documenter 0.0.1 → 0.0.3

data/README.rdoc

@@ -1,17 +1,56 @@
 = documenter
 
-Description goes here.
+Documenter is small collection of scripts to work with different format of documents
+It includes:
+* Odf and Odt classes to fill forms, tables and e.t.c
+* File format convertor based on JodConvertor. To work with it, you need to have open office istalled localy
+* Pdf worker based on pdftk. You should install it too
+* Csv class to work with csv more easely
 
-== Note on Patches/Pull Requests
+== Installation
  
-* Fork the project.
-* Make your feature addition or bug fix.
-* Add tests for it. This is important so I don't break it in a
-  future version unintentionally.
-* Commit, do not mess with rakefile, version, or history.
-  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
-* Send me a pull request. Bonus points for topic branches.
+% gem install documenter
+
+== Example
+
+=== Csv
+
+Load data from file into two demetions array
+data = File.open('test.csv').csv(:cell_split => ';')
+
+Export data to csv file
+data.to_csv(:file => 'myout.csv', :header => ['a','a+100'], :cell_split => ';')
+
+
+=== Convertor
+
+Convertor.convert 'test.xls', 'test.pdf'
+
+=== Pdf
+
+Join files together
+
+Pdf.cat ['a.pdf','b.pdf'], 'output.pdf'
+
+Split pdf to pages
+second parameter - string that would be used as a pattern to save each page
+
+Pdf.burst 'hello.pdf', 'doc/page_%.6d.pdf'
+
+
+#opening existing document
+doc = OdtFile.new 'custom_register.odt'
+#set value of form field
+doc.text.fill_form('number' => 'test')
+#search for table and yield first row copy for each data row
+doc.text.edit_table(:name => 'posts', :data =>posts) do |row, content|
+    #replace form fields
+    row.replace_form(content)
+    #we shoul return row back
+    row
+end
+doc.save  'out.odt'
+#you should use close to delete temporary files
+doc.close
 
-== Copyright
 
-Copyright (c) 2009 A N. See LICENSE for details.

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.0.3

data/documenter.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{documenter}
-  s.version = "0.0.1"
+  s.version = "0.0.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["A N"]
-  s.date = %q{2009-11-30}
+  s.date = %q{2009-12-11}
   s.description = %q{This gem uses OpenOffice and pdftk to convert, split, join, fill and copy files. It may be usefull if you have many documents to work with. It is not realy fast solution and it depend on istalled software}
   s.email = %q{goremika@gmail.com}
   s.extra_rdoc_files = [
@@ -25,7 +25,25 @@ Gem::Specification.new do |s|
      "VERSION",
      "documenter.gemspec",
      "lib/documenter.rb",
+     "lib/documenter/csv.rb",
+     "lib/documenter/ooo.rb",
+     "lib/documenter/ooo/converter.rb",
+     "lib/documenter/ooo/jod/lib/DEPENDENCIES.txt",
+     "lib/documenter/ooo/jod/lib/commons-cli-1.2.jar",
+     "lib/documenter/ooo/jod/lib/commons-io-1.4.jar",
+     "lib/documenter/ooo/jod/lib/jodconverter-2.2.2.jar",
+     "lib/documenter/ooo/jod/lib/jodconverter-cli-2.2.2.jar",
+     "lib/documenter/ooo/jod/lib/juh-3.0.1.jar",
+     "lib/documenter/ooo/jod/lib/jurt-3.0.1.jar",
+     "lib/documenter/ooo/jod/lib/ridl-3.0.1.jar",
+     "lib/documenter/ooo/jod/lib/slf4j-api-1.5.6.jar",
+     "lib/documenter/ooo/jod/lib/slf4j-jdk14-1.5.6.jar",
+     "lib/documenter/ooo/jod/lib/unoil-3.0.1.jar",
+     "lib/documenter/ooo/jod/lib/xstream-1.3.1.jar",
+     "lib/documenter/ooo/odf.rb",
+     "lib/documenter/ooo/odt.rb",
      "lib/documenter/pdf.rb",
+     "lib/documenter/pdftk/pdftk.exe",
      "test/helper.rb",
      "test/test_documenter.rb"
   ]

data/lib/documenter.rb

@@ -1,4 +1,8 @@
 module Documenter
-  require 'documenter/pdf'
+  require File.dirname(__FILE__)+'/documenter/pdf'
+  require File.dirname(__FILE__)+'/documenter/ooo'
+  require File.dirname(__FILE__)+'/documenter/csv'
 end
 
+
+

data/lib/documenter/csv.rb

@@ -0,0 +1,123 @@
+
+class Csv
+  #defaults params
+  @@defaults = {:bracket => '"', :line_break => "\n", :cell_split => ',', :file => 'out.csv'}
+  
+    #save given params[:data] two demetions array to file
+  def self.save params={}
+    params = @@defaults.merge(params)
+    File.open(params[:file],'w') do |f|
+      f.write(params[:title]+params[:line_break]) if params[:title] 
+      f.write array_to_str(params[:header],params)+params[:line_break] if params[:header] 
+      params[:data].each do |row|
+        #you can edit row in given block if you need so
+        if block_given?
+          ar = yield row
+        else
+          ar = row
+        end
+        f.write array_to_str(ar,params)+params[:line_break]
+      end
+    end
+  end
+
+  
+  #converts one demention array to single csv string
+  def self.array_to_str array, params
+    params = @@defaults.merge params
+    array.map{|x| params[:bracket]+x.to_s.gsub(/#{params[:bracket]}/,params[:bracket]+params[:bracket])+params[:bracket]}*params[:cell_split]
+  end
+  
+  #load data from file into table
+  def self.load_table file, params
+    params = @@defaults.merge params
+    bracket = params[:bracket]
+    line_break = params[:line_break]
+    cell_split = params[:cell_split]
+    
+    rows = []
+    cells = []
+    buffer = ''
+    #bracket mode show if we between brackets. If so, we should not react on several things
+    bracket_mode = false
+    prev_bracket = false
+    
+    # we will look at one char at time
+    file.each_byte do |byte|
+      char =  byte.chr
+      #if you see a bracket char
+      if char == bracket
+        #and previus was bracket to
+        if prev_bracket==true
+          #we just save one bracket
+          buffer += char
+          prev_bracket = false
+        else
+          prev_bracket = true
+        end
+        #after the bracket we change mode
+        bracket_mode = !bracket_mode
+      else
+        prev_bracket = false
+        if  !bracket_mode
+          if char == cell_split || char == line_break
+            #we met splitter
+            #in sny way we finishing cell
+            cells << buffer
+            buffer = ''
+            #but if it was a line break
+            if char == line_break
+              #we finish a line to 
+              rows << cells
+              cells = []
+            end        
+          else
+            buffer += char        
+          end
+        else
+          #in brackets mode we just copy data
+          buffer += char        
+        end
+      end
+    end
+    #wen all data finished, we just save what we got in buffers
+    cells << buffer if buffer.size>0
+    rows << cells if cells.size>0
+    rows
+  end
+end
+
+
+class File
+  #Easy loading data from file
+  def csv params
+    Csv.load_table(self, params)
+  end
+end
+
+class String
+  #Easy loading data from string
+  def csv params
+    Csv.load_table(self, params)
+  end
+end
+
+class Array
+  #saving data from array
+  def to_csv params={}
+    params[:data] = self
+    #we can you block t change data defore saving
+    if block_given?
+      Csv.save(params) do |row|
+        yield row
+      end
+    else
+      Csv.save(params)
+    end
+  end
+  
+end
+
+#data = File.open('test.csv').csv(:cell_split => ';')
+#data.to_csv(:file => 'myout.csv', :header => ['a','a+100'], :cell_split => ';')
+

data/lib/documenter/ooo.rb

@@ -0,0 +1,4 @@
+module Ooo
+  require File.dirname(__FILE__)+'/ooo/converter'
+  require File.dirname(__FILE__)+'/ooo/odt'
+end

data/lib/documenter/ooo/converter.rb

@@ -0,0 +1,28 @@
+
+class Converter
+  @@initialized  = false
+  def self.office_path
+    'c:\Program Files\OpenOffice.org 3\program\soffice.exe'
+    #todo - search for installed
+    #todo - check for small portable version
+  end
+  
+    
+  
+  def self.init
+    ooo = office_path
+    system('"'+ooo+' " -headless -accept="socket,port=8100;urp;"')  
+    @@initialized = true
+    #todo - check if already running
+  end
+  
+  
+  def self.convert from, to 
+    init if !@@initialized 
+    system("java -jar #{File.dirname(__FILE__)}/jod/lib/jodconverter-cli-2.2.2.jar #{from} #{to}")
+  end
+end
+
+#Converter.convert 'test.csv', 'text.xls'
+
+

data/lib/documenter/ooo/jod/lib/DEPENDENCIES.txt

@@ -0,0 +1,17 @@
+To use the library in your own Java app you need
+
+ * commons-io
+ * jodconverter
+ * juh
+ * jurt
+ * ridl
+ * slf4j-api
+ * slf4j-jdk14 or another slf4j implementation - see http://slf4j.org
+ * unoil
+ * xstream - only if you use XmlDocumentFormatRegistry
+
+The command line interface additionally requires
+
+ * commons-cli
+ * jodconverter-cli
+

data/lib/documenter/ooo/odf.rb

@@ -0,0 +1,42 @@
+require 'zip/zip'
+
+class OdfFile
+  
+  def random_name 
+		Time.now.strftime('%H%M%S')+rand(100000).to_s
+	end
+  
+	def initialize filename
+		#working with copy 
+		rn = random_name
+		@file = random_name+'tmp.odf'
+		@content = random_name+'tmp.xml'
+		
+		File.copy filename, @file
+		zip  = Zip::ZipFile.open(@file)
+		zip.extract('content.xml',@content)	
+	end
+	
+	def load_xml
+		File.read(@content)
+	end
+	
+	def save_xml xml
+		File.open(@content,'w') do |f|
+			f.write xml
+		end
+	end
+	
+	def close
+		File.delete @content
+		File.delete @file
+	end
+		
+	def save filename
+		zip  = Zip::ZipFile.open(@file) 
+    puts "just before saving"
+		zip.replace('content.xml',@content)
+		zip.close
+    File.copy @file, filename
+	end
+end

data/lib/documenter/ooo/odt.rb

@@ -0,0 +1,133 @@
+require File.dirname(__FILE__)+'/odf.rb'
+require 'hpricot'
+
+class OdtText 
+  attr_accessor :xml
+  
+  def initialize xml
+		@xml = Hpricot.parse(xml)
+	end
+
+  def fill_form  data 
+		(@xml/'text:user-field-decl').each do |decl|
+			name = decl['text:name']
+			decl['office:string-value']  = data[name] if data[name]
+		end
+		@xml
+	end
+	
+	def replace_form data
+		(@xml/'text:user-field-get').each do |decl|
+			name = decl['text:name']
+			if data && data[name]
+				parent_html = decl.parent.inner_html 
+        decl.parent.inner_html = parent_html.gsub(/#{decl.to_html}/,"#{data[name].to_s}")
+			end
+		end
+    puts @xml
+		@xml
+	end
+		
+		
+	def  find_table name
+	end
+	
+		
+	def rename_table oldname, newname
+	end
+	
+  def to_html
+    @xml.to_html
+  end
+  
+  def to_xml
+    @xml.to_html
+  end
+  
+		
+	def edit_table params
+		@name = params[:name]
+		@rows = params[:data]
+		raise 'cannot edit table rows without datarows' if !@rows || @rows.size==0
+		@start_row = (params[:no_header]) ? 0 : 1
+    
+    table = nil
+		@xml.search("table:table").each {|t| table = t if t['table:name'] == @name }
+    raise "no such table '#{@name.to_s}'" if !table
+    
+    table['table:name'] = params[:new_name] if params[:new_name]
+    puts table
+    row =  (table/'table:table-row')[@start_row]
+		template = row.to_html
+		row.inner_html=''
+    
+		@rows.each do |row|
+      puts 'inside'
+      table.inner_html += (yield OdtText.new(template), row).to_html
+		end
+    
+    #puts @xml
+  end
+	
+	def fill_table params
+		edit_table_rows(params) do |row, row_date|
+			row.replace_form(row_data)
+		end
+	end
+	
+end
+
+class OdtFile < OdfFile
+  attr_accessor :text
+  
+  def initialize filename
+    super
+    load
+  end
+  
+  
+  def load
+    @text = OdtText.new(load_xml)
+  end
+  
+  def save_changes
+    save_xml @text.to_xml
+  end
+  
+  
+  def save filename
+    save_changes
+    name, extention = filename.split('.')
+    extention = 'odt' if !extention 
+    raise "Wrong extention #{extention} for odt file" if extention != 'odt'
+    filename = "#{name}.#{extention}"
+    super filename
+  end
+  
+end
+
+
+=begin
+
+
+ posts = [{'posts' => 'asdasdasd'}, {'posts' => 'adfasdfasdf'}, {'posts' => 'asdfasf'}]
+ packets = [{'t' => 'qweerty'}, {'t' => 'qwerty'}]
+  
+i =0 
+	doc = OdtFile.new 'custom_register.odt'
+  doc.text.fill_form('number' => 'test')
+  doc.text.edit_table(:name => 'posts', :data =>posts) do |row, content|
+    row.replace_form(content)
+    row.edit_table(:name => 'packets', :new_name => 'packets'+i.to_s, :data => packets) do  |row2,content|
+      row2.replace_form(content)
+      i += 1
+      row2
+    end
+    row
+	end
+	
+	doc.save  'out.odt'
+	doc.close
+
+
+=end

data/lib/documenter/pdf.rb

@@ -1,16 +1,24 @@
+require 'ftools'
+
+
 class Pdf
+  # pass to localy installed pdftk
+  @@exe = File.dirname(__FILE__)+'/pdftk/pdftk.exe'
   
-  def self.is_windows?
-    processor, platform, *rest = RUBY_PLATFORM.split("-")
-    platform == 'mswin32'
+  #join array of pdfs filenames to one output file
+  def self.cat pdfs, output
+    system("#{@@exe} #{pdfs*' '} cat output #{output} compress dont_ask ")
   end
-
   
-  def self.join array_of_pdfs, output, extras = 'compress'
-    if is_windows?
-      system("pdftk/pdftk.exe #{array_of_pdfs*' '} cat output #{output} #{extras} dont_ask ")
-    else
-      raise "Currently only windows supported"
+  #cut file to single pages
+  def self.burst file, pattern
+    system("#{@@exe} #{file} burst")
+    Dir.new(".").each do |file|
+      if (file =~ /pg_[0-9]*\.pdf/)
+        number = file.match(/[0-9]{4}/)[0].to_i
+        new_file = pattern % number
+        File.move  file, new_file
+      end
     end
   end
-end
+end

data/test/test_documenter.rb

@@ -1,7 +1,13 @@
 require 'helper'
 
+#some integration style tests :)
 class TestDocumenter < Test::Unit::TestCase
-  should "probably rename this file and start testing for real" do
-    flunk "hey buddy, you should probably rename this file and start testing for real"
+  should "get to diff files and join then to one" do
+    data = [['a0','b0'],['a1','b1']]
+    data.to_csv(:file => 'myout.csv', :header => ['a','b'])
+    Converter.convert 'myout.csv', 'test1.pdf'
+    
   end
+  
+    
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: documenter
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
+  version: 0.0.3
 platform: ruby
 authors: 
 - A N
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-11-30 00:00:00 +03:00
+date: 2009-12-11 00:00:00 +03:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -60,7 +60,25 @@ files:
 - VERSION
 - documenter.gemspec
 - lib/documenter.rb
+- lib/documenter/csv.rb
+- lib/documenter/ooo.rb
+- lib/documenter/ooo/converter.rb
+- lib/documenter/ooo/jod/lib/DEPENDENCIES.txt
+- lib/documenter/ooo/jod/lib/commons-cli-1.2.jar
+- lib/documenter/ooo/jod/lib/commons-io-1.4.jar
+- lib/documenter/ooo/jod/lib/jodconverter-2.2.2.jar
+- lib/documenter/ooo/jod/lib/jodconverter-cli-2.2.2.jar
+- lib/documenter/ooo/jod/lib/juh-3.0.1.jar
+- lib/documenter/ooo/jod/lib/jurt-3.0.1.jar
+- lib/documenter/ooo/jod/lib/ridl-3.0.1.jar
+- lib/documenter/ooo/jod/lib/slf4j-api-1.5.6.jar
+- lib/documenter/ooo/jod/lib/slf4j-jdk14-1.5.6.jar
+- lib/documenter/ooo/jod/lib/unoil-3.0.1.jar
+- lib/documenter/ooo/jod/lib/xstream-1.3.1.jar
+- lib/documenter/ooo/odf.rb
+- lib/documenter/ooo/odt.rb
 - lib/documenter/pdf.rb
+- lib/documenter/pdftk/pdftk.exe
 - test/helper.rb
 - test/test_documenter.rb
 has_rdoc: true