mirror of
https://github.com/tiennm99/thptqg.git
synced 2026-10-11 03:13:48 +00:00
tiennm99
6b21c625ac
* feat(xlsxread): vendor Rust binary cloned from thptqg2017 Copies the xlsxread Rust crate from thptqg2017@8b4a755 (chore/xlsxread-rust). Adds format_detect_2016 module with per-file column-layout auto-detection mirroring detectFormat() in scripts/build-database.js (lines 63-87): - separate-scores: SBD/HOTEN/TOAN... fixed columns (dhhanghai files) - mapped: header-derived SOBAODANH|SBD + DIEM_THI dynamic indices - default: positional 6-col layout (no header) Extends ParsedRow with ten_cum_thi and gioi_tinh fields. Adds SCORE_FIELDS_2016 (12 cols: tieng_duc/tieng_nhat; no khtn/khxh/tieng_nga). Adds thptqg2016-data.toml config with 18-column schema and format_detection flag. 58 tests pass (50 unit + 8 integration), 0 failures. * feat(build): wire build:db to xlsxread CLI Replaces the Node.js build:db script with the xlsxread Rust binary. Adds build:rust script for the cargo compile step in isolation. * chore: remove deprecated build-database.js Superseded by the xlsxread Rust binary. All 119 source files (4 .xls + 115 .xlsx) are now processed by xlsxread with per-file format detection. * ci: build xlsxread before running database build job Adds dtolnay/rust-toolchain@stable and Swatinem/rust-cache@v2 steps before the xlsxread build and database generation steps. Node/pnpm steps now follow the Rust build rather than preceding it. * chore: add Rust build artifacts to .gitignore * docs: update README build instructions for xlsxread pipeline * chore(deps): drop xlsx and better-sqlite3 from package.json and lockfile
77 lines
2.0 KiB
TOML
77 lines
2.0 KiB
TOML
# Test-only config used by golden integration tests (data-old variant).
|
|
# Same column layout as thptqg2017-data.toml but with:
|
|
# - sheet_mode = "first" (reads only first sheet)
|
|
# - require_numeric_sbd = true (rejects non-digit SBDs)
|
|
# Schema and INSERT match SCORE_FIELDS_2017 (14 score cols).
|
|
|
|
[reader]
|
|
sheet_mode = "first"
|
|
strip_blank_rows = false
|
|
|
|
[columns]
|
|
ho_ten = 0
|
|
ngay_sinh = 1
|
|
so_bao_danh = 2
|
|
diem_thi = 3
|
|
|
|
[validation]
|
|
require_numeric_sbd = true
|
|
require_nonempty_name = true
|
|
require_nonempty_sbd = true
|
|
|
|
[header]
|
|
tokens = ["HO_TEN", "HỌ TÊN", "STT"]
|
|
|
|
[schema]
|
|
ddl = """
|
|
CREATE TABLE student (
|
|
so_bao_danh TEXT PRIMARY KEY,
|
|
ho_ten TEXT NOT NULL,
|
|
ho_ten_ascii TEXT NOT NULL,
|
|
ngay_sinh TEXT,
|
|
toan REAL,
|
|
ngu_van REAL,
|
|
vat_ly REAL,
|
|
hoa_hoc REAL,
|
|
sinh_hoc REAL,
|
|
khtn REAL,
|
|
lich_su REAL,
|
|
dia_ly REAL,
|
|
gdcd REAL,
|
|
khxh REAL,
|
|
tieng_anh REAL,
|
|
tieng_phap REAL,
|
|
tieng_nga REAL,
|
|
tieng_trung REAL
|
|
);
|
|
CREATE INDEX idx_ho_ten ON student(ho_ten);
|
|
CREATE INDEX idx_ho_ten_ascii ON student(ho_ten_ascii);
|
|
"""
|
|
|
|
[scores]
|
|
toan = 'Toán:\s*(\d+(?:\.\d+)?)'
|
|
ngu_van = 'Ngữ văn:\s*(\d+(?:\.\d+)?)'
|
|
vat_ly = 'Vật lí:\s*(\d+(?:\.\d+)?)'
|
|
hoa_hoc = 'Hóa học:\s*(\d+(?:\.\d+)?)'
|
|
sinh_hoc = 'Sinh học:\s*(\d+(?:\.\d+)?)'
|
|
khtn = 'KHTN:\s*(\d+(?:\.\d+)?)'
|
|
lich_su = 'Lịch sử:\s*(\d+(?:\.\d+)?)'
|
|
dia_ly = 'Địa lí:\s*(\d+(?:\.\d+)?)'
|
|
gdcd = 'GDCD:\s*(\d+(?:\.\d+)?)'
|
|
khxh = 'KHXH:\s*(\d+(?:\.\d+)?)'
|
|
tieng_anh = 'Tiếng Anh:\s*(\d+(?:\.\d+)?)'
|
|
tieng_phap = 'Tiếng Pháp:\s*(\d+(?:\.\d+)?)'
|
|
tieng_nga = 'Tiếng Nga:\s*(\d+(?:\.\d+)?)'
|
|
tieng_trung = 'Tiếng Trung:\s*(\d+(?:\.\d+)?)'
|
|
|
|
[insert]
|
|
sql = """
|
|
INSERT OR REPLACE INTO student
|
|
(so_bao_danh, ho_ten, ho_ten_ascii, ngay_sinh,
|
|
toan, ngu_van, vat_ly, hoa_hoc, sinh_hoc, khtn,
|
|
lich_su, dia_ly, gdcd, khxh,
|
|
tieng_anh, tieng_phap, tieng_nga, tieng_trung)
|
|
VALUES
|
|
(?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
|
|
"""
|