Skip to content
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

unicode : improve naming style #10838

Merged
merged 2 commits into from
Dec 16, 2024
Merged

unicode : improve naming style #10838

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a20c28
unicode : improve naming style
ggerganov Dec 15, 2024
3e92f4e
cont [no ci]
ggerganov Dec 15, 2024
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 src/llama-vocab.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -738,7 +738,7 @@ struct llm_tokenizer_wpm_session {
std::vector<std::string> words(1, "");

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

if (flags.is_whitespace) {
if (words.back().size()) { // finish previous word if any
Expand Down
102 changes: 51 additions & 51 deletions src/unicode.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,15 +71,15 @@ uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) {
throw std::invalid_argument("failed to convert utf8 to codepoint");
}

//static std::vector<uint16_t> unicode_cpt_to_utf16(uint32_t cp) {
//static std::vector<uint16_t> unicode_cpt_to_utf16(uint32_t cpt) {
// std::vector<uint16_t> result;
// if (/* 0x0000 <= cp && */ cp <= 0xffff) {
// result.emplace_back(cp);
// if (/* 0x0000 <= cpt && */ cpt <= 0xffff) {
// result.emplace_back(cpt);
// return result;
// }
// if (0x10000 <= cp && cp <= 0x10ffff) {
// result.emplace_back(0xd800 | ((cp - 0x10000) >> 10));
// result.emplace_back(0xdc00 | ((cp - 0x10000) & 0x03ff));
// if (0x10000 <= cpt && cpt <= 0x10ffff) {
// result.emplace_back(0xd800 | ((cpt - 0x10000) >> 10));
// result.emplace_back(0xdc00 | ((cpt - 0x10000) & 0x03ff));
// return result;
// }
// throw std::invalid_argument("failed to convert codepoint to utf16");
Expand Down Expand Up @@ -120,8 +120,8 @@ uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) {
// return result;
//}

static std::vector<codepoint_flags> unicode_cpt_flags_array() {
std::vector<codepoint_flags> cpt_flags(MAX_CODEPOINTS, codepoint_flags::UNDEFINED);
static std::vector<unicode_cpt_flags> unicode_cpt_flags_array() {
std::vector<unicode_cpt_flags> cpt_flags(MAX_CODEPOINTS, unicode_cpt_flags::UNDEFINED);

assert (unicode_ranges_flags.begin()[0].first == 0);
assert (unicode_ranges_flags.begin()[unicode_ranges_flags.size()-1].first == MAX_CODEPOINTS);
Expand Down Expand Up @@ -253,8 +253,8 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
};

auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
auto _get_flags = [&] (const size_t pos) -> unicode_cpt_flags {
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags_from_cpt(cpts[pos]) : unicode_cpt_flags{};
};

size_t _prev_end = offset_ini;
Expand Down Expand Up @@ -371,8 +371,8 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
};

auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
auto _get_flags = [&] (const size_t pos) -> unicode_cpt_flags {
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags_from_cpt(cpts[pos]) : unicode_cpt_flags{};
};

size_t _prev_end = offset_ini;
Expand Down Expand Up @@ -572,29 +572,29 @@ static std::vector<size_t> unicode_regex_split_custom(const std::string & text,
// interface
//

std::string unicode_cpt_to_utf8(uint32_t cp) {
std::string unicode_cpt_to_utf8(uint32_t cpt) {
std::string result;

if (/* 0x00 <= cp && */ cp <= 0x7f) {
result.push_back(cp);
if (/* 0x00 <= cpt && */ cpt <= 0x7f) {
result.push_back(cpt);
return result;
}
if (0x80 <= cp && cp <= 0x7ff) {
result.push_back(0xc0 | ((cp >> 6) & 0x1f));
result.push_back(0x80 | (cp & 0x3f));
if (0x80 <= cpt && cpt <= 0x7ff) {
result.push_back(0xc0 | ((cpt >> 6) & 0x1f));
result.push_back(0x80 | (cpt & 0x3f));
return result;
}
if (0x800 <= cp && cp <= 0xffff) {
result.push_back(0xe0 | ((cp >> 12) & 0x0f));
result.push_back(0x80 | ((cp >> 6) & 0x3f));
result.push_back(0x80 | (cp & 0x3f));
if (0x800 <= cpt && cpt <= 0xffff) {
result.push_back(0xe0 | ((cpt >> 12) & 0x0f));
result.push_back(0x80 | ((cpt >> 6) & 0x3f));
result.push_back(0x80 | (cpt & 0x3f));
return result;
}
if (0x10000 <= cp && cp <= 0x10ffff) {
result.push_back(0xf0 | ((cp >> 18) & 0x07));
result.push_back(0x80 | ((cp >> 12) & 0x3f));
result.push_back(0x80 | ((cp >> 6) & 0x3f));
result.push_back(0x80 | (cp & 0x3f));
if (0x10000 <= cpt && cpt <= 0x10ffff) {
result.push_back(0xf0 | ((cpt >> 18) & 0x07));
result.push_back(0x80 | ((cpt >> 12) & 0x3f));
result.push_back(0x80 | ((cpt >> 6) & 0x3f));
result.push_back(0x80 | (cpt & 0x3f));
return result;
}

Expand Down Expand Up @@ -624,19 +624,19 @@ std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8) {
return result;
}

codepoint_flags unicode_cpt_flags(const uint32_t cp) {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
unicode_cpt_flags unicode_cpt_flags_from_cpt(const uint32_t cpt) {
static const unicode_cpt_flags undef(unicode_cpt_flags::UNDEFINED);
static const auto cpt_flags = unicode_cpt_flags_array();
return cp < cpt_flags.size() ? cpt_flags[cp] : undef;
return cpt < cpt_flags.size() ? cpt_flags[cpt] : undef;
}

codepoint_flags unicode_cpt_flags(const std::string & utf8) {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
unicode_cpt_flags unicode_cpt_flags_from_utf8(const std::string & utf8) {
static const unicode_cpt_flags undef(unicode_cpt_flags::UNDEFINED);
if (utf8.empty()) {
return undef; // undefined
}
size_t offset = 0;
return unicode_cpt_flags(unicode_cpt_from_utf8(utf8, offset));
return unicode_cpt_flags_from_cpt(unicode_cpt_from_utf8(utf8, offset));
}

std::string unicode_byte_to_utf8(uint8_t byte) {
Expand All @@ -649,41 +649,41 @@ uint8_t unicode_utf8_to_byte(const std::string & utf8) {
return map.at(utf8);
}

uint32_t unicode_tolower(uint32_t cp) {
uint32_t unicode_tolower(uint32_t cpt) {
// binary search
auto it = std::lower_bound(unicode_map_lowercase.begin(), unicode_map_lowercase.end(), cp,
auto it = std::lower_bound(unicode_map_lowercase.begin(), unicode_map_lowercase.end(), cpt,
[](const std::pair<uint32_t, uint32_t> & pair, uint32_t value) {
return pair.first < value;
});
if (it != unicode_map_lowercase.end() && it->first == cp) {
if (it != unicode_map_lowercase.end() && it->first == cpt) {
return it->second;
}
return cp; // Return the original code point if no lowercase mapping is found
return cpt; // Return the original code point if no lowercase mapping is found
}

std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs) {
// unicode categories
static const std::map<std::string, int> k_ucat_enum = {
{ "\\p{N}", codepoint_flags::NUMBER },
{ "\\p{L}", codepoint_flags::LETTER },
{ "\\p{P}", codepoint_flags::PUNCTUATION },
{ "\\p{N}", unicode_cpt_flags::NUMBER },
{ "\\p{L}", unicode_cpt_flags::LETTER },
{ "\\p{P}", unicode_cpt_flags::PUNCTUATION },
};

static const std::map<int, int> k_ucat_cpt = {
{ codepoint_flags::NUMBER, 0xD1 },
{ codepoint_flags::LETTER, 0xD2 },
{ codepoint_flags::PUNCTUATION, 0xD3 },
{ unicode_cpt_flags::NUMBER, 0xD1 },
{ unicode_cpt_flags::LETTER, 0xD2 },
{ unicode_cpt_flags::PUNCTUATION, 0xD3 },
};

static const std::map<int, std::string> k_ucat_map = {
{ codepoint_flags::NUMBER, "\x30-\x39" }, // 0-9
{ codepoint_flags::LETTER, "\x41-\x5A\x61-\x7A" }, // A-Za-z
{ codepoint_flags::PUNCTUATION, "\x21-\x23\x25-\x2A\x2C-\x2F\x3A-\x3B\x3F-\x40\\\x5B-\\\x5D\x5F\\\x7B\\\x7D" }, // !-#%-*,-/:-;?-@\[-\]_\{\}
{ unicode_cpt_flags::NUMBER, "\x30-\x39" }, // 0-9
{ unicode_cpt_flags::LETTER, "\x41-\x5A\x61-\x7A" }, // A-Za-z
{ unicode_cpt_flags::PUNCTUATION, "\x21-\x23\x25-\x2A\x2C-\x2F\x3A-\x3B\x3F-\x40\\\x5B-\\\x5D\x5F\\\x7B\\\x7D" }, // !-#%-*,-/:-;?-@\[-\]_\{\}
};

// compute collapsed codepoints only if needed by at least one regex
bool need_collapse = false;
for (auto & regex_expr : regex_exprs) {
for (const auto & regex_expr : regex_exprs) {
// search for unicode categories
for (const auto & ucat : k_ucat_enum) {
if (std::string::npos != regex_expr.find(ucat.first)) {
Expand All @@ -709,7 +709,7 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
continue;
}

const auto flags = unicode_cpt_flags(cpts[i]);
const auto flags = unicode_cpt_flags_from_cpt(cpts[i]);

if (flags.is_whitespace) {
//NOTE: C++ std::regex \s does not mach 0x85, Rust and Python regex does.
Expand All @@ -725,7 +725,7 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std

std::vector<size_t> bpe_offsets = { cpts.size() };

for (auto & regex_expr : regex_exprs) {
for (const auto & regex_expr : regex_exprs) {
// first, see if we have an efficient custom regex implementation
auto tmp = unicode_regex_split_custom(text, regex_expr, bpe_offsets);

Expand All @@ -739,7 +739,7 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
// if a unicode category is used in the regex, we use the collapsed text and replace the unicode category
// with the corresponding collapsed representation
bool use_collapsed = false;
for (auto & ucat : k_ucat_enum) {
for (const auto & ucat : k_ucat_enum) {
if (std::string::npos != regex_expr.find(ucat.first)) {
use_collapsed = true;
break;
Expand Down Expand Up @@ -805,7 +805,7 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
// std::wregex \s does not mach non-ASCII whitespaces, using 0x0B as fallback
std::wstring wtext(cpts.begin(), cpts.end());
for (size_t i = 0; i < wtext.size(); ++i) {
if (wtext[i] > 0x7F && unicode_cpt_flags(wtext[i]).is_whitespace) {
if (wtext[i] > 0x7F && unicode_cpt_flags_from_cpt(wtext[i]).is_whitespace) {
wtext[i] = 0x0B;
}
}
Expand Down
19 changes: 9 additions & 10 deletions src/unicode.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,7 @@
#include <string>
#include <vector>

// TODO: prefix all symbols with "llama_"

struct codepoint_flags {
struct unicode_cpt_flags {
enum {
UNDEFINED = 0x0001,
NUMBER = 0x0002, // regex: \p{N}
Expand Down Expand Up @@ -35,7 +33,7 @@ struct codepoint_flags {
uint16_t is_nfd : 1;

// decode from uint16
inline codepoint_flags(const uint16_t flags=0) {
inline unicode_cpt_flags(const uint16_t flags = 0) {
*reinterpret_cast<uint16_t*>(this) = flags;
}

Expand All @@ -50,18 +48,19 @@ struct codepoint_flags {

size_t unicode_len_utf8(char src);

std::string unicode_cpt_to_utf8(uint32_t cp);
uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset);
std::string unicode_cpt_to_utf8 (uint32_t cpt);
uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset);

std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8);

std::vector<uint32_t> unicode_cpts_normalize_nfd(const std::vector<uint32_t> & cpts);

codepoint_flags unicode_cpt_flags(const uint32_t cp);
codepoint_flags unicode_cpt_flags(const std::string & utf8);
unicode_cpt_flags unicode_cpt_flags_from_cpt (uint32_t cpt);
unicode_cpt_flags unicode_cpt_flags_from_utf8(const std::string & utf8);

std::string unicode_byte_to_utf8(uint8_t byte);
uint8_t unicode_utf8_to_byte(const std::string & utf8);
uint8_t unicode_utf8_to_byte(const std::string & utf8);

uint32_t unicode_tolower(uint32_t cp);
uint32_t unicode_tolower(uint32_t cpt);

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