这是我的代码中运行非常慢的 2 个函数。基本上我读入文档名称，打开文档，然后一次处理一个单词。我需要将文档拆分成句子，并给每个句子一个哈希表，表示单词在句子中出现的次数。我还需要跟踪所有新词，以及整个文档的哈希表。
当我现在在 10 个文档上运行我的代码时，这些文档总共有 8000 个单词和 2100 个 uniq 单词，运行大约需要 8000 多秒……每个单词几乎 1 秒。
你能告诉我需要多长时间if(istream.good())吗？
或者，如果您能知道什么时候延迟了我的代码。如果某个部分不清楚，请告诉我，我会提供帮助。
PS你可以在我有的代码中看到start = clock()并end = clock()评论它不断返回<1ms。这令人难以置信
void DocProcess::indexString(string sentenceString, hash * sent){
stringstream iss;
string word;
iss.clear();
iss << sentenceString;
while(iss.good())
{
iss >> word;
word = formatWord(word);
std::unordered_map<std::string,int>::const_iterator IsNewWord = words.find(word);
if(IsNewWord == words.end())
{
std::pair<std::string,int> newWordPair (word,0);
std::pair<std::string,int> newWordPairPlusOne (word,1);
words.insert(newWordPair);
sent->insert(newWordPairPlusOne);
}
else
{
std::pair<std::string,int> newWordPairPlusOne (word,1);
sent->insert(newWordPairPlusOne);
}
}
} 无效 DocProcess::indexFile(string iFileName){
hash newDocHash;
hash newSentHash;
scoreAndInfo sentenceScore;
scoreAndInfo dummy;
fstream iFile;
fstream dFile;
string word;
string newDoc;
string fullDoc;
int minSentenceLength = 5;
int docNumber = 1;
int runningLength = 0;
int ProcessedWords = 0;
stringstream iss;
iFile.open(iFileName.c_str());
if(iFile.is_open())
{
while(iFile.good())
{
iFile >> newDoc;
dFile.open(newDoc.c_str());
DocNames.push_back(newDoc);
if(dFile.is_open())
{
scoreAndInfo documentScore;
//iss << dFile.rdbuf();
while(dFile.good())
{
//start = clock();
dFile >> word;
++ProcessedWords;
std::unordered_map<std::string,int>::const_iterator IsStopWord = stopWords.find(word);
if(runningLength >= minSentenceLength && IsStopWord != stopWords.end() || word[word.length()-1] == '.')
{
/* word is in the stop list, process the string*/
documentScore.second.second.append(" "+word);
sentenceScore.second.second.append(" "+word);
indexString(sentenceScore.second.second, &sentenceScore.second.first);
sentenceScore.first=0.0;
SentList.push_back(sentenceScore);
sentenceScore.second.first.clear(); //Clear hash
sentenceScore.second.second.clear(); // clear string
//sentenceScore = dummy;
runningLength = 0;
}
else
{
++runningLength;
sentenceScore.second.second.append(" "+word);
documentScore.second.second.append(" "+word);
}
//end = clock();
system("cls");
cout << "Processing doc number: " << docNumber << endl
<< "New Word count: " << words.size() << endl
<< "Total words: " << ProcessedWords << endl;
//<< "Last process time****: " << double(diffclock(end,start)) << " ms"<< endl;
}
indexString(documentScore.second.second, &documentScore.second.first);
documentScore.first=0.0;
DocList.push_back(documentScore);
dFile.close();
//iss.clear();
//documentScore = dummy;
++docNumber;
//end = clock();
system("cls");
cout << "Processing doc number: " << docNumber << endl
<< "Word count: " << words.size();
//<< "Last process time: " << double(diffclock(end,start)) << " ms"<< endl;
}
}
iFile.close();
}
else{ cout << "Unable to open index file: "<<endl <<iFileName << endl;}
} `