metacrunch-file 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 555569202d70aa4a0553d8d3c5ffa7396379e84d
-  data.tar.gz: f3709c10ca420fed0ab6e3ba9f8b6caf1f2ba6c4
+  metadata.gz: f457f5fcca1eb193efe81c0e7c8f02d73b42bc7e
+  data.tar.gz: 64f70e6bf5a0d45014853bbae5d09e75456a67c1
 SHA512:
-  metadata.gz: e89c3de4bde0f2c03962e44b061aa49069c96c8f7672a2f3954e97e00104977e28699defeb0741986f9379af1b86632b8613b5aad2580ed2e0e9a05e93c058b9
-  data.tar.gz: c8c17793d191d8aa21e76fc15505e82f3522a2df3009b108d83af8eb10e61112525337bc759a6bfcf3f2c4f3b39c1ac0d8c1e866c90febf32a35b0a3f79e3560
+  metadata.gz: 80edcd6aaa76b570371fd14b6bbe59a50df168e2471e265075b5607504ae8270d33a2787dfab48bf038d30d8d8261b1c178d7ec306f127873b2bac1a654f64ac
+  data.tar.gz: 3ab68b17ab6f7971e286d6177db0c80a4d1b8a83d1d97b707e1ee188e1af55eb2ba1239bc2d47262abc190f7f52503418577e62e5ec6707f4e5d188b13e77197

data/.circleci/config.yml

@@ -0,0 +1,36 @@
+# Ruby CircleCI 2.0 configuration file
+#
+# Check https://circleci.com/docs/2.0/language-ruby/ for more details
+#
+version: 2
+jobs:
+  build:
+    docker:
+      - image: circleci/ruby:2.4.1-node-browsers
+
+    working_directory: ~/repo
+
+    steps:
+      - checkout
+
+      - run:
+          name: Install dependencies
+          command: bundle install --jobs=4 --retry=3 --path vendor/bundle
+
+      - run:
+          name: Install CodeClimate test coverage reporter
+          command: |
+            curl -L https://codeclimate.com/downloads/test-reporter/test-reporter-latest-linux-amd64 > ./cc-test-reporter
+            chmod +x ./cc-test-reporter
+            ./cc-test-reporter before-build
+
+      - run:
+          name: Run tests
+          command: |
+            mkdir /tmp/test-results
+            bundle exec rspec --format progress --format RspecJunitFormatter --out /tmp/test-results/rspec.xml
+
+      - run:
+          name: Upload test coverage report to CodeClimate
+          command: ./cc-test-reporter after-build --exit-code $?
+

data/Gemfile

@@ -5,7 +5,6 @@ gemspec
 group :development do
   gem "bundler", ">= 1.15"
   gem "rake",    ">= 12.1"
-  gem "rspec",   ">= 3.5.0", "< 4.0.0"
 
   if !ENV["CI"]
     gem "pry-byebug", ">= 3.5.0"
@@ -13,5 +12,8 @@ group :development do
 end
 
 group :test do
-  gem "simplecov", ">= 0.15.0"
+  gem "rspec",                 ">= 3.5.0", "< 4.0.0"
+  gem "rspec_junit_formatter", ">= 0.3.0"
+  gem "simplecov",             ">= 0.15.0"
 end
+

data/Readme.md

@@ -0,0 +1,99 @@
+metacrunch-file
+===============
+
+[![Gem Version](https://badge.fury.io/rb/metacrunch-file.svg)](http://badge.fury.io/rb/metacrunch-file)
+[![Code Climate](https://codeclimate.com/github/ubpb/metacrunch-file/badges/gpa.svg)](https://codeclimate.com/github/ubpb/metacrunch-file)
+[![Test Coverage](https://codeclimate.com/github/ubpb/metacrunch-file/badges/coverage.svg)](https://codeclimate.com/github/ubpb/metacrunch-file/coverage)
+[![CircleCI](https://circleci.com/gh/ubpb/metacrunch-file.svg?style=svg)](https://circleci.com/gh/ubpb/metacrunch-file)
+
+This is the official file package for the [metacrunch ETL toolkit](https://github.com/ubpb/metacrunch).
+
+Installation
+------------
+
+Include the gem in your `Gemfile`
+
+```ruby
+gem "metacrunch-file", "~> 1.0.0"
+```
+
+and run `$ bundle install` to install it.
+
+Or install it manually
+
+```
+$ gem install metacrunch-file
+```
+
+
+Usage
+-----
+
+*Note: For working examples on how to use this package check out our [demo repository](https://github.com/ubpb/metacrunch-demo).*
+
+### `Metacrunch::File::Source`
+
+This class provides a metacrunch `source` implementation that can be used to read data from files in the file system into a metacrunch job. The class can be used to read regular files, compressed files (gzip), tar archives and compressed tar archives (gzip).
+
+You can access non-option arguments from the command line using the `ARGV` constant.
+
+```ruby
+# my_job.metacrunch
+
+# If you call this example like so
+#   $ metacrunch my_job.metacrunch *.xml
+# ARGV will contain all the XML files in the current directory.
+source Metacrunch::File::Source.new(ARGV)
+
+# ... or you can set the filenames directly
+source Metacrunch::File::Source.new(["my-data.xml", "my-other-data.xml", "..."])
+```
+
+**Options**
+
+NONE.
+
+The source yields objects of type `Metacrunch::File::Entry` for every file it reads. 
+
+```ruby
+# my_job.metacrunch
+
+transformation ->(file_entry) do
+  puts "** Got file entry (Metacrunch::File::Entry)"
+  puts "  Filename: #{file_entry.filename}"
+  puts "  From archive?: #{file_entry.from_archive?}"
+  puts "  Name in archive: #{file_entry.archive_filename || '-'}"
+  puts "  Contents: #{file_entry.contents}"
+end
+```
+
+
+### `Metacrunch::File::XLSXDestination`
+
+This class provides a metacrunch `destination` implementation to create simple Excel (xlsx) files.
+
+To use this destination a transformation is required to format the data in a proper array that can be feet into the destination. When defining the destination you must provide an array of column names. Each data row passed to the destination must be an array of the same size as the column array.
+
+```ruby
+# my_job.metacrunch
+
+transformation ->(data) do
+  [data["foo"], data["bar"], ...]
+end
+
+source Metacrunch::File::XLSXDestination.new(
+    "/tmp/my-data.xlsx",           # filename
+    ["Column 1", "Column 2", ...], # header columns
+    OPTIONS
+)
+```
+
+**Options**
+
+* `worksheet_title`: The name of the worksheet. Defaults to `My data`.
+
+License
+-------
+
+metacrunch-file is available at [github](https://github.com/ubpb/metacrunch-file) under [MIT license](https://github.com/ubpb/metacrunch-file/blob/master/License.txt).
+

data/lib/metacrunch/file/version.rb

@@ -1,6 +1,6 @@
 
 module Metacrunch
   module File
-    VERSION = "1.0.0"
+    VERSION = "1.1.0"
   end
 end

data/lib/metacrunch/file/xlsx_destination.rb

@@ -0,0 +1,46 @@
+require "metacrunch/file"
+require "axlsx"
+
+module Metacrunch
+  class File::XLSXDestination
+
+    DEFAULT_OPTIONS = {
+      worksheet_title: "My data"
+    }
+
+    def initialize(filename, columns, options = {})
+      @filename = filename
+      @columns = columns
+      @options = DEFAULT_OPTIONS.deep_merge(options)
+
+      @package = Axlsx::Package.new
+      @workbook = @package.workbook
+      @sheet = @workbook.add_worksheet(name: @options[:worksheet_title])
+
+      @sheet.add_row(columns, types: :string)
+    end
+
+    def write(row)
+      return if row.blank?
+      @sheet.add_row(row, types: :string)
+    end
+
+    def close
+      # Make the first row a header
+      @sheet.sheet_view.pane do |pane|
+        pane.top_left_cell = "A2"
+        pane.state = :frozen_split
+        pane.y_split = 1
+        pane.x_split = 0
+        pane.active_pane = :bottom_right
+      end
+
+      # Add a filter
+      @sheet.auto_filter = @sheet.dimension.sqref
+
+      # Generate file
+      @package.serialize(@filename)
+    end
+
+  end
+end

data/lib/metacrunch/file.rb

@@ -5,5 +5,6 @@ module Metacrunch
   module File
     require_relative "file/entry"
     require_relative "file/source"
+    require_relative "file/xlsx_destination"
   end
 end

data/metacrunch-file.gemspec

@@ -16,4 +16,5 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_dependency "activesupport", ">= 5.1.0"
+  spec.add_dependency "axlsx", "~> 2.0.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metacrunch-file
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - René Sprotte
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-09-21 00:00:00.000000000 Z
+date: 2017-11-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -24,22 +24,39 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 5.1.0
+- !ruby/object:Gem::Dependency
+  name: axlsx
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.0.1
 description: 
 email: 
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".circleci/config.yml"
 - ".gitignore"
 - ".rspec"
 - Gemfile
 - License.txt
 - Rakefile
+- Readme.md
 - bin/console
 - lib/metacrunch/file.rb
 - lib/metacrunch/file/entry.rb
 - lib/metacrunch/file/source.rb
 - lib/metacrunch/file/version.rb
+- lib/metacrunch/file/xlsx_destination.rb
 - metacrunch-file.gemspec
 homepage: http://github.com/ubpb/metacrunch-file
 licenses:
@@ -61,7 +78,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.11
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: File package for the metacrunch ETL toolkit.