smarter_csv 1.7.2 → 1.7.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 34a12dae406ef192b3fbac9dd8a4236e18a7a936d4289cc296e49bf3b88fd386
-  data.tar.gz: f317413b7467386b1337938b2288763d1a6da279c6823ad3f4653ff82ea90d39
+  metadata.gz: 3c20e6e8f4281f99aa22e67c778e1e950ef7040a48f454c7d9751f2ccf44c093
+  data.tar.gz: 14ec931e58fce24c675bd76ad39f6046c52a0a4b07cc89814fa55c6a981ebe27
 SHA512:
-  metadata.gz: ebbd40e8c6ea684200c8efedc12174da1a0a99ab9fae8bcb00f3bfdb8dcac479285644de09003b04b073b46f8ea64cbb29686628e9b7986d3baa07b041ee7dbd
-  data.tar.gz: 9c9ba18bd64474811bbb3be2b350ab3b25a33dbd3e2cc802d697d04dcefeff2cc24150e87be6f6789eedc045a717ced2590efe6e6b6056a5c0b18095edbd0b38
+  metadata.gz: cf3d642f523bf49d0867bc1768a6df247f3392390090c2b0fbfda5ac75f5f8f829eaac2ec14105936e4d317c7a1d1b865d74de1e60ce6405c6fd1f868bd703eb
+  data.tar.gz: 70522e31ca2ced36beef2a38509d1df01bad12af5bb56cb1404cfcbceffdfb4cbbbf8a8a8a535e3ea060d2d4c5b4c1049c8486d163d7de6b466dd83838aa2cf0

data/CHANGELOG.md

@@ -1,6 +1,12 @@
 
 # SmarterCSV 1.x Change Log
 
+## 1.7.4 (2022-01-13)
+  * improved guessing of the column separator, thanks to Alessandro Fazzi
+
+## 1.7.3 (2022-12-05)
+  * new option :silence_missing_keys; if set to true, it ignores missing keys in `key_mapping`
+
 ## 1.7.2 (2022-08-29)
   * new option :with_line_numbers; if set to true, it adds :csv_line_number to each data hash (issue #130)
   

data/CONTRIBUTORS.md

@@ -48,3 +48,5 @@ A Big Thank you to everyone who filed issues, sent comments, and who contributed
  * [Viacheslav Markin](https://github.com/KXEinc)
  * [Nicolas Rodriguez](https://github.com/n-rodriguez)
  * [Hirotaka Mizutani ](https://github.com/hirotaka)
+ * [Rahul Chaudhary](https://github.com/rahulch95)
+ * [Alessandro Fazzi](https://github.com/pioneerskies)

data/README.md

@@ -240,7 +240,7 @@ The options and the block are optional.
      |                             |          | You can not combine the :user_provided_headers and :key_mapping options              |
      | :remove_empty_hashes        |   true   | remove / ignore any hashes which don't have any key/value pairs or all empty values  |
      | :verbose                    |   false  | print out line number while processing (to track down problems in input files)       |
-     | :with_line_numbers          |   false  | add :csv_line_number to heach data hash                                              |
+     | :with_line_numbers          |   false  | add :csv_line_number to each data hash                                               |
      ---------------------------------------------------------------------------------------------------------------------------------
 
 #### Deprecated 1.x Options: to be replaced in 2.0
@@ -253,7 +253,8 @@ And header and data validations will also be supported in 2.x
      | Option                      | Default  |  Explanation                                                                         |
      ---------------------------------------------------------------------------------------------------------------------------------
      | :key_mapping                |   nil    | a hash which maps headers from the CSV file to keys in the result hash               |
-     | :required_headers           |   nil    | An array. Eacn of the given headers must be present after header manipulation,       |
+     | :silence_missing_key        |   false  | ignore missing keys in `key_mapping` if true                                         |
+     | :required_headers           |   nil    | An array. Each of the given headers must be present after header manipulation,       |
      |                             |          | or an exception is raised   No validation if nil is given.                           |
      | :remove_unmapped_keys       |   false  | when using :key_mapping option, should non-mapped keys / columns be removed?         |
      | :downcase_header            |   true   | downcase all column headers                                                          |

data/Rakefile

@@ -3,6 +3,17 @@
 require "bundler/gem_tasks"
 require 'rspec/core/rake_task'
 
+
+# temp fix for NoMethodError: undefined method `last_comment'
+# remove when fixed in Rake 11.x and higher
+module TempFixForRakeLastComment
+  def last_comment
+    last_description
+  end
+end
+Rake::Application.send :include, TempFixForRakeLastComment
+### end of tempfix
+
 RSpec::Core::RakeTask.new(:spec)
 
 require "rubocop/rake_task"

data/lib/smarter_csv/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SmarterCSV
-  VERSION = "1.7.2"
+  VERSION = "1.7.4"
 end

data/lib/smarter_csv.rb

@@ -227,6 +227,7 @@ module SmarterCSV
         remove_zero_values: false,
         required_headers: nil,
         row_sep: $/,
+        silence_missing_keys: false,
         skip_lines: nil,
         strings_as_keys: false,
         strip_chars_from_headers: nil,
@@ -373,24 +374,21 @@ module SmarterCSV
       return false
     end
 
-    # raise exception if none is found
+    # If file has headers, then guesses column separator from headers.
+    # Otherwise guesses column separator from contents.
+    # Raises exception if none is found.
     def guess_column_separator(filehandle, options)
-      del = [',', "\t", ';', ':', '|']
-      n = Hash.new(0)
+      possible_delimiters = [',', "\t", ';', ':', '|']
 
-      5.times do
-        line = filehandle.readline(options[:row_sep])
-        del.each do |d|
-          n[d] += line.scan(d).count
-        end
-      rescue EOFError # short files
-        break
-      end
+      candidates = if options.fetch(:headers_in_file)
+                     candidated_column_separators_from_headers(filehandle, options, possible_delimiters)
+                   else
+                     candidated_column_separators_from_contents(filehandle, options, possible_delimiters)
+                   end
 
-      filehandle.rewind
-      raise SmarterCSV::NoColSepDetected if n.values.max == 0
+      raise SmarterCSV::NoColSepDetected if candidates.values.max == 0
 
-      col_sep = n.key(n.values.max)
+      candidates.key(candidates.values.max)
     end
 
     # limitation: this currently reads the whole file in before making a decision
@@ -479,9 +477,11 @@ module SmarterCSV
         # do some key mapping on the keys in the file header
         #   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
-          missing_keys = key_mappingH.keys - headerA
-          puts "WARNING: missing header(s): #{missing_keys.join(",")}" unless missing_keys.empty?
+          unless options[:silence_missing_keys]
+            # if silence_missing_keys are not set, raise error if missing header
+            missing_keys = key_mappingH.keys - headerA
+            puts "WARNING: missing header(s): #{missing_keys.join(",")}" unless missing_keys.empty?
+          end
 
           headerA.map!{|x| key_mappingH.has_key?(x) ? (key_mappingH[x].nil? ? nil : key_mappingH[x]) : (options[:remove_unmapped_keys] ? nil : x)}
         end
@@ -522,5 +522,37 @@ module SmarterCSV
       end
       result
     end
+
+    private
+
+    def candidated_column_separators_from_headers(filehandle, options, delimiters)
+      candidates = Hash.new(0)
+      line = filehandle.readline(options[:row_sep])
+
+      delimiters.each do |d|
+        candidates[d] += line.scan(d).count
+      end
+
+      filehandle.rewind
+
+      candidates
+    end
+
+    def candidated_column_separators_from_contents(filehandle, options, delimiters)
+      candidates = Hash.new(0)
+
+      5.times do
+        line = filehandle.readline(options[:row_sep])
+        delimiters.each do |d|
+          candidates[d] += line.scan(d).count
+        end
+      rescue EOFError # short files
+        break
+      end
+
+      filehandle.rewind
+
+      candidates
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: smarter_csv
 version: !ruby/object:Gem::Version
-  version: 1.7.2
+  version: 1.7.4
 platform: ruby
 authors:
 - Tilo Sloboda
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-08-29 00:00:00.000000000 Z
+date: 2023-01-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: awesome_print
@@ -140,7 +140,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.3
+rubygems_version: 3.1.6
 signing_key:
 specification_version: 4
 summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots