csvscan-enphase 0.1.1

data/Gemfile

@@ -0,0 +1,9 @@
+source "http://rubygems.org"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "bundler", "~> 1.0.0"
+  gem "jeweler", "~> 1.6.4"
+  gem "rcov", ">= 0"
+end

data/History.txt

@@ -0,0 +1,6 @@
+=== 1.0.0 / 2009-08-11
+
+* 1 major enhancement
+
+  * Birthday!
+

data/Manifest.txt

@@ -0,0 +1,11 @@
+README.ja
+README.txt
+ext/csvscan/MANIFEST
+ext/csvscan/csvscan.c
+ext/csvscan/csvscan.rl
+ext/csvscan/extconf.rb
+setup.rb
+History.txt
+Manifest.txt
+Rakefile
+test/test_csvscan.rb

data/README.ja

@@ -0,0 +1,33 @@
+CSVScan
+
+CSVScan ��CSV���®�˥ѡ������뤿��Υ饤�֥��Ǥ���
+
+
+1. ɬ�״Ķ�
+
+  * ruby 1.8
+  * C ����ѥ���
+
+
+2. ���󥹥ȡ�����ˡ
+
+  ���ޥ�ɥ饤��ǰʲ��Τ褦�����Ϥ��Ƥ���������
+  UNIX �� OS �ǤϤ����餯 root ���¤�ɬ�פˤʤ�ޤ���
+
+    # ruby setup.rb
+
+3. �Ȥ���
+
+    require "csvscan"   # �饤�֥��Υ�����
+    
+    open(ARGV.shift) {|io|
+      CSVScan.scan(io) {|row|
+        p row
+      }
+    }
+
+4. �饤����
+
+  �饤���󥹤�Ruby�Υ饤���󥹤˽����ޤ���
+
+MoonWolf <moonwolf@moonwolf.com>

data/README.txt

@@ -0,0 +1,46 @@
+= csvscan
+
+http://github.com/dvdplm/csvscan
+
+== DESCRIPTION:
+
+This is a packaged version of CSVScan, written by MoonWolf. If you can read Japanese, checkout README.ja for whatever he said. This particular fork has some fixes to make the extension compile on ruby 1.9.
+
+On a 10,000 line file:
+
+    time cat example.csv | ruby fastercsv_benchmark.rb
+
+    real	0m8.804s
+    user	0m8.502s
+    sys	0m0.304s
+
+    time cat example.csv | ruby csvscan_benchmark.rb 
+
+    real	0m0.860s
+    user	0m0.782s
+    sys	0m0.088s
+
+
+== FEATURES/PROBLEMS:
+
+* First version.
+* I have not tested this on Windows, and have no intention to.
+
+== SYNOPSIS:
+
+    require 'csvscan'
+    CSVScan.scan(STDIN) do |row|
+        puts row.inspect
+    end
+
+== REQUIREMENTS:
+
+* FIX (list of requirements)
+
+== INSTALL:
+
+* gem install dvdplm-csvscan --source http://gems.github.com
+
+== LICENSE:
+
+Looks like the original source was LGPL, so I'm stuck with that.

data/Rakefile

@@ -0,0 +1,67 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "csvscan-enphase"
+  gem.homepage = "http://github.com/cracell/csvscan"
+  gem.license = "MIT"
+  gem.summary = %Q{This is a packaged version of CSVScan, written by MoonWolf}
+  gem.description = %Q{This is a packaged version of CSVScan, written by MoonWolf. If you can read Japanese, checkout README.ja for whatever he said.
+
+On a 10,000 line file:
+
+    time cat example.csv | ruby fastercsv_benchmark.rb
+
+    real	0m8.804s
+    user	0m8.502s
+    sys	0m0.304s
+
+    time cat example.csv | ruby csvscan_benchmark.rb 
+
+    real	0m0.860s
+    user	0m0.782s
+    sys	0m0.088s}
+  gem.email = "ecranston@enphaseenergy.com"
+  gem.authors = ["Eric Cranston"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+require 'rcov/rcovtask'
+Rcov::RcovTask.new do |test|
+  test.libs << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+  test.rcov_opts << '--exclude "gems/*"'
+end
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "csvscan #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.1

data/csvscan-enphase.gemspec

@@ -0,0 +1,74 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{csvscan-enphase}
+  s.version = "0.1.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Eric Cranston"]
+  s.date = %q{2011-10-12}
+  s.description = %q{This is a packaged version of CSVScan, written by MoonWolf. If you can read Japanese, checkout README.ja for whatever he said.
+
+On a 10,000 line file:
+
+    time cat example.csv | ruby fastercsv_benchmark.rb
+
+    real	0m8.804s
+    user	0m8.502s
+    sys	0m0.304s
+
+    time cat example.csv | ruby csvscan_benchmark.rb 
+
+    real	0m0.860s
+    user	0m0.782s
+    sys	0m0.088s}
+  s.email = %q{ecranston@enphaseenergy.com}
+  s.extensions = ["ext/csvscan/extconf.rb"]
+  s.extra_rdoc_files = [
+    "README.ja",
+    "README.txt"
+  ]
+  s.files = [
+    "Gemfile",
+    "History.txt",
+    "Manifest.txt",
+    "README.ja",
+    "README.txt",
+    "Rakefile",
+    "VERSION",
+    "csvscan-enphase.gemspec",
+    "ext/csvscan/MANIFEST",
+    "ext/csvscan/csvscan.c",
+    "ext/csvscan/csvscan.rl",
+    "ext/csvscan/extconf.rb",
+    "setup.rb",
+    "test/test_csvscan.rb"
+  ]
+  s.homepage = %q{http://github.com/cracell/csvscan}
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.4.2}
+  s.summary = %q{This is a packaged version of CSVScan, written by MoonWolf}
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
+      s.add_development_dependency(%q<rcov>, [">= 0"])
+    else
+      s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
+      s.add_dependency(%q<rcov>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+    s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
+    s.add_dependency(%q<rcov>, [">= 0"])
+  end
+end
+

data/ext/csvscan/MANIFEST

@@ -0,0 +1,4 @@
+MANIFEST
+csvscan.c
+csvscan.rl
+extconf.rb

data/ext/csvscan/csvscan.c

@@ -0,0 +1,332 @@
+#line 1 "csvscan.rl"
+#include <ruby.h>
+
+static VALUE rb_eCSVParseError;
+static ID s_read, s_to_str;
+
+#line 70 "csvscan.rl"
+
+
+
+#line 12 "csvscan.c"
+static const int csv_scan_start = 2;
+
+static const int csv_scan_error = 1;
+
+#line 73 "csvscan.rl"
+
+#define BUFSIZE 131072
+
+VALUE csv_scan(VALUE self, VALUE port) {
+    int cs, act, have = 0, nread = 0, curline = 1;
+    unsigned char *tokstart = NULL, *tokend = NULL, *buf;
+    VALUE row, coldata;
+    VALUE bufsize = Qnil;
+    int done=0, buffer_size;
+
+    if ( !rb_respond_to( port, s_read ) ) {
+        if ( rb_respond_to( port, s_to_str ) ) {
+            port = rb_funcall( port, s_to_str, 0 );
+            StringValue(port);
+        } else {
+            rb_raise( rb_eArgError, "bad argument, String or IO only please." );
+        }
+    }
+
+    buffer_size = BUFSIZE;
+    if (rb_ivar_defined(self, rb_intern("@buffer_size")) == Qtrue) {
+        bufsize = rb_ivar_get(self, rb_intern("@buffer_size"));
+        if (!NIL_P(bufsize)) {
+            buffer_size = NUM2INT(bufsize);
+        }
+    }
+    buf = ALLOC_N(unsigned char, buffer_size);
+
+    
+#line 47 "csvscan.c"
+	{
+	cs = csv_scan_start;
+	tokstart = 0;
+	tokend = 0;
+	act = 0;
+	}
+#line 102 "csvscan.rl"
+
+    row = rb_ary_new();
+    coldata = Qnil;
+
+    while( !done ) {
+        VALUE str;
+        unsigned char *p = buf + have, *pe;
+        int len, space = buffer_size - have;
+
+        if ( space == 0 ) {
+            rb_raise(rb_eCSVParseError, "ran out of buffer on line %d.", curline);
+        }
+
+        if ( rb_respond_to( port, s_read ) ) {
+            str = rb_funcall( port, s_read, 1, INT2FIX(space) );
+        } else {
+            str = rb_str_substr( port, nread, space );
+        }
+
+        StringValue(str);
+        memcpy( p, RSTRING_PTR(str), RSTRING_LEN(str) );
+        len = RSTRING_LEN(str);
+        nread += len;
+
+        /* If this is the last buffer, tack on an EOF. */
+        if ( len < space ) {
+            p[len++] = 0;
+            done = 1;
+        }
+
+        pe = p + len;
+        
+#line 87 "csvscan.c"
+	{
+	if ( p == pe )
+		goto _out;
+	switch ( cs )
+	{
+tr0:
+#line 19 "csvscan.rl"
+	{tokend = p;{p = ((tokend))-1;}}
+	goto st2;
+tr1:
+#line 10 "csvscan.rl"
+	{
+        curline += 1;
+    }
+#line 20 "csvscan.rl"
+	{
+          rb_ary_push(row, coldata);
+          rb_yield(row);
+          coldata = Qnil;
+          row = rb_ary_new();
+      }
+#line 20 "csvscan.rl"
+	{tokend = p+1;{p = ((tokend))-1;}}
+	goto st2;
+tr2:
+#line 49 "csvscan.rl"
+	{tokend = p;{
+          unsigned char ch, *start_p, *wptr, *rptr;
+          int rest, datalen;
+          start_p = wptr = tokstart;
+          rptr = tokstart + 1;
+          rest = tokend - tokstart - 2;
+          datalen = 0;
+          while(rest>0) {
+              ch = *rptr++;
+              if (ch=='"') {
+                rptr++;
+                rest--;
+              }
+              *wptr++ = ch;
+              datalen++;
+              rest--;
+          }
+          coldata = rb_str_new( start_p, datalen );
+      }{p = ((tokend))-1;}}
+	goto st2;
+tr5:
+#line 1 "csvscan.rl"
+	{	switch( act ) {
+	case 0: tokend = tokstart; {goto st1;}
+	case 4:
+	{
+          unsigned char ch, *endp;
+          int datalen;
+          datalen = tokend - tokstart;
+          endp = tokend - 1;
+          while(datalen>0) {
+              ch = *endp--;
+              if (ch==' ' || ch=='\t') {
+                  datalen--;
+              } else {
+                  break;
+              }
+          }
+          if (datalen==0) {
+              coldata = Qnil;
+          } else {
+              coldata = rb_str_new(tokstart, datalen);
+          }
+      }
+	break;
+	case 5:
+	{
+          unsigned char ch, *start_p, *wptr, *rptr;
+          int rest, datalen;
+          start_p = wptr = tokstart;
+          rptr = tokstart + 1;
+          rest = tokend - tokstart - 2;
+          datalen = 0;
+          while(rest>0) {
+              ch = *rptr++;
+              if (ch=='"') {
+                rptr++;
+                rest--;
+              }
+              *wptr++ = ch;
+              datalen++;
+              rest--;
+          }
+          coldata = rb_str_new( start_p, datalen );
+      }
+	break;
+	default: break;
+	}
+	{p = ((tokend))-1;}}
+	goto st2;
+tr6:
+#line 19 "csvscan.rl"
+	{tokend = p+1;{p = ((tokend))-1;}}
+	goto st2;
+tr7:
+#line 19 "csvscan.rl"
+	{tokend = p+1;{p = ((tokend))-1;}}
+#line 10 "csvscan.rl"
+	{
+        curline += 1;
+    }
+#line 20 "csvscan.rl"
+	{
+          rb_ary_push(row, coldata);
+          rb_yield(row);
+          coldata = Qnil;
+          row = rb_ary_new();
+      }
+	goto st2;
+tr10:
+#line 26 "csvscan.rl"
+	{tokend = p+1;{
+          rb_ary_push(row, coldata);
+          coldata = Qnil;
+      }{p = ((tokend))-1;}}
+	goto st2;
+st2:
+#line 1 "csvscan.rl"
+	{tokstart = 0;}
+#line 1 "csvscan.rl"
+	{act = 0;}
+	if ( ++p == pe )
+		goto _out2;
+case 2:
+#line 1 "csvscan.rl"
+	{tokstart = p;}
+#line 220 "csvscan.c"
+	switch( (*p) ) {
+		case 9u: goto tr6;
+		case 10u: goto tr7;
+		case 13u: goto st4;
+		case 32u: goto tr6;
+		case 34u: goto st0;
+		case 44u: goto tr10;
+	}
+	if ( 11u <= (*p) && (*p) <= 12u )
+		goto tr8;
+	goto tr4;
+tr4:
+#line 1 "csvscan.rl"
+	{tokend = p+1;}
+#line 30 "csvscan.rl"
+	{act = 4;}
+	goto st3;
+tr8:
+#line 1 "csvscan.rl"
+	{tokend = p+1;}
+#line 19 "csvscan.rl"
+	{act = 1;}
+	goto st3;
+st3:
+	if ( ++p == pe )
+		goto _out3;
+case 3:
+#line 248 "csvscan.c"
+	switch( (*p) ) {
+		case 10u: goto tr5;
+		case 13u: goto tr5;
+		case 34u: goto tr5;
+		case 44u: goto tr5;
+	}
+	goto tr4;
+st4:
+	if ( ++p == pe )
+		goto _out4;
+case 4:
+	if ( (*p) == 10u )
+		goto tr1;
+	goto tr0;
+tr11:
+#line 10 "csvscan.rl"
+	{
+        curline += 1;
+    }
+	goto st0;
+st0:
+	if ( ++p == pe )
+		goto _out0;
+case 0:
+#line 273 "csvscan.c"
+	switch( (*p) ) {
+		case 10u: goto tr11;
+		case 34u: goto tr12;
+	}
+	goto st0;
+tr12:
+#line 1 "csvscan.rl"
+	{tokend = p+1;}
+#line 49 "csvscan.rl"
+	{act = 5;}
+	goto st5;
+st5:
+	if ( ++p == pe )
+		goto _out5;
+case 5:
+#line 289 "csvscan.c"
+	if ( (*p) == 34u )
+		goto st0;
+	goto tr2;
+st1:
+	goto _out1;
+	}
+	_out2: cs = 2; goto _out; 
+	_out3: cs = 3; goto _out; 
+	_out4: cs = 4; goto _out; 
+	_out0: cs = 0; goto _out; 
+	_out5: cs = 5; goto _out; 
+	_out1: cs = 1; goto _out; 
+
+	_out: {}
+	}
+#line 134 "csvscan.rl"
+
+        if ( cs == csv_scan_error ) {
+            free(buf);
+            rb_raise(rb_eCSVParseError, "parse error on line %d.", curline);
+        }
+
+        if ( tokstart == 0 ) {
+            have = 0;
+        } else {
+            have = pe - tokstart;
+            memmove( buf, tokstart, have );
+            tokend = buf + (tokend - tokstart);
+            tokstart = buf;
+        }
+    }
+    free(buf);
+    return Qnil;
+}
+
+void Init_csvscan() {
+  VALUE mCSVScan = rb_define_module("CSVScan");
+  rb_define_attr(rb_singleton_class(mCSVScan), "buffer_size", 1, 1);
+  rb_define_singleton_method(mCSVScan, "scan", csv_scan, 1);
+  rb_eCSVParseError = rb_define_class_under(mCSVScan, "ParseError", rb_eException);
+
+  s_read = rb_intern("read");
+  s_to_str = rb_intern("to_str");
+}