mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-11 19:11:19 +00:00
3a03fce71c
* ruff settings enable ruff format and re-format outdated files feat: `EvaluationRunResult` add parameter to specify columns to keep in the comparative `Dataframe` (#7879) * adding param to explictily state which cols to keep * adding param to explictily state which cols to keep * adding param to explictily state which cols to keep * updating tests * adding release notes * Update haystack/evaluation/eval_run_result.py Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com> * Update releasenotes/notes/add-keep-columns-to-EvalRunResult-comparative-be3e15ce45de3e0b.yaml Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com> * updating docstring --------- Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com> add format-check fail on format and linting failures fix string formatting reformat long lines fix tests fix typing linter pull from main * reformat * lint -> check * lint -> check
57 lines
2.3 KiB
Python
57 lines
2.3 KiB
Python
# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
|
|
#
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
import logging
|
|
import pytest
|
|
from _pytest.logging import LogCaptureFixture
|
|
|
|
from haystack import Document
|
|
from haystack.components.routers import TextLanguageRouter
|
|
|
|
|
|
class TestTextLanguageRouter:
|
|
def test_non_string_input(self):
|
|
with pytest.raises(TypeError, match="TextLanguageRouter expects a string as input."):
|
|
classifier = TextLanguageRouter()
|
|
classifier.run(text=Document(content="This is an english sentence."))
|
|
|
|
def test_list_of_string(self):
|
|
with pytest.raises(TypeError, match="TextLanguageRouter expects a string as input."):
|
|
classifier = TextLanguageRouter()
|
|
classifier.run(text=["This is an english sentence."])
|
|
|
|
def test_empty_string(self):
|
|
classifier = TextLanguageRouter()
|
|
result = classifier.run(text="")
|
|
assert result == {"unmatched": ""}
|
|
|
|
def test_detect_language(self):
|
|
classifier = TextLanguageRouter()
|
|
detected_language = classifier._detect_language("This is an english sentence.")
|
|
assert detected_language == "en"
|
|
|
|
def test_route_to_en(self):
|
|
classifier = TextLanguageRouter()
|
|
english_sentence = "This is an english sentence."
|
|
result = classifier.run(text=english_sentence)
|
|
assert result == {"en": english_sentence}
|
|
|
|
def test_route_to_unmatched(self):
|
|
classifier = TextLanguageRouter()
|
|
german_sentence = "Ein deutscher Satz ohne Verb."
|
|
result = classifier.run(text=german_sentence)
|
|
assert result == {"unmatched": german_sentence}
|
|
|
|
def test_warning_if_no_language_detected(self, caplog: LogCaptureFixture):
|
|
with caplog.at_level(logging.WARNING):
|
|
classifier = TextLanguageRouter()
|
|
classifier.run(text=".")
|
|
assert "Langdetect cannot detect the language of text. Error: No features in text." in caplog.text
|
|
|
|
def test_warning_if_no_language_detected_if_debug(self, caplog: LogCaptureFixture):
|
|
with caplog.at_level(logging.DEBUG):
|
|
classifier = TextLanguageRouter()
|
|
classifier.run(text=".")
|
|
assert "Langdetect cannot detect the language of text. Error: No features in text." in caplog.text
|
|
assert "Langdetect cannot detect the language of text: ." in caplog.text
|