Class: Langchain::Processors::Xls

Inherits:
Base
  • Object
show all
Defined in:
lib/langchain/processors/xls.rb

Constant Summary collapse

EXTENSIONS = 
[".xls"].freeze
CONTENT_TYPES = 
["application/vnd.ms-excel"].freeze

Instance Method Summary collapse

Methods included from DependencyHelper

#depends_on

Constructor Details

#initialize ⇒ Xls

Returns a new instance of Xls.



9
10
11
12
 
# File 'lib/langchain/processors/xls.rb', line 9

def initialize(*)
  depends_on "roo"
  depends_on "roo-xls"
end

Instance Method Details

#parse(data) ⇒ Array<Array<String>>

Parse the document and return the text

Parameters:

  • data (File)

Returns:

  • (Array<Array<String>>) —

    Array of rows, each row is an array of cells



17
18
19
20
21
22
23
24
 
# File 'lib/langchain/processors/xls.rb', line 17

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