xref: /openbsd-src/lib/libcbor/src/cbor/internal/unicode.c (revision 4dcc46c4d04180142eda526ce521dfb137776d05)

/*
 * Copyright (c) 2014-2020 Pavel Kalvoda <me@pavelkalvoda.com>
 *
 * libcbor is free software; you can redistribute it and/or modify
 * it under the terms of the MIT license. See LICENSE for details.
 */

#include "unicode.h"
#include <stdint.h>

#define UTF8_ACCEPT 0
#define UTF8_REJECT 1

static const uint8_t utf8d[] = {
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0, /* 00..1f */
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0, /* 20..3f */
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0, /* 40..5f */
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,
    0,   0,   0,   0,   0,   0,   0,   0,   0,   0, /* 60..7f */
    1,   1,   1,   1,   1,   1,   1,   1,   1,   1,   1,
    1,   1,   1,   1,   1,   9,   9,   9,   9,   9,   9,
    9,   9,   9,   9,   9,   9,   9,   9,   9,   9, /* 80..9f */
    7,   7,   7,   7,   7,   7,   7,   7,   7,   7,   7,
    7,   7,   7,   7,   7,   7,   7,   7,   7,   7,   7,
    7,   7,   7,   7,   7,   7,   7,   7,   7,   7, /* a0..bf */
    8,   8,   2,   2,   2,   2,   2,   2,   2,   2,   2,
    2,   2,   2,   2,   2,   2,   2,   2,   2,   2,   2,
    2,   2,   2,   2,   2,   2,   2,   2,   2,   2, /* c0..df */
    0xa, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3,
    0x3, 0x3, 0x4, 0x3, 0x3, /* e0..ef */
    0xb, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8,
    0x8, 0x8, 0x8, 0x8, 0x8, /* f0..ff */
    0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4,
    0x6, 0x1, 0x1, 0x1, 0x1, /* s0..s0 */
    1,   1,   1,   1,   1,   1,   1,   1,   1,   1,   1,
    1,   1,   1,   1,   1,   1,   0,   1,   1,   1,   1,
    1,   0,   1,   0,   1,   1,   1,   1,   1,   1, /* s1..s2 */
    1,   2,   1,   1,   1,   1,   1,   2,   1,   2,   1,
    1,   1,   1,   1,   1,   1,   1,   1,   1,   1,   1,
    1,   2,   1,   1,   1,   1,   1,   1,   1,   1, /* s3..s4 */
    1,   2,   1,   1,   1,   1,   1,   1,   1,   2,   1,
    1,   1,   1,   1,   1,   1,   1,   1,   1,   1,   1,
    1,   3,   1,   3,   1,   1,   1,   1,   1,   1, /* s5..s6 */
    1,   3,   1,   1,   1,   1,   1,   3,   1,   3,   1,
    1,   1,   1,   1,   1,   1,   3,   1,   1,   1,   1,
    1,   1,   1,   1,   1,   1,   1,   1,   1,   1, /* s7..s8 */
};

/* Copyright of this function: (c) 2008-2009 Bjoern Hoehrmann
 * <bjoern@hoehrmann.de> */
/* See http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details. */
uint32_t _cbor_unicode_decode(uint32_t* state, uint32_t* codep, uint32_t byte) {
  uint32_t type = utf8d[byte];

  *codep = (*state != UTF8_ACCEPT) ? (byte & 0x3fu) | (*codep << 6)
                                   : (0xff >> type) & (byte);

  *state = utf8d[256 + *state * 16 + type];
  return *state;
}

uint64_t _cbor_unicode_codepoint_count(cbor_data source, uint64_t source_length,
                                       struct _cbor_unicode_status* status) {
  *status =
      (struct _cbor_unicode_status){.location = 0, .status = _CBOR_UNICODE_OK};
  uint32_t codepoint, state = UTF8_ACCEPT, res;
  uint64_t pos = 0, count = 0;

  for (; pos < source_length; pos++) {
    res = _cbor_unicode_decode(&state, &codepoint, source[pos]);

    if (res == UTF8_ACCEPT) {
      count++;
    } else if (res == UTF8_REJECT) {
      goto error;
    }
  }

  /* Unfinished multibyte codepoint */
  if (state != UTF8_ACCEPT) goto error;

  return count;

error:
  *status = (struct _cbor_unicode_status){.location = pos,
                                          .status = _CBOR_UNICODE_BADCP};
  return 0;
}