LINDAT MorphoDiTa API

# Provenance: DERIVED by API Evangelist from the operator's own published REST API
# reference, then verified against live responses from the production host.
# UFAL publishes human documentation, not a machine-readable contract, for this service.
# method: derived
# x-source-url: https://lindat.mff.cuni.cz/services/morphodita/api-reference.php
# generated: 2026-09-01
# x-operator: institution (Institute of Formal and Applied Linguistics, Faculty of
#   Mathematics and Physics, Charles University — host lindat.mff.cuni.cz is the
#   institution's own registrable domain)
openapi: 3.2.0
info:
  title: LINDAT MorphoDiTa API
  version: '1'
  summary: Morphological analysis, generation, tagging and tokenization operated by ÚFAL at Charles University.
  description: >-
    Public REST API for MorphoDiTa (Morphological Dictionary and Tagger) operated by the Institute
    of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University,
    and delivered through the LINDAT/CLARIAH-CZ research infrastructure. Provides morphological
    analysis, morphological generation, part-of-speech tagging and tokenization, principally for
    Czech. No API key is required.
    Derived by API Evangelist from the published REST API reference at
    https://lindat.mff.cuni.cz/services/morphodita/api-reference.php and verified against live
    responses from https://lindat.mff.cuni.cz/services/morphodita/api on 2026-09-01.
  contact:
    name: LINDAT/CLARIAH-CZ Helpdesk
    email: lindat-help@ufal.mff.cuni.cz
    url: https://lindat.mff.cuni.cz/user_feedback
  license:
    name: CC BY-NC-SA
    url: https://creativecommons.org/licenses/by-nc-sa/4.0/
  termsOfService: https://lindat.mff.cuni.cz/en/terms-of-use
servers:
  - url: https://lindat.mff.cuni.cz/services/morphodita/api
    description: Production service operated by ÚFAL, Charles University
tags:
  - name: morphodita
    description: Morphological analysis, generation, tagging and tokenization operations
paths:
  /models:
    get:
      operationId: listMorphoDiTaModels
      summary: List available MorphoDiTa models
      tags: [morphodita]
      responses:
        '200':
          description: Model inventory
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelList'
  /tag:
    get:
      operationId: tagText
      summary: Part-of-speech tag and lemmatize the supplied text
      tags: [morphodita]
      parameters:
        - $ref: '#/components/parameters/Data'
        - $ref: '#/components/parameters/Model'
        - $ref: '#/components/parameters/Guesser'
        - $ref: '#/components/parameters/Input'
        - $ref: '#/components/parameters/ConvertTagset'
        - $ref: '#/components/parameters/Derivation'
        - name: output
          in: query
          required: false
          description: Output format. `json` returns an array of sentences of token objects carrying `token`, `lemma`, `tag` and optionally `space`.
          schema:
            type: string
            enum: [json, xml, vertical]
            default: xml
      responses:
        '200':
          description: Tagging result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceResponse'
  /analyze:
    get:
      operationId: analyzeText
      summary: Perform morphological analysis of the supplied text
      tags: [morphodita]
      parameters:
        - $ref: '#/components/parameters/Data'
        - $ref: '#/components/parameters/Model'
        - $ref: '#/components/parameters/Guesser'
        - $ref: '#/components/parameters/Input'
        - $ref: '#/components/parameters/ConvertTagset'
        - $ref: '#/components/parameters/Derivation'
        - name: output
          in: query
          required: false
          description: Output format. `json` returns token objects each carrying an `analyses` array of `lemma`/`tag` pairs.
          schema:
            type: string
            enum: [json, xml, vertical]
            default: xml
      responses:
        '200':
          description: Analysis result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceResponse'
  /generate:
    get:
      operationId: generateForms
      summary: Perform morphological generation from supplied lemmas
      tags: [morphodita]
      parameters:
        - $ref: '#/components/parameters/Data'
        - $ref: '#/components/parameters/Model'
        - $ref: '#/components/parameters/Guesser'
        - $ref: '#/components/parameters/ConvertTagset'
        - name: output
          in: query
          required: false
          description: Output format. `json` returns an array of lemma results, each an array of objects carrying `form`, `lemma` and `tag`.
          schema:
            type: string
            enum: [json, vertical]
            default: vertical
      responses:
        '200':
          description: Generation result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceResponse'
  /tokenize:
    get:
      operationId: tokenizeTextMorphoDiTa
      summary: Tokenize the supplied text
      tags: [morphodita]
      parameters:
        - $ref: '#/components/parameters/Data'
        - $ref: '#/components/parameters/Model'
        - name: output
          in: query
          required: false
          description: Output format.
          schema:
            type: string
            enum: [json, xml, vertical]
            default: xml
      responses:
        '200':
          description: Tokenization result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceResponse'
components:
  parameters:
    Data:
      name: data
      in: query
      required: true
      description: Input text in UTF-8.
      schema:
        type: string
    Model:
      name: model
      in: query
      required: false
      description: Model to use; accepts a full name, a name without the version suffix, or a prefix.
      schema:
        type: string
    Guesser:
      name: guesser
      in: query
      required: false
      description: Use the morphological guesser for unknown words.
      schema:
        type: string
        enum: ['yes', 'no']
        default: 'yes'
    Input:
      name: input
      in: query
      required: false
      description: Input format to use.
      schema:
        type: string
        enum: [untokenized, vertical]
        default: untokenized
    ConvertTagset:
      name: convert_tagset
      in: query
      required: false
      description: Apply the specified tag-set converter.
      schema:
        type: string
        enum: [pdt_to_conll2009, strip_lemma_comment, strip_lemma_id]
    Derivation:
      name: derivation
      in: query
      required: false
      description: Apply the specified morphological derivation to lemmas.
      schema:
        type: string
        enum: [none, root, path, tree]
        default: none
  schemas:
    ModelList:
      type: object
      properties:
        models:
          type: object
          additionalProperties:
            type: array
            items:
              type: string
              enum: [tag, analyze, generate, tokenize]
        default_model:
          type: string
      required: [models, default_model]
    ServiceResponse:
      type: object
      description: Common LINDAT web-service response envelope.
      properties:
        model:
          type: string
        acknowledgements:
          type: array
          items:
            type: string
            format: uri
        result:
          description: Output in the requested output format — a string for xml/vertical, a structured array for json.
      required: [model, result]