Re-exports§
pub use engines::columnar::ArrowProfiler;pub use api::DataProfiler;pub use api::quick_quality_check;pub use api::stream_profile;pub use core::batch::BatchConfig;pub use core::batch::BatchProcessor;pub use core::batch::BatchResult;pub use core::batch::BatchSummary;pub use core::errors::DataProfilerError;pub use core::errors::ErrorSeverity;pub use core::sampling::ChunkSize;pub use core::sampling::SamplingStrategy;pub use parsers::robust_csv::CsvDiagnostics;pub use core::config::DataprofConfig;pub use core::config::DataprofConfigBuilder;pub use core::exit_codes;pub use core::validation::InputValidator;pub use core::validation::ValidationError;pub use engines::streaming::ProgressInfo;pub use engines::AdaptiveProfiler;pub use engines::EnginePerformance;pub use engines::ProcessingType;pub use engines::DataFusionLoader;pub use output::html::generate_html_report;pub use types::ColumnProfile;pub use types::ColumnStats;pub use types::DataFrameLibrary;pub use types::DataQualityMetrics;pub use types::DataSource;pub use types::DataType;pub use types::FileFormat;pub use types::OutputFormat;pub use types::Pattern;pub use types::QualityReport;pub use types::QueryEngine;pub use types::ScanInfo;pub use parsers::csv::analyze_csv;pub use parsers::csv::analyze_csv_fast;pub use parsers::csv::analyze_csv_robust;pub use parsers::csv::analyze_csv_with_sampling;pub use parsers::csv::analyze_csv_with_verbosity;pub use parsers::json::analyze_json;pub use parsers::json::analyze_json_with_quality;pub use parsers::parquet::ParquetConfig;pub use parsers::parquet::analyze_parquet_with_config;pub use parsers::parquet::analyze_parquet_with_quality;pub use parsers::parquet::is_parquet_file;pub use analysis::MetricsCalculator;pub use analysis::analyze_column_fast;pub use analysis::detect_patterns;pub use analysis::infer_type;pub use stats::calculate_numeric_stats;pub use stats::calculate_text_stats;pub use database::DatabaseConfig;pub use database::DatabaseConnector;pub use database::DatabaseCredentials;pub use database::MySqlConnector;pub use database::PostgresConnector;pub use database::RetryConfig;pub use database::SamplingConfig;pub use database::SamplingStrategy as DbSamplingStrategy;pub use database::SqliteConnector;pub use database::SslConfig;pub use database::analyze_database;pub use database::create_connector;
Modules§
- acceleration
- analysis
- api
- core
- database
- Database connectivity module for DataProfiler
- engines
- output
- parsers
- python
- serde_
helpers - Custom serde serialization helpers for formatting numeric values with appropriate precision
- stats
- types
Macros§
- process_
rows_ to_ columns - Macro to process rows into column-oriented HashMap. Used for single-query (non-streaming) profiling.
- streaming_
profile_ loop - Macro to generate the streaming batch loop for profiling queries. Handles the common pattern while allowing database-specific pool types. Includes inline row processing to avoid complex generic trait bounds.
Functions§
- check_
memory_ leaks - Global memory leak detection utility
- get_
memory_ usage_ stats - Get global memory usage statistics