google/langextract

Pattern Findings

787 matches across 15 categories. Click a row to expand file-level details.

Hyper-Verbose Identifiers463 hits · 448 pts

Severity	File	Line	Snippet
LOW	tests/chunking_test.py	69	def test_multi_sentence_chunk(self):
LOW	tests/chunking_test.py	96	def test_sentence_with_multiple_newlines_and_right_interval(self):
LOW	tests/chunking_test.py	164	def test_long_token_gets_own_chunk(self):
LOW	tests/chunking_test.py	207	def test_newline_at_chunk_boundary_does_not_create_empty_interval(self):
LOW	tests/chunking_test.py	261	def test_newlines_is_secondary_sentence_break(self):
LOW	tests/chunking_test.py	312	def test_tokenizer_propagation(self):
LOW	tests/chunking_test.py	425	def test_make_batches_of_textchunk(
LOW	tests/chunking_test.py	473	def test_text_chunk_additional_context(self):
LOW	tests/chunking_test.py	486	def test_chunk_iterator_without_additional_context(self):
LOW	tests/chunking_test.py	497	def test_multiple_chunks_with_additional_context(self):
LOW	tests/chunking_test.py	549	def test_text_chunk_properties(
LOW	tests/progress_test.py	27	def test_download_progress_bar(self):
LOW	tests/progress_test.py	37	def test_extraction_progress_bar(self):
LOW	tests/progress_test.py	47	def test_save_load_progress_bars(self):
LOW	tests/progress_test.py	57	def test_model_info_extraction(self):
LOW	tests/progress_test.py	68	def test_formatting_functions(self):
LOW	tests/format_handler_test.py	147	def test_end_to_end_integration_with_prompt_and_resolver(self):
LOW	tests/format_handler_test.py	232	def test_format_parse_roundtrip(
LOW	tests/format_handler_test.py	260	def test_think_tags_stripped_before_parsing(self):
LOW	tests/format_handler_test.py	276	def test_top_level_list_accepted_as_fallback(self):
LOW	tests/annotation_test.py	47	def assert_char_interval_match_source(
LOW	tests/annotation_test.py	80	def test_annotate_text_single_chunk(self):
LOW	tests/annotation_test.py	206	def test_annotate_text_without_index_suffix(self):
LOW	tests/annotation_test.py	325	def test_annotate_text_with_attributes_suffix(self):
LOW	tests/annotation_test.py	469	def test_annotate_text_multiple_chunks(self):
LOW	tests/annotation_test.py	569	def test_annotate_text_no_extractions(self):
LOW	tests/annotation_test.py	766	def test_annotate_documents_exceptions(
LOW	tests/annotation_test.py	817	def test_multipass_extraction_non_overlapping(self):
LOW	tests/annotation_test.py	867	def test_multipass_extraction_overlapping(self):
LOW	tests/annotation_test.py	918	def test_multipass_extraction_single_pass(self):
LOW	tests/annotation_test.py	948	def test_multipass_extraction_empty_passes(self):
LOW	tests/annotation_test.py	1052	def test_merge_non_overlapping_extractions(
LOW	tests/annotation_test.py	1160	def test_yields_documents_not_generators(self):
LOW	tests/annotation_test.py	1220	def test_context_window_includes_previous_chunk_text(self):
LOW	tests/annotation_test.py	1271	def test_no_context_included_when_disabled(self):
LOW	tests/annotation_test.py	1309	def test_context_window_per_document_isolation(self):
LOW	tests/schema_test.py	47	def _openai_attribute_properties(openai_schema, extraction_class):
LOW	tests/schema_test.py	56	def test_abstract_methods_required(self):
LOW	tests/schema_test.py	61	def test_subclass_must_implement_all_methods(self):
LOW	tests/schema_test.py	77	def test_get_schema_class_returns_none_by_default(self):
LOW	tests/schema_test.py	87	def test_apply_schema_stores_instance(self):
LOW	tests/schema_test.py	256	def test_from_examples_constructs_expected_schema(
LOW	tests/schema_test.py	263	def test_to_provider_config_returns_response_schema(self):
LOW	tests/schema_test.py	285	def test_requires_raw_output_returns_true(self):
LOW	tests/schema_test.py	306	def test_response_format_returns_json_schema_response_format(self):
LOW	tests/schema_test.py	339	def test_to_provider_config_uses_provider_schema_hook(self):
LOW	tests/schema_test.py	347	def test_from_examples_constructs_strict_openai_schema(self):
LOW	tests/schema_test.py	445	def test_from_examples_preserves_list_attribute_schema(self):
LOW	tests/schema_test.py	472	def test_from_examples_empty_examples_allow_empty_extraction_objects(self):
LOW	tests/schema_test.py	486	def test_validate_format_rejects_yaml(self):
LOW	tests/schema_test.py	497	def test_requires_raw_output_returns_true(self):
LOW	tests/schema_test.py	503	def test_validate_format_warns_when_fences_enabled(self):
LOW	tests/schema_test.py	516	def test_validate_format_warns_with_wrong_wrapper_key(self):
LOW	tests/schema_test.py	531	def test_from_examples_preserves_scalar_attribute_types(self):
LOW	tests/schema_test.py	568	def test_from_examples_preserves_mixed_numeric_attribute_types(self):
LOW	tests/schema_test.py	619	def test_from_examples_allows_none_attribute_values(self):
LOW	tests/schema_test.py	641	def test_from_examples_strict_false_emits_non_strict_response_format(self):
LOW	tests/schema_test.py	647	def test_response_format_returns_isolated_schema_dict(self):
LOW	tests/schema_test.py	658	def test_instance_is_frozen_and_dict_is_isolated(self):
LOW	tests/schema_test.py	748	def test_base_schema_no_validation(self):
403 more matches not shown…

Docstring Block Structure34 hits · 170 pts

Severity	File	Line	Snippet
HIGH	langextract/plugins.py	125	Load a provider class from module:Class specification. Args: spec: Import specification in format "module.path:Cl
HIGH	langextract/plugins.py	186	Get a provider class by name. Args: name: Provider name (e.g., "gemini", "openai", "ollama"). allow_override:
HIGH	langextract/annotation.py	124	Iterates over documents to yield text chunks along with the document ID. Args: documents: A sequence of Document
HIGH	langextract/annotation.py	222	Annotates a sequence of documents with NLP extractions. Breaks documents into chunks, processes them into prompts
HIGH	langextract/chunking.py	146	Creates a token interval. Args: start_index: first token's index (inclusive). end_index: last token's index +
HIGH	langextract/chunking.py	173	Get the text within an interval of tokens. Args: tokenized_text: Tokenized documents. token_interval: An inte
HIGH	langextract/chunking.py	220	Returns the char interval corresponding to the token interval. Args: tokenized_text: Document. token_interval
HIGH	langextract/chunking.py	247	Converts all whitespace characters in input text to a single space. Args: text: Input to sanitize. Returns:
HIGH	langextract/io.py	51	Loads the dataset from a CSV file. Args: delimiter: The delimiter to use when reading the CSV file. Yiel
HIGH	langextract/io.py	148	Loads annotated documents from a JSON Lines file. Args: jsonl_path: The file path to the JSON Lines file. sho
HIGH	langextract/io.py	198	Reads a CSV file and yields rows as dicts. Args: filepath: The path to the file. column_names: The names of t
HIGH	langextract/io.py	271	Download text content from a URL with optional progress bar. Args: url: The URL to download from. timeout: Re
HIGH	langextract/prompt_validation.py	134	Align extractions to their own example text and collect issues. Args: examples: The few-shot examples to validate
HIGH	langextract/prompting.py	56	Reads a structured prompt template from a file. Args: prompt_path: Path to a file containing PromptTemplateStruct
HIGH	langextract/factory.py	110	Create a language model instance from configuration. Args: config: Model configuration with optional model_id and
HIGH	langextract/factory.py	204	Internal helper to create a model with optional schema constraints. This function creates a language model and option
HIGH	langextract/extraction.py	66	Extracts structured information from text. Retrieves structured information from the provided text or documents using
HIGH	langextract/resolver.py	273	Runs resolve function on text with YAML/JSON extraction data. Args: input_text: The input text to be proces
HIGH	langextract/resolver.py	393	Parses a YAML or JSON-formatted string into extraction data. This method is kept for backward compatibility with te
HIGH	langextract/resolver.py	428	Extracts and orders extraction data based on their associated indexes. This function processes a list of dictionari
HIGH	langextract/core/base_model.py	157	Parses model output as JSON or YAML. Note: This expects raw JSON/YAML without code fences. Code fence extractio
HIGH	langextract/core/tokenizer.py	474	Reconstructs the substring of the original text spanning a given token interval. Args: tokenized_text: A Tokenize
HIGH	langextract/core/tokenizer.py	586	Finds a 'sentence' interval from a given start index. Sentence boundaries are defined by: - punctuation tokens in
HIGH	langextract/core/format_handler.py	154	Parse model output to extract data. Args: text: Raw model output. strict: If True, enforce strict schem
HIGH	langextract/core/format_handler.py	279	Extract content from text, handling fences if configured. Args: text: Input text that may contain fenced bloc
HIGH	langextract/providers/openai_batch.py	357	Execute batch inference on multiple prompts using OpenAI Batch API. Args: client: OpenAI client instance (or comp
HIGH	langextract/providers/router.py	140	Resolve a model ID to a provider class. Args: model_id: The model identifier to resolve. Returns: The prov
HIGH	langextract/providers/router.py	171	Resolve a provider name to a provider class. This allows explicit provider selection by name or class name. Args:
HIGH	langextract/providers/gemini_batch.py	317	Submit a file-based batch job to Vertex AI using GCS storage. Batch processing is only supported with Vertex AI becau
HIGH	langextract/providers/gemini_batch.py	552	Poll batch job until completion or timeout. Args: client: google.genai.Client instance for polling job status.
HIGH	langextract/providers/gemini_batch.py	629	Extract text outputs from file-based batch results, preserving order. Reads results from GCS output directory. Arg
HIGH	langextract/providers/gemini_batch.py	709	Execute batch inference on multiple prompts using the Vertex AI Batch API. This function provides file-based batch pr
HIGH	langextract/providers/ollama.py	561	Sends a prompt to an Ollama model and returns the generated response. Note: This is a low-level method. Constructor
HIGH	scripts/create_provider_plugin.py	240	\ """Schema implementation for {provider_name} provider.""" import langextract as lx from lange

Over-Commented Block107 hits · 101 pts

Severity	File	Line	Snippet
LOW	autoformat.sh	1	#!/bin/bash
LOW	.pre-commit-config.yaml	1	# Copyright 2025 Google LLC.
LOW	pyproject.toml	1	# Copyright 2025 Google LLC.
LOW	tox.ini	1	# Copyright 2025 Google LLC.
LOW	tests/chunking_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/progress_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/format_handler_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/annotation_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/schema_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/prompting_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/inference_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/provider_schema_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/extract_precedence_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/resolver_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/resolver_test.py	661	extraction_text="prednisone",
LOW	tests/fuzzy_alignment_cases_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/test_kwargs_passthrough.py	1	# Copyright 2025 Google LLC.
LOW	tests/gemini_retry_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/data_lib_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/init_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/openai_batch_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/registry_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/tokenizer_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/extract_schema_integration_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/prompt_validation_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/factory_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/visualization_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/io_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/provider_plugin_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/factory_schema_test.py	1	# Copyright 2025 Google LLC.
LOW	tests/test_live_api.py	1	# Copyright 2025 Google LLC.
LOW	tests/test_ollama_integration.py	1	# Copyright 2025 Google LLC.
LOW	tests/test_gemini_batch_api.py	1	# Copyright 2025 Google LLC.
LOW	langextract/plugins.py	1	# Copyright 2025 Google LLC.
LOW	langextract/annotation.py	1	# Copyright 2025 Google LLC.
LOW	langextract/chunking.py	1	# Copyright 2025 Google LLC.
LOW	langextract/registry.py	1	# Copyright 2025 Google LLC.
LOW	langextract/data_lib.py	1	# Copyright 2025 Google LLC.
LOW	langextract/io.py	1	# Copyright 2025 Google LLC.
LOW	langextract/prompt_validation.py	1	# Copyright 2025 Google LLC.
LOW	langextract/prompting.py	1	# Copyright 2025 Google LLC.
LOW	langextract/__init__.py	1	# Copyright 2025 Google LLC.
LOW	langextract/visualization.py	1	# Copyright 2025 Google LLC.
LOW	langextract/factory.py	1	# Copyright 2025 Google LLC.
LOW	langextract/tokenizer.py	1	# Copyright 2025 Google LLC.
LOW	langextract/extraction.py	1	# Copyright 2025 Google LLC.
LOW	langextract/resolver.py	1	# Copyright 2025 Google LLC.
LOW	langextract/inference.py	1	# Copyright 2025 Google LLC.
LOW	langextract/exceptions.py	1	# Copyright 2025 Google LLC.
LOW	langextract/progress.py	1	# Copyright 2025 Google LLC.
LOW	langextract/data.py	1	# Copyright 2025 Google LLC.
LOW	langextract/schema.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/__init__.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/types.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/base_model.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/tokenizer.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/format_handler.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/exceptions.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/data.py	1	# Copyright 2025 Google LLC.
LOW	langextract/core/schema.py	1	# Copyright 2025 Google LLC.
47 more matches not shown…

Cross-File Repetition12 hits · 60 pts

Severity	File	Snippet
HIGH	tests/test_live_api.py	\ extract medication information including medication name, dosage, route, frequency, and duration in the order they app
HIGH	tests/test_live_api.py	\ extract medication information including medication name, dosage, route, frequency, and duration in the order they app
HIGH	tests/test_live_api.py	\ extract medication information including medication name, dosage, route, frequency, and duration in the order they app
HIGH	tests/test_live_api.py	\ extract medication information including medication name, dosage, route, frequency, and duration in the order they app
HIGH	tests/test_live_api.py	the patient was prescribed lisinopril and metformin last month. he takes the lisinopril 10mg daily for hypertension, but
HIGH	tests/test_live_api.py	the patient was prescribed lisinopril and metformin last month. he takes the lisinopril 10mg daily for hypertension, but
HIGH	docs/examples/medication_examples.md	the patient was prescribed lisinopril and metformin last month. he takes the lisinopril 10mg daily for hypertension, but
HIGH	examples/ollama/demo_ollama.py	the patient was prescribed lisinopril and metformin last month. he takes the lisinopril 10mg daily for hypertension, but
HIGH	tests/test_live_api.py	extract medications with their details, using attributes to group related information: 1. extract entities in the order
HIGH	tests/test_live_api.py	extract medications with their details, using attributes to group related information: 1. extract entities in the order
HIGH	docs/examples/medication_examples.md	extract medications with their details, using attributes to group related information: 1. extract entities in the order
HIGH	examples/ollama/demo_ollama.py	extract medications with their details, using attributes to group related information: 1. extract entities in the order

Unused Imports48 hits · 48 pts

Severity	File	Line
LOW	tests/openai_batch_test.py	19
LOW	langextract/plugins.py	20
LOW	langextract/registry.py	21
LOW	langextract/data_lib.py	16
LOW	langextract/io.py	16
LOW	langextract/prompt_validation.py	17
LOW	langextract/prompting.py	16
LOW	langextract/__init__.py	21
LOW	langextract/visualization.py	24
LOW	langextract/factory.py	22
LOW	langextract/tokenizer.py	21
LOW	langextract/tokenizer.py	25
LOW	langextract/extraction.py	17
LOW	langextract/resolver.py	21
LOW	langextract/inference.py	21
LOW	langextract/exceptions.py	22
LOW	langextract/progress.py	16
LOW	langextract/data.py	21
LOW	langextract/data.py	25
LOW	langextract/schema.py	21
LOW	langextract/core/__init__.py	22
LOW	langextract/core/types.py	16
LOW	langextract/core/base_model.py	16
LOW	langextract/core/format_handler.py	17
LOW	langextract/core/exceptions.py	21
LOW	langextract/core/data.py	16
LOW	langextract/core/schema.py	16
LOW	langextract/core/debug_utils.py	16
LOW	langextract/providers/openai_batch.py	22
LOW	langextract/providers/gemini.py	19
LOW	langextract/providers/openai.py	18
LOW	langextract/providers/router.py	22
LOW	langextract/providers/gemini_batch.py	25
LOW	langextract/providers/ollama.py	84
LOW	langextract/providers/schemas/__init__.py	16
LOW	langextract/providers/schemas/gemini.py	18
LOW	langextract/providers/schemas/openai.py	18
LOW	langextract/_compat/registry.py	18
LOW	langextract/_compat/__init__.py	21
LOW	langextract/_compat/inference.py	17
LOW	langextract/_compat/exceptions.py	18
LOW	langextract/_compat/schema.py	18
LOW	…amples/custom_provider_plugin/test_example_provider.py	24
LOW	…ovider_plugin/langextract_provider_example/provider.py	17
LOW	…ovider_plugin/langextract_provider_example/__init__.py	17
LOW	…provider_plugin/langextract_provider_example/schema.py	17
LOW	benchmarks/fuzzy_benchmark.py	29
LOW	scripts/validate_community_providers.py	18

Excessive Try-Catch Wrapping44 hits · 45 pts

Severity	File	Line	Snippet
LOW	tests/prompt_validation_test.py	457	except Exception: # pylint: disable=broad-except
LOW	tests/prompt_validation_test.py	505	except Exception: # pylint: disable=broad-except
LOW	tests/prompt_validation_test.py	526	except Exception: # pylint: disable=broad-except
LOW	langextract/prompting.py	78	except Exception as e:
LOW	langextract/visualization.py	59	except Exception:
LOW	langextract/resolver.py	420	except Exception as e:
LOW	langextract/core/base_model.py	179	except Exception as e:
LOW	langextract/core/debug_utils.py	89	except Exception:
LOW	langextract/core/debug_utils.py	129	except Exception:
LOW	langextract/core/debug_utils.py	184	except Exception:
LOW	langextract/providers/openai_batch.py	253	except Exception as e:
LOW	langextract/providers/openai_batch.py	277	except Exception as e:
LOW	langextract/providers/openai_batch.py	313	except Exception as e:
LOW	langextract/providers/openai_batch.py	444	except Exception as e:
LOW	langextract/providers/openai_batch.py	470	except Exception as e:
LOW	langextract/providers/openai_batch.py	496	except Exception as e:
LOW	langextract/providers/openai_batch.py	508	except Exception as e:
LOW	langextract/providers/__init__.py	134	except Exception as e:
LOW	langextract/providers/__init__.py	139	except Exception as e:
LOW	langextract/providers/gemini.py	361	except Exception as e:
LOW	langextract/providers/gemini.py	441	except Exception as e:
LOW	langextract/providers/gemini.py	478	except Exception as e:
LOW	langextract/providers/openai.py	258	except Exception as e:
LOW	langextract/providers/openai.py	337	except Exception as e:
LOW	langextract/providers/openai.py	375	except Exception as e:
LOW	langextract/providers/gemini_batch.py	172	except Exception:
LOW	langextract/providers/gemini_batch.py	253	except Exception as e:
LOW	langextract/providers/gemini_batch.py	416	except Exception as e:
LOW	langextract/providers/gemini_batch.py	457	except Exception as e:
LOW	langextract/providers/gemini_batch.py	468	except Exception as e:
LOW	langextract/providers/gemini_batch.py	586	except Exception as e:
LOW	langextract/providers/gemini_batch.py	837	except Exception as e:
LOW	langextract/providers/ollama.py	313	except Exception as e:
LOW	…ovider_plugin/langextract_provider_example/provider.py	181	except Exception as e:
LOW	examples/ollama/demo_ollama.py	452	except Exception as e:
LOW	examples/ollama/demo_ollama.py	533	except Exception as e:
MEDIUM	benchmarks/plotting.py	339	print(f"Error loading {json_file}: {e}")
LOW	scripts/create_provider_plugin.py	375	except Exception as e:
LOW	scripts/create_provider_plugin.py	393	except Exception:
LOW	scripts/create_provider_plugin.py	395	except Exception as e:
LOW	scripts/create_provider_plugin.py	429	except Exception as e:
LOW	scripts/create_provider_plugin.py	444	except Exception as e:
LOW	.github/scripts/zenodo_publish.py	211	except Exception as e:
MEDIUM	.github/scripts/zenodo_publish.py	180	def main() -> int:

Magic Placeholder Names9 hits · 42 pts

Severity	File	Line	Snippet
HIGH	README.md	206	docker run --rm -e LANGEXTRACT_API_KEY="your-api-key" langextract python your_script.py
HIGH	README.md	229	export LANGEXTRACT_API_KEY="your-api-key-here"
HIGH	README.md	239	LANGEXTRACT_API_KEY=your-api-key-here
HIGH	README.md	268	api_key="your-api-key-here" # Only use this for testing/development
HIGH	docs/examples/medication_examples.md	51	api_key="your-api-key-here" # Optional if LANGEXTRACT_API_KEY environment variable is set
HIGH	docs/examples/medication_examples.md	171	api_key="your-api-key-here" # Optional if LANGEXTRACT_API_KEY environment variable is set
HIGH	docs/examples/japanese_extraction.md	43	api_key="your-api-key-here" # Optional if env var is set
HIGH	examples/custom_provider_plugin/README.md	125	provider_kwargs={"api_key": "your-api-key"},
HIGH	examples/custom_provider_plugin/README.md	142	provider_kwargs={"api_key": "your-api-key"},

Deep Nesting37 hits · 37 pts

Severity	File	Line
LOW	tests/extract_schema_integration_test.py	113
LOW	tests/extract_schema_integration_test.py	147
LOW	langextract/annotation.py	46
LOW	langextract/annotation.py	285
LOW	langextract/data_lib.py	27
LOW	langextract/io.py	85
LOW	langextract/io.py	265
LOW	langextract/prompt_validation.py	128
LOW	langextract/prompting.py	52
LOW	langextract/factory.py	53
LOW	langextract/extraction.py	36
LOW	langextract/resolver.py	1075
LOW	langextract/resolver.py	424
LOW	langextract/resolver.py	578
LOW	langextract/core/tokenizer.py	580
LOW	langextract/core/tokenizer.py	336
LOW	langextract/core/format_handler.py	151
LOW	langextract/providers/openai_batch.py	411
LOW	langextract/providers/__init__.py	74
LOW	langextract/providers/__init__.py	152
LOW	langextract/providers/gemini.py	337
LOW	langextract/providers/gemini.py	381
LOW	langextract/providers/openai.py	284
LOW	langextract/providers/router.py	170
LOW	langextract/providers/gemini_batch.py	623
LOW	langextract/providers/gemini_batch.py	442
LOW	langextract/providers/schemas/gemini.py	98
LOW	langextract/providers/schemas/openai.py	81
LOW	examples/ollama/demo_ollama.py	418
LOW	benchmarks/benchmark.py	140
LOW	benchmarks/benchmark.py	276
LOW	benchmarks/benchmark.py	311
LOW	benchmarks/fuzzy_benchmark.py	342
LOW	benchmarks/plotting.py	170
LOW	benchmarks/plotting.py	220
LOW	benchmarks/plotting.py	376
LOW	benchmarks/plotting.py	492

Self-Referential Comments9 hits · 25 pts

Severity	File	Line	Snippet
MEDIUM	tests/annotation_test.py	701	# Define a side effect function so return length based on batch length.
MEDIUM	tests/resolver_test.py	2010	# Define a chunk that includes the entire text.
MEDIUM	tests/resolver_test.py	2052	# Define a chunk that includes the entire text.
MEDIUM	tests/resolver_test.py	2098	# Define a chunk that includes too many tokens.
MEDIUM	tests/resolver_test.py	2139	# Define a correct chunk.
MEDIUM	tests/resolver_test.py	2166	# Define a chunk that includes the entire text.
MEDIUM	tests/extract_schema_integration_test.py	188	# Create a mock instance with required attributes
MEDIUM	tests/extract_schema_integration_test.py	239	# Create a mock Gemini schema with validate_format that issues warnings
MEDIUM	langextract/providers/ollama.py	24	# Create an example for few-shot learning

Decorative Section Separators5 hits · 21 pts

Severity	File	Line	Snippet
MEDIUM	tests/annotation_test.py	503	# -------------------------------------------------------------------------
MEDIUM	tests/resolver_test.py	667	# --------------------------------------------------------------------
MEDIUM	tests/resolver_test.py	670	# --------------------------------------------------------------------
MEDIUM	tests/resolver_test.py	673	# --------------------------------------------------------------------
MEDIUM	tests/resolver_test.py	676	# --------------------------------------------------------------------

Fake / Example Data12 hits · 12 pts

Severity	File	Line	Snippet
LOW	tests/annotation_test.py	91	- patient: "Jane Doe"
LOW	tests/annotation_test.py	118	extraction_text="Jane Doe",
LOW	tests/annotation_test.py	217	- patient: "Jane Doe"
LOW	tests/annotation_test.py	237	extraction_text="Jane Doe",
LOW	tests/annotation_test.py	336	- patient: "Jane Doe"
LOW	tests/annotation_test.py	371	extraction_text="Jane Doe",
LOW	tests/schema_test.py	217	extraction_text="John Doe",
LOW	tests/resolver_test.py	413	"patient": "Jane Doe",
LOW	tests/resolver_test.py	430	extraction_text="Jane Doe",
LOW	tests/resolver_test.py	454	"patient": "John Doe",
LOW	tests/resolver_test.py	493	extraction_text="John Doe",
LOW	tests/tokenizer_test.py	812	expected_substring="Jane Doe",

Hallucination Indicators1 hit · 10 pts

Severity	File	Line	Snippet
CRITICAL	langextract/_compat/README.md	16	- `from langextract.inference import InferenceOutputError` → `from langextract.core.exceptions import InferenceOutputErr

Cross-Language Confusion2 hits · 8 pts

Severity	File	Line	Snippet
HIGH	tests/test_kwargs_passthrough.py	700	"""Format key should be omitted from payload when None (not sent as null)."""
HIGH	langextract/visualization.py	492	let animationInterval = null;

AI Slop Vocabulary2 hits · 4 pts

Severity	File	Line	Snippet
MEDIUM	langextract/core/tokenizer.py	278	# Fallback to the robust regex method
MEDIUM	benchmarks/plotting.py	37	"""Generate comprehensive benchmark visualization.

Redundant / Tautological Comments2 hits · 3 pts

Severity	File	Line	Snippet
LOW	langextract/core/base_model.py	171	# Check if we have a format_type attribute (providers should set this)
LOW	langextract/providers/gemini_batch.py	236	# Check if rule already exists

Score History

Severity Breakdown

Pattern Findings