Files
hk-ipo/schema/hk_ipo.schema.sql
T
geometrybase 08db218b6d Add archivist incremental sync state
Request:
Add archivist support for remembering which IPO archive stages have already been synced and which stages should be updated next.

Changes:
- Add sync_runs, ticker_sync_state, sync_tasks, and price_performance tables to the archive schema.
- Add scripts/update_sync_state.py to derive per-ticker stage status and rebuild the next-sync task queue.
- Export the new sync-state tables as Git-friendly CSV snapshots.
- Document the incremental archive flow in the archivist skill and README.

Verification:
- Ran scripts/bootstrap_historical_data.py.
- Ran scripts/update_sync_state.py with a deterministic as-of timestamp.
- Checked SQLite integrity and DB-to-snapshot row counts with Python sqlite3.
- Parsed Python scripts with ast.parse.
- Ran git diff --check and checked for temporary SQLite/cache files.

Next useful context:
- Current derived queue has 2 open tasks for 06658 and 15 waiting_until_due tasks for future stages.
2026-06-15 06:29:54 +00:00

143 lines
3.9 KiB
SQL

PRAGMA foreign_keys = ON;
CREATE TABLE IF NOT EXISTS ipo_master (
ticker TEXT PRIMARY KEY,
company_name_en TEXT NOT NULL,
company_name_zh TEXT,
stock_short_name TEXT,
exchange TEXT NOT NULL DEFAULT 'HKEX',
board TEXT NOT NULL DEFAULT 'Main Board',
status TEXT NOT NULL,
listing_date TEXT,
application_start_date TEXT,
application_end_date TEXT,
allotment_results_expected_date TEXT,
industry_label TEXT,
data_as_of TEXT NOT NULL,
notes TEXT
);
CREATE TABLE IF NOT EXISTS offering_terms (
ticker TEXT PRIMARY KEY REFERENCES ipo_master(ticker),
source_id TEXT NOT NULL,
prospectus_date TEXT,
offer_price_hkd REAL,
board_lot INTEGER,
min_subscription_amount_hkd REAL,
global_offer_shares INTEGER,
hk_offer_shares_initial INTEGER,
international_offer_shares_initial INTEGER,
public_offer_pct_initial REAL,
over_allotment_offer_shares INTEGER,
offer_size_adjustment_offer_shares INTEGER,
market_cap_hkd_m REAL,
gross_proceeds_hkd_m REAL,
net_proceeds_hkd_m REAL,
issued_shares_upon_listing INTEGER,
data_as_of TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS ipo_demand (
demand_id TEXT PRIMARY KEY,
ticker TEXT NOT NULL REFERENCES ipo_master(ticker),
source_id TEXT NOT NULL,
stage_date TEXT NOT NULL,
valid_applications INTEGER,
successful_applications INTEGER,
public_oversubscription_times REAL,
international_placees INTEGER,
international_oversubscription_times REAL,
final_hk_offer_shares INTEGER,
final_international_offer_shares INTEGER,
data_as_of TEXT NOT NULL,
notes TEXT
);
CREATE TABLE IF NOT EXISTS price_performance (
performance_id TEXT PRIMARY KEY,
ticker TEXT NOT NULL REFERENCES ipo_master(ticker),
stage TEXT NOT NULL,
source_id TEXT,
as_of_date TEXT NOT NULL,
open_price_hkd REAL,
high_price_hkd REAL,
low_price_hkd REAL,
close_price_hkd REAL,
return_pct REAL,
turnover_hkd_m REAL,
data_as_of TEXT NOT NULL,
notes TEXT,
UNIQUE (ticker, stage)
);
CREATE TABLE IF NOT EXISTS source_refs (
source_id TEXT PRIMARY KEY,
ticker TEXT NOT NULL REFERENCES ipo_master(ticker),
source_type TEXT NOT NULL,
title TEXT NOT NULL,
path_base TEXT NOT NULL DEFAULT 'repo_root',
local_path TEXT NOT NULL,
url TEXT NOT NULL,
file_sha256 TEXT,
source_date TEXT,
archived_at TEXT NOT NULL,
notes TEXT,
CHECK (path_base = 'repo_root'),
CHECK (local_path NOT LIKE '/%'),
CHECK (local_path NOT LIKE './%'),
CHECK (local_path NOT LIKE '%\%')
);
CREATE TABLE IF NOT EXISTS data_gaps (
gap_id TEXT PRIMARY KEY,
ticker TEXT NOT NULL REFERENCES ipo_master(ticker),
stage TEXT NOT NULL,
field_name TEXT NOT NULL,
reason TEXT NOT NULL,
expected_resolution_date TEXT,
created_at TEXT NOT NULL,
notes TEXT
);
CREATE TABLE IF NOT EXISTS sync_runs (
sync_run_id TEXT PRIMARY KEY,
mode TEXT NOT NULL,
as_of TEXT NOT NULL,
started_at TEXT NOT NULL,
finished_at TEXT,
status TEXT NOT NULL,
notes TEXT,
CHECK (status IN ('running', 'complete', 'failed'))
);
CREATE TABLE IF NOT EXISTS ticker_sync_state (
ticker TEXT NOT NULL REFERENCES ipo_master(ticker),
stage TEXT NOT NULL,
status TEXT NOT NULL,
required INTEGER NOT NULL DEFAULT 1,
due_date TEXT,
completed_at TEXT,
last_source_id TEXT,
data_gap_id TEXT,
last_sync_run_id TEXT REFERENCES sync_runs(sync_run_id),
updated_at TEXT NOT NULL,
notes TEXT,
PRIMARY KEY (ticker, stage),
CHECK (status IN ('complete', 'pending_not_due', 'pending_due', 'blocked', 'not_applicable')),
CHECK (required IN (0, 1))
);
CREATE TABLE IF NOT EXISTS sync_tasks (
task_id TEXT PRIMARY KEY,
ticker TEXT NOT NULL REFERENCES ipo_master(ticker),
stage TEXT NOT NULL,
task_type TEXT NOT NULL,
task_status TEXT NOT NULL,
due_date TEXT,
data_gap_id TEXT,
last_sync_run_id TEXT REFERENCES sync_runs(sync_run_id),
updated_at TEXT NOT NULL,
notes TEXT,
CHECK (task_status IN ('open', 'waiting_until_due', 'blocked'))
);