C++ MatchResult::GetEnd方法代码示例

// 仅用来搜索关键字，结果保存在char* resultFile中
void SearchKeysInFile(const char* file,const char * keys,const char * resultFile)
{
	// text
	//char * text = "12.5, a1.1, 0.123, 178";

	// declare
	//static CRegexpT <char> regexp("\\b\\d+\\.\\d+");
	//char * key=m_Keyword.GetBuffer();
	static CRegexpT <char> regexp(keys);
	CContext * pContext;

	//读文件,分块查找
	std::ifstream ifs;
	ifs.open(file,ifstream::binary);
	ifs.seekg(0,ifstream::beg);

	std::ofstream ofs;
	ofs.open(resultFile,ofstream::binary);
	ofs.clear();
	//ofs.seekg(0,ofstream::beg);

	char * pBuffer=new char[BLOCK_SIZE];
	while(!ifs.eof())
	{
		ifs.read(pBuffer,BLOCK_SIZE);

		//////////////////////////////////////////////////////////////////////////
		//分块查找

		// prepare
		pContext= regexp.PrepareMatch(pBuffer);

		// loop
		MatchResult result = regexp.Match(pContext);

		while( result.IsMatched() )
		{
			// 写入结果文件
			//	printf("%.*s\n", result.GetEnd() - result.GetStart(), pBuffer + result.GetStart());
			
			// 先转换，再写入
			ofs.write(pBuffer + result.GetStart(),result.GetEnd() - result.GetStart());
			ofs<<endl;
			ofs<<"——————————————————————"<<endl;
			// get next
			result = regexp.Match(pContext);
		}
	}

	// 搜索成功结束
	ifs.close();
	ofs.close();
	

	// release
	regexp.ReleaseContext(pContext);

	delete[] pBuffer;

}

int main(int argc, char * argv[])
{
	std::ifstream fs("C:\\Lookup\\112.127.141.86.html");
	std::string in;
	load_file(in, fs);
	fs.close();
	//static CRegexpT <char> regexp1("\\d+");
	static CRegexpT <char> regexp1("target=\\\"_blank\\\"\\>(.+?)\\</a\\>\\</td\\>");
	// loop
	MatchResult result1 = regexp1.Match(in.c_str());

	while( result1.IsMatched() )
	{  
		//GetEnd匹配成功后，获取所匹配到的子字符串的结束位置。如果匹配失败，则返回负值。
		//GetStart匹配成功后，获取所匹配到的子字符串的开始位置。如果匹配失败，则返回负值。
		printf("%.*s\n", result1.GetEnd() - result1.GetStart(), in.c_str() + result1.GetStart());
		// get next
		result1 = regexp1.Match(in.c_str(), result1.GetEnd());  //返回匹配结果 MatchResult 对象。
		// 通过 MatchResult 对象，可以得知是否匹配成功。如果成功，通过 MatchResult 对象可以获取捕获信息。

	}

	// text
	char * text = "http://www.cppprog.com/2009/0112/48.html";
	// declare
	static CRegexpT <char> regexp("\\d+");
	// loop
	MatchResult result = regexp.Match(text);
	//IsMatched返回非零值表示匹配成功，返回 0 表示匹配失败。
	while( result.IsMatched() )
	{  
		//GetEnd匹配成功后，获取所匹配到的子字符串的结束位置。如果匹配失败，则返回负值。
		//GetStart匹配成功后，获取所匹配到的子字符串的开始位置。如果匹配失败，则返回负值。
		printf("%.*s\n", result.GetEnd() - result.GetStart(), text + result.GetStart());
		// get next
		result = regexp.Match(text, result.GetEnd());  //返回匹配结果 MatchResult 对象。
		// 通过 MatchResult 对象，可以得知是否匹配成功。如果成功，通过 MatchResult 对象可以获取捕获信息。

	}
	return 0;
}

//.........这里部分代码省略.........
			}
			catch (pfc::exception & e)
			{
				console_error(e.what());
				continue;
			}
			catch (...)
			{
				continue;
			}

			const char * regex_ahref = "<a\\shref=\"#(?P<no>\\d+)\">(?P<text>.+?)</a>";

			// expression for extract lyrics
			regexp.Compile(regex_ahref, IGNORECASE);

			// match
			MatchResult result = regexp.Match(buff.get_ptr());

			int noGroup = regexp.GetNamedGroupNumber("no");
			int textGroup = regexp.GetNamedGroupNumber("text");

			int jump_to = 0;
			pfc::string8_fast compare = title;
			compare.insert_chars(0, ". ");
			float good;
			float best = 0.0f;


			while (result.IsMatched())
			{
				int gStart = result.GetGroupStart(noGroup);
				int gEnd = result.GetGroupEnd(noGroup);
				pfc::string8_fast temp(buff.get_ptr() + gStart, gEnd - gStart);
				int no = StrToIntA(temp);

				gStart = result.GetGroupStart(textGroup);
				gEnd = result.GetGroupEnd(textGroup);

				temp = pfc::string8_fast(buff.get_ptr()+gStart, gEnd - gStart);

				int levDist = LD(compare, compare.get_length(), temp, temp.get_length());

				good = 1.0f - (levDist / (float)compare.get_length());

				if (good >= threshold && good > best)
				{
					jump_to = no;
					best = good;
				}
				result = regexp.Match(buff.get_ptr(),result.GetEnd());
			}

			if (jump_to == 0)
			{
				continue;
			}

			char regex_lyrics[100];

			sprintf(regex_lyrics, "<a\\s+name=%d><font*(.*?)</font*(.*?)>(?P<lyrics>.+?)<font", jump_to);

			// expression for extract lyrics
			regexp.Compile(regex_lyrics, IGNORECASE | SINGLELINE);

			noGroup = regexp.GetNamedGroupNumber("lyrics");

			result = regexp.Match(buff.get_ptr());

			if (result.IsMatched())
			{
				int nStart = result.GetGroupStart(noGroup);
				int nEnd = result.GetGroupEnd(noGroup);
				pfc::string8 lyric(buff.get_ptr() + nStart, nEnd - nStart);

				convert_html_to_plain(lyric);

				if (lyric.get_length() > 0)
				{
					string_helper::remove_beginning_linebreaks(lyric);
					string_helper::remove_end_linebreaks(lyric);
					string_helper::remove_beginning(lyric, ' ');
					string_helper::remove_beginning(lyric, '\t');
					return lyric;
				}
			}
		}
	}
	catch (pfc::exception & e)
	{
		console_error(e.what());
		return "";
	}
	catch (...)
	{
		return "";
	}

	return "";
}