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
|
import {input, templateCompositeFrom} from '#composite';
import {stitchArrays} from '#sugar';
import {isContentString, validateInstanceOf} from '#validators';
import {withPropertiesFromList} from '#composite/data';
export default templateCompositeFrom({
annotation: `withParsedContentEntries`,
inputs: {
// TODO: Is there any way to validate this input based on the *other*
// inputs proivded, i.e. regexes? This kind of just assumes the string
// has already been validated according to the form the regex expects,
// which *is* always the case (as used), but it seems a bit awkward.
from: input({validate: isContentString}),
caseSensitiveRegex: input({
validate: validateInstanceOf(RegExp),
}),
},
outputs: [
'#parsedContentEntryHeadings',
'#parsedContentEntryBodies',
],
steps: () => [
{
dependencies: [
input('from'),
input('caseSensitiveRegex'),
],
compute: (continuation, {
[input('from')]: commentaryText,
[input('caseSensitiveRegex')]: caseSensitiveRegex,
}) => continuation({
['#rawMatches']:
Array.from(commentaryText.matchAll(caseSensitiveRegex)),
}),
},
withPropertiesFromList({
list: '#rawMatches',
properties: input.value([
'0', // The entire match as a string.
'groups',
'index',
]),
}).outputs({
'#rawMatches.0': '#rawMatches.text',
'#rawMatches.groups': '#parsedContentEntryHeadings',
'#rawMatches.index': '#rawMatches.startIndex',
}),
{
dependencies: [
'#rawMatches.text',
'#rawMatches.startIndex',
],
compute: (continuation, {
['#rawMatches.text']: text,
['#rawMatches.startIndex']: startIndex,
}) => continuation({
['#rawMatches.endIndex']:
stitchArrays({text, startIndex})
.map(({text, startIndex}) => startIndex + text.length),
}),
},
{
dependencies: [
input('from'),
'#rawMatches.startIndex',
'#rawMatches.endIndex',
],
compute: (continuation, {
[input('from')]: commentaryText,
['#rawMatches.startIndex']: startIndex,
['#rawMatches.endIndex']: endIndex,
}) => continuation({
['#parsedContentEntryBodies']:
stitchArrays({startIndex, endIndex})
.map(({endIndex}, index, stitched) =>
(index === stitched.length - 1
? commentaryText.slice(endIndex)
: commentaryText.slice(
endIndex,
stitched[index + 1].startIndex)))
.map(body => body.trim()),
}),
},
{
dependencies: [
'#parsedContentEntryHeadings',
'#parsedContentEntryBodies',
],
compute: (continuation, {
['#parsedContentEntryHeadings']: parsedContentEntryHeadings,
['#parsedContentEntryBodies']: parsedContentEntryBodies,
}) => continuation({
['#parsedContentEntryHeadings']: parsedContentEntryHeadings,
['#parsedContentEntryBodies']: parsedContentEntryBodies,
})
}
],
});
|
