{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "$id": "https://github.com/hebrew-unified-nlp/schema/v2.1.0",
  "title": "HebrewUnifiedNLPResult",
  "description": "Async parallel Hebrew/English NLP with cross-platform sentence breaking - outputs sentence array with per-sentence language detection",
  "type": "object",
  "required": [
    "meta",
    "input",
    "sentences"
  ],
  "properties": {
    "meta": {
      "type": "object",
      "description": "Processing metadata",
      "required": [
        "version",
        "timestamp",
        "sentence_count"
      ],
      "properties": {
        "version": {
          "type": "string",
          "pattern": "^\\d+\\.\\d+\\.\\d+$",
          "example": "2025.12.5"
        },
        "timestamp": {
          "type": "string",
          "format": "date-time"
        },
        "models": {
          "type": "object",
          "properties": {
            "phonikud": {
              "type": "string",
              "description": "Phonikud model name"
            },
            "piper": {
              "type": "string",
              "description": "Piper voice manager info"
            },
            "dictabert": {
              "type": "string",
              "description": "DictaBERT model path"
            }
          }
        },
        "processing_time_ms": {
          "type": "number",
          "minimum": 0,
          "description": "Total processing time for all sentences"
        },
        "sentence_count": {
          "type": "integer",
          "minimum": 0,
          "description": "Number of sentences detected"
        },
        "parallel_workers": {
          "type": "integer",
          "minimum": 1,
          "description": "Number of parallel workers used"
        },
        "sentence_breaker": {
          "type": "string",
          "description": "Sentence breaking backend used",
          "enum": [
            "pysbd",
            "pysbd-en",
            "icu",
            "wtpsplit",
            "regex"
          ]
        }
      }
    },
    "translations": {
      "type": "object",
      "description": "Bilingual label translations (Hebrew/English)",
      "properties": {
        "pos": {
          "type": "object",
          "description": "Part-of-speech translations",
          "additionalProperties": {
            "$ref": "#/definitions/BilingualLabel"
          }
        },
        "dep": {
          "type": "object",
          "description": "Dependency relation translations",
          "additionalProperties": {
            "$ref": "#/definitions/BilingualLabel"
          }
        },
        "ner": {
          "type": "object",
          "description": "Named entity type translations",
          "additionalProperties": {
            "$ref": "#/definitions/BilingualLabel"
          }
        },
        "prefix": {
          "type": "object",
          "description": "Prefix type translations",
          "additionalProperties": {
            "$ref": "#/definitions/BilingualLabel"
          }
        },
        "special": {
          "type": "object",
          "description": "Special token translations",
          "additionalProperties": {
            "$ref": "#/definitions/BilingualLabel"
          }
        },
        "morph": {
          "type": "object",
          "description": "Morphological feature value translations",
          "additionalProperties": {
            "$ref": "#/definitions/BilingualLabel"
          }
        }
      }
    },
    "input": {
      "type": "object",
      "required": [
        "text"
      ],
      "properties": {
        "text": {
          "type": "string",
          "description": "Original input text (may contain multiple sentences)"
        },
        "language": {
          "type": "string",
          "description": "Primary input language",
          "enum": [
            "he",
            "en"
          ]
        }
      }
    },
    "sentences": {
      "type": "array",
      "description": "Array of sentence analysis results (parallel processed)",
      "items": {
        "$ref": "#/definitions/SentenceResult"
      }
    }
  },
  "definitions": {
    "BilingualLabel": {
      "type": "object",
      "description": "Label with Hebrew and English translations",
      "properties": {
        "en": {
          "type": "string"
        },
        "he": {
          "type": "string"
        }
      },
      "required": [
        "en",
        "he"
      ]
    },
    "SentenceResult": {
      "type": "object",
      "description": "Analysis result for a single sentence",
      "required": [
        "index",
        "lang",
        "text",
        "phonetics",
        "tokens"
      ],
      "properties": {
        "index": {
          "type": "integer",
          "minimum": 0,
          "description": "Sentence index in original text"
        },
        "lang": {
          "type": "string",
          "enum": [
            "he",
            "en"
          ],
          "description": "Detected language for this sentence"
        },
        "text": {
          "type": "string",
          "description": "Original sentence text"
        },
        "phonetics": {
          "$ref": "#/definitions/Phonetics"
        },
        "tokens": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Token"
          }
        },
        "ner_entities": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/NEREntity"
          }
        },
        "speech": {
          "oneOf": [
            {
              "$ref": "#/definitions/Speech"
            },
            {
              "type": "null"
            }
          ]
        },
        "tree_svg": {
          "type": "string",
          "description": "SVG string of dependency tree visualization"
        }
      }
    },
    "Phonetics": {
      "type": "object",
      "description": "Phonikud output for sentence (Hebrew) or passthrough (English)",
      "required": [
        "diacritized",
        "phonemes"
      ],
      "properties": {
        "diacritized": {
          "type": "string",
          "description": "Sentence with nikud (Hebrew) or original text (English)"
        },
        "phonemes": {
          "type": "string",
          "description": "Phoneme sequence (Hebrew) or empty string (English)"
        }
      }
    },
    "Token": {
      "type": "object",
      "description": "Unified token: DictaBERT + Phonikud enrichment",
      "required": [
        "id",
        "token"
      ],
      "properties": {
        "id": {
          "type": "integer",
          "minimum": 1,
          "description": "1-indexed token position within sentence"
        },
        "token": {
          "type": "string",
          "description": "Surface form (DictaBERT)"
        },
        "nikud": {
          "type": "string",
          "description": "Diacritized form (Phonikud for Hebrew, original for English)"
        },
        "phonemes": {
          "type": "string",
          "description": "Token phonemes (Hebrew) or empty (English)"
        },
        "seg": {
          "type": "array",
          "description": "Morphological segmentation (DictaBERT)",
          "items": {
            "type": "string"
          }
        },
        "lex": {
          "type": "string",
          "description": "Lemma (DictaBERT)"
        },
        "offsets": {
          "type": "object",
          "properties": {
            "start": {
              "type": "integer"
            },
            "end": {
              "type": "integer"
            }
          }
        },
        "morph": {
          "$ref": "#/definitions/Morphology"
        },
        "syntax": {
          "$ref": "#/definitions/Syntax"
        }
      }
    },
    "Morphology": {
      "type": "object",
      "description": "DictaBERT morphological analysis",
      "properties": {
        "token": {
          "type": "string"
        },
        "pos": {
          "type": "string",
          "enum": [
            "ADJ",
            "ADP",
            "ADV",
            "AUX",
            "CCONJ",
            "DET",
            "INTJ",
            "NOUN",
            "NUM",
            "PART",
            "PRON",
            "PROPN",
            "PUNCT",
            "SCONJ",
            "SYM",
            "VERB",
            "X"
          ]
        },
        "feats": {
          "type": "object",
          "properties": {
            "Gender": {
              "type": "string",
              "enum": [
                "Masc",
                "Fem"
              ]
            },
            "Number": {
              "type": "string",
              "enum": [
                "Sing",
                "Plur",
                "Dual"
              ]
            },
            "Person": {
              "type": "string",
              "enum": [
                "1",
                "2",
                "3"
              ]
            },
            "Tense": {
              "type": "string",
              "enum": [
                "Past",
                "Present",
                "Future",
                "Imp",
                "Inf"
              ]
            },
            "Voice": {
              "type": "string",
              "enum": [
                "Act",
                "Pass"
              ]
            },
            "Definite": {
              "type": "string",
              "enum": [
                "Def",
                "Ind"
              ]
            },
            "Case": {
              "type": "string",
              "enum": [
                "Nom",
                "Acc",
                "Gen"
              ]
            },
            "Construct": {
              "type": "string",
              "enum": [
                "Construct",
                "Free"
              ]
            }
          },
          "additionalProperties": true
        },
        "prefixes": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "suffix": {
          "type": "boolean"
        }
      }
    },
    "Syntax": {
      "type": "object",
      "description": "DictaBERT dependency syntax",
      "properties": {
        "word": {
          "type": "string"
        },
        "dep_head_idx": {
          "type": "integer",
          "minimum": -1,
          "description": "-1 for root"
        },
        "dep_func": {
          "type": "string"
        },
        "dep_head": {
          "type": "string"
        }
      }
    },
    "NEREntity": {
      "type": "object",
      "properties": {
        "phrase": {
          "type": "string",
          "description": "Entity text"
        },
        "label": {
          "type": "string",
          "enum": [
            "PER",
            "LOC",
            "GPE",
            "ORG",
            "TIME",
            "DATE",
            "MISC",
            "MONEY",
            "PERCENT"
          ]
        },
        "start": {
          "type": "integer"
        },
        "end": {
          "type": "integer"
        }
      }
    },
    "Speech": {
      "type": "object",
      "description": "TTS audio for sentence",
      "properties": {
        "format": {
          "type": "string",
          "enum": [
            "wav",
            "mp3",
            "ogg"
          ]
        },
        "sample_rate": {
          "type": "integer"
        },
        "duration_ms": {
          "type": "number"
        },
        "data_uri": {
          "type": "string",
          "description": "Base64 data URI (data:audio/wav;base64,...)"
        }
      }
    }
  }
}