datu 0.3.4

datu - a data file utility
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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158

Feature: Head
  Print the first N rows of a Parquet, Avro, CSV, JSON, or ORC file as CSV.

  Scenario: Head Parquet default (10 lines)
    When I run `datu head fixtures/userdata.parquet`
    Then the command should succeed
    And the output should have a header and 10 lines

  Scenario: Head Parquet with -n 2
    When I run `datu head fixtures/userdata.parquet -n 2`
    Then the command should succeed
    And the output should have a header and 2 lines

  Scenario: Head Avro default (10 lines)
    When I run `datu head fixtures/userdata5.avro`
    Then the command should succeed
    And the output should have a header and 10 lines
    And the first line of the output should be: registration_dttm,id,first_name,last_name,email,gender,ip_address,cc,country,birthdate,salary,title,comments

  Scenario: Head Avro with -n 3
    When I run `datu head fixtures/userdata5.avro -n 3`
    Then the command should succeed
    And the output should have a header and 3 lines
    And the first line of the output should be: registration_dttm,id,first_name,last_name,email,gender,ip_address,cc,country,birthdate,salary,title,comments

  Scenario: Head Parquet with --select
    When I run `datu head fixtures/userdata.parquet -n 2 --select id,last_name`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should be: id,last_name

  Scenario: Head Avro with --select
    When I run `datu head fixtures/userdata5.avro -n 2 --select id,email`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should be: id,email

  Scenario: Head CSV default (10 lines)
    When I run `datu head fixtures/table.csv`
    Then the command should succeed
    And the output should have a header and 3 lines
    And the first line of the output should contain "one"
    And the first line of the output should contain "two"

  Scenario: Head CSV with -n 2
    When I run `datu head fixtures/table.csv -n 2`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should contain "one,two"

  Scenario: Head JSON default (10 lines)
    When I run `datu head fixtures/table.json`
    Then the command should succeed
    And the output should have a header and 3 lines
    And the first line of the output should contain "one"
    And the first line of the output should contain "two"

  Scenario: Head JSON with -n 2
    When I run `datu head fixtures/table.json -n 2`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should contain "one"
    And the output should contain "foo"

  Scenario: Head CSV with --select
    When I run `datu head fixtures/table.csv -n 2 --select two,four`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should be: two,four

  Scenario: Head ORC default (10 lines)
    When I run `datu convert fixtures/userdata5.avro $TEMPDIR/userdata5.orc --select id,first_name --limit 10`
    Then the command should succeed
    When I run `datu head $TEMPDIR/userdata5.orc`
    Then the command should succeed
    And the output should have a header and 10 lines
    And the first line of the output should be: id,first_name

  Scenario: Head ORC with -n 3
    When I run `datu convert fixtures/userdata5.avro $TEMPDIR/userdata5.orc --select id,first_name --limit 10`
    Then the command should succeed
    When I run `datu head $TEMPDIR/userdata5.orc -n 3`
    Then the command should succeed
    And the output should have a header and 3 lines
    And the first line of the output should be: id,first_name

  Scenario: Head ORC with --select
    When I run `datu convert fixtures/userdata5.avro $TEMPDIR/userdata5.orc --select id,first_name --limit 10`
    Then the command should succeed
    When I run `datu head $TEMPDIR/userdata5.orc -n 2 --select id,first_name`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should be: id,first_name

  Scenario: Head ORC with --output csv
    When I run `datu convert fixtures/userdata5.avro $TEMPDIR/userdata5.orc --select id,first_name --limit 10`
    Then the command should succeed
    When I run `datu head $TEMPDIR/userdata5.orc -n 2 --output csv`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should be: id,first_name

  Scenario: Head ORC with --output json
    When I run `datu convert fixtures/userdata5.avro $TEMPDIR/userdata5.orc --select id,first_name --limit 10`
    Then the command should succeed
    When I run `datu head $TEMPDIR/userdata5.orc -n 2 --output json`
    Then the command should succeed
    And the output should be valid JSON
    And the output should contain "["
    And the output should contain "id"

  Scenario: Head ORC with --output yaml
    When I run `datu convert fixtures/userdata5.avro $TEMPDIR/userdata5.orc --select id,first_name --limit 10`
    Then the command should succeed
    When I run `datu head $TEMPDIR/userdata5.orc -n 2 --output yaml`
    Then the command should succeed
    And the output should be valid YAML
    And the output should contain "first_name"
    And the output should contain "id"

  Scenario: Head Parquet with --output csv
    When I run `datu head fixtures/userdata.parquet -n 2 --output csv`
    Then the command should succeed
    And the output should have a header and 2 lines

  Scenario: Head Parquet with --output json
    When I run `datu head fixtures/userdata.parquet -n 2 --output json`
    Then the command should succeed
    And the output should be valid JSON
    And the output should contain "["
    And the output should contain "id"

  Scenario: Head Avro with --output csv
    When I run `datu head fixtures/userdata5.avro -n 2 --output csv`
    Then the command should succeed
    And the output should have a header and 2 lines
    And the first line of the output should be: registration_dttm,id,first_name,last_name,email,gender,ip_address,cc,country,birthdate,salary,title,comments

  Scenario: Head Avro with --output json
    When I run `datu head fixtures/userdata5.avro -n 2 --output json`
    Then the command should succeed
    And the output should be valid JSON
    And the output should contain "["
    And the output should contain "first_name"

  Scenario: Head Parquet with --output yaml
    When I run `datu head fixtures/userdata.parquet -n 2 --output yaml`
    Then the command should succeed
    And the output should be valid YAML
    And the output should contain "id"
    And the output should contain "first_name"

  Scenario: Head Avro with --output yaml
    When I run `datu head fixtures/userdata5.avro -n 2 --output yaml`
    Then the command should succeed
    And the output should be valid YAML
    And the output should contain "first_name"
    And the output should contain "email"