Pete/internal/storage/schema.go

package storage

const schema = `
CREATE TABLE IF NOT EXISTS stories (
    id            INTEGER PRIMARY KEY AUTOINCREMENT,
    guid          TEXT UNIQUE NOT NULL,
    headline      TEXT NOT NULL,
    lede          TEXT,
    content       TEXT,
    image_url     TEXT,
    article_url   TEXT NOT NULL,
    url_canonical TEXT,
    headline_norm TEXT,
    source        TEXT NOT NULL,
    platforms     TEXT,
    channel       TEXT,
    classified    INTEGER NOT NULL DEFAULT 0,
    paywalled     INTEGER NOT NULL DEFAULT 0,
    seen_at       INTEGER NOT NULL,
    published_at  INTEGER
);

CREATE TABLE IF NOT EXISTS post_log (
    id            INTEGER PRIMARY KEY AUTOINCREMENT,
    guid          TEXT NOT NULL,
    channel       TEXT NOT NULL,
    event_id      TEXT,
    url_canonical TEXT,
    posted_at     INTEGER NOT NULL,
    forced        INTEGER NOT NULL DEFAULT 0
);

CREATE TABLE IF NOT EXISTS round_robin_state (
    id           INTEGER PRIMARY KEY CHECK (id = 1),
    last_channel TEXT,
    last_tick_at INTEGER NOT NULL DEFAULT 0
);

CREATE TABLE IF NOT EXISTS reactions (
    id         INTEGER PRIMARY KEY AUTOINCREMENT,
    post_guid  TEXT NOT NULL,
    channel    TEXT NOT NULL,
    event_id   TEXT NOT NULL,
    emoji      TEXT NOT NULL,
    user_id    TEXT NOT NULL,
    reacted_at INTEGER NOT NULL
);

CREATE TABLE IF NOT EXISTS user_preferences (
    user_sub   TEXT PRIMARY KEY,
    prefs      TEXT NOT NULL,
    username   TEXT,
    email      TEXT,
    updated_at INTEGER NOT NULL
);

-- Per-user read + bookmark state for signed-in visitors, keyed by OIDC subject.
-- One row carries both signals; a NULL timestamp means "not set". A row with
-- both timestamps NULL is meaningless and is pruned, so presence of a row means
-- the story is read, bookmarked, or both.
CREATE TABLE IF NOT EXISTS user_story_state (
    user_sub      TEXT NOT NULL,
    story_id      INTEGER NOT NULL,
    read_at       INTEGER,
    bookmarked_at INTEGER,
    PRIMARY KEY (user_sub, story_id)
);

-- Aggregate web usage. page_views holds running view counts keyed by a coarse
-- path label ("home", channel slug, …) and the UTC day, so we can report both
-- all-time totals and per-day breakdowns without storing any per-request rows.
CREATE TABLE IF NOT EXISTS page_views (
    path  TEXT NOT NULL,
    day   INTEGER NOT NULL,           -- unix day (floor(unix / 86400)), UTC
    views INTEGER NOT NULL DEFAULT 0,
    PRIMARY KEY (path, day)
);

-- Per-source poll health, one row per configured feed (keyed by source name).
-- Written on every poll (success and failure) so the owner-facing dashboard can
-- show which feeds are healthy without keeping the poller's in-memory state.
-- last_success_at / last_item_count survive failures so a broken feed still
-- shows when it last worked and how much it last returned.
CREATE TABLE IF NOT EXISTS source_health (
    source               TEXT PRIMARY KEY,
    last_poll_at         INTEGER,           -- unix, most recent poll attempt
    last_success_at      INTEGER,           -- unix, most recent successful fetch
    last_error           TEXT,              -- last failure message ('' when healthy)
    consecutive_failures INTEGER NOT NULL DEFAULT 0,
    last_item_count      INTEGER NOT NULL DEFAULT 0, -- items in the last successful fetch
    updated_at           INTEGER NOT NULL
);

-- Web Push subscriptions for signed-in users, one row per browser/device
-- endpoint. p256dh + auth are the client's encryption keys (RFC 8291); the
-- server needs them to encrypt each push. last_notified_at is the per-endpoint
-- digest watermark: the sender only counts stories seen after it. A user can
-- have several endpoints (phone, desktop) — each is notified independently.
CREATE TABLE IF NOT EXISTS push_subscriptions (
    endpoint         TEXT PRIMARY KEY,
    user_sub         TEXT NOT NULL,
    p256dh           TEXT NOT NULL,
    auth             TEXT NOT NULL,
    created_at       INTEGER NOT NULL,
    last_notified_at INTEGER NOT NULL
);

-- Privacy-preserving daily unique estimate. visitor is a salted hash of
-- IP+User-Agent; the salt rotates every UTC day and is never persisted, so the
-- hashes are irreversible and cannot be linked across days. We keep only enough
-- to dedup within a single day, then prune.
CREATE TABLE IF NOT EXISTS daily_visitors (
    day     INTEGER NOT NULL,
    visitor TEXT NOT NULL,
    PRIMARY KEY (day, visitor)
);

-- Per-story read counts, keyed by story id and UTC day. Incremented whenever a
-- visitor opens a story in reader mode (/api/article). The day dimension lets
-- us surface "popular this week" without a separate rollup; summing across all
-- days gives the all-time count shown on cards. Rows age out with their story
-- via the foreign-key-less prune in RunMaintenance.
CREATE TABLE IF NOT EXISTS story_views (
    story_id INTEGER NOT NULL,
    day      INTEGER NOT NULL,           -- unix day (floor(unix / 86400)), UTC
    views    INTEGER NOT NULL DEFAULT 0,
    PRIMARY KEY (story_id, day)
);

CREATE UNIQUE INDEX IF NOT EXISTS idx_post_log_guid_channel ON post_log(guid, channel);
CREATE INDEX IF NOT EXISTS idx_post_log_event_id ON post_log(event_id);
CREATE INDEX IF NOT EXISTS idx_post_log_channel_posted ON post_log(channel, posted_at);
CREATE INDEX IF NOT EXISTS idx_post_log_canonical_channel ON post_log(url_canonical, channel, posted_at);
CREATE INDEX IF NOT EXISTS idx_stories_classified_source ON stories(classified, source);
CREATE INDEX IF NOT EXISTS idx_stories_channel_classified_seen ON stories(channel, classified, seen_at DESC);
CREATE INDEX IF NOT EXISTS idx_stories_classified_seen ON stories(classified, seen_at DESC);
CREATE INDEX IF NOT EXISTS idx_stories_image_url ON stories(image_url) WHERE image_url IS NOT NULL AND image_url <> '';
CREATE UNIQUE INDEX IF NOT EXISTS idx_stories_url_canonical ON stories(url_canonical) WHERE url_canonical IS NOT NULL AND url_canonical <> '';
CREATE UNIQUE INDEX IF NOT EXISTS idx_stories_source_headline_norm ON stories(source, headline_norm) WHERE headline_norm IS NOT NULL AND headline_norm <> '';
CREATE INDEX IF NOT EXISTS idx_reactions_post_guid ON reactions(post_guid);
CREATE UNIQUE INDEX IF NOT EXISTS idx_reactions_event_id ON reactions(event_id);
CREATE INDEX IF NOT EXISTS idx_page_views_day ON page_views(day);
CREATE INDEX IF NOT EXISTS idx_daily_visitors_day ON daily_visitors(day);
CREATE INDEX IF NOT EXISTS idx_story_views_day ON story_views(day);
CREATE INDEX IF NOT EXISTS idx_user_state_bookmarks ON user_story_state(user_sub, bookmarked_at) WHERE bookmarked_at IS NOT NULL;
CREATE INDEX IF NOT EXISTS idx_user_state_reads ON user_story_state(user_sub, read_at) WHERE read_at IS NOT NULL;
CREATE INDEX IF NOT EXISTS idx_push_sub_user ON push_subscriptions(user_sub);
`

const ftsSchema = `
CREATE VIRTUAL TABLE stories_fts USING fts5(
    guid UNINDEXED,
    headline,
    lede,
    source UNINDEXED,
    platforms UNINDEXED,
    content='stories',
    content_rowid='id'
);
`

const ftsTriggers = `
CREATE TRIGGER stories_fts_insert AFTER INSERT ON stories BEGIN
    INSERT INTO stories_fts(rowid, guid, headline, lede, source, platforms)
    VALUES (new.id, new.guid, new.headline, new.lede, new.source, new.platforms);
END;

CREATE TRIGGER stories_fts_delete AFTER DELETE ON stories BEGIN
    INSERT INTO stories_fts(stories_fts, rowid, guid, headline, lede, source, platforms)
    VALUES ('delete', old.id, old.guid, old.headline, old.lede, old.source, old.platforms);
END;

CREATE TRIGGER stories_fts_update AFTER UPDATE ON stories BEGIN
    INSERT INTO stories_fts(stories_fts, rowid, guid, headline, lede, source, platforms)
    VALUES ('delete', old.id, old.guid, old.headline, old.lede, old.source, old.platforms);
    INSERT INTO stories_fts(rowid, guid, headline, lede, source, platforms)
    VALUES (new.id, new.guid, new.headline, new.lede, new.source, new.platforms);
END;
`