static void
next_char(Eo_Lexer *ls)
{
int nb;
Eina_Bool end = EINA_FALSE;
if (ls->stream == ls->stream_end)
{
end = EINA_TRUE;
ls->current = '\0';
}
else
ls->current = *(ls->stream++);
nb = lastbytes;
if (!nb && end) nb = 1;
if (!nb) eina_unicode_utf8_next_get(ls->stream - 1, &nb);
if (nb == 1)
{
nb = 0;
++ls->icolumn;
ls->column = ls->icolumn;
}
else --nb;
lastbytes = nb;
}
EAPI Eina_Unicode
eina_unicode_utf8_get_prev(const char *buf, int *iindex)
{
int r, ind;
EINA_SAFETY_ON_NULL_RETURN_VAL(buf, 0);
EINA_SAFETY_ON_NULL_RETURN_VAL(iindex, 0);
ind = *iindex;
/* First obtain the codepoint at iindex */
r = eina_unicode_utf8_next_get(buf, &ind);
/* although when ind == 0 there's no previous char, we still want to get
* the current char */
if (*iindex <= 0)
return r;
/* Next advance iindex to previous codepoint */
ind = *iindex;
ind--;
while ((ind > 0) && ((buf[ind] & 0xc0) == 0x80))
ind--;
*iindex = ind;
return r;
}
static void
_markup_get_text_utf8_append(Eina_Strbuf *sbuf, const char *text)
{
int ch, pos = 0, pos2 = 0;
for (;;)
{
pos = pos2;
ch = eina_unicode_utf8_next_get(text, &pos2);
if ((ch <= 0) || (pos2 <= 0)) break;
if (ch == _NEWLINE)
eina_strbuf_append(sbuf, "<br/>");
else if (ch == _TAB)
eina_strbuf_append(sbuf, "<tab/>");
else if (ch == '<')
eina_strbuf_append(sbuf, "<");
else if (ch == '>')
eina_strbuf_append(sbuf, ">");
else if (ch == '&')
eina_strbuf_append(sbuf, "&");
else if (ch == '"')
eina_strbuf_append(sbuf, """);
else if (ch == _PARAGRAPH_SEPARATOR)
eina_strbuf_append(sbuf, "<ps/>");
else if (ch == _REPLACEMENT_CHAR)
eina_strbuf_append(sbuf, "");
else if (ch != '\r')
{
eina_strbuf_append_length(sbuf, text + pos, pos2 - pos);
}
}
}
static unsigned int
_ecore_imf_xim_utf8_offset_to_index(const char *str, int offset)
{
int idx = 0;
int i;
for (i = 0; i < offset; i++)
{
eina_unicode_utf8_next_get(str, &idx);
}
return idx;
}
EAPI int
eina_unicode_utf8_get_len(const char *buf)
{
/* returns the number of utf8 characters (not bytes) in the string */
int i = 0, len = 0;
EINA_SAFETY_ON_NULL_RETURN_VAL(buf, 0);
while (eina_unicode_utf8_next_get(buf, &i))
len++;
return len;
}
static unsigned int
utf8_offset_to_characters(const char *str, int offset)
{
int index = 0;
unsigned int i = 0;
for (; index < offset; i++)
{
if (eina_unicode_utf8_next_get(str, &index) == 0)
break;
}
return i;
}
EAPI Eina_Unicode *
eina_unicode_utf8_to_unicode(const char *utf, int *_len)
{
/* FIXME: Should optimize! */
int len, i;
int ind;
Eina_Unicode *buf, *uind;
EINA_SAFETY_ON_NULL_RETURN_VAL(utf, NULL);
len = eina_unicode_utf8_get_len(utf);
if (_len)
*_len = len;
buf = (Eina_Unicode *) calloc(sizeof(Eina_Unicode), (len + 1));
if (!buf) return buf;
for (i = 0, ind = 0, uind = buf ; i < len ; i++, uind++)
{
*uind = eina_unicode_utf8_next_get(utf, &ind);
}
return buf;
}
int
evry_fuzzy_match(const char *str, const char *match)
{
const char *p, *m, *next;
int sum = 0;
unsigned int last = 0;
unsigned int offset = 0;
unsigned int min = 0;
unsigned char first = 0;
/* ignore punctuation */
unsigned char ip = 1;
unsigned int cnt = 0;
/* words in match */
unsigned int m_num = 0;
unsigned int m_cnt = 0;
unsigned int m_min[MAX_WORDS];
unsigned int m_len = 0;
unsigned int s_len = 0;
if (!match || !str || !match[0] || !str[0])
return 0;
/* remove white spaces at the beginning */
for (; (*match != 0) && isspace(*match); match++) ;
for (; (*str != 0) && isspace(*str); str++) ;
/* count words in match */
for (m = match; (*m != 0) && (m_num < MAX_WORDS); )
{
for (; (*m != 0) && !isspace(*m); m++) ;
for (; (*m != 0) && isspace(*m); m++) ;
m_min[m_num++] = MAX_FUZZ;
}
for (m = match; ip && (*m != 0); m++)
if (ip && ispunct(*m)) ip = 0;
m_len = strlen(match);
s_len = strlen(str);
/* with less than 3 chars match must be a prefix */
if (m_len < 3) m_len = 0;
next = str;
m = match;
while ((m_cnt < m_num) && (*next != 0))
{
int ii;
/* reset match */
if (m_cnt == 0) m = match;
/* end of matching */
if (*m == 0) break;
offset = 0;
last = 0;
min = 1;
first = 0;
/* m_len = 0; */
/* match current word of string against current match */
for (p = next; *next != 0; p++)
{
/* new word of string begins */
if ((*p == 0) || isspace(*p) || (ip && ispunct(*p)))
{
if (m_cnt < m_num - 1)
{
/* test next match */
for (; (*m != 0) && !isspace(*m); m++) ;
for (; (*m != 0) && isspace(*m); m++) ;
m_cnt++;
break;
}
else
{
ii = 0;
/* go to next word */
for (; (*p != 0) && ((isspace(*p) || (ip && ispunct(*p)))); p += ii)
if (!eina_unicode_utf8_next_get(p, &ii)) break;
cnt++;
next = p;
m_cnt = 0;
break;
}
}
/* current char matches? */
if (tolower(*p) != tolower(*m))
{
if (!first)
offset += 1;
else
offset += 3;
/* m_len++; */
if (offset <= m_len * 3)
continue;
}
if (min < MAX_FUZZ && offset <= m_len * 3)
{
/* first offset of match in word */
if (!first)
{
first = 1;
last = offset;
}
min += offset + (offset - last) * 5;
last = offset;
/* try next char of match */
ii = 0;
if (!eina_unicode_utf8_next_get(m, &ii)) continue;
m += ii;
if (*m != 0 && !isspace(*m))
continue;
/* end of match: store min weight of match */
min += (cnt - m_cnt) > 0 ? (cnt - m_cnt) : 0;
if (min < m_min[m_cnt])
m_min[m_cnt] = min;
}
else
{
ii = 0;
/* go to next match */
for (; (m[0] && m[ii]) && !isspace(*m); m += ii)
if (!eina_unicode_utf8_next_get(m, &ii)) break;
}
if (m_cnt < m_num - 1)
{
ii = 0;
/* test next match */
for (; (m[0] && m[ii]) && !isspace(*m); m += ii)
if (!eina_unicode_utf8_next_get(m, &ii)) break;
m_cnt++;
break;
}
else if (*p != 0)
{
ii = 0;
/* go to next word */
for (; (p[0] && (s_len - (p - str) >= ii)) && !((isspace(*p) || (ip && ispunct(*p)))); p += ii)
if (!eina_unicode_utf8_next_get(p, &ii)) break;
ii = 0;
for (; (p[0] && (s_len - (p - str) >= ii)) && ((isspace(*p) || (ip && ispunct(*p)))); p += ii)
if (!eina_unicode_utf8_next_get(p, &ii)) break;
cnt++;
next = p;
m_cnt = 0;
break;
}
else
{
next = p;
break;
}
}
}
for (m_cnt = 0; m_cnt < m_num; m_cnt++)
{
sum += m_min[m_cnt];
if (sum >= MAX_FUZZ)
{
sum = 0;
break;
}
}
if (sum > 0)
{
/* exact match ? */
if (strcmp(match, str))
sum += 10;
}
return sum;
}
