在类似的测试（g ++ 4.8.5）中，用PHP编写的解析器比同一个C ++程序快5.6倍。

#1 楼

string inPath = argv[1];
string outPath = argv[2];

std::ifstream inFile;
std::ofstream outFile;

inFile.open(inPath.c_str());
outFile.open(outPath.c_str());

std::ifstream inFile(argv[1]);
std::ofstream outFile(argv[2]);

  outFile << makeCSVLine(split);

 fmt::print(<FILE*>,
           "{},{},{},{},{},{},{},{},{},{},{}\n",
           vec[0],
           vec[1],
           vec[3],
           vec[4],
           vec[5],
           vec[6],
           vec[10],
           vec[9],
           vec[11],
           vec[7],
           vec[32]);

#2 楼

vector<string> splitStr(string const& line, const char delimiter = ',')
                               ^^^^^^
                               otherwise you are copying the line.

string makeCSVLine(vector<string> const& splitLine)
                                  ^^^^^^
                                  Copying a vector of strings that has to hurt.

 std::cout << MyFormat(splitLine);

 struct MyFormat
 {
      std::vector<std::string> const&   data;
      MyFormat(std::vector<std::string> const& data) :data(data) {}
 };

 std::ostream& operator<<(std::ostream& str, MyFormat const& value)
 {
      return str << value.data[0] << ","
                 << value.data[22] << "\n";
 }

#3 楼

#include <fstream>
#include <string>
#include <vector>
#include <sstream>
#include <optional>

constexpr std::size_t minfields{33};

std::optional<std::vector<std::string>> splitStr(const std::string& line, const char delimiter = ',')
{
    std::vector<std::string> splitLine;
    splitLine.reserve(minfields);
    std::istringstream ss(line);
    std::string buf;
    unsigned field{0};
    while (std::getline(ss, buf, delimiter)) {
        splitLine.push_back(buf);
        if (field == 3 && buf[0] != 'E' && buf[0] != 'T') {
            return std::nullopt;
        }
        ++field;
    }
    if (splitLine.size() < minfields)
        return std::nullopt;
    return splitLine;
}

std::ostream& writeLine(std::ostream& out, const std::vector<std::string>& splitLine)
{
    return out <<  
        splitLine.at(0) << ',' <<
        splitLine.at(1) << ',' <<
        splitLine.at(3) << ',' <<
        splitLine.at(4) << ',' <<
        splitLine.at(5) << ',' <<
        splitLine.at(6) << ',' <<
        splitLine.at(10) << ',' <<
        splitLine.at(9) << ',' <<
        splitLine.at(11) << ',' <<
        splitLine.at(7) << ',' <<
        splitLine.at(32) << '\n';
}

void copy_selective(std::istream& in, std::ostream& out) {
    std::string line;
    while(std::getline(in,line))
    {
        auto split = splitStr(line, ';');
        if (split) {
            writeLine(out, split.value());
        }
    }
}

int main(int argc, char* argv[])
{
    if(argc >= 3) {
        std::ifstream inFile(argv[1]);
        std::ofstream outFile(argv[2]);
        copy_selective(inFile, outFile);
    }
}
优化功能的GCC 10.1）： > \ text {version}和\ text {time（s）}和\ text {相对于PHP} \\ 
 \ hline 
 \ text {original}和2.161＆1.17 \\ 
 \ text {akki}＆1.955＆1.06 \\ 
 \ text {akki w / writeLine}＆1.898＆1.03 \\ 
 \ text {php}＆1.851＆1.00 \\ 
 \ text {爱德华特/ printf}＆1.483＆0.80 \\ 
\ text {爱德华}＆1.456＆0.79 \\ 
 \ text {Matthew}＆0.737＆0.40 \\ 
 \ text {Martin York}＆0.683＆0.37 
 \ end {array} 
 $$ 
对于这些时间，标记为-O2的代码是https://ideone.com/5ivw9R，akki是相同的代码，但修改为使用上面显示的akki w/ writeLine，writeLine是此处显示的代码，修改为使用Edward w/ printf。在我的机器上的所有情况下，fprintf版本都比相应的fstream版本快。
输入文件
我创建了一个简单的文件，共有一百万行。如上所述，只有499980在第四字段中具有必需的“ E”或“ T”。所有行都是这四行之一的重复：
 
one;two;three;Efour;five;six;seven;eight;nine;ten;eleven;twelve;thirteen;fourteen;fifteen;sixteen;seventeen;eighteen;nineteen;twenty;twenty-one;twenty-two;twenty-three;twenty-four;twenty-five;twenty-six;twenty-seven;twenty-eight;twenty-nine;thirty;thirty-one;thirty-two;thirty-three;thirty-four
one;two;three;Tfour;five;six;seven;eight;nine;ten;eleven;twelve;thirteen;fourteen;fifteen;sixteen;seventeen;eighteen;nineteen;twenty;twenty-one;twenty-two;twenty-three;twenty-four;twenty-five;twenty-six;twenty-seven;twenty-eight;twenty-nine;thirty;thirty-one;thirty-two;thirty-three;thirty-four
one;two;three;four;five;six;seven;eight;nine;ten;eleven;twelve;thirteen;fourteen;fifteen;sixteen;seventeen;eighteen;nineteen;twenty;twenty-one;twenty-two;twenty-three;twenty-four;twenty-five;twenty-six;twenty-seven;twenty-eight;twenty-nine;thirty;thirty-one;thirty-two;thirty-three;thirty-four
one;two;three;Xfour;five;six;seven;eight;nine;ten;eleven;twelve;thirteen;fourteen;fifteen;sixteen;seventeen;eighteen;nineteen;twenty;twenty-one;twenty-two;twenty-three;twenty-four;twenty-five;twenty-six;twenty-seven;twenty-eight;twenty-nine;thirty;thirty-one;thirty-two;thirty-three;thirty-four
 
固定的PHP版本
因为我无法运行最初发布的PHP代码（它因错误而中止并生成了一个长度为0的文件） ，我打算对其进行最小的更改，以使其得以编译和运行。一个PHP专家（我不是一个）可能能够进一步改进它，但是它的性能相当不错，无需花费很多精力。 （以上使用的是PHP 7.4.8和Zend Engine v3.4.0。）
 
<?php
$i_fp = fopen("million.in","r");
$o_fp = fopen("sample.out","w") or die("Unable to open outfile");

while(!feof($i_fp))
{
    $line = fgets($i_fp);
    $split = explode(';',$line);
    if(count($split) > 33 && ($split[3][0] == 'E' || $split[3][0] == 'T')) {
        fwrite($o_fp,join(',',[ $split[0], $split[1], $split[3], $split[4], $split[5], $split[6],
                                $split[10], $split[9],$split[11],$split[7],$split[32]])."\n");
    }
}
fclose($i_fp);
fclose($o_fp);
?>
 

评论
\ $ \ begingroup \ $

评论不用于扩展讨论；此对话已移至聊天。

 \ $ \ endgroup \ $

 – Mathieu Guindon♦

 20年8月1日在13:14 

#4 楼

#include <fstream>
#include <string>
#include <string_view>
#include <vector>

using std::string;
using std::string_view;
using std::vector;

void splitStr(string_view line, const char delimiter, vector<string_view>& splitLine)
{
    splitLine.clear();
    for(;;) {
        std::size_t pos = line.find(delimiter);
        if (pos == string_view::npos) {
            splitLine.push_back(line);
            return;
        }

        splitLine.push_back(line.substr(0, pos));
        line = line.substr(pos+1, string_view::npos);
    }
}

template<typename T>
void makeCSVLine(T& out, const vector<string_view>& splitLine)
{
    out <<
        splitLine[0] << ',' <<
        splitLine[1] << ',' <<
        splitLine[3] << ',' <<
        splitLine[4] << ',' <<
        splitLine[5] << ',' <<
        splitLine[6] << ',' <<
        splitLine[10] << ',' <<
        splitLine[9] << ',' <<
        splitLine[11] << ',' <<
        splitLine[7] << ',' <<
        splitLine[32] << '\n';
}

int main(int argc, char* argv[])
{
    if(argc < 3)
    {
        exit(EXIT_SUCCESS);
    }

    const char* inPath = argv[1];
    const char* outPath = argv[2];

    std::ifstream inFile;
    std::ofstream outFile;

    inFile.open(inPath);
    outFile.open(outPath);

    vector<string_view> split;
    string line;
    while(std::getline(inFile, line))
    {
        splitStr(line, ';', split);
        if(split[3][0] == 'E' || split[3][0] == 'T')
        {
            makeCSVLine(outFile, split);
        }
    }
    inFile.close();
    outFile.close();
}

#5 楼

#6 楼