PrinParLat.json

{
  "title": "PrinParLat",
  "profile": "data-package",
  "licenses": [
    {
      "name": "CC BY-SA 4.0 DEED",
      "title": "Creative Commons Attribution-ShareAlike 4.0 International",
      "path": "https://creativecommons.org/licenses/by-sa/4.0/"
    }
  ],
  "contributors": [
    {
      "title": "Matteo Pellegrini",
      "role": "author"
    },
    {
      "title": "Marco Passarotti",
      "role": "contributor"
    },
    {
      "title": "Francesco Mambrini",
      "role": "contributor"
    },
    {
      "title": "Giovanni Moretti",
      "role": "contributor"
    }
  ],
  "keywords": [
    "Latin",
    "verbs",
    "principal parts",
    "inflection classes"
  ],
  "version": "1.1",
  "resources": [
    {
      "name": "forms",
      "type": "table",
      "title": "Inflected forms",
      "path": "forms.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "name": "forms-schema",
        "fields": [
          {
            "name": "form_id",
            "type": "string",
            "title": "Form table row identifiers",
            "description": "These identifiers are specific to form, lexeme, cell triples.",
            "constraints": {
              "required": true,
              "unique": true
            }
          },
          {
            "name": "lexeme",
            "type": "string",
            "title": "Reference to a lexeme identifier",
            "description": "Lexeme identifiers must be unique to paradigms.",
            "constraints": {
              "required": true
            },
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#lexeme"
          },
          {
            "name": "cell",
            "type": "string",
            "title": "Reference to a cell identifier",
            "description": "The set of feature values as would appear in a gloss, separated by dots, eg. prs.ind.1sg or f.pl",
            "constraints": {
              "required": true
            },
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#cell"
          },
          {
            "name": "orth_form",
            "type": "string",
            "title": "Inflected form (orthographic)",
            "description": "The form, given orthographically",
            "missingValues": [
              "#DEF#"
            ],
            "constraints": {
              "pattern": "(a|b|c|d|e|f|g|h|i|k|l|m|n|o|p|q|r|s|t|u|x|y|z)+"
            },
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#orth_form"
          },
          {
            "name": "analysed_orth_form",
            "type": "string",
            "title": "Inflected form with analysis, such as segmentation markers (orthographic)",
            "description": "The form, given orthographically, with markers for analysis.",
            "missingValues": [
              "#DEF#"
            ],
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#analysed_orth_form"
          },
          {
            "name": "flexeme",
            "type": "string",
            "title": "Flexeme identifier",
            "description": "Reference to identifier(s) of the flexeme(s) to which the forms can be assigned, colon separated."
          }
        ],
        "primaryKey": [
          "form_id"
        ],
        "foreignKeys": [
          {
            "fields": [
              "cell"
            ],
            "reference": {
              "resource": "cells",
              "fields": [
                "cell_id"
              ]
            }
          },
          {
            "fields": [
              "lexeme"
            ],
            "reference": {
              "resource": "lexemes",
              "fields": [
                "lexeme_id"
              ]
            }
          }
        ]
      },
      "rdfType": "https://www.paralex-standard.org/paralex_ontology.xml#Form"
    },
    {
      "name": "cells",
      "type": "table",
      "title": "Paradigm cells",
      "path": "cells.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "name": "cells-schema",
        "fields": [
          {
            "name": "cell_id",
            "type": "string",
            "title": "Cell identifier",
            "description": "The set of feature values as would appear in a gloss, separated by dots, eg. prs.ind.1sg or f.pl",
            "constraints": {
              "required": true,
              "unique": true,
              "pattern": "(iprf|pprf|fprf|pass|sbjv|ptcp|prs|fut|prf|act|ind|imp|inf|sup|ger|gdv|nom|gen|dat|acc|voc|abl|sg|pl|1|2|3|m|f|n)(\\.(iprf|pprf|fprf|pass|sbjv|ptcp|prs|fut|prf|act|ind|imp|inf|sup|ger|gdv|nom|gen|dat|acc|voc|abl|sg|pl|1|2|3|m|f|n))*"
            }
          },
          {
            "name": "unimorph",
            "type": "string",
            "title": "Cell in unimorph format",
            "description": "The cell, written following the unimorph schema",
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#unimorph"
          }
        ],
        "primaryKey": [
          "cell_id"
        ],
        "foreignKeys": []
      },
      "rdfType": "https://www.paralex-standard.org/paralex_ontology.xml#Cell"
    },
    {
      "name": "features-values",
      "type": "table",
      "title": "Grammatical features values",
      "path": "features-values.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "name": "features-values-schema",
        "fields": [
          {
            "name": "value_id",
            "type": "string",
            "title": "Grammatical Feature value identifier",
            "description": "Identifier for the grammatical feature value (as found in the cell)",
            "constraints": {
              "required": true,
              "unique": true
            }
          },
          {
            "name": "label",
            "type": "string",
            "title": "label for this row",
            "description": "A human readable label for the row.",
            "rdfProperty": "http://www.w3.org/2000/01/rdf-schema#label"
          },
          {
            "name": "feature",
            "type": "string",
            "title": "feature",
            "description": "The name of the dimension of this feature, eg. case, tense, modality, voice, force, gender, evidentiality, person, number, polarity...",
            "constraints": {
              "required": true
            },
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#feature"
          },
          {
            "name": "canonical_order",
            "type": "integer",
            "title": "Sorting order for visual presentation",
            "description": "The order in which items are canonically presented. Use integers to represent relative order, order is used per-item.",
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#canonical_order"
          }
        ],
        "primaryKey": [
          "value_id"
        ]
      },
      "rdfType": "https://www.paralex-standard.org/paralex_ontology.xml#FeatureValue"
    },
    {
      "name": "flexemes",
      "type": "table",
      "path": "flexemes.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "fields": [
          {
            "name": "flexeme_id",
            "type": "string",
            "title": "Flexeme identifier",
            "description": "Identifier of the flexeme."
          },
          {
            "name": "inflection_class",
            "type": "string",
            "title": "Inflection class identifier",
            "description": "This identifier groups together lexemes of the same inflection class.",
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#inflection_class"
          },
          {
            "name": "lila_id_lemma",
            "type": "integer",
            "title": "lemma ID",
            "description": "ID of the corresponding lemma in the LiLa Knowledge Base."
          },
          {
            "name": "hasInflectionType",
            "type": "string",
            "title": "Inflection Type",
            "description": "Code corresponding to the Inflection Type (i.e., traditional, coarse-grained inflection class) assigned to the lemma in the LiLa Knowledge Base."
          }
        ],
        "primaryKey": [
          "flexeme_id"
        ]
      }
    },
    {
      "name": "graphemes",
      "type": "table",
      "title": "Graphemes inventory",
      "path": "graphemes.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "name": "graphemes-schema",
        "fields": [
          {
            "name": "grapheme_id",
            "type": "string",
            "title": "grapheme representation",
            "description": "These identifiers are specific to graphemes.",
            "constraints": {
              "required": true,
              "unique": true
            },
            "rdfType": "http://linguistics-ontology.org/gold/2010/Grapheme"
          },
          {
            "name": "canonical_order",
            "type": "integer",
            "title": "Sorting order for visual presentation",
            "description": "The order in which items are canonically presented. Use integers to represent relative order, order is used per-item.",
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#canonical_order"
          }
        ],
        "missingValues": [
          ""
        ],
        "primaryKey": [
          "grapheme_id"
        ]
      },
      "rdfType": "https://www.paralex-standard.org/paralex_ontology.xml#Grapheme"
    },
    {
      "name": "inflectionclasses-patterns",
      "type": "table",
      "path": "inflectionclasses-patterns.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "fields": [
          {
            "name": "inflectionclasses-patterns_id",
            "type": "integer",
            "title": "ID",
            "description": "Identifier for the row."
          },
          {
            "name": "inflection_class",
            "type": "string",
            "title": "Inflection class identifier",
            "description": "This identifier groups together lexemes of the same inflection class.",
            "rdfProperty": "https://www.paralex-standard.org/paralex_ontology.xml#inflection_class"
          },
          {
            "name": "pattern",
            "type": "string",
            "title": "Pattern identifier",
            "description": "Reference to the identifier of the alternation pattern."
          }
        ],
        "primaryKey": [
          "inflectionclasses-patterns_id"
        ]
      }
    },
    {
      "name": "lexemes",
      "type": "table",
      "title": "Lexemes",
      "path": "lexemes.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "name": "lexemes-schema",
        "fields": [
          {
            "name": "lexeme_id",
            "type": "string",
            "title": "Identifier for the lexeme",
            "description": "Lexeme identifiers. Often, they are identical to the label (lemma). However, they must be unique to paradigms, distinguishing homonyms with different inflection. For example, the animal mouse/mice and the computer peripheric mouse/mouses would both have the label 'mouse' but could be identified by the lexeme identifiers mouse_1 and mouse_2.",
            "constraints": {
              "required": true,
              "unique": true
            }
          },
          {
            "name": "label",
            "type": "string",
            "title": "label for this row",
            "description": "A human readable label for the row.",
            "rdfProperty": "http://www.w3.org/2000/01/rdf-schema#label"
          }
        ],
        "primaryKey": [
          "lexeme_id"
        ],
        "foreignKeys": [],
        "foreignKey": []
      },
      "rdfType": "https://www.paralex-standard.org/paralex_ontology.xml#Lexeme"
    },
    {
      "name": "patterns",
      "type": "table",
      "path": "patterns.csv",
      "scheme": "file",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "fields": [
          {
            "name": "pattern_id",
            "type": "string",
            "title": "Pattern ID",
            "description": "Identifier of the alternation pattern."
          },
          {
            "name": "pattern_alternation",
            "type": "string",
            "title": "Alternation pattern",
            "description": "Alternation pattern between two cells."
          },
          {
            "name": "cell_left",
            "type": "string",
            "title": "Left cell",
            "description": "Reference to the identifier of the cells on the left for the relevant alternation pattern."
          },
          {
            "name": "cell_right",
            "type": "string",
            "title": "Right cell",
            "description": "Reference to the identifier of the cells on the right for the relevant alternation pattern."
          }
        ],
        "primaryKey": [
          "pattern_id"
        ],
        "foreignKeys": [
          {
            "fields": [
              "cell_left"
            ],
            "reference": {
              "resource": "cells",
              "fields": [
                "cell_id"
              ]
            }
          },
          {
            "fields": [
              "cell_right"
            ],
            "reference": {
              "resource": "cells",
              "fields": [
                "cell_id"
              ]
            }
          }
        ]
      }
    }
  ],
  "citation": "Pellegrini, M. & Passarotti, M. & Mambrini, F. & Moretti, G. 2023. PrinParLat. Online resource.",
  "id": "http://doi.org/10.5281/zenodo.8027826",
  "basepath": "C:\\Users\\matteo.pellegrini\\OneDrive - Università Cattolica del Sacro Cuore\\Desktop\\lavoro\\Gogs repo\\PrinParLat"
}