mirror of
https://github.com/gsi-upm/senpy
synced 2024-11-14 04:32:29 +00:00
Change name to split, according to issue #37
This commit is contained in:
parent
f8ca595bc9
commit
83e2d415a1
@ -3,12 +3,12 @@ from senpy.models import Entry
|
||||
from nltk.tokenize.punkt import PunktSentenceTokenizer
|
||||
from nltk.tokenize.simple import LineTokenizer
|
||||
import nltk
|
||||
class ChunkerPlugin(AnalysisPlugin):
|
||||
class SplitPlugin(AnalysisPlugin):
|
||||
def activate(self):
|
||||
nltk.download('punkt')
|
||||
|
||||
def analyse_entry(self, entry, params):
|
||||
chunker_type = params.get("type", "sentence")
|
||||
chunker_type = params.get("delimiter", "sentence")
|
||||
original_id = entry.id
|
||||
original_text = entry.get("text", None)
|
||||
if chunker_type == "sentence":
|
@ -1,13 +1,13 @@
|
||||
---
|
||||
name: chunker
|
||||
module: chunker
|
||||
name: split
|
||||
module: split
|
||||
description: A sample plugin that chunks input text
|
||||
author: "@militarpancho"
|
||||
version: '0.1'
|
||||
url: "https://github.com/gsi-upm/senpy"
|
||||
requirements: {nltk}
|
||||
extra_params:
|
||||
type:
|
||||
delimiter:
|
||||
aliases:
|
||||
- type
|
||||
- t
|
Loading…
Reference in New Issue
Block a user