file_crawler 0.2.0 → 0.2.1
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 +4 -4
- data/lib/file_crawler/finder.rb +6 -0
- data/lib/file_crawler/finder/command/collect.rb +35 -25
- data/lib/file_crawler/version.rb +1 -1
- 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: 4e77bb0b7e6727a74e536b0c5f6acaf24b69d9ec
|
4
|
+
data.tar.gz: ca8781f50a9fc79273f8de5170bb4e40d36f7c3c
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 754443d6750b069567be5988e6c54603ab0d34bedb1b38c2336412de1c192bda2f3010a689090321358020119f60f9bbc8708a24deb774e7eac074d8e1704ca1
|
7
|
+
data.tar.gz: 25e8ee3a47612156cf55e6cd1c9213b9519483e591fbd8b312594af6ba22693ddb7ed05c55146602c645edab2141d837b782137500d96a20bd6bc7a133c36b96
|
data/lib/file_crawler/finder.rb
CHANGED
@@ -1,22 +1,46 @@
|
|
1
1
|
module FileCrawler
|
2
|
+
class Regex
|
3
|
+
attr_accessor :regexp_start, :regexp_end
|
4
|
+
|
5
|
+
def initialize(regexp_start, regexp_end)
|
6
|
+
@regexp_start = regexp_start
|
7
|
+
@regexp_end = regexp_end
|
8
|
+
end
|
9
|
+
|
10
|
+
def pattern
|
11
|
+
/#{Regexp.escape(regexp_start)}(.+)#{Regexp.escape(regexp_end)}/
|
12
|
+
end
|
13
|
+
|
14
|
+
def to_s
|
15
|
+
"#<#{self.class.name}: start='#{regexp_start}', end='#{regexp_end}'"
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
2
19
|
class Finder
|
3
20
|
module Command
|
4
21
|
module Collect
|
5
22
|
|
23
|
+
attr_accessor :regexs
|
24
|
+
|
25
|
+
def regexs
|
26
|
+
@regexs ||= []
|
27
|
+
end
|
28
|
+
|
6
29
|
def collect(file_paths, conditions = {})
|
7
30
|
collection = collect_into_filename(file_paths)
|
8
31
|
|
9
|
-
case
|
10
|
-
when !conditions[:unique].nil?
|
11
|
-
collection = unique_in_collection(collection)
|
12
|
-
end
|
13
|
-
|
14
32
|
collection
|
15
33
|
end
|
16
34
|
|
17
|
-
def
|
18
|
-
|
19
|
-
|
35
|
+
def decide_index_for_collect(string)
|
36
|
+
if !regexs.empty?
|
37
|
+
regexs.each {|regex|
|
38
|
+
return $1 unless regex.pattern.match(string).nil?
|
39
|
+
}
|
40
|
+
end
|
41
|
+
|
42
|
+
pattern = /[\p{Hiragana}|\p{Katakana}|\p{Han}|[a-zA-Z0-9]ー ]+/
|
43
|
+
return string.strip.scan(pattern).first
|
20
44
|
end
|
21
45
|
|
22
46
|
def collect_into_filename(file_paths)
|
@@ -24,23 +48,9 @@ module FileCrawler
|
|
24
48
|
|
25
49
|
file_paths.each {|file_path|
|
26
50
|
filename = File.basename(file_path)
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
}
|
31
|
-
}
|
32
|
-
|
33
|
-
hash
|
34
|
-
end
|
35
|
-
|
36
|
-
def unique_in_collection(collection)
|
37
|
-
hash = {}
|
38
|
-
|
39
|
-
collection.sort {|(k1, v1), (k2, v2)|
|
40
|
-
v2.size <=> v1.size && k1 <=> k2
|
41
|
-
}.each {|term, file_paths|
|
42
|
-
selection = file_paths.select {|v| !hash.values.flatten.include?(v) }
|
43
|
-
hash[term] = selection unless selection.empty?
|
51
|
+
term = decide_index_for_collect(filename)
|
52
|
+
hash[term] ||= []
|
53
|
+
hash[term] << file_path
|
44
54
|
}
|
45
55
|
|
46
56
|
hash
|
data/lib/file_crawler/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: file_crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Hirohisa Kawasaki
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-05-
|
11
|
+
date: 2016-05-29 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|