parslet 1.6.0 → 1.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a03d43eaaf0b663727e308d79395c84019d63d0b
-  data.tar.gz: 2d39731312fe20e6640077b1cfb3b4a9c4ff34fd
+  metadata.gz: 041b9dcd017516b0335b4553a0ffcde588d8316c
+  data.tar.gz: 6f57cfc783537bd7041a5f67703a894b6350a1e4
 SHA512:
-  metadata.gz: 5aacc9ac06b08230c6301ededf169dba75ea056c082531d62120a380a536df66e4bd310fd8ae609578cd0da8c74989c4c2d71d50ffa4acd394074e36166fd305
-  data.tar.gz: 8b7151423f165f532c24b6f5a3b3a0ce88e990c95749a7b5c918451ad5d2ed59368b528f66f5a39312495b7d33bb3ff1e3da69aadcc135a968881de0b84754ce
+  metadata.gz: dccb1e2066a77937485d82d3ac155725db744a03e2ab37360bfe105ae612447074638bc40b5f88f0ee8ece95a407d161179f82e9bedd8de585d15aaced535382
+  data.tar.gz: d1f451935a0da7518ef301eab7bc0b0d689d1d277e1e28bca4e47e48be486c45f7d9f4839df4587d4490c9833ea9f378e1fdc92eddd77a5122d5ad66bc17ae30

data/HISTORY.txt

@@ -3,7 +3,11 @@
   - prsnt? and absnt? are now finally banned into oblivion. Wasting vocals for
     the win. 
 
-= 1.6 / ??
+= 1.7 / ???
+
+  ! Small speed gains from improvements on the hot spots. 
+
+= 1.6 / 1May2014
 
   + EXPERIMENTAL: Parslet accelerators permit replacing parts of your parser 
     with optimized atoms using pattern matching. Look at 

data/lib/parslet/atoms/base.rb

@@ -36,7 +36,7 @@ class Parslet::Atoms::Base
       # Cheating has not paid off. Now pay the cost: Rerun the parse,
       # gathering error information in the process.
       reporter = options[:reporter] || Parslet::ErrorReporter::Tree.new
-      source.pos = 0
+      source.bytepos = 0
       success, value = setup_and_apply(source, reporter, !options[:prefix])
       
       fail "Assertion failed: success was true when parsing with reporter" \
@@ -78,7 +78,7 @@ class Parslet::Atoms::Base
   # @param consume_all [Boolean] true if the current parse must consume
   #   all input by itself.
   def apply(source, context, consume_all=false)
-    old_pos = source.pos
+    old_pos = source.bytepos
     
     success, value = result = context.try_with_cache(self, source, consume_all)
 
@@ -91,7 +91,7 @@ class Parslet::Atoms::Base
         offending_input = source.consume(10)
         
         # Rewind input (as happens always in error case)
-        source.pos      = old_pos
+        source.bytepos  = old_pos
         
         return context.err_at(
           self, 
@@ -106,7 +106,7 @@ class Parslet::Atoms::Base
     end
     
     # We only reach this point if the parse has failed. Rewind the input.
-    source.pos = old_pos
+    source.bytepos = old_pos
     return result
   end
   

data/lib/parslet/atoms/context.rb

@@ -24,14 +24,14 @@ module Parslet::Atoms
     # advance the input pos by the same amount of bytes.
     #
     def try_with_cache(obj, source, consume_all)
-      beg = source.pos
+      beg = source.bytepos
         
       # Not in cache yet? Return early.
       unless entry = lookup(obj, beg)
         result = obj.try(source, self, consume_all)
     
         if obj.cached?
-          set obj, beg, [result, source.pos-beg]
+          set obj, beg, [result, source.bytepos-beg]
         end
         
         return result
@@ -43,7 +43,7 @@ module Parslet::Atoms
       # The data we're skipping here has been read before. (since it is in 
       # the cache) PLUS the actual contents are not interesting anymore since
       # we know obj matches at beg. So skip reading.
-      source.pos = beg + advance
+      source.bytepos = beg + advance
       return result
     end  
     
@@ -81,11 +81,15 @@ module Parslet::Atoms
     end
     
   private 
+    # NOTE These methods use #object_id directly, since that seems to bring the
+    # most performance benefit. This is a hot spot; going through
+    # Atoms::Base#hash doesn't yield as much.
+    #
     def lookup(obj, pos)
-      @cache[pos][obj] 
+      @cache[pos][obj.object_id] 
     end
     def set(obj, pos, val)
-      @cache[pos][obj] = val
+      @cache[pos][obj.object_id] = val
     end
   end
 end

data/lib/parslet/atoms/infix.rb

@@ -62,7 +62,7 @@ class Parslet::Atoms::Infix < Parslet::Atoms::Base
 
     # Loop until we fail on operator matching or until input runs out.
     loop do
-      op_pos = source.pos
+      op_pos = source.bytepos
       op_match, prec, assoc = match_operation(source, context, false)
 
       # If no operator could be matched here, one of several cases 
@@ -82,7 +82,7 @@ class Parslet::Atoms::Infix < Parslet::Atoms::Base
         result << precedence_climb(
           source, context, consume_all, next_prec, true)
       else
-        source.pos = op_pos
+        source.bytepos = op_pos
         return unwrap(result)
       end
     end

data/lib/parslet/atoms/lookahead.rb

@@ -22,22 +22,23 @@ class Parslet::Atoms::Lookahead < Parslet::Atoms::Base
   end
   
   def try(source, context, consume_all)
-    pos = source.pos
+    rewind_pos  = source.bytepos
+    error_pos   = source.pos
 
     success, value = bound_parslet.apply(source, context, consume_all)
     
     if positive
       return succ(nil) if success
-      return context.err_at(self, source, @error_msgs[:positive], pos)
+      return context.err_at(self, source, @error_msgs[:positive], error_pos)
     else
       return succ(nil) unless success
-      return context.err_at(self, source, @error_msgs[:negative], pos)
+      return context.err_at(self, source, @error_msgs[:negative], error_pos)
     end
     
   # This is probably the only parslet that rewinds its input in #try.
   # Lookaheads NEVER consume their input, even on success, that's why. 
   ensure 
-    source.pos = pos
+    source.bytepos = rewind_pos
   end
   
   precedence LOOKAHEAD

data/lib/parslet/context.rb

@@ -17,6 +17,8 @@ class Parslet::Context < BlankSlate
   reveal :inspect
   reveal :to_s
   reveal :instance_variable_set
+
+  include Parslet
   
   def meta_def(name, &body)
     metaclass = class <<self; self; end

data/lib/parslet/position.rb

@@ -0,0 +1,21 @@
+
+# Encapsules the concept of a position inside a string. 
+#
+class Parslet::Position
+  attr_reader :bytepos
+
+  include Comparable
+
+  def initialize string, bytepos
+    @string = string
+    @bytepos = bytepos
+  end
+
+  def charpos
+    @string.byteslice(0, @bytepos).size
+  end
+
+  def <=> b
+    self.bytepos <=> b.bytepos
+  end
+end

data/lib/parslet/slice.rb

@@ -23,17 +23,23 @@
 # delegation, we opt for a partial emulation that gets the job done.
 #
 class Parslet::Slice
-  attr_reader :str, :offset
+  attr_reader :str
+  attr_reader :position
   attr_reader :line_cache
 
   # Construct a slice using a string, an offset and an optional line cache. 
   # The line cache should be able to answer to the #line_and_column message. 
   #
-  def initialize(string, offset, line_cache=nil)
-    @str, @offset = string, offset
+  def initialize(position, string, line_cache=nil)
+    @position = position
+    @str = string
     @line_cache = line_cache
   end
 
+  def offset
+    @position.charpos
+  end
+
   # Compares slices to other slices or strings.
   #
   def == other
@@ -57,7 +63,7 @@ class Parslet::Slice
   # as the one of this slice. 
   #
   def +(other)
-    self.class.new(str + other.to_s, offset, line_cache)
+    self.class.new(@position, str + other.to_s, line_cache)
   end
 
   # Returns a <line, column> tuple referring to the original input.
@@ -66,7 +72,7 @@ class Parslet::Slice
     raise ArgumentError, "No line cache was given, cannot infer line and column." \
       unless line_cache
 
-    line_cache.line_and_column(self.offset)
+    line_cache.line_and_column(@position.bytepos)
   end
 
 
@@ -96,6 +102,7 @@ class Parslet::Slice
 
   # Prints the slice as <code>"string"@offset</code>.
   def inspect
+
     str.inspect << "@#{offset}"
   end
 end

data/lib/parslet/source.rb

@@ -2,6 +2,7 @@
 require 'stringio'
 require 'strscan'
 
+require 'parslet/position'
 require 'parslet/source/line_cache'
 
 module Parslet
@@ -38,11 +39,11 @@ module Parslet
     # input. 
     #
     def consume(n)
-      original_pos = @str.pos
+      position = self.pos
       slice_str = @str.scan(@re_cache[n])
       slice = Parslet::Slice.new(
+        position, 
         slice_str,
-        original_pos,
         @line_cache)
 
       return slice
@@ -67,11 +68,19 @@ module Parslet
     end
     
     # Position of the parse as a character offset into the original string. 
-    # @note: Encodings...
+    #
+    # @note Please be aware of encodings at this point. 
+    #
     def pos
+      Position.new(@str.string, @str.pos)
+    end
+    def bytepos
       @str.pos
     end
-    def pos=(n)
+
+    # @note Please be aware of encodings at this point. 
+    #
+    def bytepos=(n)
       @str.pos = n
     rescue RangeError
     end
@@ -81,7 +90,7 @@ module Parslet
     # given by #pos. 
     #
     def line_and_column(position=nil)
-      @line_cache.line_and_column(position || self.pos)
+      @line_cache.line_and_column(position || self.bytepos)
     end
   end
 end

data/lib/parslet/source/line_cache.rb

@@ -12,9 +12,11 @@ class Parslet::Source
       @line_ends.extend RangeSearch
     end
 
-    # Returns a <line, column> tuple for the given input position. 
-    # 
+    # Returns a <line, column> tuple for the given input position. Input
+    # position must be given as byte offset into original string. 
+    #
     def line_and_column(pos)
+      pos = pos.bytepos if pos.respond_to? :bytepos
       eol_idx = @line_ends.lbound(pos)
 
       if eol_idx

metadata

@@ -1,27 +1,27 @@
 --- !ruby/object:Gem::Specification
 name: parslet
 version: !ruby/object:Gem::Version
-  version: 1.6.0
+  version: 1.6.1
 platform: ruby
 authors:
 - Kaspar Schiess
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-01 00:00:00.000000000 Z
+date: 2014-05-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: blankslate
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '2.0'
 description: 
@@ -33,49 +33,8 @@ extra_rdoc_files:
 files:
 - HISTORY.txt
 - LICENSE
-- Rakefile
 - README
-- lib/parslet/accelerator/application.rb
-- lib/parslet/accelerator/engine.rb
-- lib/parslet/accelerator.rb
-- lib/parslet/atoms/alternative.rb
-- lib/parslet/atoms/base.rb
-- lib/parslet/atoms/can_flatten.rb
-- lib/parslet/atoms/capture.rb
-- lib/parslet/atoms/context.rb
-- lib/parslet/atoms/dsl.rb
-- lib/parslet/atoms/dynamic.rb
-- lib/parslet/atoms/entity.rb
-- lib/parslet/atoms/infix.rb
-- lib/parslet/atoms/lookahead.rb
-- lib/parslet/atoms/named.rb
-- lib/parslet/atoms/re.rb
-- lib/parslet/atoms/repetition.rb
-- lib/parslet/atoms/scope.rb
-- lib/parslet/atoms/sequence.rb
-- lib/parslet/atoms/str.rb
-- lib/parslet/atoms/visitor.rb
-- lib/parslet/atoms.rb
-- lib/parslet/cause.rb
-- lib/parslet/context.rb
-- lib/parslet/convenience.rb
-- lib/parslet/error_reporter/deepest.rb
-- lib/parslet/error_reporter/tree.rb
-- lib/parslet/error_reporter.rb
-- lib/parslet/export.rb
-- lib/parslet/expression/treetop.rb
-- lib/parslet/expression.rb
-- lib/parslet/graphviz.rb
-- lib/parslet/parser.rb
-- lib/parslet/pattern/binding.rb
-- lib/parslet/pattern.rb
-- lib/parslet/rig/rspec.rb
-- lib/parslet/scope.rb
-- lib/parslet/slice.rb
-- lib/parslet/source/line_cache.rb
-- lib/parslet/source.rb
-- lib/parslet/transform.rb
-- lib/parslet.rb
+- Rakefile
 - example/big.erb
 - example/boolean_algebra.rb
 - example/calc.rb
@@ -133,30 +92,73 @@ files:
 - example/simple_xml.rb
 - example/string_parser.rb
 - example/test.lit
+- lib/parslet.rb
+- lib/parslet/accelerator.rb
+- lib/parslet/accelerator/application.rb
+- lib/parslet/accelerator/engine.rb
+- lib/parslet/atoms.rb
+- lib/parslet/atoms/alternative.rb
+- lib/parslet/atoms/base.rb
+- lib/parslet/atoms/can_flatten.rb
+- lib/parslet/atoms/capture.rb
+- lib/parslet/atoms/context.rb
+- lib/parslet/atoms/dsl.rb
+- lib/parslet/atoms/dynamic.rb
+- lib/parslet/atoms/entity.rb
+- lib/parslet/atoms/infix.rb
+- lib/parslet/atoms/lookahead.rb
+- lib/parslet/atoms/named.rb
+- lib/parslet/atoms/re.rb
+- lib/parslet/atoms/repetition.rb
+- lib/parslet/atoms/scope.rb
+- lib/parslet/atoms/sequence.rb
+- lib/parslet/atoms/str.rb
+- lib/parslet/atoms/visitor.rb
+- lib/parslet/cause.rb
+- lib/parslet/context.rb
+- lib/parslet/convenience.rb
+- lib/parslet/error_reporter.rb
+- lib/parslet/error_reporter/deepest.rb
+- lib/parslet/error_reporter/tree.rb
+- lib/parslet/export.rb
+- lib/parslet/expression.rb
+- lib/parslet/expression/treetop.rb
+- lib/parslet/graphviz.rb
+- lib/parslet/parser.rb
+- lib/parslet/pattern.rb
+- lib/parslet/pattern/binding.rb
+- lib/parslet/position.rb
+- lib/parslet/rig/rspec.rb
+- lib/parslet/scope.rb
+- lib/parslet/slice.rb
+- lib/parslet/source.rb
+- lib/parslet/source/line_cache.rb
+- lib/parslet/transform.rb
 homepage: http://kschiess.github.com/parslet
 licenses:
 - MIT
 metadata: {}
 post_install_message: 
 rdoc_options:
-- --main
+- "--main"
 - README
 require_paths:
 - lib
 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: 2.0.14
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Parser construction library with great error reporting in Ruby.
 test_files: []
+has_rdoc: