csv11 0.0.3

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2d7cb8629cffcede12c4545bc884afff3b65c306
+  data.tar.gz: aef587fdb3d5d9d7f949d91ff2f5c3ccf7b5ff5c
+SHA512:
+  metadata.gz: '0218c870f0dc609009f3b4f1cbebdb6cbd9cd2c0812897493988cff88d28c89681ce8a0b4428280ed94adaa22cc8a194973942bdd7a1beb224513cb98164cde3'
+  data.tar.gz: 5e2d3a577fb6d436e7d4e1247744250d344368e0393c799f3307e764a041243d5db26cd308fd65674a99c304b92befb24c3713c174a29b4ce80824bcce4ba4b2

data/HISTORY.md

@@ -0,0 +1,3 @@
+### 0.0.1 / 2017-07-02
+
+* Everything is new. First release.

data/Manifest.txt

@@ -0,0 +1,8 @@
+HISTORY.md
+Manifest.txt
+README.md
+Rakefile
+lib/csv11.rb
+lib/csv11/version.rb
+test/helper.rb
+test/test_version.rb

data/README.md

@@ -0,0 +1,27 @@
+# csv11
+
+csv11 library / gem - read / parse comma-separated values (csv); supports csv 1.1 incl. comments, named values, multi-line records, and more
+
+* home  :: [github.com/csv11/csv11](https://github.com/csv11/csv11)
+* bugs  :: [github.com/csv11/csv11/issues](https://github.com/csv11/csv11/issues)
+* gem   :: [rubygems.org/gems/csvalues](https://rubygems.org/gems/csv11)
+* rdoc  :: [rubydoc.info/gems/csvalues](http://rubydoc.info/gems/csv11)
+
+
+
+
+## Usage
+
+to be done
+
+
+## License
+
+![](https://publicdomainworks.github.io/buttons/zero88x31.png)
+
+The `csv11` scripts are dedicated to the public domain.
+Use it as you please with no restrictions whatsoever.
+
+## Questions? Comments?
+
+Post them to the [wwwmake forum](http://groups.google.com/group/wwwmake). Thanks!

data/Rakefile

@@ -0,0 +1,26 @@
+require 'hoe'
+require './lib/csv11/version.rb'
+
+Hoe.spec 'csv11' do
+
+  self.version = Values::VERSION
+
+  self.summary = 'csv11 - read / parse comma-separated values (csv); supports csv 1.1 incl. comments, named values, multi-line records, and more'
+  self.description = summary
+
+  self.urls    = ['https://github.com/csv11/csv11']
+
+  self.author  = 'Gerald Bauer'
+  self.email   = 'ruby-talk@ruby-lang.org'
+
+  # switch extension to .markdown for gihub formatting
+  self.readme_file  = 'README.md'
+  self.history_file = 'HISTORY.md'
+
+  self.licenses = ['Public Domain']
+
+  self.spec_extras = {
+   required_ruby_version: '>= 2.2.2'
+  }
+
+end

data/lib/csv11.rb

@@ -0,0 +1,257 @@
+# encoding: utf-8
+
+
+require 'pp'
+require 'strscan'   ## StringScanner
+
+
+# our own code
+require 'csv11/version'   # note: let version always go first
+
+
+module Values
+
+
+  class Parser
+
+
+    Token = Struct.new(:name, :value) do
+      def unquoted?()      name=='UNQUOTED';      end
+      def quoted?()        name=='QUOTED';        end
+      def triple_quoted?() name=='TRIPLE_QUOTED'; end
+    end
+
+    class Unquoted < Token
+      def initialize( value ) super( 'UNQUOTED', value ); end
+    end
+
+    class Quoted < Token
+      def initialize( value ) super( 'QUOTED', value ); end
+    end
+
+    class TripleQuoted < Token
+      def initialize( value ) super( 'TRIPLE_UNQUOTED', value ); end
+    end
+
+
+
+    def initialize
+    end
+
+##
+##   how to handle:
+##      country:dk
+##      mailto:hello             ## use excluded (reserved names urn, mailto, http, https)
+##      http://example.com
+##      urn:hello:444
+##      name:"hello, world!"
+
+
+    def parse_line
+
+      loop do
+        t = parse_token
+        if t.nil?
+           puts "!! format error: expected token with value, returns nil - rest is >>#{@buffer.rest}<<"
+           break
+        end
+
+        if @buffer.peek(1) == ','
+           @buffer.getch   ## consume ','
+           puts "adding value >>#{t.value}<<"
+           @values << t.value
+        elsif @buffer.eos?
+           puts "adding (last) value >>#{t.value}<<"
+           @values << t.value
+           break
+        elsif @buffer.peek(1) == ':'
+           @buffer.getch  ## consume ':'
+
+           ## todo/fix:
+           ##    do NOT allow names for quoted, triple_quoted for now - why? why not?
+           ##   issue a format error: why? why not??
+
+           if @values.empty?
+             ### note:special case:
+             ##  if first token is a name/key
+             ##   consume all the rest!! including commas, colons etc.
+             ##    no escape needed for nothing
+             value = @buffer.rest
+             value = value.strip
+             puts "adding (single-line) first named value >>#{t.value}<< : >>#{value}<<"
+             @values << [t.value,value]
+             break
+           else
+             t2 = parse_token( match_name: false )
+             puts "adding named value >>#{t.value}<< : >>#{t2.value}<<"
+             @values << [t.value,t2.value]
+
+             if @buffer.peek(1) == ','
+                @buffer.getch  ## consume ','
+             elsif @buffer.eos?
+                break
+             else
+                puts "!! format error: expected comma (,) or EOS - rest is >>#{@buffer.rest}<<"
+                break
+             end
+           end
+        else
+          puts "!! format error: expected comma (,) or colon (:) or EOS - rest is >>#{@buffer.rest}<<"
+          break
+        end
+      end
+    end
+
+
+
+    def match_triple_quoted?
+      ## todo/fix: use @buffer.match - """ (next letter MUST Not be "!! e.g.""""" not valid!!!
+      @buffer.peek(3) == %{"""} ||  ## double triple quotes
+      @buffer.peek(3) == %{'''}     ## single triple quotes
+    end
+
+    ## todo/fix: use @buffer.match - " (next letter MUST Not be "!! e.g."" not valid!!!
+    def match_quoted?
+       @buffer.peek(1) == %{"} ||   ## double quote
+       @buffer.peek(1) == %{'}      ## single quote
+    end
+
+
+    def parse_triple_quoted
+       token = nil # nothing found
+
+       if @buffer.peek(3) == %{"""}   ## double quote
+         @buffer.getch  # consume double quote
+         @buffer.getch
+         @buffer.getch
+         value = @buffer.scan_until( /(?=""")/)
+         @buffer.getch  # consume double quote
+         @buffer.getch
+         @buffer.getch
+         @buffer.skip( /[ \t]*/ )    ## skip trailing WHITESPACE
+         puts %{quoted """...""" value >>#{value}<<}
+         token = TripleQuoted.new( value )
+       elsif @buffer.peek(3) == %{'''}   ## single quote
+         @buffer.getch  # consume single quote
+         @buffer.getch
+         @buffer.getch
+         value = @buffer.scan_until( /(?=''')/)
+         @buffer.getch  # consume single quote
+         @buffer.getch
+         @buffer.getch
+         @buffer.skip( /[ \t]*/ )    ## skip trailing WHITESPACE
+         puts %{quoted '''...''' value >>#{value}<<}
+         token = TripleQuoted.new( value )
+       else
+         ## do nothing; report format error
+       end
+
+       token
+    end
+
+    def parse_quoted
+       token = nil # nothing found
+
+       if @buffer.peek(1) == '"'   ## double quote
+         @buffer.getch  # consume double quote
+         value = @buffer.scan_until( /(?=")/)
+         @buffer.getch  # consume double quote
+         @buffer.skip( /[ \t]*/ )    ## skip trailing WHITESPACE
+         puts %{quoted "..." value >>#{value}<<}
+         token = Quoted.new( value )
+       elsif @buffer.peek(1) == "'"   ## single quote
+         @buffer.getch  # consume single quote
+         value = @buffer.scan_until( /(?=')/)
+         @buffer.getch  # consume single quote
+         @buffer.skip( /[ \t]*/ )    ## skip trailing WHITESPACE
+         puts %{quoted '...' value >>#{value}<<}
+         token = Quoted.new( value )
+       else
+         ## do nothing; report format error
+       end
+
+       token
+    end
+
+
+    def parse_unquoted( match_name: true )
+       ## unquoted value
+       puts "collect unquoted token (match_name? => #{match_name})  - rest: >>#{@buffer.rest}<<"
+
+       if match_name
+         value = @buffer.scan_until( /(?=[,:]|$)/)
+
+         ## check for reserverd "non-keys" e.g.:
+         ###  https: http:
+         ###  urn:
+         ###  mailto:
+         ###  file:
+         ###    add some more??
+         ##    todo/fix: add ip address e.g. 127.0.0.1: too ??
+         reserved_names = %w{ https http urn mailto file }
+         name_regex = %r{^[a-zA-Z0-9._-]+$}    ## todo/fix: allow more chars
+
+         if @buffer.peek(1) == ':'
+           if reserved_names.include?( value )
+              ## continue scan until next comma or eos(end-of-string)!!!
+              value << @buffer.scan_until( /(?=,|$)/)
+           elsif name_regex.match( value ).nil?
+              ## does NOT match name/key pattern
+              ## continue scan until next comma or eos(end-of-string)!!!
+              value << @buffer.scan_until( /(?=,|$)/)
+           else
+             ## continue
+           end
+         end
+       else    ## do NOT match name (named values) e.g. do NOT include colon (:)
+         value = @buffer.scan_until( /(?=[,]|$)/)
+       end
+
+       value = value.rstrip    ## right strip whitespace
+       puts "value >>#{value}<<"
+       token = Unquoted.new( value )
+    end
+
+
+
+    def parse_token( match_name: true )
+       @buffer.skip( /[ \t]*/ )    ## skip WHITESPACE
+
+       token = nil  # nothing found
+
+       if match_triple_quoted?    # """...""" or '''...'''
+         token = parse_triple_quoted
+       elsif match_quoted?        # "..." or '...'
+         token = parse_quoted
+       else
+         token = parse_unquoted( match_name: match_name )
+       end
+       token
+    end
+
+
+
+    def parse(str)
+      puts ""
+      puts "**** parse >>#{str}<<"
+
+      @values = []
+      @buffer = StringScanner.new(str)
+
+      parse_line
+      @values
+    end
+  end   ## class Parser
+
+
+
+  def self.split( line )
+    parser = Parser.new
+    parser.parse( line )
+  end
+
+end # module Values
+
+
+# say hello
+puts Values.banner    if defined?( $RUBYLIBS_DEBUG )

data/lib/csv11/version.rb

@@ -0,0 +1,20 @@
+# encoding: utf-8
+
+module Values
+  MAJOR = 0    ## todo: namespace inside version or something - why? why not??
+  MINOR = 0
+  PATCH = 3
+  VERSION = [MAJOR,MINOR,PATCH].join('.')
+
+  def self.version
+    VERSION
+  end
+
+  def self.banner
+    "csv11/#{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 Values

data/test/helper.rb

@@ -0,0 +1,10 @@
+# encoding: utf-8
+
+## minitest setup
+require 'minitest/autorun'
+
+
+$RUBYLIBS_DEBUG = true
+
+## our own code
+require 'csv11'

data/test/test_version.rb

@@ -0,0 +1,21 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_version.rb
+
+
+require 'helper'
+
+
+class TestVersion < MiniTest::Test
+
+
+  def test_version
+
+    puts Values::VERSION
+    assert true
+    ## assume everything ok if get here
+  end
+
+end # class TestVersion

metadata

@@ -0,0 +1,86 @@
+--- !ruby/object:Gem::Specification
+name: csv11
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+platform: ruby
+authors:
+- Gerald Bauer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-08-04 00:00:00.000000000 Z
+dependencies:
+- !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: csv11 - read / parse comma-separated values (csv); supports csv 1.1 incl.
+  comments, named values, multi-line records, and more
+email: ruby-talk@ruby-lang.org
+executables: []
+extensions: []
+extra_rdoc_files:
+- HISTORY.md
+- Manifest.txt
+- README.md
+files:
+- HISTORY.md
+- Manifest.txt
+- README.md
+- Rakefile
+- lib/csv11.rb
+- lib/csv11/version.rb
+- test/helper.rb
+- test/test_version.rb
+homepage: https://github.com/csv11/csv11
+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: csv11 - read / parse comma-separated values (csv); supports csv 1.1 incl.
+  comments, named values, multi-line records, and more
+test_files: []