dircrawl 0.0.10 → 0.0.11
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/dircrawl.rb +12 -0
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 718cb5898eb443d139f06327621d10b99f38cc1e
|
|
4
|
+
data.tar.gz: 5bbd222f8a39ff40f74cfcb4f018ed3d85b1761e
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 79c85b08f37f4ceba18072d4bddb1fa0ad9f648f23de0737b031750d6bc55ef672bae6092d02b1b14ca2acf744c1f82709c955ccee8c72d0d10130f268427564
|
|
7
|
+
data.tar.gz: 376e288cfc6ec6bf6b52b5764a588e469a8fb26e835193436938cfd840097eb6b674999f1049cb3131ff074b6f462b3a16b6de8b3a19b44259b3dc032e43e89b
|
data/lib/dircrawl.rb
CHANGED
|
@@ -48,6 +48,7 @@ class DirCrawl
|
|
|
48
48
|
|
|
49
49
|
# Go to next dir
|
|
50
50
|
if File.directory?(dir+"/"+file)
|
|
51
|
+
report_status("Going to next directory: " + dir+"/"+file)
|
|
51
52
|
crawl_dir(dir+"/"+file, *args)
|
|
52
53
|
|
|
53
54
|
# Process file
|
|
@@ -70,6 +71,7 @@ class DirCrawl
|
|
|
70
71
|
end
|
|
71
72
|
|
|
72
73
|
rescue Exception => e # really catch any failures
|
|
74
|
+
report_status("Error on file "+file+": "+e.to_s
|
|
73
75
|
if @failure_mode == "debug"
|
|
74
76
|
binding.pry
|
|
75
77
|
elsif @failure_mode == "log"
|
|
@@ -102,6 +104,16 @@ class DirCrawl
|
|
|
102
104
|
end
|
|
103
105
|
end
|
|
104
106
|
|
|
107
|
+
# Report Harvester status message
|
|
108
|
+
def report_status(status_msg)
|
|
109
|
+
if @cm_url
|
|
110
|
+
curl_url = @cm_url+"/update_status"
|
|
111
|
+
c = Curl::Easy.http_post(curl_url,
|
|
112
|
+
Curl::PostField.content('selector_id', @selector_id),
|
|
113
|
+
Curl::PostField.content('status_message', status_msg))
|
|
114
|
+
end
|
|
115
|
+
end
|
|
116
|
+
|
|
105
117
|
# Report results back to Harvester incrementally
|
|
106
118
|
def report_incremental(results, path)
|
|
107
119
|
curl_url = @cm_url+"/relay_results"
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: dircrawl
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.11
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- M. C. McGrath
|
|
@@ -9,7 +9,7 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2016-10-
|
|
12
|
+
date: 2016-10-30 00:00:00.000000000 Z
|
|
13
13
|
dependencies: []
|
|
14
14
|
description: Run block on all files in dir
|
|
15
15
|
email: shidash@shidash.com
|