| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152 |
- import pynini
- from fun_text_processing.text_normalization.en.graph_utils import (
- DAMO_NOT_QUOTE,
- GraphFst,
- delete_extra_space,
- delete_space,
- insert_space,
- )
- from pynini.lib import pynutil
- class DateFst(GraphFst):
- """
- Finite state transducer for verbalizing date, e.g.
- date { day: "1" month: "enero" preserve_order: true } -> 1 de enero
- """
- def __init__(self):
- super().__init__(name="date", kind="verbalize")
- month = (
- pynutil.delete("month:")
- + delete_space
- + pynutil.delete("\"")
- + pynini.closure(DAMO_NOT_QUOTE, 1)
- + pynutil.delete("\"")
- )
- day = (
- pynutil.delete("day:")
- + delete_space
- + pynutil.delete("\"")
- + pynini.closure(DAMO_NOT_QUOTE, 1)
- + pynutil.delete("\"")
- )
- # day month
- graph_dm = day + delete_extra_space + pynutil.insert("de") + insert_space + month
- optional_preserve_order = pynini.closure(
- pynutil.delete("preserve_order:") + delete_space + pynutil.delete("true") + delete_space
- | pynutil.delete("field_order:")
- + delete_space
- + pynutil.delete("\"")
- + DAMO_NOT_QUOTE
- + pynutil.delete("\"")
- + delete_space
- )
- final_graph = graph_dm + delete_space + optional_preserve_order
- delete_tokens = self.delete_tokens(final_graph)
- self.fst = delete_tokens.optimize()
|