async def test_parser_should_find_grammar_info_in_german_verbs(
examples_downloader: FileCache,
):
url = get_search_url(query="bringen", src="de", dst="en", guess_direction=False)
page_html = await examples_downloader.download(url)
page = XExtractParser().parse_search_result_to_page(page_html)
assert page.lemmas[0].grammar_info == "Akk"
async def test_parse_to_dict_should_return_parseable_result(
examples_downloader: FileCache,
query: str,
src: LANGUAGE_CODE,
dst: LANGUAGE_CODE,
):
url = get_search_url(query=query, src=src, dst=dst, guess_direction=False)
page = await examples_downloader.download(url)
XExtractParser().parse_search_result_to_page(page)
async def test_parser_should_process_examples_without_links(
examples_downloader: FileCache,
):
url = get_search_url(query="einfach", src="de", dst="en", guess_direction=False)
page_html = await examples_downloader.download(url)
page = XExtractParser().parse_search_result_to_page(page_html)
sources = page.external_sources
assert all([s.src_url.startswith("http") for s in sources])
assert all([s.dst_url.startswith("http") for s in sources])
async def test_parse_autocompletions_should_return_autocompletions(
examples_downloader: FileCache, ):
url = get_autocompletions_url(query="katz", src="de", dst="en")
page = await examples_downloader.download(url)
parser = XExtractParser()
parse_result = parser.parse_autocompletions(page)
a = Autocompletions.AutocompletionItem
t = Autocompletions.AutocompletionItem.TranslationItem
first_item = a(
text="Katze",
pos="f",
translations=[
t(text="cat", pos="n"),
t(text="feline", pos="n"),
t(text="crab", pos="n"),
],
)
assert parse_result.autocompletions[0] == first_item
async def test_parser_should_find_correction(
examples_downloader: FileCache,
query: str,
src: LANGUAGE_CODE,
dst: LANGUAGE_CODE,
correction: Optional[str],
):
url = get_search_url(query=query, src=src, dst=dst, guess_direction=False)
page = await examples_downloader.download(url)
assert XExtractParser().find_correction(page) == correction
async def test_parser_should_detect_not_found(
examples_downloader: FileCache,
query: str,
src: LANGUAGE_CODE,
dst: LANGUAGE_CODE,
is_not_found: bool,
):
url = get_search_url(query=query, src=src, dst=dst, guess_direction=False)
page = await examples_downloader.download(url)
assert XExtractParser().is_not_found(page) == is_not_found
async def test_parser_should_find_translation_examples(
examples_downloader: FileCache,
):
url = get_search_url(query="obrigado", src="pt", dst="en", guess_direction=False)
page_html = await examples_downloader.download(url)
page = XExtractParser().parse_search_result_to_page(page_html)
examples_of_1st_translation = page.lemmas[0].translations[0].examples
assert examples_of_1st_translation is not None
assert len(examples_of_1st_translation) == 1
assert examples_of_1st_translation[0].src == (
"Obrigado por sua participação em nossa pesquisa."
)
assert examples_of_1st_translation[0].dst == (
"Thank you for your participation in our survey."
)
def linguee_client(examples_downloader) -> LingueeClient:
return LingueeClient(
page_downloader=examples_downloader, page_parser=XExtractParser()
)
from linguee_api.models import Autocompletions, ParseError, SearchResult
from linguee_api.parsers import XExtractParser
sentry_sdk.init(dsn=settings.sentry_dsn,
environment=settings.sentry_environment)
app = FastAPI(
title="Linguee API",
description=PROJECT_DESCRIPTION,
version="2.0.0",
)
app.add_middleware(SentryAsgiMiddleware)
page_downloader = MemoryCache(upstream=FileCache(
cache_directory=settings.cache_directory, upstream=HTTPXDownloader()))
client = LingueeClient(page_downloader=page_downloader,
page_parser=XExtractParser())
@app.get("/", include_in_schema=False)
def index():
return RedirectResponse("/docs")
@app.get(
"/api/v2/translations",
status_code=status.HTTP_200_OK,
responses={
status.HTTP_200_OK: {
"model": list[SearchResult.Lemma]
},
status.HTTP_500_INTERNAL_SERVER_ERROR: {