xbrlware-ce 1.0.2

data/example/benchmark/instance_parser_benchmark.rb

@@ -0,0 +1,25 @@
+require 'xbrlware'
+
+r=Xbrlware::Report.new
+class << r
+  public :xbrl_files
+end
+files=r.xbrl_files("../../../xbrlware-wiki/sample_reports/edgar_data")
+
+output = StringIO.new
+output << "|| *Instance + Taxonomy file size (KB)* || *Time (Seconds)* ||"
+output << "\n"
+
+files.each do |file_map|
+  m=Benchmark.measure do
+    instance=Xbrlware.ins(file_map["ins"])
+  end
+
+  size = File.size(file_map["ins"]) / 1024.0
+  size += File.size(file_map["tax"]) / 1024.0
+  output << "|| " << format("%.4f", size).to_s << " || "
+  output << format("%.4f", m.total).to_s << " || "
+  output << "\n"
+end
+
+puts output.string

data/example/case_study/buy_strategy.rb

@@ -0,0 +1,34 @@
+require 'rubygems' # you need this when xbrlware is installed as gem
+require 'edgar'
+require 'xbrlware'
+
+dl=Edgar::HTMLFeedDownloader.new()
+
+url="http://www.sec.gov/Archives/edgar/data/843006/000135448809002030/0001354488-09-002030-index.htm"
+download_dir=url.split("/")[-2] # download dir is : 000135448809002030
+dl.download(url, download_dir)
+
+instance_file=Xbrlware.file_grep(download_dir)["ins"]
+instance=Xbrlware.ins(instance_file)
+
+item_name="Assets"
+assets = instance.item(item_name) # Extracts "Assets"
+
+if assets.size < 2
+  puts item_name + " Not found.."
+  return
+end
+
+curr_asset, prev_asset=0, 0
+
+if Date.parse(assets[0].context.period) > Date.parse(assets[1].context.period)
+  curr_asset=assets[0].value.to_f
+  prev_asset=assets[1].value.to_f
+else
+  curr_asset=assets[1].value.to_f
+  prev_asset=assets[0].value.to_f
+end
+
+if curr_asset > prev_asset
+  puts "Buy..."
+end

data/example/case_study/c-20091230.xml

@@ -0,0 +1,29 @@
+<?xml version="1.0" encoding="US-ASCII"?>
+<xbrli:xbrl xmlns:xbrli="http://www.xbrl.org/2003/instance" xmlns:iso4217="http://www.xbrl.org/2003/iso4217"
+            xmlns:link="http://www.xbrl.org/2003/linkbase" xmlns:us-gaap="http://xbrl.us/us-gaap/2009-01-31"
+            xmlns:xbrldi="http://xbrl.org/2006/xbrldi" xmlns:xlink="http://www.w3.org/1999/xlink">
+    <link:schemaRef xlink:href="" xlink:type="simple"/>
+    <xbrli:context id="Y2009">
+        <xbrli:entity>
+            <xbrli:identifier scheme="http://www.sec.gov/CIK">9999999999</xbrli:identifier>
+        </xbrli:entity>
+        <xbrli:period>
+            <xbrli:startDate>2009-01-02</xbrli:startDate>
+            <xbrli:endDate>2009-12-30</xbrli:endDate>
+        </xbrli:period>
+    </xbrli:context>
+    <xbrli:context id="Y2008">
+        <xbrli:entity>
+            <xbrli:identifier scheme="http://www.sec.gov/CIK">9999999999</xbrli:identifier>
+        </xbrli:entity>
+        <xbrli:period>
+            <xbrli:startDate>2008-01-02</xbrli:startDate>
+            <xbrli:endDate>2008-12-30</xbrli:endDate>
+        </xbrli:period>
+    </xbrli:context>  
+    <xbrli:unit id="USD">
+        <xbrli:measure>iso4217:USD</xbrli:measure>
+    </xbrli:unit>
+    <us-gaap:NetIncomeLoss contextRef="Y2009" unitRef="USD" decimals="-6">730000000</us-gaap:NetIncomeLoss>
+    <us-gaap:NetIncomeLoss contextRef="Y2008" unitRef="USD" decimals="-6">902000000</us-gaap:NetIncomeLoss>
+</xbrli:xbrl>

data/example/case_study/c_sell_strategy.rb

@@ -0,0 +1,29 @@
+require 'rubygems' # you need this when xbrlware is installed as gem
+require 'xbrlware'
+
+instance_file="c-20091230.xml"
+instance = Xbrlware.ins(instance_file) # Create parser instance
+
+item_name="NetIncomeLoss" # This is the item we are interested in.
+net_incomes = instance.item(item_name) # Extracts "NetIncomeLoss"
+
+if net_incomes.size < 2
+  puts item_name + " Not found.."
+  return
+end
+
+curr_netincome, prev_netincome=0, 0
+
+if Date.parse(net_incomes[0].context.period["end_date"]) > Date.parse(net_incomes[1].context.period["end_date"])
+  curr_netincome=net_incomes[0].value.to_f
+  prev_netincome=net_incomes[1].value.to_f
+else
+  curr_netincome=net_incomes[1].value.to_f
+  prev_netincome=net_incomes[0].value.to_f  
+end
+
+expected_netincome=prev_netincome-(prev_netincome * 0.05)
+
+if curr_netincome < expected_netincome
+  puts "Sell..." # Sell C's stocks
+end

data/example/lang_integration/thrift/rating-client.py

@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+
+import sys
+
+sys.path.append("gen-py")
+
+from thrift.transport import TTransport
+from thrift.transport import TSocket
+from thrift.protocol import TBinaryProtocol
+
+from risk import Rating
+from risk.ttypes import *
+
+transport = TTransport.TBufferedTransport(TSocket.TSocket("localhost", "9090"))
+protocol = TBinaryProtocol.TBinaryProtocol(transport)
+
+client = Rating.Client(protocol)
+transport.open()
+
+print client.piotroski("JAVA")
+print client.altman_z("GOOG")

data/example/lang_integration/thrift/rating-impl.rb

@@ -0,0 +1,13 @@
+# provide an implementation of Rating service
+class RatingImpl
+
+  def piotroski(entity_name)
+    # Code that use xbrlware goes here
+    return 1 # return some dummy value
+  end
+
+  def altman_z(entity_name)
+    # Code that use xbrlware goes here
+    return 2.2567 # return some dummy value
+  end
+end

data/example/lang_integration/thrift/rating-server.rb

@@ -0,0 +1,25 @@
+$:.push('gen-rb')
+
+require 'thrift'
+
+require 'thrift/transport/server_socket'
+require 'thrift/transport/buffered_transport'
+require 'thrift/server/simple_server'
+
+require 'rating'
+require 'rating-impl'
+
+# Thrift provides mutiple communication endpoints
+#  - Here we will expose our service via a TCP socket
+#  - Web-service will run as a single thread, on port 9090
+
+handler = RatingImpl.new()
+processor = Risk::Rating::Processor.new(handler)
+
+transport = Thrift::ServerSocket.new(9090)
+transportFactory = Thrift::BufferedTransportFactory.new()
+server = Thrift::SimpleServer.new(processor, transport, transportFactory)
+
+puts "Starting the Rating service..."
+server.serve()
+

data/example/lang_integration/thrift/rating.thrift

@@ -0,0 +1,52 @@
+ #!/usr/local/bin/thrift --java --php --py
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#
+# Interface definition for Ratings Service
+#
+
+namespace java org.risk.service
+namespace cpp org.risk
+namespace csharp Risk
+namespace py risk
+namespace php risk
+namespace perl Risk
+namespace rb Risk
+
+#
+# constants
+#
+
+# for clients checking that server and it have same thrift definitions.
+const string VERSION = "1.2"
+
+#
+# Exceptions
+# (note that internal server errors will raise a TApplicationException, courtesy of Thrift)
+#
+
+#
+# service api
+#
+
+service Rating {
+   # compute Piotroski score 
+   i16 piotroski(1:string entity_name),
+
+   # compute Altman Z Score
+   double altman_z(1:string entity_name)
+}

data/example/quick_start/foo.rb

@@ -0,0 +1,10 @@
+require 'rubygems' # you need this when xbrlware is installed as gem
+require 'xbrlware'
+
+instance=Xbrlware.ins("foo.xml")
+items=instance.item("ProfitLoss")
+
+puts "Profit-Loss \t Context"
+items.each do |item|
+  puts item.value+" \t "+item.context.id
+end

data/example/quick_start/foo.xml

@@ -0,0 +1,29 @@
+<?xml version="1.0" encoding="US-ASCII"?>
+<xbrli:xbrl xmlns:xbrli="http://www.xbrl.org/2003/instance" xmlns:iso4217="http://www.xbrl.org/2003/iso4217" 
+xmlns:link="http://www.xbrl.org/2003/linkbase" xmlns:us-gaap="http://xbrl.us/us-gaap/2009-01-31" 
+xmlns:xbrldi="http://xbrl.org/2006/xbrldi" xmlns:xlink="http://www.w3.org/1999/xlink">
+    <link:schemaRef xlink:href="" xlink:type="simple"/>
+    <xbrli:context id="D2009Q2YTD">
+        <xbrli:entity>
+            <xbrli:identifier scheme="http://www.sec.gov/CIK">9999999999</xbrli:identifier>
+        </xbrli:entity>
+        <xbrli:period>
+            <xbrli:startDate>2009-02-01</xbrli:startDate>
+            <xbrli:endDate>2009-08-15</xbrli:endDate>
+        </xbrli:period>
+    </xbrli:context>
+    <xbrli:context id="D2008Q2YTD">
+        <xbrli:entity>
+            <xbrli:identifier scheme="http://www.sec.gov/CIK">9999999999</xbrli:identifier>
+        </xbrli:entity>
+        <xbrli:period>
+            <xbrli:startDate>2008-02-03</xbrli:startDate>
+            <xbrli:endDate>2008-08-16</xbrli:endDate>
+        </xbrli:period>
+    </xbrli:context>  
+    <xbrli:unit id="USD">
+        <xbrli:measure>iso4217:USD</xbrli:measure>
+    </xbrli:unit>
+    <us-gaap:ProfitLoss contextRef="D2008Q2YTD" unitRef="USD" decimals="-6">730000000</us-gaap:ProfitLoss>
+    <us-gaap:ProfitLoss contextRef="D2009Q2YTD" unitRef="USD" decimals="-6">902000000</us-gaap:ProfitLoss>
+</xbrli:xbrl>

data/example/quick_start/print_item.rb

@@ -0,0 +1,27 @@
+require 'rubygems' # you need this when xbrlware is installed as gem
+require 'edgar'
+require 'xbrlware'
+
+dl=Edgar::HTMLFeedDownloader.new()
+
+url="http://www.sec.gov/Archives/edgar/data/843006/000135448809002030/0001354488-09-002030-index.htm"
+download_dir=url.split("/")[-2] # download dir is : 000135448809002030
+dl.download(url, download_dir)
+
+# Name of xbrl documents downloaded from EDGAR system is in the following convention
+#    calculation linkbase document ends with _cal.xml
+#    definition linkbase document ends with _def.xml
+#    presentation linkbase ends with _pre.xml
+#    label linkbase document ends with _lab.xml
+#    taxonomy document ends with .xsd
+#    instance document ends with .xml
+# Xbrl::file_grep understands above convention.  
+instance_file=Xbrlware.file_grep(download_dir)["ins"] # use file_grep to filter xbrl files and get instance file
+
+instance=Xbrlware.ins(instance_file)
+
+items=instance.item("OtherAssetsCurrent")
+puts "Other-Assets \t Context"
+items.each do |item|
+  puts item.value+" \t "+item.context.id
+end

data/lib/edgar.rb

@@ -0,0 +1,30 @@
+#!/usr/bin/ruby
+#
+# Author:: xbrlware@bitstat.com
+#
+# Copyright:: 2009, 2010 bitstat (http://www.bitstat.com). All Rights Reserved.
+#
+# License:: Licensed under the Apache License, Version 2.0 (the "License");
+#           you may not use this file except in compliance with the License.
+#           You may obtain a copy of the License at
+#
+#           http://www.apache.org/licenses/LICENSE-2.0
+#
+#           Unless required by applicable law or agreed to in writing, software
+#           distributed under the License is distributed on an "AS IS" BASIS,
+#           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+#           implied.
+#           See the License for the specific language governing permissions and
+#           limitations under the License.
+#
+require 'ftools'
+
+require 'open-uri'
+require 'rexml/document'
+require 'rexml/streamlistener'
+
+require 'edgar/util'
+require 'edgar/edgar_data_downloader'
+
+
+

data/lib/edgar/edgar_data_downloader.rb

@@ -0,0 +1,126 @@
+#!/usr/bin/ruby
+#
+# Author:: xbrlware@bitstat.com
+#
+# Copyright:: 2009, 2010 bitstat (http://www.bitstat.com). All Rights Reserved.
+#
+# License:: Licensed under the Apache License, Version 2.0 (the "License");
+#           you may not use this file except in compliance with the License.
+#           You may obtain a copy of the License at
+#
+#           http://www.apache.org/licenses/LICENSE-2.0
+#
+#           Unless required by applicable law or agreed to in writing, software
+#           distributed under the License is distributed on an "AS IS" BASIS,
+#           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+#           implied.
+#           See the License for the specific language governing permissions and
+#           limitations under the License.
+#
+module Edgar
+  
+  # This class defines method to download XBRL files from SEC's XBRL RSS Feed.  
+  # See {report generation xbrlware wiki}[http://code.google.com/p/xbrlware/wiki/ReportGeneration] for how to use this class.  
+  class RSSFeedDownloader
+    include FileUtil
+
+    attr_reader :content
+
+    def initialize(sec_edgar_rss_file=nil)
+      sec_edgar_rss_file ||= "http://www.sec.gov/Archives/edgar/usgaap.rss.xml"
+      @content = XmlSimple.xml_in(open(sec_edgar_rss_file).read, {'ForceContent' => true})
+    end
+
+    # Takes limit (how many entities to download), download_to (where to download)
+    #  default value for limit is 100
+    #  default value for download_to is current_dir + "/edgar_data" 
+    def download(limit=100, download_to=File.expand_path(".")+File::SEPARATOR+"edgar_data")
+      items=@content["channel"][0]["item"]
+      items.each_with_index do |item, index|
+        break if index==limit
+        files=get_xbrl_files(item)
+        download_to += File::SEPARATOR unless download_to.end_with?(File::SEPARATOR)
+        data_dir=download_to
+        data_dir=data_dir+File::SEPARATOR+item["xbrlFiling"][0]["cikNumber"][0]["content"]
+        data_dir=data_dir+File::SEPARATOR+item["xbrlFiling"][0]["accessionNumber"][0]["content"]
+        mkdir(data_dir)
+        files.each do |file|
+          file_content=open(file["url"]).read
+          dump_to_file(data_dir+File::SEPARATOR+file["file"], file_content)
+        end
+      end
+    end
+
+    def print_stat # :nodoc:
+      i_url=""
+      i_size=0
+      title=""
+      items=@content["channel"][0]["item"]
+      items.each do |item|
+        files=get_xbrl_files(item)
+        files.each do |file|
+          if file["type"]=="EX-101.INS" && (i_size==0 || file["size"].to_i < i_size)
+            i_size = file["size"].to_i
+            i_url = file["url"]
+            title = item["title"]
+          end
+        end
+      end
+      puts ""
+      puts " Smallest Instance File " + i_url 
+    end
+
+    private
+    # Gets url that end with xml and xsd 
+    def get_xbrl_files(item)
+      xbrl_files=item["xbrlFiling"][0]["xbrlFiles"][0]["xbrlFile"]
+      return xbrl_files.select {|e| e["url"].end_with?("xml") || e["url"].end_with?("xsd")}
+    end
+
+  end
+
+  # This class defines method to download XBRL files from SEC's EDGAR filling url.
+  # See {report generation xbrlware wiki}[http://code.google.com/p/xbrlware/wiki/ReportGeneration] for how to use this class.
+  class HTMLFeedDownloader
+    include REXML::StreamListener
+    include FileUtil
+
+    attr_reader :links
+
+    # Takes url and download_to (where to download)
+    #  default value for download_to is current_dir    
+    def download(url, download_to=File.expand_path(".")+File::SEPARATOR)
+      $LOG.info " Starting download of fillings from SEC url ["+url+"]"
+      files=[]
+      content = open(url).read
+      @links = Set.new
+      uri=URI(url)
+      @base_path=""
+      @base_path=(uri.scheme+"://"+uri.host+((uri.port==80 && "") || ":"+uri.port.to_s)) unless uri.host.nil?
+      parse(content)
+      download_to += File::SEPARATOR unless download_to.end_with?(File::SEPARATOR)
+      mkdir(download_to)
+      @links.each do |link|
+        file=download_to + link.split("/")[-1]
+        dump_to_file(file, open(link).read)
+        files << file
+      end unless uri.host.nil?
+      files
+    end
+
+    # Callback method for notifying start of xml elements by REXML stream parser. 
+    def tag_start(name, attrs) # :nodoc:
+      if "a"==name
+        href=attrs["href"]
+        @links << @base_path + href if href.end_with?("xml") || href.end_with?("xsd")
+      end
+    end
+
+    private
+    def parse(text)
+      REXML::Document.parse_stream(text, self)
+    end
+
+  end
+
+end