csvyaml 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1d89beb0f7d059235cd458d33f33b107fba249cb
-  data.tar.gz: c6404fe2ab304c3130ba97afdd72ab1e8badf9c6
+  metadata.gz: c07f82dfd13c43d0246141a6c79d36d42222d00a
+  data.tar.gz: 45ac0671f99a0d44b7ffd782c6ab3462f1304ba3
 SHA512:
-  metadata.gz: 85372ed928cd3a8fc433afba51333951ac1632b254f9092e3eb2c0de698bbfff697e27ccfa9c90ee520fc5204ff71525ca19df6509f77e02c75a230c2d5a5a93
-  data.tar.gz: 4c0eaca93f47884b0e4c88eef1eb5eef1c688fb874dd2cbd33d9a209b2a3e833f5f5da8d5ad8624d5104a28df77003a248d6cd73952d7dfaf3f87a5476251df9
+  metadata.gz: 0fae80b8706cf2def97794fc32f0aaae92efd3bc403dd9904e7be1370b05b84c4670ba25d4b64ca3aeb3af3135a83ae4c60577904d724678c8b8d48bfed2c593
+  data.tar.gz: 996746983caeeef7ce305533c5d564e375656cbd4787a8e9698d56fc5f2ba71cb6703fb93e33b672bb0f489ae75bc6269a5cd28d8921d0d758ff4699c8c22cb5

data/Manifest.txt

@@ -3,4 +3,10 @@ Manifest.txt
 README.md
 Rakefile
 lib/csvyaml.rb
+lib/csvyaml/parser.rb
 lib/csvyaml/version.rb
+test/data/hello.yaml.csv
+test/data/hello11.yaml.csv
+test/helper.rb
+test/test_parser.rb
+test/test_parser_misc.rb

data/README.md

@@ -1,14 +1,15 @@
 # CSV <3 YAML Parser / Reader
 
-csvyaml library / gem - read tabular data in the CSV <3 YAML format, that is, comma-separated values CSV (line-by-line) records with yaml ain't markup language (YAML) encoding rules
+csvyaml library / gem - read tabular data in the CSV <3 YAML format, that is, comma-separated values (CSV) line-by-line records with yaml ain't markup language (YAML) encoding rules
 
-* home  :: [github.com/csv11/csvyaml](https://github.com/csv11/csvyaml)
-* bugs  :: [github.com/csv11/csvyaml/issues](https://github.com/csv11/csvyaml/issues)
+* home  :: [github.com/csvreader/csvyaml](https://github.com/csvreader/csvyaml)
+* bugs  :: [github.com/csvreader/csvyaml/issues](https://github.com/csvreader/csvyaml/issues)
 * gem   :: [rubygems.org/gems/csvyaml](https://rubygems.org/gems/csvyaml)
 * rdoc  :: [rubydoc.info/gems/csvyaml](http://rubydoc.info/gems/csvyaml)
 * forum :: [wwwmake](http://groups.google.com/group/wwwmake)
 
 
+
 ## Usage
 
 to be done

data/Rakefile

@@ -8,7 +8,7 @@ Hoe.spec 'csvyaml' do
   self.summary = "csvyaml - read tabular data in the CSV <3 YAML format, that is, comma-separated values CSV (line-by-line) records with yaml ain't markup language (YAML) encoding rules"
   self.description = summary
 
-  self.urls    = ['https://github.com/csv11/csvyaml']
+  self.urls    = ['https://github.com/csvreader/csvyaml']
 
   self.author  = 'Gerald Bauer'
   self.email   = 'wwwmake@googlegroups.com'

data/lib/csvyaml.rb

@@ -1,11 +1,21 @@
 # encoding: utf-8
 
 require 'pp'
-
+require 'yaml'
+require 'logger'
 
 ## our own code
 require 'csvyaml/version'    # note: let version always go first
+require 'csvyaml/parser'
+
+
+
+## add some "alternative" shortcut aliases
+CSV_YAML = CsvYaml
+CSVYAML  = CsvYaml
+CSVY     = CsvYaml
+CsvY     = CsvYaml
+
 
 
-pp CsvYaml.banner
-pp CsvYaml.root
+puts CsvYaml.banner

data/lib/csvyaml/parser.rb

@@ -0,0 +1,133 @@
+# encoding: utf-8
+
+
+class CsvYaml
+
+###################################
+## add simple logger with debug flag/switch
+#
+#  use Parser.debug = true   # to turn on
+#
+#  todo/fix: use logutils instead of std logger - why? why not?
+
+def self.build_logger()
+  l = Logger.new( STDOUT )
+  l.level = :info    ## set to :info on start; note: is 0 (debug) by default
+  l
+end
+def self.logger() @@logger ||= build_logger; end
+def logger()  self.class.logger; end
+
+
+
+
+
+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 = new( f )
+
+    # handle blocks like Ruby's open()
+    if block_given?
+      begin
+        block.call( csv )
+      ensure
+        csv.close
+      end
+    else
+      csv
+    end
+end # method self.open
+
+
+def self.read( path )
+    open( path ) { |csv| csv.read }
+end
+
+
+def self.foreach( path, &block )
+  csv = open( path )
+
+  if block_given?
+    begin
+      csv.each( &block )
+    ensure
+      csv.close
+    end
+  else
+    csv.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 )
+  csv = new( str_or_readable )
+
+  if block_given?
+    csv.each( &block )  ## note: caller (responsible) must close file!!! - add autoclose - why? why not?
+  else  # slurp contents, if no block is given
+    csv.read            ## note: caller (responsible) must close file!!! - add autoclose - why? why not?
+  end
+end # method self.parse
+
+
+
+def initialize( str_or_readable )
+  if str_or_readable.is_a?( String )
+    @input = str_or_readable   # note: just needs each for each_line
+  else  ## assume io
+    @input = str_or_readable
+  end
+end
+
+
+
+include Enumerable
+
+def each( &block )
+  if block_given?
+    @input.each_line do |line|
+
+      logger.debug  "line:"             if logger.debug?
+      logger.debug line.pretty_inspect  if logger.debug?
+
+
+      ##  note: chomp('') if is an empty string,
+      ##    it will remove all trailing newlines from the string.
+      ##    use line.sub(/[\n\r]*$/, '') or similar instead - why? why not?
+      line = line.chomp( '' )
+      line = line.strip         ## strip leading and trailing whitespaces (space/tab) too
+      logger.debug line.pretty_inspect    if logger.debug?
+
+      if line.empty?             ## skip blank lines
+        logger.debug "skip blank line"    if logger.debug?
+        next
+      end
+
+      if line.start_with?( "#" )  ## skip comment lines
+        logger.debug "skip comment line"   if logger.debug?
+        next
+      end
+
+      ## note: auto-wrap in array e.g. with []
+      ##   add document marker (---) why? why not?
+      values = YAML.load( "---\n[#{line}]" )
+      logger.debug values.pretty_inspect   if logger.debug?
+      block.call( values )
+    end
+  else
+     to_enum
+  end
+end # method each
+
+def read() to_a; end # method read
+
+def close
+  @input.close   if @input.respond_to?(:close)   ## note: string needs no close
+end
+
+end # class CsvYaml

data/lib/csvyaml/version.rb

@@ -4,10 +4,11 @@
 class CsvYaml
 
   MAJOR = 0
-  MINOR = 0
-  PATCH = 1
+  MINOR = 1
+  PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
+
   def self.version
     VERSION
   end

data/test/data/hello.yaml.csv

@@ -0,0 +1,3 @@
+1,John,12 Totem Rd. Aspen,true
+2,Bob,null,false
+3,Sue,"Bigsby, 345 Carnival, WA 23009",false

data/test/data/hello11.yaml.csv

@@ -0,0 +1,5 @@
+# hello world
+
+1, John, 12 Totem Rd. Aspen,               true
+2, Bob,  null,                             false
+3, Sue,  "Bigsby, 345 Carnival, WA 23009", false

data/test/helper.rb

@@ -0,0 +1,20 @@
+## $:.unshift(File.dirname(__FILE__))
+
+## minitest setup
+
+require 'minitest/autorun'
+
+
+## our own code
+require 'csvyaml'
+
+
+## add test_data_dir helper
+class CsvYaml
+  def self.test_data_dir
+    "#{root}/test/data"
+  end
+end
+
+
+CsvYaml.logger.level = :debug   ## turn on "global" logging

data/test/test_parser.rb

@@ -0,0 +1,104 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_parser.rb
+
+
+require 'helper'
+
+class TestParser < MiniTest::Test
+
+
+def parser
+  CsvYaml
+end
+
+
+def records   ## "standard" records for testing
+  [[1, "John", "12 Totem Rd. Aspen",             true],
+   [2, "Bob",  nil,                              false],
+   [3, "Sue",  "Bigsby, 345 Carnival, WA 23009", false]]
+end
+
+
+
+def test_parse
+  assert_equal records, parser.parse( <<TXT )
+1,John,12 Totem Rd. Aspen,true
+2,Bob,null,false
+3,Sue,"Bigsby, 345 Carnival, WA 23009",false
+TXT
+
+  assert_equal records, parser.parse( <<TXT )
+# hello world
+
+1,John,12 Totem Rd. Aspen,true
+2,Bob,null,false
+3,Sue,"Bigsby, 345 Carnival, WA 23009",false
+TXT
+
+  assert_equal records, parser.parse( <<TXT )
+  # hello world (pretty printed)
+
+  1, John, 12 Totem Rd. Aspen,               true
+  2, Bob,  null,                             false
+  3, Sue,  "Bigsby, 345 Carnival, WA 23009", false
+
+  # try more comments and empty lines
+
+TXT
+
+
+  txt =<<TXT
+  # hello world
+  1,John,12 Totem Rd. Aspen,true
+  2,Bob,null,false
+  3,Sue,"Bigsby, 345 Carnival, WA 23009",false
+TXT
+
+  recs = []
+  parser.parse( txt ) { |rec| recs << rec }
+  assert_equal records, recs
+end
+
+
+def test_read
+  assert_equal records, parser.read( "#{CsvYaml.test_data_dir}/hello.yaml.csv" )
+  assert_equal records, parser.read( "#{CsvYaml.test_data_dir}/hello11.yaml.csv" )
+end
+
+
+def test_open
+  assert_equal records, parser.open( "#{CsvYaml.test_data_dir}/hello.yaml.csv", "r:bom|utf-8" ).read
+  assert_equal records, parser.open( "#{CsvYaml.test_data_dir}/hello11.yaml.csv", "r:bom|utf-8" ).read
+end
+
+
+def test_foreach
+  recs = []
+  parser.foreach( "#{CsvYaml.test_data_dir}/hello.yaml.csv" ) { |rec| recs << rec }
+  assert_equal records, recs
+
+  recs = []
+  parser.foreach( "#{CsvYaml.test_data_dir}/hello11.yaml.csv" ) { |rec| recs << rec }
+  assert_equal records, recs
+end
+
+
+def test_enum
+  csv = CsvYaml.new( <<TXT )
+  # hello world
+
+  1,John,12 Totem Rd. Aspen,true
+  2,Bob,null,false
+  3,Sue,"Bigsby, 345 Carnival, WA 23009",false
+TXT
+
+  it = csv.to_enum
+  assert_equal [1, "John", "12 Totem Rd. Aspen",             true],  it.next
+  assert_equal [2, "Bob",  nil,                              false], it.next
+  assert_equal [3, "Sue",  "Bigsby, 345 Carnival, WA 23009", false], it.next
+end
+
+end # class TestParser

data/test/test_parser_misc.rb

@@ -0,0 +1,82 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_parser_misc.rb
+
+
+require 'helper'
+
+class TestParserMisc < MiniTest::Test
+
+
+def parser
+  CsvYaml
+end
+
+
+def test_quotes_and_commas
+  assert_equal [
+    [1, "John", "12 Totem Rd., Aspen", true],
+    [2, "Bob",  nil,                   false],
+    [3, "Sue", "\"Bigsby\", 345 Carnival, WA 23009", false]
+    ], parser.parse( <<TXT )
+  1,John,"12 Totem Rd., Aspen",true
+  2,Bob,null,false
+  3,Sue,"\\"Bigsby\\", 345 Carnival, WA 23009",false
+TXT
+end
+
+
+def test_arrays
+  assert_equal [
+    [1, "directions", ["north","south","east","west"]],
+    [2, "colors", ["red","green","blue"]],
+    [3, "drinks", ["soda","water","tea","coffe"]],
+    [4, "spells", []],
+  ], parser.parse( <<TXT )
+  # CSV <3 YAML with array values
+
+  1,directions,[north,south,east,west]
+  2,colors,[red,green,blue]
+  3,drinks,[soda,water,tea,coffe]
+  4,spells,[]
+TXT
+end
+
+def test_misc
+  ## note:
+  ##   in the csv <3 json source text backslash needs to get doubled / escaped twice e.g.
+  ##   \\"  for quotes
+  ##   \\n  for newlines and so on
+
+  assert_equal [
+    ["index", "value1", "value2"],
+    ["number", 1, 2],
+    ["boolean", false, true],
+    ["null", nil, "non null"],
+    ["array of numbers", [1], [1,2]],
+    ["simple object", {"a" => 1}, {"a" => 1, "b" => 2}],
+    ["array with mixed objects", [1, nil,"ball"], [2,{"a" => 10, "b" => 20},"cube"]],
+    ["string with quotes", "a\"b", "alert(\"Hi!\")"],
+    ["string with bell&newlines","bell is \u0007","multi\nline\ntext"]
+  ], parser.parse( <<TXT )
+  # CSV with all kinds of values
+
+  index,value1,value2
+  number,1,2
+  boolean,false,true
+  "null",null,non null
+  array of numbers,[1],[1,2]
+  ## note: key:value pairs need a space after colon!!! NOT working {a:1},{a:1, b:2}
+  simple object,{a: 1},{a: 1, b: 2}
+  ## note: again - key:value pairs need a space after colon!!! NOT working {a:10, b:20}
+  array with mixed objects,[1,null,ball],[2,{a: 10,b: 20},cube]
+  string with quotes,"a\\"b","alert(\\"Hi!\\")"
+  string with bell&newlines,"bell is \\u0007","multi\\nline\\ntext"
+TXT
+
+end
+
+
+end # class TestParserMisc

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csvyaml
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-10-17 00:00:00.000000000 Z
+date: 2018-10-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc
@@ -54,8 +54,14 @@ files:
 - README.md
 - Rakefile
 - lib/csvyaml.rb
+- lib/csvyaml/parser.rb
 - lib/csvyaml/version.rb
-homepage: https://github.com/csv11/csvyaml
+- test/data/hello.yaml.csv
+- test/data/hello11.yaml.csv
+- test/helper.rb
+- test/test_parser.rb
+- test/test_parser_misc.rb
+homepage: https://github.com/csvreader/csvyaml
 licenses:
 - Public Domain
 metadata: {}