parshap-csv_parser 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bf9451df46924fe41eda4419f25e0671935c25f7
+  data.tar.gz: 4f6f2c86e00d2d196cab35b82ee51008d9961d5a
+SHA512:
+  metadata.gz: 0dc0ca17212b387126bdfce745bbea9180c7034bfc04017458da645b0ee277dbe5100ef79f0e108a983d29d6ee66150495b9c97fbd521fb897e0af2b605c8b59
+  data.tar.gz: 83006cb3d94a7ef47d98645fba7a346ed77d264bcc5d59edcce8e400f49505c59eac84ce6da5c5c9d41d71cea45771d6296f8008a21ccb0151a7829be0c7ecd9

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in csv-parser.gemspec
+gemspec

data/README.md

@@ -0,0 +1,103 @@
+# CSVParser
+
+Parse CSV rows by defining parsing blocks for individual columns.
+
+Each row is parsed one-by-one. First a new *Hash* is initialized to
+store data for the row. Then, each **individual column** is parsed by
+calling matching parsing blocks. Parsing blocks are passed the column's
+value and header key and can set arbitrary state on the *Hash* for the
+current row.
+
+## Installation
+
+```
+$ gem install parshap-csv_parser
+```
+
+## Usage
+
+Given a `data.csv` file:
+
+```csv
+name,phone
+john doe,555-481-2345
+jane c doe,555-123-4567
+```
+
+You can parse it like so:
+
+```rb
+require "csv_parser"
+
+class MyParser < CSVParser
+  parse "Name" do |val|
+    self[:first_name], self[:last_name] = val.split(nil, 2)
+  end
+  
+  parse /Phone( Number)?/ do |val|
+    self[:phone] = val
+  end
+end
+
+MyParser.new(CSV.open "data.csv").each do |row|
+  puts "#{row[:first_name]}, #{row[:last_name]}: #{row[:phone]}"
+end
+```
+
+See [`example.rb`](example.rb) and [`test.rb`](test.rb) for more examples.
+
+### Defining Parsers
+
+Parsing blocks are added using the `CSVParser.parse` class method. The
+first and only parameter, *case*, determines if the block should be
+executed for a particular column (by using the `===` operator with the
+column's header value). The block is passed the column value and its
+associated header value. The block can update the values for the current
+row by using `self` as a *Hash*.
+
+Column and header values are always converted to strings and `strip`ped
+of whitespace first.
+
+```rb
+class MyParser < CSVParser
+  parse /^(first|last)?\W*name$/i do |val|
+    self[:name] = val.capitalize
+  end
+end
+```
+
+#### Once Parsers
+
+Using `CSVParser.parse_once`, you can define parsers that will only be
+called once per row, for the first matching column. In the above
+example, if `parse_once` was used, the block would only be called once
+even with the occurrence of multiple *name* columns.
+
+### Default Row Values
+
+The `CSVParser#defaults` method is used to generate a hash to use for
+each row. You can use this to set default values.
+
+```rb
+class MyParser < CSVParser
+  def defaults
+    { name: "User", emails: [] }
+  end
+end
+```
+
+### CSV Instance
+
+The `CSVParser` constructor takes an instance of the [Ruby Standard
+Library `CSV`
+class](http://ruby-doc.org/stdlib-2.1.0/libdoc/csv/rdoc/CSV.html). This
+object can be created in any way, but **the [`:headers`
+option](http://ruby-doc.org/stdlib-2.1.0/libdoc/csv/rdoc/CSV.html#method-c-new)
+must be `false`**.
+
+
+## Tests
+
+```
+$ ruby test.rb
+```

data/csv_parser.rb

@@ -0,0 +1,97 @@
+class CSVParser
+  class << self
+    def parsers
+      @parsers ||= []
+    end
+
+    private
+
+    # Add a column parser
+    def parse(criteria, params={}, &block)
+      parsers << {
+        criteria: criteria,
+        block: block,
+      }.merge(params)
+    end
+
+    # Add a parser that will only get called once per row
+    def parse_once(criteria, params={}, &block)
+      parse criteria, {
+        once: true,
+      }.merge(params), &block
+    end
+  end
+
+  def initialize(csv)
+    @csv = csv
+  end
+
+  include Enumerable
+
+  def each
+    # Get header values used later in prasing
+    @headers = @csv.shift.map(&:to_s).map(&:strip)
+
+    # Parse each row
+    @csv.each do |row|
+      yield parse_row row
+    end
+  end
+
+  private
+
+  def parsers
+    self.class.parsers
+  end
+
+  def parse_row(row)
+    # Create a new attributes hash for this row, this will be our result
+    @attributes = defaults
+    # Keep track of which parsers have already been executed for this row
+    @executed = []
+
+    # Parse each column of the row
+    row.each_with_index do |val, i|
+      parse_val val.to_s.strip, @headers[i].to_s
+    end
+
+    # Return the attributes that were built using #[]=
+    @attributes
+  end
+
+  # Parse a column value
+  def parse_val(val, key)
+    parsers.each do |parser|
+      # Execute any parsers that match this column
+      if ! onced?(parser) && match?(parser, val, key)
+        instance_exec val, key, &parser[:block]
+        @executed << parser
+      end
+    end
+  end
+
+  # Is the parser a once parser and has already been executed for this row?
+  def onced?(parser)
+    parser[:once] && @executed.include?(parser)
+  end
+
+  # Does the parser criteria match the column?
+  def match?(parser, val, key)
+    parser[:criteria] === key
+  end
+
+  # Default hash values to use for each row
+  def defaults
+    Hash.new
+  end
+
+  protected
+
+  def [](name)
+    @attributes[name]
+  end
+
+  def []=(name, val)
+    @attributes[name] = val
+  end
+end

data/example.rb

@@ -0,0 +1,74 @@
+class ExampleParser < CSVParser
+  parse_once "Name" do |val|
+    first_name, last_name = val.split(nil, 2)
+    self[:first_name] = first_name
+    self[:last_name] = last_name
+  end
+
+  parse_once "Search Timeframe" do |val|
+    self[:timeframe] = val
+  end
+
+  parse_once "Email (Personal) #1" do |val|
+    self[:email] = split(val).join ","
+  end
+
+  parse_once "Contact Type" do |val|
+    self[:contact_types] << val
+  end
+
+  parse_once /^Phone (Mobile) #\d$/ do |val|
+    self[:phone_numbers] << {
+      label: "Cell",
+      number: val,
+    }
+  end
+
+  # Notes
+  [
+    "Note",
+    "Home Type",
+    "Latest Communication",
+    /^Listing #\d$/,
+  ].each do |name|
+    parse name do |val|
+      self[:notes] << {
+        content: val
+      }
+    end
+  end
+
+  # Property Search
+
+  parse_once "Min. Price" do |val|
+    self[:property_search][:price_low] = val
+  end
+
+  parse_once "Max. Price" do |val|
+    self[:property_search][:price_high] = val
+  end
+
+  parse /^Location #\d$/ do |val|
+    self[:property_search][:misc_locations] << {
+      name: "Other #{val}",
+      location_value: val,
+    }
+  end
+
+  private
+
+  def split(s)
+    s.split(/[\s*,;]/).map(&:strip).reject(&:empty?)
+  end
+
+  def defaults
+    {
+      notes: [],
+      contact_types: [],
+      phone_numbers: [],
+      property_search: {
+        misc_locations: [],
+      },
+    }
+  end
+end

data/parshap-csv_parser.gemspec

@@ -0,0 +1,15 @@
+Gem::Specification.new do |spec|
+  spec.name = "parshap-csv_parser"
+  spec.version = "1.0.0"
+  spec.authors = ["Parsha Pourkhomami"]
+  spec.email = ["parshap+gem@gmail.com"]
+  spec.summary = "High-level CSV parser"
+  spec.homepage = "https://github.com/parshap/csv-parser"
+  spec.license = "Public Domain"
+  spec.require_paths = ["."]
+
+  spec.files = `git ls-files`.split($/)
+  spec.test_files = spec.files.grep(/^test/)
+
+  spec.add_development_dependency "test-unit"
+end

data/test.rb

@@ -0,0 +1,95 @@
+require "test/unit"
+require "csv"
+require_relative "csv_parser"
+
+class SimpleParser < CSVParser
+  attr_reader :called
+  attr_reader :once_called
+  attr_reader :first_called
+
+  def initialize(csv)
+    @called = 0
+    @once_called = 0
+    @first_called = 0
+    super
+  end
+
+  parse String do |val, key|
+    @called += 1
+    self[key] = val
+  end
+
+  parse_once String do
+    @once_called += 1
+  end
+
+  parse "first" do
+    @first_called += 1
+  end
+end
+
+class RegexpParser < CSVParser
+  parse /first(_name)?/ do |val, key|
+    self[key] = val
+  end
+end
+
+class CSVParserTest < Test::Unit::TestCase
+  def csv
+    CSV.new <<-EOF
+      first,last
+      parsha,pourkhomami
+      hey,you
+    EOF
+  end
+
+  def test_basic
+    count = 0
+    CSVParser.new(csv).each do |data|
+      assert data
+      count += 1
+    end
+    assert_equal 2, count
+  end
+
+  def test_simple_parser
+    assert_equal 0, CSVParser.parsers.length
+    assert_equal 3, SimpleParser.parsers.length
+
+    parser = SimpleParser.new csv
+    count = 0
+    array = []
+
+    parser.each do |data|
+      assert data
+      count += 1
+      assert_equal 2 * count, parser.called
+      assert_equal 1 * count, parser.once_called
+      assert_equal 1 * count, parser.first_called
+      array << data
+    end
+
+    assert_equal({
+      "first" => "parsha",
+      "last" => "pourkhomami",
+    }, array[0])
+
+    assert_equal({
+      "first" => "hey",
+      "last" => "you",
+    }, array[1])
+
+    assert_equal 2, count
+    assert_equal 2, array.length
+    assert_equal 4, parser.called
+    assert_equal 2, parser.once_called
+    assert_equal 2, parser.first_called
+  end
+
+  def test_regexp
+    array = RegexpParser.new(csv).to_a
+    assert_equal 2, array.length
+    assert_equal({ "first" => "parsha" }, array[0])
+    assert_equal({ "first" => "hey" }, array[1])
+  end
+end

metadata

@@ -0,0 +1,65 @@
+--- !ruby/object:Gem::Specification
+name: parshap-csv_parser
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Parsha Pourkhomami
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-12-31 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 
+email:
+- parshap+gem@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- Gemfile
+- README.md
+- csv_parser.rb
+- example.rb
+- parshap-csv_parser.gemspec
+- test.rb
+homepage: https://github.com/parshap/csv-parser
+licenses:
+- Public Domain
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- .
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: High-level CSV parser
+test_files:
+- test.rb