notes

Added borded cpp to bench
Made borded part of make all

.gitignore

@@ -5,7 +5,10 @@ publish
 books
 __pycache__
 target
+./isspam.py
 isspam
 risspam
+/jisspam
 isspam_cpp
 .build-trigger-2014-12-02 15:26
+borded_cpp_exec

Makefile

@@ -1,20 +1,32 @@
 CC = gcc 
 CFLAGS = -Ofast
 
-all: build run valgrind build_risspam run_risspam build_cpp
+all: build run valgrind build_risspam run_risspam build_cpp build_borded_cpp build_py build_jest
 
 build:
 	@echo "Compiling retoor_c project.".
 	@$(CC) $(CFLAGS) retoor_c/isspam.c -o isspam
 
+build_py:
+	@echo "Copying py file"
+	@cp retoor_c/isspam.py isspam.py
+
 build_cpp:
 	@echo "Compiling C++ version of isspam."
 	@g++ -Ofast retoor_c/isspam.cpp -o isspam_cpp
 
+build_borded_cpp:
+	@echo "Compiling Borded C++ version of isspam."
+	@g++ -std=c++23 -Ofast borded_cpp/src/main3.cpp -o borded_cpp_exec
+
 build_risspam:
 	@echo "Compiling 12bitfloat_risspam project."
 	cd 12bitfloat_rust/risspam && cargo run --release && cp target/release/risspam ../../
 
+build_jest:
+	@echo "compiling jest_rust project"
+	cd jest_rust && cargo build --release && cp target/release/jisspam ..
+
 run: run_spam wl run_not_spam
 run_risspam: run_spam_risspam run_not_spam_risspam
 

bench.py

@@ -11,4 +11,13 @@ print("Time Rust:",time.time() - time_start)
 time_start = time.time()
 subprocess.check_output('./isspam_cpp books/*.txt', shell=True)
 print("Time CPP:",time.time() - time_start)
+time_start = time.time()
+subprocess.check_output('./borded_cpp_exec books/*.txt', shell=True)
+print("Time Borded CPP:",time.time() - time_start)
+time_start = time.time()
+subprocess.check_output('./jisspam books/*.txt', shell=True)
+print("Time Jest Rust:", time.time() - time_start)
+time_start = time.time()
+subprocess.check_output('python3 isspam.py books/*.txt', shell=True)
+print("Time Retoor Python:",time.time() - time_start)
 print("***end benchmark***")

borded_cpp/.gitignore

@@ -0,0 +1,97 @@
+*.d
+*.slo
+*.lo
+*.o
+*.obj
+*.gch
+*.pch
+*.so
+*.dylib
+*.dll
+*.mod
+*.smod
+*.lai
+*.la
+*.a
+*.lib
+*.exe
+*.out
+*.app
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+.idea/**/aws.xml
+.idea/**/contentModel.xml
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+.idea/**/gradle.xml
+.idea/**/libraries
+.idea
+cmake-build-*/
+.idea/**/mongoSettings.xml
+*.iws
+out/
+.idea_modules/
+atlassian-ide-plugin.xml
+.idea/replstate.xml
+.idea/sonarlint/
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+.idea/httpRequests
+.idea/caches/build_file_checksums.ser
+*~
+.fuse_hidden*
+.directory
+.Trash-*
+.nfs*
+CMakeLists.txt.user
+CMakeCache.txt
+CMakeFiles
+CMakeScripts
+Testing
+Makefile
+cmake_install.cmake
+install_manifest.txt
+compile_commands.json
+CTestTestfile.cmake
+_deps
+CMakeUserPresets.json
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+*.stackdump
+[Dd]esktop.ini
+$RECYCLE.BIN/
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+*.lnk
+.DS_Store
+.AppleDouble
+.LSOverride
+Icon
+._*
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk

borded_cpp/CMakeLists.txt

@@ -0,0 +1,27 @@
+cmake_minimum_required(VERSION 3.25)
+project(isspam)
+
+set(CMAKE_CXX_STANDARD 26)
+if (MSVC)
+    add_compile_options(/W4)
+    add_compile_options(/WX)
+    add_compile_options(/external:anglebrackets)
+    add_compile_options(/external:W0)
+    add_compile_options(/wd4100)
+    add_compile_options(/wd5050)
+    add_definitions(-DWIN32_LEAN_AND_MEAN -DVC_EXTRALEAN)
+    add_compile_definitions(WIN32_LEAN_AND_MEAN NOMINMAX)
+else ()
+    add_compile_options(-Wall)
+    add_compile_options(-Wextra)
+    add_compile_options(-Wpedantic)
+#    add_compile_options(-Werror)
+endif ()
+
+add_executable(${PROJECT_NAME} src/main.cpp)
+add_executable(${PROJECT_NAME}3 src/main3.cpp)
+
+if (LINUX)
+    target_link_libraries(${PROJECT_NAME} tbb)
+    target_link_libraries(${PROJECT_NAME}3 tbb)
+endif ()

borded_cpp/Dockerfile

@@ -0,0 +1,3 @@
+FROM gcc:latest
+RUN apt update && apt install -y cmake gdb
+WORKDIR /home

borded_cpp/compose.yml

@@ -0,0 +1,9 @@
+services:
+  cpp:
+    build: .
+    command: ["sh","doit.sh"]
+    tty: true 
+    stdin_open: true 
+    volumes:
+      - ./:/home
+      - ../books:/books

borded_cpp/doit.sh

@@ -0,0 +1,2 @@
+rm -rf build | true
+mkdir build && cd build && cmake .. && make

borded_cpp/src/main.cpp

@@ -0,0 +1,221 @@
+#include <string>
+#include <string_view>
+#include <fstream>
+#include <algorithm>
+#include <iostream>
+#include <numeric>
+#include <execution>
+#include <format>
+#include <codecvt>
+#include <ranges>
+
+#ifdef __cpp_lib_print
+#include <print>
+#else
+namespace std {
+template <typename T, typename... Args>
+inline void print(T format, Args &&... args) {
+    auto f = std::vformat(format, std::make_format_args(args...));
+    std::cout << f;
+}
+
+template <typename T, typename... Args>
+inline void println(T format, Args &&... args) {
+    auto f = std::vformat(format, std::make_format_args(args...));
+    std::cout << f << std::endl;
+}
+}
+#endif
+
+constexpr std::array<std::wstring_view, 35> 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",
+};
+
+constexpr auto SHORTEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::max(),
+                                                          [](std::size_t current, const std::wstring_view &word) {
+                                                              return std::min(current, word.size());
+                                                          }
+    );
+constexpr auto LONGEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::min(),
+                                                         [](std::size_t current, const std::wstring_view &word) {
+                                                             return std::max(current, word.size());
+                                                         }
+    );
+
+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;
+    std::size_t fileCount = 1;
+
+    std::size_t failCount = 0;
+
+    operator std::string() const {
+        return std::format(
+            "Word Count: {}\nCapitalized Count: {}\nSentence Count: {}\nNumber Count: {}\nForbidden Count: {}\nFile Count: {}\nFail Count: {}",
+            totalWordCount, totalCapitalizedCount, totalSentenceCount, totalNumberCount, totalForbiddenCount, fileCount, failCount
+            );
+    }
+
+    friend AnalysisResult operator+(const AnalysisResult &lhs, const AnalysisResult &rhs) {
+        return {
+            lhs.totalWordCount + rhs.totalWordCount,
+            lhs.totalCapitalizedCount + rhs.totalCapitalizedCount,
+            lhs.totalSentenceCount + rhs.totalSentenceCount,
+            lhs.totalNumberCount + rhs.totalNumberCount,
+            lhs.totalForbiddenCount + rhs.totalForbiddenCount,
+            lhs.fileCount + rhs.fileCount,
+            lhs.failCount + rhs.failCount
+        };
+    };
+};
+
+void check_word(std::wstring &word, std::size_t &forbiddenCount) {
+    if (word.size() < SHORTEST_BAD_WORD || word.size() > LONGEST_BAD_WORD) {
+        return;
+    }
+    std::ranges::transform(word, word.begin(), ::towlower);
+        if (std::ranges::find(BAD_WORDS, word) != BAD_WORDS.end()) {
+            forbiddenCount++;
+        }
+    // if (std::ranges::find_if(BAD_WORDS, [&word](const std::wstring_view &badWord) {
+    //                              return word.contains(badWord);
+    //                          }
+    //         ) != BAD_WORDS.end()) {
+    //     forbiddenCount++;
+    // }
+}
+
+AnalysisResult parseFile(const std::string_view &filename) {
+    std::wifstream file;
+
+    // surpress warning of deprecation
+#pragma warning(push)
+#pragma warning(suppress : 4996)
+    file.imbue(std::locale(std::locale(), new std::codecvt_utf8<wchar_t>));
+#pragma warning(pop)
+
+    file.open(std::string(filename));
+    if (!file.is_open()) {
+        std::println("File doesn't exist: {}", filename);
+        return { };
+    }
+
+    AnalysisResult result{ };
+
+    bool inWord = false;
+    bool isDigit = false;
+    wchar_t c;
+
+    std::wstring word;
+    while (file.get(c)) {
+        if (c == '.') {
+            result.totalSentenceCount++;
+        }
+
+        if (std::isspace(c)) {
+            inWord = false;
+            isDigit = false;
+
+            if (!word.empty()) {
+                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) && !isDigit) {
+                result.totalNumberCount++;
+                isDigit = true;
+            }
+
+            word.push_back(c);
+        }
+    };
+
+    // std::cout << "File state: " << file.rdstate() << " EOF" << file.eof() << " Fail" << file.fail() << " Bad" << file.bad() << std::endl;
+
+    if (!word.empty()) {
+        check_word(word, result.totalForbiddenCount);
+    }
+
+    file.close();
+
+    if (file.fail() && !file.eof()) {
+        result.failCount++;
+    }
+
+    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_unseq, std::next(argv), argv + argc,
+                                                        AnalysisResult{.fileCount = 0},
+                                                        std::plus{ },
+                                                        parseFile
+        );
+
+    double capitalizedPercentage = (result.totalWordCount > 0)
+                                       ? static_cast<double>(result.totalCapitalizedCount) / result.totalWordCount * 100.0
+                                       : 0;
+    double forbiddenPercentage = (result.totalWordCount > 0)
+                                     ? static_cast<double>(result.totalForbiddenCount) / result.totalWordCount * 100.0
+                                     : 0;
+    double wordCountPerSentence = (result.totalSentenceCount > 0)
+                                      ? static_cast<double>(result.totalWordCount) / result.totalSentenceCount
+                                      : 0;
+
+    std::println("{}\nCapitalized Percentage: {}%\nForbidden Percentage: {}%\nWord Count Per Sentence: {}", std::string(result),
+                 capitalizedPercentage, forbiddenPercentage, wordCountPerSentence
+        );
+
+    return 0;
+}

borded_cpp/src/main2.cpp

@@ -0,0 +1,195 @@
+#include <string>
+#include <string_view>
+#include <fstream>
+#include <algorithm>
+#include <iostream>
+#include <numeric>
+#include <execution>
+#include <format>
+#include <codecvt>
+#include <ranges>
+
+#ifdef __cpp_lib_print
+#include <print>
+#else
+namespace std {
+template <typename T, typename... Args>
+inline void print(T format, Args &&... args) {
+    auto f = std::vformat(format, std::make_format_args(args...));
+    std::cout << f;
+}
+
+template <typename T, typename... Args>
+inline void println(T format, Args &&... args) {
+    auto f = std::vformat(format, std::make_format_args(args...));
+    std::cout << f << std::endl;
+}
+}
+#endif
+
+constexpr std::array<std::wstring_view, 35> 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",
+};
+
+constexpr auto SHORTEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::max(),
+                                                          [](std::size_t current, const std::wstring_view &word) {
+                                                              return std::min(current, word.size());
+                                                          }
+    );
+constexpr auto LONGEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::min(),
+                                                         [](std::size_t current, const std::wstring_view &word) {
+                                                             return std::max(current, word.size());
+                                                         }
+    );
+
+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;
+std::size_t fileCount = 1;
+
+std::size_t failCount = 0;
+
+void check_word(std::wstring &word, std::size_t &forbiddenCount) {
+    if (word.size() < SHORTEST_BAD_WORD || word.size() > LONGEST_BAD_WORD) {
+        return;
+    }
+    std::ranges::transform(word, word.begin(), ::towlower);
+    if (std::ranges::find(BAD_WORDS, word) != BAD_WORDS.end()) {
+        forbiddenCount++;
+    }
+    // if (std::ranges::find_if(BAD_WORDS, [&word](const std::wstring_view &badWord) {
+    //                              return word.contains(badWord);
+    //                          }
+    //         ) != BAD_WORDS.end()) {
+    //     forbiddenCount++;
+    // }
+}
+
+void parseFile(const std::string_view &filename) {
+    std::wifstream file;
+
+    // surpress warning of deprecation
+#pragma warning(push)
+#pragma warning(suppress : 4996)
+    file.imbue(std::locale(std::locale(), new std::codecvt_utf8<wchar_t>));
+#pragma warning(pop)
+
+    file.open(std::string(filename));
+    if (!file.is_open()) {
+        std::println("File doesn't exist: {}", filename);
+        return;
+    }
+
+    bool inWord = false;
+    bool isDigit = false;
+    wchar_t c;
+
+    std::wstring word;
+    while (file.get(c)) {
+        if (c == '.') {
+            totalSentenceCount++;
+        }
+
+        if (std::isspace(c)) {
+            inWord = false;
+            isDigit = false;
+
+            if (!word.empty()) {
+                check_word(word, totalForbiddenCount);
+                word.clear();
+            }
+            continue;
+        } else {
+            if (!inWord) {
+                totalWordCount++;
+                if (std::isupper(c)) {
+                    totalCapitalizedCount++;
+                }
+            }
+            inWord = true;
+
+            if (std::isdigit(c) && !isDigit) {
+                totalNumberCount++;
+                isDigit = true;
+            }
+
+            word.push_back(c);
+        }
+    };
+
+    // std::cout << "File state: " << file.rdstate() << " EOF" << file.eof() << " Fail" << file.fail() << " Bad" << file.bad() << std::endl;
+
+    if (!word.empty()) {
+        check_word(word, totalForbiddenCount);
+    }
+
+    file.close();
+
+    if (file.fail() && !file.eof()) {
+        failCount++;
+    }
+
+}
+
+int main(const int argc, char *argv[]) {
+    if (argc < 2) {
+        std::println("Usage: {} <file1> <file2> ... <fileN>", argv[0]);
+        return 1;
+    }
+
+    std::for_each(std::execution::par_unseq, std::next(argv), argv + argc, parseFile);
+
+    double capitalizedPercentage = (totalWordCount > 0)
+                                       ? static_cast<double>(totalCapitalizedCount) / totalWordCount * 100.0
+                                       : 0;
+    double forbiddenPercentage = (totalWordCount > 0)
+                                     ? static_cast<double>(totalForbiddenCount) / totalWordCount * 100.0
+                                     : 0;
+    double wordCountPerSentence = (totalSentenceCount > 0)
+                                      ? static_cast<double>(totalWordCount) / totalSentenceCount
+                                      : 0;
+
+    std::println(
+        "Word Count: {}\nCapitalized Count: {}\nSentence Count: {}\nNumber Count: {}\nForbidden Count: {}\nFile Count: {}\nFail Count: {}\nCapitalized Percentage: {}%\nForbidden Percentage: {}%\nWord Count Per Sentence: {}",
+        totalWordCount, totalCapitalizedCount, totalSentenceCount, totalNumberCount, totalForbiddenCount, fileCount, failCount,
+        capitalizedPercentage, forbiddenPercentage, wordCountPerSentence
+        );
+
+    return 0;
+}

borded_cpp/src/main3.cpp

@@ -0,0 +1,576 @@
+#include <string>
+#include <string_view>
+#include <fstream>
+#include <algorithm>
+#include <iostream>
+#include <execution>
+#include <format>
+#include <cstdio>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <aio.h>
+#include <condition_variable>
+#include <unordered_set>
+#include <sys/signal.h>
+
+#ifdef __cpp_lib_print
+#include <print>
+#else
+namespace std {
+template <typename T, typename... Args>
+inline void print(T format, Args &&... args) {
+    auto f = std::vformat(format, std::make_format_args(args...));
+    std::cout << f;
+}
+
+template <typename T, typename... Args>
+inline void println(T format, Args &&... args) {
+    auto f = std::vformat(format, std::make_format_args(args...));
+    std::cout << f << std::endl;
+}
+}
+#endif
+
+constexpr std::array<std::string_view, 35> BAD_WORDS = {
+    "recovery",
+    "techie",
+    "http",
+    "https",
+    "digital",
+    "hack",
+    "::",
+    "//",
+    "com",
+    "@",
+    "crypto",
+    "bitcoin",
+    "wallet",
+    "hacker",
+    "welcome",
+    "whatsapp",
+    "email",
+    "cryptocurrency",
+    "stolen",
+    "freeze",
+    "quick",
+    "crucial",
+    "tracing",
+    "scammers",
+    "expers",
+    "hire",
+    "century",
+    "transaction",
+    "essential",
+    "managing",
+    "contact",
+    "contacting",
+    "understanding",
+    "assets",
+    "funds",
+};
+const std::unordered_set<std::string_view> BAD_WORDS_SET(BAD_WORDS.begin(), BAD_WORDS.end());
+static constexpr unsigned int crc_table[256] = {
+    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
+};
+
+constexpr uint32_t crc32(std::string_view str) {
+    uint32_t crc = 0xffffffff;
+    for (auto c : str)
+        crc = (crc >> 8) ^ crc_table[(crc ^ c) & 0xff];
+    return crc ^ 0xffffffff;
+}
+
+constexpr uint32_t crc32(char const *str, const size_t size) {
+    uint32_t crc = 0xffffffff;
+    for (size_t i = 0; i < size; ++i)
+        crc = (crc >> 8) ^ crc_table[(crc ^ str[i]) & 0xff];
+    return crc ^ 0xffffffff;
+}
+
+constexpr std::array<uint32_t, 35> BAD_WORDS_HASH = {
+    crc32("recovery"),
+    crc32("techie"),
+    crc32("http"),
+    crc32("https"),
+    crc32("digital"),
+    crc32("hack"),
+    crc32("::"),
+    crc32("//"),
+    crc32("com"),
+    crc32("@"),
+    crc32("crypto"),
+    crc32("bitcoin"),
+    crc32("wallet"),
+    crc32("hacker"),
+    crc32("welcome"),
+    crc32("whatsapp"),
+    crc32("email"),
+    crc32("cryptocurrency"),
+    crc32("stolen"),
+    crc32("freeze"),
+    crc32("quick"),
+    crc32("crucial"),
+    crc32("tracing"),
+    crc32("scammers"),
+    crc32("expers"),
+    crc32("hire"),
+    crc32("century"),
+    crc32("transaction"),
+    crc32("essential"),
+    crc32("managing"),
+    crc32("contact"),
+    crc32("contacting"),
+    crc32("understanding"),
+    crc32("assets"),
+    crc32("funds")
+};
+const std::unordered_set BAD_WORDS_STR(BAD_WORDS.begin(), BAD_WORDS.end());
+
+constexpr auto SHORTEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::max(),
+                                                          [](std::size_t current, const std::string_view &word) {
+                                                              return std::min(current, word.size());
+                                                          }
+    );
+constexpr auto LONGEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::min(),
+                                                         [](std::size_t current, const std::string_view &word) {
+                                                             return std::max(current, word.size());
+                                                         }
+    );
+
+int totalWordCount = 0;
+int totalCapitalizedCount = 0;
+int totalSentenceCount = 0;
+int totalNumberCount = 0;
+int totalForbiddenCount = 0;
+int fileCount = 1;
+
+int failCount = 0;
+
+
+int done = 0;
+
+
+struct info {
+    std::string_view name;
+    aiocb *cb;
+    const std::chrono::time_point<std::chrono::steady_clock> start = std::chrono::steady_clock::now();
+};
+
+constexpr void check_word_simple(const char *word, const ssize_t size) {
+    if (size < SHORTEST_BAD_WORD || size > LONGEST_BAD_WORD) {
+        return;
+    }
+    // if (BAD_WORDS_SET.contains(word)) {
+    //     totalForbiddenCount++;
+    // }
+
+    const auto hs = crc32(word, size);
+
+    for (int i = 0; i < BAD_WORDS_HASH.size(); ++i) {
+        if (BAD_WORDS_HASH[i] == hs) {
+            totalForbiddenCount++;
+            return;
+        }
+    }
+}
+
+void read_str(char *str, ssize_t size) {
+    int mark = -1;
+
+    int fileWords = 0;
+    for (int pos = 0; pos <= size; ++pos) {
+        char *c = str + pos;
+
+        if (*c == '.') {
+            totalSentenceCount++;
+        }
+
+        if (*c == ' ' || *c == '\n' || *c == '\r' || *c == '\t') {
+            if (mark != -1) {
+                check_word_simple(str + mark, pos - mark);
+                mark = -1;
+            }
+        } else if (mark == -1) {
+            ++fileWords;
+            if (*c >= 'A' && *c <= 'Z') {
+                totalCapitalizedCount++;
+            }
+
+            mark = pos;
+        } else if (*c >= '0' && *c <= '9') {
+            totalNumberCount++;
+            for (; pos <= size; ++pos) {
+                c = str + pos;
+                if (*c == '.') {
+                    totalSentenceCount++;
+                }
+                if (*c == ' ' || *c == '\n' || *c == '\r' || *c == '\t') {
+                    break;
+                }
+            }
+            mark = -1;
+        }
+
+    }
+
+    if (mark != -1) {
+        check_word_simple(str + mark, size - mark);
+    }
+
+    totalWordCount += fileWords;
+}
+
+
+void aio_completion_handler(sigval_t sigval) {
+
+        fileCount++;
+        info *data = (info *)sigval.sival_ptr;
+        auto req = data->cb;
+        // auto req = (struct aiocb *)sigval.sival_ptr;
+        /* Did the request complete? */
+        auto error = aio_error(req);
+        if (error == 0) {
+
+            /* Request completed successfully, get the return status */
+            // const auto start{std::chrono::steady_clock::now()};
+            // const std::chrono::duration<double> start_seconds{start - (data->start)};
+            // std::println("File started {} in {}", data->name, start_seconds.count());
+            read_str((char *)req->aio_buf, aio_return(req));
+            // const auto finish{std::chrono::steady_clock::now()};
+            // const std::chrono::duration<double> elapsed_seconds{finish - (data->start)};
+            // std::println("File read {} in {}", data->name, elapsed_seconds.count());
+        } else {
+            std::println("Error at aio_error ({}): ", error);
+            failCount++;
+        }
+        --done;
+
+}
+
+int main(const int argc, char *argv[]) {
+    if (argc < 2) {
+        std::println("Usage: {} <file1> <file2> ... <fileN>", argv[0]);
+        return 1;
+    }
+
+    done = argc - 1;
+
+    // lio_listio
+    auto aiocb_list = (struct aiocb *)malloc(sizeof(struct aiocb) * (argc - 1));
+    auto aiocb_list_ptr = (struct aiocb **)malloc(sizeof(struct aiocb *) * (argc - 1));
+
+    // char *memchnk = (char *)malloc(5 * 1024 * 1024 * (argc - 1));
+
+    for (std::size_t i = 0; i < argc - 1; i++) {
+        aiocb_list[i].aio_fildes = open(argv[i + 1], O_RDONLY);
+        aiocb_list[i].aio_offset = 0;
+        // 5mb
+        aiocb_list[i].aio_buf = malloc(5 * 1024 * 1024);
+        aiocb_list[i].aio_nbytes = (5 * 1024 * 1024);;
+
+        aiocb_list[i].aio_sigevent.sigev_notify = SIGEV_THREAD;
+        aiocb_list[i].aio_sigevent.sigev_notify_function = aio_completion_handler;
+        aiocb_list[i].aio_sigevent.sigev_notify_attributes = nullptr;
+        // aiocb_list[i].aio_sigevent.sigev_value.sival_ptr = &aiocb_list[i];
+        aiocb_list[i].aio_sigevent.sigev_value.sival_ptr = new info{
+            argv[i + 1],
+            &aiocb_list[i]};
+
+        // aiocb_list[i].aio_reqprio = SIGRTMIN;
+
+        aiocb_list_ptr[i] = &aiocb_list[i];
+    }
+
+    lio_listio(LIO_WAIT, aiocb_list_ptr, argc - 1, nullptr);
+
+    while (done > 0) {
+        std::this_thread::sleep_for(std::chrono::milliseconds(1));
+    }
+
+    std::println("Done reading files, {} done", done);
+
+    double capitalizedPercentage = (totalWordCount > 0)
+                                       ? static_cast<double>(totalCapitalizedCount) / totalWordCount * 100.0
+                                       : 0;
+    double forbiddenPercentage = (totalWordCount > 0)
+                                     ? static_cast<double>(totalForbiddenCount) / totalWordCount * 100.0
+                                     : 0;
+    double wordCountPerSentence = (totalSentenceCount > 0)
+                                      ? static_cast<double>(totalWordCount) / totalSentenceCount
+                                      : 0;
+
+    std::println(
+        "Word Count: {}\nCapitalized Count: {}\nSentence Count: {}\nNumber Count: {}\nForbidden Count: {}\nFile Count: {}\nFail Count: {}\nCapitalized Percentage: {}%\nForbidden Percentage: {}%\nWord Count Per Sentence: {}",
+        totalWordCount, totalCapitalizedCount, totalSentenceCount, totalNumberCount, totalForbiddenCount, fileCount, failCount,
+        capitalizedPercentage, forbiddenPercentage, wordCountPerSentence
+        );
+
+    for (std::size_t i = 0; i < argc - 1; i++) {
+        close(aiocb_list[i].aio_fildes);
+        free((void *)aiocb_list[i].aio_buf);
+    }
+
+    free(aiocb_list);
+    free(aiocb_list_ptr);
+    // free(memchnk);
+
+    if (failCount > 0) {
+        return 1;
+    }
+}

jest_rust/.gitignore

@@ -0,0 +1,3 @@
+/target
+/Cargo.lock
+/test_books

jest_rust/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "jisspam"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+fxhash = "0.2.1"
+tokio = { version = "1.44.1", features = ["full"] }
+
+[profile.release]
+codegen-units = 1 # less means more compile work but better optimized
+lto = "fat"      # thin has best performance. fat the worst
+strip = true
+# opt-level = "z" # slows down
+panic = "abort"

jest_rust/README.md

@@ -0,0 +1,84 @@
+for https://retoor.molodetz.nl/retoor/isspam
+
+extract `../books.tar.gz`
+
+# local machine benchmarks
+
+single threaded: `33.63373279571533`
+
+rayon: `4.294418811798096`
+
+tokio: `4.717588901519775`
+
+tokio:
+
+muncher: `2486ms`
+
+for_loops: `1227ms`
+
+for_loops_forbidden_only: `987ms`
+
+trie creation and stats accumulation take 0ms
+
+FxHashMap faster than BTreeMap
+
+## compile options benchmarks
+`lto` thin, fat doesn't change much
+
+`codegen-units` 0, 1 doesn't change much
+
+`opt-level = "z"` slow things down
+
+# ubuntu terminal running
+https://snek.molodetz.nl/terminal.html ubuntu running thing instructions:
+```
+mkdir /project
+cd /project
+git clone https://retoor.molodetz.nl/retoor/isspam.git
+apt install valgrind curl
+export RUSTUP_HOME=/project/.rustup
+export CARGO_HOME=/project/.cargo
+curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
+. "/project/.cargo/env"
+cd isspam
+rustup install nightly
+rustup default nightly
+make
+make benchmark
+python3 bench.py
+```
+
+clone: `git clone https://gitlab.com/jestdotty-group/draft/jisspam.git jest_rust`
+
+edit make: `vi makefile` and add build:
+```
+build_jest:
+	@echo "compiling jest_rust project"
+	cd jest_rust && cargo build --release && cp target/release/jisspam ..
+```
+append to all script:
+```
+all: build run valgrind build_risspam run_risspam build_cpp build_borded_cpp build_py build_jest
+```
+
+add to bench: `vi bench.py`
+```py
+time_start = time.time()
+subprocess.check_output('./jisspam books/*.txt', shell=True)
+print("Time Jest Rust:", time.time() - time_start)
+```
+
+run: `python3 bench.py`
+output looks something like this:
+```
+***benchmarking***
+Time C: 31.315868377685547
+Time Rust: 41.232205867767334
+Time CPP: 20.1683189868927
+Time Borded CPP: 15.468477964401245
+Time Jest Rust: 54.74523115158081
+Time Retoor Python: 287.63036131858826
+***end benchmark***
+```
+
+add `/jisspam` to `.gitignore` to not commit the executable accidentally

jest_rust/src/main.rs

@@ -0,0 +1,122 @@
+mod parser;
+mod stats;
+mod trie;
+
+use stats::Stats;
+use std::{env, fs, sync::LazyLock};
+use tokio::sync::mpsc;
+use trie::Trie;
+
+static FORBIDDEN_WORDS: LazyLock<Trie> = LazyLock::new(|| {
+	let mut trie = Trie::default();
+	for word in [
+		"recovery",
+		"techie",
+		"http",
+		"https",
+		"digital",
+		"hack",
+		"::",
+		"//",
+		"@",
+		"com",
+		"crypto",
+		"bitcoin",
+		"wallet",
+		"hacker",
+		"welcome",
+		"whatsapp",
+		"email",
+		"cryptocurrency",
+		"stolen",
+		"freeze",
+		"quick",
+		"crucial",
+		"tracing",
+		"scammers",
+		"expers",
+		"hire",
+		"century",
+		"transaction",
+		"essential",
+		"managing",
+		"contact",
+		"contacting",
+		"understanding",
+		"assets",
+		"funds",
+	] {
+		trie.insert(word);
+	}
+	trie
+});
+
+#[tokio::main]
+async fn main() {
+	let files = env::args().skip(1);
+	let mut rx = {
+		let (tx, rx) = mpsc::unbounded_channel();
+		for file in files {
+			let tx = tx.clone();
+			tokio::spawn(async move {
+				let mut stats = Stats::default();
+				//reading files in threads doesn't change speed of any sort but oh well
+				if let Ok(text) = fs::read_to_string(&file) {
+					stats.file_count += 1;
+					parser::for_loops::parse(&mut stats, &text);
+				} else {
+					stats.failed_file_count += 1;
+				}
+				let _ = tx.send(stats);
+			});
+		}
+		rx
+	};
+	let mut stats = Stats::default();
+	while let Some(file_stat) = rx.recv().await {
+		stats += file_stat;
+	}
+	println!("{stats}");
+}
+
+/// needs ../books.tar.gz to be extracted into ../books
+#[test]
+fn test() {
+	use std::{env, fs, process::Command, time::Instant};
+	println!("cwd: {}", env::current_dir().unwrap().display());
+
+	//compile
+	let mut compile = Command::new("cargo");
+	let compile_arged = compile.arg("build").arg("--release");
+	match compile_arged.output() {
+		Ok(output) => println!("compiled {}", String::from_utf8_lossy(&output.stdout)),
+		Err(err) => eprintln!("compile failed: {err}"),
+	}
+
+	//get test files
+	let files = fs::read_dir("../books")
+		.unwrap()
+		.map(|f| {
+			f.unwrap()
+				.path()
+				.canonicalize()
+				.unwrap()
+				.to_str()
+				.unwrap()
+				.to_string()
+		})
+		.collect::<Vec<_>>();
+	println!("test files found: {}", files.len());
+
+	println!();
+
+	//benchmark run
+	let benchmark = Instant::now();
+	let mut run = Command::new("target/release/jisspam");
+	let run_arged = run.args(files);
+	match run_arged.output() {
+		Ok(output) => println!("{}", String::from_utf8_lossy(&output.stdout)),
+		Err(err) => eprintln!("run failed: {err}"),
+	}
+	println!("benchmark: {}ms", benchmark.elapsed().as_millis());
+}

jest_rust/src/parser/for_loops.rs

@@ -0,0 +1,37 @@
+use crate::{FORBIDDEN_WORDS, stats::Stats};
+
+#[allow(dead_code)]
+/// typically 5000ms
+/// with trie this is 1600ms
+pub fn parse(stats: &mut Stats, text: &str) {
+	for sentence in text
+		.split('.')
+		.map(|s| s.trim())
+		.filter(|s| !s.is_empty())
+	{
+		stats.sentence_count += 1;
+		for word in sentence
+			.split_ascii_whitespace()
+			.map(|s| s.trim())
+			.filter(|s| !s.is_empty())
+		{
+			stats.word_count += 1;
+			//get all numbers counted
+			let mut all_capitalized = true;
+			for char in word.chars() {
+				if char.is_numeric() {
+					stats.numeric_count += 1;
+					all_capitalized = false;
+				} else if !char.is_ascii_uppercase() {
+					all_capitalized = false;
+				}
+			}
+			if all_capitalized {
+				stats.capitalized_count += 1;
+			}
+			if FORBIDDEN_WORDS.contains(&word.to_lowercase()) {
+				stats.forbidden_count += 1;
+			}
+		}
+	}
+}

jest_rust/src/parser/for_loops_forbidden_only.rs

@@ -0,0 +1,14 @@
+use crate::{FORBIDDEN_WORDS, stats::Stats};
+
+#[allow(dead_code)]
+pub fn parse(stats: &mut Stats, text: &str) {
+	for word in text
+		.split_ascii_whitespace()
+		.map(|s| s.trim())
+		.filter(|s| !s.is_empty())
+	{
+		if FORBIDDEN_WORDS.contains(&word.to_lowercase()) {
+			stats.forbidden_count += 1;
+		}
+	}
+}

jest_rust/src/parser/mod.rs

@@ -0,0 +1,3 @@
+pub mod for_loops;
+pub mod for_loops_forbidden_only;
+pub mod muncher;

jest_rust/src/parser/muncher.rs

@@ -0,0 +1,66 @@
+use crate::{FORBIDDEN_WORDS, stats::Stats};
+
+#[allow(dead_code)]
+/// probably buggy. for example, are new lines sentences? what if the text has no last period?
+/// 500ms is without forbidden words check, but...
+/// 6000ms if adding forbidden words.. so not faster
+/// with trie this is 2600ms
+pub fn parse(stats: &mut Stats, text: &str) {
+	let mut capitalized = true;
+	let mut whitespaced = false;
+	let mut dotted = false;
+	let mut word = String::new();
+	for char in text.chars() {
+		if whitespaced {
+			if !char.is_whitespace() {
+				whitespaced = false; //end whiteness
+			}
+			continue;
+		} else if char.is_whitespace() {
+			whitespaced = true;
+			stats.word_count += 1; //end of word
+			if capitalized {
+				stats.capitalized_count += 1;
+			} else {
+				//reset capitalized word
+				capitalized = true;
+			}
+			let lowercase_word = word.to_lowercase();
+			if FORBIDDEN_WORDS.contains(&lowercase_word) {
+				stats.forbidden_count += 1;
+			}
+			word = String::new();
+			continue;
+		}
+		if dotted {
+			if char != '.' {
+				dotted = false; //end sentencing
+			}
+			continue;
+		} else if char == '.' {
+			dotted = true;
+			stats.sentence_count += 1;
+			stats.word_count += 1; //end of word
+			if capitalized {
+				stats.capitalized_count += 1;
+			} else {
+				//reset capitalized word
+				capitalized = true;
+			}
+			let lowercase_word = word.to_lowercase();
+			if FORBIDDEN_WORDS.contains(&lowercase_word) {
+				stats.forbidden_count += 1;
+			}
+			word = String::new();
+			continue;
+		}
+		word += &char.to_string();
+		if char.is_numeric() {
+			stats.numeric_count += 1;
+			capitalized = false;
+		}
+		if !char.is_ascii_uppercase() {
+			capitalized = false;
+		}
+	}
+}

jest_rust/src/stats.rs

@@ -0,0 +1,58 @@
+use std::{fmt::Display, ops::AddAssign};
+
+#[derive(Debug, Default)]
+pub struct Stats {
+	pub file_count: u32,
+	pub failed_file_count: u32,
+
+	pub sentence_count: u32,
+	pub word_count: u32,
+
+	pub capitalized_count: u32,
+	pub numeric_count: u32,
+	pub forbidden_count: u32,
+}
+
+impl AddAssign for Stats {
+	fn add_assign(&mut self, rhs: Self) {
+		self.file_count += rhs.file_count;
+		self.failed_file_count += rhs.failed_file_count;
+
+		self.sentence_count += rhs.sentence_count;
+		self.word_count += rhs.word_count;
+
+		self.capitalized_count += rhs.capitalized_count;
+		self.numeric_count += rhs.numeric_count;
+		self.forbidden_count += rhs.forbidden_count;
+	}
+}
+impl Display for Stats {
+	fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+		writeln!(f, "file count: {}", self.file_count)?;
+		writeln!(f, "failed file count: {}", self.failed_file_count)?;
+
+		writeln!(f, "sentence count: {}", self.sentence_count)?;
+		writeln!(f, "word count: {}", self.word_count)?;
+
+		writeln!(f, "capitalized count: {}", self.capitalized_count)?;
+		writeln!(f, "numeric count: {}", self.numeric_count)?;
+		writeln!(f, "forbidden count: {}", self.forbidden_count)?;
+
+		let word_count = self.word_count as f32;
+		writeln!(
+			f,
+			"words per sentence average: {:.1}",
+			word_count / self.sentence_count as f32
+		)?;
+		writeln!(
+			f,
+			"forbidden word percentage: {:.2}%",
+			(self.forbidden_count as f32 / word_count) * 100.0,
+		)?;
+		write!(
+			f,
+			"capitalized word percentage: {:.2}%",
+			(self.capitalized_count as f32 / word_count) * 100.0,
+		)
+	}
+}

jest_rust/src/trie.rs

@@ -0,0 +1,33 @@
+use fxhash::FxBuildHasher;
+use std::collections::HashMap;
+
+type FxHashMap<K, V> = HashMap<K, V, FxBuildHasher>; //simpler, slightly faster
+
+#[derive(Default, Debug, Clone)]
+struct Node {
+	end: bool,
+	children: FxHashMap<char, Node>,
+}
+#[derive(Default, Debug, Clone)]
+pub struct Trie {
+	root: Node,
+}
+impl Trie {
+	pub fn insert(&mut self, word: &str) {
+		let mut node = &mut self.root;
+		for char in word.chars() {
+			node = node.children.entry(char).or_default();
+		}
+		node.end = true;
+	}
+	pub fn contains(&self, word: &str) -> bool {
+		let mut current_node = &self.root;
+		for char in word.chars() {
+			match current_node.children.get(&char) {
+				Some(node) => current_node = node,
+				None => return false,
+			}
+		}
+		current_node.end
+	}
+}

retoor_c/isspam.py

@@ -0,0 +1,85 @@
+import os
+import sys
+import threading
+from concurrent.futures import ThreadPoolExecutor
+
+MAX_TEXT_LENGTH = 1024
+FORBIDDEN_WORDS_COUNT = 40
+
+forbidden_words = set([
+    "recovery", "techie", "http", "https", "digital", "hack", "::", "//", "com",
+    "@", "crypto", "bitcoin", "wallet", "hacker", "welcome", "whatsapp", "email", "cryptocurrency",
+    "stolen", "freeze", "quick", "crucial", "tracing", "scammers", "expers", "hire", "century",
+    "transaction", "essential", "managing", "contact", "contacting", "understanding", "assets", "funds",
+])
+
+class AnalysisResult:
+    def __init__(self, filename):
+        self.filename = filename
+        self.total_word_count = 0
+        self.total_capitalized_count = 0
+        self.total_sentence_count = 0
+        self.total_number_count = 0
+        self.total_forbidden_count = 0
+
+def is_forbidden(word):
+    return word in forbidden_words
+
+def read_file(filename):
+    if not os.path.exists(filename):
+        print(f"File doesn't exist: {filename}")
+        return None
+
+    with open(filename, 'r') as file:
+        return file.read()
+
+def analyze_file(result):
+    text = read_file(result.filename)
+    if text:
+        result.total_sentence_count = text.count('.')
+        tokens = text.split()
+
+        result.total_word_count = len(tokens)
+        result.total_capitalized_count = sum(1 for token in tokens if token[0].isupper())
+        result.total_number_count = sum(1 for token in tokens if any(char.isdigit() for char in token))
+        result.total_forbidden_count = sum(1 for token in tokens if is_forbidden(token))
+
+def main():
+    if len(sys.argv) < 2:
+        print(f"Usage: {sys.argv[0]} <file1> <file2> ... <fileN>")
+        return
+
+    results = []
+
+    with ThreadPoolExecutor() as executor:
+        futures = []
+        for filename in sys.argv[1:]:
+            result = AnalysisResult(filename)
+            results.append(result)
+            futures.append(executor.submit(analyze_file, result))
+
+        for future in futures:
+            future.result()
+
+    total_word_count = sum(result.total_word_count for result in results)
+    total_capitalized_count = sum(result.total_capitalized_count for result in results)
+    total_sentence_count = sum(result.total_sentence_count for result in results)
+    total_number_count = sum(result.total_number_count for result in results)
+    total_forbidden_count = sum(result.total_forbidden_count for result in results)
+
+    capitalized_percentage = (total_word_count > 0) * (total_capitalized_count / total_word_count * 100.0)
+    forbidden_percentage = (total_word_count > 0) * (total_forbidden_count / total_word_count * 100.0)
+    word_count_per_sentence = (total_sentence_count > 0) * (total_word_count / total_sentence_count)
+
+    print(f"\nTotal Words: {total_word_count}")
+    print(f"Total Capitalized words: {total_capitalized_count}")
+    print(f"Total Sentences: {total_sentence_count}")
+    print(f"Total Numbers: {total_number_count}")
+    print(f"Total Forbidden words: {total_forbidden_count}")
+    print(f"Capitalized percentage: {capitalized_percentage:.6f}%")
+    print(f"Forbidden percentage: {forbidden_percentage:.6f}%")
+    print(f"Word count per sentence: {word_count_per_sentence:.6f}")
+    print(f"Total files read: {len(sys.argv) - 1}")
+
+if __name__ == "__main__":
+    main()