ruby-boost-regex 1.0.0 → 1.0.1

data/README.markdown

@@ -58,36 +58,51 @@ Anyway, here's some results:
     DNA-Matching (Computer Language Shootout)
     =========================================
     Rehearsal ------------------------------------------------
-    Normal regex  17.190000   0.020000  17.210000 ( 17.278168)
-    Boost regex   12.120000   0.030000  12.150000 ( 12.213959)
-    -------------------------------------- total: 29.360000sec
+    Normal regex  17.240000   0.050000  17.290000 ( 17.353051)
+    Oniguruma     16.300000   0.030000  16.330000 ( 16.384928)
+    Boost regex   11.400000   0.040000  11.440000 ( 11.489252)
+    -------------------------------------- total: 45.060000sec
     
                        user     system      total        real
-    Normal regex  17.050000   0.020000  17.070000 ( 17.082539)
-    Boost regex   12.000000   0.030000  12.030000 ( 12.040932)
+    Normal regex  17.190000   0.030000  17.220000 ( 17.273140)
+    Oniguruma     16.220000   0.040000  16.260000 ( 16.325460)
+    Boost regex   11.330000   0.030000  11.360000 ( 11.402222)
     
     Failing to match a phone number in a big string of text
     =======================================================
     Rehearsal ------------------------------------------------
-    Normal regex   0.070000   0.000000   0.070000 (  0.070072)
-    Boost regex    0.030000   0.000000   0.030000 (  0.034858)
-    --------------------------------------- total: 0.100000sec
+    Normal regex   0.070000   0.000000   0.070000 (  0.072128)
+    Oniguruma      0.040000   0.000000   0.040000 (  0.043422)
+    Boost regex    0.040000   0.000000   0.040000 (  0.034708)
+    --------------------------------------- total: 0.150000sec
     
                        user     system      total        real
-    Normal regex   0.070000   0.000000   0.070000 (  0.070087)
-    Boost regex    0.040000   0.000000   0.040000 (  0.035052)
-
+    Normal regex   0.070000   0.000000   0.070000 (  0.071984)
+    Oniguruma      0.040000   0.000000   0.040000 (  0.044686)
+    Boost regex    0.030000   0.000000   0.030000 (  0.036421)
 
 ## Usage
 
-Don't have it as a gem yet. Sorry! But you could do this in theory:
+Install the gem, use as follows:
+
+    require 'ruby-boost-regex'
 
     r = Boost::Regexp.new("(\\d{3})-(\\d{3})-(\\d{4})")
     r =~ "555-123-4567"
     p $1 # ==> "555"
     matches = r.match("123-456-7890")
     p matches[2] # ==> "456"
+    
+    Boost::Regex.enable_monkey_patch!
+    
+    r = /hello|world/i.boost!
+    r =~ "i'm Mike. Hello!" #==> 10
+    
+
+
+## Installation
 
+    gem install ruby-boost-regex
 
 ## Note on Patches/Pull Requests
  

data/VERSION

@@ -1 +1 @@
-1.0.0
+1.0.1

data/benchmark/benchmark.rb

@@ -8,8 +8,11 @@
 require 'benchmark'
 require 'rubygems'
 require 'ruby-boost-regex'
+require 'oniguruma'
 require 'lorem'
 
+include Oniguruma
+
 fname = File.dirname(__FILE__) + "/fasta.input" 
 seq = File.read(fname)
 seq.gsub!(/>.*\n|\n/,"")
@@ -50,16 +53,30 @@ boost_regexes = [
   Boost::Regexp.new('agggta[cgt]a|t[acg]taccct', Boost::Regexp::IGNORECASE),
   Boost::Regexp.new('agggtaa[cgt]|[acg]ttaccct', Boost::Regexp::IGNORECASE)
 ]
+oni_regexes = [
+  ORegexp.new('agggtaaa|tttaccct', :options => OPTION_IGNORECASE),
+  ORegexp.new('[cgt]gggtaaa|tttaccc[acg]', :options => OPTION_IGNORECASE),
+  ORegexp.new('a[act]ggtaaa|tttacc[agt]t', :options => OPTION_IGNORECASE),
+  ORegexp.new('ag[act]gtaaa|tttac[agt]ct', :options => OPTION_IGNORECASE),
+  ORegexp.new('agg[act]taaa|ttta[agt]cct', :options => OPTION_IGNORECASE),
+  ORegexp.new('aggg[acg]aaa|ttt[cgt]ccct', :options => OPTION_IGNORECASE),
+  ORegexp.new('agggt[cgt]aa|tt[acg]accct', :options => OPTION_IGNORECASE),
+  ORegexp.new('agggta[cgt]a|t[acg]taccct', :options => OPTION_IGNORECASE),
+  ORegexp.new('agggtaa[cgt]|[acg]ttaccct', :options => OPTION_IGNORECASE)
+]
+
 puts "DNA-Matching (Computer Language Shootout)"
 puts "========================================="
 Benchmark.bmbm do |x|
     x.report("Normal regex") { 100.times { regexes.each { |reg| fair_scan(seq, reg)}} }
+    x.report("Oniguruma")    { 100.times { oni_regexes.each {|reg| fair_scan(seq, reg)}} }
     x.report("Boost regex")  { 100.times { boost_regexes.each { |reg| fair_scan(seq, reg)}} }
 end
 
 
 reg = /\d{3}-\d{3}-\d{4}/
 boost_reg = Boost::Regexp.new('\d{3}-\d{3}-\d{4}')
+oni_reg = ORegexp.new('\d{3}-\d{3}-\d{4}')
 text = Lorem::Base.new('paragraphs', 200).output
 
 puts ""
@@ -67,5 +84,6 @@ puts "Failing to match a phone number in a big string of text"
 puts "======================================================="
 Benchmark.bmbm do |x|
     x.report("Normal regex") { 100.times { fair_scan(text, reg)}}
+    x.report("Oniguruma")    { 100.times { fair_scan(text, oni_reg)}}
     x.report("Boost regex")  { 100.times { fair_scan(text, boost_reg)}}
 end

data/ext/ruby-boost-regex/extconf.rb

@@ -1,5 +1,9 @@
 require 'mkmf'
 
+dir_config("boost")
 have_library("stdc++")
 have_library("boost_regex")
+if RUBY_VERSION =~ /1.9/ then  
+    $CPPFLAGS += " -DRUBY_19"  
+end
 create_makefile('ruby-boost-regex/BoostRegexHook')

data/ext/ruby-boost-regex/regexp.cpp

@@ -3,7 +3,12 @@
 #include <string>
 #include <exception>
 #include "ruby.h"
+
+#ifdef RUBY_19
+#include "ruby/re.h"
+#else
 #include "re.h"
+#endif
 
 static VALUE rb_mBoost;
 static VALUE rb_cBoostRegexp;

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 1
   - 0
-  - 0
-  version: 1.0.0
+  - 1
+  version: 1.0.1
 platform: ruby
 authors: 
 - Michael Edgar
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-04-06 00:00:00 -04:00
+date: 2010-04-08 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency