csv_parser 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0182c5c8d43682eaf967338eab5d249c5036ed54
+  data.tar.gz: 249c47d4015daba1d0def6019449d400b1c8bb2c
+SHA512:
+  metadata.gz: 29835c6d4346804386d2882ee8141207a24eef5fc1fd4163b7bb01d0582b63fa091c9968e934e6dff4a425763393f953a40a0e787054c9a69b75c88a056323d0
+  data.tar.gz: 2ce0c0176e2611e7e569c295cf2b511d2266cc52bbb371ab23422186b3b1a11a023508649d922fc7ee75c237e6567300fb7d002b776a38fcf358c70b752e5519

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in csv_parser.gemspec
+gemspec
+
+gem 'byebug'

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Vanderbilt University
+
+MIT License
+
+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.md

@@ -0,0 +1,64 @@
+# CsvParser
+
+CsvParser is a CSV parser that focuses on identifying errors.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'csv_parser'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install csv_parser
+
+## Usage
+
+CsvParser's goal is to give you descriptive error messages.
+
+### Error types
+
+* missing closing quote (`CsvParser::MissingQuoteError`)
+* quote in the wrong place (`CsvParser::StrayQuoteError`)
+* rows with not enough fields (`CsvParser::MissingFieldsError`)
+* rows with too many fields (`CsvParser::ExtraFieldsError`)
+
+### Options
+
+You can pass in an options hash to the `CsvParser.parse` method
+that contains one or more of the following options:
+
+* `:field_sep` - specify field separator (default is `","`)
+* `:record_sep` - specify record separator (default is `"\n"`)
+* `:quote_char` - specify quote character (default is `"\""`)
+* `:allow_empty_record` - specify whether empty records are allowed (default is `true`)
+* `:skip_empty_record` - specify whether empty records are skipped (default is `true`)
+* `:allow_uneven_records` - specify whether records with different field lengths are allowed (default is `true`)
+
+### Example
+
+```ruby
+require 'csv_parser'
+
+data = <<EOF
+foo,"bar
+baz,quz
+EOF
+begin
+  result = CsvParser.parse(data)
+rescue CsvParser::Error => e
+  # e is a CsvParser::MissingQuoteError
+end
+```
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,16 @@
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new do |t|
+  t.libs << "test"
+  t.pattern = 'test/**/test*.rb'
+end
+task :test => :treetop
+task :default => :test
+
+desc "Compile treetop grammar"
+task :treetop => "lib/csv_parser/csv_parser.rb"
+
+file "lib/csv_parser/csv_parser.rb" => "lib/csv_parser.treetop" do
+  system("tt lib/csv_parser.treetop -o lib/csv_parser/csv_parser.rb")
+end

data/csv_parser.gemspec

@@ -0,0 +1,25 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'csv_parser/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "csv_parser"
+  spec.version       = CsvParser::VERSION
+  spec.authors       = ["Jeremy Stephens"]
+  spec.email         = ["jeremy.f.stephens@vanderbilt.edu"]
+  spec.description   = %q{CSV parser with advanced error reporting}
+  spec.summary       = %q{CSV parser with advanced error reporting}
+  spec.homepage      = "https://github.com/coupler/csv_parser"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency 'treetop'
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "test-unit"
+end

data/lib/csv_parser.rb

@@ -0,0 +1,60 @@
+require 'treetop'
+
+require 'csv_parser/version'
+require 'csv_parser/parser_extensions'
+require 'csv_parser/result'
+
+#Treetop.load(File.join(File.dirname(__FILE__), 'csv_parser.treetop'))
+require 'csv_parser/csv_parser'
+
+module CsvParser
+  class Error < Exception
+    attr_reader :line, :column
+
+    def initialize(msg, line, column)
+      super(msg)
+      @line = line
+      @column = column
+    end
+  end
+
+  class MissingQuoteError < Error; end
+  class StrayQuoteError < Error; end
+  class MissingFieldsError < Error; end
+  class ExtraFieldsError < Error; end
+
+  def self.parse(data, options = {})
+    parser = ::CsvParser::CsvParser.new
+    options.each_pair do |key, value|
+      parser.send("#{key}=", value)
+    end
+    result = parser.parse(data)
+    if result
+      warnings = parser.warnings.collect do |(desc, line, col)|
+        error(desc, line, col)
+      end
+      Result.new(result.value, warnings)
+    else
+      raise error(parser.failure_type, parser.failure_line,
+                  parser.failure_column, parser.failure_reason)
+    end
+  end
+
+  def self.error(type, line, column, msg = nil)
+    klass, msg =
+      case type
+      when :missing_quote
+        [MissingQuoteError, "no ending quote found for quote on line #{line}, column #{column}"]
+      when :stray_quote
+        [StrayQuoteError, "invalid quote found on line #{line}, column #{column}"]
+      when :missing_fields
+        [MissingFieldsError, "record on line #{line} had too few fields"]
+      when :extra_fields
+        [ExtraFieldsError, "record on line #{line} had too many fields"]
+      else
+        Error
+      end
+
+    klass.new(msg, line, column)
+  end
+end

data/lib/csv_parser.treetop

@@ -0,0 +1,232 @@
+module CsvParser
+  grammar Csv
+    include ParserExtensions
+
+    rule records
+      non_empty_records / empty_records
+    end
+
+    rule non_empty_records
+      first_record
+      other_records
+      {
+        def value
+          arr = [first_record.value]
+          rest = other_records.value
+          if rest
+            arr.push(*rest)
+          end
+          arr
+        end
+      }
+    end
+
+    rule empty_records
+      ''
+      {
+        def value
+          []
+        end
+      }
+    end
+
+    rule first_record
+      '' &{ |s| @first_record = true; true }
+      non_empty_record
+      &{ |s| @first_record_length = @record_length; true }
+      {
+        def value
+          non_empty_record.value
+        end
+      }
+    end
+
+    rule other_records
+      '' &{ |s| @first_record = false; true }
+      (
+        (
+          &{ |s| skip_empty_record? }
+          (
+            record_sep
+            ( empty_record record_sep )*
+            non_empty_record
+          )*
+          (
+            &{ |s| skip_empty_record? }
+            ( record_sep empty_record )+
+          )?
+          {
+            def value
+              val = elements[1].elements.collect { |elt| elt.non_empty_record.value }
+              val.empty? ? nil : val
+            end
+          }
+        )
+        /
+        (
+          &{ |s| !skip_empty_record? }
+          ( record_sep record )*
+          {
+            def value
+              val = elements[1].elements.collect { |elt| elt.record.value }
+              val.empty? ? nil : val
+            end
+          }
+        )
+      )
+      {
+        def value
+          elements[2].value
+        end
+      }
+    end
+
+    rule record
+      non_empty_record / empty_record
+    end
+
+    rule non_empty_record
+      first:field
+      &{ |s| @record_length = 1; @warning = nil; true }
+      rest:(
+        &{ |s|
+          if @first_record || @record_length < @first_record_length
+            true
+          else
+            if allow_uneven_records?
+              @warning ||= [:extra_fields, input.line_of(index + 1), input.column_of(index + 1)]
+              true
+            else
+              @failure_type = :extra_fields
+              false
+            end
+          end
+        }
+        field_sep
+        field
+        &{ |s| @record_length += 1; true }
+      )*
+      &{ |s|
+        if @first_record || @record_length >= @first_record_length
+          if @warning
+            warnings << @warning
+          end
+          true
+        else
+          if allow_uneven_records?
+            warnings << [:missing_fields, input.line_of(index), input.column_of(index)]
+            true
+          else
+            @failure_type = :missing_fields
+            false
+          end
+        end
+      }
+      {
+        def value
+          arr = [first.value]
+          rest.elements.each do |elt|
+            arr << elt.field.value
+          end
+          arr
+        end
+      }
+    end
+
+    rule empty_record
+      ''
+      &{ |s|
+        if allow_empty_record?
+          true
+        else
+          @failure_type = :missing_fields
+          false
+        end
+      }
+      {
+        def value
+          []
+        end
+      }
+    end
+
+    rule field
+      unquoted_text
+      {
+        def value
+          elements.map(&:text_value).join
+        end
+      }
+      /
+      quoted_text
+      {
+        def value
+          elements[1..-2].map(&:text_value).join
+        end
+      }
+    end
+
+    rule quoted_text
+      quote
+      ( !quote . )+
+      (
+        quote
+        /
+        '' !{ |s| @failure_type = :missing_quote; @failure_index = start_index; true }
+      )
+    end
+
+    rule unquoted_text
+      (
+        !field_sep
+        !record_sep
+        (
+          !quote
+          /
+          '' !{ |s| @failure_type = :stray_quote; true }
+        )
+        .
+      )+
+    end
+
+    rule field_sep
+      &{ |s| @field_sep_index = 0; true }
+      (
+        !record_sep
+        !quote
+        .
+        &{ |s|
+          if @field_sep_index < field_sep.length &&
+             s[2].text_value == field_sep[@field_sep_index]
+            @field_sep_index += 1
+            true
+          else
+            false
+          end
+        }
+      )+
+      &{ |s| s.map(&:text_value).join == field_sep }
+    end
+
+    rule record_sep
+      &{ |s| @record_sep_index = 0; true }
+      (
+        .
+        &{ |s|
+          if @record_sep_index < record_sep.length &&
+             s[0].text_value == record_sep[@record_sep_index]
+            @record_sep_index += 1
+            true
+          else
+            false
+          end
+        }
+      )+
+      &{ |s| s.map(&:text_value).join == record_sep }
+    end
+
+    rule quote
+      !"\\" . &{ |s| s[1].text_value[0] == quote_char[0] }
+    end
+  end
+end