1"""Reads chemical data in SDF format (wraps the molfile format). 

2 

3See https://en.wikipedia.org/wiki/Chemical_table_file#SDF 

4""" 

5from typing import TextIO 

6 

7from ase.atoms import Atoms 

8from ase.utils import reader 

9 

10 

11def get_num_atoms_sdf_v2000(first_line: str) -> int: 

12 """Parse the first line extracting the number of atoms.""" 

13 return int(first_line[0:3]) # first three characters 

14 # http://biotech.fyicenter.com/1000024_SDF_File_Format_Specification.html 

15 

16 

17@reader 

18def read_sdf(file_obj: TextIO) -> Atoms: 

19 """Read the sdf data and compose the corresponding Atoms object.""" 

20 lines = file_obj.readlines() 

21 # first three lines header 

22 del lines[:3] 

23 

24 num_atoms = get_num_atoms_sdf_v2000(lines.pop(0)) 

25 positions = [] 

26 symbols = [] 

27 for line in lines[:num_atoms]: 

28 x, y, z, symbol = line.split()[:4] 

29 symbols.append(symbol) 

30 positions.append((float(x), float(y), float(z))) 

31 return Atoms(symbols=symbols, positions=positions)