groff_parser 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +1 -2
- data/lib/groff_parser/document.rb +5 -1
- data/lib/groff_parser/engine.rb +11 -13
- data/lib/groff_parser/version.rb +1 -1
- data/test/document_test.rb +7 -3
- data/test/engine_test.rb +30 -5
- 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: c4fc1b9649bdc2dcc2974e4a63fbe14cc9b792d4
|
4
|
+
data.tar.gz: 9ab8d0c06bcfcc6ad0411dcd7a336c90106ed2bd
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 477c47e9a716095b00130ae0821b0811a066698c787173951cf3faf7c4d577de748e078fa959541ce1f5d77db4ca8ea376b5dbe6673c403b4f7b4025dcde7d5f
|
7
|
+
data.tar.gz: e444620aa38927793be68cac6b5f469a99af7f34a4814dacafe3cce20e78e6995086173be1668e1b64e7a0bb859c4faf19d8db2aba657e0800685c986b52dd23
|
data/README.md
CHANGED
@@ -3,7 +3,6 @@
|
|
3
3
|
### Status
|
4
4
|
[![Gem Version](https://badge.fury.io/rb/groff_parser.png)](http://badge.fury.io/rb/groff_parser)
|
5
5
|
[![Code Climate](https://codeclimate.com/github/roperzh/groff_parser.png)](https://codeclimate.com/github/roperzh/groff_parser)
|
6
|
-
[![Dependencies](https://gemnasium.com/roperzh/groff_parser.png)](https://gemnasium.com/roperzh/groff_parser)
|
7
6
|
|
8
7
|
Tiny library to parse groff files, with some handy metods to manage directories with a lot of files
|
9
8
|
|
@@ -23,7 +22,7 @@ Or install it yourself as:
|
|
23
22
|
|
24
23
|
## Basic Usage
|
25
24
|
|
26
|
-
Coming soon, in the meantime you can read the [`docs`](http://rubydoc.info/gems/)
|
25
|
+
Coming soon, in the meantime you can read the [`docs`](http://rubydoc.info/gems/groff_parser)
|
27
26
|
|
28
27
|
|
29
28
|
## Contributing
|
@@ -4,6 +4,8 @@ module GroffParser
|
|
4
4
|
|
5
5
|
class Document
|
6
6
|
|
7
|
+
attr_accessor :path
|
8
|
+
|
7
9
|
# Initializes the document class
|
8
10
|
#
|
9
11
|
# @since 0.1.0
|
@@ -42,7 +44,9 @@ module GroffParser
|
|
42
44
|
# doesn't exist yet
|
43
45
|
|
44
46
|
def section(name)
|
45
|
-
raw_content[/SH
|
47
|
+
raw_section = raw_content[/SH (?:\")?#{name}(?:\")?(.*?)SH/im]
|
48
|
+
|
49
|
+
return raw_section.gsub("SH", "").gsub("#{name}", "") if raw_section
|
46
50
|
end
|
47
51
|
|
48
52
|
# Raw content of the document, without being parsed, in pure
|
data/lib/groff_parser/engine.rb
CHANGED
@@ -44,15 +44,12 @@ module GroffParser
|
|
44
44
|
#
|
45
45
|
# @param zipped [Boolean] indicates if the file is zipped or not (gzip)
|
46
46
|
#
|
47
|
-
# @
|
48
|
-
# dvi, html, lbp, lj4, ps, ascii, cp1047, latin1, utf8, X75, X75, X100, X100
|
49
|
-
#
|
50
|
-
# @return [String] the content of the document, parsed in the proper format
|
47
|
+
# @return [GroffParser::Document] the document, parsed and ready to be manipulated
|
51
48
|
|
52
|
-
def parse(document_path, zipped
|
49
|
+
def parse(document_path, zipped: zipped)
|
53
50
|
dpath = document_path.include?(path) ? document_path : "#{path}/#{document_path}"
|
54
51
|
|
55
|
-
Document.new(dpath, zipped: zipped)
|
52
|
+
Document.new(dpath, zipped: zipped)
|
56
53
|
end
|
57
54
|
|
58
55
|
# Parse all documents in a given directory, with a given format
|
@@ -65,14 +62,14 @@ module GroffParser
|
|
65
62
|
#
|
66
63
|
# @param zipped [Boolean] indicates if the file is zipped or not (gzip)
|
67
64
|
#
|
68
|
-
# @return [Array] an array of all the parsed documents
|
65
|
+
# @return [Array<GroffParser::Document>] an array of all the parsed documents
|
69
66
|
|
70
67
|
def parse_all(format: :utf8, zipped: false)
|
71
68
|
documents = []
|
72
69
|
search_path = zipped ? "#{path}/*.gz" : "#{path}/*[0-9]"
|
73
70
|
|
74
71
|
Dir.glob(search_path) do |document|
|
75
|
-
documents << parse(document, zipped
|
72
|
+
documents << parse(document, zipped: zipped)
|
76
73
|
end
|
77
74
|
|
78
75
|
documents
|
@@ -85,9 +82,8 @@ module GroffParser
|
|
85
82
|
# @example
|
86
83
|
# parser = GroffParser::Engine.new("/path/to/file")
|
87
84
|
# parser.apply { |document| document.parse }
|
88
|
-
#
|
89
85
|
|
90
|
-
def
|
86
|
+
def apply_to(*args)
|
91
87
|
yield parse(args.join(" "))
|
92
88
|
end
|
93
89
|
|
@@ -100,13 +96,15 @@ module GroffParser
|
|
100
96
|
# parser = GroffParser::Engine.new("/folder/with/some/files")
|
101
97
|
# parser.apply_all { |document| document.parse }
|
102
98
|
#
|
99
|
+
# @param zipped [Boolean] indicates if the file is zipped or not (gzip)
|
100
|
+
#
|
103
101
|
# @return [nil]
|
104
102
|
|
105
|
-
def
|
106
|
-
search_path =
|
103
|
+
def apply_to_all(zipped: false)
|
104
|
+
search_path = zipped ? "#{path}/*.gz" : "#{path}/*"
|
107
105
|
|
108
106
|
Dir.glob(search_path) do |document|
|
109
|
-
yield parse(
|
107
|
+
yield parse(document, zipped)
|
110
108
|
end
|
111
109
|
end
|
112
110
|
end
|
data/lib/groff_parser/version.rb
CHANGED
data/test/document_test.rb
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
require "test_helper"
|
1
|
+
require File.expand_path(File.join("test/test_helper"))
|
2
2
|
|
3
3
|
describe GroffParser::Document do
|
4
4
|
|
@@ -13,11 +13,11 @@ describe GroffParser::Document do
|
|
13
13
|
describe "#section" do
|
14
14
|
it "returns the contents of a section delimited by a given title" do
|
15
15
|
zipped_document.section("NAME").must_equal(
|
16
|
-
" \"
|
16
|
+
" \"\"\ngit \\- the stupid content tracker\n."
|
17
17
|
)
|
18
18
|
|
19
19
|
unzipped_document.section("NAME").must_equal(
|
20
|
-
" \"
|
20
|
+
" \"\"\ngit \\- the stupid content tracker\n."
|
21
21
|
)
|
22
22
|
end
|
23
23
|
|
@@ -26,6 +26,10 @@ describe GroffParser::Document do
|
|
26
26
|
unzipped_document.section("NAME")
|
27
27
|
)
|
28
28
|
end
|
29
|
+
|
30
|
+
it "returns nil if the provided section does not exists" do
|
31
|
+
zipped_document.section("UNEXISTENT_SECTION").must_equal(nil)
|
32
|
+
end
|
29
33
|
end
|
30
34
|
|
31
35
|
describe "#raw_content" do
|
data/test/engine_test.rb
CHANGED
@@ -5,17 +5,42 @@ describe GroffParser::Engine do
|
|
5
5
|
let(:engine) { GroffParser::Engine.new(path: "test/fixtures") }
|
6
6
|
|
7
7
|
describe "#parse" do
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
8
|
+
context "given a zipped document" do
|
9
|
+
it "returns a new GroffParser::Document instance" do
|
10
|
+
engine.parse("git.1.gz", zipped: true).class.must_equal(
|
11
|
+
GroffParser::Document
|
12
|
+
)
|
13
|
+
end
|
14
|
+
|
15
|
+
it "allows to retrieve information of the parsed file" do
|
16
|
+
engine.parse("git.1.gz", zipped: true).raw_content.must_equal(
|
17
|
+
GroffParser::Document.new("test/fixtures/git.1.gz", zipped: true)
|
18
|
+
.raw_content
|
19
|
+
)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
context "given an unzipped document" do
|
24
|
+
it "returns a new GroffParser::Document instance" do
|
25
|
+
engine.parse("git.1").class.must_equal(
|
26
|
+
GroffParser::Document
|
27
|
+
)
|
28
|
+
end
|
29
|
+
|
30
|
+
it "allows to retrieve information of the parsed file" do
|
31
|
+
engine.parse("git.1").raw_content.must_equal(
|
32
|
+
GroffParser::Document.new("test/fixtures/git.1.gz", zipped: true)
|
33
|
+
.raw_content
|
34
|
+
)
|
35
|
+
end
|
12
36
|
end
|
37
|
+
|
13
38
|
end
|
14
39
|
|
15
40
|
describe "#parse_all" do
|
16
41
|
it "returns an array with all the documents contents present in the path" do
|
17
42
|
engine.parse_all.must_equal(
|
18
|
-
[
|
43
|
+
[GroffParser::Document.new("test/fixtures/git.1", zipped: false)]
|
19
44
|
)
|
20
45
|
end
|
21
46
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: groff_parser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Roberto Dip
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-04-
|
11
|
+
date: 2014-04-11 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|