simple-spreadsheet-extractor 0.3.2 → 0.3.3

data/.gitignore

@@ -0,0 +1,3 @@
+*.gem
+.project
+.loadpath

data/README.rdoc

@@ -1,7 +1,7 @@
 = Simple Spreadsheet Extractor
 
 Authors::    Stuart Owen
-Version::    0.3.2
+Version::    0.3.3
 Contact::    mailto:stuart.owen@manchester.ac.uk
 Licence::    BSD (See LICENCE or http://www.opensource.org/licenses/bsd-license.php)
 Copyright::  (c) 2010 The University of Manchester, UK
@@ -21,6 +21,10 @@ Java 1.6 (JRE) is required.
 
   gem install simple-spreadsheet-extractor
 
+Note that on Windows you must also do:
+
+  gem install win32-open3
+
 == Usage
 
 * require 'simple-spreadsheet-extractor'
@@ -30,12 +34,15 @@ Java 1.6 (JRE) is required.
   
 e.g.
 
+   #example.rb - takes path, i.e. ruby example.rb /tmp/spreadsheet.xls
    require 'rubygems'
    require 'simple-spreadsheet-extractor'
 
    include SysMODB::SpreadsheetExtractor
 
-   f=open("/tmp/test-spreadsheet.xls")
+   path=ARGV.first
+
+   f=open(path)
    begin
      puts spreadsheet_to_xml(f)
    rescue SysMODB::SpreadsheetExtractionException=>e
@@ -46,7 +53,7 @@ Formulas are evaluated placing the result in the XML produced for that cell, how
 
 Row and column indexes start at 1, rather than 0, to keep consistent with namings of the cells in Excel.
 
-An XSD schema for the XML is available in doc/schema-v1.xsd
+An XSD schema for the XML is available in doc/schema-v1.xsd["http://github.com/stuzart/simple-spreadsheet-extractor-gem/blob/master/doc/schema-v1.xsd]
 
 == Example XML
 

data/Rakefile

@@ -0,0 +1,37 @@
+require 'rake'
+require 'rake/testtask'
+require 'rake/rdoctask'
+require 'rubygems'
+
+require 'rake/gempackagetask'
+
+task :default => [:test]
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gemspec|
+    gemspec.name = "simple-spreadsheet-extractor"
+    gemspec.summary = "Basic spreadsheet content extraction using Apache POI"
+    gemspec.description = "Takes a stream to a spreadsheet file and produces and XML representation of its contents"
+    gemspec.email = "stuart.owen@manchester.ac.uk"
+    gemspec.homepage = "http://github.com/myGrid/simple-spreadsheet-extractor-gem"
+    gemspec.authors = ["Stuart Owen"]
+    
+    gemspec.files.include %w(jars)
+    gemspec.files.exclude "test/*"
+    gemspec.extra_rdoc_files = ["README.rdoc", "LICENCE"]
+    gemspec.add_dependency("POpen4","0.1.4")
+  end
+rescue LoadError
+  puts "Jeweler not available. Install it with: gem install jeweler"
+end
+
+task:test do
+  Rake::TestTask.new do |t|
+    t.libs << "test"
+    t.test_files = FileList['test/test*.rb']
+    t.verbose = true
+  end
+end
+
+#end

data/VERSION

@@ -0,0 +1 @@
+0.3.3

data/doc/schema-v1.xsd

@@ -0,0 +1,56 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsd:schema targetNamespace="http://www.sysmo-db.org/2010/xml/spreadsheet"
+	xml:lang="en" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns="http://www.sysmo-db.org/2010/xml/spreadsheet"
+	elementFormDefault="qualified">
+
+	<xsd:element name="workbook" type="Workbook"></xsd:element>
+
+	<xsd:complexType name="Workbook">
+		<xsd:sequence>
+			<xsd:element name="sheet" type="Sheet" minOccurs="0"
+				maxOccurs="unbounded" />
+		</xsd:sequence>
+	</xsd:complexType>
+
+	<xsd:complexType name="Sheet">
+		<xsd:sequence>
+			<xsd:element name="row" type="Row" minOccurs="0"
+				maxOccurs="unbounded" />
+		</xsd:sequence>
+		<xsd:attribute name="name" type="xsd:string" use="required"></xsd:attribute>
+		<xsd:attribute name="index" type="xsd:positiveInteger"
+			use="required"></xsd:attribute>
+		<xsd:attribute name="hidden" type="xsd:boolean" use="required"></xsd:attribute>
+		<xsd:attribute name="very_hidden" type="xsd:boolean"
+			use="required"></xsd:attribute>
+		<xsd:attribute name="first_row" type="xsd:positiveInteger"
+			use="required"></xsd:attribute>
+		<xsd:attribute name="last_row" type="xsd:positiveInteger"
+			use="required"></xsd:attribute>
+	</xsd:complexType>
+
+	<xsd:complexType name="Row">
+		<xsd:sequence>
+			<xsd:element name="cell" type="Cell" minOccurs="0"
+				maxOccurs="unbounded" />
+		</xsd:sequence>
+		<xsd:attribute name="index" type="xsd:positiveInteger"
+			use="required"></xsd:attribute>
+	</xsd:complexType>
+
+	<xsd:complexType name="Cell">
+		<xsd:simpleContent>
+			<xsd:extension base="xsd:string">
+				<xsd:attribute name="column" type="xsd:positiveInteger"
+					use="required"></xsd:attribute>
+				<xsd:attribute name="column_alpha" type="xsd:string"
+					use="required"></xsd:attribute>
+				<xsd:attribute name="row" type="xsd:positiveInteger"
+					use="required"></xsd:attribute>
+				<xsd:attribute name="type" type="xsd:string" use="required"></xsd:attribute>
+				<xsd:attribute name="formula" type="xsd:string" use="optional"></xsd:attribute>
+			</xsd:extension>
+		</xsd:simpleContent>
+	</xsd:complexType>
+
+</xsd:schema>

data/lib/simple-spreadsheet-extractor.rb

@@ -1,5 +1,5 @@
 require 'rubygems'
-require 'open4'
+require 'popen4'
 
 module SysMODB
   
@@ -14,24 +14,17 @@ module SysMODB
       command = "java -jar #{JAR_PATH}/simple-spreadsheet-extractor-0.3.2.jar"
       output = ""
       err_message = ""
-      status = Open4::popen4(command) do |pid, stdin, stdout, stderr|
-        while ((line = spreadsheet_data.gets) != nil) do        
-          stdin << line
-        end
-        stdin.close
+      status = POpen4::popen4(command) do |stdout, stderr, stdin, pid|
+      stdin=stdin.binmode
+      spreadsheet_data.each_byte{|b| stdin.putc(b)}
+      stdin.close
                      
-        while ((line = stdout.gets) != nil) do
-          output << line
-        end      
-        stdout.close
-                
-        while ((line=stderr.gets)!= nil) do
-          err_message << line
-        end
-        stderr.close
+      output=stdout.read.strip                     
+      err_message=stderr.read.strip
+        
       end
             
-      if status.to_i != 0                 
+      if status.to_i != 0                         
         raise SpreadsheetExtractionException.new(err_message)             
       end
                   

data/simple-spreadsheet-extractor.gemspec

@@ -0,0 +1,57 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{simple-spreadsheet-extractor}
+  s.version = "0.3.3"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Stuart Owen"]
+  s.date = %q{2010-07-28}
+  s.description = %q{Takes a stream to a spreadsheet file and produces and XML representation of its contents}
+  s.email = %q{stuart.owen@manchester.ac.uk}
+  s.extra_rdoc_files = [
+    "LICENCE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".gitignore",
+     "LICENCE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "doc/schema-v1.xsd",
+     "jars/lib/dom4j-1.6.1.jar",
+     "jars/lib/poi-3.6.jar",
+     "jars/lib/poi-ooxml-3.6.jar",
+     "jars/lib/poi-ooxml-schemas-3.6.jar",
+     "jars/lib/xmlbeans-2.3.0.jar",
+     "jars/simple-spreadsheet-extractor-0.3.2.jar",
+     "lib/simple-spreadsheet-extractor.rb",
+     "simple-spreadsheet-extractor.gemspec"
+  ]
+  s.homepage = %q{http://github.com/myGrid/simple-spreadsheet-extractor-gem}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{Basic spreadsheet content extraction using Apache POI}
+  s.test_files = [
+    "test/test_extraction.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<POpen4>, ["= 0.1.4"])
+    else
+      s.add_dependency(%q<POpen4>, ["= 0.1.4"])
+    end
+  else
+    s.add_dependency(%q<POpen4>, ["= 0.1.4"])
+  end
+end
+

data/test/test_extraction.rb

@@ -0,0 +1,45 @@
+require 'test/unit'
+require 'simple-spreadsheet-extractor'
+require 'libxml'
+
+class TestExtraction < Test::Unit::TestCase
+  
+  SCHEMA_FILE_PATH = File.dirname(__FILE__) + "/../doc/schema-v1.xsd"
+  
+  include SysMODB::SpreadsheetExtractor
+  
+  def test_from_file_object    
+    test_sheet = File.dirname(__FILE__) + "/files/test-spreadsheet.xls"
+    f=open(test_sheet,"rb")    
+    xml = spreadsheet_to_xml(f)     
+    assert_not_nil xml      
+  end
+  
+  def test_validate_xml
+    test_sheet = File.dirname(__FILE__) + "/files/test-spreadsheet.xls"
+    f=open(test_sheet,"rb")    
+    xml = spreadsheet_to_xml(f)
+    validate_against_schema(xml)
+  end
+  
+  def test_failure
+    test_sheet = File.dirname(__FILE__) + "/files/not-a-spreadsheet.xls"
+    f=open(test_sheet,"rb")
+    assert_raise SysMODB::SpreadsheetExtractionException do 
+      spreadsheet_to_xml(f)      
+    end
+  end
+  
+  def validate_against_schema xml
+    document = LibXML::XML::Document.string(xml)    
+    schema = LibXML::XML::Schema.new(SCHEMA_FILE_PATH)    
+    begin
+      document.validate_schema(schema)
+    rescue LibXML::XML::Error => e          
+      puts xml
+      assert false,"Error validating against schema: #{e.message}"
+    end
+  end
+  
+  
+end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: simple-spreadsheet-extractor
 version: !ruby/object:Gem::Version 
-  hash: 23
+  hash: 21
   prerelease: false
   segments: 
   - 0
   - 3
-  - 2
-  version: 0.3.2
+  - 3
+  version: 0.3.3
 platform: ruby
 authors: 
 - Stuart Owen
@@ -15,23 +15,23 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-07-27 00:00:00 +01:00
+date: 2010-07-28 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: open4
+  name: POpen4
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - "="
       - !ruby/object:Gem::Version 
-        hash: 21
+        hash: 19
         segments: 
-        - 1
         - 0
         - 1
-        version: 1.0.1
+        - 4
+        version: 0.1.4
   type: :runtime
   version_requirements: *id001
 description: Takes a stream to a spreadsheet file and produces and XML representation of its contents
@@ -41,25 +41,31 @@ executables: []
 extensions: []
 
 extra_rdoc_files: 
-- README.rdoc
 - LICENCE
+- README.rdoc
 files: 
-- lib/simple-spreadsheet-extractor.rb
-- jars/lib/poi-ooxml-schemas-3.6.jar
-- jars/lib/poi-3.6.jar
-- jars/lib/xmlbeans-2.3.0.jar
+- .gitignore
+- LICENCE
+- README.rdoc
+- Rakefile
+- VERSION
+- doc/schema-v1.xsd
 - jars/lib/dom4j-1.6.1.jar
+- jars/lib/poi-3.6.jar
 - jars/lib/poi-ooxml-3.6.jar
+- jars/lib/poi-ooxml-schemas-3.6.jar
+- jars/lib/xmlbeans-2.3.0.jar
 - jars/simple-spreadsheet-extractor-0.3.2.jar
-- README.rdoc
-- LICENCE
+- lib/simple-spreadsheet-extractor.rb
+- simple-spreadsheet-extractor.gemspec
+- test/test_extraction.rb
 has_rdoc: true
 homepage: http://github.com/myGrid/simple-spreadsheet-extractor-gem
 licenses: []
 
 post_install_message: 
-rdoc_options: []
-
+rdoc_options: 
+- --charset=UTF-8
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
@@ -87,5 +93,5 @@ rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Basic spreadsheet content extraction using Apache POI
-test_files: []
-
+test_files: 
+- test/test_extraction.rb