uploadconvert 0.0.5 → 0.0.6
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.
- data/lib/uploadconvert.rb +21 -1
- metadata +2 -2
data/lib/uploadconvert.rb
CHANGED
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
require 'json'
|
|
2
2
|
require 'docsplit'
|
|
3
|
+
require 'crack'
|
|
3
4
|
|
|
4
5
|
class UploadConvert
|
|
5
6
|
|
|
@@ -9,6 +10,26 @@ class UploadConvert
|
|
|
9
10
|
@text = ""
|
|
10
11
|
end
|
|
11
12
|
|
|
13
|
+
# Sends the document to the appropriate method
|
|
14
|
+
def handleDoc
|
|
15
|
+
if @input.include? "http"
|
|
16
|
+
`wget #{@input}`
|
|
17
|
+
path = @input.split("/")
|
|
18
|
+
@input = path[path.length-1].chomp.strip
|
|
19
|
+
handleDoc
|
|
20
|
+
elsif @input.include? ".pdf"
|
|
21
|
+
pdfTojson
|
|
22
|
+
elsif @input.include? ".xml"
|
|
23
|
+
xmlTojson(File.read(@input))
|
|
24
|
+
end
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
# Convert XML files to JSONs
|
|
28
|
+
def xmlTojson(xmlin)
|
|
29
|
+
xml = Crack::XML.parse(xmlin)
|
|
30
|
+
JSON.pretty_generate(xml)
|
|
31
|
+
end
|
|
32
|
+
|
|
12
33
|
# Convert PDFs to JSON
|
|
13
34
|
def pdfTojson
|
|
14
35
|
# Extract and clean text
|
|
@@ -100,4 +121,3 @@ class UploadConvert
|
|
|
100
121
|
return @metadata
|
|
101
122
|
end
|
|
102
123
|
end
|
|
103
|
-
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: uploadconvert
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.6
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,7 +9,7 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2014-03-
|
|
12
|
+
date: 2014-03-19 00:00:00.000000000 Z
|
|
13
13
|
dependencies: []
|
|
14
14
|
description: Converts documents to the appropriate format for Transparency Toolkit.
|
|
15
15
|
email: shidash@shidash.com
|