simple_text_extract 0.1.0 → 0.1.1
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
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 6bfb9a91dc36259a45033d005b1b5a4bc37c941b153235708ca6755d77cce66e
|
|
4
|
+
data.tar.gz: dad58cb4b7f039d258196a1ce8568e8169214b12d8ff1c024e1fd9f8412fdf5b
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 0c5923028e2ff87feecddfcc2f6b340d4ffeb20d92bde686d607a1f498a2fe94326cd5f2df514f392641bbea988776955c76c4a12651178c2a32f885fda39c3d
|
|
7
|
+
data.tar.gz: acfb70f0bc6746011111a39c5fb730e378372e21b7b5f9eafda1f072c0ead5801ac2425d00070e1b2cc6cb78f6df3a93a0d313ae4627af1e3a7de3339baab882
|
data/README.md
CHANGED
|
@@ -7,6 +7,8 @@ SimpleTextExtract handles parsing text from:
|
|
|
7
7
|
- `.pdf`
|
|
8
8
|
- `.docx`
|
|
9
9
|
- `.doc`
|
|
10
|
+
- `.xlsx`
|
|
11
|
+
- `.xls`
|
|
10
12
|
- `.txt` 😜
|
|
11
13
|
|
|
12
14
|
If no text is parsed (for `pdf`), or a file format is not supported (like images), then `nil` is returned and you can move on to the heavy-duty tools like [Henkei](https://github.com/abrom/henkei) 💪.
|
|
@@ -32,11 +34,11 @@ Or install it yourself as:
|
|
|
32
34
|
Text can be parsed from raw file content or files in the filesystem t by calling `SimpleTextExtract.extract`:
|
|
33
35
|
|
|
34
36
|
```ruby
|
|
35
|
-
|
|
36
|
-
|
|
37
|
+
# raw file content using ActiveStorage
|
|
38
|
+
SimpleTextExtract.extract(filename: attachment.blob.filename, raw: attachment.download)
|
|
37
39
|
|
|
38
|
-
|
|
39
|
-
|
|
40
|
+
# filesystem
|
|
41
|
+
SimpleTextExtract.extract(filepath: "path_to_file.pdf")
|
|
40
42
|
```
|
|
41
43
|
|
|
42
44
|
### Usage Dependencies
|
|
@@ -49,6 +51,9 @@ You can choose to use SimpleTextExtract without the following dependencies, but
|
|
|
49
51
|
`doc` parsing requires `antiword`
|
|
50
52
|
- `brew install antiword`
|
|
51
53
|
|
|
54
|
+
`xlsx` and `xls` parsing requires `ssconvert` which is part of `gnumeric`
|
|
55
|
+
- `brew install gnumeric`
|
|
56
|
+
|
|
52
57
|
### Usage on Heroku
|
|
53
58
|
|
|
54
59
|
To use on Heroku you'll have to add some custom buildpacks.
|
|
@@ -67,6 +72,7 @@ To add `antiword` as a dependency on Heroku, install the [heroku-buildpack-apt](
|
|
|
67
72
|
In your `Aptfile`, add:
|
|
68
73
|
```
|
|
69
74
|
antiword
|
|
75
|
+
gnumeric
|
|
70
76
|
```
|
|
71
77
|
|
|
72
78
|
## Development
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module SimpleTextExtract
|
|
4
|
+
module FormatExtractor
|
|
5
|
+
class XlsX < Base
|
|
6
|
+
def extract
|
|
7
|
+
return nil if `command -v ssconvert`.empty?
|
|
8
|
+
|
|
9
|
+
extract_filepath = "#{file.path.split(".")[0]}.txt"
|
|
10
|
+
|
|
11
|
+
`ssconvert -O 'separator=" "' #{Shellwords.escape(file.path)} #{extract_filepath}`
|
|
12
|
+
|
|
13
|
+
text = File.read(extract_filepath)
|
|
14
|
+
File.unlink(extract_filepath)
|
|
15
|
+
|
|
16
|
+
text
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
end
|
|
20
|
+
end
|
|
@@ -3,6 +3,7 @@
|
|
|
3
3
|
require "simple_text_extract/format_extractor/base"
|
|
4
4
|
require "simple_text_extract/format_extractor/plain_text"
|
|
5
5
|
require "simple_text_extract/format_extractor/pdf"
|
|
6
|
+
require "simple_text_extract/format_extractor/xls_x"
|
|
6
7
|
require "simple_text_extract/format_extractor/doc_x"
|
|
7
8
|
require "simple_text_extract/format_extractor/doc"
|
|
8
9
|
|
|
@@ -18,6 +19,8 @@ module SimpleTextExtract
|
|
|
18
19
|
FormatExtractor::DocX.new(file)
|
|
19
20
|
when /.doc$/i
|
|
20
21
|
FormatExtractor::Doc.new(file)
|
|
22
|
+
when /(.xlsx$|.xls$)/i
|
|
23
|
+
FormatExtractor::XlsX.new(file)
|
|
21
24
|
else
|
|
22
25
|
FormatExtractor::Base.new(file)
|
|
23
26
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: simple_text_extract
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Nick Weiland
|
|
@@ -78,6 +78,7 @@ files:
|
|
|
78
78
|
- lib/simple_text_extract/format_extractor/doc_x.rb
|
|
79
79
|
- lib/simple_text_extract/format_extractor/pdf.rb
|
|
80
80
|
- lib/simple_text_extract/format_extractor/plain_text.rb
|
|
81
|
+
- lib/simple_text_extract/format_extractor/xls_x.rb
|
|
81
82
|
- lib/simple_text_extract/format_extractor_factory.rb
|
|
82
83
|
- lib/simple_text_extract/tempfile_extractor.rb
|
|
83
84
|
- lib/simple_text_extract/text_extractor.rb
|