All files / src/shared/lib/rpn tokenizer.ts

97.67% Statements 84/86
96.42% Branches 54/56
100% Functions 8/8
97.67% Lines 84/86

Press n or j to go to the next uncovered block, b, p or k for the previous block.

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217111x                   111x                   111x   111x         136x 136x     136x     111x       115x 115x 86x           29x 29x 29x 883x 3x 880x 31x   883x   29x 1x     28x 28x 1x     27x             111x     126x 126x   126x 371x 115x 113x       113x 113x   256x 21x 21x 21x 21x     235x 1880x   235x 1x 1x 1x     234x 152x 152x 152x     82x 82x           432x     54x   82x 82x     124x     111x 126x   369x 68x         301x 14x         287x 30x       257x 28x       229x 5x       224x 90x         134x 134x 113x               21x 21x                 124x   369x 14x 2x             12x 12x         4x               363x         111x  
import {
  isConstant,
  isFunctionSymbol,
  isNumeric,
  isOperatorSymbol,
  isVariable,
  toNumber,
} from "./helpers";
import { Token } from "./types";
 
const multiCharacterOperators = [
  "<<",
  ">>",
  "==",
  "!=",
  ">=",
  "<=",
  "&&",
  "||",
];
const singleCharacterTokens = new Set("+-*/^%&|~!(),<>");
 
const readDelimitedToken = (
  input: string,
  offset: number,
  delimiter: "$" | "@",
): number => {
  const end = input.indexOf(delimiter, offset + 1);
  Iif (end === -1) {
    throw new Error(`Unterminated ${delimiter} token`);
  }
  return end + 1;
};
 
const readVariableToken = (
  input: string,
  offset: number,
): { token: string; end: number; indexExpression?: string } => {
  const symbolEnd = readDelimitedToken(input, offset, "$");
  if (input[symbolEnd] !== "[") {
    return {
      token: input.slice(offset, symbolEnd),
      end: symbolEnd,
    };
  }
 
  let depth = 1;
  let cursor = symbolEnd + 1;
  while (cursor < input.length && depth > 0) {
    if (input[cursor] === "[") {
      depth++;
    } else if (input[cursor] === "]") {
      depth--;
    }
    cursor++;
  }
  if (depth !== 0) {
    throw new Error("Unterminated array index");
  }
 
  const indexExpression = input.slice(symbolEnd + 1, cursor - 1);
  if (!indexExpression) {
    throw new Error("Array index cannot be empty");
  }
 
  return {
    token: input.slice(offset, cursor),
    end: cursor,
    indexExpression,
  };
};
 
const splitTokens = (
  input: string,
): Array<{ token: string; indexExpression?: string }> => {
  const tokens: Array<{ token: string; indexExpression?: string }> = [];
  let offset = 0;
 
  while (offset < input.length) {
    if (input[offset] === "$") {
      const variable = readVariableToken(input, offset);
      tokens.push({
        token: variable.token,
        indexExpression: variable.indexExpression,
      });
      offset = variable.end;
      continue;
    }
    if (input[offset] === "@") {
      const end = readDelimitedToken(input, offset, "@");
      tokens.push({ token: input.slice(offset, end) });
      offset = end;
      continue;
    }
 
    const multiCharacterOperator = multiCharacterOperators.find((operator) =>
      input.startsWith(operator, offset),
    );
    if (multiCharacterOperator) {
      tokens.push({ token: multiCharacterOperator });
      offset += multiCharacterOperator.length;
      continue;
    }
 
    if (singleCharacterTokens.has(input[offset])) {
      tokens.push({ token: input[offset] });
      offset++;
      continue;
    }
 
    let end = offset + 1;
    while (
      end < input.length &&
      input[end] !== "$" &&
      input[end] !== "@" &&
      !singleCharacterTokens.has(input[end]) &&
      !multiCharacterOperators.some((operator) =>
        input.startsWith(operator, end),
      )
    ) {
      end++;
    }
    tokens.push({ token: input.slice(offset, end) });
    offset = end;
  }
 
  return tokens;
};
 
const tokenizer = (input: string): Token[] => {
  const tokens = splitTokens(input.replace(/\s+/g, "")).map(
    ({ token, indexExpression }): Token => {
      if (isNumeric(token)) {
        return {
          type: "VAL",
          value: toNumber(token),
        };
      }
      if (isFunctionSymbol(token)) {
        return {
          type: "FUN",
          function: token,
        };
      }
      if (token === "(") {
        return {
          type: "LBRACE",
        };
      }
      if (token === ")") {
        return {
          type: "RBRACE",
        };
      }
      if (token === ",") {
        return {
          type: "SEPERATOR",
        };
      }
      if (isOperatorSymbol(token)) {
        return {
          type: "OP",
          operator: token,
        };
      }
      const variableSymbol = token.replace(/\[.*\]$/s, "");
      if (isVariable(variableSymbol)) {
        return {
          type: "VAR",
          symbol: variableSymbol,
          ...(indexExpression !== undefined && {
            index: tokenizer(indexExpression),
          }),
        };
      }
      Eif (isConstant(token)) {
        return {
          type: "CONST",
          symbol: token.replaceAll(/@/g, ""),
        };
      }
      throw new Error(`Unexpected token ${token}`);
    },
  );
 
  return tokens
    .map((token, i): Token[] => {
      if (token.type === "OP" && token.operator === "-") {
        if (i === 0) {
          return [
            {
              type: "OP",
              operator: "neg",
            },
          ];
        }
        const previous = tokens[i - 1];
        if (
          previous.type === "LBRACE" ||
          previous.type === "SEPERATOR" ||
          previous.type === "OP"
        ) {
          return [
            {
              type: "OP",
              operator: "neg",
            },
          ];
        }
      }
      return [token];
    })
    .flat();
};
 
export default tokenizer;