From ead8d3fbf33c96900d8a1ed539654749531e5895 Mon Sep 17 00:00:00 2001 From: Dmitry Kokorin Date: Mon, 22 Feb 2016 10:51:26 +0300 Subject: [PATCH] hamming: initial commit --- cpp/hamming/CMakeLists.txt | 52 ++++++++++++++++++++++++++ cpp/hamming/README.md | 72 ++++++++++++++++++++++++++++++++++++ cpp/hamming/hamming.cpp | 10 +++++ cpp/hamming/hamming.h | 7 ++++ cpp/hamming/hamming_test.cpp | 51 +++++++++++++++++++++++++ 5 files changed, 192 insertions(+) create mode 100644 cpp/hamming/CMakeLists.txt create mode 100644 cpp/hamming/README.md create mode 100644 cpp/hamming/hamming.cpp create mode 100644 cpp/hamming/hamming.h create mode 100644 cpp/hamming/hamming_test.cpp diff --git a/cpp/hamming/CMakeLists.txt b/cpp/hamming/CMakeLists.txt new file mode 100644 index 0000000..95c7011 --- /dev/null +++ b/cpp/hamming/CMakeLists.txt @@ -0,0 +1,52 @@ +# Get the exercise name from the current directory +get_filename_component(exercise ${CMAKE_CURRENT_SOURCE_DIR} NAME) + +# Basic CMake project +cmake_minimum_required(VERSION 2.8.11) + +# Name the project after the exercise +project(${exercise} CXX) + +# Locate Boost libraries: unit_test_framework, date_time and regex +set(Boost_USE_STATIC_LIBS ON) +set(Boost_USE_MULTITHREADED ON) +set(Boost_USE_STATIC_RUNTIME OFF) +find_package(Boost 1.55 REQUIRED COMPONENTS unit_test_framework date_time regex) + +# Enable C++11 features on gcc/clang +if("${CMAKE_CXX_COMPILER_ID}" MATCHES "(GNU|Clang)") + set(CMAKE_CXX_FLAGS "-std=c++11") +endif() + +# Configure to run all the tests? +if(${EXERCISM_RUN_ALL_TESTS}) + add_definitions(-DEXERCISM_RUN_ALL_TESTS) +endif() + +# Get a source filename from the exercise name by replacing -'s with _'s +string(REPLACE "-" "_" file ${exercise}) + +# Implementation could be only a header +if(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/${file}.cpp) + set(exercise_cpp ${file}.cpp) +else() + set(exercise_cpp "") +endif() + +# Build executable from sources and headers +add_executable(${exercise} ${file}_test.cpp ${exercise_cpp} ${file}.h) + +# We need boost includes +target_include_directories(${exercise} PRIVATE ${Boost_INCLUDE_DIRS}) + +# We need boost libraries +target_link_libraries(${exercise} ${Boost_LIBRARIES}) + +# Tell MSVC not to warn us about unchecked iterators in debug builds +if(${MSVC}) + set_target_properties(${exercise} PROPERTIES + COMPILE_DEFINITIONS_DEBUG _SCL_SECURE_NO_WARNINGS) +endif() + +# Run the tests on every build +add_custom_command(TARGET ${exercise} POST_BUILD COMMAND ${exercise}) diff --git a/cpp/hamming/README.md b/cpp/hamming/README.md new file mode 100644 index 0000000..6640895 --- /dev/null +++ b/cpp/hamming/README.md @@ -0,0 +1,72 @@ +# Hamming + +Write a program that can calculate the Hamming difference between two DNA strands. + +A mutation is simply a mistake that occurs during the creation or +copying of a nucleic acid, in particular DNA. Because nucleic acids are +vital to cellular functions, mutations tend to cause a ripple effect +throughout the cell. Although mutations are technically mistakes, a very +rare mutation may equip the cell with a beneficial attribute. In fact, +the macro effects of evolution are attributable by the accumulated +result of beneficial microscopic mutations over many generations. + +The simplest and most common type of nucleic acid mutation is a point +mutation, which replaces one base with another at a single nucleotide. + +By counting the number of differences between two homologous DNA strands +taken from different genomes with a common ancestor, we get a measure of +the minimum number of point mutations that could have occurred on the +evolutionary path between the two strands. + +This is called the 'Hamming distance'. + +It is found by comparing two DNA strands and counting how many of the +nucleotides are different from their equivalent in the other string. + + GAGCCTACTAACGGGAT + CATCGTAATGACGGCCT + ^ ^ ^ ^ ^ ^^ + +The Hamming distance between these two DNA strands is 7. + +# Implementation notes + +The Hamming distance is only defined for sequences of equal length. This means +that based on the definition, each language could deal with getting sequences +of equal length differently. + +## Getting Started + +Make sure you have read the [getting started with C++](http://help.exercism.io/getting-started-with-cpp.html) +page on the [exercism help site](http://help.exercism.io/). This covers +the basic information on setting up the development environment expected +by the exercises. + +## Passing the Tests + +Get the first test compiling, linking and passing by following the [three +rules of test-driven development](http://butunclebob.com/ArticleS.UncleBob.TheThreeRulesOfTdd). +Create just enough structure by declaring namespaces, functions, classes, +etc., to satisfy any compiler errors and get the test to fail. Then write +just enough code to get the test to pass. Once you've done that, +uncomment the next test by moving the following line past the next test. + +```C++ +#if defined(EXERCISM_RUN_ALL_TESTS) +``` + +This may result in compile errors as new constructs may be invoked that +you haven't yet declared or defined. Again, fix the compile errors minimally +to get a failing test, then change the code minimally to pass the test, +refactor your implementation for readability and expressiveness and then +go on to the next test. + +Try to use standard C++11 facilities in preference to writing your own +low-level algorithms or facilities by hand. [CppReference](http://en.cppreference.com/) +is a wiki reference to the C++ language and standard library. If you +are new to C++, but have programmed in C, beware of +[C traps and pitfalls](http://www.slideshare.net/LegalizeAdulthood/c-traps-and-pitfalls-for-c-programmers). + +## Source + +The Calculating Point Mutations problem at Rosalind [view source](http://rosalind.info/problems/hamm/) diff --git a/cpp/hamming/hamming.cpp b/cpp/hamming/hamming.cpp new file mode 100644 index 0000000..6d32766 --- /dev/null +++ b/cpp/hamming/hamming.cpp @@ -0,0 +1,10 @@ +#include "hamming.h" + +namespace hamming { + +int compute(const char *first, const char *second) { + + return 0; +} + +} diff --git a/cpp/hamming/hamming.h b/cpp/hamming/hamming.h new file mode 100644 index 0000000..b848196 --- /dev/null +++ b/cpp/hamming/hamming.h @@ -0,0 +1,7 @@ +#pragma once + +namespace hamming { + +int compute(const char *first, const char *second); + +} diff --git a/cpp/hamming/hamming_test.cpp b/cpp/hamming/hamming_test.cpp new file mode 100644 index 0000000..3e45cba --- /dev/null +++ b/cpp/hamming/hamming_test.cpp @@ -0,0 +1,51 @@ +#include "hamming.h" +#include +#define BOOST_TEST_MAIN +#include + +BOOST_AUTO_TEST_CASE(no_difference_between_identical_strands) +{ + BOOST_REQUIRE_EQUAL(0, hamming::compute("A", "A")); +} + +#if defined(EXERCISM_RUN_ALL_TESTS) +BOOST_AUTO_TEST_CASE(complete_hamming_distance_for_single_nucleotide_strand) +{ + BOOST_REQUIRE_EQUAL(1, hamming::compute("A", "G")); +} + +BOOST_AUTO_TEST_CASE(complete_hamming_distance_for_small_strand) +{ + BOOST_REQUIRE_EQUAL(2, hamming::compute("AG", "CT")); +} + +BOOST_AUTO_TEST_CASE(small_hamming_distance) +{ + BOOST_REQUIRE_EQUAL(1, hamming::compute("AT", "CT")); +} + +BOOST_AUTO_TEST_CASE(small_hamming_distance_in_longer_strand) +{ + BOOST_REQUIRE_EQUAL(1, hamming::compute("GGACG", "GGTCG")); +} + +BOOST_AUTO_TEST_CASE(domain_error_when_first_string_is_longer) +{ + BOOST_REQUIRE_THROW(hamming::compute("AAAG", "AAA"), std::domain_error); +} + +BOOST_AUTO_TEST_CASE(domain_error_when_second_string_is_longer) +{ + BOOST_REQUIRE_THROW(hamming::compute("AAA", "AAAG"), std::domain_error); +} + +BOOST_AUTO_TEST_CASE(large_hamming_distance) +{ + BOOST_REQUIRE_EQUAL(4, hamming::compute("GATACA", "GCATAA")); +} + +BOOST_AUTO_TEST_CASE(hamming_distance_in_very_long_strand) +{ + BOOST_REQUIRE_EQUAL(9, hamming::compute("GGACGGATTCTG", "AGGACGGATTCT")); +} +#endif