merge dev

.clang-format

@@ -0,0 +1,114 @@
+Language:        Cpp
+# BasedOnStyle:  LLVM
+AccessModifierOffset: -2
+AlignAfterOpenBracket: Align
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlines: DontAlign
+AlignOperands:   true
+AlignTrailingComments: false
+AllowAllParametersOfDeclarationOnNextLine: true
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterDefinitionReturnType: None
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: false
+AlwaysBreakTemplateDeclarations: Yes
+BinPackArguments: true
+BinPackParameters: true
+BreakBeforeBraces: Allman
+BraceWrapping:
+  AfterClass:      true
+  AfterControlStatement: true
+  AfterEnum:       true
+  AfterFunction:   true
+  AfterNamespace:  true
+  AfterObjCDeclaration: true
+  AfterStruct:     true
+  AfterUnion:      true
+  AfterExternBlock: true
+  BeforeCatch:     true
+  BeforeElse:      true
+  IndentBraces:    true
+  SplitEmptyFunction: false
+  SplitEmptyRecord: false
+  SplitEmptyNamespace: false
+BreakBeforeBinaryOperators: None
+BreakBeforeInheritanceComma: false
+BreakInheritanceList: BeforeColon
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakConstructorInitializers: BeforeColon
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: true
+ColumnLimit:     120
+CommentPragmas:  '^ [NOTE|WARNING|TODO|FIXME]:'
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: false
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat:   false
+FixNamespaceComments: false
+ForEachMacros:   
+  - foreach
+  - Q_FOREACH
+  - BOOST_FOREACH
+IncludeBlocks:   Preserve
+IncludeCategories: 
+  - Regex:           '^"(llvm|llvm-c|clang|clang-c)/'
+    Priority:        2
+  - Regex:           '^(<|"(gtest|gmock|isl|json)/)'
+    Priority:        3
+  - Regex:           '.*'
+    Priority:        1
+IncludeIsMainRegex: '(Test)?$'
+IndentCaseLabels: false
+IndentPPDirectives: None
+IndentWidth:     2
+IndentWrappedFunctionNames: false
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: true
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: All
+ObjCBinPackProtocolList: Auto
+ObjCBlockIndentWidth: 2
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: true
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 19
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 60
+PointerAlignment: Left
+ReflowComments:  true
+SortIncludes:    false
+SortUsingDeclarations: false
+SpaceAfterCStyleCast: false
+SpaceAfterTemplateKeyword: false
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: Never
+SpaceBeforeRangeBasedForLoopColon: false
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 1
+SpacesInAngles:  false
+SpacesInContainerLiterals: false
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard:        Cpp11
+TabWidth:        2
+UseTab:          Never

README.md

@@ -3,11 +3,11 @@
 header-only libraries written in modern C++ (11, 14, 17, 2a).
 
 
-|item| describe |
+|item| description |
 |-|-|
+|[bloom](./bloom)| nαïve bloom filter |
 |[cfg](./cfg)| hash table |
 |[channel](./channel) | [Rust](https://www.rust-lang.org)-like [channel](https://doc.rust-lang.org/std/sync/mpsc/fn.channel.html) implementation based on lock-free mpsc queue |
-|[clp](./clp) | C++17  feature test |
 |[coroutine](./coroutine) | coroutine impl from scratch, demonstrate how to impl your own coroutine |
 |[crypt](./crypt) | toy |
 |[fake_variant](./fake_variant)| tuple-like class based on multi-inherit |

bloom/CMakeLists.txt

@@ -0,0 +1,12 @@
+cmake_minimum_required(VERSION 3.15)
+project(bloom)
+
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_CXX_EXTENSIONS OFF)
+
+include_directories(${PROJECT_SOURCE_DIR}/murmur3)
+
+add_subdirectory(murmur3)
+add_executable(bloom bloom.h main.cpp)
+target_link_libraries(bloom murmur3)

bloom/README.md

@@ -0,0 +1 @@
+a naive bloom filter implementation :cherry_blossom::rooster:

bloom/bloom.h

@@ -0,0 +1,100 @@
+/*********************************************************
+          File Name:bloom_filter.h
+          Author: Abby Cin
+          Mail: [email protected]
+          Created Time: Sun 23 Aug 2020 03:51:01 PM CST
+**********************************************************/
+
+#ifndef BLOOM_FILTER_H
+#define BLOOM_FILTER_H
+
+#include <cmath>
+#include <functional>
+#include <string_view>
+#include <vector>
+#include "MurmurHash3.h"
+#include <iostream>
+
+class BloomFilter
+{
+public:
+  template<typename... Args>
+  static void print(Args&&... args)
+  {
+    ((std::cout << args << ' '), ...);
+    std::cout << '\n';
+  }
+
+  // n: collection size
+  // r: expect false positive ratio
+  BloomFilter(size_t n, double r)
+  {
+    n_ = n;
+    nb_ = -1 * (n_ * std::log(r)) / std::pow(std::log(2), 2);
+    k_ = std::ceil(std::log(2) * nb_ / n_);
+    init();
+    print("size:", bits_.size(), nb_);
+  }
+
+  [[nodiscard]] double estimate() const { return std::pow(1 - std::exp(-((double)n_ * k_ / nb_)), k_); }
+
+  void add(std::string_view x)
+  {
+    for(auto& f: hash_)
+    {
+      auto h = f(x) % nb_;
+      size_t span = h / width_;
+      size_t slot = h % width_;
+      bits_[span] |= slot;
+    }
+  }
+
+  bool test(std::string_view x)
+  {
+    for(auto& f: hash_)
+    {
+      auto h = f(x) % nb_;
+      size_t span = h / width_;
+      size_t slot = h % width_;
+      if(!(bits_[span] & slot))
+      {
+        return false;
+      }
+    }
+    return true;
+  }
+
+private:
+  using hash_func = std::function<int64_t(std::string_view)>;
+  constexpr static size_t width_ = sizeof(uint64_t) * 8;
+  size_t n_;
+  size_t nb_;
+  size_t k_;
+  std::vector<uint64_t> bits_;
+  std::vector<hash_func> hash_;
+
+  void init()
+  {
+    bits_.resize(nb_ / width_ + 1); // ceil
+    for(size_t i = 0; i < k_; ++i)
+    {
+      hash_.emplace_back([i](std::string_view x) -> uint64_t {
+        uint32_t h = 0;
+        uint32_t l = 0;
+        hash(x, &h, &l);
+        uint64_t r = h;
+        r <<= sizeof(uint32_t);
+        r |= (i + 1) * l;
+        return r;
+      });
+    }
+  }
+
+  static void hash(std::string_view x, uint32_t* h, uint32_t* l)
+  {
+    MurmurHash3_x86_32(x.data(), x.size(), 7, l);
+    MurmurHash3_x86_32(x.data(), x.size(), 17, h);
+  }
+};
+
+#endif // BLOOM_FILTER_H

bloom/main.cpp

@@ -0,0 +1,44 @@
+/*********************************************************
+          File Name:main.cpp
+          Author: Abby Cin
+          Mail: [email protected]
+          Created Time: Sun 23 Aug 2020 03:51:10 PM CST
+**********************************************************/
+
+#include "bloom.h"
+
+int main()
+{
+  using namespace std::string_view_literals;
+  using namespace std;
+  BloomFilter bl{100, 0.001};
+  cout << bl.estimate() << '\n';
+  vector<string_view> vs;
+  vs.emplace_back("are");
+  vs.emplace_back("are you");
+  vs.emplace_back("are you ok");
+  vs.emplace_back("are you ok?");
+
+  vector<string_view> ha;
+  ha.emplace_back("are ");
+  ha.emplace_back("are you ");
+  ha.emplace_back("are you ok ");
+
+  for(auto x: vs)
+  {
+    bl.add(x);
+  }
+
+  cout << boolalpha;
+  for(auto x: vs)
+  {
+    BloomFilter::print(x, "=>", bl.test(x));
+  }
+
+  BloomFilter::print("==========================");
+
+  for(auto x: ha)
+  {
+    BloomFilter::print(x, "=>", bl.test(x));
+  }
+}

bloom/murmur3/CMakeLists.txt

@@ -0,0 +1 @@
+add_library(murmur3 MurmurHash3.h MurmurHash3.cpp)