nginx_config_parser 1.0.0

data/History.txt

@@ -0,0 +1,3 @@
+== 1.0.0 / 2008-01-21
+
+* Initial release.

data/Manifest.txt

@@ -0,0 +1,20 @@
+History.txt
+Manifest.txt
+README.txt
+Rakefile
+lib/nginx_config_parser.rb
+lib/nginx_config_parser/configuration.rb
+lib/nginx_config_parser/scanner.rb
+src/scanner.rl
+tasks/annotations.rake
+tasks/doc.rake
+tasks/gem.rake
+tasks/manifest.rake
+tasks/ragel.rake
+tasks/rubyforge.rake
+tasks/setup.rb
+tasks/spec.rake
+tasks/test.rake
+test/fixtures/ezra/conf/nginx.conf
+test/fixtures/simple/conf/nginx.conf
+test/parser_test.rb

data/README.txt

@@ -0,0 +1,73 @@
+nginx_config_parser
+    by Bruce Williams
+    
+== DESCRIPTION:
+  
+A simple Nginx Configuration parser that generates an object graph for
+traversal and can emit tidied [simple] configurations.
+
+== FEATURES/PROBLEMS:
+  
+* Currently ignores `if' statements (focused on only parsing static config)
+
+== SYNOPSIS:
+
+With a file like:
+
+  user nobody www; # this is a 'setting' with key 'user'
+  workers 1;
+
+  http { # this is a 'section' with name 'http'
+    server {
+      location / { # this is a section with value = ['/']
+        
+      }
+    }
+  }
+  
+Parse
+
+  config = NginxConfigParser.parse(File.read('/path/to/nginx.conf'))
+  p config.settings
+  # => {'user' => ['nobody', 'www'], 'workers' => 1}
+  config.each do |section|
+    p section.name # eg: 'http'
+    section.each do |subsection|
+      p section.name # eg: server
+  # Emit config (`if's and comments are stripped)
+  puts config
+
+== REQUIREMENTS:
+
+* Pure Ruby parser, no compiler needed
+* No dependencies outside Ruby's standard library
+* Should work with Ruby 1.8 and 1.9
+
+== INSTALL:
+
+* sudo gem install nginx_config_parser
+
+== LICENSE:
+
+(The MIT License)
+
+Copyright (c) 2008 Bruce Williams
+
+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/Rakefile

@@ -0,0 +1,21 @@
+# Look in the tasks/setup.rb file for the various options that can be
+# configured in this Rakefile. The .rake files in the tasks directory
+# are where the options are used.
+
+load 'tasks/setup.rb'
+
+ensure_in_path 'lib'
+require 'nginx_config_parser'
+
+task :default => :test
+
+PROJ.name = 'nginx_config_parser'
+PROJ.summary = 'A simple nginx.conf parser and emitter'
+PROJ.authors = 'Bruce Williams'
+PROJ.email = 'bruce@codefluency.com'
+PROJ.url = 'http://codefluency.rubyforge.org/nginx_config_parser'
+PROJ.description = paragraphs_of('README.txt', 1).join("\n\n")
+PROJ.changes = paragraphs_of('History.txt', 0..1).join("\n\n")
+PROJ.rubyforge_name = 'codefluency'
+PROJ.exclude << '\.git$'
+PROJ.exclude << '\._[^\/]*$'

data/lib/nginx_config_parser.rb

@@ -0,0 +1,62 @@
+# $Id$
+
+# Equivalent to a header guard in C/C++
+# Used to prevent the class/module from being loaded more than once
+unless defined? NginxConfigParser
+
+module NginxConfigParser
+
+  # :stopdoc:
+  VERSION = '1.0.0'
+  LIBPATH = ::File.expand_path(::File.dirname(__FILE__)) + ::File::SEPARATOR
+  PATH = ::File.dirname(LIBPATH) + ::File::SEPARATOR
+  # :startdoc:
+
+  # Returns the version string for the library.
+  #
+  def self.version
+    VERSION
+  end
+
+  # Returns the library path for the module. If any arguments are given,
+  # they will be joined to the end of the libray path using
+  # <tt>File.join</tt>.
+  #
+  def self.libpath( *args )
+    args.empty? ? LIBPATH : ::File.join(LIBPATH, *args)
+  end
+
+  # Returns the lpath for the module. If any arguments are given,
+  # they will be joined to the end of the path using
+  # <tt>File.join</tt>.
+  #
+  def self.path( *args )
+    args.empty? ? PATH : ::File.join(PATH, *args)
+  end
+
+  # Utility method used to rquire all files ending in .rb that lie in the
+  # directory below this file that has the same name as the filename passed
+  # in. Optionally, a specific _directory_ name can be passed in such that
+  # the _filename_ does not have to be equivalent to the directory.
+  #
+  def self.require_all_libs_relative_to( fname, dir = nil )
+    dir ||= ::File.basename(fname, '.*')
+    search_me = ::File.expand_path(
+        ::File.join(::File.dirname(fname), dir, '**', '*.rb'))
+
+    Dir.glob(search_me).sort.each {|rb| require rb}
+  end
+  
+  # Parse configuration
+  # * Returns an instance of NginxConfigParser::Configuration
+  def self.parse(input)
+    NginxConfigParser::Scanner.parse(input)
+  end
+
+end  # module NginxConfigParser
+
+NginxConfigParser.require_all_libs_relative_to __FILE__
+
+end  # unless defined?
+
+# EOF

data/lib/nginx_config_parser/configuration.rb

@@ -0,0 +1,68 @@
+module NginxConfigParser
+    
+  class Configuration
+    
+    include Enumerable
+    
+    attr_reader :settings
+    def initialize(level=0)
+      @level = level
+      @settings = {}
+    end
+    
+    # Add a setting
+    def []=(key, value)
+      @settings[key] = value
+    end
+    
+    # An array of child sections
+    def sections
+      @sections ||= []
+    end
+    
+    # Add a child section
+    def section(name, value)
+      section = Section.new(@level + 1, name, value)
+      sections << section
+      section
+    end
+    
+    def each(&block)
+      sections.each(&block)
+    end
+    
+    def to_s #:nodoc:
+      lines = @settings.map do |key, value|
+        ('  ' * @level) << [key, Array(value)].flatten.compact.join(' ') << ';'
+      end
+      lines.push(*sections.map { |section| section.to_s})
+      lines.join("\n")
+    end
+        
+  end
+  
+  
+  # A Section of settings
+  class Section < Configuration
+
+    attr_reader :name, :value
+    def initialize(level, name, value=nil)
+      @name = name
+      @value = value
+      super(level)
+    end
+    
+    def to_s #:nodoc:
+      lines = []
+      lines << (('  ' * (@level - 1)) << [@name, Array(@value)].flatten.compact.map { |v| v.to_s }.join(' ') << ' {')
+      @settings.each do |key, value|
+        lines << (('  ' * @level) << [key, Array(value)].flatten.join(' ') << ';')
+      end
+      lines.push(*sections.map { |section| section.to_s})
+      lines << (('  ' * (@level - 1)) << '}')
+      lines.join("\n")
+    end
+    
+  end
+  
+end

data/lib/nginx_config_parser/scanner.rb

@@ -0,0 +1,510 @@
+# line 1 "src/scanner.rl"
+module NginxConfigParser
+
+  module Scanner
+
+	  class ConfigurationError < ::SyntaxError; end
+
+    class << self
+
+      # line 55 "src/scanner.rl"
+
+
+
+      def parse(data)
+        # Stuff for Ragel
+        data = data.unpack("c*") if data.is_a?(String)
+        eof, stack = 0, []
+        # The list of words to fill for identifiers and values
+        words = []
+        # The stack of contexts, used to accumulate data at
+        # the appropriate level
+        contexts = [Configuration.new]
+        
+# line 25 "src/scanner.rb"
+class << self
+	attr_accessor :_nginx_actions
+	private :_nginx_actions, :_nginx_actions=
+end
+self._nginx_actions = [
+	0, 1, 0, 1, 1, 1, 2, 1, 
+	3, 1, 4, 1, 5, 1, 6, 1, 
+	7, 1, 8, 1, 9, 1, 10, 1, 
+	11, 1, 12, 1, 13, 1, 14, 1, 
+	15
+]
+
+class << self
+	attr_accessor :_nginx_key_offsets
+	private :_nginx_key_offsets, :_nginx_key_offsets=
+end
+self._nginx_key_offsets = [
+	0, 1, 5, 6, 11, 12, 13, 18, 
+	21, 22, 23, 30, 35, 39, 42, 48
+]
+
+class << self
+	attr_accessor :_nginx_trans_keys
+	private :_nginx_trans_keys, :_nginx_trans_keys=
+end
+self._nginx_trans_keys = [
+	10, 32, 40, 9, 13, 41, 32, 41, 
+	123, 9, 13, 125, 10, 32, 35, 105, 
+	9, 13, 32, 9, 13, 10, 102, 32, 
+	35, 59, 123, 125, 9, 13, 32, 59, 
+	123, 9, 13, 32, 125, 9, 13, 32, 
+	9, 13, 10, 32, 59, 123, 9, 13, 
+	32, 59, 123, 9, 13, 0
+]
+
+class << self
+	attr_accessor :_nginx_single_lengths
+	private :_nginx_single_lengths, :_nginx_single_lengths=
+end
+self._nginx_single_lengths = [
+	1, 2, 1, 3, 1, 1, 3, 1, 
+	1, 1, 5, 3, 2, 1, 4, 3
+]
+
+class << self
+	attr_accessor :_nginx_range_lengths
+	private :_nginx_range_lengths, :_nginx_range_lengths=
+end
+self._nginx_range_lengths = [
+	0, 1, 0, 1, 0, 0, 1, 1, 
+	0, 0, 1, 1, 1, 1, 1, 1
+]
+
+class << self
+	attr_accessor :_nginx_index_offsets
+	private :_nginx_index_offsets, :_nginx_index_offsets=
+end
+self._nginx_index_offsets = [
+	0, 2, 6, 8, 13, 15, 17, 22, 
+	25, 27, 29, 36, 41, 45, 48, 54
+]
+
+class << self
+	attr_accessor :_nginx_indicies
+	private :_nginx_indicies, :_nginx_indicies=
+end
+self._nginx_indicies = [
+	2, 1, 3, 4, 3, 0, 5, 4, 
+	5, 5, 6, 5, 4, 7, 6, 10, 
+	9, 12, 13, 14, 12, 11, 12, 12, 
+	15, 2, 1, 3, 16, 18, 19, 20, 
+	21, 22, 18, 17, 23, 23, 23, 23, 
+	17, 18, 25, 18, 24, 25, 25, 26, 
+	10, 9, 9, 9, 9, 19, 25, 23, 
+	23, 25, 17, 0
+]
+
+class << self
+	attr_accessor :_nginx_trans_targs_wi
+	private :_nginx_trans_targs_wi, :_nginx_trans_targs_wi=
+end
+self._nginx_trans_targs_wi = [
+	6, 0, 6, 1, 2, 3, 4, 6, 
+	10, 5, 10, 6, 7, 8, 9, 6, 
+	6, 11, 12, 14, 10, 10, 15, 10, 
+	10, 13, 10
+]
+
+class << self
+	attr_accessor :_nginx_trans_actions_wi
+	private :_nginx_trans_actions_wi, :_nginx_trans_actions_wi=
+end
+self._nginx_trans_actions_wi = [
+	31, 0, 25, 0, 0, 0, 0, 21, 
+	19, 0, 11, 23, 0, 5, 5, 29, 
+	27, 0, 0, 5, 7, 9, 0, 13, 
+	17, 0, 15
+]
+
+class << self
+	attr_accessor :_nginx_to_state_actions
+	private :_nginx_to_state_actions, :_nginx_to_state_actions=
+end
+self._nginx_to_state_actions = [
+	0, 0, 0, 0, 0, 0, 1, 0, 
+	0, 0, 1, 0, 0, 0, 0, 0
+]
+
+class << self
+	attr_accessor :_nginx_from_state_actions
+	private :_nginx_from_state_actions, :_nginx_from_state_actions=
+end
+self._nginx_from_state_actions = [
+	0, 0, 0, 0, 0, 0, 3, 0, 
+	0, 0, 3, 0, 0, 0, 0, 0
+]
+
+class << self
+	attr_accessor :_nginx_eof_trans
+	private :_nginx_eof_trans, :_nginx_eof_trans=
+end
+self._nginx_eof_trans = [
+	1, 1, 1, 1, 1, 9, 0, 16, 
+	17, 17, 0, 24, 25, 27, 24, 24
+]
+
+class << self
+	attr_accessor :nginx_start
+end
+self.nginx_start = 6;
+class << self
+	attr_accessor :nginx_first_final
+end
+self.nginx_first_final = 6;
+class << self
+	attr_accessor :nginx_error
+end
+self.nginx_error = -1;
+
+class << self
+	attr_accessor :nginx_en_statement
+end
+self.nginx_en_statement = 10;
+class << self
+	attr_accessor :nginx_en_main
+end
+self.nginx_en_main = 6;
+
+# line 68 "src/scanner.rl"
+        
+# line 176 "src/scanner.rb"
+begin
+	p ||= 0
+	pe ||= data.length
+	cs = nginx_start
+	top = 0
+	ts = nil
+	te = nil
+	act = 0
+end
+# line 69 "src/scanner.rl"
+        
+# line 188 "src/scanner.rb"
+begin
+	_klen, _trans, _keys, _acts, _nacts = nil
+	_goto_level = 0
+	_resume = 10
+	_eof_trans = 15
+	_again = 20
+	_test_eof = 30
+	_out = 40
+	while true
+	_trigger_goto = false
+	if _goto_level <= 0
+	if p == pe
+		_goto_level = _test_eof
+		next
+	end
+	end
+	if _goto_level <= _resume
+	_acts = _nginx_from_state_actions[cs]
+	_nacts = _nginx_actions[_acts]
+	_acts += 1
+	while _nacts > 0
+		_nacts -= 1
+		_acts += 1
+		case _nginx_actions[_acts - 1]
+			when 1 then
+# line 1 "src/scanner.rl"
+		begin
+ts = p
+		end
+# line 1 "src/scanner.rl"
+# line 219 "src/scanner.rb"
+		end # from state action switch
+	end
+	if _trigger_goto
+		next
+	end
+	_keys = _nginx_key_offsets[cs]
+	_trans = _nginx_index_offsets[cs]
+	_klen = _nginx_single_lengths[cs]
+	_break_match = false
+	
+	begin
+	  if _klen > 0
+	     _lower = _keys
+	     _upper = _keys + _klen - 1
+
+	     loop do
+	        break if _upper < _lower
+	        _mid = _lower + ( (_upper - _lower) >> 1 )
+
+	        if data[p] < _nginx_trans_keys[_mid]
+	           _upper = _mid - 1
+	        elsif data[p] > _nginx_trans_keys[_mid]
+	           _lower = _mid + 1
+	        else
+	           _trans += (_mid - _keys)
+	           _break_match = true
+	           break
+	        end
+	     end # loop
+	     break if _break_match
+	     _keys += _klen
+	     _trans += _klen
+	  end
+	  _klen = _nginx_range_lengths[cs]
+	  if _klen > 0
+	     _lower = _keys
+	     _upper = _keys + (_klen << 1) - 2
+	     loop do
+	        break if _upper < _lower
+	        _mid = _lower + (((_upper-_lower) >> 1) & ~1)
+	        if data[p] < _nginx_trans_keys[_mid]
+	          _upper = _mid - 2
+	        elsif data[p] > _nginx_trans_keys[_mid+1]
+	          _lower = _mid + 2
+	        else
+	          _trans += ((_mid - _keys) >> 1)
+	          _break_match = true
+	          break
+	        end
+	     end # loop
+	     break if _break_match
+	     _trans += _klen
+	  end
+	end while false
+	_trans = _nginx_indicies[_trans]
+	end
+	if _goto_level <= _eof_trans
+	cs = _nginx_trans_targs_wi[_trans]
+	if _nginx_trans_actions_wi[_trans] != 0
+		_acts = _nginx_trans_actions_wi[_trans]
+		_nacts = _nginx_actions[_acts]
+		_acts += 1
+		while _nacts > 0
+			_nacts -= 1
+			_acts += 1
+			case _nginx_actions[_acts - 1]
+when 2 then
+# line 1 "src/scanner.rl"
+		begin
+te = p+1
+		end
+# line 1 "src/scanner.rl"
+when 3 then
+# line 20 "src/scanner.rl"
+		begin
+te = p+1
+ begin 
+            name = words.shift
+            values = words.dup
+            contexts.last[name] = value_of(values)
+            words.clear
+            	begin
+		top -= 1
+		cs = stack[top]
+		_trigger_goto = true
+		_goto_level = _again
+		break
+	end
+
+           end
+		end
+# line 20 "src/scanner.rl"
+when 4 then
+# line 31 "src/scanner.rl"
+		begin
+te = p+1
+ begin  
+	          name = words.shift
+            values = words.dup
+            contexts << contexts.last.section(name, value_of(values))
+            words.clear
+            	begin
+		stack[top] = cs
+		top+= 1
+		cs = 10
+		_trigger_goto = true
+		_goto_level = _again
+		break
+	end
+
+           end
+		end
+# line 31 "src/scanner.rl"
+when 5 then
+# line 43 "src/scanner.rl"
+		begin
+te = p+1
+		end
+# line 43 "src/scanner.rl"
+when 6 then
+# line 28 "src/scanner.rl"
+		begin
+te = p
+p = p - 1; begin  words << data[ts...te].pack('c*')  end
+		end
+# line 28 "src/scanner.rl"
+when 7 then
+# line 39 "src/scanner.rl"
+		begin
+te = p
+p = p - 1; begin 
+            contexts.pop
+            	begin
+		top -= 1
+		cs = stack[top]
+		_trigger_goto = true
+		_goto_level = _again
+		break
+	end
+
+           end
+		end
+# line 39 "src/scanner.rl"
+when 8 then
+# line 43 "src/scanner.rl"
+		begin
+te = p
+p = p - 1;		end
+# line 43 "src/scanner.rl"
+when 9 then
+# line 28 "src/scanner.rl"
+		begin
+ begin p = ((te))-1; end
+ begin  words << data[ts...te].pack('c*')  end
+		end
+# line 28 "src/scanner.rl"
+when 10 then
+# line 48 "src/scanner.rl"
+		begin
+te = p+1
+		end
+# line 48 "src/scanner.rl"
+when 11 then
+# line 50 "src/scanner.rl"
+		begin
+te = p+1
+ begin  words.clear; p = p - 1; 	begin
+		stack[top] = cs
+		top+= 1
+		cs = 10
+		_trigger_goto = true
+		_goto_level = _again
+		break
+	end
+  end
+		end
+# line 50 "src/scanner.rl"
+when 12 then
+# line 52 "src/scanner.rl"
+		begin
+te = p+1
+		end
+# line 52 "src/scanner.rl"
+when 13 then
+# line 50 "src/scanner.rl"
+		begin
+te = p
+p = p - 1; begin  words.clear; p = p - 1; 	begin
+		stack[top] = cs
+		top+= 1
+		cs = 10
+		_trigger_goto = true
+		_goto_level = _again
+		break
+	end
+  end
+		end
+# line 50 "src/scanner.rl"
+when 14 then
+# line 52 "src/scanner.rl"
+		begin
+te = p
+p = p - 1;		end
+# line 52 "src/scanner.rl"
+when 15 then
+# line 50 "src/scanner.rl"
+		begin
+ begin p = ((te))-1; end
+ begin  words.clear; p = p - 1; 	begin
+		stack[top] = cs
+		top+= 1
+		cs = 10
+		_trigger_goto = true
+		_goto_level = _again
+		break
+	end
+  end
+		end
+# line 50 "src/scanner.rl"
+# line 439 "src/scanner.rb"
+			end # action switch
+		end
+	end
+	if _trigger_goto
+		next
+	end
+	end
+	if _goto_level <= _again
+	_acts = _nginx_to_state_actions[cs]
+	_nacts = _nginx_actions[_acts]
+	_acts += 1
+	while _nacts > 0
+		_nacts -= 1
+		_acts += 1
+		case _nginx_actions[_acts - 1]
+when 0 then
+# line 1 "src/scanner.rl"
+		begin
+ts = nil;		end
+# line 1 "src/scanner.rl"
+# line 460 "src/scanner.rb"
+		end # to state action switch
+	end
+	if _trigger_goto
+		next
+	end
+	p += 1
+	if p != pe
+		_goto_level = _resume
+		next
+	end
+	end
+	if _goto_level <= _test_eof
+	if p == eof
+	if _nginx_eof_trans[cs] > 0
+		_trans = _nginx_eof_trans[cs] - 1;
+		_goto_level = _eof_trans
+		next;
+	end
+end
+	end
+	if _goto_level <= _out
+		break
+	end
+	end
+	end
+# line 70 "src/scanner.rl"
+        # This is a little more forgiving than
+        # using <tt>pop</tt> and validating balance
+        contexts.first
+      end
+
+      #######
+      private
+      #######
+
+      # Return single values if only one word,
+      # and make it an integer if possible
+      def value_of(words)
+        return nil if words.empty?       
+        return words unless words.size == 1
+        parsed_words = words.map do |word|
+          Integer(word) rescue word
+        end
+        parsed_words.size == 1 ? parsed_words.pop : parsed_words
+      end
+  
+    end
+
+  end
+
+end