cppcheck/lib/token.cpp

713 lines
17 KiB
C++
Raw Normal View History

2008-12-18 22:28:57 +01:00
/*
* Cppcheck - A tool for static C/C++ code analysis
* Copyright (C) 2007-2010 Daniel Marjamäki and Cppcheck team.
2008-12-18 22:28:57 +01:00
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
2008-12-18 22:28:57 +01:00
*/
#include "token.h"
#include "errorlogger.h"
#include "check.h"
#include <cassert>
2008-12-18 22:28:57 +01:00
#include <cstdlib>
#include <cstring>
#include <string>
#include <iostream>
#include <cctype>
#include <sstream>
#include <map>
Token::Token(Token **t) :
2010-04-15 20:08:51 +02:00
tokensBack(t),
_str(""),
_isName(false),
_isNumber(false),
_isBoolean(false),
_isUnsigned(false),
_isSigned(false),
_isLong(false),
_isUnused(false),
2010-04-15 20:08:51 +02:00
_varId(0),
_next(0),
_previous(0),
_link(0),
_fileIndex(0),
_linenr(0)
2008-12-18 22:28:57 +01:00
{
}
Token::~Token()
2008-12-18 22:28:57 +01:00
{
2008-12-18 22:28:57 +01:00
}
void Token::str(const std::string &s)
2008-12-18 22:28:57 +01:00
{
_str = s;
_isName = bool(_str[0] == '_' || std::isalpha(_str[0]));
if (std::isdigit(_str[0]))
_isNumber = true;
else if (_str.length() > 1 && _str[0] == '-' && std::isdigit(_str[1]))
_isNumber = true;
else
_isNumber = false;
if (_str == "true" || _str == "false")
_isBoolean = true;
else
_isBoolean = false;
2008-12-18 22:28:57 +01:00
_varId = 0;
}
void Token::concatStr(std::string const& b)
{
_str.erase(_str.length() - 1);
_str.append(b.begin() + 1, b.end());
}
std::string Token::strValue() const
{
assert(_str.length() >= 2);
assert(_str[0] == '"');
assert(_str[_str.length()-1] == '"');
return _str.substr(1, _str.length() - 2);
}
void Token::deleteNext()
2008-12-18 22:28:57 +01:00
{
Token *n = _next;
2008-12-18 22:28:57 +01:00
_next = n->next();
delete n;
if (_next)
2008-12-18 22:28:57 +01:00
_next->previous(this);
else if (tokensBack)
*tokensBack = this;
2008-12-18 22:28:57 +01:00
}
void Token::deleteThis()
{
if (_next)
{
_str = _next->_str;
_isName = _next->_isName;
_isNumber = _next->_isNumber;
_isBoolean = _next->_isBoolean;
_isUnused = _next->_isUnused;
_varId = _next->_varId;
_fileIndex = _next->_fileIndex;
_linenr = _next->_linenr;
_link = _next->_link;
if (_link)
_link->link(this);
deleteNext();
}
else if (_previous)
{
// This should never be used for tokens
// at the end of the list
str(";");
}
else
{
// We are the last token in the list, we can't delete
// ourselves, so just make us ;
str(";");
}
}
void Token::replace(Token *replaceThis, Token *start, Token *end)
{
// Fix the whole in the old location of start and end
if (start->previous())
start->previous()->next(end->next());
if (end->next())
end->next()->previous(start->previous());
// Move start and end to their new location
if (replaceThis->previous())
replaceThis->previous()->next(start);
if (replaceThis->next())
replaceThis->next()->previous(end);
start->previous(replaceThis->previous());
end->next(replaceThis->next());
if (end->tokensBack && *(end->tokensBack) == end)
{
while (end->next())
end = end->next();
*(end->tokensBack) = end;
}
// Delete old token, which is replaced
delete replaceThis;
}
const Token *Token::tokAt(int index) const
2008-12-18 22:28:57 +01:00
{
const Token *tok = this;
int num = std::abs(index);
while (num > 0 && tok)
2008-12-18 22:28:57 +01:00
{
if (index > 0)
tok = tok->next();
else
tok = tok->previous();
--num;
2008-12-18 22:28:57 +01:00
}
return tok;
}
2009-01-20 07:20:55 +01:00
Token *Token::tokAt(int index)
{
Token *tok = this;
int num = std::abs(index);
while (num > 0 && tok)
2009-01-20 07:20:55 +01:00
{
if (index > 0)
tok = tok->next();
else
tok = tok->previous();
--num;
2009-01-20 07:20:55 +01:00
}
return tok;
}
std::string Token::strAt(int index) const
2008-12-18 22:28:57 +01:00
{
const Token *tok = this->tokAt(index);
return tok ? tok->_str.c_str() : "";
2008-12-18 22:28:57 +01:00
}
int Token::multiCompare(const char *haystack, const char *needle)
2008-12-18 22:28:57 +01:00
{
bool emptyStringFound = false;
bool noMatch = false;
const char *needlePointer = needle;
for (; *haystack && *haystack != ' '; ++haystack)
2008-12-18 22:28:57 +01:00
{
if (*haystack == '|')
2008-12-18 22:28:57 +01:00
{
if (noMatch)
{
// We didn't have a match at this round
noMatch = false;
}
else if (*needlePointer == 0)
{
// If needle and haystack are both at the end, we have a match.
2008-12-18 22:28:57 +01:00
return 1;
}
else if (needlePointer == needle)
{
// If needlePointer was not increased at all, we had a empty
// string in the haystack
2008-12-18 22:28:57 +01:00
emptyStringFound = true;
}
2008-12-18 22:28:57 +01:00
needlePointer = needle;
2008-12-18 22:28:57 +01:00
continue;
}
if (noMatch)
2008-12-18 22:28:57 +01:00
continue;
// If haystack and needle don't share the same character,
// find next '|' character.
if (*needlePointer != *haystack)
2008-12-18 22:28:57 +01:00
{
noMatch = true;
2008-12-18 22:28:57 +01:00
continue;
}
// All characters in haystack and needle have matched this far
++needlePointer;
2008-12-18 22:28:57 +01:00
}
if (!noMatch)
{
if (*needlePointer == 0)
{
// If both needle and haystack are at the end, then we have a match.
return 1;
}
else if (needlePointer == needle)
{
// Last string in haystack was empty string e.g. "one|two|"
return 0;
}
}
// If empty string was found earlier from the haystack
if (emptyStringFound)
2008-12-18 22:28:57 +01:00
return 0;
return -1;
}
bool Token::simpleMatch(const Token *tok, const char pattern[])
{
const char *current, *next;
current = pattern;
2008-12-25 19:24:57 +01:00
next = strchr(pattern, ' ');
if (!next)
next = pattern + strlen(pattern);
while (*current)
{
size_t length = static_cast<size_t>(next - current);
if (!tok || length != tok->_str.length() || strncmp(current, tok->_str.c_str(), length))
return false;
current = next;
if (*next)
2008-12-25 19:24:57 +01:00
{
next = strchr(++current, ' ');
if (!next)
2008-12-25 19:24:57 +01:00
next = current + strlen(current);
}
tok = tok->next();
}
return true;
}
int Token::firstWordEquals(const char *str, const char *word)
{
for (;;)
{
if (*str == ' ' && *word == 0)
return 0;
else if (*str != *word)
return 1;
else if (*str == 0)
break;
++str;
++word;
}
return 0;
}
const char *Token::chrInFirstWord(const char *str, char c)
{
for (;;)
{
if (*str == ' ' || *str == 0)
return 0;
if (*str == c)
return str;
++str;
}
}
int Token::firstWordLen(const char *str)
{
int len = 0;
for (;;)
{
if (*str == ' ' || *str == 0)
break;
++len;
++str;
}
return len;
}
bool Token::Match(const Token *tok, const char pattern[], unsigned int varid)
2008-12-18 22:28:57 +01:00
{
const char *p = pattern;
bool firstpattern = true;
bool first = true;
while (*p)
2008-12-18 22:28:57 +01:00
{
if (!first)
{
while (*p && *p != ' ')
++p;
}
first = false;
2008-12-18 22:28:57 +01:00
// Skip spaces in pattern..
while (*p == ' ')
2009-01-01 23:22:28 +01:00
++p;
2008-12-18 22:28:57 +01:00
// No token => Success!
if (*p == 0)
2008-12-18 22:28:57 +01:00
return true;
if (!tok)
{
// If we have no tokens, pattern "!!else" should return true
if (p[1] == '!' && p[0] == '!' && p[2] != '\0')
continue;
else
return false;
}
// If we are in the first token, we skip all initial !! patterns
if (firstpattern && !tok->previous() && tok->next() && p[1] == '!' && p[0] == '!' && p[2] != '\0')
continue;
firstpattern = false;
// Compare the first character of the string for optimization reasons
// before doing more detailed checks.
bool patternIdentified = false;
if (p[0] == '%')
2008-12-18 22:28:57 +01:00
{
// TODO: %var% should match only for
// variables that have varId != 0, but that needs a lot of
// work, before that change can be made.
// Any symbolname..
if (firstWordEquals(p, "%var%") == 0)
{
if (!tok->isName())
return false;
2008-12-18 22:28:57 +01:00
patternIdentified = true;
}
2008-12-18 22:28:57 +01:00
// Type..
else if (firstWordEquals(p, "%type%") == 0)
{
if (!tok->isName())
return false;
if (tok->varId() != 0)
return false;
if (tok->str() == "delete")
return false;
patternIdentified = true;
}
// Accept any token
else if (firstWordEquals(p, "%any%") == 0)
{
patternIdentified = true;
}
2008-12-18 22:28:57 +01:00
else if (firstWordEquals(p, "%varid%") == 0)
{
if (varid == 0)
{
std::list<ErrorLogger::ErrorMessage::FileLocation> locationList;
const ErrorLogger::ErrorMessage errmsg(locationList,
Severity::error,
"Internal error. Token::Match called with varid 0.",
"cppcheckError");
Check::reportError(errmsg);
}
if (tok->varId() != varid)
2008-12-18 22:28:57 +01:00
return false;
patternIdentified = true;
}
else if (firstWordEquals(p, "%num%") == 0)
{
if (!tok->isNumber())
2008-12-18 22:28:57 +01:00
return false;
patternIdentified = true;
2008-12-18 22:28:57 +01:00
}
else if (firstWordEquals(p, "%bool%") == 0)
{
if (!tok->isBoolean())
return false;
2008-12-18 22:28:57 +01:00
patternIdentified = true;
}
2008-12-18 22:28:57 +01:00
else if (firstWordEquals(p, "%str%") == 0)
{
if (tok->_str[0] != '\"')
return false;
patternIdentified = true;
}
}
2008-12-18 22:28:57 +01:00
if (patternIdentified)
2008-12-18 22:28:57 +01:00
{
// Pattern was identified already above.
2008-12-18 22:28:57 +01:00
}
// [.. => search for a one-character token..
else if (p[0] == '[' && chrInFirstWord(p, ']') && tok->_str.length() == 1)
2008-12-18 22:28:57 +01:00
{
const char *temp = p + 1;
bool chrFound = false;
int count = 0;
while (*temp && *temp != ' ')
{
if (*temp == ']')
{
++count;
++temp;
continue;
}
if (*temp == tok->_str[0])
{
chrFound = true;
break;
}
++temp;
}
if (count > 1)
{
if (tok->_str[0] == ']')
chrFound = true;
}
if (!chrFound)
2008-12-18 22:28:57 +01:00
return false;
}
// Parse multi options, such as void|int|char (accept token which is one of these 3)
else if (chrInFirstWord(p, '|') && (p[0] != '|' || firstWordLen(p) > 2))
2008-12-18 22:28:57 +01:00
{
int res = multiCompare(p, tok->_str.c_str());
if (res == 0)
2008-12-18 22:28:57 +01:00
{
// Empty alternative matches, use the same token on next round
continue;
}
else if (res == -1)
2008-12-18 22:28:57 +01:00
{
// No match
return false;
}
}
// Parse "not" options. Token can be anything except the given one
else if (p[1] == '!' && p[0] == '!' && p[2] != '\0')
2008-12-18 22:28:57 +01:00
{
if (firstWordEquals(&(p[2]), tok->str().c_str()) == 0)
2008-12-18 22:28:57 +01:00
return false;
}
else if (firstWordEquals(p, tok->_str.c_str()) != 0)
2008-12-18 22:28:57 +01:00
return false;
tok = tok->next();
}
// The end of the pattern has been reached and nothing wrong has been found
return true;
}
size_t Token::getStrLength(const Token *tok)
{
assert(tok != NULL);
size_t len = 0;
const std::string strValue(tok->strValue());
const char *str = strValue.c_str();
while (*str)
{
if (*str == '\\')
{
++str;
// string ends at '\0'
if (*str == '0')
break;
}
++str;
++len;
}
return len;
}
bool Token::isStandardType() const
2008-12-18 22:28:57 +01:00
{
bool ret = false;
const char *type[] = {"bool", "char", "short", "int", "long", "float", "double", "size_t", "__int64", 0};
for (int i = 0; type[i]; i++)
2008-12-18 22:28:57 +01:00
ret |= (_str == type[i]);
return ret;
}
bool Token::isIntegerType() const
{
bool ret = false;
const char *type[] = {"char", "short", "int", "long", "size_t", "__int64", 0};
for (int i = 0; type[i]; i++)
ret |= (_str == type[i]);
return ret;
}
void Token::move(Token *srcStart, Token *srcEnd, Token *newLocation)
{
/**[newLocation] -> b -> c -> [srcStart] -> [srcEnd] -> f */
// Fix the gap, which tokens to be moved will leave
srcStart->previous()->next(srcEnd->next());
srcEnd->next()->previous(srcStart->previous());
// Fix the tokens to be moved
srcEnd->next(newLocation->next());
srcStart->previous(newLocation);
// Fix the tokens at newLocation
newLocation->next()->previous(srcEnd);
newLocation->next(srcStart);
}
2008-12-18 22:28:57 +01:00
//---------------------------------------------------------------------------
const Token *Token::findmatch(const Token *tok, const char pattern[], unsigned int varId)
{
for (; tok; tok = tok->next())
{
if (Token::Match(tok, pattern, varId))
return tok;
}
return 0;
}
2010-04-09 21:40:37 +02:00
void Token::insertToken(const std::string &tokenStr)
2008-12-18 22:28:57 +01:00
{
Token *newToken = new Token(tokensBack);
2010-04-09 21:40:37 +02:00
newToken->str(tokenStr);
newToken->_linenr = _linenr;
2008-12-18 22:28:57 +01:00
newToken->_fileIndex = _fileIndex;
if (this->next())
2008-12-18 22:28:57 +01:00
{
newToken->next(this->next());
newToken->next()->previous(newToken);
2008-12-18 22:28:57 +01:00
}
else if (tokensBack)
{
*tokensBack = newToken;
}
2008-12-18 22:28:57 +01:00
this->next(newToken);
newToken->previous(this);
2008-12-18 22:28:57 +01:00
}
void Token::eraseTokens(Token *begin, const Token *end)
2008-12-18 22:28:57 +01:00
{
if (! begin)
2008-12-18 22:28:57 +01:00
return;
while (begin->next() && begin->next() != end)
2008-12-18 22:28:57 +01:00
{
begin->deleteNext();
}
}
void Token::createMutualLinks(Token *begin, Token *end)
{
assert(begin != NULL);
assert(end != NULL);
assert(begin != end);
begin->link(end);
end->link(begin);
}
void Token::printOut(const char *title) const
2008-12-18 22:28:57 +01:00
{
const std::vector<std::string> fileNames;
std::cout << stringifyList(true, title, fileNames) << std::endl;
}
void Token::printOut(const char *title, const std::vector<std::string> &fileNames) const
{
std::cout << stringifyList(true, title, fileNames) << std::endl;
2008-12-18 22:28:57 +01:00
}
std::string Token::stringifyList(bool varid, const char *title) const
{
const std::vector<std::string> fileNames;
return stringifyList(varid, title, fileNames);
}
std::string Token::stringifyList(bool varid, const char *title, const std::vector<std::string> &fileNames) const
{
std::ostringstream ret;
if (title)
ret << "\n### " << title << " ###\n";
2010-04-09 21:40:37 +02:00
unsigned int lineNumber = 0;
int fileInd = -1;
std::map<unsigned int, unsigned int> lineNumbers;
for (const Token *tok = this; tok; tok = tok->next())
{
bool fileChange = false;
2010-04-09 21:40:37 +02:00
if (static_cast<int>(tok->_fileIndex) != fileInd)
{
2010-04-09 21:40:37 +02:00
if (fileInd != -1)
{
2010-04-09 21:40:37 +02:00
lineNumbers[fileInd] = tok->_fileIndex;
}
2010-04-09 21:40:37 +02:00
fileInd = static_cast<int>(tok->_fileIndex);
ret << "\n\n##file ";
2010-04-09 21:40:37 +02:00
if (fileNames.size() > static_cast<unsigned int>(fileInd))
ret << fileNames.at(fileInd);
else
2010-04-09 21:40:37 +02:00
ret << fileInd;
2010-04-09 21:40:37 +02:00
lineNumber = lineNumbers[fileInd];
fileChange = true;
}
2010-04-09 21:40:37 +02:00
if (lineNumber != tok->linenr() || fileChange)
{
2010-04-09 21:40:37 +02:00
while (lineNumber < tok->linenr())
{
2010-04-09 21:40:37 +02:00
++lineNumber;
ret << "\n" << lineNumber << ":";
}
2010-04-09 21:40:37 +02:00
lineNumber = tok->linenr();
}
ret << " " << tok->str();
if (varid && tok->varId() > 0)
ret << "@" << tok->varId();
}
ret << "\n";
return ret.str();
}