parsefile 0.0.11 → 0.0.12
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/ocrfile.rb +3 -1
- data/lib/parsefile.rb +4 -3
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b5bf09e69f1851e80512b7839555716e341c046e
|
4
|
+
data.tar.gz: 734a807444328107153a734c18aeba18676354fa
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 27d5719e889e4d2b883ea5809eee139707c0510210413752436ffd93be164a168866bdd73578af2d88b9a66ff5dd8e0e1510176c207139143234d558055d8788
|
7
|
+
data.tar.gz: 698a87c083f2ffcfa7057d3dc1fc143c384f7aeb7499dd8ff7453040ec9f8f84301d8c4eccad5c6ed4b37d3224f7d017fc4b8fd4fa1e15b59519e5f8c09a9011
|
data/lib/ocrfile.rb
CHANGED
data/lib/parsefile.rb
CHANGED
@@ -6,7 +6,7 @@ require 'extractmetadata'
|
|
6
6
|
|
7
7
|
class ParseFile
|
8
8
|
def initialize(file, input_dir, output_dir, tika)
|
9
|
-
@path = file
|
9
|
+
@path = file
|
10
10
|
@input_dir = input_dir
|
11
11
|
@output_dir = output_dir
|
12
12
|
# Pass URL of a Tika server
|
@@ -21,8 +21,9 @@ class ParseFile
|
|
21
21
|
def parse_file
|
22
22
|
begin
|
23
23
|
puts "sending file: " + @path
|
24
|
-
|
25
|
-
|
24
|
+
|
25
|
+
path_fix = @path.unpack('C*').pack('U*')
|
26
|
+
m = ExtractMetadata.new(path_fix, @input_dir, @output_dir)
|
26
27
|
@metadata = m.extract
|
27
28
|
|
28
29
|
o = OCRFile.new(@path, @input_dir, @output_dir, @metadata[:rel_path], @tika)
|