logstash-codec-csv 0.1.2 → 1.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/CHANGELOG.md +12 -0
- data/Gemfile +9 -0
- data/LICENSE +199 -10
- data/README.md +6 -1
- data/docs/index.asciidoc +185 -0
- data/lib/logstash/codecs/csv.rb +125 -88
- data/logstash-codec-csv.gemspec +7 -4
- data/spec/codecs/csv_spec.rb +208 -117
- metadata +57 -7
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: b0ee61a8601e503967b9682792838e941d543a8513eea39e16d427dae4539154
|
4
|
+
data.tar.gz: dd950c0a24b7ad601ed0fba1cf3344e9cd460a59af3151eca02cb16b2f885d01
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 9d085d074262a43fcc4f68d5b8dc83b41c8a56625b8f15429c786c85e92916256b719ca5511650dbed860d765148b386a6a84f68f9dd038d60533d9d2b47489b
|
7
|
+
data.tar.gz: e908a388ad958441e3fd8c5452bc8b2b078e75353a02c2988198ab14b9b829c8dc95d4e0fcee5fcbc42ef75a39521575b654701c54999e64eb1326c2afa5597b
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,15 @@
|
|
1
|
+
## 1.1.0
|
2
|
+
- Feat: added target => namespace support + ECS compatibility [#7](https://github.com/logstash-plugins/logstash-codec-csv/pull/7)
|
3
|
+
|
4
|
+
## 1.0.0
|
5
|
+
- Fixed dependencies to work with logstash v6 and up. Overhauled to match features of the CSV Filter. Improved spec coverage [#4](https://github.com/logstash-plugins/logstash-codec-csv/pull/4)
|
6
|
+
|
7
|
+
## 0.1.5
|
8
|
+
- Fixed asciidoc formatting for example [#3](https://github.com/logstash-plugins/logstash-codec-csv/pull/3)
|
9
|
+
|
10
|
+
## 0.1.4
|
11
|
+
- Fix some documentation issues
|
12
|
+
|
1
13
|
# 0.1.2
|
2
14
|
- Depend on logstash-core-plugin-api instead of logstash-core, removing the need to mass update plugins on major releases of logstash
|
3
15
|
# 0.1.1
|
data/Gemfile
CHANGED
@@ -1,2 +1,11 @@
|
|
1
1
|
source 'https://rubygems.org'
|
2
|
+
|
2
3
|
gemspec
|
4
|
+
|
5
|
+
logstash_path = ENV["LOGSTASH_PATH"] || "../../logstash"
|
6
|
+
use_logstash_source = ENV["LOGSTASH_SOURCE"] && ENV["LOGSTASH_SOURCE"].to_s == "1"
|
7
|
+
|
8
|
+
if Dir.exist?(logstash_path) && use_logstash_source
|
9
|
+
gem 'logstash-core', :path => "#{logstash_path}/logstash-core"
|
10
|
+
gem 'logstash-core-plugin-api', :path => "#{logstash_path}/logstash-core-plugin-api"
|
11
|
+
end
|
data/LICENSE
CHANGED
@@ -1,13 +1,202 @@
|
|
1
|
-
Copyright (c) 2012-2015 Elasticsearch <http://www.elasticsearch.org>
|
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
@@ -82,7 +82,12 @@ gem build logstash-filter-awesome.gemspec
|
|
82
82
|
```
|
83
83
|
- Install the plugin from the Logstash home
|
84
84
|
```sh
|
85
|
-
|
85
|
+
# Logstash 2.3 and higher
|
86
|
+
bin/logstash-plugin install --no-verify
|
87
|
+
|
88
|
+
# Prior to Logstash 2.3
|
89
|
+
bin/plugin install --no-verify
|
90
|
+
|
86
91
|
```
|
87
92
|
- Start Logstash and proceed to test the plugin
|
88
93
|
|
data/docs/index.asciidoc
ADDED
@@ -0,0 +1,185 @@
|
|
1
|
+
:plugin: csv
|
2
|
+
:type: codec
|
3
|
+
|
4
|
+
///////////////////////////////////////////
|
5
|
+
START - GENERATED VARIABLES, DO NOT EDIT!
|
6
|
+
///////////////////////////////////////////
|
7
|
+
:version: %VERSION%
|
8
|
+
:release_date: %RELEASE_DATE%
|
9
|
+
:changelog_url: %CHANGELOG_URL%
|
10
|
+
:include_path: ../../../../logstash/docs/include
|
11
|
+
///////////////////////////////////////////
|
12
|
+
END - GENERATED VARIABLES, DO NOT EDIT!
|
13
|
+
///////////////////////////////////////////
|
14
|
+
|
15
|
+
[id="plugins-{type}s-{plugin}"]
|
16
|
+
|
17
|
+
=== Csv codec plugin
|
18
|
+
|
19
|
+
include::{include_path}/plugin_header.asciidoc[]
|
20
|
+
|
21
|
+
==== Description
|
22
|
+
|
23
|
+
The csv codec takes CSV data, parses it and passes it along.
|
24
|
+
|
25
|
+
[id="plugins-{type}s-{plugin}-ecs"]
|
26
|
+
==== Compatibility with the Elastic Common Schema (ECS)
|
27
|
+
|
28
|
+
The plugin behaves the same regardless of ECS compatibility, except giving a warning when ECS is enabled and `target` isn't set.
|
29
|
+
|
30
|
+
TIP: Set the `target` option to avoid potential schema conflicts.
|
31
|
+
|
32
|
+
[id="plugins-{type}s-{plugin}-options"]
|
33
|
+
==== Csv Codec configuration options
|
34
|
+
|
35
|
+
[cols="<,<,<",options="header",]
|
36
|
+
|=======================================================================
|
37
|
+
|Setting |Input type|Required
|
38
|
+
| <<plugins-{type}s-{plugin}-autodetect_column_names>> |<<boolean,boolean>>|No
|
39
|
+
| <<plugins-{type}s-{plugin}-autogenerate_column_names>> |<<boolean,boolean>>|No
|
40
|
+
| <<plugins-{type}s-{plugin}-charset>> |<<string,string>>, one of `["ASCII-8BIT", "UTF-8", "US-ASCII", "Big5", "Big5-HKSCS", "Big5-UAO", "CP949", "Emacs-Mule", "EUC-JP", "EUC-KR", "EUC-TW", "GB2312", "GB18030", "GBK", "ISO-8859-1", "ISO-8859-2", "ISO-8859-3", "ISO-8859-4", "ISO-8859-5", "ISO-8859-6", "ISO-8859-7", "ISO-8859-8", "ISO-8859-9", "ISO-8859-10", "ISO-8859-11", "ISO-8859-13", "ISO-8859-14", "ISO-8859-15", "ISO-8859-16", "KOI8-R", "KOI8-U", "Shift_JIS", "UTF-16BE", "UTF-16LE", "UTF-32BE", "UTF-32LE", "Windows-31J", "Windows-1250", "Windows-1251", "Windows-1252", "IBM437", "IBM737", "IBM775", "CP850", "IBM852", "CP852", "IBM855", "CP855", "IBM857", "IBM860", "IBM861", "IBM862", "IBM863", "IBM864", "IBM865", "IBM866", "IBM869", "Windows-1258", "GB1988", "macCentEuro", "macCroatian", "macCyrillic", "macGreek", "macIceland", "macRoman", "macRomania", "macThai", "macTurkish", "macUkraine", "CP950", "CP951", "IBM037", "stateless-ISO-2022-JP", "eucJP-ms", "CP51932", "EUC-JIS-2004", "GB12345", "ISO-2022-JP", "ISO-2022-JP-2", "CP50220", "CP50221", "Windows-1256", "Windows-1253", "Windows-1255", "Windows-1254", "TIS-620", "Windows-874", "Windows-1257", "MacJapanese", "UTF-7", "UTF8-MAC", "UTF-16", "UTF-32", "UTF8-DoCoMo", "SJIS-DoCoMo", "UTF8-KDDI", "SJIS-KDDI", "ISO-2022-JP-KDDI", "stateless-ISO-2022-JP-KDDI", "UTF8-SoftBank", "SJIS-SoftBank", "BINARY", "CP437", "CP737", "CP775", "IBM850", "CP857", "CP860", "CP861", "CP862", "CP863", "CP864", "CP865", "CP866", "CP869", "CP1258", "Big5-HKSCS:2008", "ebcdic-cp-us", "eucJP", "euc-jp-ms", "EUC-JISX0213", "eucKR", "eucTW", "EUC-CN", "eucCN", "CP936", "ISO2022-JP", "ISO2022-JP2", "ISO8859-1", "ISO8859-2", "ISO8859-3", "ISO8859-4", "ISO8859-5", "ISO8859-6", "CP1256", "ISO8859-7", "CP1253", "ISO8859-8", "CP1255", "ISO8859-9", "CP1254", "ISO8859-10", "ISO8859-11", "CP874", "ISO8859-13", "CP1257", "ISO8859-14", "ISO8859-15", "ISO8859-16", "CP878", "MacJapan", "ASCII", "ANSI_X3.4-1968", "646", "CP65000", "CP65001", "UTF-8-MAC", "UTF-8-HFS", "UCS-2BE", "UCS-4BE", "UCS-4LE", "CP932", "csWindows31J", "SJIS", "PCK", "CP1250", "CP1251", "CP1252", "external", "locale"]`|No
|
41
|
+
| <<plugins-{type}s-{plugin}-columns>> |<<array,array>>|No
|
42
|
+
| <<plugins-{type}s-{plugin}-convert>> |<<hash,hash>>|No
|
43
|
+
| <<plugins-{type}s-{plugin}-ecs_compatibility>> |<<string,string>>|No
|
44
|
+
| <<plugins-{type}s-{plugin}-include_headers>> |<<boolean,boolean>>|No
|
45
|
+
| <<plugins-{type}s-{plugin}-quote_char>> |<<string,string>>|No
|
46
|
+
| <<plugins-{type}s-{plugin}-separator>> |<<string,string>>|No
|
47
|
+
| <<plugins-{type}s-{plugin}-skip_empty_columns>> |<<boolean,boolean>>|No
|
48
|
+
| <<plugins-{type}s-{plugin}-target>> |<<string,string>>|No
|
49
|
+
|=======================================================================
|
50
|
+
|
51
|
+
|
52
|
+
|
53
|
+
[id="plugins-{type}s-{plugin}-autodetect_column_names"]
|
54
|
+
===== `autodetect_column_names`
|
55
|
+
|
56
|
+
* Value type is <<boolean,boolean>>
|
57
|
+
* Default value is `false`
|
58
|
+
|
59
|
+
Define whether column names should be auto-detected from the header column or not.
|
60
|
+
Defaults to false.
|
61
|
+
|
62
|
+
[id="plugins-{type}s-{plugin}-autogenerate_column_names"]
|
63
|
+
===== `autogenerate_column_names`
|
64
|
+
|
65
|
+
* Value type is <<boolean,boolean>>
|
66
|
+
* Default value is `true`
|
67
|
+
|
68
|
+
Define whether column names should be autogenerated or not.
|
69
|
+
Defaults to true. If set to false, columns not having a header specified will not be parsed.
|
70
|
+
|
71
|
+
[id="plugins-{type}s-{plugin}-charset"]
|
72
|
+
===== `charset`
|
73
|
+
|
74
|
+
* Value can be any of: `ASCII-8BIT`, `UTF-8`, `US-ASCII`, `Big5`, `Big5-HKSCS`, `Big5-UAO`, `CP949`, `Emacs-Mule`, `EUC-JP`, `EUC-KR`, `EUC-TW`, `GB2312`, `GB18030`, `GBK`, `ISO-8859-1`, `ISO-8859-2`, `ISO-8859-3`, `ISO-8859-4`, `ISO-8859-5`, `ISO-8859-6`, `ISO-8859-7`, `ISO-8859-8`, `ISO-8859-9`, `ISO-8859-10`, `ISO-8859-11`, `ISO-8859-13`, `ISO-8859-14`, `ISO-8859-15`, `ISO-8859-16`, `KOI8-R`, `KOI8-U`, `Shift_JIS`, `UTF-16BE`, `UTF-16LE`, `UTF-32BE`, `UTF-32LE`, `Windows-31J`, `Windows-1250`, `Windows-1251`, `Windows-1252`, `IBM437`, `IBM737`, `IBM775`, `CP850`, `IBM852`, `CP852`, `IBM855`, `CP855`, `IBM857`, `IBM860`, `IBM861`, `IBM862`, `IBM863`, `IBM864`, `IBM865`, `IBM866`, `IBM869`, `Windows-1258`, `GB1988`, `macCentEuro`, `macCroatian`, `macCyrillic`, `macGreek`, `macIceland`, `macRoman`, `macRomania`, `macThai`, `macTurkish`, `macUkraine`, `CP950`, `CP951`, `IBM037`, `stateless-ISO-2022-JP`, `eucJP-ms`, `CP51932`, `EUC-JIS-2004`, `GB12345`, `ISO-2022-JP`, `ISO-2022-JP-2`, `CP50220`, `CP50221`, `Windows-1256`, `Windows-1253`, `Windows-1255`, `Windows-1254`, `TIS-620`, `Windows-874`, `Windows-1257`, `MacJapanese`, `UTF-7`, `UTF8-MAC`, `UTF-16`, `UTF-32`, `UTF8-DoCoMo`, `SJIS-DoCoMo`, `UTF8-KDDI`, `SJIS-KDDI`, `ISO-2022-JP-KDDI`, `stateless-ISO-2022-JP-KDDI`, `UTF8-SoftBank`, `SJIS-SoftBank`, `BINARY`, `CP437`, `CP737`, `CP775`, `IBM850`, `CP857`, `CP860`, `CP861`, `CP862`, `CP863`, `CP864`, `CP865`, `CP866`, `CP869`, `CP1258`, `Big5-HKSCS:2008`, `ebcdic-cp-us`, `eucJP`, `euc-jp-ms`, `EUC-JISX0213`, `eucKR`, `eucTW`, `EUC-CN`, `eucCN`, `CP936`, `ISO2022-JP`, `ISO2022-JP2`, `ISO8859-1`, `ISO8859-2`, `ISO8859-3`, `ISO8859-4`, `ISO8859-5`, `ISO8859-6`, `CP1256`, `ISO8859-7`, `CP1253`, `ISO8859-8`, `CP1255`, `ISO8859-9`, `CP1254`, `ISO8859-10`, `ISO8859-11`, `CP874`, `ISO8859-13`, `CP1257`, `ISO8859-14`, `ISO8859-15`, `ISO8859-16`, `CP878`, `MacJapan`, `ASCII`, `ANSI_X3.4-1968`, `646`, `CP65000`, `CP65001`, `UTF-8-MAC`, `UTF-8-HFS`, `UCS-2BE`, `UCS-4BE`, `UCS-4LE`, `CP932`, `csWindows31J`, `SJIS`, `PCK`, `CP1250`, `CP1251`, `CP1252`, `external`, `locale`
|
75
|
+
* Default value is `"UTF-8"`
|
76
|
+
|
77
|
+
List of valid conversion types used for the convert option
|
78
|
+
The character encoding used in this codec. Examples include "UTF-8" and
|
79
|
+
"CP1252".
|
80
|
+
|
81
|
+
[id="plugins-{type}s-{plugin}-columns"]
|
82
|
+
===== `columns`
|
83
|
+
|
84
|
+
* Value type is <<array,array>>
|
85
|
+
* Default value is `[]`
|
86
|
+
|
87
|
+
**When decoding:**
|
88
|
+
Define a list of column names (in the order they appear in the CSV,
|
89
|
+
as if it were a header line). If `columns` is not configured, or there
|
90
|
+
are not enough columns specified, the default column names are
|
91
|
+
"column1", "column2", etc.
|
92
|
+
|
93
|
+
**When encoding:**
|
94
|
+
List of fields names to include in the encoded CSV, in the order listed.
|
95
|
+
|
96
|
+
[id="plugins-{type}s-{plugin}-convert"]
|
97
|
+
===== `convert`
|
98
|
+
|
99
|
+
* Value type is <<hash,hash>>
|
100
|
+
* Default value is `{}`
|
101
|
+
|
102
|
+
Define a set of datatype conversions to be applied to columns.
|
103
|
+
Possible conversions are: `integer`, `float`, `date`, `date_time`, `boolean`
|
104
|
+
|
105
|
+
|
106
|
+
*Example*
|
107
|
+
[source,ruby]
|
108
|
+
filter {
|
109
|
+
csv {
|
110
|
+
convert => { "column1" => "integer", "column2" => "boolean" }
|
111
|
+
}
|
112
|
+
}
|
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`: CSV data added at root level
|
120
|
+
** `v1`,`v8`: Elastic Common Schema compliant behavior (`[event][original]` is also added)
|
121
|
+
* Default value depends on which version of Logstash is running:
|
122
|
+
** When Logstash provides a `pipeline.ecs_compatibility` setting, its value is used as the default
|
123
|
+
** Otherwise, the default value is `disabled`
|
124
|
+
|
125
|
+
Controls this plugin's compatibility with the {ecs-ref}[Elastic Common Schema (ECS)].
|
126
|
+
|
127
|
+
[id="plugins-{type}s-{plugin}-include_headers"]
|
128
|
+
===== `include_headers`
|
129
|
+
|
130
|
+
* Value type is <<boolean,boolean>>
|
131
|
+
* Default value is `false`
|
132
|
+
|
133
|
+
When **encoding** in an output plugin, include headers in the encoded CSV
|
134
|
+
once per codec lifecyle (not for every event). Default => false
|
135
|
+
|
136
|
+
[id="plugins-{type}s-{plugin}-quote_char"]
|
137
|
+
===== `quote_char`
|
138
|
+
|
139
|
+
* Value type is <<string,string>>
|
140
|
+
* Default value is `"\""`
|
141
|
+
|
142
|
+
Define the character used to quote CSV fields. If this is not specified
|
143
|
+
the default is a double quote `"`.
|
144
|
+
Optional.
|
145
|
+
|
146
|
+
[id="plugins-{type}s-{plugin}-separator"]
|
147
|
+
===== `separator`
|
148
|
+
|
149
|
+
* Value type is <<string,string>>
|
150
|
+
* Default value is `","`
|
151
|
+
|
152
|
+
Define the column separator value. If this is not specified, the default
|
153
|
+
is a comma `,`.
|
154
|
+
Optional.
|
155
|
+
|
156
|
+
[id="plugins-{type}s-{plugin}-skip_empty_columns"]
|
157
|
+
===== `skip_empty_columns`
|
158
|
+
|
159
|
+
* Value type is <<boolean,boolean>>
|
160
|
+
* Default value is `false`
|
161
|
+
|
162
|
+
Define whether empty columns should be skipped.
|
163
|
+
Defaults to false. If set to true, columns containing no value will not be included.
|
164
|
+
|
165
|
+
[id="plugins-{type}s-{plugin}-target"]
|
166
|
+
===== `target`
|
167
|
+
|
168
|
+
* Value type is <<string,string>>
|
169
|
+
* There is no default value for this setting.
|
170
|
+
|
171
|
+
Define the target field for placing the row values. If this setting is not
|
172
|
+
set, the CSV data will be stored at the root (top level) of the event.
|
173
|
+
|
174
|
+
For example, if you want data to be put under the `document` field:
|
175
|
+
[source,ruby]
|
176
|
+
input {
|
177
|
+
file {
|
178
|
+
codec => csv {
|
179
|
+
autodetect_column_names => true
|
180
|
+
target => "[document]"
|
181
|
+
}
|
182
|
+
}
|
183
|
+
}
|
184
|
+
|
185
|
+
|
data/lib/logstash/codecs/csv.rb
CHANGED
@@ -1,18 +1,34 @@
|
|
1
1
|
# encoding: utf-8
|
2
2
|
require "logstash/codecs/base"
|
3
3
|
require "logstash/util/charset"
|
4
|
+
require "logstash/event"
|
5
|
+
|
6
|
+
require 'logstash/plugin_mixins/ecs_compatibility_support'
|
7
|
+
require 'logstash/plugin_mixins/ecs_compatibility_support/target_check'
|
8
|
+
require 'logstash/plugin_mixins/validator_support/field_reference_validation_adapter'
|
9
|
+
require 'logstash/plugin_mixins/event_support/event_factory_adapter'
|
10
|
+
require 'logstash/plugin_mixins/event_support/from_json_helper'
|
11
|
+
|
4
12
|
require "csv"
|
5
13
|
|
6
14
|
class LogStash::Codecs::CSV < LogStash::Codecs::Base
|
7
15
|
|
16
|
+
include LogStash::PluginMixins::ECSCompatibilitySupport(:disabled, :v1, :v8 => :v1)
|
17
|
+
include LogStash::PluginMixins::ECSCompatibilitySupport::TargetCheck
|
18
|
+
|
19
|
+
extend LogStash::PluginMixins::ValidatorSupport::FieldReferenceValidationAdapter
|
20
|
+
|
21
|
+
include LogStash::PluginMixins::EventSupport::EventFactoryAdapter
|
22
|
+
|
8
23
|
config_name "csv"
|
9
24
|
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
#
|
14
|
-
#
|
15
|
-
#
|
25
|
+
# When decoding:
|
26
|
+
# Define a list of column names (in the order they appear in the CSV,
|
27
|
+
# as if it were a header line). If `columns` is not configured, or there
|
28
|
+
# are not enough columns specified, the default column names are
|
29
|
+
# "column1", "column2", etc.
|
30
|
+
# When encoding:
|
31
|
+
# List of fields names to include in the encoded CSV, in the order listed.
|
16
32
|
config :columns, :validate => :array, :default => []
|
17
33
|
|
18
34
|
# Define the column separator value. If this is not specified, the default
|
@@ -25,20 +41,22 @@ class LogStash::Codecs::CSV < LogStash::Codecs::Base
|
|
25
41
|
# Optional.
|
26
42
|
config :quote_char, :validate => :string, :default => '"'
|
27
43
|
|
28
|
-
#
|
29
|
-
#
|
30
|
-
# be reset on demand, useful for example when dealing with new files in the file input
|
31
|
-
# or new request in the http_poller. Default => false
|
44
|
+
# When encoding in an output plugin, include headers in the encoded CSV
|
45
|
+
# once per codec lifecyle (not for every event). Default => false
|
32
46
|
config :include_headers, :validate => :boolean, :default => false
|
33
47
|
|
34
|
-
# Define whether column names should autogenerated or not.
|
48
|
+
# Define whether column names should be autogenerated or not.
|
35
49
|
# Defaults to true. If set to false, columns not having a header specified will not be parsed.
|
36
50
|
config :autogenerate_column_names, :validate => :boolean, :default => true
|
37
51
|
|
38
52
|
# Define whether empty columns should be skipped.
|
39
|
-
# Defaults to false. If set to true, columns containing no value will not
|
53
|
+
# Defaults to false. If set to true, columns containing no value will not be included.
|
40
54
|
config :skip_empty_columns, :validate => :boolean, :default => false
|
41
55
|
|
56
|
+
# Define whether column names should be auto-detected from the header column or not.
|
57
|
+
# Defaults to false.
|
58
|
+
config :autodetect_column_names, :validate => :boolean, :default => false
|
59
|
+
|
42
60
|
# Define a set of datatype conversions to be applied to columns.
|
43
61
|
# Possible conversions are integer, float, date, date_time, boolean
|
44
62
|
#
|
@@ -51,113 +69,132 @@ class LogStash::Codecs::CSV < LogStash::Codecs::Base
|
|
51
69
|
# }
|
52
70
|
config :convert, :validate => :hash, :default => {}
|
53
71
|
|
54
|
-
##
|
55
|
-
# List of valid conversion types used for the convert option
|
56
|
-
##
|
57
|
-
VALID_CONVERT_TYPES = [ "integer", "float", "date", "date_time", "boolean" ].freeze
|
58
|
-
|
59
|
-
|
60
72
|
# The character encoding used in this codec. Examples include "UTF-8" and
|
61
73
|
# "CP1252".
|
62
74
|
config :charset, :validate => ::Encoding.name_list, :default => "UTF-8"
|
63
75
|
|
64
|
-
|
76
|
+
# Defines a target field for placing decoded fields.
|
77
|
+
# If this setting is omitted, data gets stored at the root (top level) of the event.
|
78
|
+
#
|
79
|
+
# NOTE: the target is only relevant while decoding data into a new event.
|
80
|
+
config :target, :validate => :field_reference
|
81
|
+
|
82
|
+
CONVERTERS = {
|
83
|
+
:integer => lambda do |value|
|
84
|
+
CSV::Converters[:integer].call(value)
|
85
|
+
end,
|
86
|
+
|
87
|
+
:float => lambda do |value|
|
88
|
+
CSV::Converters[:float].call(value)
|
89
|
+
end,
|
90
|
+
|
91
|
+
:date => lambda do |value|
|
92
|
+
result = CSV::Converters[:date].call(value)
|
93
|
+
result.is_a?(Date) ? LogStash::Timestamp.new(result.to_time) : result
|
94
|
+
end,
|
95
|
+
|
96
|
+
:date_time => lambda do |value|
|
97
|
+
result = CSV::Converters[:date_time].call(value)
|
98
|
+
result.is_a?(DateTime) ? LogStash::Timestamp.new(result.to_time) : result
|
99
|
+
end,
|
100
|
+
|
101
|
+
:boolean => lambda do |value|
|
102
|
+
value = value.strip.downcase
|
103
|
+
return false if value == "false"
|
104
|
+
return true if value == "true"
|
105
|
+
return value
|
106
|
+
end
|
107
|
+
}
|
108
|
+
CONVERTERS.default = lambda {|v| v}
|
109
|
+
CONVERTERS.freeze
|
110
|
+
|
111
|
+
def initialize(*params)
|
112
|
+
super
|
113
|
+
|
114
|
+
@original_field = ecs_select[disabled: nil, v1: '[event][original]']
|
115
|
+
|
65
116
|
@converter = LogStash::Util::Charset.new(@charset)
|
66
117
|
@converter.logger = @logger
|
118
|
+
end
|
67
119
|
|
120
|
+
def register
|
68
121
|
# validate conversion types to be the valid ones.
|
69
|
-
@convert.
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
122
|
+
bad_types = @convert.values.select do |type|
|
123
|
+
!CONVERTERS.has_key?(type.to_sym)
|
124
|
+
end.uniq
|
125
|
+
raise(LogStash::ConfigurationError, "Invalid conversion types: #{bad_types.join(', ')}") unless bad_types.empty?
|
126
|
+
|
127
|
+
# @convert_symbols contains the symbolized types to avoid symbol conversion in the transform method
|
128
|
+
@convert_symbols = @convert.each_with_object({}) { |(k, v), result| result[k] = v.to_sym }
|
74
129
|
|
75
|
-
|
76
|
-
@
|
130
|
+
# if the zero byte character is entered in the config, set the value
|
131
|
+
@quote_char = "\x00" if @quote_char == "\\x00"
|
132
|
+
|
133
|
+
@logger.debug? && @logger.debug("CSV parsing options", :col_sep => @separator, :quote_char => @quote_char)
|
77
134
|
end
|
78
135
|
|
79
136
|
def decode(data)
|
80
137
|
data = @converter.convert(data)
|
81
138
|
begin
|
82
|
-
values = CSV.parse_line(data, @
|
83
|
-
|
84
|
-
|
85
|
-
@
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
field_name =
|
96
|
-
value = fields[1]
|
139
|
+
values = CSV.parse_line(data, :col_sep => @separator, :quote_char => @quote_char)
|
140
|
+
|
141
|
+
if (@autodetect_column_names && @columns.empty?)
|
142
|
+
@columns = values
|
143
|
+
@logger.debug? && @logger.debug("Auto detected the following columns", :columns => @columns.inspect)
|
144
|
+
return
|
145
|
+
end
|
146
|
+
|
147
|
+
decoded = {}
|
148
|
+
values.each_with_index do |value, i|
|
149
|
+
unless (@skip_empty_columns && (value.nil? || value.empty?))
|
150
|
+
unless ignore_field?(i)
|
151
|
+
field_name = @columns[i] || "column#{i + 1}"
|
152
|
+
decoded[field_name] = transform(field_name, value)
|
97
153
|
end
|
98
|
-
next unless field_name
|
99
|
-
decoded[field_name] = if should_transform?(field_name)
|
100
|
-
transform(field_name, value)
|
101
|
-
else
|
102
|
-
value
|
103
|
-
end
|
104
154
|
end
|
105
|
-
yield LogStash::Event.new(decoded) if block_given?
|
106
155
|
end
|
156
|
+
|
157
|
+
event = targeted_event_factory.new_event(decoded)
|
158
|
+
event.set(@original_field, data.dup.freeze) if @original_field
|
159
|
+
yield event
|
107
160
|
rescue CSV::MalformedCSVError => e
|
108
|
-
@logger.
|
109
|
-
yield
|
161
|
+
@logger.error("CSV parse failure. Falling back to plain-text", :exception => e.class, :message => e.message, :data => data)
|
162
|
+
yield event_factory.new_event("message" => data, "tags" => ["_csvparsefailure"])
|
110
163
|
end
|
111
164
|
end
|
112
165
|
|
113
166
|
def encode(event)
|
114
|
-
|
115
|
-
|
116
|
-
|
167
|
+
if @include_headers
|
168
|
+
csv_data = CSV.generate_line(select_keys(event), :col_sep => @separator, :quote_char => @quote_char, :headers => true)
|
169
|
+
@on_event.call(event, csv_data)
|
117
170
|
|
118
|
-
|
119
|
-
|
120
|
-
|
171
|
+
# output headers only once per codec lifecycle
|
172
|
+
@include_headers = false
|
173
|
+
end
|
174
|
+
|
175
|
+
csv_data = CSV.generate_line(select_values(event), :col_sep => @separator, :quote_char => @quote_char)
|
176
|
+
@on_event.call(event, csv_data)
|
121
177
|
end
|
122
178
|
|
123
179
|
private
|
124
180
|
|
125
|
-
def
|
126
|
-
|
181
|
+
def select_values(event)
|
182
|
+
if @columns.empty?
|
183
|
+
event.to_hash.values
|
184
|
+
else
|
185
|
+
@columns.map {|column| event.get(column)}
|
186
|
+
end
|
127
187
|
end
|
128
188
|
|
129
|
-
def
|
130
|
-
|
189
|
+
def select_keys(event)
|
190
|
+
@columns.empty? ? event.to_hash.keys : @columns
|
131
191
|
end
|
132
192
|
|
133
|
-
def
|
134
|
-
|
135
|
-
converters[transformation].call(value)
|
193
|
+
def ignore_field?(index)
|
194
|
+
!@columns[index] && !@autogenerate_column_names
|
136
195
|
end
|
137
196
|
|
138
|
-
def
|
139
|
-
@
|
140
|
-
:integer => lambda do |value|
|
141
|
-
CSV::Converters[:integer].call(value)
|
142
|
-
end,
|
143
|
-
:float => lambda do |value|
|
144
|
-
CSV::Converters[:float].call(value)
|
145
|
-
|
146
|
-
end,
|
147
|
-
:date => lambda do |value|
|
148
|
-
CSV::Converters[:date].call(value)
|
149
|
-
|
150
|
-
end,
|
151
|
-
:date_time => lambda do |value|
|
152
|
-
CSV::Converters[:date_time].call(value)
|
153
|
-
end,
|
154
|
-
:boolean => lambda do |value|
|
155
|
-
value = value.strip.downcase
|
156
|
-
return false if value == "false"
|
157
|
-
return true if value == "true"
|
158
|
-
return value
|
159
|
-
end
|
160
|
-
}
|
197
|
+
def transform(field_name, value)
|
198
|
+
CONVERTERS[@convert_symbols[field_name]].call(value)
|
161
199
|
end
|
162
|
-
|
163
|
-
end # class LogStash::Codecs::Plain
|
200
|
+
end
|
data/logstash-codec-csv.gemspec
CHANGED
@@ -1,17 +1,17 @@
|
|
1
1
|
Gem::Specification.new do |s|
|
2
2
|
|
3
3
|
s.name = 'logstash-codec-csv'
|
4
|
-
s.version = '
|
4
|
+
s.version = '1.1.0'
|
5
5
|
s.licenses = ['Apache License (2.0)']
|
6
6
|
s.summary = "The csv codec take CSV data, parses it and passes it away"
|
7
|
-
s.description = "This gem is a
|
7
|
+
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
8
|
s.authors = ["Elasticsearch"]
|
9
9
|
s.email = 'info@elasticsearch.com'
|
10
10
|
s.homepage = "http://www.elasticsearch.org/guide/en/logstash/current/index.html"
|
11
11
|
s.require_paths = ["lib"]
|
12
12
|
|
13
13
|
# Files
|
14
|
-
s.files = Dir[
|
14
|
+
s.files = Dir["lib/**/*","spec/**/*","*.gemspec","*.md","CONTRIBUTORS","Gemfile","LICENSE","NOTICE.TXT", "vendor/jar-dependencies/**/*.jar", "vendor/jar-dependencies/**/*.rb", "VERSION", "docs/**/*"]
|
15
15
|
|
16
16
|
# Tests
|
17
17
|
s.test_files = s.files.grep(%r{^(test|spec|features)/})
|
@@ -20,7 +20,10 @@ Gem::Specification.new do |s|
|
|
20
20
|
s.metadata = { "logstash_plugin" => "true", "logstash_group" => "codec" }
|
21
21
|
|
22
22
|
# Gem dependencies
|
23
|
-
s.add_runtime_dependency "logstash-core-plugin-api", "
|
23
|
+
s.add_runtime_dependency "logstash-core-plugin-api", ">= 1.60", "<= 2.99"
|
24
|
+
s.add_runtime_dependency 'logstash-mixin-ecs_compatibility_support', '~> 1.3'
|
25
|
+
s.add_runtime_dependency 'logstash-mixin-event_support', '~> 1.0'
|
26
|
+
s.add_runtime_dependency 'logstash-mixin-validator_support', '~> 1.0'
|
24
27
|
|
25
28
|
s.add_development_dependency 'logstash-devutils'
|
26
29
|
end
|
data/spec/codecs/csv_spec.rb
CHANGED
@@ -1,8 +1,10 @@
|
|
1
1
|
# encoding: utf-8
|
2
|
+
require "logstash/devutils/rspec/spec_helper"
|
2
3
|
require "logstash/codecs/csv"
|
3
|
-
require "logstash/event"
|
4
4
|
|
5
|
-
|
5
|
+
require 'logstash/plugin_mixins/ecs_compatibility_support/spec_helper'
|
6
|
+
|
7
|
+
describe LogStash::Codecs::CSV, :ecs_compatibility_support do
|
6
8
|
|
7
9
|
subject(:codec) { LogStash::Codecs::CSV.new(config) }
|
8
10
|
let(:config) { Hash.new }
|
@@ -15,192 +17,281 @@ describe LogStash::Codecs::CSV do
|
|
15
17
|
|
16
18
|
let(:data) { "big,bird,sesame street" }
|
17
19
|
|
18
|
-
|
19
|
-
codec.decode(data) do |event|
|
20
|
-
expect(event["column1"]).to eq("big")
|
21
|
-
expect(event["column2"]).to eq("bird")
|
22
|
-
expect(event["column3"]).to eq("sesame street")
|
23
|
-
end
|
24
|
-
end
|
20
|
+
ecs_compatibility_matrix(:disabled, :v1, :v8 => :v1) do |ecs_select|
|
25
21
|
|
26
|
-
|
27
|
-
let(:doc) { "big,bird,sesame street" }
|
28
|
-
let(:config) do
|
29
|
-
{ "columns" => ["first", "last", "address" ] }
|
30
|
-
end
|
22
|
+
let(:config) { super().merge('ecs_compatibility' => ecs_select.active_mode.to_s) }
|
31
23
|
|
32
|
-
it "
|
24
|
+
it "return an event from CSV data" do
|
25
|
+
event_count = 0
|
33
26
|
codec.decode(data) do |event|
|
34
|
-
|
35
|
-
expect(event
|
36
|
-
expect(event
|
27
|
+
event_count += 1
|
28
|
+
expect(event.get("column1")).to eq("big")
|
29
|
+
expect(event.get("column2")).to eq("bird")
|
30
|
+
expect(event.get("column3")).to eq("sesame street")
|
37
31
|
end
|
32
|
+
expect( event_count ).to eql 1
|
38
33
|
end
|
39
34
|
|
40
|
-
|
41
|
-
|
42
|
-
let(:data) { "val1,,val3" }
|
43
|
-
|
35
|
+
describe "given column names" do
|
36
|
+
let(:doc) { "big,bird,sesame street" }
|
44
37
|
let(:config) do
|
45
|
-
{ "
|
46
|
-
"columns" => ["custom1", "custom2", "custom3"] }
|
38
|
+
{ "columns" => ["first", "last", "address" ] }
|
47
39
|
end
|
48
40
|
|
49
41
|
it "extract all the values" do
|
50
42
|
codec.decode(data) do |event|
|
51
|
-
expect(event
|
52
|
-
expect(event.
|
53
|
-
expect(event
|
43
|
+
expect(event.get("first")).to eq("big")
|
44
|
+
expect(event.get("last")).to eq("bird")
|
45
|
+
expect(event.get("address")).to eq("sesame street")
|
54
46
|
end
|
55
47
|
end
|
48
|
+
|
49
|
+
context "parse csv skipping empty columns" do
|
50
|
+
|
51
|
+
let(:data) { "val1,,val3" }
|
52
|
+
|
53
|
+
let(:config) do
|
54
|
+
{ "skip_empty_columns" => true,
|
55
|
+
"columns" => ["custom1", "custom2", "custom3"] }
|
56
|
+
end
|
57
|
+
|
58
|
+
it "extract all the values" do
|
59
|
+
codec.decode(data) do |event|
|
60
|
+
expect(event.get("custom1")).to eq("val1")
|
61
|
+
expect(event.to_hash).not_to include("custom2")
|
62
|
+
expect(event.get("custom3")).to eq("val3")
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
context "parse csv without autogeneration of names" do
|
68
|
+
|
69
|
+
let(:data) { "val1,val2,val3" }
|
70
|
+
let(:config) do
|
71
|
+
{ "autogenerate_column_names" => false,
|
72
|
+
"columns" => ["custom1", "custom2"] }
|
73
|
+
end
|
74
|
+
|
75
|
+
it "extract all the values" do
|
76
|
+
codec.decode(data) do |event|
|
77
|
+
expect(event.get("custom1")).to eq("val1")
|
78
|
+
expect(event.get("custom2")).to eq("val2")
|
79
|
+
expect(event.get("column3")).to be_falsey
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
56
84
|
end
|
57
85
|
|
58
|
-
|
86
|
+
describe "custom separator" do
|
87
|
+
let(:data) { "big,bird;sesame street" }
|
59
88
|
|
60
|
-
let(:data) { "val1,val2,val3" }
|
61
89
|
let(:config) do
|
62
|
-
{
|
63
|
-
"columns" => ["custom1", "custom2"] }
|
90
|
+
{ "separator" => ";" }
|
64
91
|
end
|
65
92
|
|
66
|
-
it "
|
93
|
+
it "return an event from CSV data" do
|
67
94
|
codec.decode(data) do |event|
|
68
|
-
expect(event
|
69
|
-
expect(event
|
70
|
-
expect(event["column3"]).to be_falsey
|
95
|
+
expect(event.get("column1")).to eq("big,bird")
|
96
|
+
expect(event.get("column2")).to eq("sesame street")
|
71
97
|
end
|
72
98
|
end
|
73
99
|
end
|
74
100
|
|
75
|
-
|
101
|
+
describe "quote char" do
|
102
|
+
let(:data) { "big,bird,'sesame street'" }
|
76
103
|
|
77
|
-
|
78
|
-
|
104
|
+
let(:config) do
|
105
|
+
{ "quote_char" => "'"}
|
106
|
+
end
|
79
107
|
|
80
|
-
|
81
|
-
|
82
|
-
|
108
|
+
it "return an event from CSV data" do
|
109
|
+
codec.decode(data) do |event|
|
110
|
+
expect(event.get("column1")).to eq("big")
|
111
|
+
expect(event.get("column2")).to eq("bird")
|
112
|
+
expect(event.get("column3")).to eq("sesame street")
|
113
|
+
end
|
114
|
+
end
|
83
115
|
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
116
|
+
context "using the default one" do
|
117
|
+
let(:data) { 'big,bird,"sesame, street"' }
|
118
|
+
let(:config) { Hash.new }
|
119
|
+
|
120
|
+
it "return an event from CSV data" do
|
121
|
+
codec.decode(data) do |event|
|
122
|
+
expect(event.get("column1")).to eq("big")
|
123
|
+
expect(event.get("column2")).to eq("bird")
|
124
|
+
expect(event.get("column3")).to eq("sesame, street")
|
125
|
+
end
|
126
|
+
end
|
88
127
|
end
|
89
|
-
end
|
90
|
-
end
|
91
128
|
|
92
|
-
|
93
|
-
|
129
|
+
context "using a null" do
|
130
|
+
let(:data) { 'big,bird,"sesame" street' }
|
131
|
+
let(:config) do
|
132
|
+
{ "quote_char" => "\x00" }
|
133
|
+
end
|
94
134
|
|
95
|
-
|
96
|
-
|
135
|
+
it "return an event from CSV data" do
|
136
|
+
codec.decode(data) do |event|
|
137
|
+
expect(event.get("column1")).to eq("big")
|
138
|
+
expect(event.get("column2")).to eq("bird")
|
139
|
+
expect(event.get("column3")).to eq('"sesame" street')
|
140
|
+
end
|
141
|
+
end
|
142
|
+
end
|
97
143
|
end
|
98
144
|
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
expect(event["column3"]).to eq("sesame street")
|
145
|
+
describe "having headers" do
|
146
|
+
|
147
|
+
let(:data) do
|
148
|
+
[ "size,animal,movie", "big,bird,sesame street"]
|
104
149
|
end
|
105
|
-
end
|
106
150
|
|
107
|
-
|
108
|
-
|
109
|
-
|
151
|
+
let(:new_data) do
|
152
|
+
[ "host,country,city", "example.com,germany,berlin"]
|
153
|
+
end
|
110
154
|
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
155
|
+
let(:config) do
|
156
|
+
{ "autodetect_column_names" => true }
|
157
|
+
end
|
158
|
+
|
159
|
+
it "include header information when requested" do
|
160
|
+
codec.decode(data[0]) # Read the headers
|
161
|
+
codec.decode(data[1]) do |event|
|
162
|
+
expect(event.get("size")).to eq("big")
|
163
|
+
expect(event.get("animal")).to eq("bird")
|
164
|
+
expect(event.get("movie")).to eq("sesame street")
|
116
165
|
end
|
117
166
|
end
|
118
167
|
end
|
119
168
|
|
120
|
-
|
121
|
-
|
169
|
+
describe "using field conversion" do
|
170
|
+
|
122
171
|
let(:config) do
|
123
|
-
{ "
|
172
|
+
{ "convert" => { "column1" => "integer", "column3" => "boolean" } }
|
124
173
|
end
|
174
|
+
let(:data) { "1234,bird,false" }
|
125
175
|
|
126
|
-
it "
|
176
|
+
it "get converted values to the expected type" do
|
127
177
|
codec.decode(data) do |event|
|
128
|
-
expect(event
|
129
|
-
expect(event
|
130
|
-
expect(event
|
178
|
+
expect(event.get("column1")).to eq(1234)
|
179
|
+
expect(event.get("column2")).to eq("bird")
|
180
|
+
expect(event.get("column3")).to eq(false)
|
131
181
|
end
|
132
182
|
end
|
133
|
-
end
|
134
|
-
end
|
135
183
|
|
136
|
-
|
184
|
+
context "when using column names" do
|
137
185
|
|
138
|
-
|
139
|
-
|
140
|
-
|
186
|
+
let(:config) do
|
187
|
+
{ "convert" => { "custom1" => "integer", "custom3" => "boolean" },
|
188
|
+
"columns" => ["custom1", "custom2", "custom3"] }
|
189
|
+
end
|
141
190
|
|
142
|
-
|
143
|
-
|
191
|
+
it "get converted values to the expected type" do
|
192
|
+
codec.decode(data) do |event|
|
193
|
+
expect(event.get("custom1")).to eq(1234)
|
194
|
+
expect(event.get("custom2")).to eq("bird")
|
195
|
+
expect(event.get("custom3")).to eq(false)
|
196
|
+
end
|
197
|
+
end
|
198
|
+
end
|
144
199
|
end
|
145
200
|
|
146
|
-
|
147
|
-
|
201
|
+
context "with target" do
|
202
|
+
|
203
|
+
let(:config) { super().merge('target' => '[csv-root]') }
|
204
|
+
|
205
|
+
it "return an event from CSV data" do
|
206
|
+
event_count = 0
|
207
|
+
codec.decode(data) do |event|
|
208
|
+
event_count += 1
|
209
|
+
expect( event.include?("column1") ).to be false
|
210
|
+
expect( event.get("csv-root") ).to eql('column1' => 'big', 'column2' => 'bird', 'column3' => "sesame street")
|
211
|
+
end
|
212
|
+
expect( event_count ).to eql 1
|
213
|
+
end
|
214
|
+
|
215
|
+
it 'set event.original in ECS mode' do
|
216
|
+
codec.decode(data) do |event|
|
217
|
+
if ecs_select.active_mode == :disabled
|
218
|
+
expect( event.get("[event][original]") ).to be nil
|
219
|
+
else
|
220
|
+
expect( event.get("[event][original]") ).to eql data
|
221
|
+
end
|
222
|
+
end
|
223
|
+
end
|
224
|
+
|
148
225
|
end
|
226
|
+
end
|
227
|
+
|
228
|
+
end
|
149
229
|
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
|
155
|
-
|
230
|
+
describe "encode" do
|
231
|
+
context "not including headers" do
|
232
|
+
let(:event) { LogStash::Event.new({"f1" => "v1", "f2" => "v2"}) }
|
233
|
+
|
234
|
+
context "without columns" do
|
235
|
+
let(:config) do
|
236
|
+
{ "include_headers" => false, "columns" => [] }
|
237
|
+
end
|
238
|
+
|
239
|
+
it "should encode to single CSV line" do
|
240
|
+
codec.on_event do |e, d|
|
241
|
+
expect(d.chomp.split(",").sort).to eq("v1,v2,1,#{event.timestamp}".split(",").sort)
|
242
|
+
end
|
243
|
+
codec.encode(event)
|
156
244
|
end
|
157
245
|
end
|
158
246
|
|
159
|
-
|
160
|
-
|
161
|
-
|
247
|
+
context "with columns" do
|
248
|
+
let(:config) do
|
249
|
+
{ "include_headers" => false, "columns" => ["f1", "f2"] }
|
162
250
|
end
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
251
|
+
|
252
|
+
it "should encode to single CSV line" do
|
253
|
+
codec.on_event do |e, d|
|
254
|
+
expect(d).to eq("v1,v2\n")
|
255
|
+
end
|
256
|
+
codec.encode(event)
|
169
257
|
end
|
170
258
|
end
|
171
259
|
end
|
172
260
|
|
173
|
-
|
261
|
+
context "including headers" do
|
262
|
+
let(:event) { LogStash::Event.new({"f1" => "v1", "f2" => "v2"}) }
|
174
263
|
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
264
|
+
context "without columns" do
|
265
|
+
let(:config) do
|
266
|
+
{ "include_headers" => true, "columns" => [] }
|
267
|
+
end
|
179
268
|
|
180
|
-
|
181
|
-
|
182
|
-
|
183
|
-
|
184
|
-
|
269
|
+
it "should encode to two CSV line" do
|
270
|
+
lines = []
|
271
|
+
codec.on_event do |e, d|
|
272
|
+
lines << d
|
273
|
+
end
|
274
|
+
codec.encode(event)
|
275
|
+
expect(lines[0].chomp.split(",").sort).to eq("f1,f2,@version,@timestamp".split(",").sort)
|
276
|
+
expect(lines[1].chomp.split(",").sort).to eq("v1,v2,1,#{event.timestamp}".split(",").sort)
|
185
277
|
end
|
186
278
|
end
|
187
279
|
|
188
|
-
context "
|
189
|
-
|
280
|
+
context "with columns" do
|
190
281
|
let(:config) do
|
191
|
-
{ "
|
192
|
-
"columns" => ["custom1", "custom2", "custom3"] }
|
282
|
+
{ "include_headers" => true, "columns" => ["f1", "f2"] }
|
193
283
|
end
|
194
284
|
|
195
|
-
it "
|
196
|
-
|
197
|
-
|
198
|
-
|
199
|
-
expect(event["custom3"]).to eq(false)
|
285
|
+
it "should encode to two CSV line" do
|
286
|
+
lines = []
|
287
|
+
codec.on_event do |e, d|
|
288
|
+
lines << d
|
200
289
|
end
|
290
|
+
codec.encode(event)
|
291
|
+
expect(lines[0]).to eq("f1,f2\n")
|
292
|
+
expect(lines[1]).to eq("v1,v2\n")
|
201
293
|
end
|
202
294
|
end
|
203
295
|
end
|
204
|
-
|
205
296
|
end
|
206
297
|
end
|
metadata
CHANGED
@@ -1,24 +1,72 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: logstash-codec-csv
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 1.1.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Elasticsearch
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2021-07-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
requirement: !ruby/object:Gem::Requirement
|
15
|
+
requirements:
|
16
|
+
- - ">="
|
17
|
+
- !ruby/object:Gem::Version
|
18
|
+
version: '1.60'
|
19
|
+
- - "<="
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '2.99'
|
22
|
+
name: logstash-core-plugin-api
|
23
|
+
type: :runtime
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '1.60'
|
30
|
+
- - "<="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '2.99'
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
requirement: !ruby/object:Gem::Requirement
|
35
|
+
requirements:
|
36
|
+
- - "~>"
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '1.3'
|
39
|
+
name: logstash-mixin-ecs_compatibility_support
|
40
|
+
type: :runtime
|
41
|
+
prerelease: false
|
42
|
+
version_requirements: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - "~>"
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: '1.3'
|
13
47
|
- !ruby/object:Gem::Dependency
|
14
48
|
requirement: !ruby/object:Gem::Requirement
|
15
49
|
requirements:
|
16
50
|
- - "~>"
|
17
51
|
- !ruby/object:Gem::Version
|
18
52
|
version: '1.0'
|
19
|
-
name: logstash-
|
53
|
+
name: logstash-mixin-event_support
|
54
|
+
type: :runtime
|
20
55
|
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - "~>"
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '1.0'
|
61
|
+
- !ruby/object:Gem::Dependency
|
62
|
+
requirement: !ruby/object:Gem::Requirement
|
63
|
+
requirements:
|
64
|
+
- - "~>"
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
version: '1.0'
|
67
|
+
name: logstash-mixin-validator_support
|
21
68
|
type: :runtime
|
69
|
+
prerelease: false
|
22
70
|
version_requirements: !ruby/object:Gem::Requirement
|
23
71
|
requirements:
|
24
72
|
- - "~>"
|
@@ -31,14 +79,16 @@ dependencies:
|
|
31
79
|
- !ruby/object:Gem::Version
|
32
80
|
version: '0'
|
33
81
|
name: logstash-devutils
|
34
|
-
prerelease: false
|
35
82
|
type: :development
|
83
|
+
prerelease: false
|
36
84
|
version_requirements: !ruby/object:Gem::Requirement
|
37
85
|
requirements:
|
38
86
|
- - ">="
|
39
87
|
- !ruby/object:Gem::Version
|
40
88
|
version: '0'
|
41
|
-
description: This gem is a
|
89
|
+
description: This gem is a Logstash plugin required to be installed on top of the
|
90
|
+
Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This
|
91
|
+
gem is not a stand-alone program
|
42
92
|
email: info@elasticsearch.com
|
43
93
|
executables: []
|
44
94
|
extensions: []
|
@@ -49,6 +99,7 @@ files:
|
|
49
99
|
- Gemfile
|
50
100
|
- LICENSE
|
51
101
|
- README.md
|
102
|
+
- docs/index.asciidoc
|
52
103
|
- lib/logstash/codecs/csv.rb
|
53
104
|
- logstash-codec-csv.gemspec
|
54
105
|
- spec/codecs/csv_spec.rb
|
@@ -73,8 +124,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
73
124
|
- !ruby/object:Gem::Version
|
74
125
|
version: '0'
|
75
126
|
requirements: []
|
76
|
-
|
77
|
-
rubygems_version: 2.4.8
|
127
|
+
rubygems_version: 3.0.6
|
78
128
|
signing_key:
|
79
129
|
specification_version: 4
|
80
130
|
summary: The csv codec take CSV data, parses it and passes it away
|