C++集输出的元素比它包含的要多得多

Question

我有一个非常大的字符串集，我想找到唯一字符串的子集，我使用集容器。这些方法转到MySQL数据库，拉入一组新的字符串，并尝试将它们添加到集合中。我检查从insert返回的信息，以确定是否添加了字符串（第一次出现），或者它已经存在。

#include <iostream>
#include <string>
#include <fstream>
#include <algorithm>
#include <vector>
#include <iostream>

#include "CDR3Sample.h"
#include "MySQLConnect.h"

using namespace std;

int main() {

    CDR3SetReturn ret;
    //CDR3Set is a typedef on set<string>
    CDR3Set total;

    try
    {
            MySQLConnect connection;
            cerr << "size of master " << connection.getMasterSize() << endl;

            SampleIDList list = connection.getSampleIDList();
            SampleIDList ids_seen;
            cerr << "size of raw ID list " << list.size() << endl;


            for (SampleIDListIterator it=list.begin(); it != list.end(); it++) {
                    // We're going to skip it if the table doesn't exist or if the sample has already been processed
                if (connection.checkTable(*it) && find(ids_seen.begin(), ids_seen.end(), *it)!=list.end()) {
            CDR3Sample s(*it, connection);
            int valid_number = 0;
            for (CDR3SetIterator sit=s.begin(); sit != s.end(); sit++) {
                ret = total.insert(*sit);
                if (ret.second) {
                    valid_number++;
                }
            }
            cout << *it << " " << s.getLength() << " " << valid_number << " " << total.size() << endl;
            ids_seen.push_back(*it);
                } else {
                    cerr << *it << " table not found" << endl;
                }
            }
    }
    catch (int i)
    {
            // Need to put code here to save state of calculation
        std::cerr << "Exception thrown by MySQLConnect " << i << std::endl;

        exit(-1);
    }

    // Need to put code here to save state of calculation
    cerr << "size of total " << total.size() << endl;
    ofstream ofs ("cdr3_tally.test", ifstream::out);
    int it_count=0;
    while (ofs.good()) {
        for (CDR3SetIterator it=total.begin(); it != total.end(); ++it) {
            cout << it_count << " " << *it  << endl;
            it_count++;
        }
    }
    ofs.close();
    cerr << "it_count " << it_count << endl;

    ofs_naive.close();


    return 0;
}

为了简洁起见，我将省略支持代码，但我可以提供它。

size of master 9243
size of raw ID list 1
~MySQLConnect
size of total 372

我在ubuntu上使用G++

$g++-v使用内置规范。collect_gcc=g++collect_lto_wrapper=/usr/lib/gcc/x86_64-linux-gnu/4.8/lto-wrapper目标：x86_64-linux-gnu配置有：../src/configure-v--with-pkgversion='Ubuntu 4.8.1-2Ubuntu1~12.04'--with-bugurl=file:///usr/share/doc/gcc-4.8/readme.bugs--enable-languages=C,C++,java,go,d,fortran,OBJ-C++--prefix=/usr-program-suffix=-4.8--enable-shared--enable-linker-build-id--libexecdir=/usr/lib-++/4.8--libdir=/usr/lib--enable-nls--with-sysroot=/--enable-clocale=gnu--enable-libstdcxx-debug--enable-libstdcxx-time=yes-enable-gnu-unique-object--enable-plugin-with-system-zlib-disable-browser-plugin-with-system-zlib-disable-browser-plugin-enable-java-awt=gtk-enable-gtk-cairo root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.8-amd64--with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.8-amd64--with-arch-directory=amd64--with-ecj-jar=/usr/share/java/eclipse-ecj.jar--enable-objc-gc--enable-multiarch--disable-werror--with-arch-32=i686--with-abi=m64--with-multilib-list=m32,m64--with-tune=generic--enable-checking=release-build=x86_64-linux-gnu--host=x86_64-linux-gnu--target=x86_64-linux-gnu线程模型：posix gcc Version4.8.1(Ubuntu4.8.1-2Ubuntu1~12.04)

谢谢

迈克

Answer 1

您的coutfor循环包含在while(ofs.good())中。for循环中的任何内容都不会使它变坏，所以它一直在集合上循环，并一次又一次地打印所有内容。