119 lines
3.6 KiB
Plaintext
119 lines
3.6 KiB
Plaintext
-- 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)
|
|
}
|
|
|
|
surface SearchIndexRuntimeSurface {
|
|
facing _: SearchRuntime
|
|
|
|
provides:
|
|
SearchIndexUpdated(post)
|
|
SearchIndexUpdated(media)
|
|
}
|
|
|
|
value StemmerLanguage {
|
|
-- Snowball stemmers for 24 languages
|
|
-- ISO 639-1 to Snowball mapping
|
|
-- Applied to both indexing and query processing
|
|
code: String
|
|
}
|
|
|
|
surface StemmerLanguageSurface {
|
|
context language: StemmerLanguage
|
|
|
|
exposes:
|
|
language.code
|
|
}
|
|
|
|
entity PostSearchIndex {
|
|
-- Full-text index projection
|
|
-- Indexed fields: title, excerpt, content, tags, categories
|
|
-- Plus all translation titles, excerpts, and content
|
|
post: post/Post
|
|
stemmed_content: String
|
|
}
|
|
|
|
entity MediaSearchIndex {
|
|
-- Full-text index projection
|
|
-- Indexed fields: title, alt, caption, original_name, tags
|
|
-- Plus all translation titles, alts, and captions
|
|
media: media/Media
|
|
stemmed_content: 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)
|
|
let stemmed_query = stem(query, detect_language(query))
|
|
let matched = search_fts(MediaSearchIndex, stemmed_query)
|
|
ensures: SearchResults(
|
|
media: matched
|
|
)
|
|
}
|
|
|
|
rule IndexPost {
|
|
when: SearchIndexUpdated(post)
|
|
-- Stems: title + excerpt + content + tags + categories
|
|
-- Plus all translations' title + excerpt + content
|
|
let all_text = concat_post_text(post)
|
|
-- Concatenates: post.title, post.excerpt, post.content,
|
|
-- join(post.tags, " "), join(post.categories, " "),
|
|
-- and all translations' title, excerpt, content
|
|
let index_entry = PostSearchIndex{post: post}
|
|
ensures:
|
|
if exists index_entry:
|
|
index_entry.stemmed_content = stem(all_text)
|
|
else:
|
|
PostSearchIndex.created(post: post, stemmed_content: stem(all_text))
|
|
}
|
|
|
|
rule IndexMedia {
|
|
when: SearchIndexUpdated(media)
|
|
-- Stems: title + alt + caption + original_name + tags
|
|
-- Plus all translations' title, alt, caption
|
|
let all_text = concat_media_text(media)
|
|
-- Concatenates: media.title, media.alt, media.caption,
|
|
-- media.original_name, join(media.tags, " "),
|
|
-- and all translations' title, alt, caption
|
|
let index_entry = MediaSearchIndex{media: media}
|
|
ensures:
|
|
if exists index_entry:
|
|
index_entry.stemmed_content = stem(all_text)
|
|
else:
|
|
MediaSearchIndex.created(media: media, stemmed_content: stem(all_text))
|
|
}
|