Skip to main content
Module

x/polkadot/util/is/utf8.ts

Package publishing for deno.land/x/polkadot
polkadot-js/build-deno.land
Very Popular
Go to Latest
File
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207


import type { HexString } from '../types.ts';
import { u8aToU8a } from '../u8a/toU8a.ts';import { isString } from './string.ts';
/** * @name isUtf8 * @summary Tests if the input is valid Utf8 * @description * Checks to see if the input string or Uint8Array is valid Utf8 */export function isUtf8 (value?: HexString | number[] | Uint8Array | string | null): boolean {  if (!value) {    return isString(value);  }
  const u8a = u8aToU8a(value);  const len = u8a.length;  let i = 0;
  while (i < len) {    if (u8a[i] <= 0x7F) /* 00..7F */ {      i += 1;    } else if (u8a[i] >= 0xC2 && u8a[i] <= 0xDF) /* C2..DF 80..BF */ {      if (i + 1 < len) /* Expect a 2nd byte */ {        if (u8a[i + 1] < 0x80 || u8a[i + 1] > 0xBF) {          // *message = "After a first byte between C2 and DF, expecting a 2nd byte between 80 and BF";          // *faulty_bytes = 2;          return false;        }      } else {        // *message = "After a first byte between C2 and DF, expecting a 2nd byte.";        // *faulty_bytes = 1;        return false;      }
      i += 2;    } else if (u8a[i] === 0xE0) /* E0 A0..BF 80..BF */ {      if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {        if (u8a[i + 1] < 0xA0 || u8a[i + 1] > 0xBF) {          // *message = "After a first byte of E0, expecting a 2nd byte between A0 and BF.";          // *faulty_bytes = 2;          return false;        }
        if (u8a[i + 2] < 0x80 || u8a[i + 2] > 0xBF) {          // *message = "After a first byte of E0, expecting a 3nd byte between 80 and BF.";          // *faulty_bytes = 3;          return false;        }      } else {        // *message = "After a first byte of E0, expecting two following bytes.";        // *faulty_bytes = 1;        return false;      }
      i += 3;    } else if (u8a[i] >= 0xE1 && u8a[i] <= 0xEC) /* E1..EC 80..BF 80..BF */ {      if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {        if (u8a[i + 1] < 0x80 || u8a[i + 1] > 0xBF) {          // *message = "After a first byte between E1 and EC, expecting the 2nd byte between 80 and BF.";          // *faulty_bytes = 2;          return false;        }
        if (u8a[i + 2] < 0x80 || u8a[i + 2] > 0xBF) {          // *message = "After a first byte between E1 and EC, expecting the 3rd byte between 80 and BF.";          // *faulty_bytes = 3;          return false;        }      } else {        // *message = "After a first byte between E1 and EC, expecting two following bytes.";        // *faulty_bytes = 1;        return false;      }
      i += 3;    } else if (u8a[i] === 0xED) /* ED 80..9F 80..BF */ {      if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {        if (u8a[i + 1] < 0x80 || u8a[i + 1] > 0x9F) {          // *message = "After a first byte of ED, expecting 2nd byte between 80 and 9F.";          // *faulty_bytes = 2;          return false;        }
        if (u8a[i + 2] < 0x80 || u8a[i + 2] > 0xBF) {          // *message = "After a first byte of ED, expecting 3rd byte between 80 and BF.";          // *faulty_bytes = 3;          return false;        }      } else {        // *message = "After a first byte of ED, expecting two following bytes.";        // *faulty_bytes = 1;        return false;      }
      i += 3;    } else if (u8a[i] >= 0xEE && u8a[i] <= 0xEF) /* EE..EF 80..BF 80..BF */ {      if (i + 2 < len) /* Expect a 2nd and 3rd byte */ {        if (u8a[i + 1] < 0x80 || u8a[i + 1] > 0xBF) {          // *message = "After a first byte between EE and EF, expecting 2nd byte between 80 and BF.";          // *faulty_bytes = 2;          return false;        }
        if (u8a[i + 2] < 0x80 || u8a[i + 2] > 0xBF) {          // *message = "After a first byte between EE and EF, expecting 3rd byte between 80 and BF.";          // *faulty_bytes = 3;          return false;        }      } else {        // *message = "After a first byte between EE and EF, two following bytes.";        // *faulty_bytes = 1;        return false;      }
      i += 3;    } else if (u8a[i] === 0xF0) /* F0 90..BF 80..BF 80..BF */ {      if (i + 3 < len) /* Expect a 2nd, 3rd 3th byte */ {        if (u8a[i + 1] < 0x90 || u8a[i + 1] > 0xBF) {          // *message = "After a first byte of F0, expecting 2nd byte between 90 and BF.";          // *faulty_bytes = 2;          return false;        }
        if (u8a[i + 2] < 0x80 || u8a[i + 2] > 0xBF) {          // *message = "After a first byte of F0, expecting 3rd byte between 80 and BF.";          // *faulty_bytes = 3;          return false;        }
        if (u8a[i + 3] < 0x80 || u8a[i + 3] > 0xBF) {          // *message = "After a first byte of F0, expecting 4th byte between 80 and BF.";          // *faulty_bytes = 4;          return false;        }      } else {        // *message = "After a first byte of F0, expecting three following bytes.";        // *faulty_bytes = 1;        return false;      }
      i += 4;    } else if (u8a[i] >= 0xF1 && u8a[i] <= 0xF3) /* F1..F3 80..BF 80..BF 80..BF */ {      if (i + 3 < len) /* Expect a 2nd, 3rd 3th byte */ {        if (u8a[i + 1] < 0x80 || u8a[i + 1] > 0xBF) {          // *message = "After a first byte of F1, F2, or F3, expecting a 2nd byte between 80 and BF.";          // *faulty_bytes = 2;          return false;        }
        if (u8a[i + 2] < 0x80 || u8a[i + 2] > 0xBF) {          // *message = "After a first byte of F1, F2, or F3, expecting a 3rd byte between 80 and BF.";          // *faulty_bytes = 3;          return false;        }
        if (u8a[i + 3] < 0x80 || u8a[i + 3] > 0xBF) {          // *message = "After a first byte of F1, F2, or F3, expecting a 4th byte between 80 and BF.";          // *faulty_bytes = 4;          return false;        }      } else {        // *message = "After a first byte of F1, F2, or F3, expecting three following bytes.";        // *faulty_bytes = 1;        return false;      }
      i += 4;    } else if (u8a[i] === 0xF4) /* F4 80..8F 80..BF 80..BF */ {      if (i + 3 < len) /* Expect a 2nd, 3rd 3th byte */ {        if (u8a[i + 1] < 0x80 || u8a[i + 1] > 0x8F) {          // *message = "After a first byte of F4, expecting 2nd byte between 80 and 8F.";          // *faulty_bytes = 2;          return false;        }
        if (u8a[i + 2] < 0x80 || u8a[i + 2] > 0xBF) {          // *message = "After a first byte of F4, expecting 3rd byte between 80 and BF.";          // *faulty_bytes = 3;          return false;        }
        if (u8a[i + 3] < 0x80 || u8a[i + 3] > 0xBF) {          // *message = "After a first byte of F4, expecting 4th byte between 80 and BF.";          // *faulty_bytes = 4;          return false;        }      } else {        // *message = "After a first byte of F4, expecting three following bytes.";        // *faulty_bytes = 1;        return false;      }
      i += 4;    } else {      // *message = "Expecting bytes in the following ranges: 00..7F C2..F4.";      // *faulty_bytes = 1;      return false;    }  }
  return true;}