feat: add initial C++ project structure with CMake build and spam word parser

Implement the first version of the borded spam parser as a C++26 project. The commit introduces a complete project skeleton including a `.gitignore` file for CMake and IDE artifacts, a `CMakeLists.txt` with strict warning flags and MSVC compatibility, and the core `src/main.cpp` containing the spam detection logic. The parser reads text files, tokenizes words, counts sentences and capitalized words, and flags occurrences from a predefined list of 35 forbidden spam-related terms (e.g., "crypto", "bitcoin", "recovery", "hack"). Results are aggregated via an `AnalysisResult` struct with a custom `operator+` for combining multiple file analyses.
2025-03-20 20:44:22 +00:00
parent 3aa6ac2451
commit 67640f034f
3 changed files with 258 additions and 0 deletions
@@ -0,0 +1,140 @@
+import std;
+
+const std::vector<std::wstring_view> BAD_WORDS = {
+    L"recovery",
+    L"techie",
+    L"http",
+    L"https",
+    L"digital",
+    L"hack",
+    L"::",
+    L"//",
+    L"com",
+    L"@",
+    L"crypto",
+    L"bitcoin",
+    L"wallet",
+    L"hacker",
+    L"welcome",
+    L"whatsapp",
+    L"email",
+    L"cryptocurrency",
+    L"stolen",
+    L"freeze",
+    L"quick",
+    L"crucial",
+    L"tracing",
+    L"scammers",
+    L"expers",
+    L"hire",
+    L"century",
+    L"transaction",
+    L"essential",
+    L"managing",
+    L"contact",
+    L"contacting",
+    L"understanding",
+    L"assets",
+    L"funds",
+};
+
+
+struct AnalysisResult {
+    std::size_t totalWordCount = 0;
+    std::size_t totalCapitalizedCount = 0;
+    std::size_t totalSentenceCount = 0;
+    std::size_t totalNumberCount = 0;
+    std::size_t totalForbiddenCount = 0;
+
+    operator std::string() const {
+        return std::format(
+            "Word Count: {}\nCapitalized Count: {}\nSentence Count: {}\nNumber Count: {}\nForbidden Count: {}",
+            totalWordCount, totalCapitalizedCount, totalSentenceCount, totalNumberCount, totalForbiddenCount
+            );
+    }
+
+    AnalysisResult operator+(const AnalysisResult &other) const {
+        return {
+            totalWordCount + other.totalWordCount,
+            totalCapitalizedCount + other.totalCapitalizedCount,
+            totalSentenceCount + other.totalSentenceCount,
+            totalNumberCount + other.totalNumberCount,
+            totalForbiddenCount + other.totalForbiddenCount
+        };
+    }
+};
+
+void check_word(const std::wstring &word, std::size_t &forbiddenCount) {
+    if (std::find(BAD_WORDS.begin(), BAD_WORDS.end(), word) != BAD_WORDS.end()) {
+        forbiddenCount++;
+    }
+}
+
+AnalysisResult parseFile(const std::string_view &filename) {
+    std::wifstream file;
+
+    file.open(filename);
+    if (!file.is_open()) {
+        std::println("File doesn't exist: {}", filename);
+        return { };
+    }
+
+    AnalysisResult result{ };
+
+    bool inWord = false;
+    wchar_t c;
+
+    std::wstring word;
+    while (file.get(c)) {
+        if (c == '.') {
+            result.totalSentenceCount++;
+        }
+
+        if (std::isspace(c) || c == '.' || c == '?' || c == '!' || c == ';' || c == ':') {
+            inWord = false;
+
+            check_word(word, result.totalForbiddenCount);
+            word.clear();
+            continue;
+        } else {
+            if (!inWord) {
+                result.totalWordCount++;
+                if (std::isupper(c)) {
+                    result.totalCapitalizedCount++;
+                }
+            }
+            inWord = true;
+
+            if (std::isdigit(c)) {
+                result.totalNumberCount++;
+                while (file.get(c) && std::isdigit(c)) { }
+                file.unget();
+                continue;
+            }
+
+            word.push_back(c);
+        }
+    };
+
+    if (!word.empty()) {
+        check_word(word, result.totalForbiddenCount);
+    }
+
+    file.close();
+
+    return result;
+}
+
+int main(const int argc, char *argv[]) {
+    if (argc < 2) {
+        std::println("Usage: {} <file1> <file2> ... <fileN>", argv[0]);
+        return 1;
+    }
+
+    const AnalysisResult result = std::transform_reduce(std::execution::par, std::next(argv), argv + argc, AnalysisResult{ }, std::plus{ },
+                                                        parseFile
+        );
+
+    std::println("{}", std::string(result));
+    return 0;
+}