novela/containers/novela/migrations.py

import re

from db import direct_connect

_DEFAULT_REGEX = [
    r"^\s*[\*\-]{3,}\s*$",
    r"^\s*[·•◦‣⁃]\s*[·•◦‣⁃]\s*[·•◦‣⁃]\s*$",
    r"^\s*~{2,}\s*$",
    r"^\s*={3,}\s*$",
    r"^\s*#{3,}\s*$",
    r"^\s*[oO0]{1,3}\s*$",
    r"^\s*[-–—]\s*[oO0]\s*[-–—]\s*$",
    r"^\s*[<>]+\s*[·•*]\s*[<>]+\s*$",
]
_DEFAULT_CSS = [
    "hr",
    "separator",
    "section-break",
    "divider",
    "break",
    "chapterbreak",
    "scene-break",
    "scenebreak",
]


def _exec(sql: str) -> None:
    conn = direct_connect()
    try:
        with conn:
            with conn.cursor() as cur:
                cur.execute(sql)
    finally:
        conn.close()


def migrate_create_library() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS library (
            id                  SERIAL PRIMARY KEY,
            filename            VARCHAR(600) UNIQUE NOT NULL,
            media_type          VARCHAR(10)  NOT NULL DEFAULT 'epub',
            title               VARCHAR(500),
            author              VARCHAR(255),
            publisher           VARCHAR(255),
            series              VARCHAR(500),
            series_index        INTEGER      DEFAULT 0,
            publication_status  VARCHAR(100),
            has_cover           BOOLEAN      DEFAULT FALSE,
            description         TEXT         DEFAULT '',
            source_url          VARCHAR(1000),
            publish_date        DATE,
            archived            BOOLEAN      DEFAULT FALSE,
            want_to_read        BOOLEAN      DEFAULT FALSE,
            needs_review        BOOLEAN      DEFAULT FALSE,
            created_at          TIMESTAMP    DEFAULT NOW(),
            updated_at          TIMESTAMP    DEFAULT NOW()
        )
        """
    )


def migrate_create_book_tags() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS book_tags (
            id        SERIAL PRIMARY KEY,
            filename  VARCHAR(600) NOT NULL REFERENCES library(filename) ON DELETE CASCADE,
            tag       VARCHAR(255) NOT NULL,
            tag_type  VARCHAR(20)  NOT NULL,
            UNIQUE (filename, tag, tag_type)
        )
        """
    )
    _exec("CREATE INDEX IF NOT EXISTS idx_book_tags_filename ON book_tags (filename)")


def migrate_create_reading_progress() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS reading_progress (
            id          SERIAL PRIMARY KEY,
            filename    VARCHAR(600) UNIQUE NOT NULL REFERENCES library(filename) ON DELETE CASCADE,
            cfi         TEXT,
            page        INTEGER,
            progress    INTEGER DEFAULT 0,
            updated_at  TIMESTAMP DEFAULT NOW()
        )
        """
    )


def migrate_create_reading_sessions() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS reading_sessions (
            id        SERIAL PRIMARY KEY,
            filename  VARCHAR(600) NOT NULL REFERENCES library(filename) ON DELETE CASCADE,
            read_at   TIMESTAMP DEFAULT NOW()
        )
        """
    )
    _exec("CREATE INDEX IF NOT EXISTS idx_reading_sessions_filename ON reading_sessions (filename)")


def migrate_create_library_cover_cache() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS library_cover_cache (
            filename    VARCHAR(600) PRIMARY KEY REFERENCES library(filename) ON DELETE CASCADE,
            mime_type   VARCHAR(100) NOT NULL,
            thumb_webp  BYTEA        NOT NULL,
            updated_at  TIMESTAMP DEFAULT NOW()
        )
        """
    )


def migrate_create_credentials() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS credentials (
            id          SERIAL PRIMARY KEY,
            site        VARCHAR(255) UNIQUE NOT NULL,
            username    TEXT NOT NULL,
            password    TEXT NOT NULL,
            updated_at  TIMESTAMP DEFAULT NOW()
        )
        """
    )
    _exec("ALTER TABLE credentials ALTER COLUMN username TYPE TEXT")
    _exec("ALTER TABLE credentials ALTER COLUMN password TYPE TEXT")


def migrate_create_break_patterns() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS break_patterns (
            id           SERIAL PRIMARY KEY,
            pattern_type VARCHAR(20)  NOT NULL,
            pattern      TEXT         NOT NULL,
            enabled      BOOLEAN      DEFAULT TRUE,
            is_default   BOOLEAN      DEFAULT FALSE,
            created_at   TIMESTAMP    DEFAULT NOW(),
            UNIQUE (pattern_type, pattern)
        )
        """
    )


def migrate_seed_break_patterns() -> None:
    conn = direct_connect()
    try:
        with conn:
            with conn.cursor() as cur:
                for pat in _DEFAULT_REGEX:
                    re.compile(pat)
                    cur.execute(
                        """
                        INSERT INTO break_patterns (pattern_type, pattern, is_default)
                        VALUES ('regex', %s, TRUE)
                        ON CONFLICT (pattern_type, pattern) DO NOTHING
                        """,
                        (pat,),
                    )
                for pat in _DEFAULT_CSS:
                    cur.execute(
                        """
                        INSERT INTO break_patterns (pattern_type, pattern, is_default)
                        VALUES ('css_class', %s, TRUE)
                        ON CONFLICT (pattern_type, pattern) DO NOTHING
                        """,
                        (pat,),
                    )
    finally:
        conn.close()


def migrate_create_backup_log() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS backup_log (
            id           SERIAL PRIMARY KEY,
            status       VARCHAR(20)  NOT NULL,
            files_count  INTEGER,
            size_bytes   BIGINT,
            error_msg    TEXT,
            started_at   TIMESTAMP    DEFAULT NOW(),
            finished_at  TIMESTAMP
        )
        """
    )


def migrate_add_rating() -> None:
    _exec("ALTER TABLE library ADD COLUMN IF NOT EXISTS rating SMALLINT NOT NULL DEFAULT 0")


def migrate_create_bookmarks() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS bookmarks (
            id            SERIAL PRIMARY KEY,
            filename      VARCHAR(600) NOT NULL REFERENCES library(filename) ON DELETE CASCADE,
            chapter_index INTEGER      NOT NULL DEFAULT 0,
            scroll_frac   REAL         NOT NULL DEFAULT 0,
            chapter_title VARCHAR(500) NOT NULL DEFAULT '',
            note          TEXT         NOT NULL DEFAULT '',
            created_at    TIMESTAMPTZ  DEFAULT NOW()
        )
        """
    )
    _exec("CREATE INDEX IF NOT EXISTS idx_bookmarks_filename ON bookmarks (filename)")


def migrate_remove_cover_missing_tag() -> None:
    _exec("DELETE FROM book_tags WHERE tag = 'Cover Missing' AND tag_type = 'tag'")


def migrate_create_perf_indexes() -> None:
    # Match library list sorting and common filters.
    _exec(
        """
        CREATE INDEX IF NOT EXISTS idx_library_sort_coalesce
        ON library (
            (COALESCE(publisher, '')),
            (COALESCE(author, '')),
            (COALESCE(series, '')),
            series_index,
            (COALESCE(title, ''))
        )
        """
    )
    _exec("CREATE INDEX IF NOT EXISTS idx_library_needs_review ON library (needs_review)")
    _exec("CREATE INDEX IF NOT EXISTS idx_library_archived ON library (archived)")

    # Speeds grouped reads + recent-read lookups.
    _exec(
        """
        CREATE INDEX IF NOT EXISTS idx_reading_sessions_filename_readat
        ON reading_sessions (filename, read_at DESC)
        """
    )

    # Helps ORDER BY filename, tag fetch for tag-map construction.
    _exec(
        """
        CREATE INDEX IF NOT EXISTS idx_book_tags_filename_tag
        ON book_tags (filename, tag)
        """
    )


def migrate_series_suffix() -> None:
    _exec(
        """
        ALTER TABLE library
        ADD COLUMN IF NOT EXISTS series_suffix VARCHAR(10) NOT NULL DEFAULT ''
        """
    )


def migrate_create_builder_drafts() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS builder_drafts (
            id          UUID PRIMARY KEY DEFAULT gen_random_uuid(),
            title       VARCHAR(500)  NOT NULL,
            author      VARCHAR(255)  NOT NULL,
            publisher   VARCHAR(255)  NOT NULL DEFAULT '',
            source_url  VARCHAR(1000) NOT NULL DEFAULT '',
            chapters    JSONB         NOT NULL DEFAULT '[]',
            created_at  TIMESTAMP     DEFAULT NOW(),
            updated_at  TIMESTAMP     DEFAULT NOW()
        )
        """
    )


def migrate_create_authors() -> None:
    _exec(
        """
        CREATE TABLE IF NOT EXISTS authors (
            id          SERIAL PRIMARY KEY,
            name        VARCHAR(255) UNIQUE NOT NULL,
            url         VARCHAR(1000),
            created_at  TIMESTAMP DEFAULT NOW(),
            updated_at  TIMESTAMP DEFAULT NOW()
        )
        """
    )


def migrate_rename_hiatus() -> None:
    _exec("UPDATE library SET publication_status = 'Long-Term Hold' WHERE publication_status = 'Hiatus'")


def run_migrations() -> None:
    migrate_create_library()
    migrate_create_book_tags()
    migrate_create_reading_progress()
    migrate_create_reading_sessions()
    migrate_create_library_cover_cache()
    migrate_create_credentials()
    migrate_create_break_patterns()
    migrate_create_backup_log()
    migrate_create_perf_indexes()
    migrate_seed_break_patterns()
    migrate_add_rating()
    migrate_remove_cover_missing_tag()
    migrate_create_bookmarks()
    migrate_series_suffix()
    migrate_create_builder_drafts()
    migrate_create_authors()
    migrate_rename_hiatus()