From b4bbe9dc4e72c1d456559a0257165b0de209aa78 Mon Sep 17 00:00:00 2001 From: Krishna Vedala <7001608+kvedala@users.noreply.github.com> Date: Thu, 27 Aug 2020 12:30:14 -0400 Subject: [PATCH] [code fix] Fixed trie_tree for code quality and docs & clang-tidy error check (#1059) * attempt to fix trie-tree code * clang-tidy fixes * remove performance-unnecessary-value-param as error - this has auto-fix * make test() static * added original author to the description * added namespace * doc updates * fix true spelling * extended to small & big caps alphabets - 52 characters * clang-format and clang-tidy fixes for edc2247a * move const parameter to after the parameters Co-authored-by: github-actions <${GITHUB_ACTOR}@users.noreply.github.com> --- .clang-tidy | 2 +- data_structures/trie_tree.cpp | 266 ++++++++++++++++++++++++---------- 2 files changed, 193 insertions(+), 75 deletions(-) diff --git a/.clang-tidy b/.clang-tidy index 113d688e7..99d867ab4 100644 --- a/.clang-tidy +++ b/.clang-tidy @@ -1,6 +1,6 @@ --- Checks: '-*,google-*,clang-analyzer-*,-clang-analyzer-security.insecureAPI.*,cppcoreguidelines-*,-cppcoreguidelines-avoid-magic-numbers,-cppcoreguidelines-pro-bounds-*,openmp-*,performance-*,portability-*,modernize-*,-modernize-use-trailing-*' -WarningsAsErrors: '*,-google-readability-*,-google-explicit-constructor,-modernize-*,modernize-avoid-c-arrays,-performance-move-const-arg,-performance-noexcept-move-constructor,-cppcoreguidelines-init-variables,-cppcoreguidelines-pro-*,-cppcoreguidelines-owning-memory,-clang-analyzer-cplusplus.Move' +WarningsAsErrors: '*,-google-readability-*,-google-explicit-constructor,-modernize-*,modernize-avoid-c-arrays,-performance-move-const-arg,-performance-noexcept-move-constructor,-performance-unnecessary-value-param,-cppcoreguidelines-init-variables,-cppcoreguidelines-pro-*,-cppcoreguidelines-owning-memory,-clang-analyzer-cplusplus.Move' HeaderFilterRegex: '' AnalyzeTemporaryDtors: false FormatStyle: '{ BasedOnStyle: Google, UseTab: Never, IndentWidth: 4, TabWidth: 4, AllowShortIfStatementsOnASingleLine: false, IndentCaseLabels: true, ColumnLimit: 80, AccessModifierOffset: -3, AlignConsecutiveMacros: true }' diff --git a/data_structures/trie_tree.cpp b/data_structures/trie_tree.cpp index a613ebd8f..c95438cab 100644 --- a/data_structures/trie_tree.cpp +++ b/data_structures/trie_tree.cpp @@ -1,91 +1,209 @@ -#include -#include - +/** + * @file + * @author [@Arctic2333](https://github.com/Arctic2333) + * @author [Krishna Vedala](https://github.com/kvedala) + * @brief Implementation of [Trie](https://en.wikipedia.org/wiki/Trie) data + * structure for English alphabets in small characters. + * @note the function ::data_structure::trie::deleteString might be erroneous + * @see trie_modern.cpp + */ +#include +#include #include +#include #include +#include -// structure definition -typedef struct trie { - struct trie* arr[26]; - bool isEndofWord; -} trie; +/** \namespace data_structure + * \brief Data-structure algorithms + */ +namespace data_structure { +/** + * @brief [Trie](https://en.wikipedia.org/wiki/Trie) implementation for + * small-case English alphabets `a-z` + */ +class trie { + private: + static constexpr uint8_t NUM_CHARS = 26; ///< Number of alphabets + /** @brief Recursive tree nodes as an array of shared-pointers */ + std::array, NUM_CHARS << 1> arr; + bool isEndofWord = false; ///< identifier if a node is terminal node -// create a new node for trie -trie* createNode() { - trie* nn = new trie(); - for (int i = 0; i < 26; i++) nn->arr[i] = NULL; - nn->isEndofWord = false; - return nn; -} - -// insert string into the trie -void insert(trie* root, std::string str) { - for (int i = 0; i < str.length(); i++) { - int j = str[i] - 'a'; - if (root->arr[j]) { - root = root->arr[j]; - } else { - root->arr[j] = createNode(); - root = root->arr[j]; + /** + * @brief Convert a character to integer for indexing + * + * @param ch character to index + * @return unsigned integer index + */ + uint8_t char_to_int(const char& ch) const { + if (ch >= 'A' && ch <= 'Z') { + return ch - 'A'; + } else if (ch >= 'a' && ch <= 'z') { + return ch - 'a' + NUM_CHARS; } - } - root->isEndofWord = true; -} -// search a string exists inside the trie -bool search(trie* root, std::string str, int index) { - if (index == str.length()) { - if (!root->isEndofWord) - return false; - return true; + std::cerr << "Invalid character present. Exiting..."; + std::exit(EXIT_FAILURE); + return 0; } - int j = str[index] - 'a'; - if (!root->arr[j]) - return false; - return search(root->arr[j], str, index + 1); -} -/* -removes the string if it is not a prefix of any other -string, if it is then just sets the endofword to false, else -removes the given string -*/ -bool deleteString(trie* root, std::string str, int index) { - if (index == str.length()) { - if (!root->isEndofWord) - return false; - root->isEndofWord = false; - for (int i = 0; i < 26; i++) return false; - return true; - } - int j = str[index] - 'a'; - if (!root->arr[j]) - return false; - bool var = deleteString(root, str, index + 1); - if (var) { - root->arr[j] = NULL; - if (root->isEndofWord) { - return false; - } else { - int i; - for (i = 0; i < 26; i++) - if (root->arr[i]) - return false; + /** search a string exists inside a given root trie + * @param str string to search for + * @param index start index to search from + * @returns `tre` if found + * @returns `false` if not found + */ + bool search(const std::shared_ptr& root, const std::string& str, + int index) { + if (index == str.length()) { + if (!root->isEndofWord) { + return false; + } return true; } + int j = char_to_int(str[index]); + if (!root->arr[j]) { + return false; + } + return search(root->arr[j], str, index + 1); } - /* should not return here */ - std::cout << __func__ << ":" << __LINE__ << "Should not reach this line\n"; - return false; + public: + trie() = default; ///< Class default constructor + + /** insert string into the trie + * @param str String to insert in the tree + */ + void insert(const std::string& str) { + std::shared_ptr root(nullptr); + + for (const char& ch : str) { + int j = char_to_int(ch); + if (root) { + if (root->arr[j]) { + root = root->arr[j]; + } else { + std::shared_ptr temp(new trie()); + root->arr[j] = temp; + root = temp; + } + } else if (arr[j]) { + root = arr[j]; + } else { + std::shared_ptr temp(new trie()); + arr[j] = temp; + root = temp; + } + } + root->isEndofWord = true; + } + + /** search a string exists inside the trie + * @param str string to search for + * @param index start index to search from + * @returns `true` if found + * @returns `false` if not found + */ + bool search(const std::string& str, int index) { + if (index == str.length()) { + if (!isEndofWord) { + return false; + } + return true; + } + int j = char_to_int(str[index]); + if (!arr[j]) { + return false; + } + return search(arr[j], str, index + 1); + } + + /** + * removes the string if it is not a prefix of any other + * string, if it is then just sets the ::data_structure::trie::isEndofWord + * to false, else removes the given string + * @note the function ::data_structure::trie::deleteString might be + * erroneous + * @todo review the function ::data_structure::trie::deleteString and the + * commented lines + * @param str string to remove + * @param index index to remove from + * @returns `true` if successful + * @returns `false` if unsuccessful + */ + bool deleteString(const std::string& str, int index) { + if (index == str.length()) { + if (!isEndofWord) { + return false; + } + isEndofWord = false; + // following lines - possible source of error? + // for (int i = 0; i < NUM_CHARS; i++) + // if (!arr[i]) + // return false; + return true; + } + int j = char_to_int(str[index]); + if (!arr[j]) { + return false; + } + bool var = deleteString(str, index + 1); + if (var) { + arr[j].reset(); + if (isEndofWord) { + return false; + } else { + int i = 0; + for (i = 0; i < NUM_CHARS; i++) { + if (arr[i]) { + return false; + } + } + return true; + } + } + + /* should not return here */ + std::cout << __func__ << ":" << __LINE__ + << "Should not reach this line\n"; + return false; + } +}; +} // namespace data_structure + +/** + * @brief Testing function + * @returns void + */ +static void test() { + data_structure::trie root; + root.insert("Hello"); + root.insert("World"); + + assert(!root.search("hello", 0)); + std::cout << "hello - " << root.search("hello", 0) << "\n"; + + assert(root.search("Hello", 0)); + std::cout << "Hello - " << root.search("Hello", 0) << "\n"; + + assert(!root.search("Word", 0)); + std::cout << "Word - " << root.search("Word", 0) << "\n"; + + assert(root.search("World", 0)); + std::cout << "World - " << root.search("World", 0) << "\n"; + + // Following lines of code give erroneous output + // root.deleteString("hello", 0); + // assert(!root.search("hello", 0)); + // std::cout << "hello - " << root.search("world", 0) << "\n"; } +/** + * @brief Main function + * @return 0 on exit + */ int main() { - trie* root = createNode(); - insert(root, "hello"); - insert(root, "world"); - int a = search(root, "hello", 0); - int b = search(root, "word", 0); - printf("%d %d ", a, b); + test(); + return 0; }