csvhuman 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 358d150c2a69a16f741b0dae47328857787d2dc2
+  data.tar.gz: fd36923138a7453510d2d26a4e2997c4475b3aea
+SHA512:
+  metadata.gz: 1540846d223cb4bcf8dd4d2982f5cdc96b13966328f4037d84d6b1a7f8a3bee998856edcc3aaeb7d14e476f12e5a3cc5fd81d81a6aeed6a44e55c39a24cd8144
+  data.tar.gz: 2fbc7a4ee6f22f75ab4cdea35c5411fc311baf4185d5ebc3012ae4b99a43d301a93a70ff388ac58aaa3eec0eb630d9c5742e94e67cb583214d88dfb05fadebad

data/HISTORY.md

@@ -0,0 +1,3 @@
+### 0.0.1 / 2018-11-06
+
+* Everything is new. First release

data/Manifest.txt

@@ -0,0 +1,10 @@
+HISTORY.md
+Manifest.txt
+README.md
+Rakefile
+lib/csvhuman.rb
+lib/csvhuman/reader.rb
+lib/csvhuman/version.rb
+test/data/test.csv
+test/helper.rb
+test/test_reader.rb

data/README.md

@@ -0,0 +1,27 @@
+# CSV Humanitarian eXchange Language (HXL) Parser / Reader
+
+csvhuman library / gem - read tabular data in the CSV Humanitarian eXchange Language (HXL)  format, that is, comma-separated values (CSV) line-by-line records with a hashtag (meta data) line using the Humanitarian eXchange Language (HXL) rules
+
+* home  :: [github.com/csvreader/csvhuman](https://github.com/csvreader/csvhuman)
+* bugs  :: [github.com/csvreader/csvhuman/issues](https://github.com/csvreader/csvhuman/issues)
+* gem   :: [rubygems.org/gems/csvhuman](https://rubygems.org/gems/csvhuman)
+* rdoc  :: [rubydoc.info/gems/csvhuman](http://rubydoc.info/gems/csvhuman)
+* forum :: [wwwmake](http://groups.google.com/group/wwwmake)
+
+
+
+## Usage
+
+to be done
+
+
+## License
+
+The `csvhuman` scripts are dedicated to the public domain.
+Use it as you please with no restrictions whatsoever.
+
+
+## Questions? Comments?
+
+Send them along to the [wwwmake forum](http://groups.google.com/group/wwwmake).
+Thanks!

data/Rakefile

@@ -0,0 +1,30 @@
+require 'hoe'
+require './lib/csvhuman/version.rb'
+
+Hoe.spec 'csvhuman' do
+
+  self.version = CsvHuman::VERSION
+
+  self.summary = "csvhuman - read tabular data in the CSV Humanitarian eXchange Language (HXL)  format, that is, comma-separated values (CSV) line-by-line records with a hashtag (meta data) line using the Humanitarian eXchange Language (HXL) rules"
+  self.description = summary
+
+  self.urls    = ['https://github.com/csvreader/csvhuman']
+
+  self.author  = 'Gerald Bauer'
+  self.email   = 'wwwmake@googlegroups.com'
+
+  # switch extension to .markdown for gihub formatting
+  self.readme_file  = 'README.md'
+  self.history_file = 'HISTORY.md'
+
+  self.extra_deps = [
+     ['csvreader',  '>=1.2.1']
+  ]
+
+  self.licenses = ['Public Domain']
+
+  self.spec_extras = {
+    required_ruby_version: '>= 2.2.2'
+  }
+
+end

data/lib/csvhuman.rb

@@ -0,0 +1,24 @@
+# encoding: utf-8
+
+require 'pp'
+require 'logger'
+
+
+require 'csvreader'
+
+## our own code
+require 'csvhuman/version'    # note: let version always go first
+require 'csvhuman/reader'
+
+
+
+## add some "alternative" shortcut aliases
+CsvHum  = CsvHuman
+CSV_HXL = CsvHuman
+CSVHXL  = CsvHuman
+HXL     = CsvHuman
+
+
+
+# say hello
+puts CsvHuman.banner     if $DEBUG || (defined?($RUBYCOCO_DEBUG) && $RUBYCOCO_DEBUG)

data/lib/csvhuman/reader.rb

@@ -0,0 +1,197 @@
+# encoding: utf-8
+
+
+class CsvHuman
+
+## Q: how to deal with un-tagged fields?
+##     - skip / ignore
+## Q: how to deal duplicate fields (e.g. #sex+#targeted,#sex+#targeted)?
+##     - value (auto-magically) turned into an array / list
+
+
+    def self.open( path, mode=nil, &block )   ## rename path to filename or name - why? why not?
+
+     ## note: default mode (if nil/not passed in) to 'r:bom|utf-8'
+     ## f = File.open( path, mode ? mode : 'r:bom|utf-8' )
+     csv = Csv.open( path, mode, parser: Csv::Parser.human )     ## note: returns an enumarator-like object
+     human = new( csv )
+
+     # handle blocks like Ruby's open(), not like the (old old) CSV library
+     if block_given?
+       begin
+         block.call( human )
+       ensure
+         csv.close
+       end
+     else
+       human
+     end
+ end # method self.open
+
+
+    def self.read( path )
+        open( path ) { |human| human.read }
+    end
+
+
+    def self.foreach( path, &block )
+          csv = Csv.open( path, parser: Csv::Parser.human )     ## note: returns an enumarator-like object
+          human = new( csv )
+
+          if block_given?
+            begin
+              human.each( &block )
+            ensure
+              csv.close
+            end
+          else
+            human.to_enum    ## note: caller (responsible) must close file!!!
+            ## remove version without block given - why? why not?
+            ## use Csv.open().to_enum  or Csv.open().each
+            ##   or Csv.new( File.new() ).to_enum or Csv.new( File.new() ).each ???
+          end
+    end # method self.foreach
+
+
+    def self.parse( str_or_readable, &block )
+          human = new( str_or_readable )
+
+          if block_given?
+            human.each( &block )  ## note: caller (responsible) must close file!!! - add autoclose - why? why not?
+          else  # slurp contents, if no block is given
+            human.read            ## note: caller (responsible) must close file!!! - add autoclose - why? why not?
+          end
+    end # method self.parse
+
+
+
+
+class Column
+   attr_reader  :tag
+
+   def initialize( tag=nil, list: false )
+     @tag  = tag
+     @list = list
+   end
+
+   def tagged?()  @tag.nil? == false; end
+   def list?()    @list; end
+end  # class Column
+
+
+
+attr_reader :header, :tags
+
+def initialize( recs_or_stream )
+   ## todo/check:  check if arg is a stream/enumarator - why? why not??
+   if recs_or_stream.is_a?( String )
+     @recs = Csv.new( recs_or_stream, parser: Csv::Parser.human )     ## note: returns an enumarator-like object
+   else
+     @recs = recs_or_stream
+   end
+
+   @header = []
+   @tags   = nil   ## add tags = nil  -- why? why not?
+   @cols   = nil   ## column mappings (used "internally")
+end
+
+
+include Enumerable
+
+def each( &block )
+  @header = []
+  @tags   = nil   ## add tags = nil  -- why? why not?
+  @cols   = nil   ## column mappings (used "internally")
+
+  @recs.each do |values|
+    ## pp values
+    if @cols.nil?
+      if values.any? { |value| value && value.start_with?('#') }
+        @cols = build_cols( values )
+        @tags = values
+      else
+        @header << values
+      end
+    else
+
+      ## data row
+      ##  strip non-tagged - how?
+      record = {}
+      @cols.each_with_index do |col,i|
+        if col.tagged?
+          key   = col.tag
+          value = values[i]
+          if col.list?
+            record[ key ] ||= []
+            record[ key ] << value
+          else
+            ## add "regular" single value
+            record[ key ] = value
+          end
+        end
+      end
+      ## pp record
+      block.call( record )
+    end
+  end
+end  # method each
+
+def read() to_a; end # method read
+
+
+###
+### todo/fix:
+##   add closed? and close
+##    if self.open used without block (user needs to close file "manually")
+
+
+####
+# helpers
+
+
+def build_cols( values )
+
+  ## "clean" unify/normalize names
+  values = values.map do |value|
+    if value
+      if value.empty?
+        nil     ## make untagged fields nil
+      else
+        ## todo: sort attributes by a-to-z
+        ##  strip / remove all spaces
+        value.strip.gsub('#','')   ## remove leading # - why? why not?
+      end
+    else
+      value   ## keep (nil) as is
+    end
+  end
+
+
+  counts = {}
+  values.each_with_index do |value,i|
+     if value
+       counts[value] ||= []
+       counts[value] << i
+     end
+  end
+  ## pp counts
+
+
+  cols = []
+  values.each do |value|
+    if value
+      count = counts[value]
+      if count.size > 1
+        cols << Column.new( value, list: true )
+      else
+        cols << Column.new( value )
+      end
+    else
+      cols << Column.new
+    end
+  end
+
+  cols
+end
+
+end # class CsvHuman

data/lib/csvhuman/version.rb

@@ -0,0 +1,24 @@
+# encoding: utf-8
+
+
+class CsvHuman
+
+  MAJOR = 0
+  MINOR = 1
+  PATCH = 0
+  VERSION = [MAJOR,MINOR,PATCH].join('.')
+
+
+  def self.version
+    VERSION
+  end
+
+  def self.banner
+    "csvhuman/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
+  end
+
+  def self.root
+    "#{File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )}"
+  end
+
+end # module CsvHuman

data/test/data/test.csv

@@ -0,0 +1,7 @@
+What,,,Who,Where,For whom,
+Record,Sector/Cluster,Subsector,Organisation,Country,Males,Females,Subregion
+,#sector+en,#subsector,#org,#country,#sex+#targeted,#sex+#targeted,#adm1
+001,WASH,Subsector 1,Org 1,Country 1,100,100,Region 1
+002,Health,Subsector 2,Org 2,Country 2,,,Region 2
+003,Education,Subsector 3,Org 3,Country 2,250,300,Region 3
+004,WASH,Subsector 4,Org 1,Country 3,80,95,Region 4

data/test/helper.rb

@@ -0,0 +1,17 @@
+## $:.unshift(File.dirname(__FILE__))
+
+## minitest setup
+
+require 'minitest/autorun'
+
+
+## our own code
+require 'csvhuman'
+
+
+## add test_data_dir helper
+class CsvHuman
+  def self.test_data_dir
+    "#{root}/test/data"
+  end
+end

data/test/test_reader.rb

@@ -0,0 +1,59 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_reader.rb
+
+
+require 'helper'
+
+class TestReader < MiniTest::Test
+
+def recs
+   [["Organisation", "Cluster", "Province" ],
+     [ "#org", "#sector", "#adm1" ],
+     [ "Org A", "WASH", "Coastal Province" ],
+     [ "Org B", "Health", "Mountain Province" ],
+     [ "Org C", "Education", "Coastal Province" ],
+     [ "Org A", "WASH", "Plains Province" ]]
+end
+
+def txt
+  <<TXT
+  What,,,Who,Where,For whom,
+  Record,Sector/Cluster,Subsector,Organisation,Country,Males,Females,Subregion
+  ,#sector+en,#subsector,#org,#country,#sex+#targeted,#sex+#targeted,#adm1
+  001,WASH,Subsector 1,Org 1,Country 1,100,100,Region 1
+  002,Health,Subsector 2,Org 2,Country 2,,,Region 2
+  003,Education,Subsector 3,Org 3,Country 2,250,300,Region 3
+  004,WASH,Subsector 4,Org 1,Country 3,80,95,Region 4
+TXT
+end
+
+
+def test_readme
+  csv = CsvHuman.new( recs )
+  csv.each do |rec|
+    pp rec
+  end
+
+  pp csv.read
+  pp CsvHuman.parse( recs )
+
+  CsvHuman.parse( recs ).each do |rec|
+    pp rec
+  end
+
+
+  pp CsvHuman.read( "#{CsvHuman.test_data_dir}/test.csv" )
+  pp CsvHuman.parse( txt )
+  CsvHuman.parse( txt ).each do |rec|
+    pp rec
+  end
+
+  CsvHuman.foreach( "#{CsvHuman.test_data_dir}/test.csv" ) do |rec|
+    pp rec
+  end
+end
+
+end # class TestReader

metadata

@@ -0,0 +1,104 @@
+--- !ruby/object:Gem::Specification
+name: csvhuman
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Gerald Bauer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-11-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: csvreader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.1
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.16'
+description: csvhuman - read tabular data in the CSV Humanitarian eXchange Language
+  (HXL)  format, that is, comma-separated values (CSV) line-by-line records with a
+  hashtag (meta data) line using the Humanitarian eXchange Language (HXL) rules
+email: wwwmake@googlegroups.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- HISTORY.md
+- Manifest.txt
+- README.md
+files:
+- HISTORY.md
+- Manifest.txt
+- README.md
+- Rakefile
+- lib/csvhuman.rb
+- lib/csvhuman/reader.rb
+- lib/csvhuman/version.rb
+- test/data/test.csv
+- test/helper.rb
+- test/test_reader.rb
+homepage: https://github.com/csvreader/csvhuman
+licenses:
+- Public Domain
+metadata: {}
+post_install_message: 
+rdoc_options:
+- "--main"
+- README.md
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.2.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.2
+signing_key: 
+specification_version: 4
+summary: csvhuman - read tabular data in the CSV Humanitarian eXchange Language (HXL)  format,
+  that is, comma-separated values (CSV) line-by-line records with a hashtag (meta
+  data) line using the Humanitarian eXchange Language (HXL) rules
+test_files: []