tag_crawler 0.1.3 → 0.1.4

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
  SHA1:
3
- metadata.gz: 13ed4f2f4d8ccf9a2372c8a480f0e233d47b86b5
4
- data.tar.gz: 5574e0f74fef547ef0fbf2b562d63ebdc2fa1a32
3
+ metadata.gz: 3996a16de9afd4b4925ead85790e4844516b8bb7
4
+ data.tar.gz: 7bedabbf2213f7da4863e181d1085bedfbcc6823
5
5
  SHA512:
6
- metadata.gz: e375536e3a849ba3afc32e3d3ab305fb31987095bb13581b26f146491b22a750c3f9fc2ba7ccc99ab9505d527291bbd40c19be21a03f56c2c37d9e4c29966dfb
7
- data.tar.gz: d562440f17a682590677410c7a2b0a4e892d1b9a0261972eb8a6b970cb3126c8c2912581e43b30581363aa2fdc5af35b64d0c73b582881031ef92f34dadd37db
6
+ metadata.gz: 372c686422828917d6f23cef80fb416dfd744a72e4cbca3373db785818de510b98b0c1a04c9f460645c6238a4247709a19e6c9f72dd4773d6604ed718d872733
7
+ data.tar.gz: bac6a26f2f9bdc876a037ba9dbccf3ebf9c609114c730b35e759eb35b6ad8f138d006ea2a5fc20fcddc51a4edbad346df3a63e1fea12554fb80df2fffec2805e
File without changes
@@ -1,3 +1,3 @@
1
1
  module TagCrawler
2
- VERSION = "0.1.3"
2
+ VERSION = "0.1.4"
3
3
  end
@@ -9,6 +9,7 @@ module TagCrawler
9
9
  CLOSING_TAG = /<\/(\w+)>/
10
10
  SELF_CLOSING_TAG = /\<(\w+)(\/\>|\s*(.*)\/\>)/
11
11
  CAPITAL_LETTER = /[A-Z]/
12
+ PUNCTUATION = /[^[:alnum:]\s]/
12
13
 
13
14
  def initialize(url)
14
15
  begin
@@ -59,6 +60,7 @@ module TagCrawler
59
60
  def find_sequences(nodes)
60
61
  sequences = []
61
62
  nodes.each do |node|
63
+ node = node.gsub(PUNCTUATION, "")
62
64
  words = node.split(" ")
63
65
  current_sequence = []
64
66
  words.each_with_index do |word, idx|
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: tag_crawler
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.3
4
+ version: 0.1.4
5
5
  platform: ruby
6
6
  authors:
7
7
  - David Jiang