added more basic syntax errors in c++ (imDarshanGK#86)

* feat: add comprehensive C++ bug patterns (arrays, vectors, pointers, loops)

* feat: enhance C++ syntax and logic bug detection

* test: add tests for C++ syntax error detection

---------

Co-authored-by: Darshan G K <122042809+imDarshanGK@users.noreply.github.com>

Author: shauryaparth1902-blip

.github/pull_request_template.md

@@ -1,21 +1,34 @@
-## Summary
+## Description
+<!-- What does this PR do? Be specific. -->
 
-Describe what this PR changes.
-
-## Type of Change
+## Related Issue
+<!-- Required — link the issue this PR fixes -->
+Fixes #
 
+## Type of change
 - [ ] Bug fix
-- [ ] New feature
+- [ ] New feature / enhancement
 - [ ] Documentation update
+- [ ] Test addition
 - [ ] Refactor
 
-## Testing
-
-- [ ] I ran backend tests (`pytest -q`)
-- [ ] I tested frontend behavior manually
-
 ## Checklist
+<!-- All boxes must be checked before requesting review -->
+- [ ] I have read [CONTRIBUTING.md](../CONTRIBUTING.md)
+- [ ] My branch is up to date with `main`
+- [ ] I have run `pytest -v` and all tests pass
+- [ ] I have not introduced duplicate issues or features
+- [ ] My PR title follows the format: `feat/fix/docs/test: short description`
+- [ ] I have added tests for new features (Level 2 and 3 issues)
+- [ ] No hardcoded secrets or API keys in my code
+- [ ] This PR is linked to a GSSoC 2026 issue
+
+## Screenshots (if frontend change)
+<!-- Add before/after screenshots -->
 
-- [ ] Code is readable and beginner-friendly
-- [ ] No fake or placeholder behavior introduced
-- [ ] Documentation updated if needed
+## Test evidence
+<!-- Paste pytest output here -->
+```bash
+pytest -v
+# paste output
+```

backend/app/services/code_assistant.py

@@ -325,6 +325,79 @@ class BugPattern:
                "Comparing signed `int` with unsigned `.size()` — undefined behavior on overflow.",
                "Cast to `(int)` or use `std::ssize()` (C++20).",
                "warning", ["C++"]),
+    BugPattern("Void Main", r"\bvoid\s+main\s*\(",
+               "`void main()` is non-standard C++ and results in a compilation error.",
+               "Use `int main()` and return 0 at the end.",
+               "error", ["C++"]),
+    BugPattern("Single Quotes for String", r"'[^'\\]{2,}'",
+               "Single quotes are used for strings. In C++, single quotes are strictly for single characters.",
+               "Use double quotes `\"...\"` for string literals.",
+               "error", ["C++"]),
+    BugPattern("Missing Semicolon", r"^(?!.*\b(if|for|while|switch|catch)\b)(?!.*[{}#])(?!^\s*(int|float|double|char|long|short|bool|string|void)\s+\w+\s*\([^)]*\)\s*$).*\b(cout|cin|return|int|float|double|char|long|short|bool|string)\b[^;]*[^\s;]\s*$",
+               "Missing semicolon at the end of the statement.",
+               "Add a semicolon `;` at the end of the line.",
+               "error", ["C++"]),
+
+    BugPattern("Incomplete Assignment", r"=\s*$",
+               "Statement ends abruptly with an assignment operator.",
+               "Provide a value for the assignment.",
+               "error", ["C++", "Java", "Python", "JavaScript", "TypeScript"]),
+    BugPattern("Semicolon After Loop", r"\b(for|while)\s*\([^)]*\)\s*;",
+               "Semicolon immediately after loop condition creates an empty loop body.",
+               "Remove the semicolon so the loop executes the intended block.",
+               "error", ["C++", "Java", "JavaScript", "TypeScript"]),
+    BugPattern("Type Mismatch: String to Int", r"\b(int|long|short)\s+[a-zA-Z_]\w*\s*=\s*\"[^\"]*\"",
+               "Attempting to assign a string literal to an integer variable.",
+               "Use `std::string` for strings, or parse the string using `std::stoi`.",
+               "error", ["C++", "Java"]),
+    BugPattern("Uninitialized Variable Risk", r"^\s*(int|float|double|char|long|short)\s+[a-zA-Z_]\w*\s*;\s*$",
+               "Variable is declared without an initial value. Using it before assignment causes undefined behavior.",
+               "Initialize the variable upon declaration (e.g., `= 0;`).",
+               "warning", ["C++"]),
+    BugPattern("Float Equality", r"==\s*\d+\.\d+",
+               "Directly comparing floating point numbers with `==` is unsafe due to precision issues.",
+               "Compare the absolute difference with an epsilon value (e.g., `abs(a - b) < 1e-9`).",
+               "warning", ["C++", "Java", "Python", "JavaScript"]),
+    BugPattern("Variable Length Array", r"\b(int|float|double|char|long|short)\s+[a-zA-Z_]\w*\s*\[\s*[a-zA-Z_]\w*\s*\]\s*;",
+               "Using a variable to define an array size (VLA) is not standard C++ and fails on some compilers.",
+               "Use `std::vector` for dynamically sized arrays.",
+               "error", ["C++"]),
+    BugPattern("Negative Array Index", r"\[\s*-\s*\d+\s*\]",
+               "Hardcoded negative index detected. In C++ this accesses memory out of bounds.",
+               "Ensure array indices are 0 or greater.",
+               "error", ["C++", "Java", "JavaScript", "TypeScript"]),
+    BugPattern("C-Style Array", r"\b(int|float|double|char|long|short)\s+[a-zA-Z_]\w*\s*\[\s*\d+\s*\]\s*;",
+               "Raw C-style arrays do not carry their size and unsafely decay to pointers.",
+               "Use `std::array<T, N>` for fixed-size arrays.",
+               "info", ["C++"]),
+    BugPattern("Vector Pass by Value", r"\b\w+\s*\(\s*std::vector\s*<\s*[\w:]+\s*>\s+\w+\s*[,)]",
+               "Passing a `std::vector` by value creates a full, expensive copy.",
+               "Pass by const reference (e.g., `const std::vector<T>&`) unless you need to mutate a copy.",
+               "warning", ["C++"]),
+    BugPattern("Vector Unsigned Underflow", r"\.size\(\)\s*-\s*1",
+               "Vector `.size()` is unsigned. If empty, subtracting 1 causes an underflow to a huge number.",
+               "Always check `.empty()` first, or cast size to a signed integer.",
+               "error", ["C++"]),
+    BugPattern("malloc in C++", r"\bmalloc\s*\(",
+               "C-style `malloc` allocates memory but does not call C++ constructors.",
+               "Use `new` or `std::make_unique` instead.",
+               "error", ["C++"]),
+    BugPattern("Dangling Pointer Return", r"return\s+&\s*\w+\s*;",
+               "Returning the address of a local variable creates a dangling pointer.",
+               "Return by value, or allocate on the heap and return a smart pointer.",
+               "error", ["C++"]),
+    BugPattern("Missing Hash in Include", r"^\s*include\s*[<\"]",
+               "Preprocessor directives must start with a `#`.",
+               "Add a `#` at the beginning of the line (e.g., `#include`).",
+               "error", ["C++"]),
+    BugPattern("Semicolon in Condition", r"\b(if|while|switch)\s*\([^)]*;\s*\)",
+               "Condition blocks (if, while, switch) should not contain semicolons.",
+               "Remove the semicolon from inside the parentheses.",
+               "error", ["C++", "Java", "JavaScript", "TypeScript"]),
+    BugPattern("Malformed For-Loop", r"\bfor\s*\([^;:]*(?:;[^;:]*)?\)",
+               "A traditional for-loop must contain exactly two semicolons.",
+               "Ensure you have two semicolons separating the initialization, condition, and increment statements.",
+               "error", ["C++", "Java", "JavaScript", "TypeScript"]),
 
     # ── PHP ──
     BugPattern("PHP MySQL Deprecated", r"\bmysql_\w+\s*\(",
@@ -601,6 +674,17 @@ def run_suggestions(code: str, language: str) -> dict:
                 "priority": "medium",
             })
 
+    # std::endl Performance (only if in a file with loops)
+    if language == "C++":
+        if re.search(r"<<\s*(std::)?endl\b", code) and re.search(r"\b(for|while)\b", code):
+            suggestions.append({
+                "category": "Performance",
+                "description": "Code contains both a loop and `std::endl`. If `std::endl` is used inside the loop, it flushes the buffer on every iteration, severely degrading performance.",
+                "example": "std::cout << value << '\\n';",
+                "priority": "medium",
+            })
+
+    # Score
     # Score calculation
     deductions = sum({"high": 15, "medium": 7, "low": 3}.get(s["priority"], 5) for s in suggestions)
     score = max(0, min(100, 100 - deductions))

backend/tests/test_endpoints.py

@@ -460,6 +460,15 @@ def test_debug_kotlin():
     d = r.json()
     assert d is not None
 
+def test_debug_cpp_syntax_errors():
+    code = "void main() {\n    cout << 'Hello World'\n}"
+    r = client.post("/debugging/", json={"code": code, "language": "cpp"})
+    assert r.status_code == 200
+    types = [i["type"] for i in r.json()["issues"]]
+    assert "Void Main" in types
+    assert "Single Quotes for String" in types
+    assert "Missing Semicolon" in types
+
 def test_debug_issue_has_required_fields():
     r = client.post("/debugging/", json={"code": PYTHON_BUGGY})
     assert r.status_code == 200