ZZY 2b4857001c feat(frontend): 重构词法分析器
- 添加 .gitignore 文件,忽略编译器生成的二进制文件
- 重构 lexer.c 文件,改进了关键字处理和字符串处理
- 更新前端的前端、解析器和 AST 相关文件,以适应新的词法分析器
- 优化了 token 相关的定义和函数,引入了新的 token 类型
2025-03-23 12:13:16 +08:00

87 lines
2.1 KiB
C
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#include <lib/core.h>
#include "lexer_log.h"
#include "token.h"
#define ROUND_IDX(idx) ((idx) % tokbuf->cap)
tok_t* pop_tok(tok_stream_t* tokbuf) {
if (tokbuf->size == 0) {
LEX_ERROR("no token to pop");
return NULL;
}
int idx = tokbuf->cur;
tokbuf->cur = ROUND_IDX(idx + 1);
tokbuf->size -= 1;
return tokbuf->buf + idx;
}
void flush_peek_tok(tok_stream_t* tokbuf) {
tokbuf->peek = tokbuf->cur;
}
void init_tokbuf(tok_stream_t *tokbuf, void *stream, tok_stream_get_func gettok) {
tokbuf->cur = 0;
tokbuf->end = 0;
tokbuf->peek = 0;
tokbuf->size = 0;
tokbuf->stream = stream;
tokbuf->gettok = gettok;
tokbuf->buf = NULL;
tokbuf->cap = 0;
}
tok_t *peek_tok(tok_stream_t *tokbuf) {
Assert(tokbuf->size <= tokbuf->cap);
int idx = tokbuf->peek;
tokbuf->peek = ROUND_IDX(idx + 1);
if (idx == tokbuf->end) {
if (tokbuf->size == tokbuf->cap) {
LEX_ERROR("peek_tok buffer overflow");
return NULL;
}
if (tokbuf->gettok == NULL) {
LEX_ERROR("peek_tok can not got tok");
return NULL;
}
tokbuf->gettok(tokbuf->stream, &(tokbuf->buf[idx]));
tokbuf->size++;
tokbuf->end = tokbuf->peek;
}
return &(tokbuf->buf[idx]);
}
cc_tktype_t peek_tok_type(tok_stream_t* tokbuf) {
return peek_tok(tokbuf)->sub_type;
}
int expect_pop_tok(tok_stream_t* tokbuf, cc_tktype_t type) {
flush_peek_tok(tokbuf);
tok_t* tok = peek_tok(tokbuf);
if (tok->sub_type != type) {
LEX_ERROR("expected tok `%s` but got `%s`", get_tok_name(type), get_tok_name(tok->type));
return 0;
} else {
pop_tok(tokbuf);
}
return 0;
}
// 生成字符串映射(根据需求选择#str或#name
static const char* token_strings[] = {
// 普通token使用#str
#define X(str, basic, tok) [tok] = #str,
TOKEN_TABLE
#undef X
// 关键字使用#name
#define X(name, std, tok) [tok] = #name,
KEYWORD_TABLE
#undef X
};
const char* get_tok_name(cc_tktype_t type) {
return token_strings[type];
}