1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
|
#
# chemicalFormulas.py
#
# Copyright (c) 2003,2019 Paul McGuire
#
import pyparsing as pp
atomic_weight = {
"O": 15.9994,
"H": 1.00794,
"Na": 22.9897,
"Cl": 35.4527,
"C": 12.0107,
}
digits = "0123456789"
# Version 1
element = pp.Word(pp.alphas.upper(), pp.alphas.lower(), max=2).set_name("element")
# for stricter matching, use this Regex instead
# element = Regex("A[cglmrstu]|B[aehikr]?|C[adeflmorsu]?|D[bsy]|"
# "E[rsu]|F[emr]?|G[ade]|H[efgos]?|I[nr]?|Kr?|L[airu]|"
# "M[dgnot]|N[abdeiop]?|Os?|P[abdmortu]?|R[abefghnu]|"
# "S[bcegimnr]?|T[abcehilm]|U(u[bhopqst])?|V|W|Xe|Yb?|Z[nr]")
element_ref = pp.Group(element + pp.Opt(pp.Word(digits), default="1"))
formula = element_ref[...]
def sum_atomic_weights(element_list):
return sum(atomic_weight[elem] * int(qty) for elem, qty in element_list)
formula.run_tests(
"""\
H2O
C6H5OH
NaCl
""",
full_dump=False,
post_parse=lambda _, tokens: f"Molecular weight: {sum_atomic_weights(tokens)}",
)
print()
# Version 2 - access parsed items by results name
element_ref = pp.Group(
element("symbol") + pp.Opt(pp.Word(digits), default="1")("qty")
)
formula = element_ref[...]
def sum_atomic_weights_by_results_name(element_list):
return sum(atomic_weight[elem.symbol] * int(elem.qty) for elem in element_list)
formula.run_tests(
"""\
H2O
C6H5OH
NaCl
""",
full_dump=False,
post_parse=lambda _, tokens:
f"Molecular weight: {sum_atomic_weights_by_results_name(tokens)}",
)
print()
# Version 3 - convert integers during parsing process
integer = pp.Word(digits).set_name("integer")
integer.add_parse_action(lambda t: int(t[0]))
element_ref = pp.Group(element("symbol") + pp.Opt(integer, default=1)("qty"))
formula = element_ref[...].set_name("chemical_formula")
def sum_atomic_weights_by_results_name_with_converted_ints(element_list):
return sum(atomic_weight[elem.symbol] * int(elem.qty) for elem in element_list)
formula.run_tests(
"""\
H2O
C6H5OH
NaCl
""",
full_dump=False,
post_parse=lambda _, tokens:
f"Molecular weight: {sum_atomic_weights_by_results_name_with_converted_ints(tokens)}",
)
print()
# Version 4 - parse and convert integers as subscript digits
subscript_digits = "₀₁₂₃₄₅₆₇₈₉"
subscript_int_map = {e[1]: e[0] for e in enumerate(subscript_digits)}
def cvt_subscript_int(s):
ret = 0
for c in s[0]:
ret = ret * 10 + subscript_int_map[c]
return ret
subscript_int = pp.Word(subscript_digits).set_name("subscript")
subscript_int.add_parse_action(cvt_subscript_int)
element_ref = pp.Group(element("symbol") + pp.Opt(subscript_int, default=1)("qty"))
formula = element_ref[1, ...].set_name("chemical_formula")
formula.run_tests(
"""\
H₂O
C₆H₅OH
NaCl
""",
full_dump=False,
post_parse=lambda _, tokens:
f"Molecular weight: {sum_atomic_weights_by_results_name_with_converted_ints(tokens)}",
)
print()
|
