#include "chromeos/ash/components/string_matching/term_break_iterator.h"
#include <ostream>
#include "base/check.h"
#include "base/compiler_specific.h"
#include "base/i18n/char_iterator.h"
#include "base/logging.h"
#include "base/notreached.h"
#include "base/strings/string_util.h"
#include "third_party/icu/source/common/unicode/uchar.h"
namespace ash::string_matching {
TermBreakIterator::TermBreakIterator(const std::u16string& word)
: word_(word),
prev_(npos),
pos_(0),
iter_(std::make_unique<base::i18n::UTF16CharIterator>(word)),
state_(STATE_START) {}
TermBreakIterator::~TermBreakIterator() = default;
bool TermBreakIterator::Advance() {
const bool kBoundary[][STATE_LAST] = {
{false, false, false, false, false},
{false, false, true, true, true},
{false, true, false, false, true},
{false, true, true, false, true},
{false, true, true, true, false},
};
while (iter_->Advance()) {
const State new_state = GetNewState((*word_)[iter_->array_pos()]);
const bool is_boundary = UNSAFE_TODO(kBoundary[state_][new_state]);
state_ = new_state;
if (is_boundary)
break;
}
prev_ = pos_;
pos_ = iter_->array_pos();
return prev_ != pos_ || !iter_->end();
}
const std::u16string TermBreakIterator::GetCurrentTerm() const {
DCHECK(prev_ != npos && pos_ != npos);
return word_->substr(prev_, pos_ - prev_);
}
TermBreakIterator::State TermBreakIterator::GetNewState(char16_t ch) {
if (base::IsAsciiDigit(ch) || ch == '.' || ch == ',')
return STATE_NUMBER;
const bool is_upper = !!u_isUUppercase(ch);
const bool is_lower = !!u_isULowercase(ch);
if (is_upper && is_lower) {
NOTREACHED() << "Invalid state for ch=" << std::u16string(1, ch);
}
if (is_upper)
return STATE_UPPER;
if (is_lower)
return STATE_LOWER;
return STATE_CHAR;
}
}