petal/internal/db/db.go

// Package db owns the SQLite connection, schema migrations, and the core data
// models. It uses modernc.org/sqlite (pure Go, no cgo) so the app stays a
// single static binary.
package db

import (
	"database/sql"
	"fmt"
	"net/url"
	"os"
	"path/filepath"

	_ "modernc.org/sqlite"
)

// LocalUserID is the id of the single hardcoded user the app runs as while auth
// is deferred. The seeded row keeps foreign keys valid; real auth replaces it
// later without a schema change.
const LocalUserID = "local"

// DB wraps the SQL handle. It's a thin alias today, leaving room for prepared
// statements or helpers later without churning call sites.
type DB struct {
	*sql.DB
}

// Open initialises the database at path: it ensures the parent directory
// exists, opens the connection with foreign keys and WAL enabled, runs all
// pending migrations, and seeds the local user.
func Open(path string) (*DB, error) {
	if dir := filepath.Dir(path); dir != "" && dir != "." {
		if err := os.MkdirAll(dir, 0o755); err != nil {
			return nil, fmt.Errorf("create data dir: %w", err)
		}
	}

	sqlDB, err := sql.Open("sqlite", dsn(path))
	if err != nil {
		return nil, fmt.Errorf("open sqlite: %w", err)
	}
	// SQLite is a single writer; one connection avoids "database is locked"
	// churn while keeping WAL's concurrent readers.
	sqlDB.SetMaxOpenConns(1)

	if err := sqlDB.Ping(); err != nil {
		_ = sqlDB.Close()
		return nil, fmt.Errorf("ping sqlite: %w", err)
	}

	d := &DB{sqlDB}
	if err := d.migrate(); err != nil {
		_ = sqlDB.Close()
		return nil, fmt.Errorf("migrate: %w", err)
	}
	if err := d.seed(); err != nil {
		_ = sqlDB.Close()
		return nil, fmt.Errorf("seed: %w", err)
	}
	return d, nil
}

// dsn builds the modernc.org/sqlite connection string with the pragmas we want
// applied to every connection.
func dsn(path string) string {
	q := url.Values{}
	q.Add("_pragma", "foreign_keys(1)")
	q.Add("_pragma", "busy_timeout(5000)")
	q.Add("_pragma", "journal_mode(WAL)")
	return "file:" + path + "?" + q.Encode()
}

// migration is one ordered, idempotent schema step. Append new migrations to the
// slice in migrate(); never edit or reorder an already-shipped one.
type migration struct {
	name string
	stmt string
}

// migrate runs every migration not yet recorded in schema_migrations, inside a
// transaction each, in order.
func (d *DB) migrate() error {
	if _, err := d.Exec(`CREATE TABLE IF NOT EXISTS schema_migrations (
		name       TEXT PRIMARY KEY,
		applied_at DATETIME DEFAULT CURRENT_TIMESTAMP
	)`); err != nil {
		return err
	}

	for _, m := range migrations() {
		var exists bool
		if err := d.QueryRow(
			`SELECT EXISTS(SELECT 1 FROM schema_migrations WHERE name = ?)`, m.name,
		).Scan(&exists); err != nil {
			return err
		}
		if exists {
			continue
		}

		tx, err := d.Begin()
		if err != nil {
			return err
		}
		if _, err := tx.Exec(m.stmt); err != nil {
			_ = tx.Rollback()
			return fmt.Errorf("migration %q: %w", m.name, err)
		}
		if _, err := tx.Exec(`INSERT INTO schema_migrations (name) VALUES (?)`, m.name); err != nil {
			_ = tx.Rollback()
			return fmt.Errorf("record migration %q: %w", m.name, err)
		}
		if err := tx.Commit(); err != nil {
			return err
		}
	}
	return nil
}

// migrations returns the ordered schema history. The initial migration mirrors
// the schema in petal-spec.md.
func migrations() []migration {
	return []migration{
		{
			name: "0001_initial_schema",
			stmt: `
CREATE TABLE users (
    id           TEXT PRIMARY KEY,
    email        TEXT NOT NULL,
    display_name TEXT,
    created_at   DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE documents (
    id           TEXT PRIMARY KEY DEFAULT (lower(hex(randomblob(16)))),
    user_id      TEXT NOT NULL REFERENCES users(id),
    title        TEXT NOT NULL DEFAULT 'Untitled',
    content      TEXT NOT NULL DEFAULT '{}',
    content_text TEXT NOT NULL DEFAULT '',
    word_count   INTEGER NOT NULL DEFAULT 0,
    created_at   DATETIME DEFAULT CURRENT_TIMESTAMP,
    updated_at   DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE suggestions (
    id           TEXT PRIMARY KEY DEFAULT (lower(hex(randomblob(16)))),
    doc_id       TEXT NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
    from_pos     INTEGER NOT NULL,
    to_pos       INTEGER NOT NULL,
    original     TEXT NOT NULL,
    replacement  TEXT NOT NULL,
    explanation  TEXT NOT NULL,
    type         TEXT NOT NULL CHECK(type IN ('grammar','phrasing','idiom','clarity','voice')),
    status       TEXT NOT NULL DEFAULT 'pending' CHECK(status IN ('pending','accepted','rejected')),
    created_at   DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE plagiarism_reports (
    id              TEXT PRIMARY KEY DEFAULT (lower(hex(randomblob(16)))),
    doc_id          TEXT NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
    backend         TEXT NOT NULL DEFAULT 'copyleaks',
    similarity_pct  REAL,
    status          TEXT NOT NULL DEFAULT 'pending'
                    CHECK(status IN ('pending','complete','error')),
    result_json     TEXT,
    created_at      DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE INDEX idx_suggestions_doc_id ON suggestions(doc_id);
CREATE INDEX idx_plagiarism_doc_id ON plagiarism_reports(doc_id);
`,
		},
		{
			// Per-document tone: guides the grammar-checkpoint LLM so advice fits
			// the writer's target register (academic essay vs casual journal).
			// 'general' means no specific tone steering.
			name: "0002_document_tone",
			stmt: `ALTER TABLE documents ADD COLUMN tone TEXT NOT NULL DEFAULT 'general';`,
		},
		{
			// Version history: point-in-time snapshots of a document's body so a
			// bad edit or LLM mishap is always recoverable. `kind` distinguishes
			// throttled background snapshots ('auto'), explicit user restore
			// points ('manual'), and the safety copy taken right before a restore
			// ('pre_restore') so restoring is itself undoable. Snapshots cascade
			// with the document. Stored fully (content + content_text) so a
			// restore is a plain copy with no re-derivation.
			name: "0003_document_versions",
			stmt: `
CREATE TABLE document_versions (
    id           TEXT PRIMARY KEY DEFAULT (lower(hex(randomblob(16)))),
    doc_id       TEXT NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
    title        TEXT NOT NULL,
    content      TEXT NOT NULL,
    content_text TEXT NOT NULL,
    word_count   INTEGER NOT NULL DEFAULT 0,
    kind         TEXT NOT NULL DEFAULT 'auto'
                 CHECK(kind IN ('auto','manual','pre_restore')),
    created_at   DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE INDEX idx_versions_doc_id ON document_versions(doc_id, created_at DESC);
`,
		},
	}
}

// seed inserts the hardcoded local user if it doesn't already exist. It's
// idempotent, so it runs safely on every startup.
func (d *DB) seed() error {
	_, err := d.Exec(
		`INSERT INTO users (id, email, display_name) VALUES (?, ?, ?)
		 ON CONFLICT(id) DO NOTHING`,
		LocalUserID, "local@petal.local", "Writer",
	)
	return err
}