explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 03:19:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Alphanumeric -> alphabetic [ci skip]

Browse Source 
see ines/spacy-course#38
This commit is contained in:
Ines Montani 2019-10-06 13:30:01 +02:00
parent cbc2cee2c8
commit 573e543e4a
4 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lexeme.pyx
View File

@ -375,7 +375,7 @@ cdef class Lexeme:
Lexeme.c_set_flag(self.c, IS_STOP, x)
property is_alpha:
"""RETURNS (bool): Whether the lexeme consists of alphanumeric
"""RETURNS (bool): Whether the lexeme consists of alphabetic
characters. Equivalent to `lexeme.text.isalpha()`.
"""
def __get__(self):

2
spacy/matcher/_schemas.py
View File

@ -111,7 +111,7 @@ TOKEN_PATTERN_SCHEMA = {
"$ref": "#/definitions/integer_value",
},
"IS_ALPHA": {
"title": "Token consists of alphanumeric characters",
"title": "Token consists of alphabetic characters",
"$ref": "#/definitions/boolean_value",
},
"IS_ASCII": {

2
website/docs/usage/rule-based-matching.md
View File

@ -163,7 +163,7 @@ rule-based matching are:
| `TEXT` <Tag variant="new">2.1</Tag> | unicode | The exact verbatim text of a token. |
| `LOWER` | unicode | The lowercase form of the token text. |
|  `LENGTH` | int | The length of the token text. |
|  `IS_ALPHA`, `IS_ASCII`, `IS_DIGIT` | bool | Token text consists of alphanumeric characters, ASCII characters, digits. |
|  `IS_ALPHA`, `IS_ASCII`, `IS_DIGIT` | bool | Token text consists of alphabetic characters, ASCII characters, digits. |
|  `IS_LOWER`, `IS_UPPER`, `IS_TITLE` | bool | Token text is in lowercase, uppercase, titlecase. |
|  `IS_PUNCT`, `IS_SPACE`, `IS_STOP` | bool | Token is punctuation, whitespace, stop word. |
|  `LIKE_NUM`, `LIKE_URL`, `LIKE_EMAIL` | bool | Token text resembles a number, URL, email. |

2
website/docs/usage/spacy-101.md
View File

@ -573,7 +573,7 @@ apple = doc[0]
print("Fine-grained POS tag", apple.pos_, apple.pos)
print("Coarse-grained POS tag", apple.tag_, apple.tag)
print("Word shape", apple.shape_, apple.shape)
print("Alphanumeric characters?", apple.is_alpha)
print("Alphabetic characters?", apple.is_alpha)
print("Punctuation mark?", apple.is_punct)
billion = doc[10]