Пример #1
0
extern int
onigenc_unicode_mbc_case_fold(OnigEncoding enc,
    OnigCaseFoldType flag ARG_UNUSED, const UChar** pp, const UChar* end,
    UChar* fold)
{
  const struct ByUnfoldKey* buk;

  OnigCodePoint code;
  int i, len, rlen;
  const UChar *p = *pp;

  code = ONIGENC_MBC_TO_CODE(enc, p, end);
  len = enclen(enc, p);
  *pp += len;

#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
  if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
    if (code == 0x0130) {
      return ONIGENC_CODE_TO_MBC(enc, 0x0069, fold);
    }
#if 0
    if (code == 0x0049) {
      return ONIGENC_CODE_TO_MBC(enc, 0x0131, fold);
    }
#endif
  }
#endif

  buk = unicode_unfold_key(code);
  if (buk != 0) {
    if (buk->fold_len == 1) {
      return ONIGENC_CODE_TO_MBC(enc, *FOLDS1_FOLD(buk->index), fold);
    }
    else {
      OnigCodePoint* addr;

      FOLDS_FOLD_ADDR_BUK(buk, addr);
      rlen = 0;
      for (i = 0; i < buk->fold_len; i++) {
        OnigCodePoint c = addr[i];
        len = ONIGENC_CODE_TO_MBC(enc, c, fold);
        fold += len;
        rlen += len;
      }
      return rlen;
    }
  }

  for (i = 0; i < len; i++) {
    *fold++ = *p++;
  }
  return len;
}
Пример #2
0
extern int
onigenc_unicode_property_name_to_ctype(OnigEncoding enc, UChar* name, UChar* end)
{
  int len;
  UChar *p;
  OnigCodePoint code;
  const struct PropertyNameCtype* pc;
  char buf[PROPERTY_NAME_MAX_SIZE];

  p = name;
  len = 0;
  while (p < end) {
    code = ONIGENC_MBC_TO_CODE(enc, p, end);
    if (code >= 0x80)
      return ONIGERR_INVALID_CHAR_PROPERTY_NAME;

    if (code != ' ' && code != '-' && code != '_') {
      buf[len++] = (char )code;
      if (len >= PROPERTY_NAME_MAX_SIZE)
        return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
    }

    p += enclen(enc, p);
  }

  buf[len] = 0;

  if (UserDefinedPropertyTable != 0) {
    UserDefinedPropertyValue* e;
    e = (UserDefinedPropertyValue* )NULL;
    onig_st_lookup_strend(UserDefinedPropertyTable,
			  (const UChar* )buf, (const UChar* )buf + len,
			  (hash_data_type* )((void* )(&e)));
    if (e != 0) {
      return e->ctype;
    }
  }

  pc = unicode_lookup_property_name(buf, len);
  if (pc != 0) {
    /* fprintf(stderr, "LOOKUP: %s: %d\n", buf, pc->ctype); */
#ifndef USE_UNICODE_PROPERTIES
    if (pc->ctype > ONIGENC_MAX_STD_CTYPE)
      return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
#endif

    return pc->ctype;
  }

  return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
}
Пример #3
0
static int
code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc)
{
  UChar *p = buf;

  if ((code & 0xff000000) != 0) *p++ = (UChar )(((code >> 24) & 0xff));
  if ((code &   0xff0000) != 0) *p++ = (UChar )(((code >> 16) & 0xff));
  if ((code &     0xff00) != 0) *p++ = (UChar )(((code >>  8) & 0xff));
  *p++ = (UChar )(code & 0xff);

  if (enclen(enc, buf, p) != (p - buf))
    return ONIGERR_INVALID_CODE_POINT_VALUE;
  return p - buf;
}
Пример #4
0
static int
code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc)
{
  UChar *p = buf;

  if ((code & 0xff00) != 0) *p++ = (UChar )(((code >>  8) & 0xff));
  *p++ = (UChar )(code & 0xff);

#if 0
  if (enclen(enc, buf) != (p - buf))
    return REGERR_INVALID_CODE_POINT_VALUE;
#endif
  return (int)(p - buf);
}
Пример #5
0
static int
code_to_mbc(OnigCodePoint code, UChar *buf)
{
  UChar *p = buf;

  if ((code & 0xff00) != 0) *p++ = (UChar )(((code >>  8) & 0xff));
  *p++ = (UChar )(code & 0xff);

#if 0
  if (enclen(ONIG_ENCODING_SJIS, buf) != (p - buf))
    return REGERR_INVALID_CODE_POINT_VALUE;
#endif
  return p - buf;
}
Пример #6
0
extern UChar*
onigenc_get_right_adjust_char_head_with_prev(OnigEncoding enc,
				   const UChar* start, const UChar* s, const UChar* end, const UChar** prev)
{
  UChar* p = ONIGENC_LEFT_ADJUST_CHAR_HEAD(enc, start, s, end);

  if (p < s) {
    if (prev) *prev = (const UChar* )p;
    p += enclen(enc, p, end);
  }
  else {
    if (prev) *prev = (const UChar* )NULL; /* Sorry */
  }
  return p;
}
Пример #7
0
static OnigCodePoint
gb18030_mbc_to_code(const UChar* p, const UChar* end, OnigEncoding enc)
{
  int c, i, len;
  OnigCodePoint n;

  len = enclen(enc, p, end);
  n = (OnigCodePoint )(*p++);
  if (len == 1) return n;

  for (i = 1; i < len; i++) {
    if (p >= end) break;
    c = *p++;
    n <<= 8;  n += c;
  }
  return n;
}
Пример #8
0
Файл: sjis.c Проект: 191919/vico
static OnigCodePoint
mbc_to_code(const UChar* p, const UChar* end)
{
  int c, i, len;
  OnigCodePoint n;

  len = enclen(ONIG_ENCODING_SJIS, p);
  c = *p++;
  n = c;
  if (len == 1) return n;

  for (i = 1; i < len; i++) {
    if (p >= end) break;
    c = *p++;
    n <<= 8;  n += c;
  }
  return n;
}
Пример #9
0
static UChar*
euckr_left_adjust_char_head(const UChar* start, const UChar* s)
{
  /* Assumed in this encoding,
     mb-trail bytes don't mix with single bytes.
  */
  const UChar *p;
  int len;

  if (s <= start) return (UChar* )s;
  p = s;

  while (!euckr_islead(*p) && p > start) p--;
  len = enclen(ONIG_ENCODING_EUC_KR, p);
  if (p + len > s) return (UChar* )p;
  p += len;
  return (UChar* )(p + ((s - p) & ~1));
}
Пример #10
0
static UChar*
euctw_left_adjust_char_head(const UChar* start, const UChar* s, const UChar* end, OnigEncoding enc)
{
  /* Assumed in this encoding,
     mb-trail bytes don't mix with single bytes.
  */
  const UChar *p;
  int len;

  if (s <= start) return (UChar* )s;
  p = s;

  while (!euctw_islead(*p) && p > start) p--;
  len = enclen(enc, p, end);
  if (p + len > s) return (UChar* )p;
  p += len;
  return (UChar* )(p + ((s - p) & ~1));
}
Пример #11
0
static UChar*
left_adjust_char_head(const UChar* start, const UChar* s, const UChar* end, OnigEncoding enc)
{
  const UChar *p;
  int len;

  if (s <= start) return (UChar* )s;
  p = s;

  if (SJIS_ISMB_TRAIL(*p)) {
    while (p > start) {
      if (! SJIS_ISMB_FIRST(*--p)) {
	p++;
	break;
      }
    }
  }
  len = enclen(enc, p, end);
  if (p + len > s) return (UChar* )p;
  p += len;
  return (UChar* )(p + ((s - p) & ~1));
}
Пример #12
0
static UChar*
big5_left_adjust_char_head(const UChar* start, const UChar* s)
{
  const UChar *p;
  int len;

  if (s <= start) return (UChar* )s;
  p = s;

  if (BIG5_ISMB_TRAIL(*p)) {
    while (p > start) {
      if (! BIG5_ISMB_FIRST(*--p)) {
	p++;
	break;
      }
    } 
  }
  len = enclen(ONIG_ENCODING_BIG5, p);
  if (p + len > s) return (UChar* )p;
  p += len;
  return (UChar* )(p + ((s - p) & ~1));
}
Пример #13
0
static int
mbc_case_fold(OnigCaseFoldType flag,
	      const UChar** pp, const UChar* end, UChar* lower,
	      OnigEncoding enc)
{
  const UChar* p = *pp;

  if (ONIGENC_IS_MBC_ASCII(p)) {
    *lower = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
    (*pp)++;
    return 1;
  }
  else {
    int i;
    int len = enclen(enc, p, end);

    for (i = 0; i < len; i++) {
      *lower++ = *p++;
    }
    (*pp) += len;
    return len; /* return byte length of converted char to lower */
  }
}
Пример #14
0
extern int
onigenc_unicode_mbc_case_fold(OnigEncoding enc,
    OnigCaseFoldType flag ARG_UNUSED, const UChar** pp, const UChar* end,
    UChar* fold)
{
  CodePointList3 *to;
  OnigCodePoint code;
  int i, len, rlen;
  const UChar *p = *pp;

  if (CaseFoldInited == 0) init_case_fold_table();

  code = ONIGENC_MBC_TO_CODE(enc, p, end);
  len = enclen(enc, p);
  *pp += len;

#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
  if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
    if (code == 0x0049) {
      return ONIGENC_CODE_TO_MBC(enc, 0x0131, fold);
    }
    else if (code == 0x0130) {
      return ONIGENC_CODE_TO_MBC(enc, 0x0069, fold);
    }
  }
#endif

  if (onig_st_lookup(FoldTable, (st_data_t )code, (void* )&to) != 0) {
    if (to->n == 1) {
      return ONIGENC_CODE_TO_MBC(enc, to->code[0], fold);
    }
#if 0
    /* NO NEEDS TO CHECK */
    else if ((flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
#else
    else {
#endif
      rlen = 0;
      for (i = 0; i < to->n; i++) {
	len = ONIGENC_CODE_TO_MBC(enc, to->code[i], fold);
	fold += len;
	rlen += len;
      }
      return rlen;
    }
  }

  for (i = 0; i < len; i++) {
    *fold++ = *p++;
  }
  return len;
}

extern int
onigenc_unicode_apply_all_case_fold(OnigCaseFoldType flag,
				    OnigApplyAllCaseFoldFunc f, void* arg)
{
  const CaseUnfold_11_Type* p11;
  OnigCodePoint code;
  int i, j, k, r;

  /* if (CaseFoldInited == 0) init_case_fold_table(); */

  for (i = 0; i < numberof(CaseUnfold_11); i++) {
    p11 = &CaseUnfold_11[i];
    for (j = 0; j < p11->to.n; j++) {
      code = p11->from;
      r = (*f)(p11->to.code[j], &code, 1, arg);
      if (r != 0) return r;

      code = p11->to.code[j];
      r = (*f)(p11->from, &code, 1, arg);
      if (r != 0) return r;

      for (k = 0; k < j; k++) {
	r = (*f)(p11->to.code[j], (OnigCodePoint* )(&p11->to.code[k]), 1, arg);
	if (r != 0) return r;

	r = (*f)(p11->to.code[k], (OnigCodePoint* )(&p11->to.code[j]), 1, arg);
	if (r != 0) return r;
      }
    }
  }

#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
  if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
    code = 0x0131;
    r = (*f)(0x0049, &code, 1, arg);
    if (r != 0) return r;
    code = 0x0049;
    r = (*f)(0x0131, &code, 1, arg);
    if (r != 0) return r;

    code = 0x0130;
    r = (*f)(0x0069, &code, 1, arg);
    if (r != 0) return r;
    code = 0x0069;
    r = (*f)(0x0130, &code, 1, arg);
    if (r != 0) return r;
  }
  else {
#endif
    for (i = 0; i < numberof(CaseUnfold_11_Locale); i++) {
      p11 = &CaseUnfold_11_Locale[i];
      for (j = 0; j < p11->to.n; j++) {
	code = p11->from;
	r = (*f)(p11->to.code[j], &code, 1, arg);
	if (r != 0) return r;

	code = p11->to.code[j];
	r = (*f)(p11->from, &code, 1, arg);
	if (r != 0) return r;

	for (k = 0; k < j; k++) {
	  r = (*f)(p11->to.code[j], (OnigCodePoint* )(&p11->to.code[k]),
		   1, arg);
	  if (r != 0) return r;

	  r = (*f)(p11->to.code[k], (OnigCodePoint* )(&p11->to.code[j]),
		   1, arg);
	  if (r != 0) return r;
	}
      }
    }
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
  }
#endif

  if ((flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
    for (i = 0; i < numberof(CaseUnfold_12); i++) {
      for (j = 0; j < CaseUnfold_12[i].to.n; j++) {
	r = (*f)(CaseUnfold_12[i].to.code[j],
		 (OnigCodePoint* )CaseUnfold_12[i].from, 2, arg);
	if (r != 0) return r;

	for (k = 0; k < CaseUnfold_12[i].to.n; k++) {
	  if (k == j) continue;

	  r = (*f)(CaseUnfold_12[i].to.code[j],
		   (OnigCodePoint* )(&CaseUnfold_12[i].to.code[k]), 1, arg);
	  if (r != 0) return r;
	}
      }
    }

#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
    if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) == 0) {
#endif
      for (i = 0; i < numberof(CaseUnfold_12_Locale); i++) {
	for (j = 0; j < CaseUnfold_12_Locale[i].to.n; j++) {
	  r = (*f)(CaseUnfold_12_Locale[i].to.code[j],
		   (OnigCodePoint* )CaseUnfold_12_Locale[i].from, 2, arg);
	  if (r != 0) return r;

	  for (k = 0; k < CaseUnfold_12_Locale[i].to.n; k++) {
	    if (k == j) continue;

	    r = (*f)(CaseUnfold_12_Locale[i].to.code[j],
		     (OnigCodePoint* )(&CaseUnfold_12_Locale[i].to.code[k]),
		     1, arg);
	    if (r != 0) return r;
	  }
	}
      }
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
    }
#endif

    for (i = 0; i < numberof(CaseUnfold_13); i++) {
      for (j = 0; j < CaseUnfold_13[i].to.n; j++) {
	r = (*f)(CaseUnfold_13[i].to.code[j],
		 (OnigCodePoint* )CaseUnfold_13[i].from, 3, arg);
	if (r != 0) return r;

	for (k = 0; k < CaseUnfold_13[i].to.n; k++) {
	  if (k == j) continue;

	  r = (*f)(CaseUnfold_13[i].to.code[j],
		   (OnigCodePoint* )(&CaseUnfold_13[i].to.code[k]), 1, arg);
	  if (r != 0) return r;
	}
      }
    }
  }

  return 0;
}

extern int
onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
    OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end,
    OnigCaseFoldCodeItem items[])
{
  int n, i, j, k, len;
  OnigCodePoint code, codes[3];
  CodePointList3 *to, *z3;
  CodePointList2 *z2;

  if (CaseFoldInited == 0) init_case_fold_table();

  n = 0;

  code = ONIGENC_MBC_TO_CODE(enc, p, end);
  len = enclen(enc, p);

#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
  if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
    if (code == 0x0049) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0131;
      return 1;
    }
    else if (code == 0x0130) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0069;
      return 1;
    }
    else if (code == 0x0131) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0049;
      return 1;
    }
    else if (code == 0x0069) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0130;
      return 1;
    }
  }
#endif

  if (onig_st_lookup(FoldTable, (st_data_t )code, (void* )&to) != 0) {
    if (to->n == 1) {
      OnigCodePoint orig_code = code;

      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = to->code[0];
      n++;

      code = to->code[0];
      if (onig_st_lookup(Unfold1Table, (st_data_t )code, (void* )&to) != 0) {
	for (i = 0; i < to->n; i++) {
	  if (to->code[i] != orig_code) {
	    items[n].byte_len = len;
	    items[n].code_len = 1;
	    items[n].code[0]  = to->code[i];
	    n++;
	  }
	}
      }
    }
    else if ((flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
      OnigCodePoint cs[3][4];
      int fn, ncs[3];

      for (fn = 0; fn < to->n; fn++) {
	cs[fn][0] = to->code[fn];
	if (onig_st_lookup(Unfold1Table, (st_data_t )cs[fn][0],
			   (void* )&z3) != 0) {
	  for (i = 0; i < z3->n; i++) {
	    cs[fn][i+1] = z3->code[i];
	  }
	  ncs[fn] = z3->n + 1;
	}
	else
	  ncs[fn] = 1;
      }

      if (fn == 2) {
	for (i = 0; i < ncs[0]; i++) {
	  for (j = 0; j < ncs[1]; j++) {
	    items[n].byte_len = len;
	    items[n].code_len = 2;
	    items[n].code[0]  = cs[0][i];
	    items[n].code[1]  = cs[1][j];
	    n++;
	  }
	}

	if (onig_st_lookup(Unfold2Table, (st_data_t )to->code,
			   (void* )&z2) != 0) {
	  for (i = 0; i < z2->n; i++) {
	    if (z2->code[i] == code) continue;

	    items[n].byte_len = len;
	    items[n].code_len = 1;
	    items[n].code[0]  = z2->code[i];
	    n++;
	  }
	}
      }
      else {
	for (i = 0; i < ncs[0]; i++) {
	  for (j = 0; j < ncs[1]; j++) {
	    for (k = 0; k < ncs[2]; k++) {
	      items[n].byte_len = len;
	      items[n].code_len = 3;
	      items[n].code[0]  = cs[0][i];
	      items[n].code[1]  = cs[1][j];
	      items[n].code[2]  = cs[2][k];
	      n++;
	    }
	  }
	}

	if (onig_st_lookup(Unfold3Table, (st_data_t )to->code,
			   (void* )&z2) != 0) {
	  for (i = 0; i < z2->n; i++) {
	    if (z2->code[i] == code) continue;

	    items[n].byte_len = len;
	    items[n].code_len = 1;
	    items[n].code[0]  = z2->code[i];
	    n++;
	  }
	}
      }

      /* multi char folded code is not head of another folded multi char */
      flag = 0; /* DISABLE_CASE_FOLD_MULTI_CHAR(flag); */
    }
  }
  else {
    if (onig_st_lookup(Unfold1Table, (st_data_t )code, (void* )&to) != 0) {
      for (i = 0; i < to->n; i++) {
	items[n].byte_len = len;
	items[n].code_len = 1;
	items[n].code[0]  = to->code[i];
	n++;
      }
    }
  }


  if ((flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
    p += len;
    if (p < end) {
      int clen;

      codes[0] = code;
      code = ONIGENC_MBC_TO_CODE(enc, p, end);
      if (onig_st_lookup(FoldTable, (st_data_t )code, (void* )&to) != 0
	  && to->n == 1) {
	codes[1] = to->code[0];
      }
      else
	codes[1] = code;

      clen = enclen(enc, p);
      len += clen;
      if (onig_st_lookup(Unfold2Table, (st_data_t )codes, (void* )&z2) != 0) {
	for (i = 0; i < z2->n; i++) {
	  items[n].byte_len = len;
	  items[n].code_len = 1;
	  items[n].code[0]  = z2->code[i];
	  n++;
	}
      }

      p += clen;
      if (p < end) {
	code = ONIGENC_MBC_TO_CODE(enc, p, end);
	if (onig_st_lookup(FoldTable, (st_data_t )code, (void* )&to) != 0
	    && to->n == 1) {
	  codes[2] = to->code[0];
	}
	else
	  codes[2] = code;

	clen = enclen(enc, p);
	len += clen;
	if (onig_st_lookup(Unfold3Table, (st_data_t )codes,
			   (void* )&z2) != 0) {
	  for (i = 0; i < z2->n; i++) {
	    items[n].byte_len = len;
	    items[n].code_len = 1;
	    items[n].code[0]  = z2->code[i];
	    n++;
	  }
	}
      }
    }
  }

  return n;
}
Пример #15
0
extern int
onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
    OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end,
    OnigCaseFoldCodeItem items[])
{
  int n, m, i, j, k, len;
  OnigCodePoint code, codes[3];
  const struct ByUnfoldKey* buk;

  n = 0;

  code = ONIGENC_MBC_TO_CODE(enc, p, end);
  len = enclen(enc, p);

#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
  if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
    if (code == 0x0049) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0131;
      return 1;
    }
    else if (code == 0x0130) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0069;
      return 1;
    }
    else if (code == 0x0131) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0049;
      return 1;
    }
    else if (code == 0x0069) {
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = 0x0130;
      return 1;
    }
  }
#endif

  buk = unicode_unfold_key(code);
  if (buk != 0) {
    if (buk->fold_len == 1) {
      int un;
      items[0].byte_len = len;
      items[0].code_len = 1;
      items[0].code[0]  = *FOLDS1_FOLD(buk->index);
      n++;

      un = FOLDS1_UNFOLDS_NUM(buk->index);
      for (i = 0; i < un; i++) {
        OnigCodePoint unfold = FOLDS1_UNFOLDS(buk->index)[i];
        if (unfold != code) {
          items[n].byte_len = len;
          items[n].code_len = 1;
          items[n].code[0]  = unfold;
          n++;
        }
      }
      code = items[0].code[0]; // for multi-code to unfold search.
    }
    else if ((flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
      OnigCodePoint cs[3][4];
      int fn, ncs[3];

      if (buk->fold_len == 2) {
        m = FOLDS2_UNFOLDS_NUM(buk->index);
        for (i = 0; i < m; i++) {
          OnigCodePoint unfold = FOLDS2_UNFOLDS(buk->index)[i];
          if (unfold == code) continue;

          items[n].byte_len = len;
          items[n].code_len = 1;
          items[n].code[0]  = unfold;
          n++;
        }

        for (fn = 0; fn < 2; fn++) {
          int index;
          cs[fn][0] = FOLDS2_FOLD(buk->index)[fn];
          index = unicode_fold1_key(&cs[fn][0]);
          if (index >= 0) {
            int m = FOLDS1_UNFOLDS_NUM(index);
            for (i = 0; i < m; i++) {
              cs[fn][i+1] = FOLDS1_UNFOLDS(index)[i];
            }
            ncs[fn] = m + 1;
          }
          else
            ncs[fn] = 1;
        }

        for (i = 0; i < ncs[0]; i++) {
          for (j = 0; j < ncs[1]; j++) {
            items[n].byte_len = len;
            items[n].code_len = 2;
            items[n].code[0]  = cs[0][i];
            items[n].code[1]  = cs[1][j];
            n++;
          }
        }
      }
      else { /* fold_len == 3 */
        m = FOLDS3_UNFOLDS_NUM(buk->index);
        for (i = 0; i < m; i++) {
          OnigCodePoint unfold = FOLDS3_UNFOLDS(buk->index)[i];
          if (unfold == code) continue;

          items[n].byte_len = len;
          items[n].code_len = 1;
          items[n].code[0]  = unfold;
          n++;
        }

        for (fn = 0; fn < 3; fn++) {
          int index;
          cs[fn][0] = FOLDS3_FOLD(buk->index)[fn];
          index = unicode_fold1_key(&cs[fn][0]);
          if (index >= 0) {
            int m = FOLDS1_UNFOLDS_NUM(index);
            for (i = 0; i < m; i++) {
              cs[fn][i+1] = FOLDS1_UNFOLDS(index)[i];
            }
            ncs[fn] = m + 1;
          }
          else
            ncs[fn] = 1;
        }

        for (i = 0; i < ncs[0]; i++) {
          for (j = 0; j < ncs[1]; j++) {
            for (k = 0; k < ncs[2]; k++) {
              items[n].byte_len = len;
              items[n].code_len = 3;
              items[n].code[0]  = cs[0][i];
              items[n].code[1]  = cs[1][j];
              items[n].code[2]  = cs[2][k];
              n++;
            }
          }
        }
      }

      /* multi char folded code is not head of another folded multi char */
      return n;
    }
  }
  else {
    int index = unicode_fold1_key(&code);
    if (index >= 0) {
      int m = FOLDS1_UNFOLDS_NUM(index);
      for (i = 0; i < m; i++) {
        items[n].byte_len = len;
        items[n].code_len = 1;
        items[n].code[0]  = FOLDS1_UNFOLDS(index)[i];
        n++;
      }
    }
  }

  if ((flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) == 0)
    return n;

  p += len;
  if (p < end) {
    int clen;
    int index;

    codes[0] = code;
    code = ONIGENC_MBC_TO_CODE(enc, p, end);

    buk = unicode_unfold_key(code);
    if (buk != 0 && buk->fold_len == 1) {
      codes[1] = *FOLDS1_FOLD(buk->index);
    }
    else
      codes[1] = code;

    clen = enclen(enc, p);
    len += clen;

    index = unicode_fold2_key(codes);
    if (index >= 0) {
      m = FOLDS2_UNFOLDS_NUM(index);
      for (i = 0; i < m; i++) {
        items[n].byte_len = len;
        items[n].code_len = 1;
        items[n].code[0]  = FOLDS2_UNFOLDS(index)[i];
        n++;
      }
    }

    p += clen;
    if (p < end) {
      code = ONIGENC_MBC_TO_CODE(enc, p, end);
      buk = unicode_unfold_key(code);
      if (buk != 0 && buk->fold_len == 1) {
        codes[2] = *FOLDS1_FOLD(buk->index);
      }
      else
        codes[2] = code;

      clen = enclen(enc, p);
      len += clen;

      index = unicode_fold3_key(codes);
      if (index >= 0) {
        m = FOLDS3_UNFOLDS_NUM(index);
        for (i = 0; i < m; i++) {
          items[n].byte_len = len;
          items[n].code_len = 1;
          items[n].code[0]  = FOLDS3_UNFOLDS(index)[i];
          n++;
        }
      }
    }
  }

  return n;
}
Пример #16
0
Файл: utf8.c Проект: 191919/vico
	  return 1;
      }
    }
#endif
  }

  return 0;
}

static OnigCodePoint
mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED)
{
  int c, len;
  OnigCodePoint n;

  len = enclen(ONIG_ENCODING_UTF8, p);
  c = *p++;
  if (len > 1) {
    len--;
    n = c & ((1 << (6 - len)) - 1);
    while (len--) {
      c = *p++;
      n = (n << 6) | (c & ((1 << 6) - 1));
    }
    return n;
  }
  else {
#ifdef USE_INVALID_CODE_SCHEME
    if (c > 0xfd) {
      return ((c == 0xfe) ? INVALID_CODE_FE : INVALID_CODE_FF);
    }
Пример #17
0
/*
Runs Argon2 with certain inputs and parameters, inputs not cleared. Prints the
Base64-encoded hash string
@out output array with at least 32 bytes allocated
@pwd NULL-terminated string, presumably from argv[]
@salt salt array with at least SALTLEN_DEF bytes allocated
@t_cost number of iterations
@m_cost amount of requested memory in KB
@lanes amount of requested parallelism
@threads actual parallelism
@type String, only "d" and "i" are accepted
*/
static void run(uint32_t outlen, char *pwd, char *salt, uint32_t t_cost,
                uint32_t m_cost, uint32_t lanes, uint32_t threads,
                argon2_type type) {
    clock_t start_time, stop_time;
    size_t pwdlen, saltlen, encodedlen;
    uint32_t i;
    int result;

    start_time = clock();

    if (!pwd) {
        fatal("password missing");
    }

    if (!salt) {
        secure_wipe_memory(pwd, strlen(pwd));
        fatal("salt missing");
    }

    pwdlen = strlen(pwd);
    saltlen = strlen(salt);

    UNUSED_PARAMETER(lanes);

    unsigned char* out = malloc(outlen + 1);
    if (!out) {
        secure_wipe_memory(pwd, strlen(pwd));
        fatal("could not allocate memory for output");
    }

    encodedlen = enclen(outlen, saltlen, t_cost, m_cost, lanes);
    char* encoded = malloc(encodedlen + 1);
    if (!encoded) {
        secure_wipe_memory(pwd, strlen(pwd));
        fatal("could not allocate memory for hash");
    }

    result = argon2_hash(t_cost, m_cost, threads, pwd, pwdlen, salt, saltlen,
                         out, outlen, encoded, encodedlen, type);
    if (result != ARGON2_OK)
        fatal(argon2_error_message(result));

    stop_time = clock();

    printf("Hash:\t\t");
    for (i = 0; i < outlen; ++i) {
        printf("%02x", out[i]);
    }
    free(out);
    printf("\n");
    printf("Encoded:\t%s\n", encoded);

    printf("%2.3f seconds\n",
           ((double)stop_time - start_time) / (CLOCKS_PER_SEC));

    result = argon2_verify(encoded, pwd, pwdlen, type);
    if (result != ARGON2_OK)
        fatal(argon2_error_message(result));
    printf("Verification ok\n");
    free(encoded);
}