smarter_csv 1.7.1 → 1.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab42c787dba96369ba0f499294d5421cc2fc9a514b1cff039e5017d19fd2ff4c
-  data.tar.gz: f3605e56395d498169c449657945c00c677a75d17e2a7cbcca1a4f4e65aa45f2
+  metadata.gz: 34a12dae406ef192b3fbac9dd8a4236e18a7a936d4289cc296e49bf3b88fd386
+  data.tar.gz: f317413b7467386b1337938b2288763d1a6da279c6823ad3f4653ff82ea90d39
 SHA512:
-  metadata.gz: a264574b464219fd53a862be345c008fc0a93c076345d62be4c75935a148f9a469ccbea14fb2f821cedaada1f2b4ec875468ef50b3ae173bcbb76a5079d43406
-  data.tar.gz: 978236fa33bf4656eba89d929545c81ec2dc28b179890dd4254fb04cfa9b8646f4040aa2a62d44361dea221714f1cba0d7e4c858d338d30080c4a0e43c003552
+  metadata.gz: ebbd40e8c6ea684200c8efedc12174da1a0a99ab9fae8bcb00f3bfdb8dcac479285644de09003b04b073b46f8ea64cbb29686628e9b7986d3baa07b041ee7dbd
+  data.tar.gz: 9c9ba18bd64474811bbb3be2b350ab3b25a33dbd3e2cc802d697d04dcefeff2cc24150e87be6f6789eedc045a717ced2590efe6e6b6056a5c0b18095edbd0b38

data/CHANGELOG.md

@@ -1,9 +1,13 @@
 
 # SmarterCSV 1.x Change Log
 
+## 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)
+  
 ## 1.7.1 (2022-07-31)
-  * bugfix (thanks to Viacheslav Markin, Nicolas Rodriguez)
-## 1.7.0 (2022-06-26)
+  * bugfix for issue #195 #197 #200 which only appeared when called from Rails (thanks to Viacheslav Markin, Nicolas Rodriguez)
+
+## 1.7.0 (2022-06-26) (replaced by 1.7.1)
   * added native code to accellerate line parsing by >10x over 1.6.0
   * added option `acceleration`, defaulting to `true`, to enable native code.
     Disable this option to use the ruby code for line parsing.

data/README.md

@@ -1,9 +1,12 @@
- [![codecov](https://codecov.io/gh/tilo/smarter_csv/branch/main/graph/badge.svg?token=1L7OD80182)](https://codecov.io/gh/tilo/smarter_csv)
+
+# SmarterCSV
+
+ [![codecov](https://codecov.io/gh/tilo/smarter_csv/branch/main/graph/badge.svg?token=1L7OD80182)](https://codecov.io/gh/tilo/smarter_csv) [![Gem Version](https://badge.fury.io/rb/smarter_csv.svg)](http://badge.fury.io/rb/smarter_csv)
  
-#### Service Announcement
+#### Work towards Future Version 2.0
 
-* Work towards SmarterCSV 2.0 is still on it's way, with much improved features, and more streamlined options.
-  Please check the [2.0-develop branch](https://github.com/tilo/smarter_csv/blob/master/README.md), open any issues and pull requests with mention of v2.0.
+* Work towards SmarterCSV 2.0 is still ongoing, with improved features, and more streamlined options, but consider it as experimental at this time.
+  Please check the [2.0-develop branch](https://github.com/tilo/smarter_csv/tree/2.0-develop), open any issues and pull requests with mention of tag v2.0.
 
 * New versions of SmarterCSV 1.x will soon print a deprecation warning if you set :verbose to true
   See below for list of deprecated options.
@@ -15,11 +18,7 @@
 
 ---------------
 
-# SmarterCSV
-
-[![Build Status](https://secure.travis-ci.org/tilo/smarter_csv.svg?branch=master)](http://travis-ci.com/tilo/smarter_csv) [![Gem Version](https://badge.fury.io/rb/smarter_csv.svg)](http://badge.fury.io/rb/smarter_csv)
-
-#### SmarterCSV 1.x
+#### SmarterCSV 1.x [Current Version]
 
 `smarter_csv` is a Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, suitable for direct processing with ActiveRecord, parallel processing, or kicking-off batch jobs with Sidekiq.
 
@@ -132,7 +131,21 @@ and how the `process` method returns the number of chunks when called with a blo
 
      => returns number of chunks / rows we processed
 ```
-#### Example 4: Populate a MongoDB Database in Chunks of 100 records with SmarterCSV:
+
+#### Example 4: Reading a CSV-like File, and Processing it with Sidekiq:
+```ruby
+    filename = '/tmp/strange_db_dump'   # a file with CRTL-A as col_separator, and with CTRL-B\n as record_separator (hello iTunes!)
+    options = {
+      :col_sep => "\cA", :row_sep => "\cB\n", :comment_regexp => /^#/,
+      :chunk_size => 100 , :key_mapping => {:export_date => nil, :name => :genre}
+    }
+    n = SmarterCSV.process(filename, options) do |chunk|
+        SidekiqWorkerClass.process_async(chunk ) # pass an array of hashes to Sidekiq workers for parallel processing
+    end
+    => returns number of chunks
+```
+
+#### Example 5: Populate a MongoDB Database in Chunks of 100 records with SmarterCSV:
 ```ruby
     # using chunks:
     filename = '/tmp/some.csv'
@@ -146,18 +159,6 @@ and how the `process` method returns the number of chunks when called with a blo
      => returns number of chunks we processed
 ```
 
-#### Example 5: Reading a CSV-like File, and Processing it with Resque:
-```ruby
-    filename = '/tmp/strange_db_dump'   # a file with CRTL-A as col_separator, and with CTRL-B\n as record_separator (hello iTunes!)
-    options = {
-      :col_sep => "\cA", :row_sep => "\cB\n", :comment_regexp => /^#/,
-      :chunk_size => 100 , :key_mapping => {:export_date => nil, :name => :genre}
-    }
-    n = SmarterCSV.process(filename, options) do |chunk|
-        Resque.enque( ResqueWorkerClass, chunk ) # pass chunks of CSV-data to Resque workers for parallel processing
-    end
-    => returns number of chunks
-```
 #### Example 6: Using Value Converters
 
 NOTE: If you use `key_mappings` and `value_converters`, make sure that the value converters has references the keys based on the final mapped name, not the original name in the CSV file.
@@ -239,6 +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                                              |
      ---------------------------------------------------------------------------------------------------------------------------------
 
 #### Deprecated 1.x Options: to be replaced in 2.0

data/lib/smarter_csv/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SmarterCSV
-  VERSION = "1.7.1"
+  VERSION = "1.7.2"
 end

data/lib/smarter_csv.rb

@@ -2,7 +2,9 @@
 
 require_relative "extensions/hash"
 require_relative "smarter_csv/version"
+
 require_relative "smarter_csv/smarter_csv" unless ENV['CI'] # does not compile/link in CI?
+# require 'smarter_csv.bundle' unless ENV['CI'] # does not compile/link in CI?
 
 module SmarterCSV
   class SmarterCSVException < StandardError; end
@@ -129,6 +131,8 @@ module SmarterCSV
 
         next if options[:remove_empty_hashes] && hash.empty?
 
+        hash[:csv_line_number] = @csv_line_count if options[:with_line_numbers]
+
         if use_chunks
           chunk << hash # append temp result to chunk
 
@@ -230,6 +234,7 @@ module SmarterCSV
         user_provided_headers: nil,
         value_converters: nil,
         verbose: false,
+        with_line_numbers: false,
       }
     end
 
@@ -247,12 +252,12 @@ module SmarterCSV
       # puts "SmarterCSV.parse OPTIONS: #{options[:acceleration]}" if options[:verbose]
 
       if options[:acceleration] && has_acceleration?
-        # puts "NOTICE: Accelerated SmarterCSV / #{options[:acceleration]}" if options[:verbose]
+        # :nocov:
         has_quotes = line =~ /#{options[:quote_char]}/
         elements = parse_csv_line_c(line, options[:col_sep], options[:quote_char], header_size)
         elements.map!{|x| cleanup_quotes(x, options[:quote_char])} if has_quotes
         return [elements, elements.size]
-
+        # :nocov:
       else
         # puts "WARNING: SmarterCSV is using un-accelerated parsing of lines. Check options[:acceleration]"
         return parse_csv_line_ruby(line, options, header_size)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: smarter_csv
 version: !ruby/object:Gem::Version
-  version: 1.7.1
+  version: 1.7.2
 platform: ruby
 authors:
 - Tilo Sloboda
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-07-31 00:00:00.000000000 Z
+date: 2022-08-29 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: 3.1.6
+rubygems_version: 3.3.3
 signing_key:
 specification_version: 4
 summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots