// 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;
}
pfc::string8 provider_darklyrics::lookup_one(unsigned p_index, const metadb_handle_ptr & p_meta, threaded_process_status & p_status, abort_callback & p_abort)
{
TRACK_CALL_TEXT("provider_darklyrics::lookup_one");
const float threshold = 0.8f;
const pfc::string8 site = "darklyrics.com";
// Regular Expression Class
CRegexpT<char> regexp;
MatchResult match;
// Buffer
pfc::string8 buff;
try
{
// Init fetcher
curl_wrapper_simple fetcher(&m_config_item);
const metadb_handle_ptr & p = p_meta;
if (p.is_empty())
{
return "";
}
pfc::string8_fast artist, title, album, keywords;
file_info_impl info;
p->get_info(info);
// Get count of artists
t_size count = info.meta_get_count_by_name("album");
if (count == 0)
return "";
// Get Album
album = info.meta_get("album", 0);
count = info.meta_get_count_by_name("title");
if (count == 0)
return "";
// Get TITLE
title = info.meta_get("title", 0);
count = info.meta_get_count_by_name("artist");
// Iterate through all artists listed
for (int j = 0; j < count; j++)
{
// Get Artist
artist = info.meta_get("artist", j); //Fetching from HTTP
keywords = artist;
keywords += "+";
keywords += album;
keywords.replace_char(' ', '+');
// Get it now
try
{
fetcher.fetch_googleluck(site, keywords, buff);
}
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 "";
}
//************************************************************************
//* Dark Lyrics *
//************************************************************************
pfc::string_list_impl * provider_darklyrics::lookup(unsigned p_index, metadb_handle_list_cref p_meta, threaded_process_status & p_status, abort_callback & p_abort)
{
TRACK_CALL_TEXT("provider_darklyrics::lookup");
const float threshold = 0.8f;
const pfc::string8 site = "darklyrics.com";
// Regular Expression Class
CRegexpT<char> regexp;
MatchResult match;
// Buffer
pfc::string8 buff;
pfc::string_list_impl * str_list = new pfc::string_list_impl;
try
{
// Init fetcher
curl_wrapper_simple fetcher(&m_config_item);
for (t_size i = 0; i < p_meta.get_count(); ++i)
{
if (p_abort.is_aborting())
break;
// Sleep
how_to_sleep(i);
// Clear buff
buff.reset();
const metadb_handle_ptr & p = p_meta.get_item(i);
if (p.is_empty())
{
str_list->add_item("");
continue;
}
// Set progress
pfc::string8_fast path = file_path_canonical(p->get_path());
// add subsong index?
if (p->get_subsong_index() > 0)
{
path.add_string(" /index:");
path.add_string(pfc::format_uint(p->get_subsong_index()));
}
p_status.set_item_path(path);
p_status.set_progress(i + 1, p_meta.get_count());
pfc::string8_fast artist, title, album, keywords;
file_info_impl info;
p->get_info(info);
// Get count of artists
t_size count = info.meta_get_count_by_name("album");
if (count == 0)
continue;
// Get Album
album = info.meta_get("album", 0);
count = info.meta_get_count_by_name("title");
if (count == 0)
continue;
// Get TITLE
title = info.meta_get("title", 0);
count = info.meta_get_count_by_name("artist");
bool found = false;
// Iterate through all artists listed
for (int j = 0; j < count && !found; j++)
{
// Get Artist
artist = info.meta_get("artist", j);
keywords = artist;
keywords += "+";
keywords += album;
keywords.replace_char(' ', '+');
// Get it now
try
{
fetcher.fetch_googleluck(site, keywords, buff);
}
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 | SINGLELINE);
// 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);
if (temp.find_first(title) != -1)
{
jump_to = no;
break;
}
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');
console::print(lyric);
str_list->add_item(lyric);
found = true;
continue;
}
}
}
if (found)
continue;
else
str_list->add_item("");
}
}
catch (pfc::exception & e)
{
console_error(e.what());
delete str_list;
return NULL;
}
catch (...)
{
delete str_list;
return NULL;
}
return str_list;
}