parsefile 0.0.7 → 0.0.8
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/ocrfile.rb +6 -2
- 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: 2738907314aac77a653fd655f4a200e2a63b6ed6
|
|
4
|
+
data.tar.gz: 8c780c9b2304699e37f71cdb7f4842918bc61fc9
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e1385fdeb0923ebe72068c529341314aabebe1123f161e636762c19ad3325518716c759f9eae5fdd4bc6f12892709a45fe2dc5381e6151e6472677800fb31865
|
|
7
|
+
data.tar.gz: 919fbc77f37f6d40b15726ae9d5f36b622fdbe37d2789f730da61b5dea61d24ec12f359b607b096dbc5f0afd936e30fb68f23ee50efdd6276e3aa3c9273d6ade
|
data/lib/ocrfile.rb
CHANGED
|
@@ -28,7 +28,7 @@ class OCRFile
|
|
|
28
28
|
end
|
|
29
29
|
end
|
|
30
30
|
rescue # Detect errors
|
|
31
|
-
binding.pry
|
|
31
|
+
#binding.pry
|
|
32
32
|
end
|
|
33
33
|
|
|
34
34
|
return @text
|
|
@@ -36,17 +36,20 @@ class OCRFile
|
|
|
36
36
|
|
|
37
37
|
# Check if file is pdf
|
|
38
38
|
def is_pdf?
|
|
39
|
+
puts "determined: is_pdf"
|
|
39
40
|
file_start = File.open(@path, 'r') { |f| f.read(8)}
|
|
40
41
|
file_start.match(/\%PDF-\d+\.?\d+/)
|
|
41
42
|
end
|
|
42
43
|
|
|
43
44
|
# Load text that is already extracted
|
|
44
45
|
def load_extracted_text(file)
|
|
46
|
+
puts "file exists: load_extracted_text"
|
|
45
47
|
@text = JSON.parse(File.read(file))["text"]
|
|
46
48
|
end
|
|
47
49
|
|
|
48
50
|
# Send file to give me text
|
|
49
51
|
def give_me_text
|
|
52
|
+
puts "using: give_me_text"
|
|
50
53
|
c = Curl::Easy.new("http://givemetext.okfnlabs.org/tika/tika/form")
|
|
51
54
|
c.multipart_form_post = true
|
|
52
55
|
c.http_post(Curl::PostField.file('file', @path))
|
|
@@ -56,6 +59,7 @@ class OCRFile
|
|
|
56
59
|
end
|
|
57
60
|
|
|
58
61
|
def give_me_text_local
|
|
62
|
+
puts "using: give_me_text_local"
|
|
59
63
|
c = Curl::Easy.new(@tika + "/tika")
|
|
60
64
|
# TODO: move this mime filtering to a higher global level
|
|
61
65
|
mime_magic = MimeMagic.by_path(@path)
|
|
@@ -65,7 +69,6 @@ class OCRFile
|
|
|
65
69
|
c.http_put(file_data)
|
|
66
70
|
|
|
67
71
|
#binding.pry
|
|
68
|
-
|
|
69
72
|
@text = c.body_str
|
|
70
73
|
gotten_text_ok?(@text)
|
|
71
74
|
end
|
|
@@ -77,6 +80,7 @@ class OCRFile
|
|
|
77
80
|
|
|
78
81
|
# OCR with tesseract
|
|
79
82
|
def ocr_pdf
|
|
83
|
+
puts "using: ocr_pdf"
|
|
80
84
|
# Dir_paths
|
|
81
85
|
base = Dir.pwd+"/"
|
|
82
86
|
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: parsefile
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.8
|
|
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:
|
|
12
|
+
date: 2017-01-19 00:00:00.000000000 Z
|
|
13
13
|
dependencies: []
|
|
14
14
|
description: OCR file and extract metadata using Apache Tika and Tesseract
|
|
15
15
|
email: shidash@shidash.com
|