如何向后读取文件以有效地找到子字符串

好吧，我发现这种有趣的东西，所以我为二元搜索的想法敲了一个概念证明。

这没有经过很好的测试，可能有点小问题，但到目前为止似乎仍然有效，并展示了“分而治之”的思想。您检查文件的中间位置，然后根据数据的高低将数据分为两部分，然后搜索相关的一半。您可以递归地进行操作，直到足够接近为止。

#include <ctime>
#include <cmath>
#include <cstdlib>
#include <string>
#include <fstream>
#include <iostream>

// Don't use this, its just to show how many reads
// are being done to find the record.
int global_counter;

std::streampos find_stamp(std::istream& is, long stamp, std::streampos pos, std::streampos end)
{
    ++global_counter;

    if(pos == 0) // can't divide zero
        return 0;

    std::string s;
    long found_stamp;

    // extract nearest timestamp after pos
    is.seekg(pos);
    if(!(std::getline(std::getline(is, s, ','), s, '"') >> found_stamp))
        return end;

    // if its too big check first half of this region
    if(found_stamp > stamp)
        return find_stamp(is, stamp, pos / 2, pos);

    // if its not within 10 timestamp seconds check end half of this region
    if(stamp - found_stamp > 10)
        return find_stamp(is, stamp, (pos + end) / 2, end);

    // read record by record (prolly more efficient than skipping)
    pos = is.tellg();
    while(std::getline(std::getline(is, s, ','), s, '"') >> found_stamp)
    {
        if(found_stamp > stamp)
            return pos;
        pos = is.tellg();
    }
    return end;
}

void print_after(const std::string& filename, long stamp)
{
    // open at end of file (to get length)
    std::ifstream ifs(filename, std::ios::ate);

    std::streampos end = ifs.tellg();
    auto pos = end / 2; // start checking in middle

    // find position before required record
    // (may be in the middle of a record)
    if((pos = find_stamp(ifs, stamp, pos, end)) != end)
    {
        ifs.seekg(pos);

        std::string line;
        std::getline(ifs, line, ','); // skip to next whole record

        // print out all following recors
        while(std::getline(ifs, line, ','))
            std::cout << line;
    }
}

inline
std::string leading_zeros(int n, int zeros = 2)
{
    std::string s;
    for(int z = std::pow(10, zeros - 1); z; z /= 10)
        s += (n < z ? "0":"");
    return s + std::to_string(n);
}

int main()
{
    std::srand(std::time(0));

    // generate some test data
    std::ofstream ofs("test.txt");

    for(int i = 0; i < 1000; ++i)
    {
        ofs << '"' << leading_zeros(i, 10) << '"';
        ofs << ":{\"AA\":" << (std::rand() % 100);
        ofs << '.' << (std::rand() % 100) << "},\n";
    }

    ofs.close();

    global_counter = 0;
    print_after("test.txt", 993);

    std::cout << "find checked " << global_counter << " places in the file\n";
}

输出：

"0000000994":{"AA":80.6}
"0000000995":{"AA":11.90}
"0000000996":{"AA":16.43}
"0000000997":{"AA":53.11}
"0000000998":{"AA":68.43}
"0000000999":{"AA":79.77}
find checked 6 places in the file