Skip to content

#3640 Escaped characters in SGroup labels in CXSMILES not properly handled #3675

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
even1024 wants to merge 17 commits into
base: master
Choose a base branch
from
Open

#3640 Escaped characters in SGroup labels in CXSMILES not properly handled #3675

Show file tree
Hide file tree
Changes from 12 commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
5423894
escape sgroups
even1024 May 20, 2026
f65ce5b
Fix daylight AP smiles
even1024 May 25, 2026
01c3596
Adjust escaped SGroup tests
even1024 May 28, 2026
73f204c
Fix terminal AP CXSMILES roundtrip
even1024 May 28, 2026
02d3ac9
Fix terminal AP CXSMILES roundtrip
even1024 May 28, 2026
36fd668
Limit AP star roundtrip
even1024 May 29, 2026
0dd7bd2
Escape dollar in SGroup fields
even1024 May 30, 2026
ef9b397
Split SGroup KET tests
even1024 May 30, 2026
5516349
Fix Jython KET test order
even1024 May 31, 2026
8226815
Format KET test
even1024 May 31, 2026
6bcd377
Write AP closure in Daylight SMILES
even1024 Jun 3, 2026
c9d8934
Add SGroup AP roundtrip test
even1024 Jun 4, 2026
10c0ebc
Fix CXSMILES AP star roundtrip
even1024 Jun 8, 2026
093457e
Revert "Fix CXSMILES AP star roundtrip"
even1024 Jun 9, 2026
e86817c
Merge branch 'master' into 3640-escape-bm
AliaksandrDziarkach Jun 15, 2026
451e7b8
Fix UT
AliaksandrDziarkach Jun 15, 2026
50cf560
Change all AP, fix UT
AliaksandrDziarkach Jun 16, 2026
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
37 changes: 37 additions & 0 deletions api/tests/integration/ref/formats/smiles.py.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,22 @@ default smiles:
CCCCC |Sg:n:1,2,3::hh|
canonical smiles:
canonical SMILES saver: can not canonicalize a polymer
default smiles:
CCCC* |$;;;;_AP1$,Sg:n:2:2,6-7:ht|
canonical smiles:
canonical SMILES saver: can not canonicalize a polymer
default smiles:
CCCCC |SgD:1,2,3:a,b:c,d::: :|
canonical smiles:
CCCCC
default smiles:
CCCCC |SgD:1,2,3:name,&#59;:|{}$field:data,&#59;:|{}$value:query,&#59;:|{}$op:unit,&#59;:|{}$text: :|
canonical smiles:
CCCCC
default smiles:
CCCCC |Sg:n:1,2,3:sub,&#59;:|{}$script:hh|
canonical smiles:
canonical SMILES saver: can not canonicalize a polymer
daylight:
CCCC
daylight:
Expand All @@ -63,6 +79,14 @@ daylight:
SMILES saver: repeating units must have exactly two outgoing bonds, has 1
daylight:
CC{-}CC{+n}C
daylight:
CCC{-}{+n}C%91.[*:1]%91
daylight:
CCCCC
daylight:
CCCCC
daylight:
CC{-}CC{+n}C
chemaxon:
CCCC |Sg:gen:0,1,2:|
chemaxon:
Expand All @@ -71,6 +95,19 @@ chemaxon:
CCCC |Sg:n:0,1,2::ht|
chemaxon:
CCCCC |Sg:n:1,2,3::hh|
chemaxon:
CCCC* |$;;;;_AP1$,Sg:n:2:2,6-7:ht|
chemaxon:
CCCCC |SgD:1,2,3:a,b:c,d::: :|
chemaxon:
CCCCC |SgD:1,2,3:name,&#59;:|{}$field:data,&#59;:|{}$value:query,&#59;:|{}$op:unit,&#59;:|{}$text: :|
chemaxon:
CCCCC |Sg:n:1,2,3:sub,&#59;:|{}$script:hh|
*** S-Group AP closure roundtrip ***
chemaxon roundtrip:
CCCC* |$;;;;_AP1$,Sg:n:2:2,6-7:ht|
daylight closure:
CCC{-}{+n}C%91.[*:1]%91
*** Atropisomers ***
atropisomer:
C1=CC=C(C)C(C2=C(N)C=C(C)C=C2)=C1O |o1:5,r,wU:5.4|
Expand Down
3 changes: 3 additions & 0 deletions api/tests/integration/ref/formats/smiles_to_ket.py.out
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
*** SMILES to KET ***
sgroup_data_all_fields.ket:SUCCEED
sgroup_sru_subscript.ket:SUCCEED
101 changes: 101 additions & 0 deletions api/tests/integration/tests/formats/ref/sgroup_data_all_fields.ket
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,101 @@
{
"root": {
"nodes": [
{
"$ref": "mol0"
}
]
},
"mol0": {
"type": "molecule",
"atoms": [
{
"label": "C",
"location": [
-1.7320506572723389,
-5.960464477539063e-8,
0.0
]
},
{
"label": "C",
"location": [
-0.8660253882408142,
0.5,
0.0
]
},
{
"label": "C",
"location": [
0.0,
0.0,
0.0
]
},
{
"label": "C",
"location": [
0.866025447845459,
0.4999999701976776,
0.0
]
},
{
"label": "C",
"location": [
1.7320506572723389,
-2.980232238769531e-7,
0.0
]
}
],
"bonds": [
{
"type": 1,
"atoms": [
0,
1
]
},
{
"type": 1,
"atoms": [
1,
2
]
},
{
"type": 1,
"atoms": [
2,
3
]
},
{
"type": 1,
"atoms": [
3,
4
]
}
],
"sgroups": [
{
"type": "DAT",
"atoms": [
1,
2,
3
],
"fieldName": "name,;:|{}$field",
"fieldData": "data,;:|{}$value",
"fieldType": "unit,;:|{}$text",
"queryOp": "query,;:|{}$op",
"x": 1.9868215517249156e-8,
"y": 0.3333333432674408,
"dataDetached": false
}
]
}
}
96 changes: 96 additions & 0 deletions api/tests/integration/tests/formats/ref/sgroup_sru_subscript.ket
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,96 @@
{
"root": {
"nodes": [
{
"$ref": "mol0"
}
]
},
"mol0": {
"type": "molecule",
"atoms": [
{
"label": "C",
"location": [
-1.7320506572723389,
-5.960464477539063e-8,
0.0
]
},
{
"label": "C",
"location": [
-0.8660253882408142,
0.5,
0.0
]
},
{
"label": "C",
"location": [
0.0,
0.0,
0.0
]
},
{
"label": "C",
"location": [
0.866025447845459,
0.4999999701976776,
0.0
]
},
{
"label": "C",
"location": [
1.7320506572723389,
-2.980232238769531e-7,
0.0
]
}
],
"bonds": [
{
"type": 1,
"atoms": [
0,
1
]
},
{
"type": 1,
"atoms": [
1,
2
]
},
{
"type": 1,
"atoms": [
2,
3
]
},
{
"type": 1,
"atoms": [
3,
4
]
}
],
"sgroups": [
{
"type": "SRU",
"atoms": [
1,
2,
3
],
"subscript": "sub,;:|{}$script",
"connectivity": "HH"
}
]
}
}
24 changes: 24 additions & 0 deletions api/tests/integration/tests/formats/smiles.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,11 +92,25 @@
print(getIndigoExceptionText(e))

print("*** S-Groups ***")
sgroup_data_all_fields = (
"CCCCC |SgD:1,2,3:"
"name,&#59;:|{}$field:"
"data,&#59;:|{}$value:"
"query,&#59;:|{}$op:"
"unit,&#59;:|{}$text: :|"
)
sgroup_sru_subscript = (
"CCCCC |Sg:n:1,2,3:sub,&#59;:|{}$script:hh|"
)
mols_smiles = [
"CCCC |Sg:gen:0,1,2:|",
"CCCC |Sg:n:0,1,2:3-6:eu|",
"CCCC |Sg:n:0,1,2::ht|",
"CCCCC |Sg:n:1,2,3::hh|",
"CCCC* |$;;;;_AP1$,Sg:n:2:2,6-7:ht|",
"CCCCC |SgD:1,2,3:a,b:c,d::: :|",
sgroup_data_all_fields,
sgroup_sru_subscript,
]
for sm in mols_smiles:
print("default smiles:")
Expand All @@ -120,6 +134,16 @@
print("chemaxon:")
print(indigo.loadMolecule(sm).smiles())

print("*** S-Group AP closure roundtrip ***")
sgroup_ap_closure = "CCCC* |$;;;;_AP1$,Sg:n:2:2,6-7:ht|"
indigo.setOption("smiles-saving-format", "chemaxon")
print("chemaxon roundtrip:")
print(indigo.loadMolecule(sgroup_ap_closure).smiles())
indigo.setOption("smiles-saving-format", "daylight")
print("daylight closure:")
print(indigo.loadMolecule(sgroup_ap_closure).smiles())
indigo.setOption("smiles-saving-format", "chemaxon")

print("*** Atropisomers ***")
mols_smiles = [
"C1C(O)=C(C2C=CC(C)=CC=2N)C(C)=CC=1 |o1:3,r,wU:3.12|",
Expand Down
36 changes: 36 additions & 0 deletions api/tests/integration/tests/formats/smiles_to_ket.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
import os
import sys

sys.path.append(
os.path.normpath(
os.path.join(os.path.abspath(__file__), "..", "..", "..", "common")
)
)
from common.util import compare_diff
from env_indigo import Indigo, joinPathPy # noqa

indigo = Indigo()
indigo.setOption("json-saving-pretty", True)

print("*** SMILES to KET ***")

ref_path = joinPathPy("ref/", __file__)

tests = [
(
"sgroup_data_all_fields",
"CCCCC |SgD:1,2,3:"
"name,&#59;:|{}$field:"
"data,&#59;:|{}$value:"
"query,&#59;:|{}$op:"
"unit,&#59;:|{}$text: :|",
),
(
"sgroup_sru_subscript",
"CCCCC |Sg:n:1,2,3:sub,&#59;:|{}$script:hh|",
),
]

for filename, smiles in tests:
ket = indigo.loadMolecule(smiles).json()
compare_diff(ref_path, filename + ".ket", ket)
Loading
Loading