filtri 0.0.1 → 0.1.0

data/README.md

@@ -11,8 +11,6 @@ Filtri is a tiny DSL for text substitution.
 
 Define a set of substitution rules using `rule` and apply to an input string:
 
-    in_str = "foobazbarfoo"
-    expected = "barbugbarbar"
 
     f = filtri do
       rule /fo+/ => "bar"
@@ -36,8 +34,69 @@ Load with `Filtri::load`:
     Filtri.load("foo.rules").apply("foobarfoobar")
     => "**b**!!a!!z**b**!!a!!g**b**!!a!!z**b**!!a!!g"
 
+## Command line tool
+
+A command line tool is included in this gem, `filtri`
+
+### Usage
+
+    Usage: filtri [options] [input]
+
+    Options:
+        -r, --rule STRING                Single rule
+        -f, --file RULE_FILE             File containing rules
+        -v, --version                    Version information
+        -h, --help                       Help
+
+
+### Examples
+
+An example applying rules from the files `f1.rule` and `f2.rule` to the input files `input1` and `input2`
+
+File `f1.rules`:
+
+    rule /(foo+)/ => 'THIS WAS \1'
+    rule /(ba+r)/ => 'THIS WAS \1'
+
+File `f1.rules`:
+
+    rule /(ba+z)/ => 'THIS WAS \1'
+    rule /bag/ => 'THIS WAS BAG'
+
+File `input1`:
+
+    foooo
+    baaaaaaaaaaaaaaaaz
+    bag
+
+File `input2`:
+
+    and baaaaaaaaaaar
+
+Running `filtri` as
+
+    $ filtri -f f1.rules -f f2.rules input1 input2 > result.txt
+
+..gives `result.txt`:
+
+    THIS WAS foooo
+    THIS WAS baaaaaaaaaaaaaaaaz
+    THIS WAS BAG
+    and THIS WAS baaaaaaaaaaar
+
+Single rules can be provided using the option `-r`:
+
+    $ echo "foo" | filtri -r '"foo" => "bar"'
+    bar
+
+
+## Syntax highlighting
+
+Definitions for syntax highlighting of `.rule` files in Sublime Text 2 and TextMate is available (`resource/filtri_rules.tmLanguage`)
+
 ## Version information
 
+* 0.1.0 - Added filtri tool and syntax highlighting
 * 0.0.1 - Initial version
 
 ## License

data/bin/filtri

@@ -0,0 +1,24 @@
+#!/usr/bin/env ruby
+
+require 'pp'
+require_relative '../lib/filtri/command'
+
+begin
+
+  debug = true
+
+  opts = FiltriCmd.parse_opts
+
+  unless FiltriCmd.validate_opts(opts)
+    exit 1
+  end
+  result = FiltriCmd.run(opts, opts[:input])
+  puts result
+rescue SystemExit => sys_exit
+  exit sys_exit.status
+rescue Exception => ex
+
+  puts "[Error] #{ex.message}"
+  puts " -----> #{ex.backtrace.join("\n        ")}" if debug
+
+end

data/filtri.gemspec

@@ -9,12 +9,14 @@ Gem::Specification.new do |spec|
   spec.version       = Filtri::VERSION
   spec.authors       = ["karl l"]
   spec.email         = ["karl@ninjacontrol.com"]
-  spec.date          = '2013-04-01'
-  spec.summary       = "A tiny DSL for filtering strings"
-  spec.description   = "Filtri is a little DSL that simplifies the work of applying multiple substitution rules to a string."
+  spec.date          = '2013-04-07'
+  spec.summary       = "A tiny tool for text substitution"
+  spec.description   = "Filtri is a tool that simplifies the work of applying multiple substitution rules to a string."
   spec.homepage      = "https://github.com/karlll/filtri/"
   spec.license       = "MIT"
-  
+
+  spec.required_ruby_version = '>= 1.9.3'
+
   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)/})
@@ -22,9 +24,9 @@ Gem::Specification.new do |spec|
   
   spec.add_development_dependency "bundler", "~> 1.3"
   spec.add_development_dependency "rake"
-  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "rspec", ">= 2.11"
   spec.add_runtime_dependency "docile"
-  spec.add_runtime_dependency "str2hash"
+  spec.add_runtime_dependency "str2hash", ">= 0.1.0"
   spec.add_runtime_dependency "to_regexp"
  
   end

data/lib/filtri/command.rb

@@ -0,0 +1,108 @@
+require 'optparse'
+require_relative 'version'
+require_relative '../filtri'
+
+class FiltriCmd
+  def self.parse_opts
+    options = {}
+
+    OptionParser.new do |o|
+      o.banner = "Usage: filtri [options] [input]"
+      o.separator ""
+      o.separator "Options:"
+
+      o.on("-r", "--rule STRING", "Single rule") do |rule|
+        if options.include?(:rules)
+          options[:rules] << rule
+        else
+          options[:rules] = [rule]
+        end
+      end
+
+      o.on("-f", "--file RULE_FILE", "File containing rules") do |rule_files|
+        if options.include?(:rule_files)
+          options[:rule_files] << rule_files
+        else
+          options[:rule_files] = [rule_files]
+        end
+      end
+
+      o.on( '-v', '--version', 'Version information' ) do
+        puts "version #{Filtri::VERSION}"
+        exit
+      end
+
+      o.on( '-h', '--help', 'Help' ) do
+        puts o
+        exit
+      end
+
+
+
+    end.parse!
+
+    options[:input] = ARGV unless ARGV.length <= 0
+    options
+
+  end
+
+  def self.validate_opts(opts)
+
+
+    unless opts.include?(:rules) || opts.include?(:rule_files)
+      puts "Error: provide a rule or a rule file."
+      return false
+    end
+
+    [:rule_files, :input].each do |f|
+      if opts.include?(f)
+        opts[f].each do |i|
+          unless File.exist?(i)
+            puts "Error: file #{i} does not exist."
+            return false
+          end
+        end
+      end
+    end
+
+    true
+
+  end
+
+  # Apply rules to the provided input
+  #
+  # @param [Hash{Symbol => Array<String>}] rules Where :rules contain single rule strings and :rule_files contain filename(s) of the rule file(s)
+  # @param [Array<String>] input Where :input contain the input file(s)
+  # @return [String] The rules applied to the input
+  # @raise [FiltriInitError, IOError] if an error occurs when initialising the rules from the provided strings or files
+  def self.run(rules, input)
+    rule_strs  = rules[:rules] || []
+    rule_files = rules[:rule_files] || []
+    result = []
+
+
+    # Allow for shorthand format of rules
+
+    upd_rule_strs = rule_strs.reduce([]) do |r,v|
+      if v =~ /^(#{Filtri.valid_rules.join("|")})/
+        r << v
+      else
+        r << "rule #{v}"
+      end
+    end
+    f = Filtri.new
+    if upd_rule_strs.length > 0
+      f.add_rule_str(upd_rule_strs.join("\n"))
+    end
+
+    rule_files.each do |rf|
+      f.load rf
+    end
+
+    ARGV.replace(input || [])
+    result << f.apply(ARGF.read)
+
+    result.join("")
+  end
+
+end

data/lib/filtri/version.rb

@@ -1,6 +1,6 @@
 class Filtri
 
   # Filtri version (semantic versioning)
-  VERSION = "0.0.1"
+  VERSION = "0.1.0"
 
 end

data/lib/filtri.rb

@@ -21,6 +21,7 @@ class Filtri
     @rules      = []
     @meta_rules = []
     @passes     = 1
+    @meta_applied = false
   end
 
   # Add a filtering rule
@@ -92,7 +93,10 @@ class Filtri
     @passes.times do
 
       unless @meta_rules.empty?
-        @rules = rewrite(@rules, @meta_rules)
+        unless @meta_applied
+          @rules = rewrite(@rules, @meta_rules)
+          @meta_applied = true
+        end
       end
 
       @rules.each do |rule|
@@ -103,8 +107,6 @@ class Filtri
     in_str
   end
 
-  # Factory, init with rule-set from a string
-  #
   # The input string is expected to contain rules and comments, one per line,
   # separated by a line break.
   # The expected format of a line is "{operation} <space> {argument} <eol>".
@@ -112,11 +114,8 @@ class Filtri
   # is trimmed.
   #
   # @param [String] rule_str
-  # @return [Filtri] A new Filtri object with the rules parsed from the provided string(s).
   # @raise [FiltriInitError] if an error occurs when initialising the rules from the provided strings
-  def self.from_str(rule_str)
-
-    inst = Filtri.new
+  def add_rule_str(rule_str)
 
     rule_str.strip.lines do |l|
 
@@ -133,7 +132,7 @@ class Filtri
             raise FiltriInitError, "Invalid rule format: '#{op_arg}' (#{err.message})"
           end
           # add rule
-          inst.send(op.to_sym,arg_hash)
+          self.send(op.to_sym,arg_hash)
         else
           raise FiltriInitError, "Unknown rule: #{op}" unless op == "#"
         end
@@ -141,12 +140,42 @@ class Filtri
       end
     end
 
+
+  end
+
+
+  # Factory, init with rule-set from a string
+  #
+  # The input string is expected to contain rules and comments, one per line,
+  # separated by a line break.
+  # The expected format of a line is '{operation} <space> {argument} <eol>'.
+  # Empty lines and lines starting with a '#' are ignored. Whitespace at the beginning of a line
+  # is trimmed.
+  #
+  # @param [String] rule_str
+  # @return [Filtri] A new Filtri object with the rules parsed from the provided string(s).
+  # @raise [FiltriInitError] if an error occurs when initialising the rules from the provided strings
+  def self.from_str(rule_str)
+
+    inst = Filtri.new
+    inst.add_rule_str rule_str
     inst
 
   end
 
   # Load rules from a file
   # @param [String] file_name
+  # @raise [IOError,SystemCallError] If an error occurs when opening the file
+  # @raise [FiltriInitError] If an error occurs when parsing the rules in the file
+  def load(file_name)
+
+    data = IO.read(file_name)
+    add_rule_str(data)
+
+  end
+
+  # Factory, Init by loading rules from a file
+  # @param [String] file_name
   # @return [Filtri] A new Filtri object with the rules contained in the file
   # @raise [IOError,SystemCallError] If an error occurs when opening the file
   # @raise [FiltriInitError] If an error occurs when parsing the rules in the file
@@ -158,6 +187,10 @@ class Filtri
   end
 
 
+  def self.valid_rules
+    Filtri::RULES
+  end
+
 end
 
 class FiltriInitError < StandardError
@@ -180,4 +213,5 @@ end
 # @return [Filtri] A new Filtri object containing the provided rules
 def filtri(&block)
   Docile.dsl_eval(Filtri.new, &block)
-end
+end
+

data/resource/filtri_rules.tmLanguage

@@ -0,0 +1,75 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>fileTypes</key>
+	<array>
+		<string>rules</string>
+	</array>
+	<key>name</key>
+	<string>Filtri rules</string>
+	<key>patterns</key>
+	<array>
+		<dict>
+			<key>comment</key>
+			<string>A comment</string>
+			<key>match</key>
+			<string>^\s*(#.*)$</string>
+			<key>name</key>
+			<string>comment.line.numer-sign.rules</string>
+		</dict>
+		<dict>
+			<key>comment</key>
+			<string>A rule</string>
+			<key>match</key>
+			<string>^\s*rule</string>
+			<key>name</key>
+			<string>support.function.rules</string>
+		</dict>
+		<dict>
+			<key>comment</key>
+			<string>A meta rule</string>
+			<key>match</key>
+			<string>^\s*meta</string>
+			<key>name</key>
+			<string>support.function.rules</string>
+		</dict>
+		<dict>
+			<key>comment</key>
+			<string>A string</string>
+			<key>match</key>
+			<string>"([^"]*)"</string>
+			<key>name</key>
+			<string>string.quoted.double.rules</string>
+		</dict>
+		<dict>
+			<key>comment</key>
+			<string>A string</string>
+			<key>match</key>
+			<string>'([^']*)'</string>
+			<key>name</key>
+			<string>string.quoted.single.rules</string>
+		</dict>
+		<dict>
+			<key>comment</key>
+			<string>A regular expression</string>
+			<key>match</key>
+			<string>/([^']*)/</string>
+			<key>name</key>
+			<string>string.regexp.rules</string>
+		</dict>
+		<dict>
+			<key>comment</key>
+			<string>A mapping</string>
+			<key>match</key>
+			<string>=&gt;</string>
+			<key>name</key>
+			<string>keyword.operator.rules</string>
+		</dict>
+	</array>
+	<key>scopeName</key>
+	<string>text.rules</string>
+	<key>uuid</key>
+	<string>7d1b615b-cfb6-41e1-83e1-6ff8508e0133</string>
+</dict>
+</plist>

data/spec/command_spec.rb

@@ -0,0 +1,127 @@
+require 'rspec'
+require 'filtri/command'
+
+describe FiltriCmd do
+
+  describe "#parse_opts" do
+
+    it 'parses multiple rules' do
+
+      stub_const("ARGV",["-r", "{:foo => 'bar'}", "--rule", "{:foo2 => 'bar2'}"])
+      out_opts = FiltriCmd.parse_opts
+      out_opts.should eq({:rules=>["{:foo => 'bar'}", "{:foo2 => 'bar2'}"]})
+
+    end
+
+    it 'parses multiple rule files' do
+
+      stub_const("ARGV",["-f", "file1", "--file", "file2"])
+      out_opts = FiltriCmd.parse_opts
+      out_opts.should eq({:rule_files=>["file1", "file2"]})
+
+    end
+
+    it 'parses multiple input files' do
+
+      stub_const("ARGV",["-f", "file1", "input1", "input2"])
+      out_opts = FiltriCmd.parse_opts
+      out_opts.should eq({:rule_files=>["file1"], :input=> ["input1", "input2"]})
+
+
+    end
+
+  end
+
+  describe "#validate_opts" do
+
+    it 'requires a rule or a rule file' do
+
+      stub_const("ARGV",["-f", "file1", "input1", "input2"])
+      out_opts = FiltriCmd.parse_opts
+      File.stub!(:exist?).and_return true
+      FiltriCmd.validate_opts(out_opts).should be_true
+
+      stub_const("ARGV",["--rule", "{:foo => 'bar'}", "input2"])
+      out_opts = FiltriCmd.parse_opts
+      FiltriCmd.validate_opts(out_opts).should be_true
+
+      stub_const("ARGV",["input1", "input2"])
+      out_opts = FiltriCmd.parse_opts
+      $stdout.should_receive(:puts).with(/Error/i)
+      FiltriCmd.validate_opts(out_opts).should be_false
+
+    end
+
+    it 'checks if files exist' do
+
+      stub_const("ARGV",["-f", "existing_file", "input_file1", "input_file2"])
+      out_opts = FiltriCmd.parse_opts
+      File.stub!(:exist?).with("existing_file").and_return true
+      File.stub!(:exist?).with("input_file1").and_return true
+      File.stub!(:exist?).with("input_file2").and_return true
+      FiltriCmd.validate_opts(out_opts).should be_true
+
+      stub_const("ARGV",["-f", "existing_file", "input_file1", "bad_input_file2"])
+      out_opts = FiltriCmd.parse_opts
+      File.stub!(:exist?).with("existing_file").and_return true
+      File.stub!(:exist?).with("input_file1").and_return true
+      File.stub!(:exist?).with("bad_input_file2").and_return false
+      $stdout.should_receive(:puts).with(/Error/i)
+      FiltriCmd.validate_opts(out_opts).should be_false
+
+    end
+
+
+  end
+
+  describe "#run" do
+
+    let(:rules) { %q(
+
+      # this is a comment
+      rule /fo+bar/ => "bazbag"
+      rule /go+blin/ => "NILBOG"
+
+    ) }
+
+    let(:input1) { %q(
+
+      fooooooooooooooobar
+      cookie
+      goooooblin
+
+    ) }
+
+    let(:result1) { %q(
+
+      bazbag
+      cookie
+      NILBOG
+
+    ) }
+
+
+
+    it 'reads rules from a file and applies to input file' do
+      opts = {:rule_files=>["rule_file"], :input=> ["input_file"]}
+
+      IO.stub(:read).with("rule_file").and_return rules
+      ARGF.stub!(:read).and_return input1
+
+      result = FiltriCmd.run(opts, opts[:input])
+      result.should eq(result1)
+    end
+
+    it 'reads single rules applies to input file' do
+      opts = {:rules=>['rule /fo+bar/ => "bazbag"','rule /go+blin/ => "NILBOG"'], :input=> ["input_file"]}
+
+      ARGF.stub!(:read).and_return input1
+
+      result = FiltriCmd.run(opts, opts[:input])
+      result.should eq(result1)
+    end
+
+  end
+
+
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: filtri
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-01 00:00:00.000000000 Z
+date: 2013-04-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -50,7 +50,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.11'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -58,7 +58,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.11'
 - !ruby/object:Gem::Dependency
   name: docile
   requirement: !ruby/object:Gem::Requirement
@@ -82,7 +82,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.1.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -90,7 +90,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.1.0
 - !ruby/object:Gem::Dependency
   name: to_regexp
   requirement: !ruby/object:Gem::Requirement
@@ -107,11 +107,12 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: Filtri is a little DSL that simplifies the work of applying multiple
-  substitution rules to a string.
+description: Filtri is a tool that simplifies the work of applying multiple substitution
+  rules to a string.
 email:
 - karl@ninjacontrol.com
-executables: []
+executables:
+- filtri
 extensions: []
 extra_rdoc_files: []
 files:
@@ -120,9 +121,13 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- bin/filtri
 - filtri.gemspec
 - lib/filtri.rb
+- lib/filtri/command.rb
 - lib/filtri/version.rb
+- resource/filtri_rules.tmLanguage
+- spec/command_spec.rb
 - spec/filtri_spec.rb
 homepage: https://github.com/karlll/filtri/
 licenses:
@@ -136,10 +141,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
-      version: '0'
-      segments:
-      - 0
-      hash: 1607576313604211744
+      version: 1.9.3
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -148,12 +150,13 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 1607576313604211744
+      hash: 107123931516266263
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
-summary: A tiny DSL for filtering strings
+summary: A tiny tool for text substitution
 test_files:
+- spec/command_spec.rb
 - spec/filtri_spec.rb