A tag could come from two places: rules.toml, or the TUI's t key, which wrote manual_tag with COALESCE(manual_tag, rule_tag) deciding the winner. That split paid for itself in the first invariant of the codebase, in ClearOverrides and the c key, in the * marker on the tag column, and in the one exception to a disposable index -- a tag set by hand was the only thing in index.db that the statements could not reproduce. Now rules.toml decides every tag. The index is derived entirely from the statements plus that file, so deleting it and re-importing gets back exactly what was there, and retag has nothing to be careful of. Tagging a one-off means writing a narrow rule on screen 4, which previews what the glob catches before it is saved. A manual tag in an existing index is dropped along with the column the first time this build opens it, and those rows read as whatever the rules say, or as untagged. TestManualTagSurvivesRetag guarded the invariant that has just been removed; TestRetagRewritesEveryTag replaces it with the one that took its place, and keeps Retag itself covered. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
389 lines
11 KiB
Go
389 lines
11 KiB
Go
// Package store is the SQLite index over the statements. It is entirely
|
|
// rebuildable: delete index.db and re-import to get it back, except for the
|
|
// tags set by hand, which live only here.
|
|
package store
|
|
|
|
import (
|
|
"database/sql"
|
|
"fmt"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
|
|
_ "modernc.org/sqlite"
|
|
|
|
"git.petrovv.com/nikola/money/internal/model"
|
|
)
|
|
|
|
// DB wraps the SQLite handle.
|
|
type DB struct {
|
|
sql *sql.DB
|
|
}
|
|
|
|
const schema = `
|
|
PRAGMA foreign_keys = ON;
|
|
|
|
CREATE TABLE IF NOT EXISTS accounts (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
slug TEXT NOT NULL UNIQUE,
|
|
name TEXT NOT NULL,
|
|
currency TEXT NOT NULL,
|
|
minor_digits INTEGER NOT NULL DEFAULT 2
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS source_files (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
account_id INTEGER NOT NULL REFERENCES accounts(id),
|
|
path TEXT NOT NULL,
|
|
sha256 TEXT NOT NULL,
|
|
imported_at TEXT NOT NULL,
|
|
UNIQUE(account_id, path)
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS transactions (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
account_id INTEGER NOT NULL REFERENCES accounts(id),
|
|
source_file_id INTEGER NOT NULL REFERENCES source_files(id),
|
|
fingerprint TEXT NOT NULL,
|
|
date TEXT NOT NULL,
|
|
description TEXT NOT NULL,
|
|
amount_minor INTEGER NOT NULL,
|
|
type TEXT NOT NULL DEFAULT '',
|
|
balance_minor INTEGER,
|
|
rule_tag TEXT,
|
|
UNIQUE(account_id, fingerprint)
|
|
);
|
|
|
|
CREATE INDEX IF NOT EXISTS idx_txn_date ON transactions(date);
|
|
CREATE INDEX IF NOT EXISTS idx_txn_account ON transactions(account_id);
|
|
`
|
|
|
|
// migrations bring an index created by an older build up to date. SQLite
|
|
// errors on a duplicate column, which is how we detect "already applied".
|
|
var migrations = []string{
|
|
`ALTER TABLE transactions ADD COLUMN type TEXT NOT NULL DEFAULT ''`,
|
|
`ALTER TABLE transactions ADD COLUMN balance_minor INTEGER`,
|
|
}
|
|
|
|
// dropped are columns an older build created that this one no longer reads.
|
|
// Nothing indexes or constrains them, so they can simply go; leaving them
|
|
// would keep a NOT NULL column alive that no INSERT here ever names.
|
|
var dropped = []string{"counterparty", "rule_transfer", "manual_transfer", "manual_tag"}
|
|
|
|
// migrate brings an index created by an older build up to date, adding the
|
|
// columns it lacks and removing the ones it should no longer have.
|
|
func migrate(db *sql.DB) error {
|
|
have, err := columns(db, "transactions")
|
|
if err != nil {
|
|
return err
|
|
}
|
|
for _, stmt := range migrations {
|
|
name := addedColumn(stmt)
|
|
if have[name] {
|
|
continue
|
|
}
|
|
if _, err := db.Exec(stmt); err != nil {
|
|
return fmt.Errorf("migrate (%s): %w", stmt, err)
|
|
}
|
|
}
|
|
for _, name := range dropped {
|
|
if !have[name] {
|
|
continue
|
|
}
|
|
stmt := fmt.Sprintf(`ALTER TABLE transactions DROP COLUMN %s`, name)
|
|
if _, err := db.Exec(stmt); err != nil {
|
|
return fmt.Errorf("migrate (%s): %w", stmt, err)
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func columns(db *sql.DB, table string) (map[string]bool, error) {
|
|
rows, err := db.Query(`SELECT name FROM pragma_table_info(?)`, table)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("inspect %s: %w", table, err)
|
|
}
|
|
defer rows.Close()
|
|
out := map[string]bool{}
|
|
for rows.Next() {
|
|
var name string
|
|
if err := rows.Scan(&name); err != nil {
|
|
return nil, err
|
|
}
|
|
out[name] = true
|
|
}
|
|
return out, rows.Err()
|
|
}
|
|
|
|
// addedColumn pulls the column name out of an ADD COLUMN statement.
|
|
func addedColumn(stmt string) string {
|
|
_, rest, ok := strings.Cut(stmt, "ADD COLUMN ")
|
|
if !ok {
|
|
return ""
|
|
}
|
|
name, _, _ := strings.Cut(rest, " ")
|
|
return name
|
|
}
|
|
|
|
// Open opens (creating if needed) the index at path.
|
|
func Open(path string) (*DB, error) {
|
|
if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
|
|
return nil, fmt.Errorf("create index dir: %w", err)
|
|
}
|
|
sqlDB, err := sql.Open("sqlite", path)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("open index %s: %w", path, err)
|
|
}
|
|
if _, err := sqlDB.Exec(schema); err != nil {
|
|
sqlDB.Close()
|
|
return nil, fmt.Errorf("apply schema: %w", err)
|
|
}
|
|
if err := migrate(sqlDB); err != nil {
|
|
sqlDB.Close()
|
|
return nil, err
|
|
}
|
|
return &DB{sql: sqlDB}, nil
|
|
}
|
|
|
|
// Close releases the underlying handle.
|
|
func (d *DB) Close() error { return d.sql.Close() }
|
|
|
|
// UpsertAccount inserts or updates an account by slug and returns its id.
|
|
func (d *DB) UpsertAccount(a model.Account) (int64, error) {
|
|
_, err := d.sql.Exec(`
|
|
INSERT INTO accounts (slug, name, currency, minor_digits)
|
|
VALUES (?, ?, ?, ?)
|
|
ON CONFLICT(slug) DO UPDATE SET
|
|
name = excluded.name,
|
|
currency = excluded.currency,
|
|
minor_digits = excluded.minor_digits`,
|
|
a.Slug, a.Name, a.Currency, a.MinorDigits)
|
|
if err != nil {
|
|
return 0, fmt.Errorf("upsert account %s: %w", a.Slug, err)
|
|
}
|
|
var id int64
|
|
if err := d.sql.QueryRow(`SELECT id FROM accounts WHERE slug = ?`, a.Slug).Scan(&id); err != nil {
|
|
return 0, fmt.Errorf("read account id %s: %w", a.Slug, err)
|
|
}
|
|
return id, nil
|
|
}
|
|
|
|
// Accounts lists every known account, ordered by slug.
|
|
func (d *DB) Accounts() ([]model.Account, error) {
|
|
rows, err := d.sql.Query(`SELECT id, slug, name, currency, minor_digits FROM accounts ORDER BY slug`)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("list accounts: %w", err)
|
|
}
|
|
defer rows.Close()
|
|
var out []model.Account
|
|
for rows.Next() {
|
|
var a model.Account
|
|
if err := rows.Scan(&a.ID, &a.Slug, &a.Name, &a.Currency, &a.MinorDigits); err != nil {
|
|
return nil, err
|
|
}
|
|
out = append(out, a)
|
|
}
|
|
return out, rows.Err()
|
|
}
|
|
|
|
// SourceFile records that a statement file was imported, returning its id.
|
|
func (d *DB) SourceFile(accountID int64, path, sha, importedAt string) (int64, error) {
|
|
_, err := d.sql.Exec(`
|
|
INSERT INTO source_files (account_id, path, sha256, imported_at)
|
|
VALUES (?, ?, ?, ?)
|
|
ON CONFLICT(account_id, path) DO UPDATE SET
|
|
sha256 = excluded.sha256,
|
|
imported_at = excluded.imported_at`,
|
|
accountID, path, sha, importedAt)
|
|
if err != nil {
|
|
return 0, fmt.Errorf("record source file %s: %w", path, err)
|
|
}
|
|
var id int64
|
|
if err := d.sql.QueryRow(
|
|
`SELECT id FROM source_files WHERE account_id = ? AND path = ?`, accountID, path).Scan(&id); err != nil {
|
|
return 0, fmt.Errorf("read source file id %s: %w", path, err)
|
|
}
|
|
return id, nil
|
|
}
|
|
|
|
// SourceFileSHA returns the recorded checksum for a statement file, and whether
|
|
// it has been imported before.
|
|
func (d *DB) SourceFileSHA(accountID int64, path string) (string, bool, error) {
|
|
var sha string
|
|
err := d.sql.QueryRow(
|
|
`SELECT sha256 FROM source_files WHERE account_id = ? AND path = ?`, accountID, path).Scan(&sha)
|
|
if err == sql.ErrNoRows {
|
|
return "", false, nil
|
|
}
|
|
if err != nil {
|
|
return "", false, err
|
|
}
|
|
return sha, true, nil
|
|
}
|
|
|
|
// InsertTransaction adds a transaction unless its fingerprint already exists
|
|
// for that account. It reports whether a new row was created.
|
|
//
|
|
// Existing rows are deliberately left untouched, so re-importing a statement
|
|
// that overlaps one already imported adds nothing rather than duplicating it.
|
|
func (d *DB) InsertTransaction(t model.Transaction) (bool, error) {
|
|
var balance any
|
|
if t.BalanceMinor != nil {
|
|
balance = *t.BalanceMinor
|
|
}
|
|
res, err := d.sql.Exec(`
|
|
INSERT INTO transactions
|
|
(account_id, source_file_id, fingerprint, date, description, amount_minor,
|
|
type, balance_minor, rule_tag)
|
|
VALUES (?, ?, ?, ?, ?, ?, ?, ?, NULLIF(?, ''))
|
|
ON CONFLICT(account_id, fingerprint) DO NOTHING`,
|
|
t.AccountID, t.SourceFileID, t.Fingerprint, t.Date, t.Description,
|
|
t.AmountMinor, t.Type, balance, t.RuleTag)
|
|
if err != nil {
|
|
return false, fmt.Errorf("insert transaction: %w", err)
|
|
}
|
|
n, err := res.RowsAffected()
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
return n > 0, nil
|
|
}
|
|
|
|
// Filter narrows a transaction query.
|
|
type Filter struct {
|
|
AccountSlug string
|
|
Untagged bool // only rows with no effective tag
|
|
Month string // YYYY-MM
|
|
Search string // case-insensitive substring of the description
|
|
Limit int
|
|
}
|
|
|
|
// Transactions returns rows matching f, newest first.
|
|
func (d *DB) Transactions(f Filter) ([]model.Transaction, error) {
|
|
q := `
|
|
SELECT t.id, t.account_id, a.slug, a.currency, a.minor_digits,
|
|
t.fingerprint, t.date, t.description, t.amount_minor,
|
|
COALESCE(s.path, ''), t.type, t.balance_minor,
|
|
COALESCE(t.rule_tag, '')
|
|
FROM transactions t
|
|
JOIN accounts a ON a.id = t.account_id
|
|
LEFT JOIN source_files s ON s.id = t.source_file_id
|
|
WHERE 1 = 1`
|
|
var args []any
|
|
if f.AccountSlug != "" {
|
|
q += ` AND a.slug = ?`
|
|
args = append(args, f.AccountSlug)
|
|
}
|
|
if f.Untagged {
|
|
q += ` AND NULLIF(t.rule_tag, '') IS NULL`
|
|
}
|
|
if f.Month != "" {
|
|
q += ` AND substr(t.date, 1, 7) = ?`
|
|
args = append(args, f.Month)
|
|
}
|
|
q += ` ORDER BY t.date DESC, t.id DESC`
|
|
// Search and Limit are applied in Go: SQLite's upper()/LIKE fold ASCII
|
|
// only, which would silently fail on Cyrillic statement descriptions.
|
|
|
|
rows, err := d.sql.Query(q, args...)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("query transactions: %w", err)
|
|
}
|
|
defer rows.Close()
|
|
|
|
needle := model.NormalizeDescription(f.Search)
|
|
var out []model.Transaction
|
|
for rows.Next() {
|
|
var (
|
|
t model.Transaction
|
|
balance sql.NullInt64
|
|
)
|
|
if err := rows.Scan(&t.ID, &t.AccountID, &t.AccountSlug, &t.Currency, &t.MinorDigits,
|
|
&t.Fingerprint, &t.Date, &t.Description, &t.AmountMinor, &t.SourcePath,
|
|
&t.Type, &balance, &t.RuleTag); err != nil {
|
|
return nil, err
|
|
}
|
|
if balance.Valid {
|
|
v := balance.Int64
|
|
t.BalanceMinor = &v
|
|
}
|
|
if needle != "" && !strings.Contains(model.NormalizeDescription(t.Description), needle) {
|
|
continue
|
|
}
|
|
out = append(out, t)
|
|
if f.Limit > 0 && len(out) >= f.Limit {
|
|
break
|
|
}
|
|
}
|
|
return out, rows.Err()
|
|
}
|
|
|
|
// RuleAssignment is one row's recomputed rule verdict.
|
|
type RuleAssignment struct {
|
|
ID int64
|
|
Tag string
|
|
}
|
|
|
|
// ApplyRuleResults rewrites rule_tag for every listed row in a single
|
|
// transaction. The manual column is never touched.
|
|
func (d *DB) ApplyRuleResults(rs []RuleAssignment) error {
|
|
tx, err := d.sql.Begin()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
defer tx.Rollback()
|
|
|
|
stmt, err := tx.Prepare(
|
|
`UPDATE transactions SET rule_tag = NULLIF(?, '') WHERE id = ?`)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
defer stmt.Close()
|
|
|
|
for _, r := range rs {
|
|
if _, err := stmt.Exec(r.Tag, r.ID); err != nil {
|
|
return fmt.Errorf("apply rules to txn %d: %w", r.ID, err)
|
|
}
|
|
}
|
|
return tx.Commit()
|
|
}
|
|
|
|
// Balance sums every transaction in an account.
|
|
func (d *DB) Balance(accountID int64) (int64, error) {
|
|
var v sql.NullInt64
|
|
err := d.sql.QueryRow(
|
|
`SELECT SUM(amount_minor) FROM transactions WHERE account_id = ?`, accountID).Scan(&v)
|
|
if err != nil {
|
|
return 0, err
|
|
}
|
|
return v.Int64, nil
|
|
}
|
|
|
|
// Count returns the number of transactions in an account.
|
|
func (d *DB) Count(accountID int64) (int, error) {
|
|
var n int
|
|
err := d.sql.QueryRow(
|
|
`SELECT COUNT(*) FROM transactions WHERE account_id = ?`, accountID).Scan(&n)
|
|
return n, err
|
|
}
|
|
|
|
// Tags lists every tag in use, for completion in the TUI.
|
|
func (d *DB) Tags() ([]string, error) {
|
|
rows, err := d.sql.Query(`
|
|
SELECT DISTINCT rule_tag FROM transactions
|
|
WHERE rule_tag IS NOT NULL AND rule_tag != '' ORDER BY rule_tag`)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer rows.Close()
|
|
var out []string
|
|
for rows.Next() {
|
|
var s string
|
|
if err := rows.Scan(&s); err != nil {
|
|
return nil, err
|
|
}
|
|
out = append(out, s)
|
|
}
|
|
return out, rows.Err()
|
|
}
|