Skip to content

adding any kind of labels #20

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

adding any kind of labels #20

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
edd82d3
allow Leu labels for cem names
0x33467 Aug 21, 2017
984e5de
allow different kind of labels for cem names
0x33467 Aug 21, 2017
b32dfc6
update cem parser tests
0x33467 Sep 8, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion chemdataextractor/parse/cem.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@

label_blacklist = R('^(31P|[12]H|[23]D|15N|14C|[4567890]\d+)$')

prefixed_label = R('^(cis|trans)-((d-)?(\d{1,2}[A-Za-z]{0,2}[′″‴‶‷⁗]?)(-d)?|[LS]\d\d?)$')
prefixed_label = R('^(trans|[A-Za-z]{,3})-((d-)?(\d{1,2}[A-Za-z]{0,2}[′″‴‶‷⁗]?)(-d)?|[LS]\d\d?)$')

#: Chemical label. Very permissive - must be used in context to avoid false positives.
strict_chemical_label = Not(label_blacklist) + (alphanumeric | roman_numeral | letter_number | prefixed_label)('label')
Expand Down
12 changes: 12 additions & 0 deletions tests/test_parse_cem.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,6 +170,18 @@ def test_to_yield_phrase(self):
]
self.do_parse(s, expected)

def test_label_start(self):
s = ['1,3,5-Tricyano-2,4,6-tris(2-dimethylaminovinyl)benzene (Leu-07)',
'1,3,5-Tricyano-2,4,6-tris(2-dimethylaminovinyl)benzene (hi-07)',
'1,3,5-Tricyano-2,4,6-tris(2-dimethylaminovinyl)benzene (hife-07)']
expected = [
['<cem_phrase><cem><name>1,3,5-Tricyano-2,4,6-tris(2-dimethylaminovinyl)benzene</name><label>Leu-07</label></cem></cem_phrase>'],
['<cem_phrase><cem><name>1,3,5-Tricyano-2,4,6-tris(2-dimethylaminovinyl)benzene</name><label>hi-07</label></cem></cem_phrase>'],
['<cem_phrase><cem><name>1,3,5-Tricyano-2,4,6-tris(2-dimethylaminovinyl)benzene</name></cem></cem_phrase>']
]
for s_elem, expected_elem in zip(s, expected):
self.do_parse(s_elem, expected_elem)


class TestParseCemHeading(unittest.TestCase):

Expand Down