dullard 0.0.3 → 0.0.5

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 76b6de08a6a72d691a3f3deb06f8a82018c90049
+  data.tar.gz: d56a5c10a24db975ce01c0e3e352739e128508f1
+SHA512:
+  metadata.gz: 943f8b15089aab39fb627fc84a45523e093b60e6980666cb139be7102d99bb2adf3f71a2ed32d5d693784d4612199390de7a62e7dd06de4d80495a7de832ccbc
+  data.tar.gz: 3402538efd1a687823a4acc8e4a9fe811d381de1e20d40d354746cacb2e2ff557b6eb6259c5446f05b89375c61cb81efe0516fdc7cf26ec22800ed92325c45eb

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2012 Edward Kaplan
+Copyright (c) 2013 Edward Kaplan
 
 MIT License
 
@@ -19,4 +19,4 @@ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
 LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
 OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
-WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -1,8 +1,11 @@
-Super simple, super fast XLSX parsing.
+Super simple, super fast stream-based XLSX parsing.  Suitable for very large
+files.
+
+Requires Ruby 2.0.
 
     require 'dullard' 
 
-    workbook = Dullard::Workbook.new "file"
-    workbook.sheet[0].rows.each do |row|
+    workbook = Dullard::Workbook.new "file.xlsx"
+    workbook.sheets[0].rows.each do |row|
       puts row # => ["a","b","c",...]
     end

data/lib/dullard/reader.rb

@@ -11,7 +11,7 @@ class Dullard::Workbook
 
   def sheets
     workbook = Nokogiri::XML::Document.parse(@zipfs.file.open("xl/workbook.xml"))
-    @sheets = workbook.css("sheet").map {|n| Dullard::Sheet.new(self, n.attr("name"), n.attr("sheetId")) }
+    @sheets = workbook.css("sheet").each_with_index.map {|n,i| Dullard::Sheet.new(self, n.attr("name"), n.attr("sheetId"), i+1) }
   end
 
   def string_table
@@ -44,10 +44,12 @@ end
 
 class Dullard::Sheet
   attr_reader :name, :workbook
-  def initialize(workbook, name, id)
+  def initialize(workbook, name, id, index)
     @workbook = workbook
     @name = name
     @id = id
+    @index = index
+    @file = @workbook.zipfs.file.open(path) if @workbook.zipfs.file.exist?(path)
   end
 
   def string_lookup(i)
@@ -55,21 +57,84 @@ class Dullard::Sheet
   end
 
   def rows
-    Enumerator.new do |y|
+    Enumerator.new(rows_size) do |y|
+      next unless @file
+      @file.rewind
       shared = false
       row = nil
-      Nokogiri::XML::Reader(@workbook.zipfs.file.open("xl/worksheets/sheet#{@id}.xml")).each do |node|
-        if node.name == "row" and node.node_type == Nokogiri::XML::Reader::TYPE_ELEMENT
-          row = []
-        elsif node.name == "row" and node.node_type == Nokogiri::XML::Reader::TYPE_END_ELEMENT
-          y << row
-        elsif node.name == "c" and node.node_type == Nokogiri::XML::Reader::TYPE_ELEMENT
+      column = nil
+      Nokogiri::XML::Reader(@file).each do |node|
+        case node.node_type
+        when Nokogiri::XML::Reader::TYPE_ELEMENT
+          case node.name
+          when "row"
+            row = []
+            column = 0
+            next
+          when "c"
+            rcolumn = node.attributes["r"]
+            if rcolumn
+              rcolumn.delete!("0-9")
+              while column < self.class.column_names.size and rcolumn != self.class.column_names[column]
+                row << nil
+                column += 1
+              end
+            end
             shared = (node.attribute("t") == "s")
-        elsif node.value?
-            row << (shared ? string_lookup(node.value.to_i) : node.value)
+            column += 1
+            next
+          end
+        when Nokogiri::XML::Reader::TYPE_END_ELEMENT
+          if node.name == "row"
+            y << row
+            next
+          end
+        end
+        value = node.value
+        if value
+          row << (shared ? string_lookup(value.to_i) : value)
         end
       end
     end
   end
-end
 
+  # Returns A to ZZZ.
+  def self.column_names
+    if @column_names
+      @column_names
+    else
+      proc = Proc.new do |prev|
+        ("#{prev}A".."#{prev}Z").to_a
+      end
+      x = proc.call("")
+      y = x.map(&proc).flatten
+      z = y.map(&proc).flatten
+      @column_names = x + y + z
+    end
+  end
+
+  private
+  def path
+    "xl/worksheets/sheet#{@index}.xml"
+  end
+
+  def rows_size
+    if defined? @rows_size
+      @rows_size
+    elsif @file
+      @file.rewind
+      Nokogiri::XML::Reader(@file).each do |node|
+        if node.node_type == Nokogiri::XML::Reader::TYPE_ELEMENT
+          case node.name
+          when "dimension"
+            if ref = node.attributes["ref"]
+              break @rows_size = ref.scan(/\d+$/).first.to_i
+            end
+          when "sheetData"
+            break @rows_size = nil
+          end
+        end
+      end
+    end
+  end
+end

data/lib/dullard/version.rb

@@ -1,3 +1,3 @@
 module Dullard
-  VERSION = "0.0.3"
+  VERSION = "0.0.5"
 end

data/specs/dullard_spec.rb

@@ -2,7 +2,7 @@ require 'dullard'
 
 describe "dullard" do
   before(:each) do
-    @file = File.open("testfiles/SHAPE5_CorePrePost.xlsx")
+    @file = File.open(File.expand_path("../test.xlsx", __FILE__))
     @xlsx = Dullard::Workbook.new @file
   end
   it "can open a file" do
@@ -10,19 +10,25 @@ describe "dullard" do
   end
 
   it "can find sheets" do
-    @xlsx.sheets.count.should == 3
+    @xlsx.sheets.count.should == 1
   end
 
-  it "can read rows" do
-    @xlsx.sheets[0].rows.first.should == ["S.NO",	"PAPER ID",	"TOPIC", "AUTHOR DETAILS", "DATE OF PRESENTATION"]
+  it "reads the right number of columns, even with blanks" do
+    rows = @xlsx.sheets[0].rows
+    rows.next.count.should == 300
+    rows.next.count.should == 9
+    rows.next.count.should == 1
   end
 
   it "reads the right number of rows" do
     count = 0
     @xlsx.sheets[0].rows.each do |row|
-      puts row
       count += 1
     end
     count.should == 115
   end
+
+  it "reads the right number of rows from the metadata when present" do
+    @xlsx.sheets[0].rows.size.should == 115
+  end
 end

metadata

@@ -1,49 +1,57 @@
 --- !ruby/object:Gem::Specification
 name: dullard
 version: !ruby/object:Gem::Version
-  version: 0.0.3
-  prerelease: 
+  version: 0.0.5
 platform: ruby
 authors:
 - Ted Kaplan
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-24 00:00:00.000000000 Z
+date: 2013-07-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70311325924940 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *70311325924940
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.6'
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &70311325924440 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: '1.5'
   type: :runtime
   prerelease: false
-  version_requirements: *70311325924440
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
 - !ruby/object:Gem::Dependency
   name: rubyzip
-  requirement: &70311325923940 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: 0.9.6
   type: :runtime
   prerelease: false
-  version_requirements: *70311325923940
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.9.6
 description: 
 email:
 - ted@shlashdot.org
@@ -61,28 +69,28 @@ files:
 - lib/dullard/reader.rb
 - lib/dullard/version.rb
 - specs/dullard_spec.rb
+- specs/test.xlsx
 homepage: http://github.com/thirtyseven/dullard
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.17
+rubygems_version: 2.0.5
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A fast XLSX parser using Nokogiri
 test_files: []