X-Git-Url: https://git.saurik.com/apt.git/blobdiff_plain/37cc828e003f51d63ed991be5acac36765b8230a..070536e61cb203a9c74013be2a26322b582a9674:/apt-pkg/contrib/strutl.cc diff --git a/apt-pkg/contrib/strutl.cc b/apt-pkg/contrib/strutl.cc index 9726138a0..2100ee47b 100644 --- a/apt-pkg/contrib/strutl.cc +++ b/apt-pkg/contrib/strutl.cc @@ -21,6 +21,11 @@ #include #include +#include +#include +#include +#include +#include #include #include #include @@ -33,10 +38,33 @@ #include #include - -using namespace std; /*}}}*/ +using namespace std; + +// Strip - Remove white space from the front and back of a string /*{{{*/ +// --------------------------------------------------------------------- +namespace APT { + namespace String { +std::string Strip(const std::string &s) +{ + size_t start = s.find_first_not_of(" \t\n"); + // only whitespace + if (start == string::npos) + return ""; + size_t end = s.find_last_not_of(" \t\n"); + return s.substr(start, end-start+1); +} + +bool Endswith(const std::string &s, const std::string &end) +{ + if (end.size() > s.size()) + return false; + return (s.substr(s.size() - end.size(), s.size()) == end); +} +} +} + /*}}}*/ // UTF8ToCodeset - Convert some UTF-8 string for some codeset /*{{{*/ // --------------------------------------------------------------------- /* This is handy to use before display some information for enduser */ @@ -130,7 +158,7 @@ char *_strrstrip(char *String) End++; *End = 0; return String; -}; +} /*}}}*/ // strtabexpand - Converts tabs into 8 spaces /*{{{*/ // --------------------------------------------------------------------- @@ -403,7 +431,7 @@ string TimeToStr(unsigned long Sec) /*}}}*/ // SubstVar - Substitute a string for another string /*{{{*/ // --------------------------------------------------------------------- -/* This replaces all occurances of Subst with Contents in Str. */ +/* This replaces all occurrences of Subst with Contents in Str. */ string SubstVar(const string &Str,const string &Subst,const string &Contents) { string::size_type Pos = 0; @@ -758,7 +786,8 @@ bool ReadMessages(int Fd, vector &List) // Look for the end of the message for (char *I = Buffer; I + 1 < End; I++) { - if (I[0] != '\n' || I[1] != '\n') + if (I[1] != '\n' || + (I[0] != '\n' && strncmp(I, "\r\n\r\n", 4) != 0)) continue; // Pull the message out @@ -766,7 +795,7 @@ bool ReadMessages(int Fd, vector &List) PartialMessage += Message; // Fix up the buffer - for (; I < End && *I == '\n'; I++); + for (; I < End && (*I == '\n' || *I == '\r'); ++I); End -= I-Buffer; memmove(Buffer,I,End-Buffer); I = Buffer; @@ -902,7 +931,7 @@ bool FTPMDTMStrToTime(const char* const str,time_t &time) /*}}}*/ // StrToTime - Converts a string into a time_t /*{{{*/ // --------------------------------------------------------------------- -/* This handles all 3 populare time formats including RFC 1123, RFC 1036 +/* This handles all 3 popular time formats including RFC 1123, RFC 1036 and the C library asctime format. It requires the GNU library function 'timegm' to convert a struct tm in UTC to a time_t. For some bizzar reason the C library does not provide any such function :< This also @@ -942,6 +971,8 @@ bool StrToTime(const string &Val,time_t &Result) Tm.tm_isdst = 0; if (Month[0] != 0) Tm.tm_mon = MonthConv(Month); + else + Tm.tm_mon = 0; // we don't have a month, so pick something Tm.tm_year -= 1900; // Convert to local time and then to GMT @@ -1104,9 +1135,11 @@ bool TokSplitString(char Tok,char *Input,char **List, also, but the advantage is that we have an iteratable vector */ vector VectorizeString(string const &haystack, char const &split) { + vector exploded; + if (haystack.empty() == true) + return exploded; string::const_iterator start = haystack.begin(); string::const_iterator end = start; - vector exploded; do { for (; end != haystack.end() && *end != split; ++end); exploded.push_back(string(start, end)); @@ -1115,6 +1148,37 @@ vector VectorizeString(string const &haystack, char const &split) return exploded; } /*}}}*/ +// StringSplit - split a string into a string vector by token /*{{{*/ +// --------------------------------------------------------------------- +/* See header for details. + */ +vector StringSplit(std::string const &s, std::string const &sep, + unsigned int maxsplit) +{ + vector split; + size_t start, pos; + + // no seperator given, this is bogus + if(sep.size() == 0) + return split; + + start = pos = 0; + while (pos != string::npos) + { + pos = s.find(sep, start); + split.push_back(s.substr(start, pos-start)); + + // if maxsplit is reached, the remaining string is the last item + if(split.size() >= maxsplit) + { + split[split.size()-1] = s.substr(start); + break; + } + start = pos+sep.size(); + } + return split; +} + /*}}}*/ // RegexChoice - Simple regex list/list matcher /*{{{*/ // --------------------------------------------------------------------- /* */ @@ -1125,7 +1189,7 @@ unsigned long RegexChoice(RxChoiceList *Rxs,const char **ListBegin, R->Hit = false; unsigned long Hits = 0; - for (; ListBegin != ListEnd; ListBegin++) + for (; ListBegin < ListEnd; ++ListBegin) { // Check if the name is a regex const char *I; @@ -1232,12 +1296,12 @@ char *safe_snprintf(char *Buffer,char *End,const char *Format,...) va_list args; int Did; - va_start(args,Format); - if (End <= Buffer) return End; - + va_start(args,Format); Did = vsnprintf(Buffer,End - Buffer,Format,args); + va_end(args); + if (Did < 0 || Buffer + Did > End) return End; return Buffer + Did; @@ -1252,11 +1316,11 @@ string StripEpoch(const string &VerStr) return VerStr; return VerStr.substr(i+1); } - + /*}}}*/ // tolower_ascii - tolower() function that ignores the locale /*{{{*/ // --------------------------------------------------------------------- /* This little function is the most called method we have and tries - therefore to do the absolut minimum - and is noteable faster than + therefore to do the absolut minimum - and is notable faster than standard tolower/toupper and as a bonus avoids problems with different locales - we only operate on ascii chars anyway. */ int tolower_ascii(int const c) @@ -1267,9 +1331,9 @@ int tolower_ascii(int const c) } /*}}}*/ -// CheckDomainList - See if Host is in a , seperate list /*{{{*/ +// CheckDomainList - See if Host is in a , separate list /*{{{*/ // --------------------------------------------------------------------- -/* The domain list is a comma seperate list of domains that are suffix +/* The domain list is a comma separate list of domains that are suffix matched against the argument */ bool CheckDomainList(const string &Host,const string &List) { @@ -1290,14 +1354,26 @@ bool CheckDomainList(const string &Host,const string &List) return false; } /*}}}*/ -// DeEscapeString - unescape (\0XX and \xXX) from a string /*{{{*/ +// strv_length - Return the length of a NULL-terminated string array /*{{{*/ +// --------------------------------------------------------------------- +/* */ +size_t strv_length(const char **str_array) +{ + size_t i; + for (i=0; str_array[i] != NULL; i++) + /* nothing */ + ; + return i; +} + +// DeEscapeString - unescape (\0XX and \xXX) from a string /*{{{*/ // --------------------------------------------------------------------- /* */ string DeEscapeString(const string &input) { char tmp[3]; - string::const_iterator it, escape_start; - string output, octal, hex; + string::const_iterator it; + string output; for (it = input.begin(); it != input.end(); ++it) { // just copy non-escape chars @@ -1483,9 +1559,12 @@ URI::operator string() if (User.empty() == false) { - Res += User; + // FIXME: Technically userinfo is permitted even less + // characters than these, but this is not conveniently + // expressed with a blacklist. + Res += QuoteString(User, ":/?#[]@"); if (Password.empty() == false) - Res += ":" + Password; + Res += ":" + QuoteString(Password, ":/?#[]@"); Res += "@"; } @@ -1524,7 +1603,6 @@ string URI::SiteOnly(const string &URI) U.User.clear(); U.Password.clear(); U.Path.clear(); - U.Port = 0; return U; } /*}}}*/ @@ -1536,7 +1614,6 @@ string URI::NoUserPassword(const string &URI) ::URI U(URI); U.User.clear(); U.Password.clear(); - U.Port = 0; return U; } /*}}}*/