query_string_parser 0.1.0

data/Rakefile

@@ -0,0 +1,88 @@
+require 'rake'
+require 'rake/clean'
+require 'rake/rdoctask'
+require 'rake/gempackagetask'
+require 'rake/testtask'
+require 'spec/rake/spectask'
+require 'fileutils'
+include FileUtils
+
+# Default Rake task is compile
+task :default => :compile
+
+def make(makedir)
+  Dir.chdir(makedir) { sh 'make' }
+end
+
+def extconf(dir)
+  Dir.chdir(dir) { ruby "extconf.rb" }
+end
+
+def setup_extension(dir, extension)
+  ext = "ext/#{dir}"
+  ext_so = "#{ext}/#{extension}.#{Config::CONFIG['DLEXT']}"
+  ext_files = FileList[
+    "#{ext}/*.c",
+    "#{ext}/*.h",
+    "#{ext}/extconf.rb",
+    "#{ext}/Makefile",
+    "lib"
+  ]
+
+  task "lib" do
+    directory "lib"
+  end
+
+  desc "Builds just the #{extension} extension"
+  task extension.to_sym => ["#{ext}/Makefile", ext_so ]
+
+  file "#{ext}/Makefile" => ["#{ext}/extconf.rb"] do
+    extconf "#{ext}"
+  end
+
+  file ext_so => ext_files do
+    make "#{ext}"
+    cp ext_so, "lib"
+  end
+end
+
+setup_extension("", "pr_query_parser")
+
+desc "Compile the extension"
+task :compile => [:pr_query_parser]
+
+Spec::Rake::SpecTask.new('do_spec') do |t|
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end
+desc "run spec tests"
+task :spec => [:clean, :compile, :do_spec]
+
+CLEAN.include ['build/*', '**/*.o', '**/*.so', '**/*.bundle', '**/*.a', '**/*.log', 'pkg']
+CLEAN.include ['ext/Makefile']
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |s|
+    s.name = "query_string_parser"
+    s.summary = "Simple query string parser"
+    s.email = "dj2@everburning.com"
+    s.homepage = "http://github.com/dj2/query_string_parser"
+    s.description = s.summary
+    s.authors = ["dan sinclair"]
+    s.files = [
+      "Rakefile",
+      "ext/extconf.rb",
+      "ext/pr_query_parser.c",
+      "lib/query_string_parser.rb",
+      "spec/query_string_parser_spec.rb"
+    ]
+    s.extensions << 'ext/extconf.rb'
+    s.require_paths = ['lib']
+    s.test_files = ['spec/query_string_parser_spec.rb']
+  end
+
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler, or one of its dependencies, is not available. Install it with: sudo gem install technicalpickles-jeweler -s http://gems.github.com"
+end
+

data/ext/extconf.rb

@@ -0,0 +1,9 @@
+require 'mkmf'
+
+#$CFLAGS = "-Wall -Werror -Wextra"
+
+extension_name = 'pr_query_parser'
+dir_config(extension_name)
+
+have_library('curl', 'curl_easy_unescape')
+create_makefile(extension_name)

data/ext/pr_query_parser.c

@@ -0,0 +1,129 @@
+#include "ruby.h"
+
+#include <stdio.h>
+#include <ctype.h>
+#include <curl/curl.h>
+
+static void
+pr_set_param(VALUE params, char *key, char *value)
+{
+    VALUE rkey, rvalue, cur;
+    char *v;
+
+    /* no key do nothing */
+    if (key == NULL || *key == 0) return;
+
+    /* strip [] from the key name */
+    v = curl_easy_unescape(NULL, key, 0, NULL);
+    if (strlen(v) > 2)
+    {
+        char *t = v;
+        char *open_bracket = NULL;
+
+        while (*(t + 1) != 0)
+        {
+            if (*t == '[') open_bracket = t;
+            t++;
+        }
+
+        if ((*t == ']') && (open_bracket != NULL))
+        {
+            char *pos = (open_bracket + 1);
+            int is_digit = 1;
+
+            while (pos != t)
+            {
+                if (!isdigit(*pos))
+                {
+                    is_digit = 0;
+                    break;
+                }
+                pos ++;
+            }
+
+            if ((*t == ']') && (*(t - 1) == '['))
+            {
+                *(t - 1) = 0;
+            }
+            else if ((*t == ']') && (*open_bracket == '[') && is_digit)
+            {
+                *open_bracket = 0;
+            }
+        }
+    }
+
+    /* key was only [], do nothing */
+    if (v == NULL || *v == 0) return;
+
+    rkey = rb_str_new2(v);
+    free(v);
+
+    v = curl_easy_unescape(NULL, value, 0, NULL);
+    rvalue = rb_str_new2(v);
+    free(v);
+
+    cur = rb_hash_aref(params, rkey);
+    if (NIL_P(cur))
+    {
+        rb_hash_aset(params, rkey, rvalue);
+    }
+    else
+    {
+        VALUE arry;
+        if (rb_obj_is_kind_of(cur, rb_cArray)  == Qtrue)
+        {
+            arry = cur;
+        }
+        else
+        {
+            arry = rb_ary_new();
+            rb_ary_push(arry, cur);
+            rb_hash_aset(params, rkey, arry);
+        }
+        rb_ary_push(arry, rvalue);
+    }
+}
+
+VALUE
+pr_query_parser(VALUE self, VALUE query_string, VALUE delim)
+{
+    VALUE params = Qnil;
+    char *qs, *p, *s, *key = NULL;
+    char delimiter = RSTRING_PTR(delim)[0];
+
+    params = rb_hash_new();
+    qs = strdup(RSTRING_PTR(query_string));
+    for (s = qs, p = qs, key = qs; *p != 0; p++)
+    {
+        if (*p == delimiter)
+        {
+            if (key != NULL)
+            {
+                *p = 0;
+                pr_set_param(params, key, s);
+            }
+            s = (p + 1);
+            key = s;
+        }
+        else if (*p == '=')
+        {
+            *p = 0;
+            key = s;
+            s = (p + 1);
+        }
+    }
+
+    if (key != NULL) pr_set_param(params, key, s);
+    free(qs);
+
+    return params;
+    self = self;
+}
+
+void
+Init_pr_query_parser(void)
+{
+    VALUE QueryStringParser = rb_define_module("QueryStringParser");
+
+    rb_define_module_function(QueryStringParser, "pr_query_parser", pr_query_parser, 2);
+}

data/lib/query_string_parser.rb

@@ -0,0 +1,13 @@
+require 'iconv'
+require 'pr_query_parser'
+
+module QueryStringParser
+  module_function
+
+  def qs_parse(query_string, delim = '&')
+    return {} if query_string.nil? || query_string == ""
+
+    ret = Iconv.iconv("UTF-8//IGNORE", "ISO-8859-1", (query_string + "\x20")).first[0..-2]
+    pr_query_parser(ret, delim)
+  end
+end

data/spec/query_string_parser_spec.rb

@@ -0,0 +1,166 @@
+# coding:utf-8
+
+$: << File.expand_path(File.join(File.dirname(__FILE__), '..', 'lib'))
+
+require 'query_string_parser'
+
+describe 'QueryStringParser' do
+  include QueryStringParser
+
+  it 'should parse a well formed query string' do
+    h = qs_parse('a=b&c=d&e=f')
+    h['a'].should == 'b'
+    h['c'].should == 'd'
+    h['e'].should == 'f'
+  end
+
+  it 'should parse a nil query string' do
+    qs_parse(nil).should == {}
+  end
+
+  it 'should allow different delimiters' do
+    h = qs_parse('a=b|c=d|e=f', '|')
+    h['a'].should == 'b'
+    h['c'].should == 'd'
+    h['e'].should == 'f'
+  end
+
+  it 'should parse a blank query string' do
+    qs_parse("").should == {}
+  end
+
+  it 'should parse a query string with multiple delimiters together' do
+    h = qs_parse("appkey=ff-postrank&&id=http%3A%2F%2Fmail.google.com%2Fmail%2Ffeed%2Fatom")
+    h.keys.length.should == 2
+    h['appkey'].should == 'ff-postrank'
+    h['id'].should == 'http://mail.google.com/mail/feed/atom'
+  end
+
+  it 'should parse a key with no value at the end of the string' do
+    h = qs_parse("appkey=ff-postrank&id=http%3A%2F%2Fmail.google.com%2Fmail%2Ffeed%2Fatom&noindex")
+    h.keys.length.should == 3
+    h['appkey'].should == 'ff-postrank'
+    h['id'].should == 'http://mail.google.com/mail/feed/atom'
+    h['noindex'].should == 'noindex'
+  end
+
+  it 'should parse a key with no value at the beginning of the string' do
+    h = qs_parse("noindex&appkey=ff-postrank&id=http%3A%2F%2Fmail.google.com%2Fmail%2Ffeed%2Fatom")
+    h.keys.length.should == 3
+    h['appkey'].should == 'ff-postrank'
+    h['id'].should == 'http://mail.google.com/mail/feed/atom'
+    h['noindex'].should == 'noindex'
+  end
+
+  it 'should parse a key with no value in the middle of the string' do
+    h = qs_parse("appkey=ff-postrank&noindex&id=http%3A%2F%2Fmail.google.com%2Fmail%2Ffeed%2Fatom")
+    h.keys.length.should == 3
+    h['appkey'].should == 'ff-postrank'
+    h['id'].should == 'http://mail.google.com/mail/feed/atom'
+    h['noindex'].should == 'noindex'
+  end
+
+  it 'should handle receiving only a key without a value' do
+    h = qs_parse('noindex')
+    h.keys.length.should == 1
+    h['noindex'].should == 'noindex'
+  end
+
+  it 'should parse a string with only =' do
+    qs_parse("=").should == {}
+  end
+
+  it 'should parse a string with only &' do
+    qs_parse('&').should == {}
+  end
+
+  it 'should parse a key with a blank value' do
+    h = qs_parse("mykey=&otherkey=zsf")
+    h.keys.length.should == 2
+    h['mykey'].should == ''
+    h['otherkey'].should == 'zsf'
+  end
+
+  it 'should parse a value with no key' do
+    h = qs_parse("mykey=asdf&=myvalue")
+    h.keys.length.should == 1
+    h['mykey'].should == 'asdf'
+  end
+
+  it 'should handle arrays of values' do
+    h = qs_parse("url[]=http%3A%2F%2Fscience.slashdot.org%2Farticle.pl%3Fsid%3D08%2F09%2F23%2F1210218%26from%3Drss&feed_id[]=132&url[]=http%3A%2F%2Fhardware.slashdot.org%2Farticle.pl%3Fsid%3D08%2F09%2F23%2F0313242%26from%3Drss&feed_id[]=132")
+    h['url'].class.should == Array
+    h['url'].length.should == 2
+    h['url'][0].should == 'http://science.slashdot.org/article.pl?sid=08/09/23/1210218&from=rss'
+    h['url'][1].should == 'http://hardware.slashdot.org/article.pl?sid=08/09/23/0313242&from=rss'
+
+    h['feed_id'].class.should == Array
+    h['feed_id'].length.should == 2
+    h['feed_id'][0].should == '132'
+    h['feed_id'][1].should == '132'
+  end
+
+  it 'should handle arrays of values with indexes' do
+    h = qs_parse("url[0]=http%3A%2F%2Fscience.slashdot.org%2Farticle.pl%3Fsid%3D08%2F09%2F23%2F1210218%26from%3Drss&feed_id[0]=132&url[1]=http%3A%2F%2Fhardware.slashdot.org%2Farticle.pl%3Fsid%3D08%2F09%2F23%2F0313242%26from%3Drss&feed_id[1]=132")
+    h['url'].class.should == Array
+    h['url'].length.should == 2
+    h['url'][0].should == 'http://science.slashdot.org/article.pl?sid=08/09/23/1210218&from=rss'
+    h['url'][1].should == 'http://hardware.slashdot.org/article.pl?sid=08/09/23/0313242&from=rss'
+
+    h['feed_id'].class.should == Array
+    h['feed_id'].length.should == 2
+    h['feed_id'][0].should == '132'
+    h['feed_id'][1].should == '132'
+  end
+
+  it "should handle escaped []'s on array keys" do
+    h = qs_parse("url%5B%5D=http%3A%2F%2Fscience.slashdot.org%2Farticle.pl%3Fsid%3D08%2F09%2F23%2F1210218%26from%3Drss&feed_id%5B%5D=132&url%5B%5D=http%3A%2F%2Fhardware.slashdot.org%2Farticle.pl%3Fsid%3D08%2F09%2F23%2F0313242%26from%3Drss&feed_id%5B%5D=132")
+    h['url'].class.should == Array
+    h['url'].length.should == 2
+    h['url'][0].should == 'http://science.slashdot.org/article.pl?sid=08/09/23/1210218&from=rss'
+    h['url'][1].should == 'http://hardware.slashdot.org/article.pl?sid=08/09/23/0313242&from=rss'
+
+    h['feed_id'].class.should == Array
+    h['feed_id'].length.should == 2
+    h['feed_id'][0].should == '132'
+    h['feed_id'][1].should == '132'
+  end
+
+  it 'should handle arrays without [] provided' do
+    h = qs_parse('key=1&key[]=2&key%5B%5D=3')
+    h['key'].class.should == Array
+    h['key'].length.should == 3
+    h['key'][0].should == '1'
+    h['key'][1].should == '2'
+    h['key'][2].should == '3'
+  end
+
+  it 'should handle blank items at the beginning and end of the strings' do
+    h = qs_parse("&baz=1&bar=2&splat=23&splat[]=42&splat=543&splat%5b%5d=99&splay=http:%2f%2f%3casdf&")
+    h.keys.length.should == 4
+
+    h['baz'].should == "1"
+    h['bar'].should == "2"
+    h['splat'].class.should == Array
+    h['splat'].length.should == 4
+    h['splat'][0].should == "23"
+    h['splat'][1].should == "42"
+    h['splat'][2].should == "543"
+    h['splat'][3].should == "99"
+    h['splay'].should == 'http://<asdf'
+  end
+
+  it 'should handle UTF-8 values' do
+    h = qs_parse("url%5B%5D=http%3A%2F%2Fwattf.com%2Fwp%2F2008%2F12%2F03%2Fmichael-nielsen-lectures-on-the-google-technology-stack%2F&feed_id%5B%5D=2e2b55b3058696ccbe633e7241d53b16&url%5B%5D=http%3A%2F%2Fjamesgolick.com%2F2008%2F10%2F27%2Foff-topic-caf%C3%A9-myriade&feed_id%5B%5D=0381dd0545852d28d82ad7d0befbfd92")
+    h.keys.length.should == 2
+    h['url'].class.should == Array
+    h['url'].length.should == 2
+    h['url'][0].should == 'http://wattf.com/wp/2008/12/03/michael-nielsen-lectures-on-the-google-technology-stack/'
+    h['url'][1].should == 'http://jamesgolick.com/2008/10/27/off-topic-café-myriade'
+
+    h['feed_id'].class.should == Array
+    h['feed_id'].length.should == 2
+    h['feed_id'][0].should == '2e2b55b3058696ccbe633e7241d53b16'
+    h['feed_id'][1].should == '0381dd0545852d28d82ad7d0befbfd92'
+  end
+end

metadata

@@ -0,0 +1,67 @@
+--- !ruby/object:Gem::Specification 
+name: query_string_parser
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- dan sinclair
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-06-15 00:00:00 -04:00
+default_executable: 
+dependencies: []
+
+description: Simple query string parser
+email: dj2@everburning.com
+executables: []
+
+extensions: 
+- ext/extconf.rb
+- ext/extconf.rb
+extra_rdoc_files: []
+
+files: 
+- Rakefile
+- ext/extconf.rb
+- ext/pr_query_parser.c
+- lib/query_string_parser.rb
+- spec/query_string_parser_spec.rb
+has_rdoc: true
+homepage: http://github.com/dj2/query_string_parser
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: Simple query string parser
+test_files: 
+- spec/query_string_parser_spec.rb