use hash instead of checksum to check if content is changed

Author: danmar

lib/analyzerinfo.cpp

@@ -72,7 +72,7 @@ void AnalyzerInformation::close()
     }
 }
 
-static bool skipAnalysis(const std::string &analyzerInfoFile, unsigned long long checksum, std::list<ErrorMessage> *errors)
+static bool skipAnalysis(const std::string &analyzerInfoFile, std::size_t hash, std::list<ErrorMessage> *errors)
 {
     tinyxml2::XMLDocument doc;
     const tinyxml2::XMLError error = doc.LoadFile(analyzerInfoFile.c_str());
@@ -83,8 +83,8 @@ static bool skipAnalysis(const std::string &analyzerInfoFile, unsigned long long
     if (rootNode == nullptr)
         return false;
 
-    const char *attr = rootNode->Attribute("checksum");
-    if (!attr || attr != std::to_string(checksum))
+    const char *attr = rootNode->Attribute("hash");
+    if (!attr || attr != std::to_string(hash))
         return false;
 
     for (const tinyxml2::XMLElement *e = rootNode->FirstChildElement(); e; e = e->NextSiblingElement()) {
@@ -125,21 +125,21 @@ std::string AnalyzerInformation::getAnalyzerInfoFile(const std::string &buildDir
     return filename;
 }
 
-bool AnalyzerInformation::analyzeFile(const std::string &buildDir, const std::string &sourcefile, const std::string &cfg, unsigned long long checksum, std::list<ErrorMessage> *errors)
+bool AnalyzerInformation::analyzeFile(const std::string &buildDir, const std::string &sourcefile, const std::string &cfg, std::size_t hash, std::list<ErrorMessage> *errors)
 {
     if (buildDir.empty() || sourcefile.empty())
         return true;
     close();
 
     mAnalyzerInfoFile = AnalyzerInformation::getAnalyzerInfoFile(buildDir,sourcefile,cfg);
 
-    if (skipAnalysis(mAnalyzerInfoFile, checksum, errors))
+    if (skipAnalysis(mAnalyzerInfoFile, hash, errors))
         return false;
 
     mOutputStream.open(mAnalyzerInfoFile);
     if (mOutputStream.is_open()) {
         mOutputStream << "<?xml version=\"1.0\"?>\n";
-        mOutputStream << "<analyzerinfo checksum=\"" << checksum << "\">\n";
+        mOutputStream << "<analyzerinfo hash=\"" << hash << "\">\n";
     } else {
         mAnalyzerInfoFile.clear();
     }

lib/analyzerinfo.h

@@ -54,7 +54,7 @@ class CPPCHECKLIB AnalyzerInformation {
 
     /** Close current TU.analyzerinfo file */
     void close();
-    bool analyzeFile(const std::string &buildDir, const std::string &sourcefile, const std::string &cfg, unsigned long long checksum, std::list<ErrorMessage> *errors);
+    bool analyzeFile(const std::string &buildDir, const std::string &sourcefile, const std::string &cfg, std::size_t hash, std::list<ErrorMessage> *errors);
     void reportErr(const ErrorMessage &msg, bool verbose);
     void setFileInfo(const std::string &check, const std::string &fileInfo);
     static std::string getAnalyzerInfoFile(const std::string &buildDir, const std::string &sourcefile, const std::string &cfg);

lib/cppcheck.cpp

@@ -707,10 +707,10 @@ unsigned int CppCheck::checkFile(const std::string& filename, const std::string
             toolinfo << mSettings.userDefines;
             mSettings.nomsg.dump(toolinfo);
 
-            // Calculate checksum so it can be compared with old checksum / future checksums
-            const unsigned int checksum = preprocessor.calculateChecksum(tokens1, toolinfo.str());
+            // Calculate hash so it can be compared with old hash / future hashes
+            const std::size_t hash = preprocessor.calculateHash(tokens1, toolinfo.str());
             std::list<ErrorMessage> errors;
-            if (!mAnalyzerInformation.analyzeFile(mSettings.buildDir, filename, cfgname, checksum, &errors)) {
+            if (!mAnalyzerInformation.analyzeFile(mSettings.buildDir, filename, cfgname, hash, &errors)) {
                 while (!errors.empty()) {
                     reportErr(errors.front());
                     errors.pop_front();
@@ -775,7 +775,7 @@ unsigned int CppCheck::checkFile(const std::string& filename, const std::string
             }
         }
 
-        std::set<unsigned long long> checksums;
+        std::set<unsigned long long> hashes;
         int checkCount = 0;
         bool hasValidConfig = false;
         std::list<std::string> configurationError;
@@ -871,18 +871,18 @@ unsigned int CppCheck::checkFile(const std::string& filename, const std::string
                     fdump << "</dump>" << std::endl;
                 }
 
-                // Need to call this even if the checksum will skip this configuration
+                // Need to call this even if the hash will skip this configuration
                 mSettings.nomsg.markUnmatchedInlineSuppressionsAsChecked(tokenizer);
 
                 // Skip if we already met the same simplified token list
                 if (mSettings.force || mSettings.maxConfigs > 1) {
-                    const unsigned long long checksum = tokenizer.list.calculateChecksum();
-                    if (checksums.find(checksum) != checksums.end()) {
+                    const std::size_t hash = tokenizer.list.calculateHash();
+                    if (hashes.find(hash) != hashes.end()) {
                         if (mSettings.debugwarnings)
                             purgedConfigurationMessage(filename, mCurrentConfig);
                         continue;
                     }
-                    checksums.insert(checksum);
+                    hashes.insert(hash);
                 }
 
                 // Check normal tokens

lib/preprocessor.cpp

@@ -30,6 +30,7 @@
 #include <algorithm>
 #include <cstddef>
 #include <cstdint>
+#include <functional>
 #include <iterator> // back_inserter
 #include <memory>
 #include <utility>
@@ -971,74 +972,20 @@ void Preprocessor::dump(std::ostream &out) const
     }
 }
 
-static const std::uint32_t crc32Table[] = {
-    0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, 0x706af48f,
-    0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
-    0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 0x1db71064, 0x6ab020f2,
-    0xf3b97148, 0x84be41de, 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
-    0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9,
-    0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
-    0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, 0x35b5a8fa, 0x42b2986c,
-    0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
-    0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423,
-    0xcfba9599, 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
-    0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190, 0x01db7106,
-    0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
-    0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d,
-    0x91646c97, 0xe6635c01, 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
-    0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950,
-    0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
-    0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, 0x4adfa541, 0x3dd895d7,
-    0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
-    0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa,
-    0xbe0b1010, 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
-    0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, 0x2eb40d81,
-    0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
-    0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 0xe3630b12, 0x94643b84,
-    0x0d6d6a3e, 0x7a6a5aa8, 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
-    0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb,
-    0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
-    0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, 0xd6d6a3e8, 0xa1d1937e,
-    0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
-    0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55,
-    0x316e8eef, 0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
-    0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, 0xb2bd0b28,
-    0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
-    0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 0x9c0906a9, 0xeb0e363f,
-    0x72076785, 0x05005713, 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
-    0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242,
-    0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
-    0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, 0x8f659eff, 0xf862ae69,
-    0x616bffd3, 0x166ccf45, 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
-    0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc,
-    0x40df0b66, 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
-    0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, 0xcdd70693,
-    0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
-    0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d
-};
-
-static void crc32(const std::string &data, uint32_t& crc)
+std::size_t Preprocessor::calculateHash(const simplecpp::TokenList &tokens1, const std::string &toolinfo) const
 {
-    for (char c : data) {
-        crc = crc32Table[(crc ^ (unsigned char)c) & 0xFF] ^ (crc >> 8);
-    }
-}
-
-uint32_t Preprocessor::calculateChecksum(const simplecpp::TokenList &tokens1, const std::string &toolinfo) const
-{
-    std::uint32_t crc = ~0U;
-    crc32(toolinfo, crc);
+    std::string hashData = toolinfo;
     for (const simplecpp::Token *tok = tokens1.cfront(); tok; tok = tok->next) {
         if (!tok->comment)
-            crc32(tok->str(), crc);
+            hashData += tok->str();
     }
     for (std::map<std::string, simplecpp::TokenList *>::const_iterator it = mTokenLists.begin(); it != mTokenLists.end(); ++it) {
         for (const simplecpp::Token *tok = it->second->cfront(); tok; tok = tok->next) {
             if (!tok->comment)
-                crc32(tok->str(), crc);
+                hashData += tok->str();
         }
     }
-    return crc ^ ~0U;
+    return (std::hash<std::string>{})(hashData);
 }
 
 void Preprocessor::simplifyPragmaAsm(simplecpp::TokenList *tokenList) const

lib/preprocessor.h

@@ -164,13 +164,13 @@ class CPPCHECKLIB Preprocessor {
     void validateCfgError(const std::string &file, const unsigned int line, const std::string &cfg, const std::string &macro);
 
     /**
-     * Calculate CRC32 checksum. Using toolinfo, tokens1, filedata.
+     * Calculate HASH. Using toolinfo, tokens1, filedata.
      *
      * @param tokens1    Sourcefile tokens
      * @param toolinfo   Arbitrary extra toolinfo
-     * @return CRC32 checksum
+     * @return HASH
      */
-    uint32_t calculateChecksum(const simplecpp::TokenList &tokens1, const std::string &toolinfo) const;
+    std::size_t calculateHash(const simplecpp::TokenList &tokens1, const std::string &toolinfo) const;
 
     void simplifyPragmaAsm(simplecpp::TokenList *tokenList) const;
 

lib/tokenlist.cpp

@@ -461,27 +461,17 @@ void TokenList::createTokens(simplecpp::TokenList&& tokenList)
 
 //---------------------------------------------------------------------------
 
-uint64_t TokenList::calculateChecksum() const
+std::size_t TokenList::calculateHash() const
 {
-    uint64_t checksum = 0;
+    std::string hashData;
     for (const Token* tok = front(); tok; tok = tok->next()) {
-        const uint32_t subchecksum1 = tok->flags() + tok->varId() + tok->tokType();
-        uint32_t subchecksum2 = 0;
-        for (char i : tok->str())
-            subchecksum2 += (uint32_t)i;
-        if (!tok->originalName().empty()) {
-            for (char i : tok->originalName())
-                subchecksum2 += (uint32_t)i;
-        }
-
-        checksum ^= ((static_cast<uint64_t>(subchecksum1) << 32) | subchecksum2);
-
-        const bool bit1 = (checksum & 1) != 0;
-        checksum >>= 1;
-        if (bit1)
-            checksum |= (1ULL << 63);
+        hashData += MathLib::toString(tok->flags());
+        hashData += MathLib::toString(tok->varId());
+        hashData += MathLib::toString(tok->tokType());
+        hashData += tok->str();
+        hashData += tok->originalName();
     }
-    return checksum;
+    return (std::hash<std::string>{})(hashData);
 }
 
 

lib/tokenlist.h

@@ -153,10 +153,10 @@ class CPPCHECKLIB TokenList {
     std::string fileLine(const Token *tok) const;
 
     /**
-     * Calculates a 64-bit checksum of the token list used to compare
-     * multiple token lists with each other as quickly as possible.
+     * Calculates a hash of the token list used to compare multiple
+     * token lists with each other as quickly as possible.
      */
-    uint64_t calculateChecksum() const;
+    std::size_t calculateHash() const;
 
     /**
      * Create abstract syntax tree.