Fixup #12929: better handling of escape sequences in Token::isCMultiC…

…har (#6597)
danmar · Jul 13, 2024 · ecd73d5 · ecd73d5
1 parent 9b9a4b8
commit ecd73d5
Show file tree

Hide file tree

Showing 6 changed files with 68 additions and 26 deletions.
diff --git a/lib/token.cpp b/lib/token.cpp
@@ -729,29 +729,10 @@ nonneg int Token::getStrLength(const Token *tok)
     assert(tok != nullptr);
     assert(tok->mTokType == eString);
 
-    int len = 0;
-    // cppcheck-suppress shadowFunction - TODO: fix this
-    const std::string str(getStringLiteral(tok->str()));
-    std::string::const_iterator it = str.cbegin();
-    const std::string::const_iterator end = str.cend();
-
-    while (it != end) {
-        if (*it == '\\') {
-            ++it;
-
-            // string ends at '\0'
-            if (*it == '0')
-                return len;
-        }
-
-        if (*it == '\0')
-            return len;
-
-        ++it;
-        ++len;
-    }
+    const std::string s(replaceEscapeSequences(getStringLiteral(tok->str())));
 
-    return len;
+    const auto pos = s.find('\0');
+    return pos < s.size() ? pos : s.size();
 }
 
 nonneg int Token::getStrArraySize(const Token *tok)

diff --git a/lib/token.h b/lib/token.h
@@ -751,14 +751,13 @@ class CPPCHECKLIB Token {
 
     bool isCChar() const {
         return (((mTokType == eString) && isPrefixStringCharLiteral(mStr, '"', emptyString)) ||
-                ((mTokType ==  eChar) && isPrefixStringCharLiteral(mStr, '\'', emptyString) && mStr.length() == 3) ||
-                ((mTokType ==  eChar) && isPrefixStringCharLiteral(mStr, '\'', emptyString) && mStr.compare(0, 2, "\'\\") == 0 && mStr.length() == 4));
+                ((mTokType == eChar) && isPrefixStringCharLiteral(mStr, '\'', emptyString) && (replaceEscapeSequences(getCharLiteral(mStr)).size() == 1)));
     }
 
     bool isCMultiChar() const {
-        return (((mTokType ==  eChar) && isPrefixStringCharLiteral(mStr, '\'', emptyString)) && (mStr.compare(0, 2, "\'\\") != 0 || mStr.length() > 4) &&
-                (mStr.length() > 3));
+        return (mTokType == eChar) && isPrefixStringCharLiteral(mStr, '\'', emptyString) && (replaceEscapeSequences(getCharLiteral(mStr)).size() > 1);
     }
+
     /**
      * @brief Is current token a template argument?
      *

diff --git a/lib/utils.cpp b/lib/utils.cpp
@@ -147,3 +147,40 @@ void findAndReplace(std::string &source, const std::string &searchFor, const std
         index += replaceWith.length();
     }
 }
+
+std::string replaceEscapeSequences(const std::string &source) {
+    std::string result;
+    result.reserve(source.size());
+    for (std::size_t i = 0; i < source.size(); ++i) {
+        if (source[i] != '\\' || i + 1 >= source.size())
+            result += source[i];
+        else {
+            ++i;
+            if (source[i] == 'n') {
+                result += '\n';
+            } else if (source[i] == 'r') {
+                result += '\r';
+            } else if (source[i] == 't') {
+                result += '\t';
+            } else if (source[i] == 'x') {
+                std::string value = "0";
+                if (i + 1 < source.size() && std::isxdigit(source[i+1]))
+                    value += source[i++ + 1];
+                if (i + 1 < source.size() && std::isxdigit(source[i+1]))
+                    value += source[i++ + 1];
+                result += static_cast<char>(std::stoi(value, nullptr, 16));
+            } else if (source[i] == '0') {
+                std::string value = "0";
+                if (i + 1 < source.size() && source[i+1] >= '0' && source[i+1] <= '7')
+                    value += source[i++ + 1];
+                if (i + 1 < source.size() && source[i+1] >= '0' && source[i+1] <= '7')
+                    value += source[i++ + 1];
+                result += static_cast<char>(std::stoi(value, nullptr, 8));
+            } else {
+                result += source[i];
+            }
+        }
+    }
+    return result;
+}
+
diff --git a/lib/utils.h b/lib/utils.h
@@ -364,6 +364,12 @@ CPPCHECKLIB std::string trim(const std::string& s, const std::string& t = " \t")
  */
 CPPCHECKLIB void findAndReplace(std::string &source, const std::string &searchFor, const std::string &replaceWith);
 
+/**
+ * Replace all escape sequences in the given string.
+ * @param source The string that contains escape sequences
+ */
+CPPCHECKLIB std::string replaceEscapeSequences(const std::string &source);
+
 namespace cppcheck
 {
     NORETURN inline void unreachable()

diff --git a/test/testtoken.cpp b/test/testtoken.cpp
@@ -371,6 +371,14 @@ class TestToken : public TestFixture {
         ASSERT_EQUALS(false, tok.isUtf32());
         ASSERT_EQUALS(false, tok.isLong());
         ASSERT_EQUALS(true, tok.isCMultiChar());
+
+        tok.str("'\\x10'");
+        ASSERT_EQUALS(true, tok.isCChar());
+        ASSERT_EQUALS(false, tok.isUtf8());
+        ASSERT_EQUALS(false, tok.isUtf16());
+        ASSERT_EQUALS(false, tok.isUtf32());
+        ASSERT_EQUALS(false, tok.isLong());
+        ASSERT_EQUALS(false, tok.isCMultiChar());
     }
 
     void stringTypes() const {

diff --git a/test/testutils.cpp b/test/testutils.cpp
@@ -40,6 +40,7 @@ class TestUtils : public TestFixture {
         TEST_CASE(startsWith);
         TEST_CASE(trim);
         TEST_CASE(findAndReplace);
+        TEST_CASE(replaceEscapeSequences);
     }
 
     void isValidGlobPattern() const {
@@ -427,6 +428,16 @@ class TestUtils : public TestFixture {
             ASSERT_EQUALS("", s);
         }
     }
+
+    void replaceEscapeSequences() const {
+        ASSERT_EQUALS("\x30", ::replaceEscapeSequences("\\x30"));
+        ASSERT_EQUALS("\030", ::replaceEscapeSequences("\\030"));
+        ASSERT_EQUALS("\r", ::replaceEscapeSequences("\\r"));
+        ASSERT_EQUALS("\n", ::replaceEscapeSequences("\\n"));
+        ASSERT_EQUALS("\t", ::replaceEscapeSequences("\\t"));
+        ASSERT_EQUALS("\\", ::replaceEscapeSequences("\\\\"));
+        ASSERT_EQUALS("\"", ::replaceEscapeSequences("\\\""));
+    }
 };
 
 REGISTER_TEST(TestUtils)