smarter_csv 1.9.0 → 1.9.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 20db4a75108d2b7934b90e6d0e3fef3053e61ad077b4ec4966a97a6e5cb3aa42
-  data.tar.gz: 44d1c3b995b3f7d53d46768437517379dfe3b93fa1db1384054ac16baadfb8d6
+  metadata.gz: 3e4032569303bd062a92b3c3f45f5166346808291667dda9ebd91af123f532ef
+  data.tar.gz: 78b73abc411d8ed866feae600b87b72c3c99fd3b00b67c81eac227c17f8d38ea
 SHA512:
-  metadata.gz: 74a2edab893bd9e1b798b03321aea55b566accb92a47d939bdddb616af57fc8525b60b50fb94d1f67face95c83d0a00300f587355dd4934130f5bac9879d5dcd
-  data.tar.gz: 1cb78471b4021dafed4fc1bdd42c2acae934eb1a89f05e9700bfb99f40543c770db58b9b42a70272de9797bdf43fe5d53fa8c352964c1574d658ab2f881a06d6
+  metadata.gz: 1712951a2ce4f6e8ad93a6e76a105a3a8d4890babacfbb9ae3eead11ac638962d9da3d45421a327049e87c9d54b43c0dca1327f11a13bbd54440d3a7fefc6253
+  data.tar.gz: 3d8b81f04c8eb16a7b2ab9ddf27bdaf2b2bfdd2ee3a8b70765a88f809fc9869500debe950d8ec27e3a6af818e6f1e415d96d078e52784d638f1363619088faa3

data/CHANGELOG.md

@@ -1,6 +1,19 @@
 
 # SmarterCSV 1.x Change Log
 
+## 1.9.2 (2023-11-12)
+  * fixed bug with '\\' at end of line (issue #252, thanks to averycrespi-moz)
+  * fixed require statements (issue #249, thanks to PikachuEXE, courtsimas)
+    
+## 1.9.1 (2023-10-30) (YANKED)
+  * yanked
+  * no functional changes
+  * refactored directory structure
+  * re-added JRuby and TruffleRuby to CI tests
+  * no C-accelleration for JRuby
+  * refactored options parsing
+  * code coverage / rubocop
+
 ## 1.9.0 (2023-09-04)
   * fixed issue #139
 

data/Gemfile

@@ -5,10 +5,13 @@ source 'https://rubygems.org'
 # Specify your gem's dependencies in smarter_csv.gemspec
 gemspec
 
-gem "rake" # , "< 11"
+gem "rake"
 gem "rake-compiler"
 
 gem 'pry'
-
-gem "rspec"
 gem "rubocop"
+
+group :test do
+  gem "rspec"
+  gem "simplecov"
+end

data/README.md

@@ -46,7 +46,11 @@ One `smarter_csv` user wrote:
  * able to ignore "columns" in the input (delete columns)
  * able to eliminate nil or empty fields from the result hashes (default)
 
-NOTE; This Gem is only for importing CSV files - writing of CSV files is not supported at this time.
+#### Assumptions / Limitations
+* It is assumed that the escape character is `\`, as on UNIX and Windows systems.
+* It is assumed that quote charcters around fields are balanced, e.g. valid: `"field"`, invalid: `"field\"`
+  e.g. an escaped `quote_char` does not denote the end of a field.
+* This Gem is only for importing CSV files - writing of CSV files is not supported at this time.
 
 ### Why?
 

data/Rakefile

@@ -21,11 +21,26 @@ RuboCop::RakeTask.new
 
 require "rake/extensiontask"
 
-task build: :compile
+if RUBY_ENGINE == 'jruby'
 
-Rake::ExtensionTask.new("smarter_csv") do |ext|
-  ext.ext_dir = "ext/smarter_csv"
+  task default: %i[spec]
+
+else
+  task build: :compile
+
+  Rake::ExtensionTask.new("smarter_csv") do |ext|
+    ext.lib_dir = "lib/smarter_csv"
+    ext.ext_dir = "ext/smarter_csv"
+    ext.source_pattern = "*.{c,h}"
+  end
+
+  # task default: %i[clobber compile spec rubocop]
+  task default: %i[clobber compile spec]
 end
 
-# task default: %i[clobber compile spec rubocop]
-task default: %i[clobber compile spec]
+desc 'Run spec with coverage'
+task :coverage do
+  ENV['COVERAGE'] = 'true'
+  Rake::Task['spec'].execute
+  `open coverage/index.html`
+end

data/ext/smarter_csv/extconf.rb

@@ -1,10 +1,10 @@
 # frozen_string_literal: true
 
 require 'mkmf'
-
 require "rbconfig"
+
 if RbConfig::MAKEFILE_CONFIG["CFLAGS"].include?("-g -O3")
-  fixed_CFLAGS = RbConfig::MAKEFILE_CONFIG["CFLAGS"].sub("-g -O3", "$(cflags)")
+  fixed_CFLAGS = RbConfig::MAKEFILE_CONFIG["CFLAGS"].sub("-g -O3", "-O3 $(cflags)")
   puts("Fix CFLAGS: #{RbConfig::MAKEFILE_CONFIG["CFLAGS"]} -> #{fixed_CFLAGS}")
   RbConfig::MAKEFILE_CONFIG["CFLAGS"] = fixed_CFLAGS
 end

data/ext/smarter_csv/smarter_csv.c

@@ -40,6 +40,7 @@ static VALUE rb_parse_csv_line(VALUE self, VALUE line, VALUE col_sep, VALUE quot
   long i;
 
   char prev_char = '\0'; // Store the previous character for comparison against an escape character
+  long backslash_count = 0; // to count consecutive backslash characters
 
   while (p < endP) {
     /* does the remaining string start with col_sep ? */
@@ -61,8 +62,13 @@ static VALUE rb_parse_csv_line(VALUE self, VALUE line, VALUE col_sep, VALUE quot
         startP = p;
       }
     } else {
-      if (*p == *quoteP && prev_char != '\\') {
-        quote_count += 1;
+      if (*p == '\\') {
+        backslash_count++;
+      } else {
+        if (*p == *quoteP && (backslash_count % 2 == 0)) {
+          quote_count++;
+        }
+        backslash_count = 0; // no more consecutive backslash characters
       }
       p++;
     }

data/lib/smarter_csv/options_processing.rb

@@ -0,0 +1,84 @@
+# frozen_string_literal: true
+
+module SmarterCSV
+  DEFAULT_OPTIONS = {
+    acceleration: true,
+    auto_row_sep_chars: 500,
+    chunk_size: nil,
+    col_sep: :auto, # was: ',',
+    comment_regexp: nil, # was: /\A#/,
+    convert_values_to_numeric: true,
+    downcase_header: true,
+    duplicate_header_suffix: nil,
+    file_encoding: 'utf-8',
+    force_simple_split: false,
+    force_utf8: false,
+    headers_in_file: true,
+    invalid_byte_sequence: '',
+    keep_original_headers: false,
+    key_mapping: nil,
+    quote_char: '"',
+    remove_empty_hashes: true,
+    remove_empty_values: true,
+    remove_unmapped_keys: false,
+    remove_values_matching: nil,
+    remove_zero_values: false,
+    required_headers: nil,
+    required_keys: nil,
+    row_sep: :auto, # was: $/,
+    silence_missing_keys: false,
+    skip_lines: nil,
+    strings_as_keys: false,
+    strip_chars_from_headers: nil,
+    strip_whitespace: true,
+    user_provided_headers: nil,
+    value_converters: nil,
+    verbose: false,
+    with_line_numbers: false,
+  }.freeze
+
+  class << self
+    # NOTE: this is not called when "parse" methods are tested by themselves
+    def process_options(given_options = {})
+      puts "User provided options:\n#{pp(given_options)}\n" if given_options[:verbose]
+
+      # fix invalid input
+      given_options[:invalid_byte_sequence] = '' if given_options[:invalid_byte_sequence].nil?
+
+      @options = DEFAULT_OPTIONS.dup.merge!(given_options)
+      puts "Computed options:\n#{pp(@options)}\n" if given_options[:verbose]
+
+      validate_options!(@options)
+      @options
+    end
+
+    # NOTE: this is not called when "parse" methods are tested by themselves
+    #
+    # ONLY FOR BACKWARDS-COMPATIBILITY
+    def default_options
+      DEFAULT_OPTIONS
+    end
+
+    private
+
+    def validate_options!(options)
+      keys = options.keys
+      errors = []
+      errors << "invalid row_sep" if keys.include?(:row_sep) && !option_valid?(options[:row_sep])
+      errors << "invalid col_sep" if keys.include?(:col_sep) && !option_valid?(options[:col_sep])
+      errors << "invalid quote_char" if keys.include?(:quote_char) && !option_valid?(options[:quote_char])
+      raise SmarterCSV::ValidationError, errors.inspect if errors.any?
+    end
+
+    def option_valid?(str)
+      return true if str.is_a?(Symbol) && str == :auto
+      return true if str.is_a?(String) && !str.empty?
+
+      false
+    end
+
+    def pp(value)
+      defined?(AwesomePrint) ? value.awesome_inspect(index: nil) : value.inspect
+    end
+  end
+end