From efd05648c88a0923a55f56e7ce1b0f9c33410afb Mon Sep 17 00:00:00 2001 From: Arik Poznanski Date: Mon, 17 Apr 2023 17:41:53 +0300 Subject: llama : well-defined static initialization of complex objects (#927) * Replaced static initialization of complex objects with a initialization on first use. This prevents an undefined behavior on program run, for example, crash in Release build, works in Debug build * replaced use of auto with exact type to avoid using -std=c++14 * Made the assessors functions for static maps be static const --- tests/test-tokenizer-0.cpp | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'tests/test-tokenizer-0.cpp') diff --git a/tests/test-tokenizer-0.cpp b/tests/test-tokenizer-0.cpp index 55b086da..b0898457 100644 --- a/tests/test-tokenizer-0.cpp +++ b/tests/test-tokenizer-0.cpp @@ -5,13 +5,17 @@ #include #include -static const std::map> k_tests = { - { "Hello World", { 1, 10994, 2787, }, }, - { " Hello World", { 1, 15043, 2787, }, }, - { " Hello World!", { 1, 15043, 2787, 29991, }, }, - { " this is 🦙.cpp", { 1, 445, 338, 29871, 243, 162, 169, 156, 29889, 8223, }, }, - { "w048 7tuijk dsdfhu", { 1, 29893, 29900, 29946, 29947, 29871, 29955, 9161, 13535, 18031, 2176, 6905, }, }, - { "нещо на Български", { 1, 821, 4851, 665, 1386, 29713, 1305, }, }, +static const std::map> & k_tests() +{ + static std::map> _k_tests = { + { "Hello World", { 1, 10994, 2787, }, }, + { " Hello World", { 1, 15043, 2787, }, }, + { " Hello World!", { 1, 15043, 2787, 29991, }, }, + { " this is 🦙.cpp", { 1, 445, 338, 29871, 243, 162, 169, 156, 29889, 8223, }, }, + { "w048 7tuijk dsdfhu", { 1, 29893, 29900, 29946, 29947, 29871, 29955, 9161, 13535, 18031, 2176, 6905, }, }, + { "нещо на Български", { 1, 821, 4851, 665, 1386, 29713, 1305, }, }, + }; + return _k_tests; }; int main(int argc, char **argv) { @@ -47,7 +51,7 @@ int main(int argc, char **argv) { return 2; } - for (const auto & test_kv : k_tests) { + for (const auto & test_kv : k_tests()) { std::vector res(test_kv.first.size()); const int n = llama_tokenize(ctx, test_kv.first.c_str(), res.data(), res.size(), true); res.resize(n); -- cgit v1.2.3