From b333b06772c89d96aacb5490d6a219fba7c09cc6 Mon Sep 17 00:00:00 2001 From: Mitja Felicijan Date: Thu, 12 Feb 2026 20:57:17 +0100 Subject: Engage! --- llama.cpp/tests/peg-parser/simple-tokenize.cpp | 37 ++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 llama.cpp/tests/peg-parser/simple-tokenize.cpp (limited to 'llama.cpp/tests/peg-parser/simple-tokenize.cpp') diff --git a/llama.cpp/tests/peg-parser/simple-tokenize.cpp b/llama.cpp/tests/peg-parser/simple-tokenize.cpp new file mode 100644 index 0000000..9abfa04 --- /dev/null +++ b/llama.cpp/tests/peg-parser/simple-tokenize.cpp @@ -0,0 +1,37 @@ +#include "simple-tokenize.h" + +std::vector simple_tokenize(const std::string & input) { + std::vector result; + std::string current; + + for (size_t i = 0; i < input.size(); i++) { + switch (input[i]) { + case ' ': + case '\n': + case '\t': + case '{': + case '}': + case ',': + case '[': + case '"': + case ']': + case '.': + case '<': + case '>': + case '=': + case '/': + if (!current.empty()) { + result.push_back(current); + current.clear(); + } + default:; + } + current += input[i]; + } + + if (!current.empty()) { + result.push_back(current); + } + + return result; +} -- cgit v1.2.3