smarter_csv 1.0.4 → 1.0.5

checksums.yaml

@@ -0,0 +1,7 @@
+--- 
+SHA1: 
+  metadata.gz: ed29542688f14930b2c88be160a092ba0e7e0398
+  data.tar.gz: 6ce2d29c27af35540f83a44f7c1af1a1f3da988e
+SHA512: 
+  metadata.gz: a88bbcfc69a77beb3ef9fbcd68d48d17880e57264f4755426d0f44c64d06905ba496de9805f48cb2c83373da2ba0bb893dd71a55556fed61016b6696a4a35d95
+  data.tar.gz: 73de0af3b952a8dc4a32f1c823162f718aeedd5304f553b4690100a245c81d68edda0280e3646e965e5c3d260176a884ea64f6a43adb3c62ae26e4bcef2bbfc7

data/README.md

@@ -126,30 +126,31 @@ The options and the block are optional.
 
 `SmarterCSV.process` supports the following options:
 
-      Option                     | Default  |  Explanation
-    --------------------------------+-----------+--------------------------------------------------------------
-     :col_sep                    |   ','    | column separator
-     :row_sep                    | $/ ,"\n" | row separator or record separator , defaults to system's $/ , which defaults to "\n"
-     :quote_char                 |   '"'    | quotation character
-     :comment_regexp             |   /^#/   | regular expression which matches comment lines (see NOTE about the CSV header)
-     :chunk_size                 |   nil    | if set, determines the desired chunk-size (defaults to nil, no chunk processing)
-     :key_mapping                |   nil    | a hash which maps headers from the CSV file to keys in the result hash
-     :downcase_header            |   true   | downcase all column headers
-     :strings_as_keys            |   false  | use strings instead of symbols as the keys in the result hashes
-     :strip_whitespace           |   true   | remove whitespace before/after values and headers
-     :remove_empty_values        |   true   | remove values which have nil or empty strings as values
-     :remove_zero_values         |   true   | remove values which have a numeric value equal to zero / 0
-     :remove_values_matching     |   nil    | removes key/value pairs if value matches given regular expressions. e.g.:
-                                 |          | /^\$0\.0+$/ to match $0.00 , or /^#VALUE!$/ to match errors in Excel spreadsheets
-     :convert_values_to_numeric  |   true   | converts strings containing Integers or Floats to the appropriate class
-     :remove_empty_hashes        |   true   | remove / ignore any hashes which don't have any key/value pairs
-     :user_provided_headers      |   nil    | *careful with that axe!*
-                                 |          | user provided Array of header strings or symbols, to define
-                                 |          | what headers should be used, overriding any in-file headers.
-                                 |          | You can not combine the :user_provided_headers and :key_mapping options
-     :headers_in_file            |   true   | Whether or not the file contains headers as the first line. 
-                                 |          | Important if the file does not contain headers, 
-                                 |          | otherwise you would lose the first line of data.
+     | Option                      | Default  |  Explanation                                                                         |
+     ---------------------------------------------------------------------------------------------------------------------------------
+     | :col_sep                    |   ','    | column separator                                                                     |
+     | :row_sep                    | $/ ,"\n" | row separator or record separator , defaults to system's $/ , which defaults to "\n" |
+     | :quote_char                 |   '"'    | quotation character                                                                  |
+     | :comment_regexp             |   /^#/   | regular expression which matches comment lines (see NOTE about the CSV header)       |
+     | :chunk_size                 |   nil    | if set, determines the desired chunk-size (defaults to nil, no chunk processing)     |
+     | :key_mapping                |   nil    | a hash which maps headers from the CSV file to keys in the result hash               |
+     | :downcase_header            |   true   | downcase all column headers                                                          |
+     | :strings_as_keys            |   false  | use strings instead of symbols as the keys in the result hashes                      |
+     | :strip_whitespace           |   true   | remove whitespace before/after values and headers                                    |
+     | :remove_empty_values        |   true   | remove values which have nil or empty strings as values                              |
+     | :remove_zero_values         |   true   | remove values which have a numeric value equal to zero / 0                           |
+     | :remove_values_matching     |   nil    | removes key/value pairs if value matches given regular expressions. e.g.:            |
+     |                             |          | /^\$0\.0+$/ to match $0.00 , or /^#VALUE!$/ to match errors in Excel spreadsheets    |
+     | :convert_values_to_numeric  |   true   | converts strings containing Integers or Floats to the appropriate class              |
+     | :remove_empty_hashes        |   true   | remove / ignore any hashes which don't have any key/value pairs                      |
+     | :user_provided_headers      |   nil    | *careful with that axe!*                                                             |
+     |                             |          | user provided Array of header strings or symbols, to define                          |
+     |                             |          | what headers should be used, overriding any in-file headers.                         |
+     |                             |          | You can not combine the :user_provided_headers and :key_mapping options              |
+     | :strip_chars_from_headers   |   nil    | remove extraneous characters from the header line (e.g. if the headers are quoted)   |
+     | :headers_in_file            |   true   | Whether or not the file contains headers as the first line.                          |
+     |                             |          | Important if the file does not contain headers,                                      |
+     |                             |          | otherwise you would lose the first line of data.                                     |
 
 
 #### NOTES about CSV Headers:
@@ -193,9 +194,17 @@ Or install it yourself as:
     $ gem install smarter_csv
 
 
+## Known Bugs
+
+ * if :col_sep (e.g. a comma) appears inside a quoted field, smarter_csv <= 1.0.4 incorrectly splits on that :col_sep
+
 
 ## Changes
 
+#### 1.0.5 (2013-05-08)
+
+ * bugfix : for :headers_in_file option
+
 #### 1.0.4 (2012-08-17)
 
  * renamed the following options: 
@@ -238,6 +247,17 @@ Or install it yourself as:
 Please [open an Issue on GitHub](https://github.com/tilo/smarter_csv/issues) if you have feedback, new feature requests, or want to report a bug. Thank you!
 
 
+## Special Thanks
+
+Many thanks to people who have filed issues and sent comments. 
+And a special thanks to those who contributed pull requests:
+
+ * [Sean Duckett](http://github.com/sduckett)
+ * [Alex Ong](http://github.com/khaong) 
+ * [Martin Nilsson](http://github.com/MrTin) 
+ * [Eustáquio Rangel](http://github.com/taq) 
+ * [Pavel](http://github.com/paxa) 
+
 
 ## Contributing
 

data/lib/smarter_csv/smarter_csv.rb

@@ -31,7 +31,7 @@ module SmarterCSV
       if options[:user_provided_headers] && options[:user_provided_headers].class == Array && ! options[:user_provided_headers].empty?
         # use user-provided headers 
         headerA = options[:user_provided_headers]
-        if defined?(file_header_size)
+        if defined?(file_header_size) && ! file_header_size.nil?
           if headerA.size != file_header_size
             raise SmarterCSV::HeaderSizeMismatch , "ERROR [smarter_csv]: :user_provided_headers defines #{headerA.size} headers !=  CSV-file #{filename} has #{file_header_size} headers" 
           else
@@ -62,18 +62,23 @@ module SmarterCSV
       else
         use_chunks = false
       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  # read one line.. this uses the input_record_separator $/ which we set previously!
         next  if  line =~ options[:comment_regexp]  # ignore all comment lines if there are any
         line.chomp!    # will use $/ which is set to options[:col_sep]
-        
-        dataA = line.split(options[:col_sep])
+
+        dataA = line.split(options[:col_sep])   # ISSUE 4 : BUG : this splits incorrectly if , is inside quoted fields
         dataA.map!{|x| x.strip}  if options[:strip_whitespace]
         hash = Hash.zip(headerA,dataA)  # from Facets of Ruby library
         # make sure we delete any key/value pairs from the hash, which the user wanted to delete:
-        hash.delete(nil); hash.delete(''); hash.delete(:"") # delete any hash keys which were mapped to be deleted
+        # Note: Ruby < 1.9 doesn't allow empty symbol literals!
+        hash.delete(nil); hash.delete('');
+        if RUBY_VERSION.to_f > 1.8
+          eval('hash.delete(:"")')
+        end
+
         hash.delete_if{|k,v| v.nil? || v =~ /^\s*$/}  if options[:remove_empty_values]
         hash.delete_if{|k,v| ! v.nil? && v =~ /^(\d+|\d+\.\d+)$/ && v.to_f == 0} if options[:remove_zero_values]   # values are typically Strings!
         hash.delete_if{|k,v| v =~ options[:remove_values_matching]} if options[:remove_values_matching]

data/lib/smarter_csv/version.rb

@@ -1,3 +1,3 @@
 module SmarterCSV
-  VERSION = "1.0.4"
+  VERSION = "1.0.5"
 end

metadata

@@ -1,29 +1,31 @@
---- !ruby/object:Gem::Specification
+--- !ruby/object:Gem::Specification 
 name: smarter_csv
-version: !ruby/object:Gem::Version
-  version: 1.0.4
-  prerelease: 
+version: !ruby/object:Gem::Version 
+  version: 1.0.5
 platform: ruby
-authors:
-- ! 'Tilo Sloboda
+authors: 
+- |
+  Tilo Sloboda
 
-'
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-08-17 00:00:00.000000000 Z
+
+date: 2013-05-09 00:00:00 Z
 dependencies: []
-description: Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, with
-  optional features for processing large files in parallel, embedded comments, unusual
-  field- and record-separators, flexible mapping of CSV-headers to Hash-keys
-email:
-- ! 'tilo.sloboda@gmail.com
 
-'
+description: Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, with optional features for processing large files in parallel, embedded comments, unusual field- and record-separators, flexible mapping of CSV-headers to Hash-keys
+email: 
+- |
+  tilo.sloboda@gmail.com
+
 executables: []
+
 extensions: []
+
 extra_rdoc_files: []
-files:
+
+files: 
 - .gitignore
 - .rvmrc
 - Gemfile
@@ -35,29 +37,31 @@ files:
 - lib/smarter_csv/smarter_csv.rb
 - lib/smarter_csv/version.rb
 - smarter_csv.gemspec
-homepage: ''
+homepage: ""
 licenses: []
+
+metadata: {}
+
 post_install_message: 
 rdoc_options: []
-require_paths:
+
+require_paths: 
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
-required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - &id001 
+    - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - *id001
 requirements: []
+
 rubyforge_project: 
-rubygems_version: 1.8.15
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
-summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots
-  of optional features, e.g. chunked processing for huge CSV files
+specification_version: 4
+summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots of optional features, e.g. chunked processing for huge CSV files
 test_files: []
+