hippie_csv 0.0.5 → 0.0.6

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: 25ff6543c2223eed975723e6b5718081b2f03e33
4
- data.tar.gz: 5f62a6c390164ade3e7880ed59171f56f6d608fe
3
+ metadata.gz: f53a562b556d85f2c893855cf0aa34ea6126afab
4
+ data.tar.gz: 9c1a2954a38b2c01b1a9dcbc13c25fb21e9799be
5
5
  SHA512:
6
- metadata.gz: 43c0883650a3091512b8c60e55c882a22ea60fe0f946a9e74280739e0765306296fc53b8807189f9aecf71b76f41c7d23758056e025281d73e83639a301a4147
7
- data.tar.gz: 8318a4e154ddce8ef9d5d835faf30b5ae08a94a252350380d59538a34e01a7de7c07ee968e521c1efd34d53a15720f21372beda179d0ca3513c2a02a644abc35
6
+ metadata.gz: 7db7d04670863b9bffc7c66d8c1410b57892b4729819c6755816bd3e5deffcf0acc2af75870d6e26b41dc5643f1ef7eb8ec9cce86aa9868fff49129c2872e204
7
+ data.tar.gz: 2a587740e0ee24c021a373c71e4c3038447de70595d7ff1e89d86dc51aa696083a238cef221bdb2e6970a53eca11d407b6a0c5ee11df1449e32305ce25113055
@@ -1,10 +1,12 @@
1
- require 'csv'
1
+ require "csv"
2
2
 
3
3
  module HippieCSV
4
4
  QUOTE_CHARACTERS = %w(" ' |).freeze
5
5
  DELIMETERS = %W(, ; \t).freeze
6
6
  ENCODING = "utf-8".freeze
7
7
  ALTERNATE_ENCODING = "utf-16".freeze
8
- FIELD_SAMPLE_COUNT = 10
8
+ FIELD_SAMPLE_COUNT = 10.freeze
9
+ ENCODING_SAMPLE_CHARACTER_COUNT = 10000.freeze
9
10
  ENCODING_WITH_BOM = "bom|#{ENCODING}".freeze
11
+ BLANK_LINE_REGEX = /^,+\r+$/.freeze
10
12
  end
@@ -10,16 +10,18 @@ module HippieCSV
10
10
 
11
11
  def encode(string)
12
12
  unless string.valid_encoding?
13
- current_encoding = CharDet.detect(string)["encoding"]
14
-
15
- string = if !current_encoding.nil?
16
- string.encode(ENCODING, current_encoding)
17
- else
18
- string.encode(ALTERNATE_ENCODING, ENCODING, invalid: :replace, replace: "")
19
- .encode(ENCODING, ALTERNATE_ENCODING)
13
+ string = begin
14
+ current_encoding = detect_encoding(string)
15
+ if !current_encoding.nil?
16
+ string.encode(ENCODING, current_encoding)
17
+ else
18
+ magical_encode(string)
19
+ end
20
+ rescue Encoding::InvalidByteSequenceError
21
+ magical_encode(string)
20
22
  end
21
23
  end
22
-
24
+ string.gsub!(BLANK_LINE_REGEX, "")
23
25
  string.encode(string.encoding, universal_newline: true)
24
26
  end
25
27
 
@@ -59,6 +61,15 @@ module HippieCSV
59
61
 
60
62
  private
61
63
 
64
+ def detect_encoding(string)
65
+ CharDet.detect(string[0..ENCODING_SAMPLE_CHARACTER_COUNT])["encoding"]
66
+ end
67
+
68
+ def magical_encode(string)
69
+ string.encode(ALTERNATE_ENCODING, ENCODING, invalid: :replace, replace: "")
70
+ .encode(ENCODING, ALTERNATE_ENCODING)
71
+ end
72
+
62
73
  def field_count(file, delimeter, quote_character)
63
74
  csv = CSV.new(file, col_sep: delimeter, quote_char: quote_character)
64
75
  csv.lazy.take(FIELD_SAMPLE_COUNT).map(&:size).inject(:+)
@@ -1,3 +1,3 @@
1
1
  module HippieCSV
2
- VERSION = "0.0.5"
2
+ VERSION = "0.0.6"
3
3
  end