Add support for .xls (Excel 1997-2004)

Gemfile.lock

@@ -336,6 +336,10 @@ GEM
     roo (2.10.1)
       nokogiri (~> 1)
       rubyzip (>= 1.3.0, < 3.0.0)
+    roo-xls (1.2.0)
+      nokogiri
+      roo (>= 2.0.0, < 3)
+      spreadsheet (> 0.9.0)
     rspec (3.13.0)
       rspec-core (~> 3.13.0)
       rspec-expectations (~> 3.13.0)
@@ -374,6 +378,7 @@ GEM
     ruby-next-core (1.0.1)
     ruby-next-parser (3.2.2.0)
       parser (>= 3.0.3.1)
+    ruby-ole (1.2.13.1)
     ruby-openai (6.4.0)
       event_stream_parser (>= 0.3.0, < 2.0.0)
       faraday (>= 1)
@@ -389,6 +394,9 @@ GEM
       faraday (>= 0.17.5, < 3.a)
       jwt (>= 1.5, < 3.0)
       multi_json (~> 1.10)
+    spreadsheet (1.3.1)
+      bigdecimal
+      ruby-ole
     standard (1.34.0)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.0)
@@ -488,6 +496,7 @@ DEPENDENCIES
   rdiscount (~> 2.2.7)
   replicate-ruby (~> 0.2.2)
   roo (~> 2.10.0)
+  roo-xls (~> 1.2.0)
   rspec (~> 3.0)
   rubocop
   ruby-openai (~> 6.4.0)

langchain.gemspec

@@ -73,6 +73,7 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "replicate-ruby", "~> 0.2.2"
   spec.add_development_dependency "qdrant-ruby", "~> 0.9.4"
   spec.add_development_dependency "roo", "~> 2.10.0"
+  spec.add_development_dependency "roo-xls", "~> 1.2.0"
   spec.add_development_dependency "ruby-openai", "~> 6.4.0"
   spec.add_development_dependency "safe_ruby", "~> 1.0.4"
   spec.add_development_dependency "sequel", "~> 5.68.0"

lib/langchain/processors/xls.rb

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+module Langchain
+  module Processors
+    class Xls < Base
+      EXTENSIONS = [".xls"].freeze
+      CONTENT_TYPES = ["application/vnd.ms-excel"].freeze
+
+      def initialize(*)
+        depends_on "roo"
+        depends_on "roo-xls"
+      end
+
+      # Parse the document and return the text
+      # @param [File] data
+      # @return [Array<Array<String>>] Array of rows, each row is an array of cells
+      def parse(data)
+        xls_file = Roo::Spreadsheet.open(data)
+        xls_file.each_with_pagename.flat_map do |_, sheet|
+          sheet.map do |row|
+            row.map { |i| i.to_s.strip }
+          end
+        end
+      end
+    end
+  end
+end

spec/langchain/processors/xls_spec.rb

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+RSpec.describe Langchain::Processors::Xls do
+  describe "#parse" do
+    let(:file) { File.open("spec/fixtures/loaders/sample.xls") }
+    let(:data) {
+      [
+        ["Username", "Identifier", "First name", "Last name"],
+        ["booker12", "9012", "Rachel", "Booker"],
+        ["grey07", "2070", "Laura", "Grey"],
+        ["johnson81", "4081", "Craig", "Johnson"],
+        ["jenkins46", "9346", "Mary", "Jenkins"],
+        ["smith79", "5079", "Jamie", "Smith"],
+
+        ["FirstName", "LastName", "Street", "Town", "ZIP"],
+        ["John", "Doe", "120 jefferson st.", "Riverside", "8075"],
+        ["Jack", "McGinnis", "220 hobo Av.", "Phila", "9119"],
+        ['John "Da Man"', "Repici", "120 Jefferson St.", "Riverside", "8075"],
+        ["Stephen", "Tyler", '7452 Terrace "At the Plaza" road', "SomeTown", "91234"],
+        ["", "Blankman", "", "SomeTown", "298"],
+        ['Joan "the bone", Anne', "Jet", "9th, at Terrace plc", "Desert City", "123"]
+      ]
+    }
+
+    it "parses the file and returns the text" do
+      expect(described_class.new.parse(file)).to eq(data)
+    end
+  end
+end