crawler-movie-core 1.0.0 → 1.1.0
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/crawler-movie-core.gemspec +1 -0
- data/lib/crawler/movie.rb +7 -16
- data/lib/crawler/movie/core/version.rb +1 -1
- metadata +15 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: c09660f760f7aad4dd88b7b73d8580b9760a28b2339240c0e153e11e6a6619c9
|
4
|
+
data.tar.gz: c569adae99e851476dc3acc569cc0edfca62c226724d99993e5791112da62a75
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 40dda74a2f4e84f4ccda4a1fca6fda3890c580a80a83af0fb50624c4dfe766ec75dbca6be4995cbdc1f2a3d3620276e8ab3db623bdcf9c35519685d0c218a96a
|
7
|
+
data.tar.gz: 285870055ab6182b48ff2412dae6b6b0bdd7c3fec2d8ccbc5af983df880f7ff302ab8eb1fe5a85facea024a92cae1e1972d1e44c2bd8efd40d6843bc8fef51b3
|
data/crawler-movie-core.gemspec
CHANGED
data/lib/crawler/movie.rb
CHANGED
@@ -1,9 +1,12 @@
|
|
1
1
|
require 'active_support/core_ext/hash/keys'
|
2
2
|
require 'active_support/inflector'
|
3
|
-
require '
|
3
|
+
require 'crawler/base'
|
4
|
+
require 'crawler/utils'
|
4
5
|
|
5
6
|
module Crawler
|
6
7
|
module Movie
|
8
|
+
include Base
|
9
|
+
|
7
10
|
PROVIDERS = []
|
8
11
|
SCORES = {}
|
9
12
|
|
@@ -17,27 +20,15 @@ module Crawler
|
|
17
20
|
end
|
18
21
|
end
|
19
22
|
|
20
|
-
def self.configure
|
21
|
-
yield self
|
22
|
-
end
|
23
|
-
|
24
|
-
def self.transliterate(string)
|
25
|
-
ActiveSupport::Inflector.transliterate(string.gsub(/[:\-.,!?]/, ' ').strip.gsub(/\s+/, ' ')).downcase
|
26
|
-
end
|
27
|
-
|
28
23
|
def self.search(query, year: nil)
|
29
24
|
movies = PROVIDERS.flat_map do |provider_name|
|
30
25
|
camelized = ActiveSupport::Inflector.camelize("crawler/movie/providers/#{provider_name.to_s}")
|
31
26
|
klass = ActiveSupport::Inflector.constantize(camelized)
|
32
|
-
movies = klass.search(transliterate(query))
|
27
|
+
movies = klass.search(Utils.transliterate(query))
|
33
28
|
|
34
29
|
movies.map do |movie|
|
35
30
|
provider_score = SCORES[provider_name] || 0.5
|
36
|
-
|
37
|
-
title_transliterated = transliterate(movie[:title])
|
38
|
-
levenshtein_distance = Levenshtein.distance(query_transliterated, title_transliterated)
|
39
|
-
max_size = [query_transliterated.size, title_transliterated.size].max.to_f
|
40
|
-
title_score = (max_size - levenshtein_distance) / max_size
|
31
|
+
title_score = Utils.levenshtein_score(query, movie[:title])
|
41
32
|
year_score = 1.0 unless year
|
42
33
|
year_score ||= movie[:release_date] && year.to_s == movie[:release_date].year.to_s ? 1.0 : 0.9
|
43
34
|
|
@@ -49,7 +40,7 @@ module Crawler
|
|
49
40
|
end
|
50
41
|
|
51
42
|
movies.group_by do |movie|
|
52
|
-
[transliterate(movie[:data][:title]), movie[:data][:release_date] && movie[:data][:release_date].year]
|
43
|
+
[Utils.transliterate(movie[:data][:title]), movie[:data][:release_date] && movie[:data][:release_date].year]
|
53
44
|
end
|
54
45
|
end
|
55
46
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crawler-movie-core
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.1.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jonathan PHILIPPE
|
@@ -66,6 +66,20 @@ dependencies:
|
|
66
66
|
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '1.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: crawler-core
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0.2'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0.2'
|
69
83
|
description: ''
|
70
84
|
email:
|
71
85
|
- jonathan@cinema.paris
|