如何使用 stringstream 来标记像这样的一行。
[标签] 操作码 [arg1] [,arg2]
标签可能不会一直存在，但如果不存在，就会有一个空白区域。操作码始终存在，操作码和 arg1 之间有一个空格或制表符。然后 arg1 和 arg2 之间没有空格，但用逗号分隔。
此外，一些空白行上会有空白，因此需要将其丢弃。 '#'是注释
例如:
#Sample Input
TOP NoP
L 2,1
VAL INT 0
这只是我将从中读取的文本文件的示例。因此，第一行的标签将是 TOP 并且操作码将 = NOP 且不传递任何参数。
我一直在研究它，但我需要一种更简单的标记化方法，据我所知，stringstream 似乎是我想要使用的方法，所以如果有人能告诉我如何做的话, 我真的很感激。
我一直在绞尽脑汁思考如何做到这一点，只是为了向您展示我不只是问而不做，这是我当前的代码:
int counter = 0;
int i = 0;
int j = 0;
int p = 0;
while (getline(myFile, line, '\n'))
{
if (line[0] == '#')
{
continue;
}
if (line.length() == 0)
{
continue;
}
if (line.empty())
{
continue;
}
// If the first letter isn't a tab or space then it's a label
if (line[0] != '\t' && line[0] != ' ')
{
string delimeters = "\t ";
int current;
int next = -1;
current = next + 1;
next = line.find_first_of( delimeters, current);
label = line.substr( current, next - current );
Symtablelab[i] = label;
Symtablepos[i] = counter;
if(next>0)
{
current = next + 1;
next = line.find_first_of(delimeters, current);
opcode = line.substr(current, next - current);
if (opcode != "WORDS" && opcode != "INT")
{
counter += 3;
}
if (opcode == "INT")
{
counter++;
}
if (next > 0)
{
delimeters = ", \n\t";
current = next + 1;
next = line.find_first_of(delimeters, current);
arg1 = line.substr(current, next-current);
if (opcode == "WORDS")
{
counter += atoi(arg1.c_str());
}
}
if (next > 0)
{
delimeters ="\n";
current = next +1;
next = line.find_first_of(delimeters,current);
arg2 = line.substr(current, next-current);
}
}
i++;
}
// If the first character is a tab or space then there is no label and we just need to get a counter
if (line[0] == '\t' || line[0] == ' ')
{
string delimeters = "\t \n";
int current;
int next = -1;
current = next + 1;
next = line.find_first_of( delimeters, current);
label = line.substr( current, next - current );
if(next>=0)
{
current = next + 1;
next = line.find_first_of(delimeters, current);
opcode = line.substr(current, next - current);
if (opcode == "\t" || opcode =="\n"|| opcode ==" ")
{
continue;
}
if (opcode != "WORDS" && opcode != "INT")
{
counter += 3;
}
if (opcode == "INT")
{
counter++;
}
if (next > 0)
{
delimeters = ", \n\t";
current = next + 1;
next = line.find_first_of(delimeters, current);
arg1 = line.substr(current, next-current);
if (opcode == "WORDS")
{
counter += atoi(arg1.c_str());
}
}
if (next > 0)
{
delimeters ="\n\t ";
current = next +1;
next = line.find_first_of(delimeters,current);
arg2 = line.substr(current, next-current);
}
}
}
}
myFile.clear();
myFile.seekg(0, ios::beg);
while(getline(myFile, line))
{
if (line.empty())
{
continue;
}
if (line[0] == '#')
{
continue;
}
if (line.length() == 0)
{
continue;
}
// If the first letter isn't a tab or space then it's a label
if (line[0] != '\t' && line[0] != ' ')
{
string delimeters = "\t ";
int current;
int next = -1;
current = next + 1;
next = line.find_first_of( delimeters, current);
label = line.substr( current, next - current );
if(next>0)
{
current = next + 1;
next = line.find_first_of(delimeters, current);
opcode = line.substr(current, next - current);
if (next > 0)
{
delimeters = ", \n\t";
current = next + 1;
next = line.find_first_of(delimeters, current);
arg1 = line.substr(current, next-current);
}
if (next > 0)
{
delimeters ="\n\t ";
current = next +1;
next = line.find_first_of(delimeters,current);
arg2 = line.substr(current, next-current);
}
}
if (opcode == "INT")
{
memory[p] = arg1;
p++;
continue;
}
if (opcode == "HALT" || opcode == "NOP" || opcode == "P_REGS")
{
memory[p] = opcode;
p+=3;
continue;
}
if(opcode == "J" || opcode =="JEQR" || opcode == "JNE" || opcode == "JNER" || opcode == "JLT" || opcode == "JLTR" || opcode == "JGT" || opcode == "JGTR" || opcode == "JLE" || opcode == "JLER" || opcode == "JGE" || opcode == "JGER" || opcode == "JR")
{
memory[p] = opcode;
memory[p+1] = arg1;
p+=3;
continue;
}
if (opcode == "WORDS")
{
int l = atoi(arg1.c_str());
for (int k = 0; k <= l; k++)
{
memory[p+k] = "0";
}
p+=l;
continue;
}
else
{
memory[p] = opcode;
memory[p+1] = arg1;
memory[p+2] = arg2;
p+=3;
}
}
// If the first character is a tab or space then there is no label and we just need to get a counter
if (line[0] == '\t' || line[0] == ' ')
{
string delimeters = "\t ";
int current;
int next = -1;
current = next + 1;
next = line.find_first_of( delimeters, current);
label = line.substr( current, next - current );
if(next>=0)
{
current = next + 1;
next = line.find_first_of(delimeters, current);
opcode = line.substr(current, next - current);
if (opcode == "\t" || opcode =="\n"|| opcode ==" "|| opcode == "")
{
continue;
}
if (next > 0)
{
delimeters = ", \n\t";
current = next + 1;
next = line.find_first_of(delimeters, current);
arg1 = line.substr(current, next-current);
}
if (next > 0)
{
delimeters ="\n\t ";
current = next +1;
next = line.find_first_of(delimeters,current);
arg2 = line.substr(current, next-current);
}
}
if (opcode == "INT")
{
memory[p] = arg1;
p++;
continue;
}
if (opcode == "HALT" || opcode == "NOP" || opcode == "P_REGS")
{
memory[p] = opcode;
p+=3;
continue;
}
if(opcode == "J" || opcode =="JEQR" || opcode == "JNE" || opcode == "JNER" || opcode == "JLT" || opcode == "JLTR" || opcode == "JGT" || opcode == "JGTR" || opcode == "JLE" || opcode == "JLER" || opcode == "JGE" || opcode == "JGER" || opcode == "JR")
{
memory[p] = opcode;
memory[p+1] = arg1;
p+=3;
continue;
}
if (opcode == "WORDS")
{
int l = atoi(arg1.c_str());
for (int k = 0; k <= l; k++)
{
memory[p+k] = "0";
}
p+=l;
continue;
}
else
{
memory[p] = opcode;
memory[p+1] = arg1;
memory[p+2] = arg2;
p+=3;
}
}
}
我显然想让它变得更好，所以我们将不胜感激任何帮助。
最佳答案
在您为维护那些巨大的 if 状态或尝试学习 Boost Spirit 而发疯之前，让我们尝试编写一个非常简单的解析器。这是一个有点长的帖子，
并没有直接进入正题，所以请多多包涵。
首先，我们需要一个语法，它看起来非常简单:
line label(optional) opcode argument-list(optional) argument-list argument argument, argument-list
英文:一行代码由一个可选标签、一个操作码和一个可选参数列表组成。参数列表是单个参数(整数)或后跟分隔符(逗号)和另一个参数列表的参数。
让我们首先定义两个数据结构。标签应该是唯一的(对吗？)，所以我们将有一组字符串，以便我们可以随时轻松地查找它们，如果我们发现重复的标签，则可能会报告错误。下一个是字符串到 size_t 的映射，它充当有效操作码的符号表以及每个操作码的预期参数数量。
std::set<std::string> labels;
std::map<std::string, size_t> symbol_table = {
{ "INT", 1},
{ "NOP", 0},
{ "L", 2}
};
我不知道您的代码中的memory 到底是什么，但是您计算偏移量以确定参数放置位置的方法似乎不必要地复杂。让我们定义一个可以优雅地保存一行代码的数据结构。我会做这样的事情:
typedef std::vector<int> arg_list;
struct code_line {
code_line() : label(), opcode(), args() {}
std::string label; // labels are optional, so an empty string
// will mean absence of label
std::string opcode; // opcode, doh
arg_list args; // variable number of arguments, it can be empty, too.
// It needs to match with opcode, we'll deal with
// that later
};
语法错误是一种不容易恢复的异常情况，所以让我们通过抛出异常来处理它们。我们的简单异常类可能如下所示:
struct syntax_error {
syntax_error(std::string m) : msg(m) { }
std::string msg;
};
分词、词法分析和解析通常是分开的任务。但我想对于这个简单的例子，我们可以在一个类中结合 tokenizer 和 lexer。我们已经知道组成语法的元素，所以让我们编写一个类，将输入作为文本并从中提取语法元素。界面可能如下所示:
class token_stream {
std::istringstream stream; // stringstream for input
std::string buffer; // a buffer for a token, more on this later
public:
token_stream(std::string str) : stream(str), buffer() { }
// these methods are self-explanatory
std::string get_label();
std::string get_opcode();
arg_list get_arglist();
// we're taking a kind of top-down approach with this,
// so let's forget about implementations for now
};
还有工作马，一个试图理解标记并在一切顺利的情况下返回 code_line 结构的函数:
code_line parse(std::string line)
{
code_line temp;
token_stream stream(line);
// Again, self-explanatory, get a label, opcode and argument list from
// token stream.
temp.label = stream.get_label();
temp.opcode = stream.get_opcode();
temp.args = stream.get_arglist();
// Everything went fine so far, remember we said we'd be throwing exceptions
// in case of syntax errors.
// Now we can check if we got the correct number of arguments for the given opcode:
if (symbol_table[temp.opcode] != temp.args.size()) {
throw syntax_error("Wrong number of parameters.");
}
// The last thing, if there's a label in the line, we insert it in the table.
// We couldn't do that inside the get_label method, because at that time
// we didn't yet know if the rest of the line is sintactically valid and a
// exception thrown would have left us with a "dangling" label in the table.
if (!temp.label.empty()) labels.insert(temp.label);
return temp;
}
下面是我们如何使用所有这些:
int main()
{
std::string line;
std::vector<code_line> code;
while (std::getline(std::cin, line)) {
// empty line or a comment, ignore it
if (line.empty() || line[0] = '#') continue;
try {
code.push_back(parse(line));
} catch (syntax_error& e) {
std::cout << e.msg << '\n';
// Give up, try again, log... up to you.
}
}
}
如果输入被成功解析，我们现在得到一个包含所有信息(标签、参数数量)的有效行 vector ，并且可以用它做我们想做的几乎所有事情。这段代码将比你的代码更容易维护和扩展，IMO。例如，如果您需要引入新的操作码，只需在映射 (symbol_table) 中创建另一个条目。与您的 if 语句相比如何？ :)
唯一剩下的就是 token_stream 方法的实际实现。下面是我为 get_label 做的:
std::string token_stream::get_label()
{
std::string temp;
// Unless the stream is empty (and it shouldn't be, we checked that in main),
// operator>> for std::string is unlikely to fail. It doesn't hurt to be robust
// with error checking, though
if (!(stream >> temp)) throw ("Fatal error, empty line, bad stream?");
// Ok, we got something. First we should check if the string consists of valid
// characters - you probably don't want punctuation characters and such in a label.
// I leave this part out for simplicity.
// Since labels are optional, we need to check if the token is an opcode.
// If that's the case, we return an empty (no) label.
if (symbol_table.find(temp) != symbol_table.end()) {
buffer = temp;
return "";
}
// Note that above is where that `buffer` member of token_stream class got used.
// If the token was an opcode, we needed to save it so get_opcode method can make
// use of it. The other option would be to put the string back in the underlying
// stringstream, but that's more work and more code. This way, get_opcode needs
// to check if there's anything in buffer and use it, or otherwise extract from
// the stringstream normally.
// Check if the label was used before:
if (labels.count(temp))
throw syntax_error("Label already used.");
return temp;
}
就是这样。我将其余的实现留给您作为练习。希望它有所帮助。 :)
关于c++ - 使用 stringstream 来标记具有不同分隔符的字符串，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/12468798/