mek_advanced_search
Combine up to five field conditions with AND, OR, NOT to search the MEK catalogue across 24 metadata fields, including author, subject, title, language, and more.
Instructions
Advanced (fielded) search in the MEK catalogue with up to 5 conditions combined via AND / OR / NOT over 24 metadata fields.
Available fields: main_title, subtitle, collection_title, part_title, parallel_title, original_title, series, author, author_role, corporate_author, contributor, contributor_role, publisher, subject, geographic_subject, period_subject, document_type, format, language, original_language, printed_source, rights_owner, rights_note, creative_commons.
Typical patterns:
Works BY a person: field=author, value='Petőfi Sándor'.
Works ABOUT a person: field=subject, value='Petőfi Sándor'.
Person in any role: run separate author / subject / contributor searches (OR across different fields of different records is best done client-side by merging results).
Exclusions: add a condition with operator='not' (e.g. document_type='útikönyv' with 'not' to drop travel guides).
Language filter: field=language, value='magyar' / 'angol' / ...
Values are matched against controlled vocabulary; use mek_browse_index to discover exact term forms, and * for prefixes.
Returns: {total, offset, hits: [{mek_id, url, authors, title, date_added}], has_more, accent_fallback_used}.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| offset | No | Result offset for paging. The server returns up to 100 hits per page; pass 100, 200, ... for further pages. | |
| conditions | Yes | 1 to 5 search conditions. Each condition has a field, a value and an operator ('and'/'or'/'not') that links it to the previous condition. Example (Hungarian-language AI works excluding programming textbooks): [{'field':'subject','value':'mesterséges intelligencia'}, {'field':'language','value':'magyar','operator':'and'}, {'field':'subject','value':'programozás','operator':'not'}] | |
| accent_insensitive | No | If true, accented and unaccented letter forms are treated as equal (MEK 'ékezet nélküli keresés'). Useful when the exact accented form of a name/term is unknown. | |
| auto_accent_fallback | No | If true (default) and the search yields 0 hits, the search is automatically retried with accent-insensitive matching; the response then contains accent_fallback_used=true so you can tell the user the hit set was widened this way. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||