simple-spreadsheet-extractor 0.16.1 → 0.17.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 2b5cbc7c8d64f1bddf52010333ab4f3133beae3f
-  data.tar.gz: 7a476ed21f5a07a750d8dbe56dcc8f3c8984e3b7
+SHA256:
+  metadata.gz: 8d5351032c2b34dfcce4bed0469415ab1b98e8f11f305d8e76bca707ed2554e1
+  data.tar.gz: 01d1abb6c2f8a025ab489f1a83e9b9c627bbc67f151fb3ace3968175b4c69cb2
 SHA512:
-  metadata.gz: 7e7104b1f357c3bd5e8086c4c285dd6d353df0282b30baf2ea96848df98b3a0f64a6d9337c39f9690ed0fbef12e1dbc13c3db251b9cc80aae69a81dff832e210
-  data.tar.gz: 3b6d98271565b991e47178b5e2e384a5afbdcb2c1b7c3ec2ea91e6798ae5512c83c6d648ed279526cc1a00f3387d2a25317880b1d0c6e1a6a3e093d8cc01870f
+  metadata.gz: 29bea0ec37798888a1e414ed947015c8c991450e8e017b0f4dde822c88ce5ceea32197cd3c93b5f8886bc704be2946c82edb9c7410235f17c53150509485e846
+  data.tar.gz: aad58ac8c66c8091ae3d9f1d05366c889727cc3f07981d2c9841a02e25dfc289060c57327d6d79b087ae9df8685ecf98ce3f63a9b1ea23300b5c870114802515

data/.ruby-version

@@ -1 +1 @@
-ruby-2.2.8
+ruby-2.7.6

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2014, The University of Manchester, UK.
+Copyright (c) 2010-2022, The University of Manchester, UK.
 
 All rights reserved.
 

data/README.rdoc

@@ -1,7 +1,7 @@
 = Simple Spreadsheet Extractor
 
 Authors::    Stuart Owen, Finn Bacall
-Version::    0.15.0
+Version::    0.17.0
 Contact::    mailto:stuart.owen@manchester.ac.uk
 Licence::    BSD (See LICENCE or http://www.opensource.org/licenses/bsd-license.php)
 Copyright::  (c) 2010-2015 The University of Manchester, UK
@@ -23,7 +23,7 @@ This is a simple tool developed for use within SysMO-DB[http://www.sysmo-db.org]
 
 == Installation
 
-Java 1.7 (JRE) is required.
+Java 8 or above (JRE) is required.
 
   gem install simple-spreadsheet-extractor
 
@@ -34,6 +34,7 @@ Java 1.7 (JRE) is required.
 * 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 spreadsheet. Alternatively use spreadsheet_to_csv for CSV.
+  * you can now also pass in the filepath to the Excel file instead of an IO object
 * if something goes wrong with the extraction then a SysMODB::SpreadsheetExtractionException will be thrown
 * by default the JVM is allocated 512M of memory, you can override this by passing a string as the last argument. This will be passed to -Xmx in the java command.
   

data/lib/simple-spreadsheet-extractor.rb

@@ -1 +1,3 @@
+# frozen_string_literal: true
+
 require 'sysmodb/simple-spreadsheet-extractor'

data/lib/sysmodb/extractor.rb

@@ -1,38 +1,49 @@
-require 'open4'
+require 'terrapin'
 
 module SysMODB
-  #Exception that is thrown when a problem occurs during the extraction
+  # Exception that is thrown when a problem occurs during the extraction
   class SpreadsheetExtractionException < Exception; end
 
-  #handles the delegation to java, and executes the extraction passing the
-  #input file through STDIN, and reading the results through STDOUT.
+  # handles the delegation to java
   class Extractor
-    JAR_VERSION="0.16.0".freeze
+    JAR_VERSION = '0.16.0'.freeze
     DEFAULT_PATH = File.dirname(__FILE__) + "/../../jars/simple-spreadsheet-extractor-#{JAR_VERSION}.jar"
-    BUFFER_SIZE=250000 # 1/4 a megabyte
 
     def initialize(memory_allocation)
       @memory_allocation = memory_allocation
-      if is_windows?
-        raise Exception.new("Windows is not currently supported")
-      end
+      raise Exception, 'Windows is not currently supported' if is_windows?
     end
 
+    # spreadsheet_data can be an IO like object or the path to a file
     def spreadsheet_to_xml(spreadsheet_data)
-      read_with_open4 spreadsheet_data,"xml"
+      spreadsheet_to_requested_format(spreadsheet_data, 'xml')
     end
 
-    def spreadsheet_to_csv(spreadsheet_data,sheet=1,trim=false)
-      read_with_open4 spreadsheet_data,"csv",sheet,trim
+    # spreadsheet_data can be an IO like object or the path to a file
+    def spreadsheet_to_csv(spreadsheet_data, sheet = 1, trim = false)
+      spreadsheet_to_requested_format(spreadsheet_data, 'csv', sheet, trim)
     end
 
     private
 
-    def spreadsheet_extractor_command(format="xml",sheet=nil,trim=false)
+    def spreadsheet_to_requested_format(spreadsheet_data, format, sheet = nil, trim = nil)
+      if spreadsheet_data.is_a?(IO) || spreadsheet_data.is_a?(StringIO)
+        Tempfile.create('spreadsheet-extraction') do |f|
+          f.write(spreadsheet_data.read)
+          f.flush
+          execute_command_line f.path, format, sheet, trim
+        end
+      elsif spreadsheet_data.is_a?(String)
+        execute_command_line spreadsheet_data, format, sheet, trim
+      end
+    end
+
+    def spreadsheet_extractor_command(filepath, format = 'xml', sheet = nil, trim = false)
       command = "java -Xmx#{@memory_allocation} -jar #{(defined? SPREADSHEET_EXTRACTOR_JAR_PATH) ? SPREADSHEET_EXTRACTOR_JAR_PATH : DEFAULT_PATH}"
-      command +=  " -o #{format}"
+      command += " -o #{format}"
       command += " -s #{sheet}" if sheet
-      command += " -t" if trim
+      command += ' -t' if trim
+      command += " < #{filepath}"
       command
     end
 
@@ -40,32 +51,14 @@ module SysMODB
       !(RUBY_PLATFORM =~ /mswin32/ || RUBY_PLATFORM =~ /mingw32/).nil?
     end
 
-    def read_with_open4(spreadsheet_data,format="xml",sheet=nil,trim=false)
-      output = ""
-      err_message = ""
-      command = spreadsheet_extractor_command format,sheet,trim
-      status = Open4.popen4(command) do |_pid, stdin, stdout, stderr|
-        while ((line = spreadsheet_data.gets(BUFFER_SIZE)) != nil) do
-          stdin << line
-        end
-        stdin.close
-
-        while ((line = stdout.gets(BUFFER_SIZE)) != nil) do
-          output << line
-        end
-        stdout.close
-
-        until ((line=stderr.gets((BUFFER_SIZE))).nil?) do
-          err_message << line
-        end
-        stderr.close
+    def execute_command_line(filepath, format = 'xml', sheet = nil, trim = false)
+      command = spreadsheet_extractor_command filepath, format, sheet, trim
+      begin
+        Terrapin::CommandLine.new(command).run.strip
+      rescue Terrapin::ExitStatusError, Terrapin::CommandNotFoundError => e
+        raise SpreadsheetExtractionException, e.message
       end
-
-      if status.to_i != 0
-        raise SpreadsheetExtractionException.new(err_message)
-      end
-
-      output.strip
     end
+
   end
 end

data/lib/sysmodb/simple-spreadsheet-extractor.rb

@@ -1,4 +1,3 @@
-
 require 'sysmodb/extractor'
 
 module SysMODB
@@ -8,12 +7,11 @@ module SysMODB
   #   simple_spreadsheet_to_xml to extract to an xml format (see README and schema in doc/schema-v1.xsd)
   #   simple_spreadhseet_to_csv to extract to CSV format for a single sheet
   module SpreadsheetExtractor
-
     # :call-seq:
     #   spreadsheet_to_xml(spreadsheet_data) -> String
     #   spreadsheet_to_xml(spreadsheet_data, memory_allocation) -> String
     #
-    # reads the incoming data from an IO object and returns the generated XML.
+    # reads the incoming data from an IO object or path to a file and returns the generated XML.
     # it is extracted using java, and the default memory allocation is 512M (passed to -Xmx) this can
     # be changed by passing an option final parameter memory_allocation
     def spreadsheet_to_xml(spreadsheet_data, memory_allocation = DEFAULT_MEMORY_ALLOCATION)
@@ -26,7 +24,7 @@ module SysMODB
     #   spreadsheet_to_csv(spreadsheet_data, sheet, trim) -> String
     #   spreadsheet_to_csv(spreadsheet_data, sheet, trim, memory_allocation) -> String
     #
-    # reads the incoming data from an IO object and returns the generated CSV.
+    # reads the incoming data from an IO object or path to a file and returns the generated CSV.
     # only 1 sheet is processed, which by default it the first sheet.
     # if trim is set to true, proceeding or trailing cells will be removed whilst keeping the csv uniform.
     # it is extracted using java, and the default memory allocation is 512M (passed to -Xmx) this can

data/lib/sysmodb/version.rb

@@ -1,4 +1,3 @@
 module SysMODB
-  VERSION = "0.16.1".freeze
-
+  VERSION = '0.17.0'.freeze
 end

data/simple-spreadsheet-extractor.gemspec

@@ -19,12 +19,13 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_dependency('libxml-ruby', ['~> 2.8'])
-  spec.add_dependency('open4', ['1.3.0'])
+  spec.add_dependency('libxml-ruby', '~> 2.9')
+  spec.add_dependency('terrapin', '~> 0.6')
 
-  spec.add_development_dependency('rubocop', ['~> 0.48'])
-  spec.add_development_dependency('rubycritic', ['~> 3.2'])
-  spec.add_development_dependency 'bundler', '~> 1.16'
-  spec.add_development_dependency 'rake', '~> 10.0'
-  spec.add_development_dependency 'minitest', '~> 5.0'
+  spec.add_development_dependency('rubocop','~> 1.25')
+  spec.add_development_dependency('rubycritic')
+  spec.add_development_dependency('bundler','~> 2.3')
+
+  spec.add_development_dependency('rake')
+  spec.add_development_dependency('minitest','~>5.14')
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: simple-spreadsheet-extractor
 version: !ruby/object:Gem::Version
-  version: 0.16.1
+  version: 0.17.0
 platform: ruby
 authors:
 - Stuart Owen
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-05-10 00:00:00.000000000 Z
+date: 2022-12-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libxml-ruby
@@ -18,98 +18,98 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.8'
+        version: '2.9'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.8'
+        version: '2.9'
 - !ruby/object:Gem::Dependency
-  name: open4
+  name: terrapin
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.3.0
+        version: '0.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.3.0
+        version: '0.6'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.48'
+        version: '1.25'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.48'
+        version: '1.25'
 - !ruby/object:Gem::Dependency
   name: rubycritic
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: '2.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: '2.3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '5.14'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '5.14'
 description: Takes a stream to a spreadsheet file and produces an XML or CSV representation
   of its contents
 email:
@@ -126,7 +126,6 @@ files:
 - LICENSE
 - README.rdoc
 - Rakefile
-- VERSION
 - doc/schema-v1.xsd
 - examples/example.rb
 - jars/lib/commons-codec-1.10.jar
@@ -165,8 +164,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.13
+rubygems_version: 3.3.26
 signing_key: 
 specification_version: 4
 summary: Basic spreadsheet content extraction using Apache POI

data/VERSION

@@ -1 +0,0 @@
-0.15.2