cjk-autospace/rules/golden-vectors.schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://juzhen.dev/schemas/golden-vectors.schema.json",
  "title": "Juzhen shared rules golden vectors",
  "type": "object",
  "additionalProperties": false,
  "required": [ "schemaVersion", "rulesetVersion", "vectors" ],
  "properties": {
    "$schema": { "type": "string" },
    "schemaVersion": { "const": 1 },
    "rulesetVersion": {
      "type": "string",
      "pattern": "^(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)$"
    },
    "vectors": {
      "type": "array",
      "minItems": 20,
      "items": {
        "oneOf": [
          { "$ref": "#/$defs/languageVector" },
          { "$ref": "#/$defs/punctuationClassVector" },
          { "$ref": "#/$defs/punctuationStyleVector" },
          { "$ref": "#/$defs/punctuationAdjacencyVector" },
          { "$ref": "#/$defs/spacingVector" },
          { "$ref": "#/$defs/ivsAtomVector" },
          { "$ref": "#/$defs/jinzeVector" },
          { "$ref": "#/$defs/orphanVector" }
        ]
      }
    }
  },
  "$defs": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
    },
    "punctuationClass": {
      "enum": [ "stop", "pause", "open", "close", "middle", "liga" ]
    },
    "style": {
      "enum": [ "quanjiao", "kaiming", "banjiao" ]
    },
    "atoms": {
      "type": "array",
      "minItems": 1,
      "items": { "type": "string", "minLength": 1 }
    },
    "languageVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "language-classification" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "lang" ],
          "properties": {
            "lang": { "type": "string" }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "langClass" ],
          "properties": {
            "langClass": { "enum": [ "zh-Hans", "zh-Hant", "ja", "other" ] }
          }
        }
      }
    },
    "punctuationClassVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "punctuation-classification" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "character" ],
          "properties": {
            "character": { "type": "string", "minLength": 1 }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "punctuationClass" ],
          "properties": {
            "punctuationClass": {
              "oneOf": [ { "$ref": "#/$defs/punctuationClass" }, { "type": "null" } ]
            }
          }
        }
      }
    },
    "punctuationStyleVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "punctuation-style" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "style", "punctuationClass" ],
          "properties": {
            "style": { "$ref": "#/$defs/style" },
            "punctuationClass": { "$ref": "#/$defs/punctuationClass" }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "halfWidth" ],
          "properties": {
            "halfWidth": { "type": "boolean" }
          }
        }
      }
    },
    "punctuationAdjacencyVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "punctuation-adjacency" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "left", "right" ],
          "properties": {
            "left": { "$ref": "#/$defs/punctuationClass" },
            "right": { "$ref": "#/$defs/punctuationClass" }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "squeezeLeft", "squeezeRight" ],
          "properties": {
            "squeezeLeft": { "type": "boolean" },
            "squeezeRight": { "type": "boolean" }
          }
        }
      }
    },
    "spacingVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "spacing" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "text" ],
          "properties": {
            "text": { "type": "string" }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "managedGaps", "normalizedText" ],
          "properties": {
            "managedGaps": { "type": "integer", "minimum": 0 },
            "normalizedText": { "type": "string" },
            "gapEm": { "const": 0.25 },
            "authorSpaceDisposition": {
              "enum": [ "remove-and-use-managed-gap", "remove-without-gap" ]
            }
          }
        }
      }
    },
    "ivsAtomVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "ivs-atom" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "text" ],
          "properties": {
            "text": { "type": "string", "minLength": 1 }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "atoms" ],
          "properties": {
            "atoms": { "$ref": "#/$defs/atoms" }
          }
        }
      }
    },
    "jinzeVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "jinze" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "left", "right" ],
          "properties": {
            "left": { "type": "string", "minLength": 1 },
            "right": { "type": "string", "minLength": 1 }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "prohibitedBreak" ],
          "properties": {
            "prohibitedBreak": { "type": "boolean" },
            "reason": { "enum": [ "before-stop", "before-close", "after-open" ] },
            "atoms": { "$ref": "#/$defs/atoms" }
          }
        }
      }
    },
    "orphanVector": {
      "type": "object",
      "additionalProperties": false,
      "required": [ "id", "category", "input", "expected" ],
      "properties": {
        "id": { "$ref": "#/$defs/id" },
        "category": { "const": "orphan" },
        "input": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "text", "minimum" ],
          "properties": {
            "text": { "type": "string", "minLength": 1 },
            "minimum": { "type": "integer", "minimum": 1 }
          }
        },
        "expected": {
          "type": "object",
          "additionalProperties": false,
          "required": [ "meaningfulCjkCount", "protectedSuffix" ],
          "properties": {
            "meaningfulCjkCount": { "type": "integer", "minimum": 0 },
            "protectedSuffix": {
              "oneOf": [ { "type": "string" }, { "type": "null" } ]
            },
            "atoms": { "$ref": "#/$defs/atoms" }
          }
        }
      }
    }
  }
}