五笔�~�码查询

Thu, 20 Nov 2008 08:54:00 GMT

借用�~�码表，查询对应汉字的五�W�编码：

��乓�l�题�Q?br>

int main(int argc, char* argv[])
{
    if (argc==1)
    {
        std::cout<<"用法: wubi <需要查询编码的汉字>"<<std::endl;
        return 0;
    }
    // 文�g路径
    char* szPath = "wubi.txt";

    std::ifstream fin(szPath);
    if (!fin)
    {
        std::cout<<"无法打开五笔�~�码文�g�Q�文件名wubi.txt�Q�请�|�于wubi.exe同目录中"<<std::endl;
        return -1;
    }
    // 通常我们�q�样��d��一个文本文件的全文
    std::string strText = std::string(std::istreambuf_iterator<char>(fin), std::istreambuf_iterator<char>());

    typedef std::map<std::string, std::string> WubiMap;
    WubiMap wubiMap;

    int nLength = strText.length();
    int nLeft = 0;
    int nRight = -1;

    // ��d��五笔�~�码
    std::string strWord;
    std::string strCode;
    while(nRight < nLength)
    {
        nLeft = nRight+1;
        nRight = nLeft+1;
        //tab前的部分为key:strWord
        while (nRight<nLength && strText[nRight] != '\t')
        {
            nRight++;
        }
        if(nRight < nLength)
        {
            strWord = strText.substr(nLeft, nRight - nLeft);
        }

        nLeft = nRight + 1;
        nRight = nLeft + 1;
        //回�R前的为Code
        while (nRight<nLength && strText[nRight] != '\n')
        {
            nRight++;
        }
        if(nRight < nLength)
        {
            strCode = strText.substr(nLeft, nRight - nLeft);
            wubiMap[strWord]= strCode;
        }

    }

    // 循环查找相关汉字的编�?/span>
    std::string strLine=argv[1];
    nLength= strLine.length();
    for (int i=0; i<nLength; ++i)
    {
        // 判断是汉字的前半部分
        if (strLine[i]<0)
        {
            strWord= strLine.substr(i, 2);
            std::cout<<strWord<<"\t"<<wubiMap[strWord]<<std::endl;
            ++i;
        }else
        {
            std::cout<<strLine[i]<<"\t"<<"无对应编�?/span>"<<std::endl;
        }
    }

    return 0;
}

�C�Z��Q?br>D:\>wubi 我是一本书
�?nbsp; trnt
�?nbsp; jghu
一 ggll
�?nbsp; sgd
�?nbsp; nnhy

附：python解决�Ҏ��一个：

import sys

wbx={
'�?/span>':'aaaa',
'�?/span>':'aad',

'�?/span>':'yywf',
'�a�':'yyyy',
'�?/span>':'ttgg',
'�?/span>':'gii'}

if len(sys.argv)==1:
    print('wubi <需要查找五�W�编码的汉字>')
    sys.exit(1)
argv=sys.argv[1:]
for line in argv:
    for c in line:
        if c in wbx:
            print(' %s  %s'%(c, wbx[c]))
        elif ord(c)<128 or c in '�Q�。！~“”�Q?/span>':
            print(' %s'%c)
        else:
            print(' %s  -->�~�码�~�失'%c)

附：五笔�~�码表一张： wubi.7z

��乓加��a :D

李现�?/a> 2008-11-20 16:54 发表评论

单词�l�计

Wed, 19 Nov 2008 02:29:00 GMT

要求�Q�读取一个文本，然后�l�计里面出现的单词，打印每个单词出现的次数。仅仅考虑英文单词的情形，不考虑中文

��乓�l�题�Q?br>

int main(int argc, char* argv[])
{
    using namespace std;

    ifstream infile("c:\\a.txt",ios::binary );
    if(!infile)
    {
        cout<<"Can not open sourse file!"<<endl;
        return 0;
    }
    //ofstream outfile("out.txt");
    //if(!outfile)
    //{
    //    cout<<"Can not open destination file!"<    //}

    int nLength = 0;
    char * pBuffer;

    // get length of file:
    infile.seekg (0, ios::end);
    nLength = infile.tellg();
    infile.seekg (0, ios::beg);


    //read the file to the buffer
    pBuffer = new char[nLength];
    memset(pBuffer, 0, nLength);
    infile.read(pBuffer,nLength);
    infile.close();

    //copy the buffer to the string s
    string s = pBuffer;
    delete[] pBuffer;
    pBuffer = NULL;

    string temp;

    vector<string> vecSubstr;
    vector<int> vecCount;

    int pre=0,next=0;

    while(next<nLength)
    {
        pre=next;
        //find the word
        while((next<nLength)&&isalnum(s[next]))
        {
            next++;
        }
        if(pre!=next)
        {
            //计算当前的单词个�?/span>
            temp = s.substr(pre,next-pre);
            cout<<temp<<endl;
            //std::vector::iterator iter = std::find(vecSubstr.begin(), vecSubstr.end(), temp);
            //if (vecSubstr.end() != iter)
            //{
            //    std::cout<            //}else
            //{
            //    vecSubstr.push_back(temp);
            //}

            unsigned int iPosition=0;


            while(iPosition<vecSubstr.size())
            {

                if(vecSubstr[iPosition].compare(temp)==0)
                    break;

                iPosition++;

            }

            if (iPosition==vecSubstr.size())
            {
                vecSubstr.push_back(temp);
                vecCount.push_back(1);
            }
            else
            {
                vecCount[iPosition]++;
            }

        }
        next++;
    }
    for (int j=0;j<vecSubstr.size();j++)
    {
        cout<<vecSubstr[j]<<endl<<vecCount[j]<<endl;
    }

    //for(int i=0;i    //{
    //    cout<    //    cout<    //}

    //delete[] pBuffer;
    //pBuffer = NULL;

    system("pause");

    return 0;
}

C++代码�Q?br>

int main(int argc, char* argv[])
{

    // 文�g路径
    char* szPath = "C:\\text.txt";

    std::ifstream fin(szPath);
    if (!fin)
    {
        std::cout<<"Can not open file"<<std::endl;
        return -1;
    }
    // 通常我们�q�样��d��一个文本文件的全文
    std::string strText = std::string(std::istreambuf_iterator<char>(fin), std::istreambuf_iterator<char>());

    typedef std::map<std::string, int> CountMap;
    CountMap counter;

    int nLength = strText.length();
    int nLeft = 0;
    int nRight = -1;

    while(nRight<nLength)
    {
        nLeft = nRight+1;
        // 扑ֈ��W�一个是字母的位�|?/span>
        while (nLeft<nLength && !isalnum(strText[nLeft]))
        {
            ++nLeft;
        }
        nRight = nLeft+1;
        // 扑ֈ��W�一个非字母的位�|?/span>
        while (nRight<nLength && isalnum(strText[nRight]))
        {
            ++nRight;
        }
        // 取nRight-nLeft可以保证取到的是一个word�Q�其中不会含有字�W?/span>
        if (nRight < nLength)
        {
            // 提取单词
            std::string strWord = strText.substr(nLeft, nRight - nLeft);
            // 加入记数�?/span>
            counter[strWord]+=1;
        }
    }

    // 打印输出
    for (CountMap::iterator iter = counter.begin(); counter.end()!=iter; ++iter)
    {
        std::cout<<iter->first<<"\t\t"<<iter->second<<std::endl;
    }

    system("pause");
    return 0;
}

python 代码�Q?br>

import re

filepath=r'c:/text.txt'
with open(filepath) as file:
    text=file.read()
    text=re.split('\W+', text)
    d={}
    for item in text:
        d[item]=d.get(item, 0) +1
    for key, value in d.items():
        print('%s\t\t%s'%(key, value))

��乓加��a�Q?br>

李现�?/a> 2008-11-19 10:29 发表评论

国产精品久久久久影院亚瑟,西西人体一区二区,国产精品欧美久久久久无广告

五笔�~�码查询

单词�l�计