From 93a8c2c265cec8db0c599d2d46621c294f571e7d Mon Sep 17 00:00:00 2001
From: andy <1414772332@qq.com>
Date: Tue, 29 Oct 2024 00:02:03 +0800
Subject: [PATCH] =?UTF-8?q?=E6=B7=BB=E5=8A=A0=20c=E8=AF=AD=E8=A8=80?=
 =?UTF-8?q?=E8=AF=8D=E6=B3=95=E5=88=86=E6=9E=90=20=E5=88=9D=E6=AD=A5?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 make.py         |   3 +-
 soft/clexical.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 115 insertions(+), 1 deletion(-)
 create mode 100644 soft/clexical.c

diff --git a/make.py b/make.py
index 73d79ed..66ba86c 100644
--- a/make.py
+++ b/make.py
@@ -152,7 +152,8 @@ def build_object(src:list[str]):
         print(f"{i} 没有更新依赖关系")
     elif(file_type in ['s','S','asm','ASM']):
       if(check_rebuild(dst,[i])):
-        cmd=f"{AS} -c {i} -o {dst} {flags}"
+        # cmd=f"{AS} -c {i} -o {dst} {flags}"
+        pass
       else:
         print(f"{i} 没有更新依赖关系")
     if(len(cmd)>0):
diff --git a/soft/clexical.c b/soft/clexical.c
new file mode 100644
index 0000000..a6efc2a
--- /dev/null
+++ b/soft/clexical.c
@@ -0,0 +1,113 @@
+#include "stdio.h"
+#include "regex.h"
+#include "stdlib.h"
+#include "stdint.h"
+#include "exception.h"
+#include "mythread.h"
+#include "unistd.h"
+#include "debug.h"
+
+
+// c语言词法分析
+
+
+
+
+const char *g_keyword_table[]={
+    "if","break","while","switch","case","do",
+    "char","int","void",
+};
+
+typedef enum {
+    TOKEN_IF = 256,
+    TOKEN_BREAK,
+    TOKEN_WHILE,
+    TOKEN_SWITCH,
+    TOKEN_CASE,
+    TOKEN_DO,
+    TOKEN_CHAR,
+    TOKEN_INT,
+    TOKEN_VOID,
+    TOKEN_NAME,
+}token_def;
+
+#define TOKEN_BUFF_MAX_LEN      128
+
+typedef struct{
+    char buff[TOKEN_BUFF_MAX_LEN];
+    int used;
+    int line;
+    int pos;
+    int token;
+}token_def;
+
+typedef struct{
+    int current_c;
+    int current_line;
+    int current_line_pos;
+    token_def token_buff;
+    char *input_text;
+    int input_len;
+    int input_pos;
+}lex_def;
+
+
+// 获取下一个字符 返回0成功
+int lex_get_next(lex_def *lex)
+{
+    token_def *t=&lex->token_buff;
+    if(lex->input_pos>=lex->input_len){
+        return -1;
+    }
+    lex->current_c=lex->input_text[lex->input_pos];
+    lex->input_pos++;
+    lex->current_line_pos++;
+    return 0;
+}
+
+
+// 保存当前字符
+int lex_save_char(lex_def *lex){
+    token_def *t=&lex->token_buff;
+    if(t->used>=TOKEN_BUFF_MAX_LEN){
+        return -1;
+    }
+    t->buff[t->used]=lex->current_c;
+    t->used++;
+    t->line=lex->current_line;
+    t->pos=lex->current_line_pos;
+    return 0;
+}
+
+
+
+
+int lex_analysis(const char *text,int len){
+    lex_def lex={0};
+    lex.input_text=text;
+    lex.input_len=len;
+    lex_get_next(&lex);
+    while(1){
+        switch (lex.current_c)
+        {
+        case '\r':{
+            lex_get_next(&lex);
+            if(lex.current_c=='\n'){
+                lex_get_next(&lex);
+            }
+            lex.current_line++;
+            lex.current_line_pos=0;
+            break;
+        }
+        case ' ':case '\t':case '\v':case '\f':{
+            lex_get_next(&lex);
+            lex.current_line_pos++;
+        }
+        default:
+            break;
+        }
+    }
+}
+
+
+