diff options
| -rw-r--r-- | include/lexer/parseline.h | 10 | ||||
| -rw-r--r-- | module-test/parseline_test.cc | 61 | ||||
| -rw-r--r-- | src/lexer/parseline.cc | 80 | ||||
| -rw-r--r-- | src/lexer/token.cc | 2 |
4 files changed, 152 insertions, 1 deletions
diff --git a/include/lexer/parseline.h b/include/lexer/parseline.h new file mode 100644 index 0000000..e52b50e --- /dev/null +++ b/include/lexer/parseline.h @@ -0,0 +1,10 @@ +#pragma once + +#include <string> + +namespace ov4 +{ + +char **parseline(const std::string &s); + +} diff --git a/module-test/parseline_test.cc b/module-test/parseline_test.cc new file mode 100644 index 0000000..047be48 --- /dev/null +++ b/module-test/parseline_test.cc @@ -0,0 +1,61 @@ +/* + * test lexer/parseline +$ +g++ \ + module-test/parseline_test.cc \ + src/lexer/parseline.cc \ + src/util/string.cc \ + -std=c++23 -Iinclude \ + -O0 -ggdb3 -fno-omit-frame-pointer -fno-inline -D_GLIBCXX_ASSERTIONS \ + -o module-test/parseline_test.out +*/ + +#include <iostream> +#include <print> + +#include "lexer/parseline.h" + +using namespace std; + +int main() +{ + int test_case = 0; + println("start test"); + cin >> test_case; + string s; + + switch (test_case) + { + case 0: + s = "alpha beta"; + break; + + case 1: + s = "alpha \'arg1 and arg2\'"; + break; + + case 2: + s = "alpha \'arg1 \" arg2 arg3 \'"; + break; + + case 3: + s = "alpha \'arg1 \"arg2 arg3\" arg4 \'"; + break; + + default: + return 0; + } + char **p = ov4::parseline(s); + if (p == nullptr) + { + println("Ooooops nullptr"); + return 0; + } + for (size_t i = 0; ; i++) + { + if (p[i] == nullptr) + break; + println("{}", p[i]); + } + return 0; +} diff --git a/src/lexer/parseline.cc b/src/lexer/parseline.cc new file mode 100644 index 0000000..064f876 --- /dev/null +++ b/src/lexer/parseline.cc @@ -0,0 +1,80 @@ +#include "lexer/parseline.h" + +#include <vector> + +#include "lexer/enum_type.h" +#include "util/string.h" + +using namespace std; + +namespace ov4 +{ + +char **parseline(const std::string &s) +{ + guard_type guard = GUARD_OFF; + vector<string> v; + size_t len = s.size(); + string prev_str = ""; + char c; + + for (size_t i = 0; i < len; i++) + { + + c = s[i]; + if (c == ' ' && guard == GUARD_OFF) continue; + + if (c == '\'' || c == '\"') + { + + // turn on GUARD + if (guard == GUARD_OFF) + { + guard = (c == '\'') ? GUARD_STRONG : GUARD_WEAK; + if (i+1 == len) + { + v.push_back(prev_str); + prev_str = ""; + } + continue; + } + // turn off + else if (guard == GUARD_STRONG && c == '\'') + { + guard = GUARD_OFF; + if (i+1 == len) + { + v.push_back(prev_str); + prev_str = ""; + } + continue; + } + // turn off + else if (guard == GUARD_WEAK && c == '\"') + { + guard = GUARD_OFF; + if (i+1 == len) + { + v.push_back(prev_str); + prev_str = ""; + } + continue; + } + // if this (single/double) quotation mark is guarded + // it should be saved + } + + prev_str += c; + + if ((i+1 >= len) || (s[i+1] == ' ' && guard == GUARD_OFF)) + { + v.push_back(prev_str); + prev_str = ""; + continue; + } + } + + return string2argv_alloc(v); +} + +} diff --git a/src/lexer/token.cc b/src/lexer/token.cc index b9b8242..ec69090 100644 --- a/src/lexer/token.cc +++ b/src/lexer/token.cc @@ -12,7 +12,7 @@ using namespace std; // remove this -constexpr bool TOKEN_DEBUG = true; +constexpr bool TOKEN_DEBUG = false; namespace ov4 { |