structured_csv 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 5f0d139cdc9ff3d124d745b783e00c1e9128efaf723df4976c19605a823dec6f
+  data.tar.gz: 396d9c993b850a571746a68cd64ee1c7a295d41d612c534196cb48c87c0415d7
+SHA512:
+  metadata.gz: 656fa1acf23c402402f8bc3ddc5b00c81fb805dbd3128be8c6ea301e7e3fdc4fa2105126ac2e452e5050178442bd0910f1ad141cc8820f39af68a09ce2c7f2de
+  data.tar.gz: d5371f377396641b87f878ada7e0e9c15cdff14afe46c2c3035e1da4d92bfc6b7a1323e2d9df0447574d35861d04abec394f1237d57e605479cc67dd00264c01

data/.github/workflows/main.yml

@@ -0,0 +1,18 @@
+name: Ruby
+
+on: [push,pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: 2.6.6
+    - name: Run the default task
+      run: |
+        gem install bundler -v 2.2.15
+        bundle install
+        bundle exec rake

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

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

data/.rubocop.yml

@@ -0,0 +1,13 @@
+AllCops:
+  TargetRubyVersion: 2.4
+
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Layout/LineLength:
+  Max: 120

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,84 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at ronald.tse@ribose.com. All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior,  harassment of an individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0,
+available at https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/translations.

data/Gemfile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in structured_csv.gemspec
+gemspec
+
+gem "rake", "~> 13.0"
+
+gem "rspec", "~> 3.0"
+
+gem "rubocop", "~> 1.7"

data/README.adoc

@@ -0,0 +1,205 @@
+= Process Structured CSV files (`structured_csv`)
+
+== Purpose
+
+The `structured_csv_to_yaml.rb` script converts a "`Structured CSV`" file into a YAML file.
+
+When you have data of a yet-undefined data structure, it is useful to manage
+them inside a CSV file which can be viewed and edited by a CSV editor,
+such as Excel.
+
+This is extremely useful in developing a normalized structure for such data,
+as you can ensure that the existing data can be normalized according to a
+defined structure.
+
+Ultimately, the data is to be meant to exported to a YAML file.
+
+This script supports UTF-8 CSV files.
+
+NOTE: This was originally developed to create over 50 normalized data models for ITU Operational Bulletin data. See https://github.com/ituob/ for more details.
+
+
+== Usage
+
+[source,sh]
+----
+$ exe/structured_csv_to_yaml.rb [input-file.csv]
+----
+
+Where,
+
+`input-file.csv`:: is the input CSV file, the output will be named as `input-file.yaml`.
+
+
+== Details
+
+A Structured CSV file has these properties:
+
+Two structured sections. A section is defined by the first column on an otherwise empty row that is either the first row or a row preceded by an empty row. Two section types are allowed: `METADATA` and `DATA`.
+
+The `METADATA` section has values organized like key-value pairs:
+
+* Column 1 is the name of key
+* Column 2 is the value
+
+The `key` can be a normal string or namespaced:
+
+* `foobar`, this maps to the YAML key `foobar:`
+
+* `foo.bar.boo`, this maps to the YAML structure: +
++
+[source,yaml]
+----
+foo:
+  bar:
+    boo:
+----
+
+A typical YAML output is like:
+
+[source,yaml]
+----
+---
+metadata:
+  locale:
+    bar:
+      en: beef
+      fr: boeuf
+      jp: 牛肉
+data:
+  foo:
+    bar:
+    ...
+----
+
+
+
+A sample METADATA section looks like this table:
+
+[cols,"a,a"]
+|===
+|METADATA |
+|locale.bar.en | beef
+|locale.bar.fr | boeuf
+|locale.bar.jp | 牛肉
+|===
+
+And generates this YAML:
+
+[source,yaml]
+----
+---
+metadata:
+  locale:
+    bar:
+      en: beef
+      fr: boeuf
+      jp: 牛肉
+----
+
+
+The `DATA` section has values organized in a table form. The first row is the header row.
+The first column is assumed to be the key.
+
+
+A sample DATA section looks like this table:
+
+[cols,"a,a,a,a"]
+|===
+|DATA | | |
+|foo.bar.en | foo.bar.fr | foo.bar.jp | description
+|beef | boeuf | 牛肉 | Yummy!
+|pork | porc | 豚肉 | Delicious!
+|===
+
+By default, this table generates this YAML format:
+
+[source,yaml]
+----
+---
+data:
+  beef:
+    foo:
+      bar:
+        en: beef
+        fr: boeuf
+        jp: 牛肉
+    description: Yummy!
+  pork:
+    foo:
+      bar:
+        en: pork
+        fr: porc
+        jp: 豚肉
+    description: Delicious!
+  ...
+----
+
+In cases where there is no DATA key, you have to specify the `type=array` to generate an array:
+
+[cols,"a,a,a,a"]
+|===
+|DATA | type=array | |
+|foo.bar.en | foo.bar.fr | foo.bar.jp | description
+|beef | boeuf | 牛肉 | Yummy!
+|pork | porc | 豚肉 | Delicious!
+|===
+
+[source,yaml]
+----
+---
+data:
+  - foo:
+      bar:
+        en: beef
+        fr: boeuf
+        jp: 牛肉
+    description: Yummy!
+  - foo:
+      bar:
+        en: pork
+        fr: porc
+        jp: 豚肉
+    description: Delicious!
+  ...
+----
+
+
+You are also allowed to specify the data types of columns. The types of `string`, `boolean` and `integer` are supported.
+
+[cols,"a,a,a,a"]
+|===
+|DATA | | |
+|foo.bar.en[string] | foo.bar.fr[string] | yummy[boolean] | availability[integer]
+|beef | boeuf | TRUE | 3
+|pork | porc | FALSE | 10
+|===
+
+[source,yaml]
+----
+---
+data:
+  beef:
+    foo:
+      bar:
+        en: beef
+        fr: boeuf
+    yummy: true
+    availability: 3
+  pork:
+    foo:
+      bar:
+        en: pork
+        fr: porc
+    yummy: false
+    availability: 10
+  ...
+----
+
+
+
+
+== Examples
+
+The `samples/` folder contains a number of complex examples.
+

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 "structured_csv"
+
+# 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/exe/csv_join.rb

@@ -0,0 +1,95 @@
+#!/usr/bin/env ruby
+require 'csv'
+require 'yaml'
+require 'pathname'
+
+module CsvJoin
+
+  def self.join(csv, section_name)
+    first_row = nil
+    last_row = -1
+
+    puts "section_name #{section_name}"
+
+    csv.each_with_index do |row, index|
+      if first_row.nil? && is_start_of_portion?(row, section_name)
+        puts "found first"
+        first_row = index+1
+        next
+      end
+
+      if !first_row.nil? && is_row_empty?(row)
+        puts "found last"
+        last_row = index
+        break
+      end
+    end
+
+    puts "first #{first_row}  last #{last_row}"
+    csv[first_row..last_row]
+  end
+
+  def self.load_csv(csvfile)
+    # puts csvfile
+
+    content = File.read(csvfile, encoding: "bom|utf-8").scrub
+    CSV.parse(content, liberal_parsing: true, encoding: "UTF-8")
+  end
+
+  def self.convert(csvdir, outfile)
+    raise "first argument must be a directory!" unless File.directory?(csvdir)
+
+    csv = CSV.open(outfile, "wb", encoding: "UTF-8")
+
+    csvfiles = Dir.glob(File.join(csvdir, "**", "*.csv")).sort
+    raise "directory must contain .csv files!" if csvfiles.empty?
+
+    # Assume all files use the same header structure as the first CSV file
+    header = []
+    csvheader = ""
+
+    csvfiles.each do |csvfile|
+      content = load_csv(csvfile)
+
+      csvheader = content.shift
+      if header.empty?
+        header = ['name'] + csvheader
+        csv << header
+      end
+
+      basename = Pathname.new(csvfile).basename.sub_ext('').to_s
+      content.each do |filerow|
+        row = []
+        filerow.each do |value|
+          row << case value
+                 when String
+                   value.strip
+                 else
+                   value
+                 end
+        end
+
+        all_empty = row.all? do |f|
+          f.nil? || f.empty?
+        end
+        next if all_empty
+
+        row.unshift(basename)
+
+        csv << row
+      end
+    end
+
+    csv
+  end
+
+end
+
+csvdir = ARGV.pop
+outfile = Pathname.new(csvdir).sub_ext(".csv").to_s
+
+# puts outfile
+
+CsvJoin.convert(csvdir, outfile)
+
+# puts CsvJoin.convert(csvdir)