mirror of
https://github.com/tiennm99/thptqg.git
synced 2026-10-11 03:13:48 +00:00
tiennm99
99465fda59
* feat(xlsxread): stage 0 scaffold with pinned deps and clap CLI skeleton * feat(xlsxread): stage 1 reader — calamine sheet enumeration and header skip * feat(xlsxread): stage 2 transform — to_ascii, score regex, validation with 38 unit tests * feat(xlsxread): stage 3 writer — SQLite DDL, INSERT OR REPLACE, VACUUM, stats output * feat(xlsxread): stage 4 audit — distinct SBD scan vs DB count, mirrors audit-row-counts.js output * feat(xlsxread): stage 5 golden tests — in-process xlsx fixtures, 8 integration tests pass * chore(xlsxread): commit Cargo.lock for reproducible Rust builds * feat(build): wire root build:db scripts to xlsxread CLI Replace node scripts/build-database*.js invocations with the Rust xlsxread binary. Each build:db* script now calls `pnpm build:rust` (cargo build --release) before invoking the xlsxread build subcommand with the matching per-dataset config. Drop xlsx and better-sqlite3 from devDependencies — no Node script consumes them anymore. sql.js (runtime DB reader in the SPA) is unaffected and remains in dependencies. * ci: build xlsxread before running database build jobs Add dtolnay/rust-toolchain@stable and Swatinem/rust-cache@v2 (workspaces: tools/xlsxread) for warm incremental Rust builds. Replace the single `pnpm build:db:all` step with explicit xlsxread invocations so CI doesn't call pnpm build:rust redundantly three times. The binary is built once, then each of the three datasets is processed in sequence. * chore: remove deprecated xlsx-based build scripts Delete scripts/build-database.js, build-database-old.js, build-database-old2.js, build-lib.js, and audit-row-counts.js. Functionality replaced by the xlsxread Rust CLI configured via tools/xlsxread/configs/*.toml. History preserved in git; one-click revert available via the chore/migration-backup-260519 branch. * docs: update README build instructions for xlsxread pipeline Replace Node.js + xlsx references with Rust + xlsxread workflow. Update requirements (Node 24+, pnpm, Rust stable), quickstart, scripts table, and project layout tree to reflect the current state after the xlsx-based build scripts were removed. * chore(deps): drop xlsx and better-sqlite3 from package.json and lockfile Remove xlsx (SheetJS, vulnerable: GHSA-4r6h-8v6p-xvw6, GHSA-5pgg-2g8v-p4x9) and better-sqlite3 from devDependencies. Both were only used by the now-deleted Node build scripts. The Rust xlsxread CLI vendors SQLite via rusqlite-bundled; no Node-side SQLite dependency is needed. `pnpm audit` returns clean.
31 lines
775 B
TOML
31 lines
775 B
TOML
[package]
|
|
name = "xlsxread"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Rust CLI replacing SheetJS xlsx build scripts for thptqg2017/thptqg2016"
|
|
|
|
[dependencies]
|
|
calamine = "0.26"
|
|
rusqlite = { version = "0.32", features = ["bundled"] }
|
|
clap = { version = "4", features = ["derive"] }
|
|
serde = { version = "1", features = ["derive"] }
|
|
toml = "0.8"
|
|
regex = "1"
|
|
unicode-normalization = "0.1"
|
|
thiserror = "1"
|
|
anyhow = "1"
|
|
glob = "0.3"
|
|
|
|
# zip is already a transitive dep of calamine; pin explicitly so tests can use it
|
|
[dev-dependencies]
|
|
zip = "2"
|
|
rusqlite = { version = "0.32", features = ["bundled"] }
|
|
|
|
[[bin]]
|
|
name = "xlsxread"
|
|
path = "src/main.rs"
|
|
|
|
[[test]]
|
|
name = "golden"
|
|
path = "tests/golden.rs"
|