Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 29 additions & 4 deletions dateparser/search/search.py
Original file line number Diff line number Diff line change
Expand Up @@ -218,6 +218,21 @@ def __init__(self):
self.available_language_map = self.loader.get_locale_map()
self.search = _ExactLanguageSearch(self.loader)

def _get_candidate_languages(self, detected_language, languages):
candidates = []
if detected_language:
candidates.append(detected_language)

if isinstance(languages, (list, tuple, Set)) and len(languages) > 1:
candidates.extend(languages)

seen = set()
return [
language
for language in candidates
if not (language in seen or seen.add(language))
]

@apply_settings
def detect_language(
self, text, languages, settings=None, detect_languages_function=None
Expand Down Expand Up @@ -304,13 +319,23 @@ def search_dates(
settings=settings,
detect_languages_function=detect_languages_function,
)
if not language_shortname:

candidate_languages = self._get_candidate_languages(
language_shortname, languages
)
if not candidate_languages:
return {"Language": None, "Dates": None}

for candidate_language in candidate_languages:
dates = self.search.search_parse(
candidate_language, text, settings=settings
)
if dates:
return {"Language": candidate_language, "Dates": dates}

return {
"Language": language_shortname,
"Dates": self.search.search_parse(
language_shortname, text, settings=settings
),
"Dates": [],
}

def preprocess_text(self, text, languages):
Expand Down
6 changes: 6 additions & 0 deletions tests/test_search.py
Original file line number Diff line number Diff line change
Expand Up @@ -1020,6 +1020,12 @@ def test_detection(self, shortname, text):
settings={"STRICT_PARSING": True},
expected=None,
),
param(
text="Date de facture 23 juillet 2020 Condition Redevable livraison FR",
languages=["en", "fr", "es", "pt", "de", "it", "ar"],
settings={"STRICT_PARSING": True},
expected=[("23 juillet 2020", datetime.datetime(2020, 7, 23, 0, 0))],
),
param(text="a Americ", languages=None, settings=None, expected=None),
# Date with comma and apostrophe
param(
Expand Down
Loading