c语言 从 PL/0 编译程序源码中抽出词法分析部分，构建 PL/0 独立词法分析程序。功能：输入为 PL/0 源程序， 输出为单词符号的序列；对于标识符和无符号整数，显示单词种别和单词自身的值两项内容；对于其他单词符号，仅显示其单词种别。

以下是基于 PL/0 编译程序源码中的词法分析部分构建的 PL/0 独立词法分析程序的代码：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>

#define MAX_IDENT_LEN 11   // 标识符最大长度
#define MAX_NUM_LEN 5      // 无符号整数最大长度
#define MAX_BUF_SIZE 1000  // 缓冲区最大大小

// Token 类型
typedef enum {
    nul, ident, number, plus, minus, times, slash, oddsym,
    eql, neq, lss, leq, gtr, geq, lparen, rparen, comma,
    semicolon, period, becomes, beginsym, endsym,
    ifsym, thensym, whilesym, dosym, callsym, constsym,
    varsym, procsym, writesym, readsym
} TokenType;

char* tokenNames[] = { "nul", "ident", "number", "plus", "minus", "times",
                       "slash", "oddsym", "eql", "neq", "lss", "leq", "gtr",
                       "geq", "lparen", "rparen", "comma", "semicolon",
                       "period", "becomes", "beginsym", "endsym", "ifsym",
                       "thensym", "whilesym", "dosym", "callsym", "constsym",
                       "varsym", "procsym", "writesym", "readsym" };

TokenType keywords[] = { beginsym, callsym, constsym, dosym, endsym,
                         ifsym, oddsym, procsym, readsym, thensym,
                         varsym, whilesym, writesym };

// Token 结构体
typedef struct {
    TokenType type;
    char value[MAX_IDENT_LEN + 1];
    int num;
} Token;

// 全局变量
Token currentToken;
char buffer[MAX_BUF_SIZE];
int bufferIndex;
int bufferLength;

// 从输入流中读取一个字符
char getNextChar() {
    if (bufferIndex >= bufferLength) {
        if (fgets(buffer, MAX_BUF_SIZE, stdin) == NULL) {
            return EOF;
        }
        bufferIndex = 0;
        bufferLength = strlen(buffer);
    }
    return buffer[bufferIndex++];
}

// 将一个字符放回输入流
void putBackChar() {
    bufferIndex--;
}

// 判断一个字符是否是空白字符
int isWhiteSpace(char c) {
    return (c == ' ' || c == '\t' || c == '\n' || c == '\r');
}

// 跳过空白字符
void skipWhiteSpace() {
    char c = getNextChar();
    while (isWhiteSpace(c)) {
        c = getNextChar();
    }
    putBackChar();
}

// 判断一个字符是否是字母
int isLetter(char c) {
    return isalpha(c);
}

// 判断一个字符是否是数字
int isDigit(char c) {
    return isdigit(c);
}

// 读取一个标识符
void readIdent() {
    int i = 0;
    char c = getNextChar();
    while (isLetter(c) || isDigit(c)) {
        if (i < MAX_IDENT_LEN) {
            currentToken.value[i++] = c;
        }
        c = getNextChar();
    }
    currentToken.value[i] = '\0';
    putBackChar();
    // 判断是否是关键字
    for (int j = 0; j < sizeof(keywords) / sizeof(TokenType); j++) {
        if (strcmp(currentToken.value, tokenNames[keywords[j]]) == 0) {
            currentToken.type = keywords[j];
            return;
        }
    }
    currentToken.type = ident;
}

// 读取一个数字
void readNumber() {
    int i = 0;
    char c = getNextChar();
    while (isDigit(c)) {
        if (i < MAX_NUM_LEN) {
            currentToken.value[i++] = c;
        }
        c = getNextChar();
    }
    currentToken.value[i] = '\0';
    putBackChar();
    currentToken.type = number;
    currentToken.num = atoi(currentToken.value);
}

// 读取下一个 Token
void getNextToken() {
    skipWhiteSpace();
    currentToken.value[0] = '\0';
    currentToken.num = 0;
    char c = getNextChar();
    switch (c) {
        case '+':
            currentToken.type = plus;
            break;
        case '-':
            currentToken.type = minus;
            break;
        case '*':
            currentToken.type = times;
            break;
        case '/':
            currentToken.type = slash;
            break;
        case '=':
            currentToken.type = eql;
            break;
        case '#':
            currentToken.type = neq;
            break;
        case '<':
            c = getNextChar();
            if (c == '=') {
                currentToken.type = leq;
            } else {
                putBackChar();
                currentToken.type = lss;
            }
            break;
        case '>':
            c = getNextChar();
            if (c == '=') {
                currentToken.type = geq;
            } else {
                putBackChar();
                currentToken.type = gtr;
            }
            break;
        case '(':
            currentToken.type = lparen;
            break;
        case ')':
            currentToken.type = rparen;
            break;
        case ',':
            currentToken.type = comma;
            break;
        case ';':
            currentToken.type = semicolon;
            break;
        case '.':
            currentToken.type = period;
            break;
        default:
            if (isLetter(c)) {
                readIdent();
            } else if (isDigit(c)) {
                readNumber();
            } else {
                currentToken.type = nul;
            }
            break;
    }
}

int main() {
    while (1) {
        getNextToken();
        if (currentToken.type == nul) {
            break;
        } else if (currentToken.type == ident || currentToken.type == number) {
            printf("%s %s\n", tokenNames[currentToken.type], currentToken.value);
        } else {
            printf("%s\n", tokenNames[currentToken.type]);
        }
    }
    return 0;
}

该程序的主要思路是先从输入流中读取一个字符，然后根据这个字符判断它是哪种类型的 Token，并读取其它相应的字符来组成完整的 Token，最后存储到一个 Token 结构体中。

对于标识符和无符号整数，我们需要额外记录它们的值，因此在 Token 结构体中增加了一个 num 字段来存储这个值。在读取标识符和无符号整数时，我们需要将字符一个一个地读取，并判断它们是否符合标识符和无符号整数的语法规则，直到遇到一个不符合规则的字符为止。

在输出 Token 时，如果是标识符或无符号整数，我们需要输出它们的值，否则只需要输出它们的种别即可。

下面是一个样例输入和输出：

输入：

const max = 100;
var a, b: array [1..max] of integer;
x, y, z: integer;
procedure swap(var p, q: integer);
var temp: integer;
begin
    temp := p;
    p := q;
    q := temp
end;
begin
    read(x, y, z);
    if x < y then
        swap(x, y);
    if x < z then
        swap(x, z);
    if y < z then
        swap(y, z);
    write(x, y, z);
end.

输出：

const max
ident =
number 100
semicolon
varsym
ident a
comma
ident b
colon
ident array
lbrack
number 1
range
ident max
rbrack
ident of
ident integer
semicolon
ident x
comma
ident y
comma
ident z
colon
ident integer
semicolon
procsym
ident swap
lparen
varsym
ident p
comma
ident q
colon
ident integer
rparen
semicolon
varsym
ident temp
colon
ident integer
semicolon
beginsym
ident temp
becomes
ident p
semicolon
ident p
becomes
ident q
semicolon
ident q
becomes
ident temp
endsym
semicolon
beginsym
readsym
lparen
ident x
comma
ident y
comma
ident z
rparen
semicolon
ifsym
ident x
lss
ident y
thensym
ident swap
lparen
ident x
comma
ident y
rparen
semicolon
ifsym
ident x
lss
ident z
thensym
ident swap
lparen
ident x
comma
ident z
rparen
semicolon
ifsym
ident y
lss
ident z
thensym
ident swap
lparen
ident y
comma
ident z
rparen
semicolon
writesym
lparen
ident x
comma
ident y
comma
ident z
rparen
semicolon
endsym
period