如何迭代由空格分隔的单词组成的字符串中的单词？
注意，我对C字符串函数或那种字符操作/访问不感兴趣。比起效率，我更喜欢优雅。我当前的解决方案：
#include <iostream>
#include <sstream>
#include <string>
using namespace std;
int main() {
string s = "Somewhere down the road";
istringstream iss(s);
do {
string subs;
iss >> subs;
cout << "Substring: " << subs << endl;
} while (iss);
}
当前回答
我有一种与其他解决方案非常不同的方法，它提供了很多其他解决方案所缺乏的价值，但当然也有其缺点。这是一个工作实现，示例是在单词周围放置＜tag＞＜/tag＞。
首先，这个问题可以通过一个循环解决，不需要额外的内存，只需考虑四种逻辑情况。从概念上讲，我们对边界感兴趣。我们的代码应该反映出这一点：让我们遍历字符串，一次查看两个字符，记住字符串的开头和结尾都有特殊情况。
缺点是我们必须编写实现，这有点冗长，但大多是方便的样板。
好处是我们编写了实现，因此很容易根据特定的需要定制它，例如区分左和写单词边界，使用任何一组分隔符，或处理其他情况，例如无边界或错误位置。
using namespace std;
#include <iostream>
#include <string>
#include <cctype>
typedef enum boundary_type_e {
E_BOUNDARY_TYPE_ERROR = -1,
E_BOUNDARY_TYPE_NONE,
E_BOUNDARY_TYPE_LEFT,
E_BOUNDARY_TYPE_RIGHT,
} boundary_type_t;
typedef struct boundary_s {
boundary_type_t type;
int pos;
} boundary_t;
bool is_delim_char(int c) {
return isspace(c); // also compare against any other chars you want to use as delimiters
}
bool is_word_char(int c) {
return ' ' <= c && c <= '~' && !is_delim_char(c);
}
boundary_t maybe_word_boundary(string str, int pos) {
int len = str.length();
if (pos < 0 || pos >= len) {
return (boundary_t){.type = E_BOUNDARY_TYPE_ERROR};
} else {
if (pos == 0 && is_word_char(str[pos])) {
// if the first character is word-y, we have a left boundary at the beginning
return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos};
} else if (pos == len - 1 && is_word_char(str[pos])) {
// if the last character is word-y, we have a right boundary left of the null terminator
return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
} else if (!is_word_char(str[pos]) && is_word_char(str[pos + 1])) {
// if we have a delimiter followed by a word char, we have a left boundary left of the word char
return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos + 1};
} else if (is_word_char(str[pos]) && !is_word_char(str[pos + 1])) {
// if we have a word char followed by a delimiter, we have a right boundary right of the word char
return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
}
return (boundary_t){.type = E_BOUNDARY_TYPE_NONE};
}
}
int main() {
string str;
getline(cin, str);
int len = str.length();
for (int i = 0; i < len; i++) {
boundary_t boundary = maybe_word_boundary(str, i);
if (boundary.type == E_BOUNDARY_TYPE_LEFT) {
// whatever
} else if (boundary.type == E_BOUNDARY_TYPE_RIGHT) {
// whatever
}
}
}
正如您所看到的，代码非常容易理解和微调，代码的实际使用非常简短和简单。使用C++不应阻止我们编写最简单、最容易定制的代码，即使这意味着不使用STL。我认为这是Linus Torvalds所说的“品味”的一个例子，因为我们已经消除了所有不需要的逻辑，而写作风格自然允许在需要处理的时候处理更多的案件。
可以改进此代码的可能是使用enum类，在maybe_word_boundary中接受指向is_word_char的函数指针，而不是直接调用is_word_char，并传递lambda。
其他回答
我用这个分隔符分隔字符串。第一个将结果放入预先构建的向量中，第二个返回新向量。
#include <string>
#include <sstream>
#include <vector>
#include <iterator>
template <typename Out>
void split(const std::string &s, char delim, Out result) {
std::istringstream iss(s);
std::string item;
while (std::getline(iss, item, delim)) {
*result++ = item;
}
}
std::vector<std::string> split(const std::string &s, char delim) {
std::vector<std::string> elems;
split(s, delim, std::back_inserter(elems));
return elems;
}
请注意，此解决方案不会跳过空令牌，因此下面将找到4项，其中一项为空：
std::vector<std::string> x = split("one:two::three", ':');
LazyString拆分器：
#include <string>
#include <algorithm>
#include <unordered_set>
using namespace std;
class LazyStringSplitter
{
string::const_iterator start, finish;
unordered_set<char> chop;
public:
// Empty Constructor
explicit LazyStringSplitter()
{}
explicit LazyStringSplitter (const string cstr, const string delims)
: start(cstr.begin())
, finish(cstr.end())
, chop(delims.begin(), delims.end())
{}
void operator () (const string cstr, const string delims)
{
chop.insert(delims.begin(), delims.end());
start = cstr.begin();
finish = cstr.end();
}
bool empty() const { return (start >= finish); }
string next()
{
// return empty string
// if ran out of characters
if (empty())
return string("");
auto runner = find_if(start, finish, [&](char c) {
return chop.count(c) == 1;
});
// construct next string
string ret(start, runner);
start = runner + 1;
// Never return empty string
// + tail recursion makes this method efficient
return !ret.empty() ? ret : next();
}
};
我将此方法称为LazyStringSplitter是因为一个原因——它不会一次性拆分字符串。本质上，它的行为类似于python生成器它公开了一个名为next的方法，该方法返回从原始字符串拆分的下一个字符串我使用了c++11STL中的无序集，因此查找分隔符的速度要快得多下面是它的工作原理
测试程序
#include <iostream>
using namespace std;
int main()
{
LazyStringSplitter splitter;
// split at the characters ' ', '!', '.', ','
splitter("This, is a string. And here is another string! Let's test and see how well this does.", " !.,");
while (!splitter.empty())
cout << splitter.next() << endl;
return 0;
}
输出，输出
This
is
a
string
And
here
is
another
string
Let's
test
and
see
how
well
this
does
改进这一点的下一个计划是实施开始和结束方法，以便可以执行以下操作：
vector<string> split_string(splitter.begin(), splitter.end());
这是另一种方法。。
void split_string(string text,vector<string>& words)
{
int i=0;
char ch;
string word;
while(ch=text[i++])
{
if (isspace(ch))
{
if (!word.empty())
{
words.push_back(word);
}
word = "";
}
else
{
word += ch;
}
}
if (!word.empty())
{
words.push_back(word);
}
}
这是我最喜欢的遍历字符串的方法。每个词你都可以做你想做的事。
string line = "a line of text to iterate through";
string word;
istringstream iss(line, istringstream::in);
while( iss >> word )
{
// Do something on `word` here...
}
我使用以下代码：
namespace Core
{
typedef std::wstring String;
void SplitString(const Core::String& input, const Core::String& splitter, std::list<Core::String>& output)
{
if (splitter.empty())
{
throw std::invalid_argument(); // for example
}
std::list<Core::String> lines;
Core::String::size_type offset = 0;
for (;;)
{
Core::String::size_type splitterPos = input.find(splitter, offset);
if (splitterPos != Core::String::npos)
{
lines.push_back(input.substr(offset, splitterPos - offset));
offset = splitterPos + splitter.size();
}
else
{
lines.push_back(input.substr(offset));
break;
}
}
lines.swap(output);
}
}
// gtest:
class SplitStringTest: public testing::Test
{
};
TEST_F(SplitStringTest, EmptyStringAndSplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(Core::String(), Core::String(), result));
}
TEST_F(SplitStringTest, NonEmptyStringAndEmptySplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(L"xy", Core::String(), result));
}
TEST_F(SplitStringTest, EmptyStringAndNonEmptySplitter)
{
std::list<Core::String> result;
Core::SplitString(Core::String(), Core::String(L","), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(Core::String(), *result.begin());
}
TEST_F(SplitStringTest, OneCharSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,y", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
Core::SplitString(L",xy", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L"xy", *result.rbegin());
Core::SplitString(L"xy,", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"xy", *result.begin());
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, TwoCharsSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,.y,z", L",.", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
Core::SplitString(L"x,,y,z", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
}
TEST_F(SplitStringTest, RecursiveSplitter)
{
std::list<Core::String> result;
Core::SplitString(L",,,", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L",", *result.rbegin());
Core::SplitString(L",.,.,", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L".,", *result.rbegin());
Core::SplitString(L"x,.,.,y", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L".,y", *result.rbegin());
Core::SplitString(L",.,,.,", L",.,", result);
ASSERT_EQ(3, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(Core::String(), *(++result.begin()));
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, NullTerminators)
{
std::list<Core::String> result;
Core::SplitString(L"xy", Core::String(L"\0", 1), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(L"xy", *result.begin());
Core::SplitString(Core::String(L"x\0y", 3), Core::String(L"\0", 1), result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
}
