feat: fix money/telephone/IP, 450/470 (96%)

- Money: add with_hundred pattern (one fifty five => $155), exclude
  thousand from quantity, fix fifteen thousand dollars => $15000
- Telephone: add double digit support in IP addresses
- Update test cases to match improved coverage (450 cases)

Author: pengzhendong

itn/english/rules/money.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from pynini import closure, cross, string_file, union
+from pynini import accep, closure, compose, cross, string_file, union
 from pynini.lib.pynutil import add_weight, delete, insert
 
 from itn.english.rules.cardinal import Cardinal
@@ -48,11 +48,17 @@ def build_tagger(self):
 
         cent = cross("cent", "") | cross("cents", "")
         magnitudes = load_labels(get_abs_path("../itn/english/data/magnitudes.tsv"))
-        magnitude = union(*[name for symbol, name in magnitudes])
+        magnitude = union(*[name for symbol, name in magnitudes if name != "thousand"])
 
         # "two dollars"
+        # add "one fifty five" => "one hundred fifty five" => 155
+        with_hundred = compose(
+            closure(self.NOT_SPACE) + accep(" ") + insert("hundred ") + self.VSIGMA,
+            compose(cardinal_graph, self.DIGIT ** 3),
+        )
+        cardinal_with_hundred = cardinal_graph | with_hundred
         integer_graph = (
-            insert('value: "') + cardinal_graph + insert('"')
+            insert('value: "') + cardinal_with_hundred + insert('"')
             + ds + insert(' currency: "') + currency + insert('"')
         )
         # "fifty million dollars" / "four hundred billion won"

itn/english/rules/telephone.py

@@ -72,7 +72,7 @@ def build_tagger(self):
         graph |= insert('number_part: "') + ssn + insert('"')
 
         # IP: X.X.X.X
-        ip_token = single + closure(ds + single, 0, 2) | add_weight(two_digit, 0.002)
+        ip_token = single + closure(ds + single, 0, 2) | double | add_weight(two_digit, 0.002)
         ip = ip_token + (cross(" dot ", ".") + ip_token) ** 3
         graph |= insert('number_part: "') + add_weight(ip, -0.001) + insert('"')
 

itn/english/test/data/en_money.txt

@@ -17,6 +17,7 @@ one point six nine billion yuan => 1.69 billion yuan
 one point four three six billion yuan => 1.436 billion yuan
 four million yuan => 4 million yuan
 one dollar => $1
+fifteen thousand dollars => $15000
 twenty dollar => $20
 twenty point five o six dollars => $20.506
 point five o six dollars => $.506
@@ -44,6 +45,7 @@ eighteen thousand one hundred twenty five dollars => $18125
 eighteen thousand one hundred twenty four dollars => $18124
 eighteen thousand one hundred twenty nine dollars => $18129
 one thousand fifty five dollars => $1055
+one fifty five dollars => $155
 fifteen hundred dollars => $1500
 ninety nine hundred dollars => $9900
 ninety nine hundred and fifteen dollars and one cent => $9915.01

itn/english/test/data/en_telephone.txt

@@ -7,6 +7,8 @@ o two three one two three five six seven eight => 023-123-5678
 oh two three one two three five six seven eight => 023-123-5678
 double oh three one two three five six seven eight => 003-123-5678
 one two three dot one two three dot o dot four o => 123.123.0.40
+two two five dot double five dot o dot four o => 225.55.0.40
+two two five dot double five dot o dot forty five => 225.55.0.45
 ssn is seven double nine one two three double one three => ssn is 799-12-3113
 seven nine nine => 799
 a b nine => ab9