inline void SearchBuffer::prependContext(const UChar* characters,
size_t length) {
DCHECK(m_needsMoreContext);
DCHECK_EQ(m_prefixLength, m_buffer.size());
if (!length)
return;
m_atBreak = false;
size_t wordBoundaryContextStart = length;
if (wordBoundaryContextStart) {
U16_BACK_1(characters, 0, wordBoundaryContextStart);
wordBoundaryContextStart =
startOfLastWordBoundaryContext(characters, wordBoundaryContextStart);
}
size_t usableLength = std::min(m_buffer.capacity() - m_prefixLength,
length - wordBoundaryContextStart);
m_buffer.prepend(characters + length - usableLength, usableLength);
m_prefixLength += usableLength;
if (wordBoundaryContextStart || m_prefixLength == m_buffer.capacity())
m_needsMoreContext = false;
}
inline size_t SearchBuffer::search(size_t& start) {
size_t size = m_buffer.size();
if (m_atBreak) {
if (!size)
return 0;
} else {
if (size != m_buffer.capacity())
return 0;
}
m_textSearcher->setText(m_buffer.data(), size);
m_textSearcher->setOffset(m_prefixLength);
MatchResult match;
nextMatch:
if (!m_textSearcher->nextMatchResult(match))
return 0;
// Matches that start in the overlap area are only tentative.
// The same match may appear later, matching more characters,
// possibly including a combining character that's not yet in the buffer.
if (!m_atBreak && match.start >= size - m_overlap) {
size_t overlap = m_overlap;
if (m_options & AtWordStarts) {
// Ensure that there is sufficient context before matchStart the next time
// around for determining if it is at a word boundary.
int wordBoundaryContextStart = match.start;
U16_BACK_1(m_buffer.data(), 0, wordBoundaryContextStart);
wordBoundaryContextStart = startOfLastWordBoundaryContext(
m_buffer.data(), wordBoundaryContextStart);
overlap = std::min(size - 1,
std::max(overlap, size - wordBoundaryContextStart));
}
memcpy(m_buffer.data(), m_buffer.data() + size - overlap,
overlap * sizeof(UChar));
m_prefixLength -= std::min(m_prefixLength, size - overlap);
m_buffer.shrink(overlap);
return 0;
}
SECURITY_DCHECK(match.start + match.length <= size);
// If this match is "bad", move on to the next match.
if (isBadMatch(m_buffer.data() + match.start, match.length) ||
((m_options & AtWordStarts) &&
!isWordStartMatch(match.start, match.length))) {
goto nextMatch;
}
size_t newSize = size - (match.start + 1);
memmove(m_buffer.data(), m_buffer.data() + match.start + 1,
newSize * sizeof(UChar));
m_prefixLength -= std::min<size_t>(m_prefixLength, match.start + 1);
m_buffer.shrink(newSize);
start = size - match.start;
return match.length;
}
inline size_t SearchBuffer::search(size_t& start)
{
size_t size = m_buffer.size();
if (m_atBreak) {
if (!size)
return 0;
} else {
if (size != m_buffer.capacity())
return 0;
}
UStringSearch* searcher = blink::searcher();
UErrorCode status = U_ZERO_ERROR;
usearch_setText(searcher, m_buffer.data(), size, &status);
ASSERT(status == U_ZERO_ERROR);
usearch_setOffset(searcher, m_prefixLength, &status);
ASSERT(status == U_ZERO_ERROR);
int matchStart = usearch_next(searcher, &status);
ASSERT(status == U_ZERO_ERROR);
nextMatch:
if (!(matchStart >= 0 && static_cast<size_t>(matchStart) < size)) {
ASSERT(matchStart == USEARCH_DONE);
return 0;
}
// Matches that start in the overlap area are only tentative.
// The same match may appear later, matching more characters,
// possibly including a combining character that's not yet in the buffer.
if (!m_atBreak && static_cast<size_t>(matchStart) >= size - m_overlap) {
size_t overlap = m_overlap;
if (m_options & AtWordStarts) {
// Ensure that there is sufficient context before matchStart the next time around for
// determining if it is at a word boundary.
int wordBoundaryContextStart = matchStart;
U16_BACK_1(m_buffer.data(), 0, wordBoundaryContextStart);
wordBoundaryContextStart = startOfLastWordBoundaryContext(m_buffer.data(), wordBoundaryContextStart);
overlap = std::min(size - 1, std::max(overlap, size - wordBoundaryContextStart));
}
memcpy(m_buffer.data(), m_buffer.data() + size - overlap, overlap * sizeof(UChar));
m_prefixLength -= std::min(m_prefixLength, size - overlap);
m_buffer.shrink(overlap);
return 0;
}
size_t matchedLength = usearch_getMatchedLength(searcher);
ASSERT_WITH_SECURITY_IMPLICATION(matchStart + matchedLength <= size);
// If this match is "bad", move on to the next match.
if (isBadMatch(m_buffer.data() + matchStart, matchedLength) || ((m_options & AtWordStarts) && !isWordStartMatch(matchStart, matchedLength))) {
matchStart = usearch_next(searcher, &status);
ASSERT(status == U_ZERO_ERROR);
goto nextMatch;
}
size_t newSize = size - (matchStart + 1);
memmove(m_buffer.data(), m_buffer.data() + matchStart + 1, newSize * sizeof(UChar));
m_prefixLength -= std::min<size_t>(m_prefixLength, matchStart + 1);
m_buffer.shrink(newSize);
start = size - matchStart;
return matchedLength;
}
