This commit is contained in:
23
docs/snippets/ruby/plugins/word_count_processor.md
Normal file
23
docs/snippets/ruby/plugins/word_count_processor.md
Normal file
@@ -0,0 +1,23 @@
|
||||
```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']}"
|
||||
```
|
||||
Reference in New Issue
Block a user