刪除C語言程式中所有的備註陳述式，代碼實現，語言程式注釋

刪除C語言程式中所有的備註陳述式，代碼實現，語言程式注釋

原文連結：http://lixing123.com/archives/310

學習《C程式設計語言》到第1章最後，有一道題目：

編寫一個刪除C語言程式中所有的備註陳述式。要正確處理帶引號的字串與字元常量。在C語言中,注釋不允許嵌套。Exercise 1-23. Write a program to remove all comments from a C program. Don't forget to handle quoted strings and character constants properly. C comments don't nest.

剛開始，我用一種brute-force的方式，對每個字元進行遍曆，然後進行判斷，有沒有進入注釋。

這樣做有一個非常麻煩的問題：只有連續檢測到“//”或者"/*"時，才確定進入了注釋狀態；如果我們只檢測到1個"/"，後面就是其它字串的話，還得將這個單獨的"/"列印出來。

而且有許多的分支狀態，如果用if/else的話，會難以理解，並容易出錯。

在網上搜了一下，發現有一種解法非常好：狀態機器。在各種狀態之間跳轉，邏輯清晰，不易出錯，出錯了也容易調試。

下面把代碼貼出來：

#include <stdio.h>int state;int c1,c2;void change_state(int c);int main(int argc, const char * argv[]) {    int c;    state = 0;    c1 = 0;    c2 = 0;    while ((c=getchar())!=EOF) {        c1 = c2;        c2 = c;        change_state(c);    }    if (/* DISABLES CODE */ (0)==1) {        printf("just test://abcd");        printf("just test:/*hello*/");    }}/*狀態機器函數*/void change_state(int c){    if (state==0) {//普通狀態        if (c=='/') {            state = 1;        }else if (c=='"'){            state = 5;            putchar(c);        }else if (c=='\''){            state = 6;            putchar(c);        }        else{            state = 0;            putchar(c);        }    }else if (state==1) {//檢測到1個'/'        if (c=='/') {            state = 2;        }else if (c=='*'){            state = 3;        }else{            state = 0;            putchar(c1);            putchar(c);        }    }else if (state==2) {// "//"注釋狀態        if (c=='\n') {            state = 0;            putchar(c);        }else{            state = 2;        }    }else if (state==3) {// "/*"注釋狀態        if (c=='*') {            state = 4;        }else{            state = 3;        }    }else if (state==4) {        if (c=='/') {            state = 0;        }else{            state = 3;        }    }else if (state==5){//在"字串裡        if (c=='"') {            state = 0;            putchar(c);        }else if(c=='\\'){            state = 7;            putchar(c);        }else{            state = 5;            putchar(c);        }    }else if (state==6){//在'字元裡        if (c=='\'') {            state = 0;            putchar(c);        }else if(c=='\\'){            state = 8;            putchar(c);        }else{            state = 6;            putchar(c);        }    }else if (state==7){//在"字串裡的"\"        state = 5;        putchar(c);    }else if (state==8){//在'字串裡的"\"        state = 6;        putchar(c);    }}

以本段代碼作為輸入，結果如下：

#include <stdio.h>int state;int c1,c2;void change_state(int c);int main(int argc, const char * argv[]) {    int c;    state = 0;    c1 = 0;    c2 = 0;    while ((c=getchar())!=EOF) {        c1 = c2;        c2 = c;        change_state(c);    }    if ( (0)==1) {        printf("just test://abcd");        printf("just test:/*hello*/");    }}void change_state(int c){    if (state==0) {        if (c=='/') {            state = 1;        }else if (c=='"'){            state = 5;            putchar(c);        }else if (c=='\''){            state = 6;            putchar(c);        }        else{            state = 0;            putchar(c);        }    }else if (state==1) {        if (c=='/') {            state = 2;        }else if (c=='*'){            state = 3;        }else{            state = 0;            putchar(c1);            putchar(c);        }    }else if (state==2) {        if (c=='\n') {            state = 0;            putchar(c);        }else{            state = 2;        }    }else if (state==3) {        if (c=='*') {            state = 4;        }else{            state = 3;        }    }else if (state==4) {        if (c=='/') {            state = 0;        }else{            state = 3;        }    }else if (state==5){        if (c=='"') {            state = 0;            putchar(c);        }else if(c=='\\'){            state = 7;            putchar(c);        }else{            state = 5;            putchar(c);        }    }else if (state==6){        if (c=='\'') {            state = 0;            putchar(c);        }else if(c=='\\'){            state = 8;            putchar(c);        }else{            state = 6;            putchar(c);        }    }else if (state==7){        state = 5;        putchar(c);    }else if (state==8){        state = 6;        putchar(c);    }

perfect！

感謝@roma823 及其文章：http://blog.csdn.net/roma823/article/details/6364849