typogruby 1.0.7 → 1.0.8

data/.gitignore

@@ -21,3 +21,5 @@ pkg
 ## PROJECT::SPECIFIC
 .yardoc
 doc
+.bundle
+tmp

data/Gemfile

@@ -5,3 +5,8 @@ group :development do
   gem 'yard'
   gem 'jeweler'
 end
+
+group :test do
+  gem 'aruba'
+  gem 'cucumber'
+end

data/Gemfile.lock

@@ -0,0 +1,41 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    aruba (0.2.4)
+      background_process
+      cucumber (~> 0.9.3)
+    background_process (1.2)
+    builder (2.1.2)
+    cucumber (0.9.3)
+      builder (~> 2.1.2)
+      diff-lcs (~> 1.1.2)
+      gherkin (~> 2.2.9)
+      json (~> 1.4.6)
+      term-ansicolor (~> 1.0.5)
+    diff-lcs (1.1.2)
+    gemcutter (0.6.1)
+    gherkin (2.2.9)
+      json (~> 1.4.6)
+      term-ansicolor (~> 1.0.5)
+    git (1.2.5)
+    jeweler (1.4.0)
+      gemcutter (>= 0.1.0)
+      git (>= 1.2.5)
+      rubyforge (>= 2.0.0)
+    json (1.4.6)
+    json_pure (1.4.6)
+    rubyforge (2.0.4)
+      json_pure (>= 1.1.7)
+    rubypants (0.2.0)
+    term-ansicolor (1.0.5)
+    yard (0.6.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  aruba
+  cucumber
+  jeweler
+  rubypants
+  yard

data/HISTORY.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## 1.0.8
+
+* Allow command-line output to disk via -o option
+* command-line tool reads both files and STDIN, enabling piping of content
+* added filter to replace special characters with HTML entities
+* better tests for the command-line tool with cucumber and aruba
+
 ## 1.0.7
 
 * Improved Ruby 1.9 compatibility
@@ -32,4 +39,4 @@
 
 ## 1.0
 
-* First release
+* First release

data/VERSION

@@ -1 +1 @@
-1.0.7
+1.0.8

data/bin/typogruby

@@ -1,10 +1,12 @@
 #!/usr/bin/env ruby -rubygems
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 require 'typogruby'
 require 'optparse'
 
 operations = [:smartypants, :initial_quotes, :amp, :widont, :caps]
 explicit_on = []
 explicit_off = []
+output_filename = nil
 
 OptionParser.new do |options|
   options.banner = <<-EOS
@@ -19,6 +21,8 @@ Examples:
   typogruby --no-widows FILE  Runs all filters except for widows
   typogruby -w FILE           Runs only the filter for widows
   typogruby --widows FILE     Runs only the filter for widows
+  typogruby -o FILE2 FILE1    Filters FILE1 and saves to FILE2
+  cat FILE | typogruby        Filter input from STDIN
 
 Usage: typogruby [options] filename [filename, ...]
 EOS
@@ -38,6 +42,10 @@ EOS
     (v ? explicit_on : explicit_off) << :amp
   end
 
+  options.on '-n', '--[no-]entities', 'Convert special characters to HTML entities' do |v|
+    (v ? explicit_on : explicit_off) << :entities
+  end
+
   options.on '-w', '--[no-]widows', 'Prevent widows' do |v|
     (v ? explicit_on : explicit_off) << :widont
   end
@@ -46,13 +54,17 @@ EOS
     (v ? explicit_on : explicit_off) << :caps
   end
 
+  options.on '-o', '--output FILENAME', 'Save output to file' do |v|
+    output_filename = v
+  end
+
   options.on_tail '-h', '--help', 'Show this message' do
     $stderr.print options
     exit
   end
 
   options.on_tail '-v', '--version', 'Display version information' do
-    $stderr.print Typogruby.version
+    $stderr.print "Typogruby #{Typogruby.version}"
     exit
   end
   options.parse!
@@ -66,18 +78,34 @@ else
   operations
 end
 
-unless ARGV.any?
-  $stderr.puts 'No file specified'
+begin
+  # Apply every filter to our input text
+  output = operations_todo.inject(ARGF.read) { |t, o| Typogruby.send(o, t) }
+
+# End the program nicely when the user interrupt with ctrl-c
+rescue Interrupt
+  $stderr.puts "Interrupted by user."
+  exit 1
+
+# Inform the user of any errors that have occured
+rescue Exception => e
+  $stderr.puts "Error processing input:"
+  $stderr.puts e.message
   exit 1
 end
 
-output = ARGV.inject('') do |output, filename|
+# Either use the output_filename to save the output to a file on disk,
+# or print it to stdout
+if output_filename
   begin
-    output + operations_todo.inject(File.read(filename)) { |t, o| Typogruby.send(o, t) }
-  rescue
-    $stderr.print "Error processing '#{filename}'"
-    output
+    File.open(output_filename, 'w') do |f|
+      f.print output
+    end
+  rescue Exception => e
+    $stdout.print "A problem occured when trying to write to file #{output_filename}:"
+    $stdout.print e.message
+    exit 1
   end
+else
+  $stdout.print output
 end
-
-$stdout.print output

data/features/ignoring.feature

@@ -0,0 +1,23 @@
+Feature: ignoring parts of a file
+
+    In order to not mess up mixed files
+    As a web developer using typogruby
+    I want to filter just HTML and not Javascript
+
+    Scenario:
+        Given a file named "input.html" with:
+        """
+        <script>
+        document.write("<p>Foo BAR!</p>");
+        </script>
+        <p>"This IS a simple file!</p>
+        """
+        When I run "typogruby input.html"
+        Then the output should contain exactly:
+        """
+        <script>
+        document.write("<p>Foo BAR!</p>");
+        </script>
+        <p><span class="dquo">&#8220;</span>This <span class="caps">IS</span> a simple&nbsp;file!</p>
+        """
+        And the exit status should be 0

data/features/inputs.feature

@@ -0,0 +1,31 @@
+Feature: various inputs
+
+    In order to work quickly
+    As a hasty web developer using typogruby
+    I want to use various input methods
+
+    Background:
+        Given a file named "input.html" with:
+        """
+        <p>"This IS a simple file!</p>
+        """
+        And a file named "input2.html" with:
+        """
+        <p>This is another file</p>
+        """
+
+    Scenario: take input from STDIN
+        When I run "cat input.html | typogruby"
+        Then the output should contain exactly:
+        """
+        <p><span class="dquo">&#8220;</span>This <span class="caps">IS</span> a simple&nbsp;file!</p>
+        """
+        And the exit status should be 0
+
+    Scenario: multiple input files
+        When I run "typogruby input.html input2.html"
+        Then the output should contain exactly:
+        """
+        <p><span class="dquo">&#8220;</span>This <span class="caps">IS</span> a simple&nbsp;file!</p><p>This is another&nbsp;file</p>
+        """
+        And the exit status should be 0

data/features/selective_filtering.feature

@@ -0,0 +1,43 @@
+Feature: selective filtering
+
+    In order to get just the results I like
+    As a picky web developer using typogruby
+    I want to only apply certain filters to a file
+
+    Background:
+        Given a file named "input.html" with:
+        """
+        <p>"This IS a simple file!</p>
+        """
+
+    Scenario: using just one filter
+        When I run "typogruby -w input.html"
+        Then the output should contain exactly:
+        """
+        <p>"This IS a simple&nbsp;file!</p>
+        """
+        And the exit status should be 0
+
+    Scenario: using just several filters
+        When I run "typogruby -cw input.html"
+        Then the output should contain exactly:
+        """
+        <p>"This <span class="caps">IS</span> a simple&nbsp;file!</p>
+        """
+        And the exit status should be 0
+
+    Scenario: excluding a single filter
+        When I run "typogruby --no-widows input.html"
+        Then the output should contain exactly:
+        """
+        <p><span class="dquo">&#8220;</span>This <span class="caps">IS</span> a simple file!</p>
+        """
+        And the exit status should be 0
+
+    Scenario: excluding multiple filters
+        When I run "typogruby --no-widows --no-caps input.html"
+        Then the output should contain exactly:
+        """
+        <p><span class="dquo">&#8220;</span>This IS a simple file!</p>
+        """
+        And the exit status should be 0

data/features/simple.feature

@@ -0,0 +1,38 @@
+Feature: Simple usage
+
+    In order to improve my web file's typography
+    As a web developer using typogruby
+    I want to apply typogruby to a file
+
+    Scenario: getting help
+        When I run "typogruby -h"
+        Then the output should contain "Usage: typogruby [options] filename [filename, ...]"
+        And the exit status should be 0
+
+    Scenario: getting the version number
+        When I run "typogruby -v"
+        Then the output should contain "Typogruby "
+
+    Scenario: filtering a file
+        Given a file named "input.html" with:
+        """
+        <p>"This IS a simple file!</p>
+        """
+        When I run "typogruby input.html"
+        Then the output should contain exactly:
+        """
+        <p><span class="dquo">&#8220;</span>This <span class="caps">IS</span> a simple&nbsp;file!</p>
+        """
+        And the exit status should be 0
+
+    Scenario: Writing output to a file
+        Given a file named "input.html" with:
+        """
+        <p>"This IS a simple file!</p>
+        """
+        When I run "typogruby -o output.html input.html"
+        Then the file "output.html" should contain exactly:
+        """
+        <p><span class="dquo">&#8220;</span>This <span class="caps">IS</span> a simple&nbsp;file!</p>
+        """
+        And the exit status should be 0

data/features/support/env.rb

@@ -0,0 +1,5 @@
+$LOAD_PATH.unshift(File.dirname(__FILE__) + '/../../lib')
+require 'typogruby'
+require 'bundler'
+Bundler.require :default, :test
+

data/lib/characters.txt

@@ -0,0 +1,252 @@
+160 nbsp
+161 iexcl
+162 cent
+163 pound
+164 curren
+165 yen
+166 brvbar
+167 sect
+168 uml
+169 copy
+170 ordf
+171 laquo
+172 not
+173 shy
+174 reg
+175 macr
+176 deg
+177 plusmn
+178 sup2
+179 sup3
+180 acute
+181 micro
+182 para
+183 middot
+184 cedil
+185 sup1
+186 ordm
+187 raquo
+188 frac14
+189 frac12
+190 frac34
+191 iquest
+192 Agrave
+193 Aacute
+194 Acirc
+195 Atilde
+196 Auml
+197 Aring
+198 AElig
+199 Ccedil
+200 Egrave
+201 Eacute
+202 Ecirc
+203 Euml
+204 Igrave
+205 Iacute
+206 Icirc
+207 Iuml
+208 ETH
+209 Ntilde
+210 Ograve
+211 Oacute
+212 Ocirc
+213 Otilde
+214 Ouml
+215 times
+216 Oslash
+217 Ugrave
+218 Uacute
+219 Ucirc
+220 Uuml
+221 Yacute
+222 THORN
+223 szlig
+224 agrave
+225 aacute
+226 acirc
+227 atilde
+228 auml
+229 aring
+230 aelig
+231 ccedil
+232 egrave
+233 eacute
+234 ecirc
+235 euml
+236 igrave
+237 iacute
+238 icirc
+239 iuml
+240 eth
+241 ntilde
+242 ograve
+243 oacute
+244 ocirc
+245 otilde
+246 ouml
+247 divide
+248 oslash
+249 ugrave
+250 uacute
+251 ucirc
+252 uuml
+253 yacute
+254 thorn
+255 yuml
+402 fnof
+913 Alpha
+914 Beta
+915 Gamma
+916 Delta
+917 Epsilon
+918 Zeta
+919 Eta
+920 Theta
+921 Iota
+922 Kappa
+923 Lambda
+924 Mu
+925 Nu
+926 Xi
+927 Omicron
+928 Pi
+929 Rho
+931 Sigma
+932 Tau
+933 Upsilon
+934 Phi
+935 Chi
+936 Psi
+937 Omega
+945 alpha
+946 beta
+947 gamma
+948 delta
+949 epsilon
+950 zeta
+951 eta
+952 theta
+953 iota
+954 kappa
+955 lambda
+956 mu
+957 nu
+958 xi
+959 omicron
+960 pi
+961 rho
+962 sigmaf
+963 sigma
+964 tau
+965 upsilon
+966 phi
+967 chi
+968 psi
+969 omega
+977 thetasym
+978 upsih
+982 piv
+8226    bull
+8230    hellip
+8242    prime
+8243    Prime
+8254    oline
+8260    frasl
+8472    weierp
+8465    image
+8476    real
+8482    trade
+8501    alefsym
+8592    larr
+8593    uarr
+8594    rarr
+8595    darr
+8596    harr
+8629    crarr
+8656    lArr
+8657    uArr
+8658    rArr
+8659    dArr
+8660    hArr
+8704    forall
+8706    part
+8707    exist
+8709    empty
+8711    nabla
+8712    isin
+8713    notin
+8715    ni
+8719    prod
+8721    sum
+8722    minus
+8727    lowast
+8730    radic
+8733    prop
+8734    infin
+8736    ang
+8743    and
+8744    or
+8745    cap
+8746    cup
+8747    int
+8756    there4
+8764    sim
+8773    cong
+8776    asymp
+8800    ne
+8801    equiv
+8804    le
+8805    ge
+8834    sub
+8835    sup
+8836    nsub
+8838    sube
+8839    supe
+8853    oplus
+8855    otimes
+8869    perp
+8901    sdot
+8968    lceil
+8969    rceil
+8970    lfloor
+8971    rfloor
+9001    lang
+9002    rang
+9674    loz
+9824    spades
+9827    clubs
+9829    hearts
+9830    diams
+34  quot
+38  amp
+60  lt
+62  gt
+338 OElig
+339 oelig
+352 Scaron
+353 scaron
+376 Yuml
+710 circ
+732 tilde
+8194    ensp
+8195    emsp
+8201    thinsp
+8204    zwnj
+8205    zwj
+8206    lrm
+8207    rlm
+8211    ndash
+8212    mdash
+8216    lsquo
+8217    rsquo
+8218    sbquo
+8220    ldquo
+8221    rdquo
+8222    bdquo
+8224    dagger
+8225    Dagger
+8240    permil
+8249    lsaquo
+8250    rsaquo
+8364    euro

data/lib/typogruby.rb

@@ -1,5 +1,6 @@
 require 'rubypants'
 require 'digest/md5'
+$KCODE = 'U'
 
 # A collection of simple helpers for improving web
 # typograhy. Based on TypographyHelper by Luke Hartman and Typogrify.
@@ -187,6 +188,34 @@ module Typogruby
     end
   end
 
+  # Converts special characters (excluding HTML tags) to HTML entities.
+  #
+  # @example
+  # entities("Aloë Vera") # => "Aloë Vera"
+  #
+  # @param [String] text input text
+  # @return [String] input text with all special characters converted to
+  #   HTML entities.
+  def entities(text)
+    o = ''
+    text.scan(/(?x)
+
+        ( <\?(?:[^?]*|\?(?!>))*\?>
+        | <!-- (?m:.*?) -->
+        | <\/? (?i:a|abbr|acronym|address|applet|area|b|base|basefont|bdo|big|blockquote|body|br|button|caption|center|cite|code|col|colgroup|dd|del|dfn|dir|div|dl|dt|em|fieldset|font|form|frame|frameset|h1|h2|h3|h4|h5|h6|head|hr|html|i|iframe|img|input|ins|isindex|kbd|label|legend|li|link|map|menu|meta|noframes|noscript|object|ol|optgroup|option|p|param|pre|q|s|samp|script|select|small|span|strike|strong|style|sub|sup|table|tbody|td|textarea|tfoot|th|thead|title|tr|tt|u|ul|var)\b
+            (?:[^>"']|"[^"]*"|'[^']*')*
+          >
+        | &(?:[a-zA-Z0-9]+|\#[0-9]+|\#x[0-9a-fA-F]+);
+        )
+        |([^<&]+|[<&])
+
+      /x) do |tag, text|
+      o << tag.to_s
+      o << encode(text.to_s)
+    end
+    o
+  end
+
   # main function to do all the functions from the method.
   # @param [String] text input text
   # @return [String] input text with all filters applied
@@ -196,6 +225,26 @@ module Typogruby
 
 private
 
+  # Convert characters from the map in ./lib/characters.txt
+  # Code taken from TextMate HTML bundle
+  # @param [String] text input text
+  # @return [String] input text with all special characters converted to
+  #   HTML entities.
+  def encode(text)
+    @char_to_entity ||= begin
+      map = {}
+      File.read(File.join(File.dirname(__FILE__), 'characters.txt')).scan(/^(\d+)\s*(.+)$/) do |key, value|
+        map[[key.to_i].pack('U')] = value
+      end
+      map
+    end
+
+    text.gsub(/[^\x00-\x7F]|["'<>&]/) do |ch|
+      ent = @char_to_entity[ch]
+      ent ? "&#{ent};" : sprintf("&#x%02X;", ch.unpack("U")[0])
+    end
+  end
+
   # Hackish text filter that will make sure our text filters leave inline
   # javascript alone without resorting to a full-blown HTML parser.
   #
@@ -216,4 +265,4 @@ private
   end
 
   extend self
-end
+end

data/test/test_typogruby.rb

@@ -91,4 +91,9 @@ class TestTypogruby < Test::Unit::TestCase
     assert_equal "<script>\nreturn window;\n</script>", widont("<script>\nreturn window;\n</script>")
     assert_equal '<div><p>But divs with paragraphs&nbsp;do!</p></div>', widont('<div><p>But divs with paragraphs do!</p></div>')
   end
-end
+
+  def test_should_convert_entities
+    assert_equal "Vari&euml;ren&hellip;", entities('Variëren…')
+    assert_equal "<p>Ol&eacute;</p>", entities('<p>Olé</p>')
+  end
+end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: typogruby
 version: !ruby/object:Gem::Version 
-  hash: 25
+  hash: 7
   prerelease: false
   segments: 
   - 1
   - 0
-  - 7
-  version: 1.0.7
+  - 8
+  version: 1.0.8
 platform: ruby
 authors: 
 - Arjan van der Gaag
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-08-23 00:00:00 +02:00
+date: 2010-11-06 00:00:00 +01:00
 default_executable: typogruby
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -73,12 +73,19 @@ files:
 - .document
 - .gitignore
 - Gemfile
+- Gemfile.lock
 - HISTORY.md
 - LICENSE
 - README.md
 - Rakefile
 - VERSION
 - bin/typogruby
+- features/ignoring.feature
+- features/inputs.feature
+- features/selective_filtering.feature
+- features/simple.feature
+- features/support/env.rb
+- lib/characters.txt
 - lib/typogruby.rb
 - test/test_typogruby.rb
 - typogrify.gemspec