csv_lazy 0.0.0

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/.rspec

@@ -0,0 +1 @@
+--color

data/Gemfile

@@ -0,0 +1,13 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "rspec", "~> 2.8.0"
+  gem "rdoc", "~> 3.12"
+  gem "bundler", ">= 1.0.0"
+  gem "jeweler", "~> 1.8.4"
+end

data/Gemfile.lock

@@ -0,0 +1,31 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    diff-lcs (1.1.3)
+    git (1.2.5)
+    jeweler (1.8.4)
+      bundler (~> 1.0)
+      git (>= 1.2.5)
+      rake
+      rdoc
+    json (1.7.4)
+    rake (0.9.2.2)
+    rdoc (3.12)
+      json (~> 1.4)
+    rspec (2.8.0)
+      rspec-core (~> 2.8.0)
+      rspec-expectations (~> 2.8.0)
+      rspec-mocks (~> 2.8.0)
+    rspec-core (2.8.0)
+    rspec-expectations (2.8.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.8.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (>= 1.0.0)
+  jeweler (~> 1.8.4)
+  rdoc (~> 3.12)
+  rspec (~> 2.8.0)

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2012 Kasper Johansen
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,19 @@
+= csv_lazy
+
+Description goes here.
+
+== Contributing to csv_lazy
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
+* Fork the project.
+* Start a feature/bugfix branch.
+* Commit and push until you are happy with your contribution.
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+== Copyright
+
+Copyright (c) 2012 Kasper Johansen. See LICENSE.txt for
+further details.
+

data/Rakefile

@@ -0,0 +1,49 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "csv_lazy"
+  gem.homepage = "http://github.com/kaspernj/csv_lazy"
+  gem.license = "MIT"
+  gem.summary = %Q{A small CSV lib that skips whitespace-format-bugs and more.}
+  gem.description = %Q{A small CSV lib that skips whitespace-format-bugs and more.}
+  gem.email = "k@spernj.org"
+  gem.authors = ["Kasper Johansen"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+RSpec::Core::RakeTask.new(:rcov) do |spec|
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :default => :spec
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "csv_lazy #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.0.0

data/csv_lazy.gemspec

@@ -0,0 +1,61 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{csv_lazy}
+  s.version = "0.0.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Kasper Johansen"]
+  s.date = %q{2012-08-09}
+  s.description = %q{A small CSV lib that skips whitespace-format-bugs and more.}
+  s.email = %q{k@spernj.org}
+  s.extra_rdoc_files = [
+    "LICENSE.txt",
+    "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+    ".rspec",
+    "Gemfile",
+    "Gemfile.lock",
+    "LICENSE.txt",
+    "README.rdoc",
+    "Rakefile",
+    "VERSION",
+    "csv_lazy.gemspec",
+    "lib/csv_lazy.rb",
+    "spec/csv_lazy_spec.rb",
+    "spec/spec_helper.rb",
+    "spec/test1.csv.gz"
+  ]
+  s.homepage = %q{http://github.com/kaspernj/csv_lazy}
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.6.2}
+  s.summary = %q{A small CSV lib that skips whitespace-format-bugs and more.}
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<rspec>, ["~> 2.8.0"])
+      s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_development_dependency(%q<bundler>, [">= 1.0.0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.8.4"])
+    else
+      s.add_dependency(%q<rspec>, ["~> 2.8.0"])
+      s.add_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_dependency(%q<bundler>, [">= 1.0.0"])
+      s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
+    end
+  else
+    s.add_dependency(%q<rspec>, ["~> 2.8.0"])
+    s.add_dependency(%q<rdoc>, ["~> 3.12"])
+    s.add_dependency(%q<bundler>, [">= 1.0.0"])
+    s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
+  end
+end
+

data/lib/csv_lazy.rb

@@ -0,0 +1,160 @@
+class Csv_lazy
+  include Enumerable
+  
+  def initialize(args, &blk)
+    @args = {
+      :quote_char => '"',
+      :row_sep => "\n",
+      :col_sep => ";"
+    }.merge(args)
+    
+    @io = @args[:io]
+    @eof = false
+    @buffer = ""
+    @debug = @args[:debug]
+    #@debug = true
+    
+    accepted = [:quote_char, :row_sep, :col_sep, :io]
+    @args.each do |key, val|
+      if accepted.index(key) == nil
+        raise "Unknown argument: '#{key}'."
+      end
+    end
+    
+    raise "No ':quote_char' was given." if @args[:quote_char].to_s.strip.empty?
+    raise "No ':col_sep' was given." if @args[:col_sep].to_s.strip.empty?
+    raise "No ':row_sep' was given." if @args[:row_sep].to_s.empty?
+    raise "No ':io' was given." if !@args[:io]
+    
+    @regex_begin_quote_char = /\A\s*#{Regexp.escape(@args[:quote_char])}/
+    
+    @regex_row_end = /\A\s*?#{Regexp.escape(@args[:row_sep])}/
+    @regex_colsep_next = /\A#{Regexp.escape(@args[:col_sep])}/
+    
+    @regex_read_until_quote_char = /\A(.*?)#{Regexp.escape(@args[:quote_char])}/
+    @regex_read_until_col_sep = /\A(.*?)#{Regexp.escape(@args[:col_sep])}/
+    @regex_read_until_row_sep = /\A(.+?)#{Regexp.escape(@args[:row_sep])}/
+    @regex_read_until_end = /\A(.+?)\Z/
+    
+    self.each(&blk) if blk
+  end
+  
+  #Yields each row as an array.
+  def each
+    while row = read_row
+      yield(row)
+    end
+  end
+  
+  private
+  
+  #Reads more content into the buffer.
+  def read_buffer
+    read = @io.read(4096)
+    if !read
+      @eof = true
+    else
+      @buffer << read
+    end
+  end
+  
+  #Returns the next row.
+  def read_row
+    @row = []
+    while !@eof or !@buffer.empty?
+      break if !read_next_col
+    end
+    
+    row = @row
+    @row = nil
+    
+    puts "csv_lazy: Row: #{row}\n\n" if @debug
+    
+    if row.empty?
+      return false
+    else
+      return row
+    end
+  end
+  
+  #Runs a regex against the buffer. If matched it also removes it from the buffer.
+  def read_remove_regex(regex)
+    if match = @buffer.match(regex)
+      oldbuffer = @buffer
+      @buffer = @buffer.gsub(regex, "")
+      
+      if @debug
+        print "csv_lazy: Regex: #{regex.to_s}\n"
+        print "csv_lazy: Match: #{match.to_a}\n"
+        print "csv_lazy: Buffer before: #{oldbuffer}\n"
+        print "csv_lazy: Buffer after: #{@buffer}\n"
+        print "\n"
+      end
+      
+      raise "Buffer was the same before regex?" if oldbuffer == @buffer
+      return match
+    end
+    
+    return false
+  end
+  
+  #Adds the next column to the row. Returns true if more columns should be read or false if this was the end of the row.
+  def read_next_col
+    read_buffer if @buffer.length < 4096
+    return false if @buffer.empty? and @eof
+    
+    if @buffer.empty? or read_remove_regex(@regex_row_end)
+      return false
+    elsif match = read_remove_regex(@regex_begin_quote_char)
+      read = ""
+      
+      loop do
+        match_read = read_remove_regex(@regex_read_until_quote_char)
+        if !match_read
+          read_buffer
+        else
+          @row << match_read[1]
+          break
+        end
+      end
+      
+      read_buffer if @buffer.length < 4096
+      
+      if read_remove_regex(@regex_colsep_next)
+        return true
+      elsif @eof and @buffer.empty?
+        puts "csv_lazy: End-of-file and empty buffer." if @debug
+        return false
+      elsif read_remove_regex(@regex_row_end)
+        puts "csv_lazy: Row-end found." if @debug
+        return false
+      else
+        raise "Dont know what to do (#{@buffer.length}): #{@buffer}"
+      end
+    elsif match = read_remove_regex(@regex_read_until_col_sep)
+      @row << match[1]
+      return true
+    elsif match = read_remove_regex(@regex_read_until_row_sep)
+      puts "csv_lazy: Row seperator reached." if @debug
+      @row << match[1]
+      return false
+    elsif match = read_remove_regex(@regex_read_until_end)
+      if @eof
+        @row << match[1]
+        return false
+      end
+      
+      @buffer << match[0]
+      read_buffer
+      raise Csv_lazy::Retry
+    else
+      raise "Dont know what to do with buffer: #{@buffer}"
+    end
+  rescue Csv_lazy::Retry
+    retry
+  end
+end
+
+class Csv_lazy::Retry < RuntimeError
+
+end

data/spec/csv_lazy_spec.rb

@@ -0,0 +1,67 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe "CsvLazy" do
+  it "should be able to read CSV" do
+    cont = "1;2;3;4;5\n6;7;8;9;10"
+    
+    count = 0
+    Csv_lazy.new(:io => StringIO.new(cont)) do |csv|
+      raise "Expected count of 5 but it wasnt: #{csv.length} (#{csv})" if csv.length != 5
+      
+      csv.each do |csv_ele|
+        raise "Expected numeric value but it wasnt: '#{csv_ele}'." if !csv_ele.to_s.match(/^(\d+)$/)
+      end
+      
+      count += 1
+    end
+    
+    raise "Expected 2 rows but got #{count}" if count != 2
+  end
+  
+  it "should be able to read mixed CSV" do
+    cont = "1;\"2\";3;\"4\";5\n6;7;8;9;10"
+    
+    count = 0
+    Csv_lazy.new(:io => StringIO.new(cont)) do |csv|
+      raise "Expected count of 5 but it wasnt: #{csv.length} (#{csv})" if csv.length != 5
+      
+      csv.each do |csv_ele|
+        raise "Expected numeric value but it wasnt: '#{csv_ele}'." if !csv_ele.to_s.match(/^(\d+)$/)
+      end
+      
+      count += 1
+    end
+    
+    raise "Expected 2 rows but got #{count}" if count != 2
+  end
+  
+  it "should be able to handle ending whitespaces" do
+    cont = "1;2;3;4;\"5\"     \n6;7;8;9;\"10\""
+    
+    count = 0
+    Csv_lazy.new(:io => StringIO.new(cont)) do |csv|
+      raise "Expected count of 5 but it wasnt: #{csv.length} (#{csv})" if csv.length != 5
+      
+      csv.each do |csv_ele|
+        raise "Expected numeric value but it wasnt: '#{csv_ele}'." if !csv_ele.to_s.match(/^(\d+)$/)
+      end
+      
+      count += 1
+    end
+    
+    raise "Expected 2 rows but got #{count}" if count != 2
+  end
+  
+  it "should read sample 1" do
+    count = 0
+    Zlib::GzipReader.open("#{File.dirname(__FILE__)}/test1.csv.gz") do |gz|
+      Csv_lazy.new(:io => gz, :col_sep => ",", :row_sep => "\r\n") do |row|
+        raise "Expected length of 32 but it wasnt: #{row.length}" if row.length != 32
+        raise "Expected C-format or 'contract_id' column as the first but it wasnt: #{row[0]}" if !row[0].to_s.match(/^C(\d+)$/) and row[0] != "contract_id"
+        count += 1
+      end
+    end
+    
+    raise "Expected 23 rows but got #{count}" if count != 23
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,12 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'rspec'
+require 'csv_lazy'
+
+# Requires supporting files with custom matchers and macros, etc,
+# in ./support/ and its subdirectories.
+Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
+
+RSpec.configure do |config|
+  
+end

metadata

@@ -0,0 +1,115 @@
+--- !ruby/object:Gem::Specification 
+name: csv_lazy
+version: !ruby/object:Gem::Version 
+  prerelease: 
+  version: 0.0.0
+platform: ruby
+authors: 
+- Kasper Johansen
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2012-08-09 00:00:00 +02:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: 2.8.0
+  type: :development
+  prerelease: false
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: rdoc
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: "3.12"
+  type: :development
+  prerelease: false
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: bundler
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.0.0
+  type: :development
+  prerelease: false
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: jeweler
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: 1.8.4
+  type: :development
+  prerelease: false
+  version_requirements: *id004
+description: A small CSV lib that skips whitespace-format-bugs and more.
+email: k@spernj.org
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE.txt
+- README.rdoc
+files: 
+- .document
+- .rspec
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.rdoc
+- Rakefile
+- VERSION
+- csv_lazy.gemspec
+- lib/csv_lazy.rb
+- spec/csv_lazy_spec.rb
+- spec/spec_helper.rb
+- spec/test1.csv.gz
+has_rdoc: true
+homepage: http://github.com/kaspernj/csv_lazy
+licenses: 
+- MIT
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 4190482346075524299
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.6.2
+signing_key: 
+specification_version: 3
+summary: A small CSV lib that skips whitespace-format-bugs and more.
+test_files: []
+