feat: add tags_search and contributors_search fields to database

Schema changes:
- Add tags_search TEXT[] column for case-insensitive, punctuation-free search
- Add contributors_search TEXT[] column for case-insensitive, punctuation-free search
- Create GIN indexes for fast array searches on both search fields

Query updates:
- CreateMediaItem: Include tags_search and contributors_search parameters
- UpdateMediaItem: Include tags_search and contributors_search parameters
- SearchMediaItems: Search against tags_search instead of tags
- SearchMediaItems: Search against contributors_search instead of contributors
- SearchMediaItemsFuzzy: Use tags_search and contributors_search for fuzzy matching
- Update ranking and priority logic to use search fields

Benefits:
- Case-insensitive search: "acme corp" finds "ACME CORP."
- Punctuation-agnostic search: "oreilly" finds "O'Reilly Media"
- Better UX: Users don't need to match exact casing or punctuation
- Improved performance with dedicated GIN indexes

Relates to Tags & Contributors Migration Phases 5 & 8
This commit is contained in:
2026-02-08 11:05:18 -05:00
parent 08e823d6ab
commit c606a7ffcc
3 changed files with 473 additions and 413 deletions
+20 -18
View File
@@ -207,24 +207,26 @@ type MediaItems struct {
// Open Library identifier for integration
OpenlibraryID pgtype.Text `db:"openlibrary_id" json:"openlibrary_id"`
// Google Books identifier for integration
GoogleBooksID pgtype.Text `db:"google_books_id" json:"google_books_id"`
AddedByAdminID pgtype.UUID `db:"added_by_admin_id" json:"added_by_admin_id"`
CreatedAt pgtype.Timestamptz `db:"created_at" json:"created_at"`
UpdatedAt pgtype.Timestamptz `db:"updated_at" json:"updated_at"`
FormatGroup string `db:"format_group" json:"format_group"`
FormatMimetype pgtype.Text `db:"format_mimetype" json:"format_mimetype"`
IsReflowable pgtype.Bool `db:"is_reflowable" json:"is_reflowable"`
HasFixedLayout pgtype.Bool `db:"has_fixed_layout" json:"has_fixed_layout"`
TotalCharacters pgtype.Int8 `db:"total_characters" json:"total_characters"`
ChapterCount pgtype.Int4 `db:"chapter_count" json:"chapter_count"`
EntitlementID pgtype.Text `db:"entitlement_id" json:"entitlement_id"`
RevisionNumber pgtype.Int4 `db:"revision_number" json:"revision_number"`
KoboContentID pgtype.Text `db:"kobo_content_id" json:"kobo_content_id"`
KoboMetadata []byte `db:"kobo_metadata" json:"kobo_metadata"`
FileSha256 pgtype.Text `db:"file_sha256" json:"file_sha256"`
OpfIdentifier pgtype.Text `db:"opf_identifier" json:"opf_identifier"`
OpfUuid pgtype.Text `db:"opf_uuid" json:"opf_uuid"`
HashConfidence pgtype.Text `db:"hash_confidence" json:"hash_confidence"`
GoogleBooksID pgtype.Text `db:"google_books_id" json:"google_books_id"`
AddedByAdminID pgtype.UUID `db:"added_by_admin_id" json:"added_by_admin_id"`
CreatedAt pgtype.Timestamptz `db:"created_at" json:"created_at"`
UpdatedAt pgtype.Timestamptz `db:"updated_at" json:"updated_at"`
FormatGroup string `db:"format_group" json:"format_group"`
FormatMimetype pgtype.Text `db:"format_mimetype" json:"format_mimetype"`
IsReflowable pgtype.Bool `db:"is_reflowable" json:"is_reflowable"`
HasFixedLayout pgtype.Bool `db:"has_fixed_layout" json:"has_fixed_layout"`
TotalCharacters pgtype.Int8 `db:"total_characters" json:"total_characters"`
ChapterCount pgtype.Int4 `db:"chapter_count" json:"chapter_count"`
EntitlementID pgtype.Text `db:"entitlement_id" json:"entitlement_id"`
RevisionNumber pgtype.Int4 `db:"revision_number" json:"revision_number"`
KoboContentID pgtype.Text `db:"kobo_content_id" json:"kobo_content_id"`
KoboMetadata []byte `db:"kobo_metadata" json:"kobo_metadata"`
TagsSearch []string `db:"tags_search" json:"tags_search"`
ContributorsSearch []string `db:"contributors_search" json:"contributors_search"`
FileSha256 pgtype.Text `db:"file_sha256" json:"file_sha256"`
OpfIdentifier pgtype.Text `db:"opf_identifier" json:"opf_identifier"`
OpfUuid pgtype.Text `db:"opf_uuid" json:"opf_uuid"`
HashConfidence pgtype.Text `db:"hash_confidence" json:"hash_confidence"`
}
type MediaNotes struct {