etl: initial commit

This commit is contained in:
Dmitry Kokorin 2016-03-07 21:17:32 +03:00
parent e5991ec511
commit 3cb7c2bff1
3 changed files with 209 additions and 0 deletions

52
cpp/etl/CMakeLists.txt Normal file
View file

@ -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})

81
cpp/etl/README.md Normal file
View file

@ -0,0 +1,81 @@
# Etl
We are going to do the `Transform` step of an Extract-Transform-Load.
### ETL
Extract-Transform-Load (ETL) is a fancy way of saying, "We have some crufty, legacy data over in this system, and now we need it in this shiny new system over here, so
we're going to migrate this."
(Typically, this is followed by, "We're only going to need to run this
once." That's then typically followed by much forehead slapping and
moaning about how stupid we could possibly be.)
### The goal
We're going to extract some scrabble scores from a legacy system.
The old system stored a list of letters per score:
- 1 point: "A", "E", "I", "O", "U", "L", "N", "R", "S", "T",
- 2 points: "D", "G",
- 3 points: "B", "C", "M", "P",
- 4 points: "F", "H", "V", "W", "Y",
- 5 points: "K",
- 8 points: "J", "X",
- 10 points: "Q", "Z",
The shiny new scrabble system instead stores the score per letter, which
makes it much faster and easier to calculate the score for a word. It
also stores the letters in lower-case regardless of the case of the
input letters:
- "a" is worth 1 point.
- "b" is worth 3 points.
- "c" is worth 3 points.
- "d" is worth 2 points.
- Etc.
Your mission, should you choose to accept it, is to write a program that
transforms the legacy data format to the shiny new format.
### Notes
A final note about scoring, Scrabble is played around the world in a
variety of languages, each with its own unique scoring table. For
example, an "A" is scored at 14 in the Basque-language version of the
game while being scored at 9 in the Latin-language version.
## 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 Jumpstart Lab team [view source](http://jumpstartlab.com)

76
cpp/etl/etl_test.cpp Normal file
View file

@ -0,0 +1,76 @@
#include "etl.h"
#define BOOST_TEST_MAIN
#include <boost/test/unit_test.hpp>
namespace boost
{
// teach Boost.Test how to print std::pair
template <typename K, typename V>
inline wrap_stringstream&
operator<<(wrap_stringstream& wrapped, std::pair<const K, V> const& item)
{
return wrapped << '<' << item.first << ',' << item.second << '>';
}
}
#define REQUIRE_EQUAL_CONTAINERS(left_, right_) \
BOOST_REQUIRE_EQUAL_COLLECTIONS(left_.begin(), left_.end(), right_.begin(), right_.end())
BOOST_AUTO_TEST_CASE(transforms_one_value)
{
const std::map<int, std::vector<char>> old{{1, {'A'}}};
const auto actual = etl::transform(old);
const std::map<char, int> expected{{'a', 1}};
REQUIRE_EQUAL_CONTAINERS(expected, actual);
}
#if defined(EXERCISM_RUN_ALL_TESTS)
BOOST_AUTO_TEST_CASE(transforms_more_values)
{
const std::map<int, std::vector<char>> old{{1, {'A', 'E', 'I', 'O', 'U'}}};
const auto actual = etl::transform(old);
const std::map<char, int> expected{{'a', 1}, {'e', 1}, {'i', 1}, {'o', 1}, {'u', 1}};
REQUIRE_EQUAL_CONTAINERS(expected, actual);
}
BOOST_AUTO_TEST_CASE(transforms_more_keys)
{
const std::map<int, std::vector<char>> old{{1, {'A', 'E'}}, {2, {'D', 'G'}}};
const auto actual = etl::transform(old);
const std::map<char, int> expected{{'a', 1}, {'e', 1}, {'d', 2}, {'g', 2}};
REQUIRE_EQUAL_CONTAINERS(expected, actual);
}
BOOST_AUTO_TEST_CASE(transforms_a_full_dataset)
{
const std::map<int, std::vector<char>> old{
{1, {'A', 'E', 'I', 'O', 'U', 'L', 'N', 'R', 'S', 'T'}},
{2, {'D', 'G'}},
{3, {'B', 'C', 'M', 'P'}},
{4, {'F', 'H', 'V', 'W', 'Y'}},
{5, {'K'}},
{8, {'J', 'X'}},
{10, {'Q', 'Z'}}
};
const auto actual = etl::transform(old);
const std::map<char, int> expected{
{'a', 1}, {'b', 3}, {'c', 3}, {'d', 2}, {'e', 1},
{'f', 4}, {'g', 2}, {'h', 4}, {'i', 1}, {'j', 8},
{'k', 5}, {'l', 1}, {'m', 3}, {'n', 1}, {'o', 1},
{'p', 3}, {'q', 10}, {'r', 1}, {'s', 1}, {'t', 1},
{'u', 1}, {'v', 4}, {'w', 4}, {'x', 8}, {'y', 4},
{'z', 10}
};
REQUIRE_EQUAL_CONTAINERS(expected, actual);
}
#endif