explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-11 08:42:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Implement is_number

Browse Source
This commit is contained in:
Matthew Honnibal 2014-11-01 19:13:24 +11:00
parent f685218e21
commit 5484fbea69
1 changed files with 18 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
spacy/orth.py
View File

@ -49,6 +49,7 @@ def is_lower(string):
def is_upper(string): def is_upper(string):
return string.isupper() return string.isupper()
TLDs = set("com|org|edu|gov|net|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|" TLDs = set("com|org|edu|gov|net|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|"
"name|pro|tel|travel|xxx|" "name|pro|tel|travel|xxx|"
"ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|" "ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|"
@ -63,6 +64,7 @@ TLDs = set("com|org|edu|gov|net|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|mu
"tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|" "tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|"
"wf|ws|ye|yt|za|zm|zw".split('|')) "wf|ws|ye|yt|za|zm|zw".split('|'))
def is_urlish(string): def is_urlish(string):
# We're looking for things that function in text like URLs. So, valid URL # We're looking for things that function in text like URLs. So, valid URL
# or not, anything they say http:// is going to be good. # or not, anything they say http:// is going to be good.
@ -82,13 +84,23 @@ def is_urlish(string):
return False return False
NUM_WORDS = set('zero one two three four five six seven eight nine ten'
'eleven twelve thirteen fourteen fifteen sixteen seventeen'
'eighteen nineteen twenty thirty forty fifty sixty seventy'
'eighty ninety hundred thousand million billion trillion'
'quadrillion gajillion bazillion'.split())
def is_number(string): def is_number(string):
pass string = string.replace(',', '')
string = string.replace('.', '')
if string.isdigit():
def is_emoticon(string): return True
pass if string.count('/') == 1:
num, denom = string.split('/')
if is_number(num) and is_number(denom):
return True
if string in NUM_WORDS:
return True
return False
# Statistics features # Statistics features
def oft_case(name, thresh): def oft_case(name, thresh):