smarter_csv 1.8.3 → 1.8.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 654b04532f0d0b1e15bf84c2e23231e00946a1f57c613f53555ba2d531eaf4f9
-  data.tar.gz: d99a921a908864764a39e94818be45c9feb8a1fbe15eb776e24ef10e98c749fd
+  metadata.gz: 8a812edc2e7a7778b0722a120acf8432eb844895b09668c3adf37184cfa08408
+  data.tar.gz: e78756cef3558b32cfa2788fdbfdd8723cc7a06872c97916fc2c95e16cf363d7
 SHA512:
-  metadata.gz: 8005c2b6bdd4e82ab1acc8849afd4b8d7abf0d744bb18fa76aaac68a707a8f14300b4e844abac3dacab24b254c81787dc4501a1cc1138ebdc97fe52728e82f30
-  data.tar.gz: 0baead2aa4d6841f3770e27a24e5dc5d783873db253c8185e81366a2b5a36045d82f4dc2011fbd46373cf434968675b232217c8764c2c858d74c1cceaebd45ed
+  metadata.gz: e81dfd9e713a301f58c64311a02e5047aa3678652e7c410fd8bfaaa5f49459faa3766f5e152d27b080d8677fb3cb452b45ae76086f9feba5caf5f1cd57220260
+  data.tar.gz: c2a6206128b0860138ca739a70b9546fe6ddbb37b4d09069607abc17a08fd51a2f2070d9ab2a6f55955a5f6a98f9def1dad7ce5ac03d0d6aabe67c9593be792f

data/CHANGELOG.md

@@ -1,6 +1,12 @@
 
 # SmarterCSV 1.x Change Log
 
+## 1.8.5 (2023-06-25)
+  * fix parsing of escaped quote characters (thanks to JP Camara)
+    
+## 1.8.4 (2023-04-01)
+  * fix gem loading issue (issue #232, #234)
+  
 ## 1.8.3 (2023-03-30)
   * bugfix: windows one-column files were raising NoColSepDetected (issue #229)
     

data/CONTRIBUTORS.md

@@ -50,3 +50,4 @@ A Big Thank you to everyone who filed issues, sent comments, and who contributed
  * [Hirotaka Mizutani ](https://github.com/hirotaka)
  * [Rahul Chaudhary](https://github.com/rahulch95)
  * [Alessandro Fazzi](https://github.com/pioneerskies)
+ * [JP Camara](https://github.com/jpcamara)

data/ext/smarter_csv/smarter_csv.c

@@ -39,6 +39,8 @@ static VALUE rb_parse_csv_line(VALUE self, VALUE line, VALUE col_sep, VALUE quot
   VALUE field;
   long i;
 
+  char prev_char = '\0'; // Store the previous character for comparison against an escape character
+
   while (p < endP) {
     /* does the remaining string start with col_sep ? */
     col_sep_found = true;
@@ -59,11 +61,13 @@ static VALUE rb_parse_csv_line(VALUE self, VALUE line, VALUE col_sep, VALUE quot
         startP = p;
       }
     } else {
-      if (*p == *quoteP) {
+      if (*p == *quoteP && prev_char != '\\') {
         quote_count += 1;
       }
       p++;
     }
+
+    prev_char = *(p - 1); // Update the previous character
   } /* while */
 
   /* check if the last part of the line needs to be processed */

data/lib/smarter_csv/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SmarterCSV
-  VERSION = "1.8.3"
+  VERSION = "1.8.5"
 end

data/lib/smarter_csv.rb

@@ -3,11 +3,8 @@
 require_relative "extensions/hash"
 require_relative "smarter_csv/version"
 
-if `uname -s`.chomp == 'Darwin'
-  require 'smarter_csv.bundle' unless ENV['CI'] # local testing
-else
-  require_relative "smarter_csv/smarter_csv" unless ENV['CI'] # does not compile/link in CI?
-end
+require_relative "smarter_csv/smarter_csv" unless ENV['CI'] # does not compile/link in CI?
+# require 'smarter_csv.bundle' unless ENV['CI'] # local testing
 
 module SmarterCSV
   class SmarterCSVException < StandardError; end
@@ -72,8 +69,8 @@ module SmarterCSV
         # in which case the row data will be split across multiple lines (see the sample content in spec/fixtures/carriage_returns_rn.csv)
         # by detecting the existence of an uneven number of quote characters
 
-        multiline = line.count(options[:quote_char]).odd? # should handle quote_char nil
-        while line.count(options[:quote_char]).odd? # should handle quote_char nil
+        multiline = count_quote_chars(line, options[:quote_char]).odd? # should handle quote_char nil
+        while count_quote_chars(line, options[:quote_char]).odd? # should handle quote_char nil
           next_line = fh.readline(options[:row_sep])
           next_line = next_line.force_encoding('utf-8').encode('utf-8', invalid: :replace, undef: :replace, replace: options[:invalid_byte_sequence]) if options[:force_utf8] || options[:file_encoding] !~ /utf-8/i
           line += next_line
@@ -199,6 +196,21 @@ module SmarterCSV
       @headers
     end
 
+    # Counts the number of quote characters in a line, excluding escaped quotes.
+    def count_quote_chars(line, quote_char)
+      return 0 if line.nil? || quote_char.nil?
+
+      count = 0
+      previous_char = ''
+
+      line.each_char do |char|
+        count += 1 if char == quote_char && previous_char != '\\'
+        previous_char = char
+      end
+
+      count
+    end
+
     protected
 
     # NOTE: this is not called when "parse" methods are tested by themselves
@@ -313,15 +325,18 @@ module SmarterCSV
       start = 0
       i = 0
 
+      previous_char = ''
       while i < line_size
         if line[i...i+col_sep_size] == col_sep && quote_count.even?
           break if !header_size.nil? && elements.size >= header_size
 
           elements << cleanup_quotes(line[start...i], quote)
+          previous_char = line[i]
           i += col_sep.size
           start = i
         else
-          quote_count += 1 if line[i] == quote
+          quote_count += 1 if line[i] == quote && previous_char != '\\'
+          previous_char = line[i]
           i += 1
         end
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: smarter_csv
 version: !ruby/object:Gem::Version
-  version: 1.8.3
+  version: 1.8.5
 platform: ruby
 authors:
 - Tilo Sloboda
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-03-30 00:00:00.000000000 Z
+date: 2023-06-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: awesome_print
@@ -141,7 +141,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.6
+rubygems_version: 3.2.3
 signing_key:
 specification_version: 4
 summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots