From fd566f4ad145bd4ab28b9288679178c39a24436e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Xingchen=20Song=28=E5=AE=8B=E6=98=9F=E8=BE=B0=29?=
 <xingchensong1996@163.com>
Date: Thu, 20 Jun 2024 18:48:19 +0800
Subject: [PATCH] [tn] english, fix crash on "" (#249)

* [tn] english, fix crash on ""

* [tn] english, fix crash on ""
---
 tn/english/normalizer.py            | 34 ++++++++++++++++++++---------
 tn/english/test/data/normalizer.txt |  1 +
 tn/main.py                          |  5 ++---
 3 files changed, 27 insertions(+), 13 deletions(-)

diff --git a/tn/english/normalizer.py b/tn/english/normalizer.py
index 1103fed..d2adbdc 100644
--- a/tn/english/normalizer.py
+++ b/tn/english/normalizer.py
@@ -57,13 +57,21 @@ def build_tagger(self):
         punct = add_weight(Punctuation().tagger, 2.00)
         rang = add_weight(Range().tagger, 1.01)
         # TODO(xcsong): add roman
-        tagger = punct.star + \
-            (cardinal | ordinal | word
-             | date | decimal | fraction
-             | time | measure | money
+        tagger = \
+            (cardinal
+             | ordinal
+             | word
+             | date
+             | decimal
+             | fraction
+             | time
+             | measure
+             | money
              | telephone | electronic
              | whitelist
-             | rang).optimize() + (punct.plus | self.DELETE_SPACE)
+             | rang
+             | punct
+             ).optimize() + (punct.plus | self.DELETE_SPACE)
         # delete the last space
         self.tagger = tagger.star @ self.build_rule(delete(' '), r='[EOS]')
 
@@ -83,14 +91,20 @@ def build_verbalizer(self):
         punct = Punctuation().verbalizer
         rang = Range().verbalizer
         verbalizer = \
-            (cardinal | ordinal | word
-             | date | decimal
-             | fraction | time
-             | measure | money
+            (cardinal
+             | ordinal
+             | word
+             | date
+             | decimal
+             | fraction
+             | time
+             | measure
+             | money
              | telephone
              | electronic
              | whitelist
              | punct
-             | rang).optimize() + (punct.plus | self.INSERT_SPACE)
+             | rang
+             ).optimize() + (punct.plus | self.INSERT_SPACE)
         self.verbalizer = verbalizer.star @ self.build_rule(delete(' '),
                                                             r='[EOS]')
diff --git a/tn/english/test/data/normalizer.txt b/tn/english/test/data/normalizer.txt
index c2b95dc..fc5cc92 100644
--- a/tn/english/test/data/normalizer.txt
+++ b/tn/english/test/data/normalizer.txt
@@ -3,3 +3,4 @@ The National Map, accessed April 1, 2011" Site Description of Koppers Co. From t
 .345" and ".456" "9.456" or 6.7890" => point three four five" and ".four hundred and fifty six" "nine point four five six" or six point seven eight nine oh"
 The museum is open Mon.-Sun. children of 3-4 years 123 The plan will help you lose 3-4 pounds the first week, and 1-2 pounds the weeks thereafter. => The museum is open Monday to Sunday children of three to four years one hundred and twenty three The plan will help you lose three to four pounds the first week, and one to two pounds the weeks thereafter.
 Try searching for 'Toyota' or 'Investment' => Try searching for 'Toyota' or 'Investment'
+"" => ""
diff --git a/tn/main.py b/tn/main.py
index b592ef4..3ca45f1 100644
--- a/tn/main.py
+++ b/tn/main.py
@@ -73,9 +73,8 @@ def main():
             full_to_half=str2bool(args.full_to_half),
             tag_oov=str2bool(args.tag_oov))
     elif args.language == "en":
-        normalizer = EnNormalizer(
-            cache_dir=args.cache_dir,
-            overwrite_cache=args.overwrite_cache)
+        normalizer = EnNormalizer(cache_dir=args.cache_dir,
+                                  overwrite_cache=args.overwrite_cache)
 
     if args.text:
         print(normalizer.tag(args.text))