Files
fil/docs/snippets/ruby/plugins/word_count_processor.md

24 lines
581 B
Markdown
Raw Normal View History

2026-06-01 23:40:55 +02:00
```ruby title="Ruby"
require 'kreuzberg'
class WordCountProcessor
def call(result)
return result if result['content'].empty?
word_count = result['content'].split.length
result['metadata'] ||= {}
result['metadata']['word_count'] = word_count
result
end
end
processor = WordCountProcessor.new
Kreuzberg.register_post_processor('word_count', processor, 10)
config = Kreuzberg::ExtractionConfig.new(
postprocessor: { enabled: true }
)
result = Kreuzberg.extract_file_sync('document.pdf', config: config)
puts "Words: #{result.metadata['word_count']}"
```