Function split

tfjs-backend-cpu/src/kernels/StringSplit_impl.ts:20–62

(
    str: Uint8Array, delimiters: Uint8Array, skipEmpty: boolean,
    result: Uint8Array[])

import {TypedArray, util} from '@tensorflow/tfjs-core';

function split(
    str: Uint8Array, delimiters: Uint8Array, skipEmpty: boolean,
    result: Uint8Array[]): void {
  if (!str.length) {
    return;
  }
  // When the delimiter is empty, the input is split into individual characters.
  if (delimiters.length === 0) {
    for (let i = 0; i < str.length; ++i) {
      result.push(str.subarray(i, i + 1));
    }
    return;
  }
  // When there is one delimiter, the input is split only at that delimiter.
  if (delimiters.length === 1) {
    const delimiter = delimiters[0];
    let f = str.indexOf(delimiter);
    while (f !== -1) {
      const token = str.subarray(0, f);
      if (!skipEmpty || token.length !== 0) {
        result.push(token);
      }
      str = str.subarray(f + 1);
      f = str.indexOf(delimiter);
    }
    if (!skipEmpty || str.length !== 0) {
      result.push(str);
    }
    return;
  }
  // When there are multiple delimiters, the input is split at every instance
  // one of the delimiters appears.
  let tokenStart = 0;
  for (let i = 0; i < str.length + 1; i++) {
    if ((i === str.length) || (delimiters.indexOf(str[i]) !== -1)) {
      const token = str.subarray(tokenStart, i);
      if (!skipEmpty || token.length !== 0) {
        result.push(token);
      }
      tokenStart = i + 1;
    }
  }
}

export function stringSplitImpl(
    input: Uint8Array[], delimiter: Uint8Array,