southeastern-daily-performance 0.0.2 → 0.0.3

data/README.md

@@ -0,0 +1,19 @@
+## Installation
+
+    $ gem install southeastern-daily-performance -r http://gemcutter.org
+
+## Usage
+
+    $ sedpr-to-csv <location-of-html>
+
+## Examples
+
+### Explicitly download html and convert local file
+
+    $ curl "http://www.southeasternrailway.co.uk/index.php/cms/pages/view/132" > sedpr.html
+    $ sedpr-to-csv sedpr.html
+
+
+### Implicitly download html and convert
+
+    $ sedpr-to-csv http://www.southeasternrailway.co.uk/index.php/cms/pages/view/132

data/Rakefile

@@ -1,24 +1,24 @@
 task :default => :test
 
-# require "rake/testtask"
-# Rake::TestTask.new do |t|
-#   t.libs << "test"
-#   t.test_files = FileList["test/**/*_test.rb"]
-#   t.verbose = true
-# end
-# 
-# require File.join(File.dirname(__FILE__), 'lib', 'sedpr')
-# task 'convert' do
-#   if data_dir = ENV['DATA_DIR']
-#     Dir[File.join(data_dir, '*.html')].each do |html_file|
-#       html = File.read(html_file)
-#       puts DailyPerformanceReport.new(html).to_csv
-#     end
-#   else
-#     puts "Usage: DATA_DIR=/path/to/html-reports rake convert"
-#     exit 1
-#   end
-# end
+require "rake/testtask"
+Rake::TestTask.new do |t|
+  t.libs << "test"
+  t.test_files = FileList["test/**/*_test.rb"]
+  t.verbose = true
+end
+
+require File.join(File.dirname(__FILE__), 'lib', 'sedpr')
+task 'convert' do
+  if data_dir = ENV['DATA_DIR']
+    Dir[File.join(data_dir, '*.html')].each do |html_file|
+      html = File.read(html_file)
+      puts DailyPerformanceReport.new(html).to_csv
+    end
+  else
+    puts "Usage: DATA_DIR=/path/to/html-reports rake convert"
+    exit 1
+  end
+end
 
 require "rubygems"
 require "rake/gempackagetask"
@@ -33,24 +33,24 @@ spec = Gem::Specification.new do |s|
 
   # Change these as appropriate
   s.name              = "southeastern-daily-performance"
-  s.version           = "0.0.2"
+  s.version           = "0.0.3"
   s.summary           = "Converts Southeaster Daily Performance reports from HTML to CSV"
   s.author            = "Chris Roos"
   s.email             = "chris@seagul.co.uk"
   s.homepage          = "http://github.com/chrisroos/southeastern-daily-performance"
 
   s.has_rdoc          = true
-  s.extra_rdoc_files  = %w(README)
-  s.rdoc_options      = %w(--main README)
+  s.extra_rdoc_files  = %w(README.md)
+  s.rdoc_options      = %w(--main README.md)
 
   # Add any extra files to include in the gem
-  s.files             = %w(README Rakefile) + Dir.glob("{bin,test,lib/**/*}")
+  s.files             = %w(README.md Rakefile) + Dir.glob("{bin,test,lib/**/*}")
   s.executables       = FileList["bin/**"].map { |f| File.basename(f) }
   s.require_paths     = ["lib"]
 
   # If you want to depend on other gems, add them here, along with any
   # relevant versions
-  # s.add_dependency("some_other_gem", "~> 0.1.0")
+  s.add_dependency('hpricot')
 
   # If your tests use any gems, include them here
   # s.add_development_dependency("mocha") # for example

data/bin/sedpr-to-csv

@@ -8,5 +8,5 @@ unless html_location = ARGV[0]
   exit 1
 end
 
-html = open(html_location)
-puts DailyPerformanceReport.new(html).to_csv
+io = open(html_location)
+puts SoutheasternDailyPerformance::DailyPerformanceReport.new(io.read).to_csv

data/lib/sedpr.rb

@@ -1,3 +1,3 @@
-$: << File.join(File.dirname(__FILE__), 'sedpr')
-
-require 'daily_performance_report'
+require File.expand_path '../sedpr/affected_service',         __FILE__
+require File.expand_path '../sedpr/affected_services_report', __FILE__
+require File.expand_path '../sedpr/daily_performance_report', __FILE__

data/lib/sedpr/affected_service.rb

@@ -1,41 +1,43 @@
-class AffectedService
+module SoutheasternDailyPerformance
+  class AffectedService
   
-  attr_reader :reason_for_disruption
-  attr_reader :scheduled_start_time, :scheduled_start_station, :scheduled_destination_station
-  attr_reader :effect_on_service
+    attr_reader :reason_for_disruption
+    attr_reader :scheduled_start_time, :scheduled_start_station, :scheduled_destination_station
+    attr_reader :effect_on_service
   
-  def initialize(reason_for_disruption, incident_text)
-    @reason_for_disruption = reason_for_disruption
-    if incident_text =~ /(\d\d:\d\d) (.*?) ?(?:-|to|\?) (.*)/
-      @scheduled_start_time, @scheduled_start_station = $1, $2
-      destination_and_effect_on_service = $3
-      @scheduled_start_station.gsub!(/[^a-zA-Z ]/, '')
-      reasons = [
-        'cancelled', 'started', 'delayed by', 'did not call', 'terminated at', 'diverted'
-      ]
-      matches = reasons.collect do |reason|
-        destination_and_effect_on_service =~ /#{reason}/i
-      end
-      if matches.compact.min && reason = reasons[matches.index(matches.compact.min)]
-        destination_and_effect_on_service =~ /(.*) (#{reason}.*)/i
-      else
-        unless destination_and_effect_on_service.split(' ').length == 1
-          warn "Warning. Unknown, or missing, affect on service: '#{incident_text}'"
+    def initialize(reason_for_disruption, incident_text)
+      @reason_for_disruption = reason_for_disruption
+      if incident_text =~ /(\d\d:\d\d) (.*?) ?(?:-|to|\?) (.*)/
+        @scheduled_start_time, @scheduled_start_station = $1, $2
+        destination_and_effect_on_service = $3
+        @scheduled_start_station.gsub!(/[^a-zA-Z ]/, '')
+        reasons = [
+          'cancelled', 'started', 'delayed by', 'did not call', 'terminated at', 'diverted'
+        ]
+        matches = reasons.collect do |reason|
+          destination_and_effect_on_service =~ /#{reason}/i
         end
-        destination_and_effect_on_service =~ /(.*)/
+        if matches.compact.min && reason = reasons[matches.index(matches.compact.min)]
+          destination_and_effect_on_service =~ /(.*) (#{reason}.*)/i
+        else
+          unless destination_and_effect_on_service.split(' ').length == 1
+            warn "Warning. Unknown, or missing, affect on service: '#{incident_text}'"
+          end
+          destination_and_effect_on_service =~ /(.*)/
+        end
+        @scheduled_destination_station, @effect_on_service = $1, ($2||'')
+      else
+        warn "Warning. Cannot parse service details: '#{incident_text}'"
       end
-      @scheduled_destination_station, @effect_on_service = $1, ($2||'')
-    else
-      warn "Warning. Cannot parse service details: '#{incident_text}'"
     end
-  end
   
-  def ==(incident)
-    self.reason_for_disruption         == incident.reason_for_disruption and
-    self.scheduled_start_time          == incident.scheduled_start_time and
-    self.scheduled_start_station       == incident.scheduled_start_station and
-    self.scheduled_destination_station == incident.scheduled_destination_station and
-    self.effect_on_service             == incident.effect_on_service
-  end
+    def ==(incident)
+      self.reason_for_disruption         == incident.reason_for_disruption and
+      self.scheduled_start_time          == incident.scheduled_start_time and
+      self.scheduled_start_station       == incident.scheduled_start_station and
+      self.scheduled_destination_station == incident.scheduled_destination_station and
+      self.effect_on_service             == incident.effect_on_service
+    end
   
+  end
 end

data/lib/sedpr/affected_services_report.rb

@@ -1,28 +1,28 @@
-require 'rubygems'
 require 'hpricot'
-require 'affected_service'
 
-class AffectedServicesReport
+module SoutheasternDailyPerformance
+  class AffectedServicesReport
   
-  def initialize(html)
-    html.gsub!(/ /, ' ')
-    @doc = Hpricot(html)
-  end
+    def initialize(html)
+      html.gsub!(/ /, ' ')
+      @doc = Hpricot(html)
+    end
   
-  def affected_services
-    @doc.search('*').collect do |elem|
-      if elem.text? and incident_text = elem.inner_text[/\d\d:\d\d.*/]
-        reason = find_previous_strong_element(elem).inner_text
-        AffectedService.new(reason.strip, incident_text.strip)
-      end
-    end.compact
-  end
+    def affected_services
+      @doc.search('*').collect do |elem|
+        if elem.text? and incident_text = elem.inner_text[/\d\d:\d\d.*/]
+          reason = find_previous_strong_element(elem).inner_text
+          AffectedService.new(reason.strip, incident_text.strip)
+        end
+      end.compact
+    end
   
-  private
+    private
   
-    def find_previous_strong_element(elem)
-      return elem if (elem.respond_to?(:name) and elem.name == 'strong')
-      find_previous_strong_element(elem.previous)
-    end
+      def find_previous_strong_element(elem)
+        return elem if (elem.respond_to?(:name) and elem.name == 'strong')
+        find_previous_strong_element(elem.previous)
+      end
   
+  end
 end

data/lib/sedpr/daily_performance_report.rb

@@ -1,55 +1,57 @@
-require 'rubygems'
 require 'hpricot'
-require 'affected_services_report'
 require 'csv'
+require 'date'
 
-class DailyPerformanceReport
+module SoutheasternDailyPerformance
+  class DailyPerformanceReport
   
-  def initialize(html)
-    @doc = Hpricot(html)
-  end
+    def initialize(html)
+      html = html.gsub(%r! !, ' ')
+      @doc = Hpricot(html)
+    end
   
-  def date
-    date = (@doc/'h1').inner_text
-    date.gsub!(/\?/, ' ')
-    if date =~ /(.+?) (\d+) (.+)/
-    elsif (@doc/'h2').inner_text =~ /(.+?) (\d+) (.+)/
+    def date
+      date = (@doc/'h1').inner_text
+      date.gsub!(/\?/, ' ')
+      if date =~ /(.+?) (\d+) (.+)/
+      elsif (@doc/'h2').inner_text =~ /(.+?) (\d+) (.+)/
+      end
+      day_name, day, month_name = $1, $2, $3
+      date = [day, month_name[0..2].downcase, '2010'].join('-')
+      Date.parse(date)
     end
-    day_name, day, month_name = $1, $2, $3
-    date = [day, month_name[0..2].downcase, '2010'].join('-')
-    Date.parse(date)
-  end
   
-  def scheduled_services
-    report[/(\d+) train services were scheduled/, 1].to_i
-  end
+    def scheduled_services
+      report[/(\d+) train services were scheduled/, 1].to_i
+    end
   
-  def actual_services
-    report[/of which (\d+) ran/, 1].to_i
-  end
+    def actual_services
+      report[/of which (\d+) ran/, 1].to_i
+    end
   
-  def services_within_five_minutes_of_schedule
-    report[/(\d+)% of services ran within 5 minutes of schedule/, 1].to_i
-  end
+    def services_within_five_minutes_of_schedule
+      report[/(\d+)% of services ran within 5 minutes of schedule/, 1].to_i
+    end
   
-  def affected_services
-    AffectedServicesReport.new(report_container.inner_html).affected_services
-  end
+    def affected_services
+      AffectedServicesReport.new(report_container.inner_html).affected_services
+    end
   
-  def to_csv
-    affected_services.collect do |service|
-      CSV.generate_line [date, service.reason_for_disruption, service.scheduled_start_time, service.scheduled_start_station, service.scheduled_destination_station, service.effect_on_service]
-    end.join("\n")
-  end
+    def to_csv
+      affected_services.collect do |service|
+        CSV.generate_line [date, service.reason_for_disruption, service.scheduled_start_time, service.scheduled_start_station, service.scheduled_destination_station, service.effect_on_service]
+      end.join("\n")
+    end
   
-  private
+    private
   
-    def report
-      report_container.inner_text
-    end
+      def report
+        report_container.inner_text
+      end
     
-    def report_container
-      (@doc/'h1').first.parent.next_sibling
-    end
+      def report_container
+        (@doc/'h1').first.parent.next_sibling
+      end
     
+  end
 end

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: southeastern-daily-performance
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 3
+  version: 0.0.3
 platform: ruby
 authors: 
 - Chris Roos
@@ -9,10 +14,21 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-02-14 00:00:00 +00:00
+date: 2010-10-09 00:00:00 +01:00
 default_executable: 
-dependencies: []
-
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
 description: 
 email: chris@seagul.co.uk
 executables: 
@@ -20,9 +36,9 @@ executables:
 extensions: []
 
 extra_rdoc_files: 
-- README
+- README.md
 files: 
-- README
+- README.md
 - Rakefile
 - lib/sedpr/affected_service.rb
 - lib/sedpr/affected_services_report.rb
@@ -35,25 +51,27 @@ licenses: []
 post_install_message: 
 rdoc_options: 
 - --main
-- README
+- README.md
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: southeastern-daily-performance
-rubygems_version: 1.3.5
+rubygems_version: 1.3.6
 signing_key: 
 specification_version: 3
 summary: Converts Southeaster Daily Performance reports from HTML to CSV

data/README

@@ -1,18 +0,0 @@
-Installation
-============
-$ gem install southeastern-daily-performance -r http://gemcutter.org
-
-
-Usage
-=====
-$ sedpr-to-csv <location-of-html>
-
-
-Examples
-========
-# Explicitly download html and convert local file
-$ curl "http://www.southeasternrailway.co.uk/index.php/cms/pages/view/132" > sedpr.html
-$ sedpr-to-csv sedpr.html
-
-# Implicitly download html and convert
-$ sedpr-to-csv http://www.southeasternrailway.co.uk/index.php/cms/pages/view/132