#109 fix all Ruff formatting and linting errors

.github/workflows/pr_ci.yaml

@@ -46,4 +46,4 @@ jobs:
 
       - name: Run ruff - Linting and import sorting check
         if: always()
-        run: ruff check .
+        run: ruff check .

src/scribe_data/checkquery.py

@@ -24,6 +24,7 @@
 """
 
 import argparse
+import contextlib
 import math
 import os
 import subprocess
@@ -304,12 +305,10 @@ def check_positive_int(value: str, err_msg: str) -> int:
     ------
         argparse.ArgumentTypeError
     """
-    try:
+    with contextlib.suppress(ValueError):
         number = int(value)
         if number >= 1:
             return number
-    except ValueError:
-        pass
 
     raise argparse.ArgumentTypeError(err_msg)
 

src/scribe_data/extract_transform/extract_wiki.py

@@ -320,9 +320,9 @@ def parse_to_ndjson(
         print(f"Making {output_dir} directory for the output")
         os.makedirs(output_dir)
 
-    if multicore == True:
+    if multicore:
         num_cores = os.cpu_count()
-    elif multicore == False:
+    elif not multicore:
         num_cores = 1
     elif isinstance(multicore, int):
         num_cores = multicore
@@ -372,8 +372,8 @@ def read_and_combine_json(file_path):
             data = []
 
             with open(file_path, "r", encoding="utf-8") as f:
-                for l in f:
-                    data.append(json.loads(l))
+                for line in f:
+                    data.append(json.loads(line))
 
             return data
 

src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/English/translations/translate_words.py

@@ -14,7 +14,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import translate_to_other_languages
+from scribe_data.utils import translate_to_other_languages  # noqa: E402
 
 SRC_LANG = "English"
 translate_script_dir = os.path.dirname(os.path.abspath(__file__))

src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py

@@ -10,7 +10,11 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data, map_genders
+from scribe_data.utils import (  # noqa: E402
+    export_formatted_data,
+    load_queried_data,
+    map_genders,
+)
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/French/translations/translate_words.py

@@ -14,7 +14,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import translate_to_other_languages
+from scribe_data.utils import translate_to_other_languages  # noqa: E402
 
 SRC_LANG = "French"
 translate_script_dir = os.path.dirname(os.path.abspath(__file__))

src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py

@@ -10,7 +10,11 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data, map_genders
+from scribe_data.utils import (  # noqa: E402
+    export_formatted_data,
+    load_queried_data,
+    map_genders,
+)
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py

@@ -15,7 +15,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py

@@ -10,7 +10,11 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data, map_genders
+from scribe_data.utils import (  # noqa: E402
+    export_formatted_data,
+    load_queried_data,
+    map_genders,
+)
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py

@@ -10,7 +10,11 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data, map_genders
+from scribe_data.utils import (  # noqa: E402
+    export_formatted_data,
+    load_queried_data,
+    map_genders,
+)
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py

@@ -10,7 +10,11 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data, map_genders
+from scribe_data.utils import (  # noqa: E402
+    export_formatted_data,
+    load_queried_data,
+    map_genders,
+)
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py

@@ -14,7 +14,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import translate_to_other_languages
+from scribe_data.utils import translate_to_other_languages  # noqa: E402
 
 SRC_LANG = "Russian"
 translate_script_dir = os.path.dirname(os.path.abspath(__file__))

src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py

@@ -10,7 +10,11 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data, map_genders
+from scribe_data.utils import (  # noqa: E402
+    export_formatted_data,
+    load_queried_data,
+    map_genders,
+)
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py

@@ -10,7 +10,11 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data, map_genders
+from scribe_data.utils import (  # noqa: E402
+    export_formatted_data,
+    load_queried_data,
+    map_genders,
+)
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py

@@ -10,7 +10,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import export_formatted_data, load_queried_data
+from scribe_data.utils import export_formatted_data, load_queried_data  # noqa: E402
 
 file_path = sys.argv[0]
 

src/scribe_data/extract_transform/process_unicode.py

@@ -8,15 +8,14 @@
 import csv
 import fileinput
 import json
-import re
 from importlib.resources import files
 
 import emoji
 from icu import Char, UProperty
 from tqdm.auto import tqdm
 
 from scribe_data.extract_transform.emoji_utils import get_emoji_codes_to_ignore
-from scribe_data.load.update_utils import (
+from scribe_data.utils import (
     get_language_iso,
     get_path_from_et_dir,
 )

src/scribe_data/extract_transform/process_wiki.py

@@ -19,7 +19,6 @@
 from tqdm.auto import tqdm
 
 from scribe_data.utils import (
-    get_ios_data_path,
     get_language_qid,
     get_language_words_to_ignore,
     get_language_words_to_remove,

src/scribe_data/load/data_to_sqlite.py

@@ -23,7 +23,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import get_ios_data_path, get_language_iso
+from scribe_data.utils import get_language_iso  # noqa: E402
 
 PATH_TO_ET_FILES = "../extract_transform/"
 
@@ -76,32 +76,32 @@
 languages_update = current_languages if languages is None else languages
 
 language_word_type_dict = {
-    l: [
+    lang: [
         f.split(".json")[0]
-        for f in os.listdir(f"{PATH_TO_ET_FILES}{l}/formatted_data")
+        for f in os.listdir(f"{PATH_TO_ET_FILES}{lang}/formatted_data")
         if f.split(".json")[0] in word_types
     ]
-    for l in languages_update
+    for lang in languages_update
 }
 
 print(
     f"Creating SQLite databases for the following languages: {', '.join(languages_update)}"
 )
-for l in tqdm(
+for lang in tqdm(
     language_word_type_dict,
     desc="Databases created",
     unit="dbs",
 ):
-    if language_word_type_dict[l] != []:
+    if language_word_type_dict[lang] != []:
         maybe_over = ""  # output string formatting variable (see below)
         if os.path.exists(
-            f"databases/{get_language_iso(l).upper()}LanguageData.sqlite"
+            f"databases/{get_language_iso(lang).upper()}LanguageData.sqlite"
         ):
-            os.remove(f"databases/{get_language_iso(l).upper()}LanguageData.sqlite")
+            os.remove(f"databases/{get_language_iso(lang).upper()}LanguageData.sqlite")
             maybe_over = "over"
 
         connection = sqlite3.connect(
-            f"databases/{get_language_iso(l).upper()}LanguageData.sqlite"
+            f"databases/{get_language_iso(lang).upper()}LanguageData.sqlite"
         )
         cursor = connection.cursor()
 
@@ -139,11 +139,11 @@ def table_insert(word_type, keys):
                 keys,
             )
 
-        print(f"Database for {l} {maybe_over}written and connection made.")
-        for wt in language_word_type_dict[l]:
-            print(f"Creating {l} {wt} table...")
+        print(f"Database for {lang} {maybe_over}written and connection made.")
+        for wt in language_word_type_dict[lang]:
+            print(f"Creating {lang} {wt} table...")
             json_data = json.load(
-                open(f"{PATH_TO_ET_FILES}{l}/formatted_data/{wt}.json")
+                open(f"{PATH_TO_ET_FILES}{lang}/formatted_data/{wt}.json")
             )
 
             if wt == "nouns":
@@ -153,9 +153,9 @@ def table_insert(word_type, keys):
                     keys = [row, json_data[row]["plural"], json_data[row]["form"]]
                     table_insert(word_type=wt, keys=keys)
 
-                if "Scribe" not in json_data and l != "Russian":
+                if "Scribe" not in json_data and lang != "Russian":
                     table_insert(word_type=wt, keys=["Scribe", "Scribes", ""])
-                # elif "Писец" not in json_data and l == "Russian":
+                # elif "Писец" not in json_data and lang == "Russian":
                 #     table_insert(word_type=wt, keys=["Писец", "Писцы", ""])
 
                 connection.commit()
@@ -214,7 +214,7 @@ def table_insert(word_type, keys):
                 connection.commit()
 
         wt = "autocomplete_lexicon"
-        print(f"Creating {l} {wt} table...")
+        print(f"Creating {lang} {wt} table...")
         cols = ["word"]
         create_table(word_type=wt, cols=cols)
 
@@ -306,7 +306,7 @@ def table_insert(word_type, keys):
 
         connection.commit()
 
-        print(f"{l} database created.")
+        print(f"{lang} database created.")
 
     else:
-        print(f"Skipping {l} database creation as no JSON data files were found.")
+        print(f"Skipping {lang} database creation as no JSON data files were found.")

src/scribe_data/load/send_dbs_to_scribe.py

@@ -13,7 +13,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.utils import (
+from scribe_data.utils import (  # noqa: E402
     get_ios_data_path,
     get_language_from_iso,
     get_path_from_load_dir,