Skip to content

unicode : avoid char32_t #7957

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 16, 2024
Merged

unicode : avoid char32_t #7957

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13246,7 +13246,7 @@ struct llm_tokenizer_wpm {
const std::vector<uint32_t> cpts_nfd = unicode_cpts_normalize_nfd(unicode_cpts_from_utf8(text));
std::vector<std::string> words(1, "");

for (const char32_t cpt : cpts_nfd) {
for (const uint32_t cpt : cpts_nfd) {
const auto flags = unicode_cpt_flags(cpt);

if (flags.is_whitespace) {
Expand Down
22 changes: 11 additions & 11 deletions unicode.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,7 +226,7 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
assert(offset_end <= cpts.size());
start = offset_end;

auto _get_cpt = [&] (const size_t pos) -> char32_t {
auto _get_cpt = [&] (const size_t pos) -> uint32_t {
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : 0;
};

Expand All @@ -253,18 +253,18 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
};

for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
const char32_t cpt = _get_cpt(pos);
const uint32_t cpt = _get_cpt(pos);
const auto flags = _get_flags(pos);

// regex: 's|'t|'re|'ve|'m|'ll|'d
if (cpt == '\'' && pos+1 < offset_end) {
char32_t cpt_next = _get_cpt(pos+1);
uint32_t cpt_next = _get_cpt(pos+1);
if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
pos += _add_token(pos+2);
continue;
}
if (pos+2 < offset_end) {
char32_t cpt_next_next = _get_cpt(pos+2);
uint32_t cpt_next_next = _get_cpt(pos+2);
if ((cpt_next == 'r' && cpt_next_next == 'e') ||
(cpt_next == 'v' && cpt_next_next == 'e') ||
(cpt_next == 'l' && cpt_next_next == 'l')) {
Expand Down Expand Up @@ -344,7 +344,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
assert(offset_end <= cpts.size());
start = offset_end;

auto _get_cpt = [&] (const size_t pos) -> char32_t {
auto _get_cpt = [&] (const size_t pos) -> uint32_t {
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : 0;
};

Expand All @@ -371,18 +371,18 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
};

for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
const char32_t cpt = _get_cpt(pos);
const uint32_t cpt = _get_cpt(pos);
const auto flags = _get_flags(pos);

// regex: (?i:'s|'t|'re|'ve|'m|'ll|'d) // case insensitive
if (cpt == '\'' && pos+1 < offset_end) {
char32_t cpt_next = unicode_tolower(_get_cpt(pos+1));
uint32_t cpt_next = unicode_tolower(_get_cpt(pos+1));
if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
pos += _add_token(pos+2);
continue;
}
if (pos+2 < offset_end) {
char32_t cpt_next_next = unicode_tolower(_get_cpt(pos+2));
uint32_t cpt_next_next = unicode_tolower(_get_cpt(pos+2));
if ((cpt_next == 'r' && cpt_next_next == 'e') ||
(cpt_next == 'v' && cpt_next_next == 'e') ||
(cpt_next == 'l' && cpt_next_next == 'l')) {
Expand Down Expand Up @@ -424,7 +424,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
flags2 = _get_flags(++pos);
}
char32_t cpt2 = _get_cpt(pos);
uint32_t cpt2 = _get_cpt(pos);
while (cpt2 == '\r' || cpt2 == '\n') {
cpt2 = _get_cpt(++pos);
}
Expand All @@ -435,7 +435,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
size_t num_whitespaces = 0;
size_t last_end_r_or_n = 0;
while (_get_flags(pos+num_whitespaces).is_whitespace) {
char32_t cpt2 = _get_cpt(pos+num_whitespaces);
uint32_t cpt2 = _get_cpt(pos+num_whitespaces);
if (cpt2 == '\r' || cpt2 == '\n') {
last_end_r_or_n = pos + num_whitespaces + 1;
}
Expand Down Expand Up @@ -626,7 +626,7 @@ uint8_t unicode_utf8_to_byte(const std::string & utf8) {
return map.at(utf8);
}

char32_t unicode_tolower(char32_t cp) {
uint32_t unicode_tolower(uint32_t cp) {
auto it = unicode_map_lowercase.find(cp);
return it == unicode_map_lowercase.end() ? cp : it->second;
}
Expand Down
2 changes: 1 addition & 1 deletion unicode.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,6 @@ codepoint_flags unicode_cpt_flags(const std::string & utf8);
std::string unicode_byte_to_utf8(uint8_t byte);
uint8_t unicode_utf8_to_byte(const std::string & utf8);

char32_t unicode_tolower(char32_t cp);
uint32_t unicode_tolower(uint32_t cp);

std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs);
Loading