int xdl_blankline(const char *line, long size, long flags)
{
long i;
if (!(flags & XDF_WHITESPACE_FLAGS))
return (size <= 1);
for (i = 0; i < size && XDL_ISSPACE(line[i]); i++)
;
return (i == size);
}
static int match_string_spaces(const char *line1, int len1,
const char *line2, int len2,
long flags)
{
if (flags & XDF_WHITESPACE_FLAGS) {
for (; len1 > 0 && XDL_ISSPACE(line1[len1 - 1]); len1--);
for (; len2 > 0 && XDL_ISSPACE(line2[len2 - 1]); len2--);
}
if (!(flags & (XDF_IGNORE_WHITESPACE | XDF_IGNORE_WHITESPACE_CHANGE)))
return (len1 == len2 && !memcmp(line1, line2, len1));
while (len1 > 0 && len2 > 0) {
len1--;
len2--;
if (XDL_ISSPACE(line1[len1]) || XDL_ISSPACE(line2[len2])) {
if ((flags & XDF_IGNORE_WHITESPACE_CHANGE) &&
(!XDL_ISSPACE(line1[len1]) || !XDL_ISSPACE(line2[len2])))
return 0;
for (; len1 > 0 && XDL_ISSPACE(line1[len1]); len1--);
for (; len2 > 0 && XDL_ISSPACE(line2[len2]); len2--);
}
if (line1[len1] != line2[len2])
return 0;
}
if (flags & XDF_IGNORE_WHITESPACE) {
/* Consume remaining spaces */
for (; len1 > 0 && XDL_ISSPACE(line1[len1 - 1]); len1--);
for (; len2 > 0 && XDL_ISSPACE(line2[len2 - 1]); len2--);
}
/* We matched full line1 and line2 */
if (!len1 && !len2)
return 1;
return 0;
}
static unsigned long xdl_hash_record_with_whitespace(char const **data,
char const *top, long flags) {
unsigned long ha = 5381;
char const *ptr = *data;
for (; ptr < top && *ptr != '\n'; ptr++) {
if (XDL_ISSPACE(*ptr)) {
const char *ptr2 = ptr;
int at_eol;
while (ptr + 1 < top && XDL_ISSPACE(ptr[1])
&& ptr[1] != '\n')
ptr++;
at_eol = (top <= ptr + 1 || ptr[1] == '\n');
if (flags & XDF_IGNORE_WHITESPACE)
; /* already handled */
else if (flags & XDF_IGNORE_WHITESPACE_CHANGE
&& !at_eol) {
ha += (ha << 5);
ha ^= (unsigned long) ' ';
}
else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL
&& !at_eol) {
while (ptr2 != ptr + 1) {
ha += (ha << 5);
ha ^= (unsigned long) *ptr2;
ptr2++;
}
}
continue;
}
ha += (ha << 5);
ha ^= (unsigned long) *ptr;
}
*data = ptr < top ? ptr + 1: ptr;
return ha;
}
/*
* Return the amount of indentation of the specified line, treating TAB as 8
* columns. Return -1 if line is empty or contains only whitespace. Clamp the
* output value at MAX_INDENT.
*/
static int get_indent(xrecord_t *rec)
{
long i;
int ret = 0;
for (i = 0; i < rec->size; i++) {
char c = rec->ptr[i];
if (!XDL_ISSPACE(c))
return ret;
else if (c == ' ')
ret += 1;
else if (c == '\t')
ret += 8 - ret % 8;
/* ignore other whitespace characters */
if (ret >= MAX_INDENT)
return MAX_INDENT;
}
/* The line contains only whitespace. */
return -1;
}
int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
{
int i1, i2;
if (s1 == s2 && !memcmp(l1, l2, s1))
return 1;
if (!(flags & XDF_WHITESPACE_FLAGS))
return 0;
i1 = 0;
i2 = 0;
/*
* -w matches everything that matches with -b, and -b in turn
* matches everything that matches with --ignore-space-at-eol.
*
* Each flavor of ignoring needs different logic to skip whitespaces
* while we have both sides to compare.
*/
if (flags & XDF_IGNORE_WHITESPACE) {
goto skip_ws;
while (i1 < s1 && i2 < s2) {
if (l1[i1++] != l2[i2++])
return 0;
skip_ws:
while (i1 < s1 && XDL_ISSPACE(l1[i1]))
i1++;
while (i2 < s2 && XDL_ISSPACE(l2[i2]))
i2++;
}
} else if (flags & XDF_IGNORE_WHITESPACE_CHANGE) {
while (i1 < s1 && i2 < s2) {
if (XDL_ISSPACE(l1[i1]) && XDL_ISSPACE(l2[i2])) {
/* Skip matching spaces and try again */
while (i1 < s1 && XDL_ISSPACE(l1[i1]))
i1++;
while (i2 < s2 && XDL_ISSPACE(l2[i2]))
i2++;
continue;
}
if (l1[i1++] != l2[i2++])
return 0;
}
} else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL) {
while (i1 < s1 && i2 < s2 && l1[i1++] == l2[i2++])
; /* keep going */
}
/*
* After running out of one side, the remaining side must have
* nothing but whitespace for the lines to match. Note that
* ignore-whitespace-at-eol case may break out of the loop
* while there still are characters remaining on both lines.
*/
if (i1 < s1) {
while (i1 < s1 && XDL_ISSPACE(l1[i1]))
i1++;
if (s1 != i1)
return 0;
}
if (i2 < s2) {
while (i2 < s2 && XDL_ISSPACE(l2[i2]))
i2++;
return (s2 == i2);
}
return 1;
}