lang", "und")

g2p/transducer/__init__.py

@@ -34,7 +34,8 @@
 Index = Dict
 
 # A ChangeLog is a list of changes (List[int])
-# The first item (int) in a change is the index of where the change occurs, and the second item (int) is the change offset
+# The first item (int) in a change is the index of where the change occurs, and
+# the second item (int) is the change offset
 # Example:
 # an insertion of length 1 at index 0 followed by a deletion of length one at index 2
 # [[0,1],[2,-1]]
@@ -187,7 +188,8 @@ def __iadd__(self, tg):
 class Transducer:
     """This is the fundamental class for performing conversions in the g2p library.
 
-    Each Transducer must be initialized with a Mapping object. The Transducer object can then be called to apply the rules from Mapping on a given input.
+    Each Transducer must be initialized with a Mapping object. The Transducer
+    object can then be called to apply the rules from Mapping on a given input.
 
     Attributes:
         mapping (Mapping): Formatted input/output pairs using the g2p.mappings.Mapping class.
@@ -211,7 +213,9 @@ def __call__(self, to_convert: str, index: bool = False, debugger: bool = False)
             to_convert (str): The string to convert.
 
         Returns:
-            TransductionGraph: Returns an object with all the nodes representing input and output characters and their corresponding edges representing the indices of the transformation.
+            TransductionGraph: Returns an object with all the nodes representing input
+            and output characters and their corresponding edges representing the indices
+            of the transformation.
         """
         return self.apply_rules(to_convert)
 
@@ -272,13 +276,15 @@ def get_match_groups(
             inputs = {'1': [{'index': 0, 'string': 'a'}], '2': [{'index': 1, 'string': 'b'}] }
             outputs = {'1': [{'index': 0, 'string': 'b'}], '2': [{'index': 1, 'string': 'a'}] }
 
-            This allows input match groups to be iterated through in sequence regardless of their character sequence.
+            This allows input match groups to be iterated through in sequence regardless of their
+            character sequence.
 
         Args:
             tg (TransductionGraph): the graph holding information about the transduction
-            start_end (Tuple(int, int)): a tuple contianing the start and end of the input match
+            start_end (Tuple(int, int)): a tuple containing the start and end of the input match
             io (List): an input/output rule
-            diff_from_input (DefaultDict): A dictionary containing the single character distance from a given character index to its input
+            diff_from_input (DefaultDict): A dictionary containing the single character distance
+                                           from a given character index to its input
             out_string (str): the raw output string
             output_start (int): the diff-offset start of the match with respect to the output
 
@@ -382,7 +388,7 @@ def change_character(self, tg, character, index_to_change):
     def update_explicit_indices(
         self, tg, match, start_end, io, diff_from_input, diff_from_output, out_string
     ):
-        """Takes an arbitrary number of input & output strings and their corresponding index offsets.
+        r"""Takes an arbitrary number of input & output strings and their corresponding index offsets.
         It then zips them up according to the provided indexing notation.
 
         Example:
@@ -543,7 +549,7 @@ def apply_unidecode(self, to_convert: str):
 
         return tg
 
-    def apply_rules(self, to_convert: str):
+    def apply_rules(self, to_convert: str):  # noqa: C901
         if self.mapping.kwargs.get("type", "") == "unidecode":
             return self.apply_unidecode(to_convert)
 
@@ -696,7 +702,8 @@ def check(
             if display_warnings:
                 display_input = original_input or tg.input_string
                 LOGGER.warning(
-                    f'Transducer output "{tg.output_string}" for input "{display_input}" is not fully valid eng-arpabet as recognized by soundswallower.'
+                    f'Transducer output "{tg.output_string}" for input "{display_input}" '
+                    "is not fully valid eng-arpabet as recognized by soundswallower."
                 )
             return False
         elif is_ipa(out_lang):