ci: Fix invalid escape sequences in Python code (#5802)

* ci: Use ruff in pre-commit to further limit complexity

* Fix invalid escape sequences in Python code

* Delete releasenotes/notes/ruff-4d2504d362035166.yaml

pyproject.toml

@@ -378,18 +378,38 @@ plugins = [
 ]
 
 [tool.ruff]
+select = [
+ "AIR", # Airflow
+ "ASYNC", # flake8-async
+ "C90", # McCabe cyclomatic complexity
+ "CPY", # flake8-copyright
+ "DJ", # flake8-django
+ "E501", # Long lines
+ "EXE", # flake8-executable
+ "FURB", # refurb
+ "INT", # flake8-gettext
+ "PL", # Pylint
+ "Q", # flake8-quotes
+ "SLOT", # flake8-slots
+ "T10", # flake8-debugger
+ "W", # pycodestyle
+ "YTT", # flake8-2020
+ # "E", # pycodestyle
+ # "F", # Pyflakes
+ # "NPY", # NumPy-specific rules
+ # "PD", # pandas-vet
+ # "PERF", # Perflint
+ # "PT", # flake8-pytest-style
+ # "UP", # pyupgrade
+]
+line-length = 1486
+target-version = "py38"
 ignore = [
  "PLR1714", # repeated-equality-comparison
  "PLR5501", # collapsible-else-if
  "PLW0603", # global-statement
  "PLW1510", # subprocess-run-without-check
  "PLW2901", # redefined-loop-name
- "W605", # invalid-escape-sequence
-]
-select = [
- "C90", # McCabe cyclomatic complexity
- "PL", # Pylint
- "W", # Pycodestyle warnings
 ]
 
 [tool.ruff.mccabe]

test/document_stores/test_opensearch.py

@@ -578,7 +578,7 @@ def test__validate_and_adjust_document_index_but_no_method(self, mocked_document
  assert mocked_document_store.space_type == "innerproduct"
  with pytest.raises(
  DocumentStoreError,
- match=f"Set `similarity` to one of '\['l2'\]' to properly use the embedding field 'embedding' of index '{self.index_name}'. Similarity 'dot_product' is not compatible with embedding field's space type 'l2', it requires 'innerproduct'.",
+ match=rf"Set `similarity` to one of '\['l2'\]' to properly use the embedding field 'embedding' of index '{self.index_name}'. Similarity 'dot_product' is not compatible with embedding field's space type 'l2', it requires 'innerproduct'.",
  ):
  mocked_document_store._validate_and_adjust_document_index(self.index_name)
 
@@ -597,7 +597,7 @@ def test__validate_and_adjust_document_index_similarity_mismatch(self, mocked_do
 
  with pytest.raises(
  DocumentStoreError,
- match=f"Set `similarity` to one of '\['dot_product'\]' to properly use the embedding field 'embedding' of index '{self.index_name}'. Similarity 'dot_product' is not compatible with embedding field's space type 'innerproduct', it requires 'cosinesimil'.",
+ match=rf"Set `similarity` to one of '\['dot_product'\]' to properly use the embedding field 'embedding' of index '{self.index_name}'. Similarity 'dot_product' is not compatible with embedding field's space type 'innerproduct', it requires 'cosinesimil'.",
  ):
  mocked_document_store._validate_and_adjust_document_index(self.index_name)
 

test/document_stores/test_pinecone.py

@@ -331,7 +331,7 @@ def test_get_all_documents_extended_filter_compound_dates_and_other_field_explic
  }
  }
 
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]te' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]te' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters)
 
  @pytest.mark.integration
@@ -343,7 +343,7 @@ def test_get_all_documents_extended_filter_compound_dates_and_other_field_simpli
  "name": ["file_5.txt", "file_3.txt"],
  }
 
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]te' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]te' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters_simplified)
 
  @pytest.mark.integration
@@ -357,7 +357,7 @@ def test_get_all_documents_extended_filter_compound_dates_and_or_explicit(
  }
  }
 
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]te' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]te' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters)
 
  @pytest.mark.integration
@@ -369,7 +369,7 @@ def test_get_all_documents_extended_filter_compound_dates_and_or_simplified(
  "$or": {"name": ["file_5.txt", "file_3.txt"], "numeric_field": {"$lte": 5.0}},
  }
 
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]te' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]te' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters_simplified)
 
  @pytest.mark.integration
@@ -385,7 +385,7 @@ def test_get_all_documents_extended_filter_compound_dates_and_or_and_not_explici
  },
  }
  }
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]te' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]te' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters)
 
  @pytest.mark.integration
@@ -399,7 +399,7 @@ def test_get_all_documents_extended_filter_compound_dates_and_or_and_not_simplif
  "$and": {"numeric_field": {"$lte": 5.0}, "$not": {"meta_field": "test-2"}},
  },
  }
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]te' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]te' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters_simplified)
 
  @pytest.mark.integration
@@ -413,7 +413,7 @@ def test_get_all_documents_extended_filter_compound_nested_not(self, doc_store_w
  }
  }
  }
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]t' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]t' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters)
 
  @pytest.mark.integration
@@ -428,7 +428,7 @@ def test_get_all_documents_extended_filter_compound_same_level_not(
  ]
  }
 
- with pytest.raises(FilterError, match="Comparison value for '\$[l|g]te' operation must be a float or int."):
+ with pytest.raises(FilterError, match=r"Comparison value for '\$[l|g]te' operation must be a float or int."):
  doc_store_with_docs.get_all_documents(filters=filters)
 
  @pytest.mark.integration

test/nodes/test_generator.py

@@ -77,7 +77,7 @@ def test_openai_answer_generator_custom_template(haystack_openai_config, docs):
 
  lfqa_prompt = PromptTemplate(
  """Synthesize a comprehensive answer from your knowledge and the following topk most relevant paragraphs and
- the given question.\n===\Paragraphs: {context}\n===\n{query}"""
+ the given question.\n===\\Paragraphs: {context}\n===\n{query}"""
  )
  node = OpenAIAnswerGenerator(
  api_key=haystack_openai_config["api_key"],

test/nodes/test_image_to_text.py

@@ -88,6 +88,6 @@ def test_image_to_text_not_image_document(image_to_text):
 def test_image_to_text_unsupported_model_after_loading():
  with pytest.raises(
  ValueError,
- match="The model 'deepset/minilm-uncased-squad2' \(class 'BertForQuestionAnswering'\) is not supported for ImageToText",
+ match=r"The model 'deepset/minilm-uncased-squad2' \(class 'BertForQuestionAnswering'\) is not supported for ImageToText",
  ):
  _ = TransformersImageToText(model_name_or_path="deepset/minilm-uncased-squad2")

test/nodes/test_shaper.py

@@ -829,7 +829,7 @@ def test_strings_to_answers_yaml(tmp_path):
 def test_strings_to_answers_with_reference_meta_yaml(tmp_path):
  with open(tmp_path / "tmp_config.yml", "w") as tmp_file:
  tmp_file.write(
- f"""
+ rf"""
  version: ignore
  components:
  - name: shaper

test/pipelines/test_pipeline_yaml.py

@@ -1122,7 +1122,7 @@ def run_batch(self):
 
  with open(tmp_path / "tmp_config.yml", "w", encoding="utf-8") as tmp_file:
  tmp_file.write(
- f"""
+ rf"""
  version: '1.9.0'
 
  components: