diff --git a/.github/workflows/pr_ci.yaml b/.github/workflows/pr_ci.yaml new file mode 100644 index 00000000..0f317ee6 --- /dev/null +++ b/.github/workflows/pr_ci.yaml @@ -0,0 +1,49 @@ +name: pr_ci +on: + push: + branches: [main] + pull_request: + branches: + - main + types: [opened, reopened, synchronize] + +jobs: + format_check: + strategy: + fail-fast: false + matrix: + os: + - ubuntu-latest + python-version: + - "3.9" + + runs-on: ${{ matrix.os }} + + name: Run PR Check + + steps: + - name: Checkout + uses: actions/checkout@v3 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v4 + with: + python-version: ${{ matrix.python-version }} + + - name: Install dependencies + run: | + python -m pip install --upgrade uv + uv venv + uv pip install -r requirements.txt + + - name: Activate virtualenv + run: | + . .venv/bin/activate + echo PATH=$PATH >> $GITHUB_ENV + + - name: Run ruff format - Formatting check + run: ruff check . + + - name: Run ruff - Linting and import sorting check + if: always() + run: ruff check . diff --git a/CHANGELOG.md b/CHANGELOG.md index 5689d33e..f2bce29c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -21,9 +21,10 @@ Emojis for the following are chosen based on [gitmoji](https://gitmoji.dev/). ### ♻️ Code Refactoring +- Code formatting was shifted from [black](https://github.com/psf/black) to [Ruff](https://github.com/astral-sh/ruff). +- A Ruff based GitHub workflow was added to check the code formatting and lint the codebase on each pull request ([#109](https://github.com/scribe-org/Scribe-Data/issues/109)). - The `_update_files` directory was renamed `update_files` as these files are used in non-internal manners now ([#57](https://github.com/scribe-org/Scribe-Data/issues/57)). - A common function has been created to map Wikidata ids to noun genders ([#69](https://github.com/scribe-org/Scribe-Data/issues/69)). -- Code formatting was shifted from [black](https://github.com/psf/black) to [Ruff](https://github.com/astral-sh/ruff). ## Scribe-Data 3.2.2 diff --git a/src/scribe_data/checkquery.py b/src/scribe_data/checkquery.py index 71ab4410..1a035f2a 100755 --- a/src/scribe_data/checkquery.py +++ b/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) diff --git a/src/scribe_data/extract_transform/extract_wiki.py b/src/scribe_data/extract_transform/extract_wiki.py index 1466fd8d..2f98dca0 100644 --- a/src/scribe_data/extract_transform/extract_wiki.py +++ b/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 diff --git a/src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py index 502a2f22..5356c054 100644 --- a/src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/English/translations/translate_words.py b/src/scribe_data/extract_transform/languages/English/translations/translate_words.py index 944c9cd4..fad6e9ec 100644 --- a/src/scribe_data/extract_transform/languages/English/translations/translate_words.py +++ b/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__)) diff --git a/src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py index 24219922..92c42927 100644 --- a/src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py index 569c81ff..7ea0576d 100644 --- a/src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/French/translations/translate_words.py b/src/scribe_data/extract_transform/languages/French/translations/translate_words.py index 35b82eef..a8177bdb 100644 --- a/src/scribe_data/extract_transform/languages/French/translations/translate_words.py +++ b/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__)) diff --git a/src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py index 8310504a..c2b9e367 100644 --- a/src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py index a28c8700..557903c5 100644 --- a/src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py b/src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py index 69486dcb..d03e209b 100644 --- a/src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py index 042170bd..5a6bda6e 100644 --- a/src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py index 7c618616..99566f59 100644 --- a/src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py index 6b905c21..95bb2a35 100644 --- a/src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py index 280aeda5..6c84b6ec 100644 --- a/src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py b/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py index d170c943..884083d8 100644 --- a/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py +++ b/src/scribe_data/extract_transform/languages/Portuguese/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 = "Portuguese" translate_script_dir = os.path.dirname(os.path.abspath(__file__)) diff --git a/src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py index 285bb7cf..c71ed07f 100644 --- a/src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py index 4c3ae853..0fb2d20a 100644 --- a/src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py b/src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py index 4dd10a13..8702881e 100644 --- a/src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py b/src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py index a9c295fc..a2b78e8f 100644 --- a/src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py +++ b/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__)) diff --git a/src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py index 4c914bee..7b3d49a1 100644 --- a/src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py index 4339fb38..ff552e16 100644 --- a/src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py index 43ede52e..e69d439d 100644 --- a/src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py index 6fca6254..cf717068 100644 --- a/src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py index 01767e6e..c58b6de8 100644 --- a/src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py +++ b/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] diff --git a/src/scribe_data/extract_transform/languages/__init__.py b/src/scribe_data/extract_transform/languages/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/src/scribe_data/extract_transform/process_unicode.py b/src/scribe_data/extract_transform/process_unicode.py index 5185cd1e..4297f56d 100644 --- a/src/scribe_data/extract_transform/process_unicode.py +++ b/src/scribe_data/extract_transform/process_unicode.py @@ -8,7 +8,6 @@ import csv import fileinput import json -import re from importlib.resources import files import emoji @@ -16,7 +15,7 @@ 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, ) diff --git a/src/scribe_data/extract_transform/process_wiki.py b/src/scribe_data/extract_transform/process_wiki.py index c937d05a..227e12ab 100644 --- a/src/scribe_data/extract_transform/process_wiki.py +++ b/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, diff --git a/src/scribe_data/load/data_to_sqlite.py b/src/scribe_data/load/data_to_sqlite.py index 50adde11..09cb2c34 100644 --- a/src/scribe_data/load/data_to_sqlite.py +++ b/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.") diff --git a/src/scribe_data/load/send_dbs_to_scribe.py b/src/scribe_data/load/send_dbs_to_scribe.py index 4da7b93a..082784c1 100644 --- a/src/scribe_data/load/send_dbs_to_scribe.py +++ b/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,