smarter_csv 1.1.2 → 1.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 430c575cd14bb098e7754d0228186f0a29007495
-  data.tar.gz: 903d566d2c3569c954ecabf5ebf310c8f9aa5234
+  metadata.gz: cbd937d958dbb95653e9368a6b10075162f122e7
+  data.tar.gz: eaf5a03e4a209900189f035d2b5b876cc1c08e51
 SHA512:
-  metadata.gz: c846301856cbcf8e76efcf42d1d532a3317e6fdfce9ca06577794bae11b1e739086c6d40df70210fd3f0c75836bb9265ccff4d6d286fa998af735d43ef5c46ae
-  data.tar.gz: 52274d68e87f3e194be610bd69cfee6b084c193e389cf3591399a70e4051f23d1a2206c4d61aadb25c6c63c8675f285ef343e022f9dc70c95aac518f849ed005
+  metadata.gz: 7abffcc904a90122851159a5d241ad0f5944c0b3c67a288c5f91f93c86667f3ce0293cbb14dbe5d8c507a8ed955d8583d39099431ec929ba0d822b163a3e0ff1
+  data.tar.gz: a96735123fb0c8f5dae9eeea4b7606feba984d6daa6f347125a2cd6a810cb5a3eecf3af733277f4ee8143077b08fffbca4ce9a83c0eecccc7972e3a0ce43ef77

data/README.md

@@ -293,6 +293,9 @@ Planned in the next releases:
 
 ## Changes
 
+#### 1.1.3 (2016-12-30)
+ * added warning when options indicate UTF-8 processing, but input filehandle is not opened with r:UTF-8 option
+
 #### 1.1.2 (2016-12-29)
  * added option `invalid_byte_sequence` (thanks to polycarpou)
  * added comments on handling of UTF-8 encoding when opening from File vs. OpenURI (thanks to KevinColemanInc)

data/lib/smarter_csv/smarter_csv.rb

@@ -22,6 +22,10 @@ module SmarterCSV
     begin
       f = input.respond_to?(:readline) ? input : File.open(input, "r:#{options[:file_encoding]}")
 
+      if (options[:force_utf8] || options[:file_encoding] =~ /utf-8/i) && ( f.respond_to?(:external_encoding) && f.external_encoding != Encoding.find('UTF-8') || f.respond_to?(:encoding) && f.encoding != Encoding.find('UTF-8') )
+        puts 'WARNING: you are trying to process UTF-8 input, but did not open the input with "b:utf-8" option. See README file "NOTES about File Encodings".'
+      end
+
       if options[:row_sep] == :auto
         options[:row_sep] =  SmarterCSV.guess_line_ending( f, options )
         f.rewind
@@ -36,7 +40,7 @@ module SmarterCSV
         # process the header line in the CSV file..
         # the first line of a CSV file contains the header .. it might be commented out, so we need to read it anyhow
         header = f.readline.sub(options[:comment_regexp],'').chomp(options[:row_sep])
-        header = header.encode!('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: options[:invalid_byte_sequence]) if options[:force_utf8] || options[:file_encoding] == 'utf-8'
+        header = header.encode!('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: options[:invalid_byte_sequence]) if options[:force_utf8] || options[:file_encoding] =~ /utf-8/i
 
         file_line_count += 1
         csv_line_count += 1
@@ -103,7 +107,7 @@ module SmarterCSV
         line = line.encode!('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '') if options[:force_utf8]
 
         # replace invalid byte sequence in UTF-8 with question mark to avoid errors
-        line = line.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: options[:invalid_byte_sequence]) if options[:force_utf8] || options[:file_encoding] == 'utf-8'
+        line = line.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: options[:invalid_byte_sequence]) if options[:force_utf8] || options[:file_encoding] =~ /utf-8/i
 
         file_line_count += 1
         csv_line_count += 1

data/lib/smarter_csv/version.rb

@@ -1,3 +1,3 @@
 module SmarterCSV
-  VERSION = "1.1.2"
+  VERSION = "1.1.3"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: smarter_csv
 version: !ruby/object:Gem::Version
-  version: 1.1.2
+  version: 1.1.3
 platform: ruby
 authors:
 - |