int
stricmp(const char *s1, const char *s2)
{ while(*s1 && makeLower(*s1) == makeLower(*s2))
s1++, s2++;
return makeLower(*s1) - makeLower(*s2);
}
static bool
differentSeparated(register char *s1, register char *s2)
{ register char c1, c2;
if ( *s1 != *s2 || *s1 == EOS )
fail;
c1 = *++s1, c2 = *++s2;
while(c1 && c1 == c2)
{ if ((c1 = *++s1) == '_')
{ c1 = *++s1;
} else
{ if (isLower(s1[-1]) && isUpper(c1))
c1 = makeLower(c1);
}
if ((c2 = *++s2) == '_')
{ c2 = *++s2;
} else
{ if (isLower(s2[-1]) && isUpper(c2))
c2 = makeLower(c2);
}
}
if (c1 == EOS && c2 == EOS)
succeed;
fail;
}
void BisonCSSParser::tokenToLowerCase(CSSParserString& token)
{
// Since it's our internal token, we know that we created it out
// of our writable work buffers. Therefore the const_cast is just
// ugly and not a potential crash.
size_t length = token.length();
if (token.is8Bit()) {
makeLower(token.characters8(), const_cast<LChar*>(token.characters8()), length);
} else {
makeLower(token.characters16(), const_cast<UChar*>(token.characters16()), length);
}
}
int
strcasecmp(const char *s1, const char *s2)
{
#ifdef HAVE_STRICMP
return stricmp(s1, s2);
#else
while(*s1 && makeLower(*s1) == makeLower(*s2))
s1++, s2++;
return makeLower(*s1) - makeLower(*s2);
#endif
}
BOOL CutupProtocol::Str2CPGuid( LPCTSTR str, CPGUID& cpguid )
{
tstring s = str;
if (s.size() != 32) return FALSE;
LPBYTE p = (LPBYTE) &cpguid;
makeLower(s);
for (int i = 0; i < 32; i+=2, p++)
{
BYTE b = 0;
TCHAR ch = s[i];
if (ch >= '0' && ch <= '9') b = ch - '0';
else if (ch >= 'a' && ch <= 'f') b = ch - 'a' + 10;
b <<= 4;
ch = s[i + 1];
if (ch >= '0' && ch <= '9') b |= ch - '0';
else if (ch >= 'a' && ch <= 'f') b |= ch - 'a' + 10;
*p = b;
}
return TRUE;
}
void FTSSpec::_scoreStringV2( const Tools& tools,
StringData raw,
TermFrequencyMap* docScores,
double weight ) const {
ScoreHelperMap terms;
unsigned numTokens = 0;
Tokenizer i( tools.language, raw );
while ( i.more() ) {
Token t = i.next();
if ( t.type != Token::TEXT )
continue;
string term = t.data.toString();
makeLower( &term );
if ( tools.stopwords->isStopWord( term ) ) {
continue;
}
term = tools.stemmer->stem( term );
ScoreHelperStruct& data = terms[term];
if ( data.exp ) {
data.exp *= 2;
}
else {
data.exp = 1;
}
data.count += 1;
data.freq += ( 1 / data.exp );
numTokens++;
}
for ( ScoreHelperMap::const_iterator i = terms.begin(); i != terms.end(); ++i ) {
const string& term = i->first;
const ScoreHelperStruct& data = i->second;
// in order to adjust weights as a function of term count as it
// relates to total field length. ie. is this the only word or
// a frequently occuring term? or does it only show up once in
// a long block of text?
double coeff = ( 0.5 * data.count / numTokens ) + 0.5;
// if term is identical to the raw form of the
// field (untokenized) give it a small boost.
double adjustment = 1;
if ( raw.size() == term.length() && raw.equalCaseInsensitive( term ) )
adjustment += 0.1;
double& score = (*docScores)[term];
score += ( weight * data.freq * coeff * adjustment );
verify( score <= MAX_WEIGHT );
}
}
char *
strlwr(char *s)
{ char *q;
for(q=s; *q; q++)
*q = makeLower(*q);
return s;
}
void SearchEng::add_parse_page(std::string filename,
PageParser* parser) {
MySetString currentWords;
MySetString currentLinks_strings;
parser->parse(filename, currentWords, currentLinks_strings);
std::cout << "Just ran parse" << std::endl;
WebPage* currentPage = new WebPage;
currentPage->filename( filename );
currentPage->all_words(currentWords);
for( MySetString::iterator it = currentLinks_strings.begin(); it != currentLinks_strings.end(); ++it) {
currentPage->add_outgoing_link(looks_for_webpage(*it));
//Need to deal with links still
/*MySetString::iterator it2 = allPages.find(*it);
if(it2 != allPages.end() ) {
currentPage->add_outgoing_link(it);
}*/
}
allPages.insert(currentPage);
// std::cout << "inserted page" << std::endl; //debug
MySetString::iterator it;
for( it = currentWords.begin(); it != currentWords.end(); ++it ) { // makes wordMap;
std::string word = *it;
makeLower(word);
std::map<std::string, MySetWebPage>::iterator it2 = wordMap.find(word);
//std::cout << "trying to insert: " << word << std::endl; //debug
if(it2 != wordMap.end()) {
it2->second.insert(currentPage);
//std::cout << "added page to " << it2->first << std::endl; //debug
} else {
MySetWebPage newSet;
newSet.insert( currentPage );
wordMap.insert( make_pair(word, newSet));
//std::cout << "inserted: " << word << std::endl; //debug
}
//std::cout << "went through for loop" << std::endl; //debug
}
//deals with all incoming links;
MySetWebPage::iterator it3;
for( it3 = allPages.begin(); it3!= allPages.end(); ++it3) {
WebPage* outgoingPage = *it3;
MySetWebPage outgoingLinks = outgoingPage->outgoing_links();
MySetWebPage::iterator it4;
for( it4 = outgoingLinks.begin(); it4 != outgoingLinks.end(); ++it4) {
WebPage* incomingPage = *it4;
incomingPage->add_incoming_link(outgoingPage);
}
}
//delete currentPage;
return;
}
BOOL ClientInfoManager::InstallModule( LPCTSTR clientid, LPCTSTR moduleName )
{
tstring modname = moduleName;
makeLower(modname);
tstring datFilepath;
if (! ClientmodManager::GetInstanceRef().GetModuleDatFilepath(modname.c_str(), datFilepath))
{
errorLog(_T("no such clientmodule [%s]"), moduleName);
return FALSE;
}
CommData sendData;
sendData.SetMsgID(MSGID_INSTALL_MODULE);
sendData.SetData(_T("modname"), moduleName);
if (! ReadDataFile(datFilepath.c_str(), sendData))
{
errorLog(_T("read datafile failed[%s]"), datFilepath.c_str());
return FALSE;
}
MSGSERIALID requestInstallModMsgID = CommManager::GetInstanceRef().AddToSendMessage(clientid, sendData, TRUE);
if (INVALID_MSGSERIALID == requestInstallModMsgID)
{
errorLog(_T("send msg to install mod[%s] in [%s] failed"), moduleName, clientid);
return FALSE;
}
BOOL bPushOK = FALSE;
m_infoMapSection.Enter();
{
ClientBaseInfoMap::iterator iter = m_clientBaseInfoMap.find(clientid);
if (iter != m_clientBaseInfoMap.end())
{
iter->second.installModMsgIDMap[moduleName] = requestInstallModMsgID;
bPushOK = TRUE;
}
}
m_infoMapSection.Leave();
if (bPushOK)
{
infoLog(_T("send install msg OK. install mod[%s] to [%s]"), moduleName, clientid);
}
else
{
errorLog(_T("send install msg OK.id=%I64u. but no info for client[%s]"), requestInstallModMsgID, clientid);
}
return TRUE;
}
BOOL CommandManager::Execute( LPCTSTR cmdline, tstring& replyText )
{
//分割并整理命令行的各个部分
TStringVector parts;
splitByChar(cmdline, parts, ' ');
TStringVector::iterator iter = parts.begin();
while (iter != parts.end())
{
tstring& part = *iter;
trim(part);
if (part.size() == 0)
{
iter = parts.erase(iter);
}
else
{
iter++;
}
}
//检查是否有可用的部分
if (parts.size() == 0)
{
replyText = _T("invalid command.");
return FALSE;
}
//查找可用的命令
tstring& cmdname = parts[0];
makeLower(cmdname);
CommandMap::iterator cmdIter = m_cmdMap.find(cmdname);
if (cmdIter == m_cmdMap.end())
{
replyText = _T("no such command.");
return FALSE;
}
//执行命令
ICmd* pCmd = cmdIter->second;
BOOL bExecuteOK = pCmd->Execute(parts, replyText, m_env);
return bExecuteOK;
}
static char *
subWord(register char *s, register char *store)
{ *store++ = makeLower(*s);
s++;
for(;;)
{ if (*s == EOS)
{ *store = EOS;
return s;
}
if (*s == '_')
{ *store = EOS;
return ++s;
}
if (isLower(s[-1]) && isUpper(s[0]) )
{ *store = EOS;
return s;
}
*store++ = *s++;
}
}
std::string xlw::StringUtilities::toLower(std::string inputString)
{
makeLower(inputString);
return inputString;
}
BOOL Shell::ExecuteCommand( LPCTSTR cmdlinestr, tstring& reply )
{
//分割并整理命令行的各个部分
tstring cmdline = cmdlinestr;
trim(cmdline, ' ');
trim(cmdline, '\n');
trim(cmdline, '\r');
TStringVector parts;
splitByChar(cmdline.c_str(), parts, ' ');
//清理无效参数
TStringVector::iterator iter = parts.begin();
while (iter != parts.end())
{
tstring& part = *iter;
trim(part);
if (part.size() == 0)
{
iter = parts.erase(iter);
}
else
{
iter++;
}
}
//检查是否有可用的部分
if (parts.size() == 0)
{
reply = _T("");
return TRUE;
}
//查找可用的命令
tstring& cmdname = parts[0];
makeLower(cmdname);
if (cmdname == _T("dir"))
{
return Execute_Dir(parts, reply);
}
else if (cmdname == _T("cd"))
{
return Execute_Cd(parts, reply);
}
else if (cmdname == _T("disks"))
{
return Execute_Disks(parts, reply);
}
//将命令发到客户端去执行
CommData commandCommData;
commandCommData.SetMsgID(MSGID_EXECUTE_CMDLINE);
commandCommData.SetData(_T("cmdline"), cmdline.c_str());
CommData replyCommData;
if (! AskAndWaitForReply(commandCommData, replyCommData))
{
reply = _T("等待客户端回应超时");
return FALSE;
}
else
{
tstring result;
replyCommData.GetStrData(_T("result"), result);
if (result == _T("OK"))
{
reply = s2ws(std::string((LPCSTR)(LPBYTE)replyCommData.GetByteData(), replyCommData.GetByteData().Size()));
return TRUE;
}
else
{
reply = result;
return FALSE;
}
}
}
int main(int argc, char* arg[]){
int flag = 1;
char index_file[MAX_WORD_LEN];
char target_dir[MAX_WORD_LEN];
struct stat sb; // used for stat call
INVERTED_INDEX *index;
printf("starting the program\n");
// initialize the qholder for first time
initializeQHOLDER();
// initialize index
index = (INVERTED_INDEX*)malloc(sizeof(INVERTED_INDEX)+1);
if(index == NULL){
printf("No enough memory at %s:line%d ", __FILE__, __LINE__);
exit(-1);
}
bzero(index, sizeof(INVERTED_INDEX)+1);
index->start = index->end = NULL;
// input arg check
// check to see if the user inputs too many or too few args
if(argc != 3){
printf("You did not enter the correct number of arguments.\n");
exit(-1);
}
// copy in filename of the printed index
strcpy(index_file, arg[1]);
// set target directory and check if it's available
strcpy(target_dir, arg[2]);
stat(target_dir, &sb);
if(!S_ISDIR(sb.st_mode)){
printf("The directory you chose is not available.\n");
return 1;
}
// read file into new index -- now index is loaded from file
index = readFile(index_file);
// initialize user input variable
char *input;
input = malloc(sizeof(char)*(MAX_WORD_LEN+1));
if(index == NULL){
printf("No enough memory at %s:line%d ", __FILE__, __LINE__);
exit(-1);
}
bzero(input, MAX_WORD_LEN+1);
// Main while loop used in query - see psuedocode above
// Used to create a node for every word containing a list of the
// documents the word is in. Each node will contain the
// list of DOCUMENTNODES which contain the document id and
// the frequency of the word in that document.
int keepInWhile = 1;
while(keepInWhile){
// initialize the QHOLDER so it is empty for every search
// only want words in the qholder from each different search
flag = 0;
// prompt user for a query search
printf("\nTinySearch > ");
fgets(input, MAX_WORD_LEN, stdin);
if(strcmp(input, "c\n") == 0){
printf("You are now exitting the program.\n");
break;
}
printf("The word you are searching for is %s\n", input);
// load input words into list of words using getNextWord...
// create and zero word and list inputs will be written to
int currentPosition =0;
int i = 0;
char **wordList;
wordList = malloc(sizeof(char)*(MAX_WORD_LEN+1));
if(wordList == NULL){
printf("No enough memory at %s:line%d ", __FILE__, __LINE__); \
exit(-1);
}
bzero(wordList, MAX_WORD_LEN);
// Get a list of all the user input words to be searched.
// The list is called wordList and after getNextWord is called,
// the wordList will be loaded
getNextWord(input, currentPosition, wordList, i);
// initialize new word node to be set at the correct
// position in the index
WORDNODE *wn;
i = 0;
while(wordList[i] != NULL){
// if user wrote AND or OR, keep it in list, but don't add node
if(strcmp(wordList[i], "OR") == 0){
printf("continuing...\n");
i++;
continue;
} else if(strcmp(wordList[i], "AND") == 0){
printf("continuing...\n");
i++;
continue;
} else{
// find the wordnode form index for the current query word
makeLower(wordList[i]);
wn = searchIndex(&flag, wordList[i], index);
// this flag is for if the word was found or not. 1 is yes.
if(flag == 0){
printf("Word not found. Try again.\n");
break;
}
// add WORDNODE to the qholder to be used later
addWORDNODE(wn);
i++;
}
}
if(flag == 0)
continue;
if(rankWords(wordList, i) == 0){
continue;
}
printDOCs(target_dir);
bzero(input, MAX_WORD_LEN+1);
initializeQHOLDER();
}
return 0;
}
static char *compile_pattern(compiled_pattern *, char *, int);
static bool match_pattern(matchcode *, char *);
#define Output(c) { if ( Out->size > MAXCODE-1 ) \
{ warning("pattern too large"); \
return (char *) NULL; \
} \
Out->code[Out->size++] = c; \
}
static inline void
setMap(matchcode *map, int c)
{ GET_LD
if ( !truePrologFlag(PLFLAG_FILE_CASE) )
c = makeLower(c);
map[(c)/8] |= 1 << ((c) % 8);
}
static bool
compilePattern(char *p, compiled_pattern *cbuf)
{ cbuf->size = 0;
if ( compile_pattern(cbuf, p, NOCURL) == (char *) NULL )
fail;
succeed;
}
string toLower(const string & str)
{
string s(str);
makeLower(s);
return s;
}
