csv-probe 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 138cd78aa31ccab66bbaa4a629c4f2c0d3b37a547006ed635e6fed935a223051
+  data.tar.gz: 87f700fcb9c7a620f101b5a63bf095b9f6a611f72d83f876b11ca33797564a72
+SHA512:
+  metadata.gz: 1357f59d7446f937c3719feeafd86aa29a10844203d72dd20f30c338243ad347adeca2c5d1dca93195cd223403fb024263330f398f029455f8ae5562fd906812
+  data.tar.gz: aee4fa829429c8cc4590351da2b303b5879a163b412d987ec7dff63f5c45e5e8e9e4b5dd40af4619a19ceaa166bf09670e3f4f0b50b79f83e4c048552ec0ec7c

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,13 @@
+AllCops:
+  TargetRubyVersion: 2.6
+
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Layout/LineLength:
+  Max: 120

data/CHANGELOG.md

@@ -0,0 +1,5 @@
+## [Unreleased]
+
+## [0.1.0] - 2022-01-02
+
+- Initial release

data/Gemfile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in csv-probe.gemspec
+gemspec
+
+gem "rake", "~> 13.0"
+
+gem "rspec", "~> 3.0"
+
+gem "rubocop", "~> 1.21"

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2022 homebase.dev
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,61 @@
+# Probe
+
+Probe provides a simple framework for CSV::Table and CSV::Row linting using custom rules.
+Probe extens CSV::Table and CSV::Row with a `lint(rules, opts)` method.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'csv-probe'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install csv-probe
+
+## Usage
+
+Example how to use Probe
+
+```
+  # load CSV into CSV::Table
+  csv_table = CSV.parse(<<~ROWS, headers: true)
+    col1,col2,col3,col4,col5,col6,col7
+    0,NU,customer,1,02-12-2021,FO;FO;RU,eagle|hawk
+    0,PA,customer,2,03-12-2021,SHA;AN;RU,badger|ant
+    0,TE,guest,1000,06-11-2021,RU,spider|racoon|ant
+  ROWS
+  checks = [Probe::ColumnIsEqualTo.new("col1", "0"),
+            Probe::ColumnMatchesRegEx.new("col2", /^(NU|PA|TE)$/),
+            Probe::ColumnIsOneOf.new("col3", ["customer","guest"]),
+            Probe::ColumnMeetsCondition.new("col4", ->(val, _opts) { Integer(val, exception: false) != nil }, "Not an Integer"),
+            Probe::ColumnIsDate.new("col5", "%d-%m-%Y"),
+            Probe::ColumnIsListWithDomain.new("col6", ["FO", "RU", "SHA", "AN"], ";"),
+            Probe::ColumnIsSetWithDomain.new("col7", ["eagle", "hawk", "badger", "spider", "racoon", "ant"], "|")]
+
+  # lint table
+  csv_table.lint(checks)
+
+  # lint single row of table
+  csv_table[0].lint(checks)
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/csv-probe.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+require "rubocop/rake_task"
+
+RuboCop::RakeTask.new
+
+task default: %i[spec rubocop]

data/bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require "bundler/setup"
+require "csv/probe"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/csv-probe.gemspec

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+require_relative "lib/csv/probe/version"
+
+Gem::Specification.new do |spec|
+  spec.name = "csv-probe"
+  spec.version = Probe::VERSION
+  spec.authors = ["homebase.dev"]
+  spec.email = ["homebase.dev@gmail.com"]
+
+  spec.summary = "Allows validation of CSV::Table or CSV::Rows via custom rules"
+  spec.description = "This gem provides a simple framework for CSV::Table/CSV::Row validation using custom rules for columns and rows"
+  spec.homepage = "https://gitlab.com/homebase-dev/csv-probe"
+  spec.license = "MIT"
+  spec.required_ruby_version = ">= 2.6.0"
+
+  # spec.metadata["allowed_push_host"] = "TODO: Set to your gem server 'https://example.com'"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://gitlab.com/homebase-dev/csv-probe"
+  spec.metadata["changelog_uri"] = "https://gitlab.com/homebase-dev/csv-probe"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (f == __FILE__) || f.match(%r{\A(?:(?:test|spec|features)/|\.(?:git|travis|circleci)|appveyor)})
+    end
+  end
+  spec.bindir = "exe"
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  # Uncomment to register a new dependency of your gem
+  spec.add_dependency "csv", "~> 3.1.9"
+  spec.add_dependency "terminal-table", "~> 3.0"
+
+  # For more information and examples about making a new gem, checkout our
+  # guide at: https://bundler.io/guides/creating_gem.html
+end

data/lib/csv/probe/checks.rb

@@ -0,0 +1,236 @@
+# frozen_string_literal: true
+
+module Probe
+  class Error < StandardError; end
+
+  class LintingError < Error; end
+
+  class RowError < LintingError
+    def initialize(msg = "CheckRowError")
+      super
+    end
+  end
+
+  class RowWarning < LintingError
+    def initialize(msg = "CheckRowWarning")
+      super
+    end
+  end
+
+  class ColumnError < LintingError
+    def initialize(msg = "CheckColumnError")
+      super
+    end
+  end
+
+  class ColumnWarning < LintingError
+    def initialize(msg = "CheckColumnWarning")
+      super
+    end
+  end
+
+  class RowMeetsCondition
+    attr_accessor :ok_condition_fn, :fail_msg, :severity, :pre_checks
+
+    def initialize(ok_condition_fn, fail_msg)
+      @pre_checks = []
+      @ok_condition_fn = ok_condition_fn
+      @fail_msg = fail_msg
+      @severity = "ERROR"
+      @error_classes = {
+        "ERROR" => RowError,
+        "WARNING" => RowWarning
+      }
+    end
+
+    def evaluate_pre_checks(row, opts)
+      @pre_checks.each do |c|
+        c.evaluate(row, opts)
+      end
+    end
+
+    def evaluate(row, opts = {})
+      evaluate_pre_checks(row, opts)
+      raise @error_classes.fetch(@severity), error_msg(row, opts) unless @ok_condition_fn.call(row, opts)
+    end
+
+    def error_msg(row, opts)
+      row_location = source_row_location(row, opts)
+      row_str = source_row(row, opts) # [#{self.class}] verbose only?
+      err_msg = "#{row_location} [#{@severity}] #{render_pretty_fail_msg(row, opts)}\n"
+      if opts[:verbose]
+        err_msg = "#{err_msg}#{self.class.name.split("::").last}\n"
+        err_msg = "#{err_msg}#{@error_classes.fetch(@severity).name.split("::").last}\n"
+      end
+      "#{err_msg}#{row_str}\n"
+    end
+
+    def render_fail_msg(row, opts)
+      return @fail_msg.call(row, opts) if @fail_msg.is_a?(Proc)
+
+      @fail_msg
+    end
+
+    def render_pretty_fail_msg(row, opts)
+      render_fail_msg(row, opts)
+    end
+
+    def source_row_location(_row, opts)
+      "#{opts[:fpath]}:#{opts[:lineno]}"
+    end
+
+    def source_row(row, opts = {})
+      return report_columns_hash(row, opts) if opts[:only_report_columns]
+
+      if opts[:source_row_renderer]
+        return row.inspect if opts[:source_row_renderer] == "inspect"
+        return "#{Terminal::Table.new rows: row.to_a}\n" if opts[:source_row_renderer] == "tabular"
+        return "#{Terminal::Table.new rows: row.to_a.transpose}\n" if opts[:source_row_renderer] == "tabular_transposed"
+      end
+      row
+    end
+
+    # def row_colval(row, varname, opts)
+    #   return row[varname] if varname.is_a? Integer
+    #   return row.fetch(varname)
+    # end
+
+    def report_columns_hash(row, opts)
+      h = {}
+      opts[:only_report_columns].each { |varname| h[varname] = row.fetch(varname) }
+      h
+    end
+  end
+
+  class ColumnMeetsCondition < RowMeetsCondition
+    attr_accessor :varname, :ok_condition_fn, :fail_msg
+
+    def initialize(varname, ok_condition_fn, fail_msg)
+      super(ok_condition_fn, fail_msg)
+      @varname = varname
+      @error_classes = {
+        "ERROR" => ColumnError,
+        "WARNING" => ColumnWarning
+      }
+    end
+
+    def render_pretty_fail_msg(row, opts)
+      "Unexpected value:#{row.fetch(@varname).inspect} for column:#{@varname.inspect}, #{render_fail_msg(row, opts)}"
+    end
+
+    def evaluate(row, opts = {})
+      evaluate_pre_checks(row, opts)
+      raise @error_classes.fetch(@severity), error_msg(row, opts) unless @ok_condition_fn.call(row.fetch(@varname), opts)
+    end
+  end
+
+  class ColumnIsEqualTo < ColumnMeetsCondition
+    def initialize(varname, expected_val, _placeholder = nil)
+      super(varname, nil, nil)
+      @ok_condition_fn = ->(val, _cfg) { val == expected_val }
+      @fail_msg = "expected to be #{expected_val.inspect}"
+    end
+  end
+
+  class ColumnIsOneOf < ColumnMeetsCondition
+    def initialize(varname, expected_vals_arr, _placeholder = nil)
+      super(varname, nil, nil)
+      @ok_condition_fn = ->(val, _cfg) { expected_vals_arr.include?(val) }
+      @fail_msg = "expected to be one of #{expected_vals_arr.inspect}"
+    end
+  end
+
+  class ColumnIsDate < ColumnMeetsCondition
+    def initialize(varname, expected_date_format, _placeholder = nil)
+      super(varname, nil, nil)
+      @ok_condition_fn = lambda { |val, _cfg|
+        success = true
+        begin
+          Date.strptime(val, expected_date_format)
+        rescue Date::Error
+          success = false
+        end
+        return success
+      }
+      @fail_msg = "expected date with format #{expected_date_format.inspect}"
+    end
+  end
+
+  # class ColumnIsInteger < ColumnMeetsCondition
+  #   def initialize(varname, placeholder1=nil, placeholder=nil)
+  #     super(varname, nil, nil)
+  #     @ok_condition_fn = ->(val, cfg){ val.is_a? Integer } # TODO: achtung 12abc -> integer auch 1.1 wird zu 1... ist nicht so einfach, lieber über regex prüfen
+  #     @fail_msg = "expected to be an Integer"
+  #   end
+  # end
+
+  class ColumnMatchesRegEx < ColumnMeetsCondition
+    def initialize(varname, expected_regex_pattern, _placeholder = nil)
+      super(varname, nil, nil)
+      @ok_condition_fn = ->(val, _cfg) { val.to_s =~ expected_regex_pattern }
+      @fail_msg = "expected to match regex pattern #{expected_regex_pattern.inspect}"
+    end
+  end
+
+  # TODO: fixme uniq als eigenen check machen
+  class ColumnIsListWithDomain < ColumnMeetsCondition
+    def initialize(varname, expected_items_arr, separator, _placeholder = nil)
+      super(varname, nil, nil)
+      @ok_condition_fn = lambda { |val, _cfg|
+        items = val.split(separator)
+        return items.all? { |e| expected_items_arr.include?(e) }
+      }
+      @fail_msg = lambda { |row, _opts|
+        items = row.fetch(@varname).split(separator)
+        diff_items = items - expected_items_arr
+        "expected that tokenized items of value #{items.inspect} are a subset of #{expected_items_arr.inspect}, but items #{diff_items.inspect} are not"
+      }
+    end
+  end
+
+  class ColumnIsSet < ColumnMeetsCondition
+    def initialize(varname, separator, _placeholder = nil)
+      super(varname, nil, nil)
+      @ok_condition_fn = lambda { |val, _cfg|
+        return true if val.to_s == ""
+
+        items = val.split(separator)
+        all_uniq = (items.size == items.uniq.size)
+        return all_uniq
+      }
+      @fail_msg = lambda { |row, _opts|
+        items = row.fetch(@varname).split(separator)
+        non_uniq_items = items.detect { |e| items.count(e) > 1 }
+        "expected that items of tokenized value #{items.inspect} are uniqe, but items #{non_uniq_items.inspect} are not"
+      }
+    end
+  end
+
+  class ColumnIsSetWithDomain < ColumnMeetsCondition
+    def initialize(varname, expected_items_arr, separator, _placeholder = nil)
+      super(varname, nil, nil)
+      @pre_checks << ColumnIsSet.new(varname, separator)
+      @ok_condition_fn = lambda { |val, _cfg|
+        return true if val.to_s == ""
+
+        items = val.split(separator)
+        all_valid = items.all? { |i| expected_items_arr.include?(i) }
+        return all_valid
+      }
+      @fail_msg = lambda { |row, _opts|
+        items = row.fetch(@varname).split(separator)
+        "expected that items of tokenized value #{items.inspect} are a subset of #{expected_items_arr.inspect}"
+      }
+      # @fail_msg = ->(row, opts) { "Unexpected value:#{row.fetch(@varname).inspect} for column:#{@varname.inspect}, expected that items of tokenized value #{row.fetch(@varname).split(separator)} are uniqe and a subset of #{expected_items_arr.inspect}" }
+    end
+  end
+
+  # TODO: nice to have
+  # * if_second_not_empty_then_first_yes_check(varname1, varname2)
+  # * if_first_eyes_then_second_not_empty_check(varname1, varname2)
+  # * if_first_yes_then_others_too_checks(varname1, varname_arr)
+  # * if_first_NC2_then_others_not_yes_checks(varname1, varname_arr)
+  # * if_first_yes_then_also_second_check(varname1, varname2)
+  # * warn_if_first_yes_then_others_not_empty_checks(main_varname, sub_varnames_arr)
+  # * is_comment_of_size(main_varname, char_len)
+end

data/lib/csv/probe/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Probe
+  VERSION = "0.1.0"
+end

data/lib/csv/probe.rb

@@ -0,0 +1,58 @@
+# frozen_string_literal: true
+
+require "csv"
+require "terminal-table"
+require_relative "probe/version"
+require_relative "probe/checks"
+
+# Probe provides methods for linting a:
+# * CSV::Table
+# * CSV::Row
+#
+# The linting methods:
+# * lint_rows takes following arguments
+#   * csv_rows: CSV::Table
+#   * checks: Array of Probe Checks and
+#   * options
+# * lint_row takes following arguments
+#   * csv_row: CSV::Row
+#   * checks: Array of Probe Checks and
+#   * optsions
+module Probe
+  def self.lint_rows(csv_rows, checks, opts = {})
+    lineno_start = opts[:headers] ? 2 : 1
+    csv_rows.each.with_index(lineno_start) do |row, lineno|
+      opts[:lineno] = lineno
+      lint_row(row, checks, opts)
+    end
+  end
+
+  def self.lint_row(csv_row, checks, opts = {})
+    unless csv_row.is_a? CSV::Row
+      raise Error "lint_row(csv_row,...), csv_row is not of type CSV::Row, but of type '#{csv_row.class}'"
+    end
+
+    checks.each do |check|
+      check.evaluate(csv_row, opts)
+    rescue LintingError => e
+      raise e unless opts[:exception] == false
+
+      puts e.message # if exception oppressed, write error out on stdout
+    end
+  end
+end
+
+# Extend CSV::Table with .lint(...) method
+class CSV::Table
+  def lint(checks, opts = {})
+    opts[:headers] = true unless opts.key?(:headers) # CSV::Table has always headers, hence set :headers = true
+    Probe.lint_rows(self, checks, opts)
+  end
+end
+
+# Extend CSV::Row with .lint(...) method
+class CSV::Row
+  def lint(checks, opts = {})
+    Probe.lint_row(self, checks, opts)
+  end
+end

data/sig/csv/probe.rbs

@@ -0,0 +1,6 @@
+module Csv
+  module Probe
+    VERSION: String
+    # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+  end
+end

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification
+name: csv-probe
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- homebase.dev
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2022-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: csv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.1.9
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.1.9
+- !ruby/object:Gem::Dependency
+  name: terminal-table
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: This gem provides a simple framework for CSV::Table/CSV::Row validation
+  using custom rules for columns and rows
+email:
+- homebase.dev@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- ".rubocop.yml"
+- CHANGELOG.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- csv-probe.gemspec
+- lib/csv/probe.rb
+- lib/csv/probe/checks.rb
+- lib/csv/probe/version.rb
+- sig/csv/probe.rbs
+homepage: https://gitlab.com/homebase-dev/csv-probe
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://gitlab.com/homebase-dev/csv-probe
+  source_code_uri: https://gitlab.com/homebase-dev/csv-probe
+  changelog_uri: https://gitlab.com/homebase-dev/csv-probe
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.29
+signing_key:
+specification_version: 4
+summary: Allows validation of CSV::Table or CSV::Rows via custom rules
+test_files: []