geometrybase/hk-ipo
Private
Public Access
0
0
Fork 0
Code Activity
Files
222f55c1409fc8f0917cd43edcec49cdb56eeedd
hk-ipo/scripts/bootstrap_historical_data.py
T
geometrybase c65b20a1c4 Archive recent HKEX IPO targets 
Request:
Use the project archivist workflow to update IPO target coverage for the most recent three-year window.

Changes:
- Add scripts/update_recent_ipo_list.py to discover HKEXnews annual new listing reports, archive XLSX sources, parse subscription-relevant IPO rows, and update SQLite plus snapshots.
- Add new_listing_report_entries to preserve annual report row-level evidence.
- Archive 2023-2026 Main Board new listing reports and 2024-2026 GEM new listing reports.
- Seed 290 report-backed IPO targets for 2023-06-15 through 2026-06-15, skipping 10 non-IPO rows without numeric offer prices.
- Refresh ipo_master, missing offering_terms fields, source_refs, ticker_sync_state, and sync_tasks.
- Add openpyxl as the XLSX parser dependency and document the archivist refresh flow.
- Limit sync summary output while keeping the full queue in SQLite and CSV snapshots.

Verification:
- Ran update_recent_ipo_list.py for 2023-06-15 to 2026-06-15 with as-of 2026-06-15T07:30:00Z.
- Parsed project Python scripts with ast.parse.
- Checked SQLite integrity and DB-to-snapshot row counts.
- Verified source_refs paths are repo-relative, files exist, and SHA-256 hashes match.
- Ran git diff --check and git diff --cached --check.
- Checked for Python cache and SQLite transient files.

Next useful context:
- ipo_master now has 293 tickers; new_listing_report_entries has 290 report-backed targets.
- Current sync queue has 2005 open tasks and 42 waiting_until_due tasks for deeper per-ticker archival stages.
2026-06-15 06:42:31 +00:00

319 lines
12 KiB
Python
Raw Blame History

#!/usr/bin/env python3
"""Bootstrap the project-local HK IPO historical archive."""
from __future__ import annotations
import csv
import hashlib
import sqlite3
from pathlib import Path
ARCHIVE_AS_OF = "2026-06-15T06:15:00Z"
DB_PATH = Path("data/hk_ipo.sqlite")
SCHEMA_PATH = Path("schema/hk_ipo.schema.sql")
SNAPSHOT_DIR = Path("data/snapshots")
STALE_GAP_IDS = [
"06106_full_prospectus_classification_2026_06_15",
]
IPO_MASTER = [
{
"ticker": "06658",
"company_name_en": "Liuliumei Co., Ltd.",
"company_name_zh": "溜溜梅股份有限公司",
"stock_short_name": "LIULIUMEI",
"status": "listed",
"listing_date": "2026-06-15",
"application_start_date": "2026-06-05",
"application_end_date": "2026-06-10",
"allotment_results_expected_date": "2026-06-12",
"industry_label": "Snack food / preserved fruit",
"data_as_of": ARCHIVE_AS_OF,
"notes": "Seeded from HKEXnews prospectus and allotment results.",
},
{
"ticker": "06675",
"company_name_en": "SENASIC Electronics Technology Co., Ltd.",
"company_name_zh": "琻捷電子科技(江蘇)股份有限公司",
"stock_short_name": None,
"status": "pending_listing",
"listing_date": "2026-06-17",
"application_start_date": "2026-06-09",
"application_end_date": "2026-06-12",
"allotment_results_expected_date": "2026-06-16",
"industry_label": "Automotive wireless sensing SoC / semiconductors",
"data_as_of": ARCHIVE_AS_OF,
"notes": "Seeded from HKEXnews prospectus and global offering announcement; allotment results not yet archived.",
},
{
"ticker": "06106",
"company_name_en": "Shanghai Seer Intelligent Technology Co., Ltd.",
"company_name_zh": "上海仙工智能科技股份有限公司",
"stock_short_name": None,
"status": "open_for_subscription",
"listing_date": "2026-06-24",
"application_start_date": "2026-06-15",
"application_end_date": "2026-06-18",
"allotment_results_expected_date": "2026-06-23",
"industry_label": "Industrial intelligent robots / robot controllers",
"data_as_of": ARCHIVE_AS_OF,
"notes": "Seeded from HKEXnews global offering announcement; full prospectus source classification needs follow-up.",
},
]
OFFERING_TERMS = [
{
"ticker": "06658",
"source_id": "06658_prospectus_2026_06_05",
"prospectus_date": "2026-06-05",
"offer_price_hkd": 43.58,
"board_lot": 100,
"min_subscription_amount_hkd": 4401.96,
"global_offer_shares": 11464100,
"hk_offer_shares_initial": 1146500,
"international_offer_shares_initial": 10317600,
"public_offer_pct_initial": 0.10,
"over_allotment_offer_shares": None,
"offer_size_adjustment_offer_shares": None,
"market_cap_hkd_m": 3434.59,
"gross_proceeds_hkd_m": 499.6,
"net_proceeds_hkd_m": 440.1,
"issued_shares_upon_listing": 78811208,
"data_as_of": ARCHIVE_AS_OF,
},
{
"ticker": "06675",
"source_id": "06675_global_offering_announcement_2026_06_09",
"prospectus_date": "2026-06-09",
"offer_price_hkd": 18.36,
"board_lot": 200,
"min_subscription_amount_hkd": 3709.04,
"global_offer_shares": 53407000,
"hk_offer_shares_initial": 5340800,
"international_offer_shares_initial": 48066200,
"public_offer_pct_initial": 0.10,
"over_allotment_offer_shares": 8011000,
"offer_size_adjustment_offer_shares": None,
"market_cap_hkd_m": 6959.2,
"gross_proceeds_hkd_m": None,
"net_proceeds_hkd_m": 906.7,
"issued_shares_upon_listing": 379041820,
"data_as_of": ARCHIVE_AS_OF,
},
{
"ticker": "06106",
"source_id": "06106_prospectus_candidate_2026_06_15",
"prospectus_date": "2026-06-15",
"offer_price_hkd": 101.60,
"board_lot": 50,
"min_subscription_amount_hkd": 5131.24,
"global_offer_shares": 10497300,
"hk_offer_shares_initial": 524900,
"international_offer_shares_initial": 9972400,
"public_offer_pct_initial": 0.05,
"over_allotment_offer_shares": 1574550,
"offer_size_adjustment_offer_shares": 1574550,
"market_cap_hkd_m": 11226.52568,
"gross_proceeds_hkd_m": 1066.52568,
"net_proceeds_hkd_m": 995.4,
"issued_shares_upon_listing": 110497300,
"data_as_of": ARCHIVE_AS_OF,
},
]
IPO_DEMAND = [
{
"demand_id": "06658_allotment_2026_06_12",
"ticker": "06658",
"source_id": "06658_allotment_results_2026_06_12",
"stage_date": "2026-06-12",
"valid_applications": 180507,
"successful_applications": 11465,
"public_oversubscription_times": 6586.73,
"international_placees": 64,
"international_oversubscription_times": 2.64,
"final_hk_offer_shares": 1146500,
"final_international_offer_shares": 10317600,
"data_as_of": ARCHIVE_AS_OF,
"notes": "Claw-back shown as N/A in the HKEXnews allotment results.",
},
]
SOURCES = [
{
"source_id": "06658_prospectus_2026_06_05",
"ticker": "06658",
"source_type": "prospectus",
"title": "Liuliumei Co., Ltd. Prospectus",
"local_path": "data/raw/06658/prospectus_2026-06-05.pdf",
"url": "https://www1.hkexnews.hk/listedco/listconews/sehk/2026/0605/2026060500023.pdf",
"source_date": "2026-06-05",
"notes": "HKEXnews prospectus.",
},
{
"source_id": "06658_allotment_results_2026_06_12",
"ticker": "06658",
"source_type": "allotment_results",
"title": "Liuliumei Co., Ltd. Announcement of Allotment Results",
"local_path": "data/raw/06658/allotment_results_2026-06-12.pdf",
"url": "https://www1.hkexnews.hk/listedco/listconews/sehk/2026/0612/2026061202100.pdf",
"source_date": "2026-06-12",
"notes": "HKEXnews allotment results.",
},
{
"source_id": "06675_prospectus_2026_06_09",
"ticker": "06675",
"source_type": "prospectus",
"title": "SENASIC Electronics Technology Co., Ltd. Prospectus",
"local_path": "data/raw/06675/prospectus_2026-06-09.pdf",
"url": "https://www.hkexnews.hk/listedco/listconews/sehk/2026/0609/2026060900029.pdf",
"source_date": "2026-06-09",
"notes": "HKEXnews prospectus.",
},
{
"source_id": "06675_global_offering_announcement_2026_06_09",
"ticker": "06675",
"source_type": "global_offering_announcement",
"title": "SENASIC Electronics Technology Co., Ltd. Global Offering Announcement",
"local_path": "data/raw/06675/global_offering_announcement_2026-06-09.pdf",
"url": "https://www.hkexnews.hk/listedco/listconews/sehk/2026/0609/2026060900009.pdf",
"source_date": "2026-06-09",
"notes": "HKEXnews global offering announcement.",
},
{
"source_id": "06106_prospectus_notice_2026_06_15",
"ticker": "06106",
"source_type": "prospectus_notice",
"title": "Shanghai Seer Intelligent Technology Co., Ltd. Prospectus Notice",
"local_path": "data/raw/06106/prospectus_notice_2026-06-15.pdf",
"url": "https://www1.hkexnews.hk/listedco/listconews/sehk/2026/0615/2026061500011.pdf",
"source_date": "2026-06-15",
"notes": "HKEXnews announcement containing global offering terms and timetable.",
},
{
"source_id": "06106_prospectus_candidate_2026_06_15",
"ticker": "06106",
"source_type": "prospectus",
"title": "Shanghai Seer Intelligent Technology Co., Ltd. Prospectus",
"local_path": "data/raw/06106/prospectus_candidate_2026-06-15.pdf",
"url": "https://www1.hkexnews.hk/listedco/listconews/sehk/2026/0615/2026061500013.pdf",
"source_date": "2026-06-15",
"notes": "HKEXnews prospectus; verified by text extraction as a 424-page GLOBAL OFFERING document.",
},
]
DATA_GAPS = [
{
"gap_id": "06675_allotment_results_pending_2026_06_15",
"ticker": "06675",
"stage": "T1_allotment",
"field_name": "ipo_demand",
"reason": "Allotment results were expected on 2026-06-16 and were not available in this seed archive.",
"expected_resolution_date": "2026-06-16",
"created_at": ARCHIVE_AS_OF,
"notes": "Update after the HKEXnews allotment results announcement is published.",
},
{
"gap_id": "06106_allotment_results_pending_2026_06_15",
"ticker": "06106",
"stage": "T1_allotment",
"field_name": "ipo_demand",
"reason": "Allotment results were expected on 2026-06-23 and were not available in this seed archive.",
"expected_resolution_date": "2026-06-23",
"created_at": ARCHIVE_AS_OF,
"notes": "Update after the HKEXnews allotment results announcement is published.",
},
]
def repo_root() -> Path:
return Path.cwd()
def hash_file(relative_path: str) -> str:
path = repo_root() / relative_path
digest = hashlib.sha256()
with path.open("rb") as handle:
for chunk in iter(lambda: handle.read(1024 * 1024), b""):
digest.update(chunk)
return digest.hexdigest()
def ensure_relative_path(relative_path: str) -> None:
path = Path(relative_path)
if path.is_absolute() or relative_path.startswith("./") or "\\" in relative_path:
raise ValueError(f"Path must be repo-relative POSIX style: {relative_path}")
if not (repo_root() / relative_path).exists():
raise FileNotFoundError(relative_path)
def upsert_rows(conn: sqlite3.Connection, table: str, rows: list[dict[str, object]]) -> None:
if not rows:
return
columns = list(rows[0])
placeholders = ", ".join("?" for _ in columns)
assignments = ", ".join(f"{column}=excluded.{column}" for column in columns)
sql = (
f"INSERT INTO {table} ({', '.join(columns)}) VALUES ({placeholders}) "
f"ON CONFLICT DO UPDATE SET {assignments}"
)
conn.executemany(sql, ([row[column] for column in columns] for row in rows))
def export_snapshot(conn: sqlite3.Connection, table: str) -> None:
SNAPSHOT_DIR.mkdir(parents=True, exist_ok=True)
cursor = conn.execute(f"SELECT * FROM {table} ORDER BY 1")
columns = [description[0] for description in cursor.description]
with (SNAPSHOT_DIR / f"{table}.csv").open("w", newline="", encoding="utf-8") as handle:
writer = csv.writer(handle, lineterminator="\n")
writer.writerow(columns)
writer.writerows(cursor.fetchall())
def main() -> None:
DB_PATH.parent.mkdir(parents=True, exist_ok=True)
with sqlite3.connect(DB_PATH) as conn:
conn.executescript(SCHEMA_PATH.read_text(encoding="utf-8"))
conn.executemany("DELETE FROM data_gaps WHERE gap_id = ?", [(gap_id,) for gap_id in STALE_GAP_IDS])
upsert_rows(conn, "ipo_master", IPO_MASTER)
upsert_rows(conn, "offering_terms", OFFERING_TERMS)
upsert_rows(conn, "ipo_demand", IPO_DEMAND)
source_rows = []
for source in SOURCES:
ensure_relative_path(source["local_path"])
source_rows.append(
{
**source,
"path_base": "repo_root",
"file_sha256": hash_file(source["local_path"]),
"archived_at": ARCHIVE_AS_OF,
}
)
upsert_rows(conn, "source_refs", source_rows)
upsert_rows(conn, "data_gaps", DATA_GAPS)
for table in [
"ipo_master",
"offering_terms",
"ipo_demand",
"price_performance",
"new_listing_report_entries",
"source_refs",
"data_gaps",
"sync_runs",
"ticker_sync_state",
"sync_tasks",
]:
export_snapshot(conn, table)
if __name__ == "__main__":
main()
View Git Blame Copy Permalink