zzy/scc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(lex_parser): 移除旧的词法解析器实现并更新依赖

Browse Source 
移除了 libs/lex_parser 目录下的所有头文件和源文件，包括：
- lex_parser.h 和 lex_parser.c 核心解析功能
- 所有测试文件（test_char.c, test_identifier.c, test_number.c,
  test_skip_block_comment.c, test_skip_line.c, test_string.c）

更新了 lexer 模块的依赖配置，将 lex_parser 替换为 sstream，
同时更新了 lexer.h 中的相关包含头文件和数据结构定义，
简化了 scc_lexer_t 结构体的字段。
This commit is contained in:
zzy
2026-02-16 16:56:40 +08:00
parent 088050c903
commit 0e7dec202a
30 changed files with 1840 additions and 1979 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
libs/lexer/cbuild.toml
View File

@@ -4,5 +4,5 @@ version = "0.1.0"
dependencies = [
{ name = "scc_core", path = "../../runtime/scc_core" },
{ name = "lex_parser", path = "../lex_parser" },
{ name = "lex_parser", path = "../sstream" },
]

12
libs/lexer/include/lexer.h
View File

@@ -8,6 +8,7 @@
#include "lexer_token.h"
#include <scc_core.h>
#include <scc_sstream.h>
/**
* @brief 词法分析器核心结构体
@@ -15,16 +16,11 @@
* 封装词法分析所需的状态信息和缓冲区管理
*/
typedef struct scc_lexer {
scc_probe_stream_t *stream;
scc_pos_t pos;
scc_sstream_ring_t stream_ref;
int jump_macro;
} scc_lexer_t;
/**
* @brief 初始化词法分析器
* @param[out] lexer 要初始化的词法分析器实例
* @param[in] stream 输入流对象指针
*/
void scc_lexer_init(scc_lexer_t *lexer, scc_probe_stream_t *stream);
void scc_lexer_init(scc_lexer_t *lexer, scc_sstream_ring_t *stream_ref);
/**
* @brief 获取原始token

119
libs/lexer/include/lexer_token.h
View File

@@ -2,6 +2,7 @@
#define __SCC_LEXER_TOKEN_H__
#include <scc_core.h>
#include <scc_pos.h>
typedef enum scc_cstd {
SCC_CSTD_C89,
@@ -54,64 +55,64 @@ typedef enum scc_cstd {
// KEYWORD_TABLE
#define SCC_CTOK_TABLE \
X(unknown , SCC_TOK_SUBTYPE_INVALID, SCC_TOK_UNKNOWN ) \
X(EOF , SCC_TOK_SUBTYPE_EOF, SCC_TOK_EOF ) \
X(blank , SCC_TOK_SUBTYPE_EMPTYSPACE, SCC_TOK_BLANK ) \
X(endline , SCC_TOK_SUBTYPE_EMPTYSPACE, SCC_TOK_ENDLINE ) \
X("#" , SCC_TOK_SUBTYPE_EMPTYSPACE, SCC_TOK_SHARP ) \
X("==" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_EQ ) \
X("=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN ) \
X("++" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ADD_ADD ) \
X("+=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_ADD ) \
X("+" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ADD ) \
X("--" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_SUB_SUB ) \
X("-=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_SUB ) \
X("->" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_DEREF ) \
X("-" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_SUB ) \
X("*=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_MUL ) \
X("*" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_MUL ) \
X("/=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_DIV ) \
X("/" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_DIV ) \
X("//" , SCC_TOK_SUBTYPE_COMMENT , SCC_TOK_LINE_COMMENT ) \
X("/* */" , SCC_TOK_SUBTYPE_COMMENT , SCC_TOK_BLOCK_COMMENT ) \
X("%=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_MOD ) \
X("%" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_MOD ) \
X("&&" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_AND_AND ) \
X("&=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_AND ) \
X("&" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_AND ) \
X("||" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_OR_OR ) \
X("|=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_OR ) \
X("|" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_OR ) \
X("^=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_XOR ) \
X("^" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_XOR ) \
X("<<=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_L_SH ) \
X("<<" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_SH ) \
X("<=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_LE ) \
X("<" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_LT ) \
X(">>=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_R_SH ) \
X(">>" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_SH ) \
X(">=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_GE ) \
X(">" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_GT ) \
X("!" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_NOT ) \
X("!=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_NEQ ) \
X("~" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_BIT_NOT ) \
X("[" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_BRACKET ) \
X("]" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_BRACKET ) \
X("(" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_PAREN ) \
X(")" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_PAREN ) \
X("{" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_BRACE ) \
X("}" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_BRACE ) \
X(";" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_SEMICOLON ) \
X("," , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_COMMA ) \
X(":" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_COLON ) \
X("." , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_DOT ) \
X("..." , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ELLIPSIS ) \
X("?" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_COND ) \
X(ident , SCC_TOK_SUBTYPE_IDENTIFIER, SCC_TOK_IDENT ) \
X(int_literal , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_INT_LITERAL ) \
X(float_literal , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_FLOAT_LITERAL ) \
X(char_literal , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_CHAR_LITERAL ) \
X(string_literal , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_STRING_LITERAL ) \
X(unknown , SCC_TOK_SUBTYPE_INVALID, SCC_TOK_UNKNOWN ) \
X(EOF , SCC_TOK_SUBTYPE_EOF, SCC_TOK_EOF ) \
X(blank , SCC_TOK_SUBTYPE_EMPTYSPACE, SCC_TOK_BLANK ) \
X(endline , SCC_TOK_SUBTYPE_EMPTYSPACE, SCC_TOK_ENDLINE ) \
X("#" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_SHARP ) \
X("==" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_EQ ) \
X("=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN ) \
X("++" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ADD_ADD ) \
X("+=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_ADD ) \
X("+" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ADD ) \
X("--" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_SUB_SUB ) \
X("-=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_SUB ) \
X("->" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_DEREF ) \
X("-" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_SUB ) \
X("*=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_MUL ) \
X("*" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_MUL ) \
X("/=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_DIV ) \
X("/" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_DIV ) \
X("//" , SCC_TOK_SUBTYPE_COMMENT , SCC_TOK_LINE_COMMENT ) \
X("/* */" , SCC_TOK_SUBTYPE_COMMENT , SCC_TOK_BLOCK_COMMENT ) \
X("%=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_MOD ) \
X("%" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_MOD ) \
X("&&" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_AND_AND ) \
X("&=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_AND ) \
X("&" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_AND ) \
X("||" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_OR_OR ) \
X("|=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_OR ) \
X("|" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_OR ) \
X("^=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_XOR ) \
X("^" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_XOR ) \
X("<<=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_L_SH ) \
X("<<" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_SH ) \
X("<=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_LE ) \
X("<" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_LT ) \
X(">>=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ASSIGN_R_SH ) \
X(">>" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_SH ) \
X(">=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_GE ) \
X(">" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_GT ) \
X("!" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_NOT ) \
X("!=" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_NEQ ) \
X("~" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_BIT_NOT ) \
X("[" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_BRACKET ) \
X("]" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_BRACKET ) \
X("(" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_PAREN ) \
X(")" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_PAREN ) \
X("{" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_L_BRACE ) \
X("}" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_R_BRACE ) \
X(";" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_SEMICOLON ) \
X("," , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_COMMA ) \
X(":" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_COLON ) \
X("." , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_DOT ) \
X("..." , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_ELLIPSIS ) \
X("?" , SCC_TOK_SUBTYPE_OPERATOR, SCC_TOK_COND ) \
X(ident , SCC_TOK_SUBTYPE_IDENTIFIER, SCC_TOK_IDENT ) \
X(int , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_INT_LITERAL ) \
X(float , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_FLOAT_LITERAL ) \
X(char , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_CHAR_LITERAL ) \
X(string , SCC_TOK_SUBTYPE_LITERAL, SCC_TOK_STRING_LITERAL ) \
// END
/* clang-format on */
@@ -145,7 +146,7 @@ const char *scc_get_tok_name(scc_tok_type_t type);
typedef struct scc_lexer_token {
scc_tok_type_t type;
scc_cvalue_t value;
scc_cstring_t lexeme;
scc_pos_t loc;
} scc_lexer_tok_t;

799
libs/lexer/src/lexer.c
View File

@@ -1,4 +1,3 @@
#include <lex_parser.h>
#include <lexer.h>
#include <lexer_log.h>
@@ -13,442 +12,460 @@ static const struct {
};
// by using binary search to find the keyword
static inline int keyword_cmp(const char *name, int len) {
static int keyword_cmp(const char *name, int len) {
int low = 0;
int high = sizeof(keywords) / sizeof(keywords[0]) - 1;
while (low <= high) {
int mid = (low + high) / 2;
const char *key = keywords[mid].name;
int cmp = 0;
// 自定义字符串比较逻辑
for (int i = 0; i < len; i++) {
if (name[i] != key[i]) {
cmp = (unsigned char)name[i] - (unsigned char)key[i];
break;
}
if (name[i] == '\0')
break; // 遇到终止符提前结束
break;
}
if (cmp == 0) {
// 完全匹配检查（长度相同）
if (key[len] == '\0')
return mid;
cmp = -1; // 当前关键词比输入长
cmp = -1;
}
if (cmp < 0) {
if (cmp < 0)
high = mid - 1;
} else {
else
low = mid + 1;
}
}
return -1; // Not a keyword.
return -1; // 不是关键字
}
void scc_lexer_init(scc_lexer_t *lexer, scc_probe_stream_t *stream) {
lexer->stream = stream;
lexer->pos = scc_pos_create();
// FIXME
lexer->pos.name = scc_cstring_copy(&stream->name);
void scc_lexer_init(scc_lexer_t *lexer, scc_sstream_ring_t *stream_ref) {
lexer->stream_ref = *stream_ref;
lexer->jump_macro = false;
}
static inline cbool is_whitespace(int ch) {
return ch == ' ' || ch == '\t' || ch == '\v' || ch == '\f';
}
static inline cbool is_newline(int ch) { return ch == '\n' || ch == '\r'; }
static inline cbool is_digit(int ch) { return ch >= '0' && ch <= '9'; }
static inline cbool is_alpha(int ch) {
return (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z');
}
static inline cbool is_alnum(int ch) { return is_alpha(ch) || is_digit(ch); }
static inline cbool is_identifier_start(int ch) {
return is_alpha(ch) || ch == '_';
}
static inline cbool is_identifier_part(int ch) {
return is_alnum(ch) || ch == '_';
}
static inline cbool is_octal_digit(int ch) { return ch >= '0' && ch <= '7'; }
static inline cbool is_hex_digit(int ch) {
return is_digit(ch) || (ch >= 'a' && ch <= 'f') || (ch >= 'A' && ch <= 'F');
}
/* 从环形缓冲区预览一个字符（带EOF检测） */
static inline cbool peek_char(scc_lexer_t *lexer, scc_sstream_char_t *out) {
cbool ok;
scc_ring_peek(lexer->stream_ref, *out, ok);
return ok;
}
/* 从环形缓冲区消费一个字符，并将它追加到lexeme中 */
static inline cbool next_char(scc_lexer_t *lexer, scc_cstring_t *lexeme,
scc_sstream_char_t *out) {
cbool ok;
scc_ring_next(lexer->stream_ref, *out, ok);
if (!ok)
return false;
scc_cstring_append_ch(lexeme, out->character);
return true;
}
#define set_err_token(token) ((token)->type = SCC_TOK_UNKNOWN)
static void parse_line(scc_lexer_t *lexer, scc_lexer_tok_t *token) {
token->loc = lexer->pos;
scc_probe_stream_t *stream = lexer->stream;
scc_probe_stream_reset(stream);
int ch = scc_probe_stream_next(stream);
usize n;
scc_cstring_t str = scc_cstring_create();
if (ch == scc_stream_eof) {
LEX_WARN("Unexpected EOF at begin");
goto ERR;
} else if (ch != '#') {
LEX_WARN("Unexpected character '%c' at begin", ch);
goto ERR;
}
const char line[] = "line";
for (int i = 0; i < (int)sizeof(line); i++) {
ch = scc_probe_stream_consume(stream);
scc_pos_next(&lexer->pos);
if (ch != line[i]) {
LEX_WARN("Maroc does not support in lexer rather in preprocessor, "
"it will be ignored");
goto SKIP_LINE;
}
}
if (scc_lex_parse_number(stream, &lexer->pos, &n) == false) {
LEX_ERROR("Invalid line number");
goto SKIP_LINE;
}
if (scc_probe_stream_consume(stream) != ' ') {
scc_lex_parse_skip_line(stream, &lexer->pos);
token->loc.line = token->value.u;
}
if (scc_probe_stream_next(stream) != '"') {
LEX_ERROR("Invalid `#` line");
goto SKIP_LINE;
}
if (scc_lex_parse_string(stream, &lexer->pos, &str) == false) {
LEX_ERROR("Invalid filename");
goto SKIP_LINE;
}
scc_lex_parse_skip_line(stream, &lexer->pos);
scc_probe_stream_sync(stream);
token->loc.line = n;
// FIXME memory leak
token->loc.name = scc_cstring_copy(&str);
scc_cstring_free(&str);
return;
SKIP_LINE:
scc_lex_parse_skip_line(stream, &lexer->pos);
scc_probe_stream_sync(stream);
ERR:
set_err_token(token);
scc_cstring_free(&str);
}
// /zh/c/language/operator_arithmetic.html
void scc_lexer_get_token(scc_lexer_t *lexer, scc_lexer_tok_t *token) {
token->loc = lexer->pos;
token->type = SCC_TOK_UNKNOWN;
scc_probe_stream_t *stream = lexer->stream;
scc_sstream_char_t cur;
scc_cstring_t lex = scc_cstring_create(); // 临时lexeme
scc_probe_stream_reset(stream);
scc_tok_type_t type = SCC_TOK_UNKNOWN;
int ch = scc_probe_stream_next(stream);
// 尝试预览第一个字符
if (!peek_char(lexer, &cur)) {
token->type = SCC_TOK_EOF;
token->loc = (scc_pos_t){0, 1, 1, 0}; // 默认位置
token->lexeme = lex; // 空字符串
return;
}
// 记录起始位置
scc_pos_t start_loc = cur.pos;
int ch = cur.character;
// once step
switch (ch) {
case '=':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_EQ;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_ASSIGN;
break;
if (is_whitespace(ch)) {
// 空白符: 连续收集
token->type = SCC_TOK_BLANK;
while (peek_char(lexer, &cur) && is_whitespace(cur.character)) {
next_char(lexer, &lex, &cur);
}
break;
case '+':
switch (scc_probe_stream_next(stream)) {
case '+':
type = SCC_TOK_ADD_ADD;
goto double_char;
case '=':
type = SCC_TOK_ASSIGN_ADD;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_ADD;
break;
}
break;
case '-':
switch (scc_probe_stream_next(stream)) {
case '-':
type = SCC_TOK_SUB_SUB;
goto double_char;
case '=':
type = SCC_TOK_ASSIGN_SUB;
goto double_char;
case '>':
type = SCC_TOK_DEREF;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_SUB;
break;
}
break;
case '*':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_ASSIGN_MUL;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_MUL;
break;
}
break;
case '/':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_ASSIGN_DIV;
goto double_char;
case '/':
scc_probe_stream_reset(stream);
scc_lex_parse_skip_line(stream, &lexer->pos);
scc_probe_stream_sync(stream);
token->type = SCC_TOK_LINE_COMMENT;
goto END;
case '*':
scc_probe_stream_reset(stream);
scc_lex_parse_skip_block_comment(stream, &lexer->pos);
scc_probe_stream_sync(stream);
token->type = SCC_TOK_BLOCK_COMMENT;
goto END;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_DIV;
break;
}
break;
case '%':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_ASSIGN_MOD;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_MOD;
break;
}
break;
case '&':
switch (scc_probe_stream_next(stream)) {
case '&':
type = SCC_TOK_AND_AND;
goto double_char;
case '=':
type = SCC_TOK_ASSIGN_AND;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_AND;
break;
}
break;
case '|':
switch (scc_probe_stream_next(stream)) {
case '|':
type = SCC_TOK_OR_OR;
goto double_char;
case '=':
type = SCC_TOK_ASSIGN_OR;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_OR;
break;
}
break;
case '^':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_ASSIGN_XOR;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_XOR;
break;
}
break;
case '<':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_LE;
goto double_char;
case '<': {
if (scc_probe_stream_next(stream) == '=') {
type = SCC_TOK_ASSIGN_L_SH;
goto triple_char;
} else {
type = SCC_TOK_L_SH;
goto double_char;
}
break;
}
default:
scc_probe_stream_reset(stream), type = SCC_TOK_LT;
break;
}
break;
case '>':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_GE;
goto double_char;
case '>': {
if (scc_probe_stream_next(stream) == '=') {
type = SCC_TOK_ASSIGN_R_SH;
goto triple_char;
} else {
type = SCC_TOK_R_SH;
goto double_char;
}
break;
}
default:
scc_probe_stream_reset(stream), type = SCC_TOK_GT;
break;
}
break;
case '~':
type = SCC_TOK_BIT_NOT;
break;
case '!':
switch (scc_probe_stream_next(stream)) {
case '=':
type = SCC_TOK_NEQ;
goto double_char;
default:
scc_probe_stream_reset(stream), type = SCC_TOK_NOT;
break;
}
break;
/* clang-format off */
case '[': type = SCC_TOK_L_BRACKET; break;
case ']': type = SCC_TOK_R_BRACKET; break;
case '(': type = SCC_TOK_L_PAREN; break;
case ')': type = SCC_TOK_R_PAREN; break;
case '{': type = SCC_TOK_L_BRACE; break;
case '}': type = SCC_TOK_R_BRACE; break;
case ';': type = SCC_TOK_SEMICOLON; break;
case ',': type = SCC_TOK_COMMA; break;
case ':': type = SCC_TOK_COLON; break;
/* clang-format on */
case '.':
if (scc_probe_stream_next(stream) == '.' &&
scc_probe_stream_next(stream) == '.') {
type = SCC_TOK_ELLIPSIS;
goto triple_char;
}
type = SCC_TOK_DOT;
break;
case '?':
type = SCC_TOK_COND;
break;
case '\v':
case '\f':
case ' ':
case '\t':
type = SCC_TOK_BLANK;
break;
case '\r':
case '\n':
scc_probe_stream_back(stream);
scc_lex_parse_skip_endline(stream, &lexer->pos);
scc_probe_stream_sync(stream);
} else if (is_newline(ch)) {
// 换行符：处理 \r 或 \n，以及 \r\n 组合
token->type = SCC_TOK_ENDLINE;
goto END;
case '#':
parse_line(lexer, token);
token->type = SCC_TOK_SHARP;
goto END;
case '\0':
case scc_stream_eof:
// EOF
type = SCC_TOK_EOF;
break;
case '\'': {
token->loc = lexer->pos;
next_char(lexer, &lex, &cur); // 消费第一个字符
if (ch == '\r') {
// 尝试消费后面的 \n
if (peek_char(lexer, &cur) && cur.character == '\n') {
next_char(lexer, &lex, &cur);
}
}
} else if (ch == '/') {
// 可能为注释或除号
scc_sstream_char_t next = {0};
next_char(lexer, &lex, &cur); // 消费 '/'
peek_char(lexer, &next);
if (next.character == '=') {
token->type = SCC_TOK_ASSIGN_DIV;
next_char(lexer, &lex, &cur);
} else if (next.character == '/') {
// 行注释 //
token->type = SCC_TOK_LINE_COMMENT;
next_char(lexer, &lex, &cur); // 消费 '/'
while (peek_char(lexer, &cur) && !is_newline(cur.character)) {
next_char(lexer, &lex, &cur);
scc_ring_consume(lexer->stream_ref);
}
// 注释结束，不包含换行符（换行符单独成token）
} else if (next.character == '*') {
// 块注释 /*
token->type = SCC_TOK_BLOCK_COMMENT;
next_char(lexer, &lex, &cur); // 消费 '*'
while (1) {
if (!next_char(lexer, &lex, &cur)) {
// 文件结束，注释未闭合
LOG_ERROR("Unterminated block comment");
break;
}
if (cur.character == '*' && peek_char(lexer, &next) &&
next.character == '/') {
next_char(lexer, &lex, &cur); // 消费 '/'
break;
}
scc_ring_consume(lexer->stream_ref);
}
} else {
// 只是除号 /
token->type = SCC_TOK_DIV;
}
} else if (is_identifier_start(ch)) {
// 标识符或关键字
token->type = SCC_TOK_IDENT; // 暂定
while (peek_char(lexer, &cur) && is_identifier_part(cur.character)) {
next_char(lexer, &lex, &cur);
scc_ring_consume(lexer->stream_ref);
}
// 检查是否为关键字
int idx = keyword_cmp(scc_cstring_as_cstr(&lex), scc_cstring_len(&lex));
if (idx != -1) {
token->type = keywords[idx].tok;
}
} else if (is_digit(ch)) {
// 数字字面量（整数/浮点）
token->type = SCC_TOK_INT_LITERAL; // 先假定整数
cbool maybe_float = false;
while (1) {
next_char(lexer, &lex, &cur); // 消费当前数字
if (!peek_char(lexer, &cur))
break;
ch = cur.character;
if (is_digit(ch) || (ch == '.' && !maybe_float)) {
if (ch == '.')
maybe_float = true;
continue;
}
if (ch == 'e' || ch == 'E' || ch == 'p' || ch == 'P') {
maybe_float = true;
// 后面可能跟符号或数字
continue;
}
if (ch == 'x' || ch == 'X') {
// 十六进制前缀，需特殊处理
// 这里简化：将整个序列作为整数（保留前缀）
continue;
}
break;
}
if (maybe_float)
token->type = SCC_TOK_FLOAT_LITERAL;
} else if (ch == '\'') {
// 字符字面量
token->type = SCC_TOK_CHAR_LITERAL;
scc_probe_stream_reset(stream);
int ch = scc_lex_parse_char(stream, &lexer->pos);
scc_probe_stream_sync(stream);
if (ch == scc_stream_eof) {
LEX_ERROR("Unexpected character literal");
token->type = SCC_TOK_UNKNOWN;
} else {
token->value.ch = ch;
next_char(lexer, &lex, &cur); // 开头的 '
while (1) {
if (!peek_char(lexer, &cur)) {
LOG_ERROR("Unterminated character literal");
break;
}
if (cur.character == '\'') {
next_char(lexer, &lex, &cur); // 闭引号
break;
}
if (cur.character == '\\') {
// 转义序列：原样保存反斜杠和下一个字符
next_char(lexer, &lex, &cur);
if (!peek_char(lexer, &cur))
break;
next_char(lexer, &lex, &cur);
} else {
next_char(lexer, &lex, &cur);
}
}
goto END;
}
case '"': {
token->loc = lexer->pos;
} else if (ch == '"') {
// 字符串字面量
token->type = SCC_TOK_STRING_LITERAL;
scc_cstring_t output = scc_cstring_create();
scc_probe_stream_reset(stream);
if (scc_lex_parse_string(stream, &lexer->pos, &output) == true) {
scc_probe_stream_sync(stream);
token->value.cstr.data = scc_cstring_as_cstr(&output);
token->value.cstr.len = scc_cstring_len(&output);
} else {
LEX_ERROR("Unexpected string literal");
next_char(lexer, &lex, &cur); // 开头的 "
while (1) {
if (!peek_char(lexer, &cur)) {
LOG_ERROR("Unterminated string literal");
break;
}
if (cur.character == '"') {
next_char(lexer, &lex, &cur); // 闭引号
break;
}
if (cur.character == '\\') {
// 转义序列
next_char(lexer, &lex, &cur);
if (!peek_char(lexer, &cur))
break;
next_char(lexer, &lex, &cur);
} else {
next_char(lexer, &lex, &cur);
}
scc_ring_consume(lexer->stream_ref);
}
} else {
scc_sstream_char_t next = {0};
next_char(lexer, &lex, &cur);
peek_char(lexer, &next);
switch (ch) {
case '=':
switch (next.character) {
case '=':
token->type = SCC_TOK_EQ;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_ASSIGN;
break;
}
break;
case '+':
switch (next.character) {
case '+':
token->type = SCC_TOK_ADD_ADD;
next_char(lexer, &lex, &cur);
break;
case '=':
token->type = SCC_TOK_ASSIGN_ADD;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_ADD;
break;
}
break;
case '-':
switch (next.character) {
case '-':
token->type = SCC_TOK_SUB_SUB;
next_char(lexer, &lex, &cur);
break;
case '=':
token->type = SCC_TOK_ASSIGN_SUB;
next_char(lexer, &lex, &cur);
break;
case '>':
token->type = SCC_TOK_DEREF;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_SUB;
break;
}
break;
case '*':
switch (next.character) {
case '=':
token->type = SCC_TOK_ASSIGN_MUL;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_MUL;
break;
}
break;
case '%':
switch (next.character) {
case '=':
token->type = SCC_TOK_ASSIGN_MOD;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_MOD;
break;
}
break;
case '&':
switch (next.character) {
case '&':
token->type = SCC_TOK_AND_AND;
next_char(lexer, &lex, &cur);
break;
case '=':
token->type = SCC_TOK_ASSIGN_AND;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_AND;
break;
}
break;
case '|':
switch (next.character) {
case '|':
token->type = SCC_TOK_OR_OR;
next_char(lexer, &lex, &cur);
break;
case '=':
token->type = SCC_TOK_ASSIGN_OR;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_OR;
break;
}
break;
case '^':
switch (next.character) {
case '=':
token->type = SCC_TOK_ASSIGN_XOR;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_XOR;
break;
}
break;
case '<':
switch (next.character) {
case '=':
token->type = SCC_TOK_LE;
next_char(lexer, &lex, &cur);
break;
case '<': {
next_char(lexer, &lex, &cur);
if (peek_char(lexer, &next) && next.character == '=') {
token->type = SCC_TOK_ASSIGN_L_SH;
next_char(lexer, &lex, &cur);
} else {
token->type = SCC_TOK_L_SH;
}
break;
}
default:
token->type = SCC_TOK_LT;
break;
}
break;
case '>':
switch (next.character) {
case '=':
token->type = SCC_TOK_GE;
next_char(lexer, &lex, &cur);
break;
case '>': {
next_char(lexer, &lex, &cur);
if (peek_char(lexer, &next) && next.character == '=') {
token->type = SCC_TOK_ASSIGN_R_SH;
next_char(lexer, &lex, &cur);
} else {
token->type = SCC_TOK_R_SH;
}
break;
}
default:
token->type = SCC_TOK_GT;
break;
}
break;
case '~':
token->type = SCC_TOK_BIT_NOT;
break;
case '!':
switch (next.character) {
case '=':
token->type = SCC_TOK_NEQ;
next_char(lexer, &lex, &cur);
break;
default:
token->type = SCC_TOK_NOT;
break;
}
break;
/* clang-format off */
case '[': token->type = SCC_TOK_L_BRACKET; break;
case ']': token->type = SCC_TOK_R_BRACKET; break;
case '(': token->type = SCC_TOK_L_PAREN; break;
case ')': token->type = SCC_TOK_R_PAREN; break;
case '{': token->type = SCC_TOK_L_BRACE; break;
case '}': token->type = SCC_TOK_R_BRACE; break;
case ';': token->type = SCC_TOK_SEMICOLON; break;
case ',': token->type = SCC_TOK_COMMA; break;
case ':': token->type = SCC_TOK_COLON; break;
/* clang-format on */
case '.':
if (next.character == '.' && peek_char(lexer, &next) &&
next.character == '.') {
token->type = SCC_TOK_ELLIPSIS;
next_char(lexer, &lex, &cur);
next_char(lexer, &lex, &cur);
} else {
token->type = SCC_TOK_DOT;
}
break;
case '?':
token->type = SCC_TOK_COND;
break;
case '#':
token->type = SCC_TOK_SHARP;
break;
default:
token->type = SCC_TOK_UNKNOWN;
LEX_ERROR("unsupport char in sourse code `%c`:0x%x", ch, ch);
break;
}
goto END;
}
/* clang-format off */
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
/* clang-format on */
token->loc = lexer->pos;
token->type = SCC_TOK_INT_LITERAL;
usize output;
scc_probe_stream_reset(stream);
if (scc_lex_parse_number(stream, &lexer->pos, &output) == true) {
scc_probe_stream_sync(stream);
token->value.u = output;
} else {
LEX_ERROR("Unexpected number literal");
token->type = SCC_TOK_UNKNOWN;
}
goto END;
/* clang-format off */
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g':
case 'h': case 'i': case 'j': case 'k': case 'l': case 'm': case 'n':
case 'o': case 'p': case 'q': case 'r': case 's': case 't': case 'u':
case 'v': case 'w': case 'x': case 'y': case 'z':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N':
case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': case 'U':
case 'V': case 'W': case 'X': case 'Y': case 'Z': case '_':
/* clang-format on */
scc_cstring_t str = scc_cstring_create();
scc_probe_stream_reset(stream);
cbool ret = scc_lex_parse_identifier(stream, &lexer->pos, &str);
scc_probe_stream_sync(stream);
Assert(ret == true);
int res = keyword_cmp(scc_cstring_as_cstr(&str), scc_cstring_len(&str));
if (res == -1) {
token->value.cstr.data = (char *)scc_cstring_as_cstr(&str);
token->value.cstr.len = scc_cstring_len(&str);
type = SCC_TOK_IDENT;
} else {
scc_cstring_free(&str);
type = keywords[res].tok;
}
token->type = type;
goto END;
default:
LEX_ERROR("unsupport char in sourse code `%c`:0x%x", ch, ch);
break;
}
goto once_char;
triple_char:
scc_probe_stream_consume(stream);
scc_pos_next(&lexer->pos);
double_char:
scc_probe_stream_consume(stream);
scc_pos_next(&lexer->pos);
once_char:
scc_probe_stream_consume(stream);
scc_pos_next(&lexer->pos);
token->type = type;
END:
LEX_DEBUG("get token `%s` in %s:%d:%d", scc_get_tok_name(token->type),
token->loc.name, token->loc.line, token->loc.column);
// 设置token
scc_ring_consume(lexer->stream_ref);
token->type = token->type; // 上面已设
token->loc = start_loc;
token->lexeme = lex; // 转移所有权
LEX_DEBUG("get token `%s` (%s) at %s:%d:%d", scc_get_tok_name(token->type),
scc_cstring_as_cstr(&token->lexeme), token->loc.name,
token->loc.line, token->loc.col);
}
// scc_lexer_get_token maybe got invalid (with parser)
void scc_lexer_get_valid_token(scc_lexer_t *lexer, scc_lexer_tok_t *token) {
scc_tok_subtype_t type;
scc_tok_subtype_t subtype;
do {
scc_lexer_get_token(lexer, token);
type = scc_get_tok_subtype(token->type);
AssertFmt(type != SCC_TOK_SUBTYPE_INVALID,
subtype = scc_get_tok_subtype(token->type);
AssertFmt(subtype != SCC_TOK_SUBTYPE_INVALID,
"Invalid token: `%s` at %s:%d:%d",
scc_get_tok_name(token->type), token->loc.name,
token->loc.line, token->loc.col);
Assert(type != SCC_TOK_SUBTYPE_INVALID);
} while (type == SCC_TOK_SUBTYPE_EMPTYSPACE ||
type == SCC_TOK_SUBTYPE_COMMENT);
} while (subtype == SCC_TOK_SUBTYPE_EMPTYSPACE ||
subtype == SCC_TOK_SUBTYPE_COMMENT);
}

66
libs/lexer/src/main.c Normal file
View File

@@ -0,0 +1,66 @@
#include <lexer.h>
#include <lexer_log.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/// gcc -g ../lexer.c ../token.c test_lexer.c -o test_lexer
/*
tok_tConstant {
int have;
union {
char ch;
int i;
float f;
double d;
long long ll;
char* str;
};
};
*/
int g_num;
int g_num_arr[3];
int main(int argc, char *argv[]) {
// int num = 0;
if (argc == 3 && strcmp(argv[2], "--debug") == 0) {
log_set_level(NULL, LOG_LEVEL_ALL);
} else {
// FIXME it is a hack lexer_logger
log_set_level(&__scc_lexer_log, LOG_LEVEL_NOTSET);
log_set_level(NULL, LOG_LEVEL_INFO | LOG_LEVEL_WARN | LOG_LEVEL_ERROR |
LOG_LEVEL_FATAL);
}
const char *file_name = __FILE__;
if (argc == 2) {
file_name = argv[1];
}
scc_lexer_t lexer;
scc_sstream_t stream;
scc_sstream_init(&stream, file_name, 16);
scc_sstream_ring_t *ref = scc_sstream_ref_ring(&stream);
scc_lexer_init(&lexer, ref);
scc_lexer_tok_t token;
while (1) {
scc_lexer_get_valid_token(&lexer, &token);
if (token.type == SCC_TOK_EOF) {
break;
}
LOG_DEBUG("get token [%-8s] `%s` at %s:%d:%d",
scc_get_tok_name(token.type),
scc_cstring_as_cstr(&token.lexeme), token.loc.name,
token.loc.line, token.loc.col);
// LOG_DEBUG("%s", token.val.str);
// printf("line: %d, column: %d, type: %3d, typename: %s\n",
// lexer.line, lexer.index, token.type,
// scc_get_tok_name(token.type));
}
scc_sstream_drop_ring(ref);
scc_sstream_drop(&stream);
LOG_INFO("Lexer is Ok...");
return 0;
}

403
libs/lexer/tests/test_lexer.c Normal file
View File

@@ -0,0 +1,403 @@
// test_lexer.c
#include <lexer.h>
#include <string.h>
#include <utest/acutest.h>
// 辅助函数：释放 token 的 lexeme
static void free_token(scc_lexer_tok_t *tok) { scc_cstring_free(&tok->lexeme); }
// 单 token 测试宏（检查类型）
#define TEST_TOKEN(input, expected_type) \
do { \
scc_lexer_t lexer; \
scc_lexer_tok_t token; \
scc_sstream_t stream; \
scc_sstream_init_by_buffer(&stream, input, strlen(input), 0, 16); \
scc_sstream_ring_t *ref = scc_sstream_ref_ring(&stream); \
scc_lexer_init(&lexer, ref); \
scc_lexer_get_token(&lexer, &token); \
\
TEST_CHECK(token.type == expected_type); \
TEST_MSG("Input: '%s'", input); \
TEST_MSG("Expected: %s", scc_get_tok_name(expected_type)); \
TEST_MSG("Got: %s", scc_get_tok_name(token.type)); \
\
free_token(&token); \
scc_sstream_drop_ring(ref); \
scc_sstream_drop(&stream); \
} while (0)
// 多 token 序列测试宏（接受类型数组）
#define TEST_SEQUENCE(input, ...) \
do { \
scc_lexer_t lexer; \
scc_lexer_tok_t token; \
scc_sstream_t stream; \
scc_sstream_init_by_buffer(&stream, input, strlen(input), 0, 16); \
scc_sstream_ring_t *ref = scc_sstream_ref_ring(&stream); \
scc_lexer_init(&lexer, ref); \
\
scc_tok_type_t expected[] = {__VA_ARGS__}; \
size_t count = sizeof(expected) / sizeof(expected[0]); \
for (size_t i = 0; i < count; i++) { \
scc_lexer_get_token(&lexer, &token); \
TEST_CHECK(token.type == expected[i]); \
TEST_MSG("Token %zu: input '%s'", i, input); \
TEST_MSG("Expected: %s", scc_get_tok_name(expected[i])); \
TEST_MSG("Got: %s", scc_get_tok_name(token.type)); \
free_token(&token); \
} \
\
scc_sstream_drop_ring(ref); \
scc_sstream_drop(&stream); \
} while (0)
// ============================ 测试用例 ============================
void test_operators() {
TEST_CASE("Arithmetic operators");
TEST_TOKEN("+", SCC_TOK_ADD);
TEST_TOKEN("++", SCC_TOK_ADD_ADD);
TEST_TOKEN("+=", SCC_TOK_ASSIGN_ADD);
TEST_TOKEN("-", SCC_TOK_SUB);
TEST_TOKEN("--", SCC_TOK_SUB_SUB);
TEST_TOKEN("-=", SCC_TOK_ASSIGN_SUB);
TEST_TOKEN("*", SCC_TOK_MUL);
TEST_TOKEN("*=", SCC_TOK_ASSIGN_MUL);
TEST_TOKEN("/", SCC_TOK_DIV);
TEST_TOKEN("/=", SCC_TOK_ASSIGN_DIV);
TEST_TOKEN("%", SCC_TOK_MOD);
TEST_TOKEN("%=", SCC_TOK_ASSIGN_MOD);
TEST_CASE("Bitwise operators");
TEST_TOKEN("&", SCC_TOK_AND);
TEST_TOKEN("&&", SCC_TOK_AND_AND);
TEST_TOKEN("&=", SCC_TOK_ASSIGN_AND);
TEST_TOKEN("|", SCC_TOK_OR);
TEST_TOKEN("||", SCC_TOK_OR_OR);
TEST_TOKEN("|=", SCC_TOK_ASSIGN_OR);
TEST_TOKEN("^", SCC_TOK_XOR);
TEST_TOKEN("^=", SCC_TOK_ASSIGN_XOR);
TEST_TOKEN("~", SCC_TOK_BIT_NOT);
TEST_TOKEN("<<", SCC_TOK_L_SH);
TEST_TOKEN("<<=", SCC_TOK_ASSIGN_L_SH);
TEST_TOKEN(">>", SCC_TOK_R_SH);
TEST_TOKEN(">>=", SCC_TOK_ASSIGN_R_SH);
TEST_CASE("Comparison operators");
TEST_TOKEN("==", SCC_TOK_EQ);
TEST_TOKEN("!=", SCC_TOK_NEQ);
TEST_TOKEN("<", SCC_TOK_LT);
TEST_TOKEN("<=", SCC_TOK_LE);
TEST_TOKEN(">", SCC_TOK_GT);
TEST_TOKEN(">=", SCC_TOK_GE);
TEST_CASE("Special symbols");
TEST_TOKEN("(", SCC_TOK_L_PAREN);
TEST_TOKEN(")", SCC_TOK_R_PAREN);
TEST_TOKEN("[", SCC_TOK_L_BRACKET);
TEST_TOKEN("]", SCC_TOK_R_BRACKET);
TEST_TOKEN("{", SCC_TOK_L_BRACE);
TEST_TOKEN("}", SCC_TOK_R_BRACE);
TEST_TOKEN(";", SCC_TOK_SEMICOLON);
TEST_TOKEN(",", SCC_TOK_COMMA);
TEST_TOKEN(":", SCC_TOK_COLON);
TEST_TOKEN(".", SCC_TOK_DOT);
TEST_TOKEN("...", SCC_TOK_ELLIPSIS);
TEST_TOKEN("->", SCC_TOK_DEREF);
TEST_TOKEN("?", SCC_TOK_COND);
}
void test_keywords() {
TEST_CASE("C89 keywords");
TEST_TOKEN("while", SCC_TOK_WHILE);
TEST_TOKEN("sizeof", SCC_TOK_SIZEOF);
TEST_TOKEN("if", SCC_TOK_IF);
TEST_TOKEN("else", SCC_TOK_ELSE);
TEST_TOKEN("for", SCC_TOK_FOR);
TEST_TOKEN("do", SCC_TOK_DO);
TEST_TOKEN("switch", SCC_TOK_SWITCH);
TEST_TOKEN("case", SCC_TOK_CASE);
TEST_TOKEN("default", SCC_TOK_DEFAULT);
TEST_TOKEN("break", SCC_TOK_BREAK);
TEST_TOKEN("continue", SCC_TOK_CONTINUE);
TEST_TOKEN("return", SCC_TOK_RETURN);
TEST_TOKEN("goto", SCC_TOK_GOTO);
TEST_TOKEN("auto", SCC_TOK_AUTO);
TEST_TOKEN("register", SCC_TOK_REGISTER);
TEST_TOKEN("static", SCC_TOK_STATIC);
TEST_TOKEN("extern", SCC_TOK_EXTERN);
TEST_TOKEN("typedef", SCC_TOK_TYPEDEF);
TEST_TOKEN("const", SCC_TOK_CONST);
TEST_TOKEN("volatile", SCC_TOK_VOLATILE);
TEST_TOKEN("signed", SCC_TOK_SIGNED);
TEST_TOKEN("unsigned", SCC_TOK_UNSIGNED);
TEST_TOKEN("short", SCC_TOK_SHORT);
TEST_TOKEN("long", SCC_TOK_LONG);
TEST_TOKEN("int", SCC_TOK_INT);
TEST_TOKEN("char", SCC_TOK_CHAR);
TEST_TOKEN("float", SCC_TOK_FLOAT);
TEST_TOKEN("double", SCC_TOK_DOUBLE);
TEST_TOKEN("void", SCC_TOK_VOID);
TEST_TOKEN("struct", SCC_TOK_STRUCT);
TEST_TOKEN("union", SCC_TOK_UNION);
TEST_TOKEN("enum", SCC_TOK_ENUM);
TEST_CASE("C99 keywords");
TEST_TOKEN("inline", SCC_TOK_INLINE);
TEST_TOKEN("restrict", SCC_TOK_RESTRICT);
// _Bool, _Complex, _Imaginary 可根据需要添加
TEST_CASE("SCC extensions (if enabled)");
TEST_TOKEN("asm", SCC_TOK_ASM);
TEST_TOKEN("atomic", SCC_TOK_ATOMIC);
TEST_TOKEN("bool", SCC_TOK_BOOL);
TEST_TOKEN("complex", SCC_TOK_COMPLEX);
}
void test_literals() {
TEST_CASE("Integer literals - decimal");
TEST_TOKEN("0", SCC_TOK_INT_LITERAL);
TEST_TOKEN("123", SCC_TOK_INT_LITERAL);
TEST_TOKEN("2147483647", SCC_TOK_INT_LITERAL);
TEST_TOKEN("4294967295", SCC_TOK_INT_LITERAL);
TEST_CASE("Integer literals - hexadecimal");
TEST_TOKEN("0x0", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0x1A3F", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0XABCDEF", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0x123abc", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0XFF", SCC_TOK_INT_LITERAL);
TEST_CASE("Integer literals - octal");
TEST_TOKEN("0123", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0777", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0", SCC_TOK_INT_LITERAL); // 0 既是十进制也是八进制
TEST_CASE("Integer literals - binary (C23 extension)");
TEST_TOKEN("0b1010", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0B1100", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0b0", SCC_TOK_INT_LITERAL);
TEST_CASE("Integer literals with suffixes");
TEST_TOKEN("123U", SCC_TOK_INT_LITERAL);
TEST_TOKEN("456L", SCC_TOK_INT_LITERAL);
TEST_TOKEN("789UL", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0x1FFLL", SCC_TOK_INT_LITERAL);
TEST_TOKEN("0b1010ULL", SCC_TOK_INT_LITERAL);
TEST_CASE("Floating literals - decimal");
TEST_TOKEN("0.0", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("3.14", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN(".5", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("0.", SCC_TOK_FLOAT_LITERAL);
TEST_CASE("Floating literals - scientific");
TEST_TOKEN("1e10", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("1E-5", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("2.5e+3", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN(".1e2", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("1.e3", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("123.456e-7", SCC_TOK_FLOAT_LITERAL);
TEST_CASE("Floating literals - hexadecimal (C99)");
TEST_TOKEN("0x1.2p3", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("0x1p-2", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("0x0.1p10", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("0X1.2P3", SCC_TOK_FLOAT_LITERAL);
TEST_CASE("Floating literals with suffixes");
TEST_TOKEN("1.0f", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("2.0F", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("3.0l", SCC_TOK_FLOAT_LITERAL);
TEST_TOKEN("4.0L", SCC_TOK_FLOAT_LITERAL);
TEST_CASE("Character literals - simple");
TEST_TOKEN("'a'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'0'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("' '", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\t'", SCC_TOK_CHAR_LITERAL); // 制表符在单引号内
TEST_CASE("Character literals - escape sequences");
TEST_TOKEN("'\\n'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\t'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\\\'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\''", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\\"'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\?'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\0'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\123'", SCC_TOK_CHAR_LITERAL); // 八进制
TEST_TOKEN("'\\xAB'", SCC_TOK_CHAR_LITERAL); // 十六进制
TEST_CASE("Character literals - multi-byte (implementation defined)");
TEST_TOKEN("'ab'", SCC_TOK_CHAR_LITERAL);
TEST_TOKEN("'\\x41\\x42'", SCC_TOK_CHAR_LITERAL); // 多个转义
TEST_CASE("String literals - basic");
TEST_TOKEN("\"hello\"", SCC_TOK_STRING_LITERAL);
TEST_TOKEN("\"\"", SCC_TOK_STRING_LITERAL);
TEST_TOKEN("\"a b c\"", SCC_TOK_STRING_LITERAL);
TEST_CASE("String literals - escape sequences");
TEST_TOKEN("\"a\\nb\\tc\"", SCC_TOK_STRING_LITERAL);
TEST_TOKEN("\"\\\\ \\\" \\' \\?\"", SCC_TOK_STRING_LITERAL);
TEST_TOKEN("\"\\123\\xAB\"", SCC_TOK_STRING_LITERAL);
TEST_CASE("String literals - wide and UTF-8 prefixes (C11)");
TEST_TOKEN("L\"wide\"", SCC_TOK_STRING_LITERAL);
TEST_TOKEN("u\"utf16\"", SCC_TOK_STRING_LITERAL);
TEST_TOKEN("U\"utf32\"", SCC_TOK_STRING_LITERAL);
TEST_TOKEN("u8\"utf8\"", SCC_TOK_STRING_LITERAL);
}
void test_whitespace() {
TEST_CASE("Whitespace characters");
TEST_TOKEN(" ", SCC_TOK_BLANK);
TEST_TOKEN("\t", SCC_TOK_BLANK);
TEST_TOKEN("\v", SCC_TOK_BLANK);
TEST_TOKEN("\f", SCC_TOK_BLANK);
TEST_TOKEN(" \t\v\f", SCC_TOK_BLANK); // 连续空白应为一个 token
}
void test_newlines() {
TEST_CASE("Newline characters");
TEST_TOKEN("\n", SCC_TOK_ENDLINE);
TEST_TOKEN("\r", SCC_TOK_ENDLINE);
TEST_TOKEN("\r\n", SCC_TOK_ENDLINE); // 应视为单个换行符
}
void test_comments() {
TEST_CASE("Line comments");
TEST_TOKEN("// single line comment", SCC_TOK_LINE_COMMENT);
TEST_TOKEN("// comment with // inside", SCC_TOK_LINE_COMMENT);
TEST_TOKEN("// comment at end", SCC_TOK_LINE_COMMENT);
TEST_CASE("Block comments");
TEST_TOKEN("/* simple */", SCC_TOK_BLOCK_COMMENT);
TEST_TOKEN("/* multi\nline */", SCC_TOK_BLOCK_COMMENT);
TEST_TOKEN("/**/", SCC_TOK_BLOCK_COMMENT); // 空注释
TEST_TOKEN("/* with * inside */", SCC_TOK_BLOCK_COMMENT);
TEST_TOKEN("/* nested /* not allowed in C */",
SCC_TOK_BLOCK_COMMENT); // 词法上不会嵌套
}
void test_identifiers() {
TEST_CASE("Valid identifiers");
TEST_TOKEN("foo", SCC_TOK_IDENT);
TEST_TOKEN("_foo", SCC_TOK_IDENT);
TEST_TOKEN("foo123", SCC_TOK_IDENT);
TEST_TOKEN("foo_bar", SCC_TOK_IDENT);
TEST_TOKEN("FOO", SCC_TOK_IDENT);
TEST_TOKEN("_", SCC_TOK_IDENT);
TEST_TOKEN("__LINE__", SCC_TOK_IDENT); // 预处理宏名也是标识符
// 超长标识符（假设缓冲区足够）
char long_id[1024];
memset(long_id, 'a', sizeof(long_id) - 1);
long_id[sizeof(long_id) - 1] = '\0';
TEST_TOKEN(long_id, SCC_TOK_IDENT);
}
void test_preprocessor() {
TEST_CASE("Preprocessor directives - just the # token");
TEST_TOKEN("#", SCC_TOK_SHARP);
TEST_TOKEN("##", SCC_TOK_SHARP); // 第一个 # 是 token，第二个 # 将是下一个
// token（在序列测试中验证）
// 多 token 序列测试 #include 等
TEST_SEQUENCE("#include <stdio.h>", SCC_TOK_SHARP, SCC_TOK_IDENT,
SCC_TOK_BLANK, SCC_TOK_LT, SCC_TOK_IDENT, SCC_TOK_DOT,
SCC_TOK_IDENT, SCC_TOK_GT);
TEST_SEQUENCE("#define FOO 123", SCC_TOK_SHARP, SCC_TOK_IDENT,
SCC_TOK_BLANK, SCC_TOK_IDENT, SCC_TOK_BLANK,
SCC_TOK_INT_LITERAL);
}
void test_edge_cases() {
TEST_CASE("Invalid characters");
TEST_TOKEN("@", SCC_TOK_UNKNOWN);
TEST_TOKEN("`", SCC_TOK_UNKNOWN);
TEST_TOKEN("$", SCC_TOK_UNKNOWN); // 在 C 中不是标识符字符
TEST_CASE("Empty input");
TEST_TOKEN("", SCC_TOK_EOF); // 立即 EOF
TEST_CASE("Only whitespace");
TEST_TOKEN(" \t", SCC_TOK_BLANK);
// 之后应该为 EOF，但我们的单 token 测试只取第一个 token
TEST_CASE("Numbers followed by letters (no suffix)");
// 词法上应拆分为数字和标识符
TEST_SEQUENCE("123abc", SCC_TOK_INT_LITERAL, SCC_TOK_IDENT);
TEST_SEQUENCE("0x123xyz", SCC_TOK_INT_LITERAL, SCC_TOK_IDENT);
}
void test_sequences() {
TEST_CASE("Simple expression");
TEST_SEQUENCE("a + b * c", SCC_TOK_IDENT, SCC_TOK_BLANK, SCC_TOK_ADD,
SCC_TOK_BLANK, SCC_TOK_IDENT, SCC_TOK_BLANK, SCC_TOK_MUL,
SCC_TOK_BLANK, SCC_TOK_IDENT);
TEST_CASE("Function call");
TEST_SEQUENCE("func(1, 2);", SCC_TOK_IDENT, SCC_TOK_L_PAREN,
SCC_TOK_INT_LITERAL, SCC_TOK_COMMA, SCC_TOK_BLANK,
SCC_TOK_INT_LITERAL, SCC_TOK_R_PAREN, SCC_TOK_SEMICOLON);
TEST_CASE("Multi-character operators");
TEST_SEQUENCE(">>=", SCC_TOK_ASSIGN_R_SH);
TEST_SEQUENCE("<<=", SCC_TOK_ASSIGN_L_SH);
TEST_SEQUENCE("...", SCC_TOK_ELLIPSIS);
TEST_SEQUENCE("->", SCC_TOK_DEREF);
TEST_SEQUENCE("##", SCC_TOK_SHARP, SCC_TOK_SHARP); // 两个预处理记号
TEST_CASE("Comments and whitespace interleaved");
TEST_SEQUENCE("/* comment */ a // line comment\n b", SCC_TOK_BLOCK_COMMENT,
SCC_TOK_BLANK, SCC_TOK_IDENT, SCC_TOK_BLANK,
SCC_TOK_LINE_COMMENT, SCC_TOK_ENDLINE, SCC_TOK_BLANK,
SCC_TOK_IDENT);
TEST_CASE("String literals with escapes");
TEST_SEQUENCE("\"hello\\nworld\"", SCC_TOK_STRING_LITERAL);
TEST_SEQUENCE(
"L\"wide\"",
SCC_TOK_STRING_LITERAL); // 前缀作为标识符？不，整个是字符串字面量
TEST_CASE("Character literals with escapes");
TEST_SEQUENCE("'\\x41'", SCC_TOK_CHAR_LITERAL);
TEST_SEQUENCE("'\\123'", SCC_TOK_CHAR_LITERAL);
}
void test_error_recovery() {
// 测试未闭合的字符字面量：词法分析器可能继续直到遇到换行或 EOF
// 这里假设它会产生一个 SCC_TOK_CHAR_LITERAL 但包含到结束
// 但标准 C 中未闭合是错误，我们可能返回 UNKNOWN
TEST_CASE("Unterminated character literal");
TEST_TOKEN("'a", SCC_TOK_UNKNOWN); // 取决于实现，可能为 CHAR_LITERAL
// 更可靠的测试：序列中下一个 token 是什么
TEST_SEQUENCE("'a b", SCC_TOK_UNKNOWN,
SCC_TOK_IDENT); // 假设第一个 token 是错误
TEST_CASE("Unterminated string literal");
TEST_TOKEN("\"hello", SCC_TOK_UNKNOWN); // 同样
TEST_CASE("Unterminated block comment");
TEST_SEQUENCE("/* comment",
SCC_TOK_BLOCK_COMMENT); // 直到 EOF，可能仍为注释
}
// ============================ 主测试列表 ============================
TEST_LIST = {
{"operators", test_operators},
{"keywords", test_keywords},
{"literals", test_literals},
{"whitespace", test_whitespace},
{"newlines", test_newlines},
{"comments", test_comments},
{"identifiers", test_identifiers},
{"preprocessor", test_preprocessor},
{"edge_cases", test_edge_cases},
{"sequences", test_sequences},
{"error_recovery", test_error_recovery},
{NULL, NULL},
};

170
libs/lexer/tests/test_parse.c
View File

@@ -1,170 +0,0 @@
// test_lexer.c
#include <lexer.h>
#include <string.h>
#include <utest/acutest.h>
// 测试辅助函数
static inline void test_lexer_string(const char *input,
scc_tok_type_t expected_type) {
scc_lexer_t lexer;
scc_lexer_tok_t token;
scc_mem_probe_stream_t stream;
scc_lexer_init(&lexer, scc_mem_probe_stream_init(&stream, input,
strlen(input), false));
scc_lexer_get_token(&lexer, &token);
TEST_CHECK(token.type == expected_type);
TEST_MSG("Expected: %s", scc_get_tok_name(expected_type));
TEST_MSG("Got: %s", scc_get_tok_name(token.type));
}
// 基础运算符测试
void test_operators() {
TEST_CASE("Arithmetic operators");
{
test_lexer_string("+", SCC_TOK_ADD);
test_lexer_string("++", SCC_TOK_ADD_ADD);
test_lexer_string("+=", SCC_TOK_ASSIGN_ADD);
test_lexer_string("-", SCC_TOK_SUB);
test_lexer_string("--", SCC_TOK_SUB_SUB);
test_lexer_string("-=", SCC_TOK_ASSIGN_SUB);
test_lexer_string("*", SCC_TOK_MUL);
test_lexer_string("*=", SCC_TOK_ASSIGN_MUL);
test_lexer_string("/", SCC_TOK_DIV);
test_lexer_string("/=", SCC_TOK_ASSIGN_DIV);
test_lexer_string("%", SCC_TOK_MOD);
test_lexer_string("%=", SCC_TOK_ASSIGN_MOD);
}
TEST_CASE("Bitwise operators");
{
test_lexer_string("&", SCC_TOK_AND);
test_lexer_string("&&", SCC_TOK_AND_AND);
test_lexer_string("&=", SCC_TOK_ASSIGN_AND);
test_lexer_string("|", SCC_TOK_OR);
test_lexer_string("||", SCC_TOK_OR_OR);
test_lexer_string("|=", SCC_TOK_ASSIGN_OR);
test_lexer_string("^", SCC_TOK_XOR);
test_lexer_string("^=", SCC_TOK_ASSIGN_XOR);
test_lexer_string("~", SCC_TOK_BIT_NOT);
test_lexer_string("<<", SCC_TOK_L_SH);
test_lexer_string("<<=", SCC_TOK_ASSIGN_L_SH);
test_lexer_string(">>", SCC_TOK_R_SH);
test_lexer_string(">>=", SCC_TOK_ASSIGN_R_SH);
}
TEST_CASE("Comparison operators");
{
test_lexer_string("==", SCC_TOK_EQ);
test_lexer_string("!=", SCC_TOK_NEQ);
test_lexer_string("<", SCC_TOK_LT);
test_lexer_string("<=", SCC_TOK_LE);
test_lexer_string(">", SCC_TOK_GT);
test_lexer_string(">=", SCC_TOK_GE);
}
TEST_CASE("Special symbols");
{
test_lexer_string("(", SCC_TOK_L_PAREN);
test_lexer_string(")", SCC_TOK_R_PAREN);
test_lexer_string("[", SCC_TOK_L_BRACKET);
test_lexer_string("]", SCC_TOK_R_BRACKET);
test_lexer_string("{", SCC_TOK_L_BRACE);
test_lexer_string("}", SCC_TOK_R_BRACE);
test_lexer_string(";", SCC_TOK_SEMICOLON);
test_lexer_string(",", SCC_TOK_COMMA);
test_lexer_string(":", SCC_TOK_COLON);
test_lexer_string(".", SCC_TOK_DOT);
test_lexer_string("...", SCC_TOK_ELLIPSIS);
test_lexer_string("->", SCC_TOK_DEREF);
test_lexer_string("?", SCC_TOK_COND);
}
}
// 关键字测试
void test_keywords() {
TEST_CASE("C89 keywords");
test_lexer_string("while", SCC_TOK_WHILE);
test_lexer_string("sizeof", SCC_TOK_SIZEOF);
TEST_CASE("C99 keywords");
test_lexer_string("restrict", SCC_TOK_RESTRICT);
// test_lexer_string("_Bool", SCC_TOK_INT); // 需确认你的类型定义
}
// 字面量测试
void test_literals() {
TEST_CASE("Integer literals");
{
// 十进制
test_lexer_string("0", SCC_TOK_INT_LITERAL);
test_lexer_string("123", SCC_TOK_INT_LITERAL);
test_lexer_string("2147483647", SCC_TOK_INT_LITERAL);
// 十六进制
test_lexer_string("0x0", SCC_TOK_INT_LITERAL);
test_lexer_string("0x1A3F", SCC_TOK_INT_LITERAL);
test_lexer_string("0XABCDEF", SCC_TOK_INT_LITERAL);
// 八进制
test_lexer_string("0123", SCC_TOK_INT_LITERAL);
test_lexer_string("0777", SCC_TOK_INT_LITERAL);
// 边界值测试
test_lexer_string("2147483647", SCC_TOK_INT_LITERAL); // INT_MAX
test_lexer_string("4294967295", SCC_TOK_INT_LITERAL); // UINT_MAX
}
TEST_CASE("Character literals");
{
test_lexer_string("'a'", SCC_TOK_CHAR_LITERAL);
test_lexer_string("'\\n'", SCC_TOK_CHAR_LITERAL);
test_lexer_string("'\\t'", SCC_TOK_CHAR_LITERAL);
test_lexer_string("'\\\\'", SCC_TOK_CHAR_LITERAL);
test_lexer_string("'\\0'", SCC_TOK_CHAR_LITERAL);
}
TEST_CASE("String literals");
{
test_lexer_string("\"hello\"", SCC_TOK_STRING_LITERAL);
test_lexer_string("\"multi-line\\nstring\"", SCC_TOK_STRING_LITERAL);
test_lexer_string("\"escape\\\"quote\"", SCC_TOK_STRING_LITERAL);
}
// TEST_CASE("Floating literals");
// test_lexer_string("3.14e-5", SCC_TOK_FLOAT_LITERAL);
}
// 边界测试
void test_edge_cases() {
// TEST_CASE("Long identifiers");
// char long_id[LEXER_MAX_ SCC_TOK_SIZE+2] = {0};
// memset(long_id, 'a', LEXER_MAX_ SCC_TOK_SIZE+1);
// test_lexer_string(long_id, SCC_TOK_IDENT);
// TEST_CASE("Buffer boundary");
// char boundary[LEXER_BUFFER_SIZE*2] = {0};
// memset(boundary, '+', LEXER_BUFFER_SIZE*2-1);
// test_lexer_string(boundary, SCC_TOK_ADD);
}
// 错误处理测试
// void test_error_handling() {
// TEST_CASE("Invalid characters");
// cc_lexer_t lexer;
// tok_t token;
// init_lexer(&lexer, "test.c", NULL, test_read);
// get_valid_token(&lexer, &token);
// TEST_CHECK(token.type == SCC_TOK_EOF); // 应触发错误处理
// }
// 测试列表
TEST_LIST = {{"operators", test_operators},
{"keywords", test_keywords},
{"literals", test_literals},
{"edge_cases", test_edge_cases},
// {"error_handling", test_error_handling},
{NULL, NULL}};

93
libs/lexer/tests/test_run.c
View File

@@ -1,93 +0,0 @@
#include <lexer.h>
#include <lexer_log.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/// gcc -g ../lexer.c ../token.c test_lexer.c -o test_lexer
/*
tok_tConstant {
int have;
union {
char ch;
int i;
float f;
double d;
long long ll;
char* str;
};
};
*/
int g_num;
int g_num_arr[3];
int main(int argc, char *argv[]) {
// int num = 0;
if (argc == 3 && strcmp(argv[2], "--debug") == 0) {
log_set_level(NULL, LOG_LEVEL_ALL);
} else {
// FIXME it is a hack lexer_logger
log_set_level(&__scc_lexer_log, LOG_LEVEL_NOTSET);
log_set_level(NULL, LOG_LEVEL_INFO | LOG_LEVEL_WARN | LOG_LEVEL_ERROR |
LOG_LEVEL_FATAL);
}
const char *file_name = __FILE__;
if (argc == 2) {
file_name = argv[1];
}
FILE *fp = fopen(file_name, "rb");
if (fp == NULL) {
perror("open file failed");
return 1;
}
if (fseek(fp, 0, SEEK_END) != 0) {
perror("fseek failed");
return 1;
}
usize fsize = ftell(fp);
LOG_INFO("file size: %zu", fsize);
if (fseek(fp, 0, SEEK_SET)) {
perror("fseek failed");
return 1;
}
char *buffer = (char *)malloc(fsize);
usize read_ret = fread(buffer, 1, fsize, fp);
fclose(fp);
if (read_ret != fsize) {
LOG_FATAL("fread failed read_ret %u != fsize %u", read_ret, fsize);
free(buffer);
return 1;
}
scc_lexer_t lexer;
scc_mem_probe_stream_t mem_stream = {0};
scc_probe_stream_t *stream =
scc_mem_probe_stream_init(&mem_stream, buffer, fsize, false);
Assert(stream != null);
scc_cstring_clear(&stream->name);
scc_cstring_append_cstr(&stream->name, file_name, strlen(file_name));
scc_lexer_init(&lexer, stream);
scc_lexer_tok_t tok;
while (1) {
scc_lexer_get_valid_token(&lexer, &tok);
if (tok.type == SCC_TOK_EOF) {
break;
}
LOG_DEBUG("token `%s` at %s:%u:%u", scc_get_tok_name(tok.type),
scc_cstring_as_cstr(&tok.loc.name), tok.loc.line,
tok.loc.col);
Assert(tok.loc.offset <= fsize);
// LOG_DEBUG("%s", tok.val.str);
// printf("line: %d, column: %d, type: %3d, typename: %s\n",
// lexer.line, lexer.index, tok.type, scc_get_tok_name(tok.type));
}
free(buffer);
LOG_INFO("Lexer is Ok...");
return 0;
}