search_solr_tools 5.1.0.pre.1 → 5.1.0.pre.2
Sign up to get free protection for your applications and to get access to all the features.
Potentially problematic release.
This version of search_solr_tools might be problematic. Click here for more details.
- checksums.yaml +4 -4
- data/CHANGELOG.md +3 -1
- data/bin/search_solr_tools +1 -1
- data/lib/search_solr_tools/errors/harvest_error.rb +19 -4
- data/lib/search_solr_tools/harvesters/base.rb +3 -3
- data/lib/search_solr_tools/harvesters/nsidc_json.rb +4 -3
- data/lib/search_solr_tools/helpers/harvest_status.rb +10 -32
- data/lib/search_solr_tools/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1b2767fe90ced0e512cd651820392f512e0d5ebb5bd5d1ec8d8044d01c90966f
|
4
|
+
data.tar.gz: 3c01a52136449c3281534f0353091fb607d2a28c6595392b035e14bae042c62c
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f478d8680f4ef4dd3acc5958906d65d1470f197e999f6206208a315051e3017ce54c32cc92730b78472e953b68f988bf1fea6681c2c3903a46ffe4a8bf4dbde6
|
7
|
+
data.tar.gz: 31c5f916ae86a7e2878598568e5de3caa5dade77378788a7721360bf742f8d433b8b3db7b34eef06e850fc69adf606ea697aeec3b6295991681da50f7e9b95bf
|
data/CHANGELOG.md
CHANGED
@@ -1,7 +1,9 @@
|
|
1
|
-
##
|
1
|
+
## v5.1.0 (2020-07-23)
|
2
2
|
|
3
3
|
- Added a CLI method to "ping" the Solr and Source servers for a given
|
4
4
|
data center.
|
5
|
+
- Added a CLI method "errcode" to get information about the various
|
6
|
+
error codes that may be returned during harvest
|
5
7
|
- Updated the CLI harvest to return more useful error codes on failure.
|
6
8
|
|
7
9
|
## v5.0.1 (2020-07-02)
|
data/bin/search_solr_tools
CHANGED
@@ -13,7 +13,7 @@ class SolrHarvestCLI < Thor
|
|
13
13
|
puts SearchSolrTools::VERSION
|
14
14
|
end
|
15
15
|
|
16
|
-
desc 'errcode', '
|
16
|
+
desc 'errcode CODE', 'Print all exit codes bundled in CODE. Omit CODE to print all codes'
|
17
17
|
def errcode(code = -1)
|
18
18
|
codes = SearchSolrTools::Errors::HarvestError.describe_exit_code(code)
|
19
19
|
|
@@ -19,6 +19,19 @@ module SearchSolrTools
|
|
19
19
|
ERRCODE_OTHER => 'General error code for non-harvest related issues'
|
20
20
|
}.freeze
|
21
21
|
|
22
|
+
PING_ERRCODE_MAP = {
|
23
|
+
'ping_solr' => ERRCODE_SOLR_PING,
|
24
|
+
'ping_source' => ERRCODE_SOURCE_PING,
|
25
|
+
}
|
26
|
+
|
27
|
+
STATUS_ERRCODE_MAP = {
|
28
|
+
Helpers::HarvestStatus::HARVEST_NO_DOCS => ERRCODE_SOURCE_NO_RESULTS,
|
29
|
+
Helpers::HarvestStatus::HARVEST_FAILURE => ERRCODE_SOURCE_HARVEST_ERROR,
|
30
|
+
Helpers::HarvestStatus::INGEST_ERR_INVALID_DOC => ERRCODE_DOCUMENT_INVALID,
|
31
|
+
Helpers::HarvestStatus::INGEST_ERR_SOLR_ERROR => ERRCODE_INGEST_ERROR,
|
32
|
+
Helpers::HarvestStatus::OTHER_ERROR => ERRCODE_OTHER
|
33
|
+
}.freeze
|
34
|
+
|
22
35
|
# If code is -1, it means display all error codes
|
23
36
|
def self.describe_exit_code(code = -1)
|
24
37
|
code = code.to_i
|
@@ -52,13 +65,15 @@ module SearchSolrTools
|
|
52
65
|
return ERRCODE_OTHER
|
53
66
|
end
|
54
67
|
|
68
|
+
puts "EXIT CODE STATUS:\n#{@status_data.status}"
|
69
|
+
|
55
70
|
code = 0
|
56
71
|
code += ERRCODE_SOLR_PING unless @status_data.ping_solr
|
57
72
|
code += ERRCODE_SOURCE_PING unless @status_data.ping_source
|
58
|
-
code += ERRCODE_SOURCE_NO_RESULTS if @status_data.
|
59
|
-
code += ERRCODE_SOURCE_HARVEST_ERROR if @status_data.
|
60
|
-
code += ERRCODE_DOCUMENT_INVALID if @status_data.
|
61
|
-
code += ERRCODE_INGEST_ERROR if @status_data.
|
73
|
+
code += ERRCODE_SOURCE_NO_RESULTS if @status_data.status[Helpers::HarvestStatus::HARVEST_NO_DOCS] > 0
|
74
|
+
code += ERRCODE_SOURCE_HARVEST_ERROR if @status_data.status[Helpers::HarvestStatus::HARVEST_FAILURE] > 0
|
75
|
+
code += ERRCODE_DOCUMENT_INVALID if @status_data.status[Helpers::HarvestStatus::INGEST_ERR_INVALID_DOC] > 0
|
76
|
+
code += ERRCODE_INGEST_ERROR if @status_data.status[Helpers::HarvestStatus::INGEST_ERR_SOLR_ERROR] > 0
|
62
77
|
|
63
78
|
code = ERRCODE_OTHER if code == 0
|
64
79
|
|
@@ -59,7 +59,7 @@ module SearchSolrTools
|
|
59
59
|
end
|
60
60
|
|
61
61
|
# This should be overridden by child classes to implement the ability
|
62
|
-
# to "ping" the
|
62
|
+
# to "ping" the data center. Returns true if the ping is successful (or, as
|
63
63
|
# in this default, no ping method was defined)
|
64
64
|
def ping_source
|
65
65
|
puts "Harvester does not have ping method defined, assuming true"
|
@@ -117,8 +117,8 @@ module SearchSolrTools
|
|
117
117
|
status = Helpers::HarvestStatus.new
|
118
118
|
|
119
119
|
docs.each do |doc|
|
120
|
-
doc_status = insert_solr_doc(doc, content_type, core)
|
121
|
-
status.
|
120
|
+
doc_status = insert_solr_doc(doc, content_type, core)
|
121
|
+
status.record_status doc_status
|
122
122
|
doc_status == Helpers::HarvestStatus::INGEST_OK ? success += 1 : failure += 1
|
123
123
|
end
|
124
124
|
puts "#{success} document#{success == 1 ? '' : 's'} successfully added to Solr."
|
@@ -37,9 +37,10 @@ module SearchSolrTools
|
|
37
37
|
|
38
38
|
status = insert_solr_docs result[:add_docs], Base::JSON_CONTENT_TYPE
|
39
39
|
|
40
|
-
status.
|
41
|
-
|
42
|
-
|
40
|
+
status.record_status(Helpers::HarvestStatus::HARVEST_NO_DOCS) if result[:num_docs] == 0
|
41
|
+
|
42
|
+
# Record the number of harvest failures; note that if this is 0, thats OK, the status will stay at 0
|
43
|
+
status.record_status(Helpers::HarvestStatus::HARVEST_FAILURE, result[:failure_ids].length)
|
43
44
|
|
44
45
|
raise Errors::HarvestError, status unless status.ok?
|
45
46
|
rescue Errors::HarvestError => e
|
@@ -1,7 +1,6 @@
|
|
1
1
|
module SearchSolrTools
|
2
2
|
module Helpers
|
3
3
|
class HarvestStatus
|
4
|
-
|
5
4
|
INGEST_OK = :ok
|
6
5
|
HARVEST_NO_DOCS = :harvest_none
|
7
6
|
HARVEST_FAILURE = :harvest_fail
|
@@ -13,54 +12,33 @@ module SearchSolrTools
|
|
13
12
|
|
14
13
|
ERROR_STATUS = [HARVEST_NO_DOCS, HARVEST_FAILURE, INGEST_ERR_INVALID_DOC, INGEST_ERR_SOLR_ERROR, OTHER_ERROR]
|
15
14
|
|
15
|
+
attr_reader :status, :ping_solr, :ping_source
|
16
|
+
attr_writer :ping_solr, :ping_source
|
17
|
+
|
16
18
|
# init_info is an optional hash that contains the various status keys and the documents to
|
17
19
|
# associate with them
|
18
20
|
def initialize(init_info={})
|
19
|
-
@status = { INGEST_OK =>
|
21
|
+
@status = { INGEST_OK => 0 }
|
20
22
|
@ping_solr = true
|
21
23
|
@ping_source = true
|
22
|
-
ERROR_STATUS.each { |s| @status[s] =
|
24
|
+
ERROR_STATUS.each { |s| @status[s] = 0 }
|
23
25
|
|
24
|
-
init_info.each do |key,
|
25
|
-
@status[key] =
|
26
|
+
init_info.each do |key, count|
|
27
|
+
@status[key] = count if @status.include? key
|
26
28
|
end
|
27
29
|
|
28
30
|
@ping_solr = init_info[PING_SOLR] if init_info.include? PING_SOLR
|
29
31
|
@ping_source = init_info[PING_SOURCE] if init_info.include? PING_SOURCE
|
30
32
|
end
|
31
33
|
|
32
|
-
def
|
33
|
-
|
34
|
-
end
|
35
|
-
|
36
|
-
def record_document_status(document, doc_status)
|
37
|
-
@status[doc_status] << document
|
38
|
-
end
|
39
|
-
|
40
|
-
def ping_solr=(newval)
|
41
|
-
@ping_solr = newval
|
42
|
-
end
|
43
|
-
|
44
|
-
def ping_source=(newval)
|
45
|
-
@ping_source = newval
|
34
|
+
def record_status(status, count = 1)
|
35
|
+
@status[status] += count
|
46
36
|
end
|
47
37
|
|
48
38
|
def ok?
|
49
|
-
ERROR_STATUS.each { |s| return false unless @status[s]
|
39
|
+
ERROR_STATUS.each { |s| return false unless @status[s] == 0 }
|
50
40
|
@ping_solr && @ping_source
|
51
41
|
end
|
52
|
-
|
53
|
-
def ping_solr
|
54
|
-
@ping_solr
|
55
|
-
end
|
56
|
-
|
57
|
-
def ping_source
|
58
|
-
@ping_source
|
59
|
-
end
|
60
|
-
|
61
|
-
def documents_with_status(doc_status)
|
62
|
-
@status[doc_status]
|
63
|
-
end
|
64
42
|
end
|
65
43
|
end
|
66
44
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: search_solr_tools
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 5.1.0.pre.
|
4
|
+
version: 5.1.0.pre.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Chris Chalstrom
|
@@ -14,7 +14,7 @@ authors:
|
|
14
14
|
autorequire:
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
|
-
date: 2020-07-
|
17
|
+
date: 2020-07-23 00:00:00.000000000 Z
|
18
18
|
dependencies:
|
19
19
|
- !ruby/object:Gem::Dependency
|
20
20
|
name: ffi-geos
|