# ============================================================ # Project: EDGAR Research Database # Description: SEC EDGAR Research Infrastructure # # Authors: # - Manel Kammoun — manel.kammoun@uqo.ca # - Djerrycharli Tandjambianda — djerrycharli.tandjambianda@uqo.ca # - Simon-Pierre Boucher — simon-pierre.boucher@uqo.ca # # Institution: # Université du Québec en Outaouais (UQO) # # License: # Research / Academic Use # ============================================================ from pathlib import Path PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent DATA_DIRS = { "raw": PROJECT_ROOT / "data" / "raw" / "sec", "processed": PROJECT_ROOT / "data" / "processed", "parquet": PROJECT_ROOT / "data" / "parquet", "duckdb": PROJECT_ROOT / "data" / "duckdb", "embeddings": PROJECT_ROOT / "data" / "embeddings", "metadata": PROJECT_ROOT / "data" / "metadata", "logs": PROJECT_ROOT / "data" / "logs", } CONFIG_DIR = PROJECT_ROOT / "config" SEC_BASE_URL = "https://www.sec.gov" SEC_ARCHIVES_URL = "https://www.sec.gov/Archives/edgar/data" SEC_SUBMISSIONS_URL = "https://data.sec.gov/submissions" SEC_FULL_TEXT_URL = "https://efts.sec.gov/LATEST/search-index" SEC_COMPANY_TICKERS_URL = "https://www.sec.gov/files/company_tickers.json" SEC_FORM_TYPES = ["10-K", "10-Q", "8-K"] SEC_FORM_TYPES_EXTENDED = [ "10-K", "10-Q", "8-K", "DEF 14A", "S-1", "13F-HR", "10-K/A", "10-Q/A", "8-K/A", ] FORM_10K_SECTIONS = { "1": "business", "1A": "risk_factors", "1B": "unresolved_staff_comments", "2": "properties", "3": "legal_proceedings", "4": "mine_safety", "5": "market_for_equity", "6": "selected_financial_data", "7": "md_and_a", "7A": "quantitative_disclosures", "8": "financial_statements", "9": "changes_in_accounting", "9A": "controls_and_procedures", "9B": "other_information", } FORM_10Q_SECTIONS = { "P1_1": "financial_statements", "P1_2": "md_and_a", "P1_3": "quantitative_disclosures", "P1_4": "controls_and_procedures", "P2_1": "legal_proceedings", "P2_1A": "risk_factors", "P2_2": "unregistered_sales", } DUCKDB_PATH = DATA_DIRS["duckdb"] / "edgar_research.duckdb" DEFAULT_START_YEAR = 2010 PARQUET_COMPRESSION = "zstd" PARQUET_COMPRESSION_LEVEL = 3