smarter_csv 1.7.3 → 1.7.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d4046758f38c21262fdec6bc7e13e3a7811c7aee3944d92e0cc36a2a1cfb032a
-  data.tar.gz: 9d111e2f36171ca488034f3af73fc71c7c9f6fde73986d277aeaf1560a066fa2
+  metadata.gz: 3c20e6e8f4281f99aa22e67c778e1e950ef7040a48f454c7d9751f2ccf44c093
+  data.tar.gz: 14ec931e58fce24c675bd76ad39f6046c52a0a4b07cc89814fa55c6a981ebe27
 SHA512:
-  metadata.gz: c46c5c45dd3fafe66735b2b17b0679c5aaff27b3670140d97bc19e1c825ad91310fa2cf55a12a5c7b0c31ef82fe9cc12a2c4bda0a78b218d80ad5816c01c0d9f
-  data.tar.gz: ba03acd95955f8afeb8e96f16c7cfa2e1605dbaf6fddb7008930294aab83196aed21f57605efb3553799381c1c4811528eee2db221efa50dc82f58bcf9135842
+  metadata.gz: cf3d642f523bf49d0867bc1768a6df247f3392390090c2b0fbfda5ac75f5f8f829eaac2ec14105936e4d317c7a1d1b865d74de1e60ce6405c6fd1f868bd703eb
+  data.tar.gz: 70522e31ca2ced36beef2a38509d1df01bad12af5bb56cb1404cfcbceffdfb4cbbbf8a8a8a535e3ea060d2d4c5b4c1049c8486d163d7de6b466dd83838aa2cf0

data/CHANGELOG.md

@@ -1,6 +1,9 @@
 
 # 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`
 

data/CONTRIBUTORS.md

@@ -49,3 +49,4 @@ A Big Thank you to everyone who filed issues, sent comments, and who contributed
  * [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/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 = "1.7.3"
+  VERSION = "1.7.4"
 end

data/lib/smarter_csv.rb

@@ -374,24 +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
@@ -525,5 +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: 1.7.3
+  version: 1.7.4
 platform: ruby
 authors:
 - Tilo Sloboda
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-12-09 00:00:00.000000000 Z
+date: 2023-01-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: awesome_print