zuzu-rust 0.2.0

Rust implementation of ZuzuScript
Documentation 
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

from test/more import *;
from std/data/csv import CSV;

let csv := new CSV(
	headers: true,
);

let parsed := csv.decode(
	"name,age\n"
	_ "\"Ada, A.\",32\n"
	_ "Bob,27\n",
);
is( parsed.length(), 2, "decode returns data rows after header line" );
is( parsed[0]{name}, "Ada, A.", "decode handles quoted commas" );
is( parsed[1]{age}, "27", "decode preserves scalar text values" );
is( csv.encode_row( [ "Ada", 32 ] ), "Ada,32\n", "encode_row writes one delimited row" );
ok( csv.encode_binarystring( [ { name: "Ada", age: 32 } ] ) instanceof BinaryString, "encode_binarystring returns BinaryString" );
is( to_string( csv.encode_row_binarystring( [ "Ada", 32 ] ) ), "Ada,32\n", "encode_row_binarystring emits CSV bytes" );
let binary_rows := csv.decode_binarystring( to_binary("name,city\nAda,Zürich\n") );
is( binary_rows[0]{city}, "Zürich", "decode_binarystring decodes UTF-8 CSV bytes" );

let sniffed := csv.sniff(
	"name\tage\n"
	_ "Ada\t32\n"
	_ "Bob\t27\n",
);
is( sniffed{sep_char}, "\t", "sniff detects tab separator" );
ok( sniffed{headers}, "sniff detects likely header row" );
is( csv.sniff_binarystring( to_binary("name\tage\nAda\t32\n") ){sep_char}, "\t", "sniff_binarystring detects tab separator" );

let transposed := csv.transpose(
	[
		[ "name", "Ada", "Bob" ],
		[ "age", "32", "27" ],
	],
);
is( transposed[0][1], "age", "transpose swaps table axes" );
is( transposed[2][0], "Bob", "transpose keeps later values" );

let typed := new CSV(
	headers: true,
	trim_headers: true,
	lowercase_headers: true,
	rename_headers: {
		enabled: "active",
	},
	types: {
		age: "integer",
		active: "boolean",
	},
	defaults: {
		nickname: "n/a",
	},
	required_columns: [ "name", "age", "active" ],
);
let typed_rows := typed.decode(
	" Name ,Age,Enabled\n"
	_ "Ada,32,true\n"
	_ "Bob,27,false\n",
);
is( typed_rows[0]{age}, 32, "typed decode coerces integer columns" );
is( typed_rows[1]{active}, 0, "typed decode coerces boolean columns" );
is( typed_rows[0]{nickname}, "n/a", "typed decode applies defaults" );

let duplicate := new CSV(
	headers: true,
	duplicate_headers: "suffix",
);
let dup_rows := duplicate.decode(
	"name,name\n"
	_ "Ada,A.\n",
);
is( dup_rows[0]{name}, "Ada", "duplicate header keeps first field" );
is( dup_rows[0]{name_2}, "A.", "duplicate header suffixes later field" );

let ragged := new CSV(
	headers: true,
	ragged: "fill",
	fill_value: "x",
);
let ragged_rows := ragged.decode(
	"a,b,c\n"
	_ "1,2\n",
);
is( ragged_rows[0]{c}, "x", "ragged fill pads missing values" );

let report := ( new CSV(
	headers: true,
	on_error: "collect",
) ).decode_report(
	"name,age\n"
	_ "Ada,32\n"
	_ "Bob,\"oops\"x\n"
	_ "Cam,40\n",
);
is( report{rows}.length(), 1, "decode_report keeps good rows before malformed row" );
ok( report{errors}.length() >= 1, "decode_report collects parse errors" );
like( report{errors}[0]{message}, /line/, "decode_report error includes line information" );
let binary_report := ( new CSV( headers: true, on_error: "collect" ) ).decode_report_binarystring(
	to_binary(
		"name,age\n"
		_ "Ada,32\n"
		_ "Bob,\"oops\"x\n",
	),
);
ok( binary_report{errors}.length() >= 1, "decode_report_binarystring collects parse errors" );

let tsv := new CSV(
	headers: true,
	sep_char: "\t",
);
let tsv_rows := tsv.decode(
	"name\trole\n"
	_ "Ada\tdev\n"
	_ "Bob\tops\n",
);
is( tsv_rows[1]{role}, "ops", "sep_char option supports TSV-style decoding" );

done_testing();