csvrecord 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e37c870fe8f3bd7dcd5321254961dcf62e13a36e
-  data.tar.gz: 2fa49f5f6ab2d7d5ddd293654a70512afd51f9e8
+  metadata.gz: 7bec20faf657130128c9a70953bc48160b3e1d99
+  data.tar.gz: 92900195cb8f791286e4d07920b4f5d1ebb4b13a
 SHA512:
-  metadata.gz: df82e31279d1c49404ccc25b314c85602f0537a4c4c503e170322a7a65feb72e33017b157a95b81f976dac23ee20d928c423f2f3f2ce3d1aa59a8a3321e8e316
-  data.tar.gz: c92aefd53c73c43f7b14465643616b6ed7c2b464017a6ebedd01e81657ee01f5bd45d139f3e412b4b40f010d501288dda3cbc591ad855ff926905fe2188c7d1a
+  metadata.gz: c02849458381b9dd23643f0a6f9358c04984ef69aa5e2b72c61a791b3da7340a431049dd08a0059a09c0c188c5c5fbafedeaf815fe062d9ab4c61f8f704ce75d
+  data.tar.gz: b79e7e35a4d016ac38cbc281d59a534df054d508d8ccc45130f1b351850622ed0991e59336b564c42aa1919c14da62de973b1e797b44d8ae26e428e80db2a106

data/Manifest.txt

@@ -4,4 +4,9 @@ Manifest.txt
 README.md
 Rakefile
 lib/csvrecord.rb
+lib/csvrecord/base.rb
+lib/csvrecord/builder.rb
 lib/csvrecord/version.rb
+test/data/beer.csv
+test/helper.rb
+test/test_beer.rb

data/README.md

@@ -11,7 +11,120 @@
 
 ## Usage
 
-To be done
+[`beer.csv`](test/data/beer.csv):
+
+```
+Brewery,City,Name,Abv
+Andechser Klosterbrauerei,Andechs,Doppelbock Dunkel,7%
+Augustiner Bräu München,München,Edelstoff,5.6%
+Bayerische Staatsbrauerei Weihenstephan,Freising,Hefe Weissbier,5.4%
+Brauerei Spezial,Bamberg,Rauchbier Märzen,5.1%
+Hacker-Pschorr Bräu,München,Münchner Dunkel,5.0%
+Staatliches Hofbräuhaus München,München,Hofbräu Oktoberfestbier,6.3%
+```
+
+Step 1: Define a (typed) struct for the comma-separated values (csv) records. Example:
+
+```ruby
+require 'csvrecord'
+
+Beer = CsvRecord.define do
+  field :brewery        ## note: default type is :string
+  field :city
+  field :name
+  field :abv, Float     ## allows type specified as class (or use :float)
+end
+```
+
+or in "classic" style:
+
+```ruby
+class Beer < CsvRecord::Base
+  field :brewery
+  field :city
+  field :name
+  field :abv, Float
+end
+```
+
+
+Step 2: Read in the comma-separated values (csv) datafile. Example:
+
+```ruby
+beers = Beer.read( 'beer.csv' ).to_a
+
+puts "#{beers.size} beers:"
+pp beers
+```
+
+pretty prints (pp):
+
+```
+6 beers:
+[#<Beer:0x302c760
+    @abv     = 7.0,
+    @brewery = "Andechser Klosterbrauerei",
+    @city    = "Andechs",
+    @name    = "Doppelbock Dunkel">,
+ #<Beer:0x3026fe8
+    @abv     = 5.6,
+    @brewery = "Augustiner Br\u00E4u M\u00FCnchen",
+    @city    = "M\u00FCnchen",
+    @name    = "Edelstoff">,
+ #<Beer:0x30257a0
+    @abv     = 5.4,
+    @brewery = "Bayerische Staatsbrauerei Weihenstephan",
+    @city    = "Freising",
+    @name    = "Hefe Weissbier">,
+ ...
+]
+```
+
+Or loop over the records. Example:
+
+``` ruby
+Beer.read( data ).each do |rec|
+  puts "#{rec.name} (#{rec.abv}%) by #{rec.brewery}, #{rec.city}"
+end
+```
+
+printing:
+
+```
+Doppelbock Dunkel (7.0%) by Andechser Klosterbrauerei, Andechs
+Edelstoff (5.6%) by Augustiner Bräu München, München
+Hefe Weissbier (5.4%) by Bayerische Staatsbrauerei Weihenstephan, Freising
+Rauchbier Märzen (5.1%) by Brauerei Spezial, Bamberg
+Münchner Dunkel (5.0%) by Hacker-Pschorr Bräu, München
+Hofbräu Oktoberfestbier (6.3%) by Staatliches Hofbräuhaus München, München
+```
+
+
+Or create new records from scratch. Example:
+
+``` ruby
+beer = Beer.new( brewery: 'Andechser Klosterbrauerei',
+                 city:    'Andechs',
+                 name:    'Doppelbock Dunkel' )
+pp beer
+
+# -or-
+
+beer = Beer.new
+beer.update( abv: 12.7 )
+beer.update( brewery: 'Andechser Klosterbrauerei',
+             city:    'Andechs',
+             name:    'Doppelbock Dunkel' )
+
+# -or-
+
+beer.abv     = 12.7
+beer.name    = 'Doppelbock Dunkel'
+beer.brewery = 'Andechser Klosterbrauerei'
+```
+
+
+And so on. That's it.
 
 
 

data/lib/csvrecord.rb

@@ -1,8 +1,15 @@
 # encoding: utf-8
 
+require 'csv'
+require 'json'
+require 'pp'
+
+
 ###
 # our own code
 require 'csvrecord/version' # let version always go first
+require 'csvrecord/base'
+require 'csvrecord/builder'
 
 
 

data/lib/csvrecord/base.rb

@@ -0,0 +1,161 @@
+# encoding: utf-8
+
+
+module CsvRecord
+
+  ## note on naming:
+  ##   use naming convention from awk and tabular data package/json schema for now
+  ##    use - records  (use rows for "raw" untyped (string) data rows )
+  ##        - fields  (NOT columns or attributes) -- might add an alias later - why? why not?
+
+  class Field  ## ruby record class field
+    attr_reader :name, :type
+
+    def initialize( name, type )
+      ## todo: always symbol-ify (to_sym) name and type - why? why not?
+      @name = name.to_sym
+
+      if type.is_a?( Class )
+        @type = type    ## assign class to its own property - why? why not?
+      else
+        @type = type.to_sym
+      end
+    end
+  end  # class Field
+
+
+
+  def self.define( &block )
+    builder = Builder.new
+    builder.instance_eval(&block)
+    builder.to_record
+  end
+
+
+class Base
+
+def self.fields   ## note: use class instance variable (@fields and NOT @@fields)!!!! (derived classes get its own copy!!!)
+  @fields ||= []
+end
+
+
+def self.field( name, type=:string )
+
+  fields << Field.new( name, type )
+
+  define_method( name ) do
+    instance_variable_get( "@#{name}" )
+  end
+
+  define_method( "#{name}=" ) do |value|
+    instance_variable_set( "@#{name}", value )
+  end
+
+  define_method( "parse_#{name}") do |value|
+    instance_variable_set( "@#{name}", self.class.typecast( value, type ) )
+  end
+end
+def self.add_field( name, type ) field( name, type ); end  ## add alias for builder
+
+
+
+def self.typecast( value, type )
+  ## convert string value to (field) type
+  if type == :string || type == 'string' || type == String
+     value   ## pass through as is
+  elsif type == :float || type == 'float' || type == Float
+    ## note: allow/check for nil values
+    float = (value.nil? || value.empty?) ? nil : value.to_f
+    puts "typecast >#{value}< to float number >#{float}<"
+    float
+  elsif type == :number || type == 'number' || type == Integer
+    number = (value.nil? || value.empty?) ? nil : value.to_i(10)   ## always use base10 for now (e.g. 010 => 10 etc.)
+    puts "typecast >#{value}< to integer number >#{number}<"
+    number
+  else
+     ## raise exception about unknow type
+     puts "!!!! unknown type >#{type}< - don't know how to convert/typecast string value >#{value}<"
+     value
+  end
+end
+
+
+def self.build_hash( values )   ## find a better name - build_attrib? or something?
+  ## convert to key-value (attribute) pairs
+  ## puts "== build_hash:"
+  ## pp values
+
+  h = {}
+  values.each_with_index do |value,i|
+    field = fields[i]
+    ## pp field
+    h[ field.name ] = value
+  end
+  h
+end
+
+
+def parse( values )   ## use read (from array) or read_values or read_row - why? why not?
+  h = self.build_hash( values )
+  update( h )
+end
+
+
+
+def self.parse( txt_or_rows )  ## note: returns an (lazy) enumarator
+  if txt_or_rows.is_a? String
+    txt = txt_or_rows
+    rows = CSV.parse( txt, headers: true )
+  else
+    ### todo/fix: use only self.create( array-like ) for array-like data  - why? why not?
+    rows = txt_or_rows    ## assume array-like records that responds to :each
+  end
+
+  pp rows
+
+  Enumerator.new do |yielder|
+    rows.each do |row|
+     ## check - check for to_h - why? why not?  supported/built-into by CSV::Row??
+     ## if row.respond_to?( :to_h )
+     ## else
+       ## pp row.fields
+       ## pp row.to_hash
+       ## fix/todo: use row.to_hash
+       h = build_hash( row.fields )
+       ## pp h
+       rec = new( h )
+     ## end
+     yielder.yield( rec )
+    end
+  end
+end
+
+
+def self.read( path )  ## not returns an enumarator
+  txt  = File.open( path, 'r:utf-8' ).read
+  parse( txt )
+end
+
+
+
+def initialize( **kwargs )
+  update( kwargs )
+end
+
+def update( **kwargs )
+  pp kwargs
+  kwargs.each do |name,value|
+    ## note: only convert/typecast string values
+    if value.is_a?( String )
+      send( "parse_#{name}", value )  ## note: use parse_<name> setter (for typecasting)
+    else  ## use "regular" plain/classic attribute setter
+      send( "#{name}=", value )
+    end
+  end
+
+  ## todo: check if args.first is an array  (init/update from array)
+  self   ## return self for chaining
+end
+
+end # class Base
+end # module CsvRecord

data/lib/csvrecord/builder.rb

@@ -0,0 +1,37 @@
+# encoding: utf-8
+
+## (record) builder mini language / domain-specific language (dsl)
+
+module CsvRecord
+
+class Builder  # check: rename to RecordDefinition or RecordDsl or similar - why? why not?
+  def initialize
+    @clazz = Class.new(Base)
+  end
+
+  def field( name, type=:string )   ## note: type defaults to string
+    puts "  adding field >#{name}< with type >#{type}<"
+    @clazz.add_field( name, type )  ## auto-add getter and setter
+  end
+
+  def string( name )
+    puts "  adding string field >#{name}<"
+    field( name, 'string' )
+  end
+
+  def number( name )  ## use for alias for integer ???
+    puts "  adding number field >#{name}<"
+    field( name, 'number' )
+  end
+
+  def float( name )
+    puts "  adding float number field >#{name}<"
+    field( name, 'float' )
+  end
+
+
+  def to_record   ## check: rename to just record or obj or finish or end something?
+    @clazz
+  end
+end # class Builder
+end # module CsvRecord

data/lib/csvrecord/version.rb

@@ -1,13 +1,14 @@
 # encoding: utf-8
 
-## note: for now CsvRecord is a class!!! NOT a module - change - why? why not?
-class CsvRecord
+
+module CsvRecord
 
   MAJOR = 0    ## todo: namespace inside version or something - why? why not??
-  MINOR = 0
-  PATCH = 1
+  MINOR = 1
+  PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
+
   def self.version
     VERSION
   end

data/test/data/beer.csv

@@ -0,0 +1,7 @@
+Brewery,City,Name,Abv
+Andechser Klosterbrauerei,Andechs,Doppelbock Dunkel,7%
+Augustiner Bräu München,München,Edelstoff,5.6%
+Bayerische Staatsbrauerei Weihenstephan,Freising,Hefe Weissbier,5.4%
+Brauerei Spezial,Bamberg,Rauchbier Märzen,5.1%
+Hacker-Pschorr Bräu,München,Münchner Dunkel,5.0%
+Staatliches Hofbräuhaus München,München,Hofbräu Oktoberfestbier,6.3%

data/test/helper.rb

@@ -0,0 +1,16 @@
+## $:.unshift(File.dirname(__FILE__))
+
+## minitest setup
+
+require 'minitest/autorun'
+
+
+## our own code
+require 'csvrecord'
+
+## add test_data_dir helper
+module CsvRecord
+  def self.test_data_dir
+    "#{root}/test/data"
+  end
+end

data/test/test_beer.rb

@@ -0,0 +1,160 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_beer.rb
+
+
+require 'helper'
+
+class TestBeer < MiniTest::Test
+
+  def test_version
+    pp CsvRecord::VERSION
+    pp CsvRecord.banner
+    pp CsvRecord.root
+
+    assert true  ## assume ok if we get here
+  end
+
+
+  def test_class_style1
+     clazz1 = CsvRecord.define do
+       field :brewery, :string   # fix: do NOT use 'Brewery' - name SHOULD be a valid variable name
+       field :city,    :string
+       field :name     ## default type is :string
+       field :abv,     Float    ## allow type specified as class
+     end
+     pp clazz1
+     pp clazz1.fields
+
+     assert true  ## assume ok if we get here
+  end
+
+  Beer = CsvRecord.define do
+     string :brewery   # fix: do NOT use 'Brewery' - name SHOULD be a valid variable name
+     string :city
+     string :name
+     float  :abv
+  end
+
+  class BeerClassic < CsvRecord::Base
+    field :brewery
+    field :city
+    field :name
+    field :abv, Float
+  end
+
+
+  def test_class_style2
+    clazz2 = CsvRecord.define do
+       string :brewery   # fix: do NOT use 'Brewery' - name SHOULD be a valid variable name
+       string :city
+       string :name
+       float  :abv
+    end
+    pp clazz2
+    pp clazz2.class.name
+    pp clazz2.fields
+
+    txt  = File.open( "#{CsvRecord.test_data_dir}/beer.csv", 'r:utf-8' ).read
+    data = CSV.parse( txt, headers: true )
+    pp data
+    pp data.to_a   ## note: includes header (first row with field names)
+
+    puts "== parse( data ).to_a:"
+    pp clazz2.parse( data ).to_a
+    pp Beer.parse( data ).to_a
+
+    puts "== parse( data ).each:"
+    ## loop over records
+    clazz2.parse( data ).each do |rec|
+      puts "#{rec.name} (#{rec.abv}%) by #{rec.brewery}, #{rec.city}"
+    end
+
+    puts "== parse( txt ).to_a:"
+    pp Beer.parse( txt ).to_a
+
+    pp clazz2.class.name
+    pp clazz2.class.name
+    pp Beer.class.name
+
+    assert true  ## assume ok if we get here
+  end
+
+
+  def test_read
+    puts "== read( data ).to_a:"
+    beers = Beer.read( "#{CsvRecord.test_data_dir}/beer.csv" ).to_a
+    puts "#{beers.size} beers:"
+    pp beers
+
+    pp Beer.fields
+
+    assert true  ## assume ok if we get here
+  end
+
+  def test_classic
+    puts "== read( data ).to_a:"
+    beers = BeerClassic.read( "#{CsvRecord.test_data_dir}/beer.csv" ).to_a
+    puts "#{beers.size} beers:"
+    pp beers
+
+    pp BeerClassic.fields
+
+    beer = BeerClassic.new
+    pp beer
+    beer.update( abv: 12.7 )
+    beer.update( brewery: 'Andechser Klosterbrauerei',
+                 city:   'Andechs',
+                 name:   'Doppelbock Dunkel' )
+    pp beer
+
+    assert_equal 12.7, beer.abv
+    assert_equal 'Andechser Klosterbrauerei', beer.brewery
+    assert_equal 'Andechs', beer.city
+    assert_equal 'Doppelbock Dunkel', beer.name
+  end
+
+
+  def test_new
+    beer = Beer.new
+    pp beer
+    beer.update( abv: 12.7 )
+    beer.update( brewery: 'Andechser Klosterbrauerei',
+                 city:   'Andechs',
+                 name:   'Doppelbock Dunkel' )
+    pp beer
+
+    assert_equal 12.7, beer.abv
+    assert_equal 'Andechser Klosterbrauerei', beer.brewery
+    assert_equal 'Andechs', beer.city
+    assert_equal 'Doppelbock Dunkel', beer.name
+
+
+    pp beer.abv
+    pp beer.abv = 12.7
+    pp beer.abv
+    assert_equal 12.7, beer.abv
+
+    pp beer.parse_abv( '12.8%' )   ## (auto-)converts/typecasts string to specified type (e.g. float)
+    assert_equal 12.8, beer.abv
+
+    pp beer.name
+    pp beer.name = 'Doppelbock Dunkel'
+    pp beer.name
+    assert_equal 'Doppelbock Dunkel', beer.name
+
+
+    beer2 = Beer.new( brewery: 'Andechser Klosterbrauerei',
+                      city:   'Andechs',
+                      name:   'Doppelbock Dunkel' )
+    pp beer2
+
+    assert_equal nil, beer2.abv
+    assert_equal 'Andechser Klosterbrauerei', beer2.brewery
+    assert_equal 'Andechs', beer2.city
+    assert_equal 'Doppelbock Dunkel', beer2.name
+  end
+
+end # class TestBeer

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csvrecord
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-08-11 00:00:00.000000000 Z
+date: 2018-08-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc
@@ -55,7 +55,12 @@ files:
 - README.md
 - Rakefile
 - lib/csvrecord.rb
+- lib/csvrecord/base.rb
+- lib/csvrecord/builder.rb
 - lib/csvrecord/version.rb
+- test/data/beer.csv
+- test/helper.rb
+- test/test_beer.rb
 homepage: https://github.com/csv11/csvrecord
 licenses:
 - Public Domain