ast/ast_tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[SOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[EOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "[MSK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFD"
      },
      {
        "type": "StripAccents"
      },
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "[PAD]": 0,
      "[SOS]": 1,
      "[EOS]": 2,
      "[UNK]": 3,
      "[MSK]": 4,
      "[SEP]": 5,
      "MethodInv": 6,
      "ExprStmt": 7,
      "InfixExpr": 8,
      "SingleVarDecl": 9,
      "VarDeclFrag": 10,
      "VarDeclStmt": 11,
      "IfStmt": 12,
      "ReturnStmt": 13,
      "MethodDecl": 14,
      "Asgn": 15,
      "ClassInstCreat": 16,
      "ParenthesizedExpr": 17,
      "PrefixExpr": 18,
      "CastExpr": 19,
      "ThrowStmt": 20,
      "TryStmt": 21,
      "CatchClus": 22,
      "EnhancedForStmt": 23,
      "PostfixExpr": 24,
      "ForStmt": 25,
      "BrkStmt": 26,
      "CondnExpr": 27,
      "ArrayCret": 28,
      "InstofExpr": 29,
      "WhileStmt": 30,
      "LambdaExpr": 31,
      "AnonClassDeclMethodDecl": 32,
      "ContStmt": 33,
      "SwitchStmt": 34,
      "SynchronizedStmt": 35,
      "AssertStmt": 36,
      "MethodInvMethodDecl": 37,
      "DoStmt": 38,
      "AnonClassDecl": 39,
      "ReturnStmtMethodDecl": 40,
      "FieldDecl": 41,
      "VarDeclFragMethodDecl": 42,
      "EmptyStmt": 43,
      "LabeledStmt": 44,
      "SingleVarDeclMethodDecl": 45,
      "ClassInstCreatMethodDecl": 46,
      "InfixExprMethodDecl": 47,
      "AsgnMethodDecl": 48,
      "PrefixExprMethodDecl": 49,
      "CastExprMethodDecl": 50,
      "ArrayCretMethodDecl": 51,
      "PostfixExprMethodDecl": 52,
      "ExprStmtMethodDecl": 53,
      "AnonClassDeclMethodDeclMethodDecl": 54,
      "MethodInvMethodDeclMethodDecl": 55,
      "ReturnStmtMethodDeclMethodDecl": 56,
      "ThrowStmtMethodDecl": 57,
      "ClassInstCreatMethodDeclMethodDecl": 58,
      "MethodDeclMethodDecl": 59,
      "SingleVarDeclMethodDeclMethodDecl": 60,
      "AnonClassDeclMethodDeclMethodDeclMethodDeclMethodDeclMethodDecl": 61,
      "BrkStmtMethodDecl": 62,
      "ClassInstCreatMethodDeclMethodDeclMethodDecl": 63,
      "ReturnStmtMethodDeclMethodDeclMethodDecl": 64,
      "SingleVarDeclMethodDeclMethodDeclMethodDecl": 65
    },
    "unk_token": "[UNK]"
  }
}