smarter_csv 1.5.1 → 1.5.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 352cf76ac0cd6b2eb4a1cac9e5056aa6e92a8a61b627d7c922e063dcf82ad675
-  data.tar.gz: 0c6e3ab1eaee02a9361fe0b418191244d81bc558dbcd10ee1d2c5f15390d91b6
+  metadata.gz: 88b9932c898320fb05d5697e155dc0bd3ade887d2fcfab7b660933e230007364
+  data.tar.gz: f0525d9c917aff44f910d4547b8e918faa3beb50d47adc29182df1fc1ec2be19
 SHA512:
-  metadata.gz: 3763cd8e493e7da6560e8ce9adc58bd411f745f5af119c97d70c02667a524ccb1055b5c640ef795c3cb25b79fa5e17800018da6e76f9d358afa1c7a3513caae3
-  data.tar.gz: '039183fdece20e80007f3f0d3e395fac8d273df6c21928a35b685ade5915503b3c55918fc7015ead0a7d768a545bb76bcfb1087006af6118dc3d22df83e68ddb'
+  metadata.gz: 330ad44b9808150f6fdf96dec65d259c2d9cf5eb25e22dc80f63095f4014b065b8aa97a2ba9b814c6cea6f4c0361e04567be403ab78b54d0518b49dc072f36ac
+  data.tar.gz: 27531bd508b5b455a32947badfb85d7e95489ad282a837ef046864806ba7fa12539148ab2fe4c84174fba3ef085dd3adda5d7c070615d684cd99ed0f90b903a3

data/CHANGELOG.md

@@ -1,7 +1,10 @@
 
 # SmarterCSV 1.x Change Log
 
-## 1.5.1 (2022-04-26)
+## 1.5.2 (2022-04-29)
+  * added missing keys to the SmarterCSV::KeyMappingError exception message #189 (thanks to John Dell)
+  
+## 1.5.1 (2022-04-27)
   * added raising of `KeyMappingError` if `key_mapping` refers to a non-existent key
   * added option `duplicate_header_suffix` (thanks to Skye Shaw)
     When given a non-nil string, it uses the suffix to append numbering 2..n to duplicate headers.

data/CONTRIBUTORS.md

@@ -44,3 +44,4 @@ A Big Thank you to everyone who filed issues, sent comments, and who contributed
  * [Nicolas Guillemain](https://github.com/Viiruus)
  * [Sp6](https://github.com/sp6)
  * [Joel Fouse](https://github.com/jfouse)
+ * [John Dell](https://github.com/spovich)

data/lib/smarter_csv/smarter_csv.rb

@@ -18,24 +18,28 @@ module SmarterCSV
     @csv_line_count = 0
     has_rails = !! defined?(Rails)
     begin
-      f = input.respond_to?(:readline) ? input : File.open(input, "r:#{options[:file_encoding]}")
+      fh = input.respond_to?(:readline) ? input : File.open(input, "r:#{options[:file_encoding]}")
 
       # auto-detect the row separator
-      options[:row_sep] = SmarterCSV.guess_line_ending(f, options) if options[:row_sep].to_sym == :auto
+      options[:row_sep] = SmarterCSV.guess_line_ending(fh, options) if options[:row_sep].to_sym == :auto
       # attempt to auto-detect column separator
-      options[:col_sep] = guess_column_separator(f, options) if options[:col_sep].to_sym == :auto
+      options[:col_sep] = guess_column_separator(fh, options) if options[:col_sep].to_sym == :auto
       # preserve options, in case we need to call the CSV class
       csv_options = options.select{|k,v| [:col_sep, :row_sep, :quote_char].include?(k)} # options.slice(:col_sep, :row_sep, :quote_char)
       csv_options.delete(:row_sep) if [nil, :auto].include?( options[:row_sep].to_sym )
       csv_options.delete(:col_sep) if [nil, :auto].include?( options[:col_sep].to_sym )
 
-      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') )
+      if (options[:force_utf8] || options[:file_encoding] =~ /utf-8/i) && ( fh.respond_to?(:external_encoding) && fh.external_encoding != Encoding.find('UTF-8') || fh.respond_to?(:encoding) && fh.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
 
-      options[:skip_lines].to_i.times{f.readline(options[:row_sep])} if options[:skip_lines].to_i > 0
+      if options[:skip_lines].to_i > 0
+        options[:skip_lines].to_i.times do
+          readline_with_counts(fh, options)
+        end
+      end
 
-      headerA, header_size = process_headers(f, options, csv_options)
+      headerA, header_size = process_headers(fh, options, csv_options)
 
       # in case we use chunking.. we'll need to set it up..
       if ! options[:chunk_size].nil? && options[:chunk_size].to_i > 0
@@ -48,10 +52,8 @@ module SmarterCSV
       end
 
       # now on to processing all the rest of the lines in the CSV file:
-      while ! f.eof?    # we can't use f.readlines() here, because this would read the whole file into memory at once, and eof => true
-        line = f.readline(options[:row_sep])  # read one line
-        @file_line_count += 1
-        @csv_line_count += 1
+      while ! fh.eof?    # we can't use fh.readlines() here, because this would read the whole file into memory at once, and eof => true
+        line = readline_with_counts(fh, options)
 
         # replace invalid byte sequence in UTF-8 with question mark to avoid errors
         line = 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
@@ -65,7 +67,7 @@ module SmarterCSV
         # by detecting the existence of an uneven number of quote characters
         multiline = line.count(options[:quote_char])%2 == 1 # should handle quote_char nil
         while line.count(options[:quote_char])%2 == 1 # should handle quote_char nil
-          next_line = f.readline(options[:row_sep])
+          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
           @file_line_count += 1
@@ -138,7 +140,7 @@ module SmarterCSV
         if use_chunks
           chunk << hash  # append temp result to chunk
 
-          if chunk.size >= chunk_size || f.eof?   # if chunk if full, or EOF reached
+          if chunk.size >= chunk_size || fh.eof?   # if chunk if full, or EOF reached
             # do something with the chunk
             if block_given?
               yield chunk  # do something with the hashes in the chunk in the block
@@ -179,7 +181,7 @@ module SmarterCSV
         chunk = []  # initialize for next chunk of data
       end
     ensure
-      f.close if f.respond_to?(:close)
+      fh.close if fh.respond_to?(:close)
     end
     if block_given?
       return chunk_count  # when we do processing through a block we only care how many chunks we processed
@@ -190,6 +192,13 @@ module SmarterCSV
 
   private
 
+  def self.readline_with_counts(filehandle, options)
+    line  = filehandle.readline(options[:row_sep])
+    @file_line_count += 1
+    @csv_line_count += 1
+    line
+  end
+
   def self.default_options
     {
       auto_row_sep_chars: 500,
@@ -314,9 +323,7 @@ module SmarterCSV
     if options[:headers_in_file]        # extract the header line
       # 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 = filehandle.readline(options[:row_sep])
-      @file_line_count += 1
-      @csv_line_count += 1
+      header = readline_with_counts(filehandle, options)
 
       header = header.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
       header = header.sub(options[:comment_regexp],'') if options[:comment_regexp]
@@ -371,7 +378,8 @@ module SmarterCSV
       #   if you want to completely delete a key, then map it to nil or to ''
       if ! key_mappingH.nil? && key_mappingH.class == Hash && key_mappingH.keys.size > 0
         # we can't map keys that are not there
-        raise SmarterCSV::KeyMappingError unless (key_mappingH.keys - headerA).empty?
+        missing_keys = key_mappingH.keys - headerA
+        raise(SmarterCSV::KeyMappingError, "missing header(s): #{missing_keys.join(",")}") unless missing_keys.empty?
 
         headerA.map!{|x| key_mappingH.has_key?(x) ? (key_mappingH[x].nil? ? nil : key_mappingH[x]) : (options[:remove_unmapped_keys] ? nil : x)}
       end

data/lib/smarter_csv/version.rb

@@ -1,3 +1,3 @@
 module SmarterCSV
-  VERSION = "1.5.1"
+  VERSION = "1.5.2"
 end

data/spec/smarter_csv/duplicate_headers_spec.rb

@@ -17,12 +17,12 @@ describe 'duplicate headers' do
       }.to raise_exception(SmarterCSV::DuplicateHeaders)
     end
 
-    it 'raises error on missing mapped headers' do
+    it 'raises error on missing mapped headers and includes missing headers in message' do
       expect {
         # the mapping is right, but the underlying csv file is bad
         options = {:key_mapping => {:email => :a, :firstname => :b, :lastname => :c, :manager_email => :d, :age => :e} }
         SmarterCSV.process("#{fixture_path}/duplicate_headers.csv", options)
-      }.to raise_exception(SmarterCSV::KeyMappingError)
+      }.to raise_exception(SmarterCSV::KeyMappingError, "missing header(s): manager_email")
     end
   end
 

data/spec/smarter_csv/invalid_headers_spec.rb

@@ -28,11 +28,11 @@ describe 'test exceptions for invalid headers' do
     }.to raise_exception(SmarterCSV::MissingHeaders)
   end
 
-  it 'raises error on missing mapped headers' do
+  it 'raises error on missing mapped headers and includes missing headers in message' do
     expect {
       # :age does not exist in the CSV header
       options = {:key_mapping => {:email => :a, :firstname => :b, :lastname => :c, :manager_email => :d, :age => :e} }
       SmarterCSV.process("#{fixture_path}/user_import.csv", options)
-    }.to raise_exception(SmarterCSV::KeyMappingError)
+    }.to raise_exception(SmarterCSV::KeyMappingError, "missing header(s): age")
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: smarter_csv
 version: !ruby/object:Gem::Version
-  version: 1.5.1
+  version: 1.5.2
 platform: ruby
 authors:
 - Tilo Sloboda
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-04-27 00:00:00.000000000 Z
+date: 2022-04-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec