logstash-filter-csv 3.0.5 → 3.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/CHANGELOG.md +22 -0
- data/CONTRIBUTORS +1 -0
- data/LICENSE +199 -10
- data/README.md +1 -1
- data/VERSION +1 -0
- data/docs/index.asciidoc +55 -5
- data/lib/logstash/filters/csv.rb +41 -4
- data/logstash-filter-csv.gemspec +5 -3
- data/spec/filters/csv_spec.rb +310 -222
- metadata +22 -5
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
|
-
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
2
|
+
SHA256:
|
|
3
|
+
metadata.gz: 61380dfaee5f7c768ba33dbeb372644941053ccf3694c441b5f6bc5b7758af46
|
|
4
|
+
data.tar.gz: c9a4bfd2b2a2c0f4d4ccac90ba8d01722a5ed7833294e8cb749f1b4c2685d2ba
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 472e1b1028701925b45aaa1990349cd6f277326e1151ba8eaacc7d48125d67528f8873c08bab7698237cdb1e35eaf39506de51623758327f91a29af36f4059f1
|
|
7
|
+
data.tar.gz: 0cc77c798c6fa3319f63aa4c9d56314686fa5bab7f6cbb0d6f221532e2007aacc1545235bfbe37fb3822125b62201bd78ef7fd3e6d48732e18f7d1990674db7b
|
data/CHANGELOG.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
|
1
|
+
## 3.1.0
|
|
2
|
+
- Add ECS support [#85](https://github.com/logstash-plugins/logstash-filter-csv/pull/85)
|
|
3
|
+
|
|
4
|
+
## 3.0.11
|
|
5
|
+
- [DOC] Fixed formatting to improve readability [#84](https://github.com/logstash-plugins/logstash-filter-csv/pull/84)
|
|
6
|
+
|
|
7
|
+
## 3.0.10
|
|
8
|
+
- [DOC] Fix asciidoc formatting for example [#73](https://github.com/logstash-plugins/logstash-filter-csv/pull/73)
|
|
9
|
+
|
|
10
|
+
## 3.0.9
|
|
11
|
+
- [DOC] Document that the `autodetect_column_names` and `skip_header` options work only when the number of Logstash
|
|
12
|
+
pipeline workers is set to `1`.
|
|
13
|
+
|
|
14
|
+
## 3.0.8
|
|
15
|
+
- feature: Added support for tagging empty rows which users can reference to conditionally drop events
|
|
16
|
+
|
|
17
|
+
## 3.0.7
|
|
18
|
+
- Update gemspec summary
|
|
19
|
+
|
|
20
|
+
## 3.0.6
|
|
21
|
+
- Fix a bug where `[nested][field]` references were incorrectly used. (#24, #52)
|
|
22
|
+
|
|
1
23
|
## 3.0.5
|
|
2
24
|
- Fix some documentation issues
|
|
3
25
|
|
data/CONTRIBUTORS
CHANGED
|
@@ -12,6 +12,7 @@ Contributors:
|
|
|
12
12
|
* Pier-Hugues Pellerin (ph)
|
|
13
13
|
* Richard Pijnenburg (electrical)
|
|
14
14
|
* Suyog Rao (suyograo)
|
|
15
|
+
* Abdul Haseeb Hussain (AbdulHaseebHussain)
|
|
15
16
|
|
|
16
17
|
Note: If you've sent us patches, bug reports, or otherwise contributed to
|
|
17
18
|
Logstash, and you aren't on the list above and want to be, please let us know
|
data/LICENSE
CHANGED
|
@@ -1,13 +1,202 @@
|
|
|
1
|
-
Copyright (c) 2012–2016 Elasticsearch <http://www.elastic.co>
|
|
2
1
|
|
|
3
|
-
|
|
4
|
-
|
|
5
|
-
|
|
2
|
+
Apache License
|
|
3
|
+
Version 2.0, January 2004
|
|
4
|
+
http://www.apache.org/licenses/
|
|
6
5
|
|
|
7
|
-
|
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
8
7
|
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
8
|
+
1. Definitions.
|
|
9
|
+
|
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
14
|
+
the copyright owner that is granting the License.
|
|
15
|
+
|
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
17
|
+
other entities that control, are controlled by, or are under common
|
|
18
|
+
control with that entity. For the purposes of this definition,
|
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
20
|
+
direction or management of such entity, whether by contract or
|
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
23
|
+
|
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
25
|
+
exercising permissions granted by this License.
|
|
26
|
+
|
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
28
|
+
including but not limited to software source code, documentation
|
|
29
|
+
source, and configuration files.
|
|
30
|
+
|
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
|
32
|
+
transformation or translation of a Source form, including but
|
|
33
|
+
not limited to compiled object code, generated documentation,
|
|
34
|
+
and conversions to other media types.
|
|
35
|
+
|
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
37
|
+
Object form, made available under the License, as indicated by a
|
|
38
|
+
copyright notice that is included in or attached to the work
|
|
39
|
+
(an example is provided in the Appendix below).
|
|
40
|
+
|
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
47
|
+
the Work and Derivative Works thereof.
|
|
48
|
+
|
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
|
50
|
+
the original version of the Work and any modifications or additions
|
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
62
|
+
|
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
65
|
+
subsequently incorporated within the Work.
|
|
66
|
+
|
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
|
73
|
+
|
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
79
|
+
where such license applies only to those patent claims licensable
|
|
80
|
+
by such Contributor that are necessarily infringed by their
|
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
83
|
+
institute patent litigation against any entity (including a
|
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
86
|
+
or contributory patent infringement, then any patent licenses
|
|
87
|
+
granted to You under this License for that Work shall terminate
|
|
88
|
+
as of the date such litigation is filed.
|
|
89
|
+
|
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
92
|
+
modifications, and in Source or Object form, provided that You
|
|
93
|
+
meet the following conditions:
|
|
94
|
+
|
|
95
|
+
(a) You must give any other recipients of the Work or
|
|
96
|
+
Derivative Works a copy of this License; and
|
|
97
|
+
|
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
|
99
|
+
stating that You changed the files; and
|
|
100
|
+
|
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
|
103
|
+
attribution notices from the Source form of the Work,
|
|
104
|
+
excluding those notices that do not pertain to any part of
|
|
105
|
+
the Derivative Works; and
|
|
106
|
+
|
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
|
109
|
+
include a readable copy of the attribution notices contained
|
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
|
112
|
+
of the following places: within a NOTICE text file distributed
|
|
113
|
+
as part of the Derivative Works; within the Source form or
|
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
|
115
|
+
within a display generated by the Derivative Works, if and
|
|
116
|
+
wherever such third-party notices normally appear. The contents
|
|
117
|
+
of the NOTICE file are for informational purposes only and
|
|
118
|
+
do not modify the License. You may add Your own attribution
|
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
121
|
+
that such additional attribution notices cannot be construed
|
|
122
|
+
as modifying the License.
|
|
123
|
+
|
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
|
125
|
+
may provide additional or different license terms and conditions
|
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
129
|
+
the conditions stated in this License.
|
|
130
|
+
|
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
134
|
+
this License, without any additional terms or conditions.
|
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
136
|
+
the terms of any separate license agreement you may have executed
|
|
137
|
+
with Licensor regarding such Contributions.
|
|
138
|
+
|
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
141
|
+
except as required for reasonable and customary use in describing the
|
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
143
|
+
|
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
|
153
|
+
|
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
|
159
|
+
incidental, or consequential damages of any character arising as a
|
|
160
|
+
result of this License or out of the use or inability to use the
|
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
163
|
+
other commercial damages or losses), even if such Contributor
|
|
164
|
+
has been advised of the possibility of such damages.
|
|
165
|
+
|
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
169
|
+
or other liability obligations and/or rights consistent with this
|
|
170
|
+
License. However, in accepting such obligations, You may act only
|
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
175
|
+
of your accepting any such warranty or additional liability.
|
|
176
|
+
|
|
177
|
+
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
180
|
+
|
|
181
|
+
To apply the Apache License to your work, attach the following
|
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
183
|
+
replaced with your own identifying information. (Don't include
|
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
185
|
+
comment syntax for the file format. We also recommend that a
|
|
186
|
+
file or class name and description of purpose be included on the
|
|
187
|
+
same "printed page" as the copyright notice for easier
|
|
188
|
+
identification within third-party archives.
|
|
189
|
+
|
|
190
|
+
Copyright 2020 Elastic and contributors
|
|
191
|
+
|
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
193
|
+
you may not use this file except in compliance with the License.
|
|
194
|
+
You may obtain a copy of the License at
|
|
195
|
+
|
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
197
|
+
|
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
201
|
+
See the License for the specific language governing permissions and
|
|
202
|
+
limitations under the License.
|
data/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Logstash Plugin
|
|
2
2
|
|
|
3
|
-
[](https://travis-ci.com/logstash-plugins/logstash-filter-csv)
|
|
4
4
|
|
|
5
5
|
This is a plugin for [Logstash](https://github.com/elastic/logstash).
|
|
6
6
|
|
data/VERSION
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
3.1.0
|
data/docs/index.asciidoc
CHANGED
|
@@ -21,8 +21,14 @@ include::{include_path}/plugin_header.asciidoc[]
|
|
|
21
21
|
==== Description
|
|
22
22
|
|
|
23
23
|
The CSV filter takes an event field containing CSV data, parses it,
|
|
24
|
-
and stores it as individual fields
|
|
25
|
-
This filter can
|
|
24
|
+
and stores it as individual fields with optionally-specified field names.
|
|
25
|
+
This filter can parse data with any separator, not just commas.
|
|
26
|
+
|
|
27
|
+
[id="plugins-{type}s-{plugin}-ecs_metadata"]
|
|
28
|
+
==== Event Metadata and the Elastic Common Schema (ECS)
|
|
29
|
+
The plugin behaves the same regardless of ECS compatibility, except giving a warning when ECS is enabled and `target` isn't set.
|
|
30
|
+
|
|
31
|
+
TIP: Set the `target` option to avoid potential schema conflicts.
|
|
26
32
|
|
|
27
33
|
[id="plugins-{type}s-{plugin}-options"]
|
|
28
34
|
==== Csv Filter Configuration Options
|
|
@@ -36,9 +42,12 @@ This plugin supports the following configuration options plus the <<plugins-{typ
|
|
|
36
42
|
| <<plugins-{type}s-{plugin}-autogenerate_column_names>> |<<boolean,boolean>>|No
|
|
37
43
|
| <<plugins-{type}s-{plugin}-columns>> |<<array,array>>|No
|
|
38
44
|
| <<plugins-{type}s-{plugin}-convert>> |<<hash,hash>>|No
|
|
45
|
+
| <<plugins-{type}s-{plugin}-ecs_compatibility>> | <<string,string>>|No
|
|
39
46
|
| <<plugins-{type}s-{plugin}-quote_char>> |<<string,string>>|No
|
|
40
47
|
| <<plugins-{type}s-{plugin}-separator>> |<<string,string>>|No
|
|
41
48
|
| <<plugins-{type}s-{plugin}-skip_empty_columns>> |<<boolean,boolean>>|No
|
|
49
|
+
| <<plugins-{type}s-{plugin}-skip_empty_rows>> |<<boolean,boolean>>|No
|
|
50
|
+
| <<plugins-{type}s-{plugin}-skip_header>> |<<boolean,boolean>>|No
|
|
42
51
|
| <<plugins-{type}s-{plugin}-source>> |<<string,string>>|No
|
|
43
52
|
| <<plugins-{type}s-{plugin}-target>> |<<string,string>>|No
|
|
44
53
|
|=======================================================================
|
|
@@ -57,6 +66,8 @@ filter plugins.
|
|
|
57
66
|
Define whether column names should be auto-detected from the header column or not.
|
|
58
67
|
Defaults to false.
|
|
59
68
|
|
|
69
|
+
Logstash pipeline workers must be set to `1` for this option to work.
|
|
70
|
+
|
|
60
71
|
[id="plugins-{type}s-{plugin}-autogenerate_column_names"]
|
|
61
72
|
===== `autogenerate_column_names`
|
|
62
73
|
|
|
@@ -88,7 +99,8 @@ in the data than specified in this column list, extra columns will be auto-numbe
|
|
|
88
99
|
Define a set of datatype conversions to be applied to columns.
|
|
89
100
|
Possible conversions are integer, float, date, date_time, boolean
|
|
90
101
|
|
|
91
|
-
|
|
102
|
+
Example:
|
|
103
|
+
|
|
92
104
|
[source,ruby]
|
|
93
105
|
filter {
|
|
94
106
|
csv {
|
|
@@ -99,6 +111,18 @@ Possible conversions are integer, float, date, date_time, boolean
|
|
|
99
111
|
}
|
|
100
112
|
}
|
|
101
113
|
|
|
114
|
+
[id="plugins-{type}s-{plugin}-ecs_compatibility"]
|
|
115
|
+
===== `ecs_compatibility`
|
|
116
|
+
|
|
117
|
+
* Value type is <<string,string>>
|
|
118
|
+
* Supported values are:
|
|
119
|
+
** `disabled`: does not use ECS-compatible field names
|
|
120
|
+
** `v1`: uses the value in `target` as field name
|
|
121
|
+
|
|
122
|
+
Controls this plugin's compatibility with the
|
|
123
|
+
{ecs-ref}[Elastic Common Schema (ECS)].
|
|
124
|
+
See <<plugins-{type}s-{plugin}-ecs_metadata>> for detailed information.
|
|
125
|
+
|
|
102
126
|
[id="plugins-{type}s-{plugin}-quote_char"]
|
|
103
127
|
===== `quote_char`
|
|
104
128
|
|
|
@@ -129,6 +153,33 @@ Optional.
|
|
|
129
153
|
Define whether empty columns should be skipped.
|
|
130
154
|
Defaults to false. If set to true, columns containing no value will not get set.
|
|
131
155
|
|
|
156
|
+
[id="plugins-{type}s-{plugin}-skip_empty_rows"]
|
|
157
|
+
===== `skip_empty_rows`
|
|
158
|
+
|
|
159
|
+
* Value type is <<boolean,boolean>>
|
|
160
|
+
* Default value is `false`
|
|
161
|
+
|
|
162
|
+
Define whether empty rows could potentially be skipped.
|
|
163
|
+
Defaults to false. If set to true, rows containing no value will be tagged with "_csvskippedemptyfield".
|
|
164
|
+
This tag can referenced by users if they wish to cancel events using an 'if' conditional statement.
|
|
165
|
+
|
|
166
|
+
[id="plugins-{type}s-{plugin}-skip_header"]
|
|
167
|
+
===== `skip_header`
|
|
168
|
+
|
|
169
|
+
* Value type is <<boolean,boolean>>
|
|
170
|
+
* Default value is `false`
|
|
171
|
+
|
|
172
|
+
Define whether the header should be skipped.
|
|
173
|
+
Defaults to false. If set to true, the header will be skipped.
|
|
174
|
+
Assumes that header is not repeated within further rows as such rows will also be skipped.
|
|
175
|
+
If `skip_header` is set without `autodetect_column_names` being set then columns should be set which
|
|
176
|
+
will result in the skipping of any row that exactly matches the specified column values.
|
|
177
|
+
If `skip_header` and `autodetect_column_names` are specified then columns should not be specified, in this case
|
|
178
|
+
`autodetect_column_names` will fill the columns setting in the background, from the first event seen, and any
|
|
179
|
+
subsequent values that match what was autodetected will be skipped.
|
|
180
|
+
|
|
181
|
+
Logstash pipeline workers must be set to `1` for this option to work.
|
|
182
|
+
|
|
132
183
|
[id="plugins-{type}s-{plugin}-source"]
|
|
133
184
|
===== `source`
|
|
134
185
|
|
|
@@ -148,6 +199,5 @@ Define target field for placing the data.
|
|
|
148
199
|
Defaults to writing to the root of the event.
|
|
149
200
|
|
|
150
201
|
|
|
151
|
-
|
|
152
202
|
[id="plugins-{type}s-{plugin}-common-options"]
|
|
153
|
-
include::{include_path}/{type}.asciidoc[]
|
|
203
|
+
include::{include_path}/{type}.asciidoc[]
|
data/lib/logstash/filters/csv.rb
CHANGED
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
# encoding: utf-8
|
|
2
2
|
require "logstash/filters/base"
|
|
3
3
|
require "logstash/namespace"
|
|
4
|
+
require "logstash/plugin_mixins/ecs_compatibility_support"
|
|
4
5
|
|
|
5
6
|
require "csv"
|
|
6
7
|
|
|
@@ -8,6 +9,8 @@ require "csv"
|
|
|
8
9
|
# and stores it as individual fields (can optionally specify the names).
|
|
9
10
|
# This filter can also parse data with any separator, not just commas.
|
|
10
11
|
class LogStash::Filters::CSV < LogStash::Filters::Base
|
|
12
|
+
include LogStash::PluginMixins::ECSCompatibilitySupport(:disabled, :v1, :v8 => :v1)
|
|
13
|
+
|
|
11
14
|
config_name "csv"
|
|
12
15
|
|
|
13
16
|
# The CSV data in the value of the `source` field will be expanded into a
|
|
@@ -41,10 +44,19 @@ class LogStash::Filters::CSV < LogStash::Filters::Base
|
|
|
41
44
|
# Defaults to true. If set to false, columns not having a header specified will not be parsed.
|
|
42
45
|
config :autogenerate_column_names, :validate => :boolean, :default => true
|
|
43
46
|
|
|
47
|
+
# Define whether the header should be skipped or not
|
|
48
|
+
# Defaults to false, If set to true, the header is dropped
|
|
49
|
+
config :skip_header, :validate => :boolean, :default => false
|
|
50
|
+
|
|
44
51
|
# Define whether empty columns should be skipped.
|
|
45
52
|
# Defaults to false. If set to true, columns containing no value will not get set.
|
|
46
53
|
config :skip_empty_columns, :validate => :boolean, :default => false
|
|
47
54
|
|
|
55
|
+
# Define whether empty rows could potentially be skipped.
|
|
56
|
+
# Defaults to false. If set to true, rows containing no value will be tagged with _csvskippedemptyfield.
|
|
57
|
+
# This tag can referenced by users if they wish to cancel events using an 'if' conditional statement.
|
|
58
|
+
config :skip_empty_rows, :validate => :boolean, :default => false
|
|
59
|
+
|
|
48
60
|
# Define a set of datatype conversions to be applied to columns.
|
|
49
61
|
# Possible conversions are integer, float, date, date_time, boolean
|
|
50
62
|
#
|
|
@@ -93,6 +105,15 @@ class LogStash::Filters::CSV < LogStash::Filters::Base
|
|
|
93
105
|
CONVERTERS.default = lambda {|v| v}
|
|
94
106
|
CONVERTERS.freeze
|
|
95
107
|
|
|
108
|
+
def initialize(params)
|
|
109
|
+
super
|
|
110
|
+
if ecs_compatibility != :disabled && @target.nil?
|
|
111
|
+
logger.info('ECS compatibility is enabled but no ``target`` option was specified, it is recommended'\
|
|
112
|
+
' to set the option to avoid potential schema conflicts (if your data is ECS compliant or'\
|
|
113
|
+
' non-conflicting feel free to ignore this message)')
|
|
114
|
+
end
|
|
115
|
+
end
|
|
116
|
+
|
|
96
117
|
def register
|
|
97
118
|
# validate conversion types to be the valid ones.
|
|
98
119
|
bad_types = @convert.values.select do |type|
|
|
@@ -105,7 +126,7 @@ class LogStash::Filters::CSV < LogStash::Filters::Base
|
|
|
105
126
|
@convert_symbols = @convert.inject({}){|result, (k, v)| result[k] = v.to_sym; result}
|
|
106
127
|
|
|
107
128
|
# make sure @target is in the format [field name] if defined, i.e. surrounded by brakets
|
|
108
|
-
@target = "[#{@target}]" if @target &&
|
|
129
|
+
@target = "[#{@target}]" if @target && !@target.start_with?("[")
|
|
109
130
|
|
|
110
131
|
# if the zero byte character is entered in the config, set the value
|
|
111
132
|
if (@quote_char == "\\x00")
|
|
@@ -120,7 +141,8 @@ class LogStash::Filters::CSV < LogStash::Filters::Base
|
|
|
120
141
|
|
|
121
142
|
if (source = event.get(@source))
|
|
122
143
|
begin
|
|
123
|
-
|
|
144
|
+
|
|
145
|
+
values = CSV.parse_line(source, :col_sep => @separator, :quote_char => @quote_char)
|
|
124
146
|
|
|
125
147
|
if (@autodetect_column_names && @columns.empty?)
|
|
126
148
|
@columns = values
|
|
@@ -128,6 +150,17 @@ class LogStash::Filters::CSV < LogStash::Filters::Base
|
|
|
128
150
|
return
|
|
129
151
|
end
|
|
130
152
|
|
|
153
|
+
if (@skip_header && (!@columns.empty?) && (@columns == values))
|
|
154
|
+
event.cancel
|
|
155
|
+
return
|
|
156
|
+
end
|
|
157
|
+
|
|
158
|
+
if(@skip_empty_rows && values.nil?)
|
|
159
|
+
# applies tag to empty rows, users can cancel event referencing this tag in an 'if' conditional statement
|
|
160
|
+
event.tag("_csvskippedemptyfield")
|
|
161
|
+
return
|
|
162
|
+
end
|
|
163
|
+
|
|
131
164
|
values.each_index do |i|
|
|
132
165
|
unless (@skip_empty_columns && (values[i].nil? || values[i].empty?))
|
|
133
166
|
unless ignore_field?(i)
|
|
@@ -151,10 +184,14 @@ class LogStash::Filters::CSV < LogStash::Filters::Base
|
|
|
151
184
|
private
|
|
152
185
|
|
|
153
186
|
# construct the correct Event field reference for given field_name, taking into account @target
|
|
154
|
-
# @param field_name [String] the
|
|
187
|
+
# @param field_name [String] the field name.
|
|
155
188
|
# @return [String] fully qualified Event field reference also taking into account @target prefix
|
|
156
189
|
def field_ref(field_name)
|
|
157
|
-
"
|
|
190
|
+
if field_name.start_with?("[")
|
|
191
|
+
"#{@target}#{field_name}"
|
|
192
|
+
else
|
|
193
|
+
"#{@target}[#{field_name}]"
|
|
194
|
+
end
|
|
158
195
|
end
|
|
159
196
|
|
|
160
197
|
def ignore_field?(index)
|
data/logstash-filter-csv.gemspec
CHANGED
|
@@ -1,9 +1,11 @@
|
|
|
1
|
+
CSV_VERSION = File.read(File.expand_path(File.join(File.dirname(__FILE__), "VERSION"))).strip unless defined?(CSV_VERSION)
|
|
2
|
+
|
|
1
3
|
Gem::Specification.new do |s|
|
|
2
4
|
|
|
3
5
|
s.name = 'logstash-filter-csv'
|
|
4
|
-
s.version =
|
|
6
|
+
s.version = CSV_VERSION
|
|
5
7
|
s.licenses = ['Apache License (2.0)']
|
|
6
|
-
s.summary = "
|
|
8
|
+
s.summary = "Parses comma-separated value data into individual fields"
|
|
7
9
|
s.description = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program"
|
|
8
10
|
s.authors = ["Elastic"]
|
|
9
11
|
s.email = 'info@elastic.co'
|
|
@@ -21,7 +23,7 @@ Gem::Specification.new do |s|
|
|
|
21
23
|
|
|
22
24
|
# Gem dependencies
|
|
23
25
|
s.add_runtime_dependency "logstash-core-plugin-api", ">= 1.60", "<= 2.99"
|
|
24
|
-
|
|
25
26
|
s.add_development_dependency 'logstash-devutils'
|
|
27
|
+
s.add_runtime_dependency 'logstash-mixin-ecs_compatibility_support', '~>1.2'
|
|
26
28
|
end
|
|
27
29
|
|
data/spec/filters/csv_spec.rb
CHANGED
|
@@ -1,224 +1,260 @@
|
|
|
1
1
|
# encoding: utf-8
|
|
2
2
|
require "logstash/devutils/rspec/spec_helper"
|
|
3
3
|
require "logstash/filters/csv"
|
|
4
|
+
require 'logstash/plugin_mixins/ecs_compatibility_support/spec_helper'
|
|
4
5
|
|
|
5
|
-
describe LogStash::Filters::CSV do
|
|
6
|
+
describe LogStash::Filters::CSV, :ecs_compatibility_support, :aggregate_failures do
|
|
7
|
+
ecs_compatibility_matrix(:disabled, :v1, :v8 => :v1) do |ecs_select|
|
|
6
8
|
|
|
7
|
-
|
|
8
|
-
|
|
9
|
+
subject(:plugin) { LogStash::Filters::CSV.new(config) }
|
|
10
|
+
let(:config) { Hash.new }
|
|
9
11
|
|
|
10
|
-
|
|
11
|
-
|
|
12
|
+
let(:doc) { "" }
|
|
13
|
+
let(:event) { LogStash::Event.new("message" => doc) }
|
|
12
14
|
|
|
13
|
-
|
|
15
|
+
describe "registration" do
|
|
14
16
|
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
|
|
17
|
+
context "when using invalid data types" do
|
|
18
|
+
let(:config) do
|
|
19
|
+
{ "convert" => { "custom1" => "integer", "custom3" => "wrong_type" },
|
|
20
|
+
"columns" => ["custom1", "custom2", "custom3"] }
|
|
21
|
+
end
|
|
20
22
|
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
23
|
+
it "should register" do
|
|
24
|
+
input = LogStash::Plugin.lookup("filter", "csv").new(config)
|
|
25
|
+
expect {input.register}.to raise_error(LogStash::ConfigurationError)
|
|
26
|
+
end
|
|
24
27
|
end
|
|
25
28
|
end
|
|
26
|
-
end
|
|
27
|
-
|
|
28
|
-
describe "receive" do
|
|
29
|
-
|
|
30
|
-
before(:each) do
|
|
31
|
-
plugin.register
|
|
32
|
-
end
|
|
33
|
-
|
|
34
|
-
describe "all defaults" do
|
|
35
29
|
|
|
36
|
-
|
|
30
|
+
describe "receive" do
|
|
37
31
|
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
plugin.filter(event)
|
|
42
|
-
expect(event.get("column1")).to eq("big")
|
|
43
|
-
expect(event.get("column2")).to eq("bird")
|
|
44
|
-
expect(event.get("column3")).to eq("sesame street")
|
|
32
|
+
before(:each) do
|
|
33
|
+
allow_any_instance_of(described_class).to receive(:ecs_compatibility).and_return(ecs_compatibility)
|
|
34
|
+
plugin.register
|
|
45
35
|
end
|
|
46
36
|
|
|
47
|
-
|
|
48
|
-
plugin.filter(event)
|
|
49
|
-
expect(event.get("message")).to be_kind_of(String)
|
|
50
|
-
end
|
|
51
|
-
end
|
|
37
|
+
describe "all defaults" do
|
|
52
38
|
|
|
53
|
-
|
|
54
|
-
let(:doc) { "big,bird;sesame street" }
|
|
39
|
+
let(:config) { Hash.new }
|
|
55
40
|
|
|
56
|
-
|
|
57
|
-
{ "separator" => ";" }
|
|
58
|
-
end
|
|
59
|
-
it "extract all the values" do
|
|
60
|
-
plugin.filter(event)
|
|
61
|
-
expect(event.get("column1")).to eq("big,bird")
|
|
62
|
-
expect(event.get("column2")).to eq("sesame street")
|
|
63
|
-
end
|
|
64
|
-
end
|
|
41
|
+
let(:doc) { "big,bird,sesame street" }
|
|
65
42
|
|
|
66
|
-
|
|
67
|
-
|
|
43
|
+
it "extract all the values" do
|
|
44
|
+
plugin.filter(event)
|
|
45
|
+
expect(event.get("column1")).to eq("big")
|
|
46
|
+
expect(event.get("column2")).to eq("bird")
|
|
47
|
+
expect(event.get("column3")).to eq("sesame street")
|
|
48
|
+
end
|
|
68
49
|
|
|
69
|
-
|
|
70
|
-
|
|
50
|
+
it "should not mutate the source field" do
|
|
51
|
+
plugin.filter(event)
|
|
52
|
+
expect(event.get("message")).to be_kind_of(String)
|
|
53
|
+
end
|
|
71
54
|
end
|
|
72
55
|
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
expect(event.get("column1")).to eq("big")
|
|
76
|
-
expect(event.get("column2")).to eq("bird")
|
|
77
|
-
expect(event.get("column3")).to eq("sesame street")
|
|
78
|
-
end
|
|
56
|
+
describe "empty message" do
|
|
57
|
+
let(:doc) { "" }
|
|
79
58
|
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
59
|
+
let(:config) do
|
|
60
|
+
{ "skip_empty_rows" => true }
|
|
61
|
+
end
|
|
83
62
|
|
|
84
|
-
it "
|
|
63
|
+
it "skips empty rows" do
|
|
85
64
|
plugin.filter(event)
|
|
86
|
-
expect(event.get("
|
|
87
|
-
expect(event
|
|
88
|
-
expect(event.get("column3")).to eq("sesame, street")
|
|
65
|
+
expect(event.get("tags")).to include("_csvskippedemptyfield")
|
|
66
|
+
expect(event).not_to be_cancelled
|
|
89
67
|
end
|
|
90
68
|
end
|
|
91
69
|
|
|
92
|
-
|
|
93
|
-
let(:doc) {
|
|
70
|
+
describe "custom separator" do
|
|
71
|
+
let(:doc) { "big,bird;sesame street" }
|
|
72
|
+
|
|
94
73
|
let(:config) do
|
|
95
|
-
{ "
|
|
74
|
+
{ "separator" => ";" }
|
|
96
75
|
end
|
|
97
|
-
|
|
98
76
|
it "extract all the values" do
|
|
99
77
|
plugin.filter(event)
|
|
100
|
-
expect(event.get("column1")).to eq("big")
|
|
101
|
-
expect(event.get("column2")).to eq("
|
|
102
|
-
expect(event.get("column3")).to eq('"sesame" street')
|
|
78
|
+
expect(event.get("column1")).to eq("big,bird")
|
|
79
|
+
expect(event.get("column2")).to eq("sesame street")
|
|
103
80
|
end
|
|
104
81
|
end
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
let(:doc) {
|
|
82
|
+
|
|
83
|
+
describe "quote char" do
|
|
84
|
+
let(:doc) { "big,bird,'sesame street'" }
|
|
85
|
+
|
|
108
86
|
let(:config) do
|
|
109
|
-
{ "quote_char" => "
|
|
87
|
+
{ "quote_char" => "'"}
|
|
110
88
|
end
|
|
111
89
|
|
|
112
90
|
it "extract all the values" do
|
|
113
91
|
plugin.filter(event)
|
|
114
92
|
expect(event.get("column1")).to eq("big")
|
|
115
93
|
expect(event.get("column2")).to eq("bird")
|
|
116
|
-
expect(event.get("column3")).to eq(
|
|
94
|
+
expect(event.get("column3")).to eq("sesame street")
|
|
117
95
|
end
|
|
118
|
-
end
|
|
119
|
-
end
|
|
120
96
|
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
{ "columns" => ["first", "last", "address" ] }
|
|
125
|
-
end
|
|
97
|
+
context "using the default one" do
|
|
98
|
+
let(:doc) { 'big,bird,"sesame, street"' }
|
|
99
|
+
let(:config) { Hash.new }
|
|
126
100
|
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
|
|
101
|
+
it "extract all the values" do
|
|
102
|
+
plugin.filter(event)
|
|
103
|
+
expect(event.get("column1")).to eq("big")
|
|
104
|
+
expect(event.get("column2")).to eq("bird")
|
|
105
|
+
expect(event.get("column3")).to eq("sesame, street")
|
|
106
|
+
end
|
|
107
|
+
end
|
|
108
|
+
|
|
109
|
+
context "using a null" do
|
|
110
|
+
let(:doc) { 'big,bird,"sesame" street' }
|
|
111
|
+
let(:config) do
|
|
112
|
+
{ "quote_char" => "\x00" }
|
|
113
|
+
end
|
|
114
|
+
|
|
115
|
+
it "extract all the values" do
|
|
116
|
+
plugin.filter(event)
|
|
117
|
+
expect(event.get("column1")).to eq("big")
|
|
118
|
+
expect(event.get("column2")).to eq("bird")
|
|
119
|
+
expect(event.get("column3")).to eq('"sesame" street')
|
|
120
|
+
end
|
|
121
|
+
end
|
|
133
122
|
|
|
134
|
-
|
|
123
|
+
context "using a null as read from config" do
|
|
124
|
+
let(:doc) { 'big,bird,"sesame" street' }
|
|
125
|
+
let(:config) do
|
|
126
|
+
{ "quote_char" => "\\x00" }
|
|
127
|
+
end
|
|
128
|
+
|
|
129
|
+
it "extract all the values" do
|
|
130
|
+
plugin.filter(event)
|
|
131
|
+
expect(event.get("column1")).to eq("big")
|
|
132
|
+
expect(event.get("column2")).to eq("bird")
|
|
133
|
+
expect(event.get("column3")).to eq('"sesame" street')
|
|
134
|
+
end
|
|
135
|
+
end
|
|
136
|
+
end
|
|
135
137
|
|
|
136
|
-
|
|
138
|
+
describe "given column names" do
|
|
139
|
+
let(:doc) { "big,bird,sesame street" }
|
|
137
140
|
let(:config) do
|
|
138
|
-
{
|
|
139
|
-
"columns" => ["custom1", "custom2"] }
|
|
141
|
+
{ "columns" => ["first", "last", "address" ] }
|
|
140
142
|
end
|
|
141
143
|
|
|
142
144
|
it "extract all the values" do
|
|
143
145
|
plugin.filter(event)
|
|
144
|
-
expect(event.get("
|
|
145
|
-
expect(event.get("
|
|
146
|
-
expect(event.get("
|
|
146
|
+
expect(event.get("first")).to eq("big")
|
|
147
|
+
expect(event.get("last")).to eq("bird")
|
|
148
|
+
expect(event.get("address")).to eq("sesame street")
|
|
147
149
|
end
|
|
148
|
-
end
|
|
149
150
|
|
|
150
|
-
|
|
151
|
+
context "parse csv without autogeneration of names" do
|
|
151
152
|
|
|
152
|
-
|
|
153
|
+
let(:doc) { "val1,val2,val3" }
|
|
154
|
+
let(:config) do
|
|
155
|
+
{ "autogenerate_column_names" => false,
|
|
156
|
+
"columns" => ["custom1", "custom2"] }
|
|
157
|
+
end
|
|
153
158
|
|
|
154
|
-
|
|
155
|
-
|
|
156
|
-
"
|
|
157
|
-
"
|
|
159
|
+
it "extract all the values" do
|
|
160
|
+
plugin.filter(event)
|
|
161
|
+
expect(event.get("custom1")).to eq("val1")
|
|
162
|
+
expect(event.get("custom2")).to eq("val2")
|
|
163
|
+
expect(event.get("column3")).to be_falsey
|
|
164
|
+
end
|
|
158
165
|
end
|
|
159
166
|
|
|
160
|
-
let(:event) { LogStash::Event.new("datafield" => doc) }
|
|
161
167
|
|
|
162
|
-
|
|
163
|
-
plugin.filter(event)
|
|
164
|
-
expect(event.get("custom1")).to eq("val1")
|
|
165
|
-
expect(event.get("custom2")).to be_falsey
|
|
166
|
-
expect(event.get("custom3")).to eq("val3")
|
|
167
|
-
end
|
|
168
|
-
end
|
|
168
|
+
context "parse csv and skip the header" do
|
|
169
169
|
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
170
|
+
let(:doc) { "first_column,second_column,third_column" }
|
|
171
|
+
let(:config) do
|
|
172
|
+
{ "skip_header" => true,
|
|
173
|
+
"columns" => ["first_column", "second_column", "third_column"] }
|
|
174
|
+
end
|
|
175
|
+
|
|
176
|
+
it "expects the event to be cancelled" do
|
|
177
|
+
plugin.filter(event)
|
|
178
|
+
expect(event).to be_cancelled
|
|
179
|
+
end
|
|
174
180
|
end
|
|
175
181
|
|
|
176
|
-
|
|
177
|
-
|
|
178
|
-
|
|
179
|
-
|
|
180
|
-
|
|
182
|
+
context "parse csv skipping empty columns" do
|
|
183
|
+
|
|
184
|
+
let(:doc) { "val1,,val3" }
|
|
185
|
+
|
|
186
|
+
let(:config) do
|
|
187
|
+
{ "skip_empty_columns" => true,
|
|
188
|
+
"source" => "datafield",
|
|
189
|
+
"columns" => ["custom1", "custom2", "custom3"] }
|
|
190
|
+
end
|
|
191
|
+
|
|
192
|
+
let(:event) { LogStash::Event.new("datafield" => doc) }
|
|
193
|
+
|
|
194
|
+
it "extract all the values" do
|
|
195
|
+
plugin.filter(event)
|
|
196
|
+
expect(event.get("custom1")).to eq("val1")
|
|
197
|
+
expect(event.get("custom2")).to be_falsey
|
|
198
|
+
expect(event.get("custom3")).to eq("val3")
|
|
199
|
+
end
|
|
181
200
|
end
|
|
182
|
-
end
|
|
183
201
|
|
|
184
|
-
|
|
185
|
-
|
|
186
|
-
|
|
187
|
-
|
|
188
|
-
|
|
202
|
+
context "parse csv with more data than defined" do
|
|
203
|
+
let(:doc) { "val1,val2,val3" }
|
|
204
|
+
let(:config) do
|
|
205
|
+
{ "columns" => ["custom1", "custom2"] }
|
|
206
|
+
end
|
|
207
|
+
|
|
208
|
+
it "extract all the values" do
|
|
209
|
+
plugin.filter(event)
|
|
210
|
+
expect(event.get("custom1")).to eq("val1")
|
|
211
|
+
expect(event.get("custom2")).to eq("val2")
|
|
212
|
+
expect(event.get("column3")).to eq("val3")
|
|
213
|
+
end
|
|
189
214
|
end
|
|
190
|
-
let(:event) { LogStash::Event.new("datafield" => doc) }
|
|
191
215
|
|
|
192
|
-
|
|
193
|
-
|
|
194
|
-
|
|
195
|
-
|
|
196
|
-
|
|
216
|
+
context "parse csv from a given source" do
|
|
217
|
+
let(:doc) { "val1,val2,val3" }
|
|
218
|
+
let(:config) do
|
|
219
|
+
{ "source" => "datafield",
|
|
220
|
+
"columns" => ["custom1", "custom2", "custom3"] }
|
|
221
|
+
end
|
|
222
|
+
let(:event) { LogStash::Event.new("datafield" => doc) }
|
|
223
|
+
|
|
224
|
+
it "extract all the values" do
|
|
225
|
+
plugin.filter(event)
|
|
226
|
+
expect(event.get("custom1")).to eq("val1")
|
|
227
|
+
expect(event.get("custom2")).to eq("val2")
|
|
228
|
+
expect(event.get("custom3")).to eq("val3")
|
|
229
|
+
end
|
|
197
230
|
end
|
|
198
|
-
end
|
|
199
|
-
end
|
|
200
231
|
|
|
201
|
-
|
|
202
|
-
|
|
203
|
-
|
|
204
|
-
|
|
205
|
-
|
|
206
|
-
|
|
207
|
-
|
|
208
|
-
|
|
209
|
-
|
|
210
|
-
|
|
211
|
-
|
|
212
|
-
|
|
232
|
+
context "that use [@metadata]" do
|
|
233
|
+
let(:metadata_field) { "[@metadata][one]" }
|
|
234
|
+
let(:config) do
|
|
235
|
+
{
|
|
236
|
+
"columns" => [ metadata_field, "foo" ]
|
|
237
|
+
}
|
|
238
|
+
end
|
|
239
|
+
|
|
240
|
+
let(:event) { LogStash::Event.new("message" => "hello,world") }
|
|
241
|
+
|
|
242
|
+
before do
|
|
243
|
+
plugin.filter(event)
|
|
244
|
+
end
|
|
245
|
+
|
|
246
|
+
it "should work correctly" do
|
|
247
|
+
expect(event.get(metadata_field)).to eq("hello")
|
|
248
|
+
end
|
|
249
|
+
end
|
|
213
250
|
end
|
|
214
251
|
|
|
215
|
-
|
|
252
|
+
describe "givin target" do
|
|
216
253
|
let(:config) do
|
|
217
|
-
{
|
|
218
|
-
"target" => "data" }
|
|
254
|
+
{ "target" => "data" }
|
|
219
255
|
end
|
|
220
|
-
let(:event) { LogStash::Event.new("datain" => doc) }
|
|
221
256
|
let(:doc) { "big,bird,sesame street" }
|
|
257
|
+
let(:event) { LogStash::Event.new("message" => doc) }
|
|
222
258
|
|
|
223
259
|
it "extract all the values" do
|
|
224
260
|
plugin.filter(event)
|
|
@@ -226,100 +262,152 @@ describe LogStash::Filters::CSV do
|
|
|
226
262
|
expect(event.get("data")["column2"]).to eq("bird")
|
|
227
263
|
expect(event.get("data")["column3"]).to eq("sesame street")
|
|
228
264
|
end
|
|
229
|
-
end
|
|
230
|
-
end
|
|
231
265
|
|
|
232
|
-
|
|
266
|
+
context "when having also source" do
|
|
267
|
+
let(:config) do
|
|
268
|
+
{ "source" => "datain",
|
|
269
|
+
"target" => "data" }
|
|
270
|
+
end
|
|
271
|
+
let(:event) { LogStash::Event.new("datain" => doc) }
|
|
272
|
+
let(:doc) { "big,bird,sesame street" }
|
|
273
|
+
|
|
274
|
+
it "extract all the values" do
|
|
275
|
+
plugin.filter(event)
|
|
276
|
+
expect(event.get("data")["column1"]).to eq("big")
|
|
277
|
+
expect(event.get("data")["column2"]).to eq("bird")
|
|
278
|
+
expect(event.get("data")["column3"]).to eq("sesame street")
|
|
279
|
+
end
|
|
280
|
+
end
|
|
233
281
|
|
|
234
|
-
|
|
235
|
-
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
|
|
239
|
-
"column4" => "float",
|
|
240
|
-
"column5" => "date",
|
|
241
|
-
"column6" => "date_time",
|
|
242
|
-
"column7" => "date",
|
|
243
|
-
"column8" => "date_time",
|
|
282
|
+
context "which uses [nested][fieldref] syntax" do
|
|
283
|
+
let(:target) { "[foo][bar]" }
|
|
284
|
+
let(:config) do
|
|
285
|
+
{
|
|
286
|
+
"target" => target
|
|
244
287
|
}
|
|
245
|
-
|
|
246
|
-
end
|
|
247
|
-
# 2017-06-01,2001-02-03T04:05:06+07:00
|
|
248
|
-
let(:doc) { "1234,bird,false,3.14159265359,2017-06-01,2001-02-03 04:05:06,invalid_date,invalid_date_time" }
|
|
249
|
-
let(:event) { LogStash::Event.new("message" => doc) }
|
|
288
|
+
end
|
|
250
289
|
|
|
251
|
-
|
|
252
|
-
plugin.filter(event)
|
|
253
|
-
expect(event.get("column1")).to eq(1234)
|
|
254
|
-
end
|
|
290
|
+
let(:event) { LogStash::Event.new("message" => "hello,world") }
|
|
255
291
|
|
|
256
|
-
|
|
257
|
-
|
|
258
|
-
|
|
259
|
-
end
|
|
292
|
+
before do
|
|
293
|
+
plugin.filter(event)
|
|
294
|
+
end
|
|
260
295
|
|
|
261
|
-
|
|
262
|
-
|
|
263
|
-
|
|
264
|
-
|
|
296
|
+
it "should set fields correctly in the target" do
|
|
297
|
+
expect(event.get("#{target}[column1]")).to eq("hello")
|
|
298
|
+
expect(event.get("#{target}[column2]")).to eq("world")
|
|
299
|
+
end
|
|
265
300
|
|
|
266
|
-
|
|
267
|
-
|
|
268
|
-
|
|
269
|
-
|
|
301
|
+
context "with nested fieldrefs as columns" do
|
|
302
|
+
let(:config) do
|
|
303
|
+
{
|
|
304
|
+
"target" => target,
|
|
305
|
+
"columns" => [ "[test][one]", "[test][two]" ]
|
|
306
|
+
}
|
|
307
|
+
end
|
|
270
308
|
|
|
271
|
-
|
|
272
|
-
|
|
273
|
-
|
|
274
|
-
|
|
275
|
-
|
|
309
|
+
it "should set fields correctly in the target" do
|
|
310
|
+
expect(event.get("#{target}[test][one]")).to eq("hello")
|
|
311
|
+
expect(event.get("#{target}[test][two]")).to eq("world")
|
|
312
|
+
end
|
|
313
|
+
end
|
|
276
314
|
|
|
277
|
-
|
|
278
|
-
plugin.filter(event)
|
|
279
|
-
expect(event.get("column6")).to be_a(LogStash::Timestamp)
|
|
280
|
-
expect(event.get("column6").to_s).to eq(LogStash::Timestamp.new(DateTime.parse("2001-02-03 04:05:06").to_time).to_s)
|
|
315
|
+
end
|
|
281
316
|
end
|
|
282
317
|
|
|
283
|
-
|
|
284
|
-
plugin.filter(event)
|
|
285
|
-
expect(event.get("column7")).to eq("invalid_date")
|
|
286
|
-
end
|
|
318
|
+
describe "using field convertion" do
|
|
287
319
|
|
|
288
|
-
|
|
289
|
-
|
|
290
|
-
|
|
291
|
-
|
|
320
|
+
let(:config) do
|
|
321
|
+
{
|
|
322
|
+
"convert" => {
|
|
323
|
+
"column1" => "integer",
|
|
324
|
+
"column3" => "boolean",
|
|
325
|
+
"column4" => "float",
|
|
326
|
+
"column5" => "date",
|
|
327
|
+
"column6" => "date_time",
|
|
328
|
+
"column7" => "date",
|
|
329
|
+
"column8" => "date_time",
|
|
330
|
+
}
|
|
331
|
+
}
|
|
332
|
+
end
|
|
333
|
+
# 2017-06-01,2001-02-03T04:05:06+07:00
|
|
334
|
+
let(:doc) { "1234,bird,false,3.14159265359,2017-06-01,2001-02-03 04:05:06,invalid_date,invalid_date_time" }
|
|
335
|
+
let(:event) { LogStash::Event.new("message" => doc) }
|
|
292
336
|
|
|
293
|
-
|
|
337
|
+
it "converts to integer" do
|
|
338
|
+
plugin.filter(event)
|
|
339
|
+
expect(event.get("column1")).to eq(1234)
|
|
340
|
+
end
|
|
294
341
|
|
|
295
|
-
|
|
296
|
-
|
|
297
|
-
|
|
342
|
+
it "does not convert without converter" do
|
|
343
|
+
plugin.filter(event)
|
|
344
|
+
expect(event.get("column2")).to eq("bird")
|
|
298
345
|
end
|
|
299
346
|
|
|
300
|
-
it "
|
|
347
|
+
it "converts to boolean" do
|
|
301
348
|
plugin.filter(event)
|
|
302
|
-
expect(event.get("
|
|
303
|
-
|
|
304
|
-
|
|
349
|
+
expect(event.get("column3")).to eq(false)
|
|
350
|
+
end
|
|
351
|
+
|
|
352
|
+
it "converts to float" do
|
|
353
|
+
plugin.filter(event)
|
|
354
|
+
expect(event.get("column4")).to eq(3.14159265359)
|
|
355
|
+
end
|
|
356
|
+
|
|
357
|
+
it "converts to date" do
|
|
358
|
+
plugin.filter(event)
|
|
359
|
+
expect(event.get("column5")).to be_a(LogStash::Timestamp)
|
|
360
|
+
expect(event.get("column5").to_s).to eq(LogStash::Timestamp.new(Date.parse("2017-06-01").to_time).to_s)
|
|
361
|
+
end
|
|
362
|
+
|
|
363
|
+
it "converts to date_time" do
|
|
364
|
+
plugin.filter(event)
|
|
365
|
+
expect(event.get("column6")).to be_a(LogStash::Timestamp)
|
|
366
|
+
expect(event.get("column6").to_s).to eq(LogStash::Timestamp.new(DateTime.parse("2001-02-03 04:05:06").to_time).to_s)
|
|
305
367
|
end
|
|
306
|
-
end
|
|
307
|
-
end
|
|
308
368
|
|
|
309
|
-
|
|
310
|
-
|
|
311
|
-
|
|
312
|
-
|
|
313
|
-
|
|
369
|
+
it "tries to converts to date but return original" do
|
|
370
|
+
plugin.filter(event)
|
|
371
|
+
expect(event.get("column7")).to eq("invalid_date")
|
|
372
|
+
end
|
|
373
|
+
|
|
374
|
+
it "tries to converts to date_time but return original" do
|
|
375
|
+
plugin.filter(event)
|
|
376
|
+
expect(event.get("column8")).to eq("invalid_date_time")
|
|
377
|
+
end
|
|
378
|
+
|
|
379
|
+
context "when using column names" do
|
|
380
|
+
|
|
381
|
+
let(:config) do
|
|
382
|
+
{ "convert" => { "custom1" => "integer", "custom3" => "boolean" },
|
|
383
|
+
"columns" => ["custom1", "custom2", "custom3"] }
|
|
384
|
+
end
|
|
385
|
+
|
|
386
|
+
it "get converted values to the expected type" do
|
|
387
|
+
plugin.filter(event)
|
|
388
|
+
expect(event.get("custom1")).to eq(1234)
|
|
389
|
+
expect(event.get("custom2")).to eq("bird")
|
|
390
|
+
expect(event.get("custom3")).to eq(false)
|
|
391
|
+
end
|
|
392
|
+
end
|
|
314
393
|
end
|
|
315
394
|
|
|
316
|
-
|
|
317
|
-
|
|
318
|
-
|
|
319
|
-
|
|
320
|
-
|
|
321
|
-
|
|
395
|
+
describe "given autodetect option" do
|
|
396
|
+
let(:header) { LogStash::Event.new("message" => "first,last,address") }
|
|
397
|
+
let(:doc) { "big,bird,sesame street" }
|
|
398
|
+
let(:config) do
|
|
399
|
+
{ "autodetect_column_names" => true }
|
|
400
|
+
end
|
|
401
|
+
|
|
402
|
+
it "extract all the values with the autodetected header" do
|
|
403
|
+
plugin.filter(header)
|
|
404
|
+
plugin.filter(event)
|
|
405
|
+
expect(event.get("first")).to eq("big")
|
|
406
|
+
expect(event.get("last")).to eq("bird")
|
|
407
|
+
expect(event.get("address")).to eq("sesame street")
|
|
408
|
+
end
|
|
322
409
|
end
|
|
323
410
|
end
|
|
411
|
+
|
|
324
412
|
end
|
|
325
413
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: logstash-filter-csv
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 3.0
|
|
4
|
+
version: 3.1.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Elastic
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2021-06-03 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -44,7 +44,23 @@ dependencies:
|
|
|
44
44
|
- - ">="
|
|
45
45
|
- !ruby/object:Gem::Version
|
|
46
46
|
version: '0'
|
|
47
|
-
|
|
47
|
+
- !ruby/object:Gem::Dependency
|
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
|
49
|
+
requirements:
|
|
50
|
+
- - "~>"
|
|
51
|
+
- !ruby/object:Gem::Version
|
|
52
|
+
version: '1.2'
|
|
53
|
+
name: logstash-mixin-ecs_compatibility_support
|
|
54
|
+
prerelease: false
|
|
55
|
+
type: :runtime
|
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
57
|
+
requirements:
|
|
58
|
+
- - "~>"
|
|
59
|
+
- !ruby/object:Gem::Version
|
|
60
|
+
version: '1.2'
|
|
61
|
+
description: This gem is a Logstash plugin required to be installed on top of the
|
|
62
|
+
Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This
|
|
63
|
+
gem is not a stand-alone program
|
|
48
64
|
email: info@elastic.co
|
|
49
65
|
executables: []
|
|
50
66
|
extensions: []
|
|
@@ -56,6 +72,7 @@ files:
|
|
|
56
72
|
- LICENSE
|
|
57
73
|
- NOTICE.TXT
|
|
58
74
|
- README.md
|
|
75
|
+
- VERSION
|
|
59
76
|
- docs/index.asciidoc
|
|
60
77
|
- lib/logstash/filters/csv.rb
|
|
61
78
|
- logstash-filter-csv.gemspec
|
|
@@ -82,9 +99,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
82
99
|
version: '0'
|
|
83
100
|
requirements: []
|
|
84
101
|
rubyforge_project:
|
|
85
|
-
rubygems_version: 2.
|
|
102
|
+
rubygems_version: 2.6.13
|
|
86
103
|
signing_key:
|
|
87
104
|
specification_version: 4
|
|
88
|
-
summary:
|
|
105
|
+
summary: Parses comma-separated value data into individual fields
|
|
89
106
|
test_files:
|
|
90
107
|
- spec/filters/csv_spec.rb
|