bDS2/specs/search.allium

-- allium: 1
-- bDS Full-Text Search
-- Scope: core (Wave 1 — in-app full-text search with Snowball stemmers)
-- Distilled from: src/main/engine/PostEngine.ts (FTS methods),
--   MediaEngine.ts (FTS methods), stemmer.ts

use "./post.allium" as post
use "./media.allium" as media

surface SearchControlSurface {
    facing _: SearchOperator

    provides:
        SearchPostsRequested(query, filters)
        SearchMediaRequested(query, filters)
}

surface SearchIndexRuntimeSurface {
    facing _: SearchRuntime

    provides:
        SearchIndexUpdated(post)
        SearchIndexUpdated(media)
}

value StemmerLanguage {
    -- Snowball stemmers via library (Stemex)
    -- Languages with a Snowball algorithm get real stemming;
    -- others pass through unstemmed
    -- Applied to both indexing and query processing
    code: String
}

surface StemmerLanguageSurface {
    context language: StemmerLanguage

    exposes:
        language.code
}

entity PostSearchIndex {
    -- FTS5 virtual table with per-field stemmed columns
    -- Each field is stemmed independently; translations are
    -- stemmed with their own language stemmer and appended
    -- to the corresponding field
    post: post/Post
    title: String
    excerpt: String
    content: String
    tags: String
    categories: String
}

entity MediaSearchIndex {
    -- FTS5 virtual table with per-field stemmed columns
    -- Each field is stemmed independently; translations are
    -- stemmed with their own language stemmer and appended
    -- to the corresponding field
    media: media/Media
    title: String
    alt: String
    caption: String
    original_name: String
    tags: String
}

invariant CrossLanguageStemming {
    -- Search index uses Snowball stemmer matched to content language
    -- A post in German is stemmed with the German stemmer
    -- Translations are stemmed with their respective language stemmers
    -- Query-time stemming matches the index language
}

rule SearchPosts {
    when: SearchPostsRequested(query, filters)
    -- Full-text search with optional filters:
    --   status, tags, categories, language, missingTranslationLanguage,
    --   year, month, date range (from/to)
    -- Returns paginated results with total count
    let stemmed_query = stem(query, detect_language(query))
    let matched = search_fts(PostSearchIndex, stemmed_query, filters)
    ensures: SearchResults(
        posts: matched,
        total: matched.count,
        offset: filters.offset,
        limit: filters.limit
    )
}

rule SearchMedia {
    when: SearchMediaRequested(query, filters)
    -- Full-text search with optional filters:
    --   language, tags, year, month, date range (from/to)
    -- Returns paginated results with total count
    let stemmed_query = stem(query, detect_language(query))
    let matched = search_fts(MediaSearchIndex, stemmed_query, filters)
    ensures: SearchResults(
        media: matched,
        total: matched.count,
        offset: filters.offset,
        limit: filters.limit
    )
}

rule IndexPost {
    when: SearchIndexUpdated(post)
    -- Delete-and-reinsert: no in-place update for FTS5 rows
    -- Each field is stemmed per-language; translations are stemmed
    -- with their own language stemmer and joined into the same field
    let lang = post.language
    let translations = post.translations
    let title = join_stemmed(
        stem(post.title, lang),
        for t in translations: stem(t.title, t.language)
    )
    let excerpt = join_stemmed(
        stem(post.excerpt, lang),
        for t in translations: stem(t.excerpt, t.language)
    )
    let content = join_stemmed(
        stem(post.content, lang),
        for t in translations: stem(t.content, t.language)
    )
    let tags = stem(join(post.tags, " "), lang)
    let categories = stem(join(post.categories, " "), lang)
    ensures: not exists PostSearchIndex{post: post}
    ensures: PostSearchIndex.created(
        post: post,
        title: title,
        excerpt: excerpt,
        content: content,
        tags: tags,
        categories: categories
    )
}

rule IndexMedia {
    when: SearchIndexUpdated(media)
    -- Delete-and-reinsert: no in-place update for FTS5 rows
    -- Each field is stemmed per-language; translations are stemmed
    -- with their own language stemmer and joined into the same field
    let lang = media.language
    let translations = media.translations
    let title = join_stemmed(
        stem(media.title, lang),
        for t in translations: stem(t.title, t.language)
    )
    let alt = join_stemmed(
        stem(media.alt, lang),
        for t in translations: stem(t.alt, t.language)
    )
    let caption = join_stemmed(
        stem(media.caption, lang),
        for t in translations: stem(t.caption, t.language)
    )
    let original_name = stem(media.original_name, lang)
    let tags = stem(join(media.tags, " "), lang)
    ensures: not exists MediaSearchIndex{media: media}
    ensures: MediaSearchIndex.created(
        media: media,
        title: title,
        alt: alt,
        caption: caption,
        original_name: original_name,
        tags: tags
    )
}