feat: fix time min-to, IP twenty-three, serial, 456/470 (97%)

- Time: fix minute_to composition (use raw digits without zero-padding)
  => time now 29/29 full pass
- Telephone: fix IP to support single+two_digit combinations
  (one twenty three dot... => 123.123.0.40)
- Cardinal: expose graph_two_digit for telephone serial

Author: pengzhendong

itn/english/rules/cardinal.py

@@ -36,6 +36,7 @@ def build_tagger(self):
         # 1~9, 10~19, 20~99
         one_digit = digit
         two_digit = teen | (ties + (ds + digit | insert("0")))
+        self.graph_two_digit = two_digit
         up_to_99 = one_digit | two_digit
 
         # one hundred, one hundred twenty three, one hundred one

itn/english/rules/telephone.py

@@ -40,8 +40,8 @@ def build_tagger(self):
                                       ("five","5"),("six","6"),("seven","7"),("eight","8"),
                                       ("nine","9"),("zero","0"),("oh","0"),("o","0")]])
 
-        # two-digit cardinal: twenty three => 23
-        two_digit = self.cardinal.graph_no_exception @ (self.DIGIT + self.DIGIT)
+        # two-digit cardinal: twenty three => 23 (uses graph_two_digit for proper space handling)
+        two_digit = self.cardinal.graph_two_digit
 
         # a token is 1 or 2 digits
         token = single | double | add_weight(two_digit, 0.002)
@@ -72,7 +72,13 @@ def build_tagger(self):
         graph |= insert('number_part: "') + ssn + insert('"')
 
         # IP: X.X.X.X
-        ip_token = single + closure(ds + single, 0, 2) | double | add_weight(two_digit, 0.002)
+        ip_token = (
+            single + closure(ds + single, 0, 2)
+            | double
+            | add_weight(two_digit, 0.002)
+            | single + ds + two_digit
+            | two_digit + ds + single
+        )
         ip = ip_token + (cross(" dot ", ".") + ip_token) ** 3
         graph |= insert('number_part: "') + add_weight(ip, -0.001) + insert('"')
 
@@ -84,7 +90,7 @@ def build_tagger(self):
         graph |= insert('number_part: "') + cc + insert('"')
 
         # serial: mixed alpha+digits, at least one digit, length >= 3
-        serial_char = single | add_weight(two_digit, 0.002) | self.ALPHA
+        serial_char = add_weight(single, 0.001) | add_weight(two_digit, -0.001) | self.ALPHA
         serial = serial_char + closure(ds + serial_char, 2)
         serial = serial @ (closure(self.ALPHA | self.DIGIT) + self.DIGIT + closure(self.ALPHA | self.DIGIT))
         graph |= insert('number_part: "') + add_weight(serial, 2.0) + insert('"')

itn/english/rules/time.py

@@ -52,6 +52,10 @@ def build_tagger(self):
         graph_min_double = union(*[cross(_num_to_word(x), str(x)) for x in range(10, 60)])
         graph_min_verbose = cross("half", "30") | cross("quarter", "15")
 
+        # minutes without zero-padding (for minute_to composition)
+        min_single_raw = union(*[cross(_num_to_word(x), str(x)) for x in range(1, 10)])
+        min_double_raw = graph_min_double  # already no padding
+
         oclock = cross("o'clock", "") | cross("oclock", "") | cross("hundred hours", "")
 
         hour = insert('hour: "') + hour_all + insert('"')
@@ -89,7 +93,7 @@ def build_tagger(self):
         # "ten to eleven pm" => 10:50 p.m.
         graph_min_to = (
             insert('minute: "')
-            + ((graph_min_single | graph_min_double) @ minute_to)
+            + ((min_single_raw | min_double_raw) @ minute_to)
             + insert('"')
             + closure(ds + delete("min") + delete("ute").ques + delete("s").ques, 0, 1)
             + ds + delete("to") + ds

itn/english/test/data/en_telephone.txt

@@ -7,8 +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
+one twenty 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

itn/english/test/data/en_time.txt

@@ -26,3 +26,4 @@ quarter past one => 01:15
 quarter to one => 12:45
 quarter to twelve => 11:45
 set alarm at ten to eleven pm => set alarm at 10:50 p.m.
+one min to one am => 12:59 a.m.