mirror of
https://github.com/explosion/spaCy.git
synced 2025-06-29 17:33:10 +03:00
Add tokenizer exception for 'Ph.D.', to fix 592.
This commit is contained in:
parent
532318e80b
commit
41a90a7fbb
|
@ -112,6 +112,10 @@ TOKENIZER_INFIXES = (r'''\.\.\.+ (?<=[a-z])\.(?=[A-Z]) (?<=[a-zA-Z])-(?=[a-zA-z]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = {
|
TOKENIZER_EXCEPTIONS = {
|
||||||
|
"Ph.D.": [
|
||||||
|
{
|
||||||
|
"F": "Ph.D."
|
||||||
|
}],
|
||||||
"d.": [
|
"d.": [
|
||||||
{
|
{
|
||||||
"F": "d."
|
"F": "d."
|
||||||
|
|
Loading…
Reference in New Issue
Block a user