simple-spreadsheet-extractor 0.4.2 → 0.5.0

data/README.rdoc

@@ -1,7 +1,7 @@
 = Simple Spreadsheet Extractor
 
-Authors::    Finn Bacall, Stuart Owen
-Version::    0.4.0
+Authors::    Stuart Owen, Finn Bacall
+Version::    0.5.0
 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
@@ -11,6 +11,8 @@ Copyright::  (c) 2010 The University of Manchester, UK
 
 This is a simple gem that provides a facility to read an XLS or XLSX Excel spreadsheet document and produce an XML representation of its content.
 
+CSV output can also be generated for a single sheet.
+
 Internally it uses Apache POI, using the sister http://github.com/myGrid/simple-spreadsheet-extractor tool.
 
 This is a simple tool developed for use within SysMO-DB[http://www.sysmo-db.org].
@@ -29,7 +31,7 @@ Note that on Windows you must also do:
 
 * require 'simple-spreadsheet-extractor'
 * include the module SysMODB::SpreadsheetExtractor
-* pass an IO object to the method spreedsheet_to_xml which responds with the XML for the contents of the sheet.
+* pass an IO object to the method spreedsheet_to_xml which responds with the XML for the contents of the spreadsheet. Alternatively use spreadsheet_to_csv for CSV.
 * if something goes wrong with the extraction then a SysMODB::SpreadsheetExtractionException will be thrown
   
 e.g.
@@ -42,7 +44,7 @@ e.g.
 
    path=ARGV.first
 
-   f=open(path)
+   f=open path
    begin
      puts spreadsheet_to_xml(f)
    rescue SysMODB::SpreadsheetExtractionException=>e
@@ -53,10 +55,20 @@ 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["http://github.com/fbacall/simple-spreadsheet-extractor-gem/blob/master/doc/schema-v1.xsd"]
+An XSD schema for the XML is available in doc/schema-v1.xsd["tree/master/doc/schema-v1.xsd"]
 
 The desired spreadsheet extractor jar can be specified by defining SPREADSHEET_EXTRACTOR_JAR_PATH in a config file (e.g. environment.rb)
 
+CSV can be generated in a similar way, and also takes an optional sheet number. If the sheet number is missing then the first sheet is used.
+
+Note that the sheet number for the first sheet is 1, and can either be a string or integer.
+
+e.g.
+
+   puts spreadsheet_to_csv(f,"1")
+
+
+
 == Example XML
 
   <?xml version="1.0" encoding="UTF-8"?>
@@ -105,4 +117,4 @@ The desired spreadsheet extractor jar can be specified by defining SPREADSHEET_E
     </sheet>
     <sheet name="Sheet2" index="2" hidden="false" very_hidden="false" first_row="1" last_row="1"/>
     <sheet name="Sheet3" index="3" hidden="false" very_hidden="false" first_row="1" last_row="1"/>
-  </workbook>
+  </workbook>

data/VERSION

@@ -1 +1 @@
-0.4.2
+0.5.0

data/lib/simple-spreadsheet-extractor.rb

@@ -10,32 +10,46 @@ module SysMODB
   
   module SpreadsheetExtractor
     
-    DEFAULT_PATH = File.dirname(__FILE__) + "/../jars/simple-spreadsheet-extractor-0.4.1.jar"
+    DEFAULT_PATH = File.dirname(__FILE__) + "/../jars/simple-spreadsheet-extractor-0.5.0.jar"
     
-    def spreadsheet_to_xml spreadsheet_data
-      
-      if RUBY_PLATFORM =~ /mswin32/
-        output = read_with_popen4 spreadsheet_data
+    def spreadsheet_to_xml spreadsheet_data      
+      if is_windows?              
+        read_with_popen4 spreadsheet_data,"xml"
       else        
-        output = read_with_open4 spreadsheet_data
+        read_with_open4 spreadsheet_data,"xml"
+      end
+    end
+
+    def spreadsheet_to_csv spreadsheet_data,sheet=1,trim=false
+      if is_windows?
+        read_with_popen4 spreadsheet_data,"csv",sheet,trim
+      else
+        read_with_open4 spreadsheet_data,"csv",sheet,trim
       end
-      
-      return output
     end
     
     
     
-    def spreadsheet_extractor_command
-      "java -jar #{(defined? SPREADSHEET_EXTRACTOR_JAR_PATH) ? SPREADSHEET_EXTRACTOR_JAR_PATH : DEFAULT_PATH}"
+    def spreadsheet_extractor_command format="xml",sheet=nil,trim=false
+      command = "java -jar #{(defined? SPREADSHEET_EXTRACTOR_JAR_PATH) ? SPREADSHEET_EXTRACTOR_JAR_PATH : DEFAULT_PATH}"
+      command +=  " -o #{format}"
+      command += " -s #{sheet}" if sheet
+      command += " -t" if trim
+      command
     end
     
     private
-    
-    #opens using POpen4 - this is for the benefit of Windows. It has been found to be unstable in Linux and give occaisional segmentation faults
-    def read_with_popen4 spreadsheet_data
+       
+    def is_windows?
+        !(RUBY_PLATFORM =~ /mswin32/ || RUBY_PLATFORM =~ /mingw32/).nil?
+    end        
+
+    #opens using POpen4 - this is for the benefit of Windows. It has been found to be unstable in Linux and give occasional segmentation faults
+    def read_with_popen4 spreadsheet_data,format="xml",sheet=nil,trim=false
       output=""
       err_message = ""
-      status = POpen4::popen4(spreadsheet_extractor_command) do |stdout, stderr, stdin, pid|
+      command = spreadsheet_extractor_command format,sheet,trim
+      status = POpen4::popen4(command) do |stdout, stderr, stdin, pid|
         stdin=stdin.binmode
         spreadsheet_data.each_byte{|b| stdin.putc(b)}
         stdin.close
@@ -49,13 +63,14 @@ module SysMODB
         raise SpreadsheetExtractionException.new(err_message)             
       end
       
-      return output
+      output.strip
     end
     
-    def read_with_open4 spreadsheet_data
+    def read_with_open4 spreadsheet_data,format="xml",sheet=nil,trim=false
       output = ""
       err_message = ""
-      status = Open4::popen4(spreadsheet_extractor_command) do |pid, stdin, stdout, stderr|
+      command = spreadsheet_extractor_command format,sheet,trim      
+      status = Open4::popen4(command) do |pid, stdin, stdout, stderr|
         while ((line = spreadsheet_data.gets) != nil) do        
           stdin << line
         end
@@ -76,7 +91,7 @@ module SysMODB
         raise SpreadsheetExtractionException.new(err_message)             
       end
                   
-      return output
+      output.strip
     end
     
   end

data/simple-spreadsheet-extractor.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{simple-spreadsheet-extractor}
-  s.version = "0.4.2"
+  s.version = "0.5.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Stuart Owen", "Finn Bacall"]
-  s.date = %q{2011-01-18}
+  s.date = %q{2011-03-03}
   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 = [
@@ -24,27 +24,26 @@ Gem::Specification.new do |s|
     "doc/schema-v1.xsd",
     "example.rb",
     "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/poi-3.7.jar",
+    "jars/lib/poi-ooxml-3.7.jar",
+    "jars/lib/poi-ooxml-schemas-3.7.jar",
     "jars/lib/xmlbeans-2.3.0.jar",
-    "jars/simple-spreadsheet-extractor-0.4.1.jar",
+    "jars/simple-spreadsheet-extractor-0.5.0.jar",
     "lib/simple-spreadsheet-extractor.rb",
     "simple-spreadsheet-extractor.gemspec"
   ]
   s.homepage = %q{http://github.com/myGrid/simple-spreadsheet-extractor-gem}
   s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.3.6}
+  s.rubygems_version = %q{1.4.2}
   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::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_runtime_dependency(%q<POpen4>, ["= 0.1.4"])
       s.add_runtime_dependency(%q<open4>, ["= 1.0.1"])
     else

data/test/test_extraction.rb

@@ -40,6 +40,31 @@ class TestExtraction < Test::Unit::TestCase
       assert false,"Error validating against schema: #{e.message}"
     end
   end
+
+  def test_csv_output
+    test_sheet = File.dirname(__FILE__) + "/files/test-spreadsheet.xls"
+    expected_file = File.dirname(__FILE__) + "/files/test-csv-output1.csv"
+    expected = open(expected_file,"rb").read
+    
+    f=open(test_sheet,"rb")
+    csv = spreadsheet_to_csv(f,2)
+    assert_equal expected,csv
+
+    #try sheet as a string
+    f=open(test_sheet,"rb")
+    csv = spreadsheet_to_csv(f,"2")
+    assert_equal expected,csv
+  end
+
+#  def test_csv_output_trimmed
+#    test_sheet = File.dirname(__FILE__) + "/files/test-spreadsheet.xls"
+#    expected_file = File.dirname(__FILE__) + "/files/test-csv-output1-trimmed.csv"
+#    expected = open(expected_file,"rb").read
+#
+#    f=open(test_sheet,"rb")
+#    csv = spreadsheet_to_csv(f,2,true)
+#    assert_equal expected,csv
+#  end
   
   def test_for_segfault  
     test_sheet = File.dirname(__FILE__) + "/files/test-spreadsheet.xls"

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: simple-spreadsheet-extractor
 version: !ruby/object:Gem::Version 
-  prerelease: false
+  hash: 11
+  prerelease: 
   segments: 
   - 0
-  - 4
-  - 2
-  version: 0.4.2
+  - 5
+  - 0
+  version: 0.5.0
 platform: ruby
 authors: 
 - Stuart Owen
@@ -15,16 +16,18 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-01-18 00:00:00 +00:00
+date: 2011-03-03 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: POpen4
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - "="
       - !ruby/object:Gem::Version 
+        hash: 19
         segments: 
         - 0
         - 1
@@ -36,9 +39,11 @@ dependencies:
   name: open4
   prerelease: false
   requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - "="
       - !ruby/object:Gem::Version 
+        hash: 21
         segments: 
         - 1
         - 0
@@ -63,13 +68,14 @@ files:
 - doc/schema-v1.xsd
 - example.rb
 - 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/poi-3.7.jar
+- jars/lib/poi-ooxml-3.7.jar
+- jars/lib/poi-ooxml-schemas-3.7.jar
 - jars/lib/xmlbeans-2.3.0.jar
-- jars/simple-spreadsheet-extractor-0.4.1.jar
+- jars/simple-spreadsheet-extractor-0.5.0.jar
 - 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: []
@@ -80,23 +86,27 @@ rdoc_options: []
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.6
+rubygems_version: 1.4.2
 signing_key: 
 specification_version: 3
 summary: Basic spreadsheet content extraction using Apache POI