csvreader 1.2.2 → 1.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a8e2f4f6e06ec63483735c1e0966b61398df85eb
-  data.tar.gz: 6c867acfa43c261473b6d6300e3ecd8d7042f0dc
+  metadata.gz: e54c57c44e895f8daacd12261b87195ab0ab6cd2
+  data.tar.gz: b63d0d183d98c3ab1f291e3bdf6168e0d5bd39fc
 SHA512:
-  metadata.gz: 2ddc944ee42de5660c68e057d0cbdbdf81b0f135b603e87231da2258bbd9001fc2483881e1c0ff15d5d7b23d2cb9f1b2c799a77a3551dbaee18094ba9aad5086
-  data.tar.gz: 39743a7df8b49b45a9ad1dd7ce8598616733348ecdbc52b94de4e8fc1fb7a54e33d0cbc36f3750a5940c9d46310d94a4c6d983811fb506efa2349bb0adc94d16
+  metadata.gz: 06756ee95e4810ded31be95abb5136bf0d0c8d7b79e2e19df483590bac051b449daee4f6178571bf177635ec35847220d859a6b5ba72068325710f022dbb6115
+  data.tar.gz: 884f5eff36a5d4cf03e1d7d5bab3a53632361ad6a7ab09ce16a502c0d25f25dcfea025efa8d79e8127fd735627683c3d8a91f22e3c03cf3d033ff7e64d7004b0

data/Manifest.txt

@@ -3,6 +3,16 @@ LICENSE.md
 Manifest.txt
 README.md
 Rakefile
+datasets/beer.csv
+datasets/beer11.csv
+datasets/cars11.csv
+datasets/cities11.csv
+datasets/customers11.csv
+datasets/iris.attrib.csv
+datasets/iris11.csv
+datasets/lcc.attrib.csv
+datasets/shakespeare.csv
+datasets/test.csv
 lib/csvreader.rb
 lib/csvreader/base.rb
 lib/csvreader/buffer.rb
@@ -15,19 +25,10 @@ lib/csvreader/parser_std.rb
 lib/csvreader/parser_strict.rb
 lib/csvreader/parser_tab.rb
 lib/csvreader/parser_table.rb
+lib/csvreader/parser_yaml.rb
 lib/csvreader/reader.rb
 lib/csvreader/reader_hash.rb
 lib/csvreader/version.rb
-test/data/beer.csv
-test/data/beer11.csv
-test/data/cars11.csv
-test/data/cities11.csv
-test/data/customers11.csv
-test/data/iris.attrib.csv
-test/data/iris11.csv
-test/data/lcc.attrib.csv
-test/data/shakespeare.csv
-test/data/test.csv
 test/helper.rb
 test/test_buffer.rb
 test/test_converter.rb

data/Rakefile

@@ -17,6 +17,12 @@ Hoe.spec 'csvreader' do
   self.readme_file  = 'README.md'
   self.history_file = 'HISTORY.md'
 
+  self.extra_deps = [
+     ['tabreader',  '>=1.0.1'],
+     ['csvyaml',    '>=0.1.0'],
+     ['csvjson',    '>=1.0.0']
+   ]
+
   self.licenses = ['Public Domain']
 
   self.spec_extras = {

data/lib/csvreader/base.rb

@@ -9,6 +9,10 @@ require 'date'    ## use for Date.parse and DateTime.parse
 require 'yaml'    ## used for (optional) meta data blocks
 
 
+require 'tabreader'
+require 'csvjson'
+require 'csvyaml'
+
 
 ###
 # our own code
@@ -19,6 +23,7 @@ require 'csvreader/parser_strict'   # flexible (strict - no leading/trailing spa
 require 'csvreader/parser_tab'
 require 'csvreader/parser_fixed'
 require 'csvreader/parser_json'
+require 'csvreader/parser_yaml'
 require 'csvreader/parser_table'
 require 'csvreader/parser'
 require 'csvreader/converter'
@@ -68,6 +73,8 @@ class Parser
   TABLE   = ParserTable.new    ## space-separated e.g /[ \t]+/
   FIXED   = ParserFixed.new
 
+  JSON    = ParserJson.new
+  YAML    = ParserYaml.new
 
   def self.default()         DEFAULT;         end ## alternative alias for DEFAULT
   def self.numeric()         NUMERIC;         end
@@ -85,11 +92,17 @@ class Parser
   def self.postgres()        postgresql;      end
   def self.postgresql_text() POSTGRESQL_TEXT; end
   def self.postgres_text()   postgresql_text; end
+
   def self.tab()             TAB;             end
   def self.table()           TABLE;           end
   def self.fixed()           FIXED;           end
   def self.fix()             fixed;           end
   def self.f()               fixed;           end
+
+  def self.json()            JSON;            end
+  def self.j()               json;            end
+  def self.yaml()            YAML;            end
+  def self.y()               yaml;            end
 end # class Parser
 end # class CsvReader
 
@@ -114,6 +127,8 @@ class CsvReader
   TABLE = Builder.new( Parser::TABLE )
   FIXED = Builder.new( Parser::FIXED )
 
+  JSON  = Builder.new( Parser::JSON )
+  YAML  = Builder.new( Parser::YAML )
 
   def self.default()         DEFAULT;         end ## alternative alias for DEFAULT
   def self.numeric()         NUMERIC;         end
@@ -131,11 +146,17 @@ class CsvReader
   def self.postgres()        postgresql;      end
   def self.postgresql_text() POSTGRESQL_TEXT; end
   def self.postgres_text()   postgresql_text; end
+
   def self.tab()             TAB;             end
   def self.table()           TABLE;           end
   def self.fixed()           FIXED;           end
   def self.fix()             fixed;           end
   def self.f()               fixed;           end
+
+  def self.json()            JSON;            end
+  def self.j()               json;            end
+  def self.yaml()            YAML;            end
+  def self.y()               yaml;            end
 end # class CsvReader
 
 
@@ -158,6 +179,9 @@ class CsvHashReader
   TABLE = Builder.new( Parser::TABLE )
   FIXED = Builder.new( Parser::FIXED )
 
+  JSON  = Builder.new( Parser::JSON )
+  YAML  = Builder.new( Parser::YAML )
+
 
   def self.default()         DEFAULT;         end ## alternative alias for DEFAULT
   def self.numeric()         NUMERIC;         end
@@ -171,11 +195,17 @@ class CsvHashReader
   def self.postgres()        postgresql;      end
   def self.postgresql_text() POSTGRESQL_TEXT; end
   def self.postgres_text()   postgresql_text; end
+
   def self.tab()             TAB;             end
   def self.table()           TABLE;           end
   def self.fixed()           FIXED;           end
   def self.fix()             fixed;           end
   def self.f()               fixed;           end
+
+  def self.json()            JSON;            end
+  def self.j()               json;            end
+  def self.yaml()            YAML;            end
+  def self.y()               yaml;            end
 end # class CsvHashReader
 
 

data/lib/csvreader/parser_json.rb

@@ -1,5 +1,24 @@
 # encoding: utf-8
 
 
-#######
-## todo: add parser for new CSV <3 JSON format
+class CsvReader
+
+class ParserJson
+
+def parse( data, **kwargs, &block )
+  ## note: kwargs NOT used for now (but required for "protocol/interface" by other parsers)
+
+  ## note: input: required each_line (string or io/file for example)
+  ## assume data is a string or io/file handle
+  csv = CsvJson.new( data )
+
+  if block_given?
+    csv.each( &block )
+  else
+    csv.to_a
+  end
+end ## method parse
+
+
+end # class ParserJson
+end # class CsvReader

data/lib/csvreader/parser_std.rb

@@ -378,8 +378,8 @@ def parse_meta( input )
   skip_newline( input )
 
   buf = "---\n"    ## note: start buffer with yaml header line - why?
-  ##   YAML.load("")        return false !!!
-  ##   YAML.load("---\n")   returns nil -- yes!!  if we get nil return empty hash {}
+  ##   ::YAML.load("")        return false !!!
+  ##   ::YAML.load("---\n")   returns nil -- yes!!  if we get nil return empty hash {}
 
   newline = true
 
@@ -406,7 +406,7 @@ def parse_meta( input )
     end
   end
 
-  data = YAML.load( buf )
+  data = ::YAML.load( buf )  ## note: MUST use "outer" scope (CsvReader defines its own YAML parser)
   ## todo: check edge cases - always should return a hash or nil
   ##     what to do with just integer, string or array etc. ???
 

data/lib/csvreader/parser_tab.rb

@@ -5,58 +5,19 @@ class CsvReader
 class ParserTab
 
 def parse( data, **kwargs, &block )
-
-  ## note: input: required each_line (string or io/file for example)
   ## note: kwargs NOT used for now (but required for "protocol/interface" by other parsers)
 
-  input = data   ## assume it's a string or io/file handle
+  ## note: input: required each_line (string or io/file for example)
+  ## assume data is a string or io/file handle
+  tab = TabReader.new( data )
 
   if block_given?
-    parse_lines( input, &block )
+    tab.each( &block )
   else
-    records = []
-
-    parse_lines( input ) do |record|
-      records << record
-    end
-
-    records
+    tab.to_a
   end
 end ## method parse
 
 
-
-private
-
-def parse_lines( input, &block )
-
-  ## note: each line only works with \n (windows) or \r\n (unix)
-  ##   will NOT work with \r (old mac, any others?) only!!!!
-  input.each_line do |line|
-
-    ## puts "line:"
-    ## pp line
-
-    ##  note: chomp('') if is an empty string,
-    ##    it will remove all trailing newlines from the string.
-    ##    use line.sub(/[\n\r]*$/, '') or similar instead - why? why not?
-    line = line.chomp( '' )
-    ## pp line
-
-    # note: trailing empty fields get (auto-)trimmed by split !!!!!!!
-    #  Solution!!  change split( "\t" ) to split( "\t", -1 ) 
-    #    If the limit parameter is omitted, trailing null fields are suppressed. 
-    #     If limit is a positive number, at most that number of fields will be returned 
-    #     (if limit is 1, the entire string is returned as the only entry in an array). 
-    #     If negative, there is no limit to the number of fields returned, and trailing null fields are not suppressed.    
-    values = line.split( "\t", -1 )
-    ## pp values
-
-    ## note: requires block - enforce? how? why? why not?
-    block.call( values )
-  end
-end # method parse_lines
-
-
 end # class ParserTab
 end # class CsvReader

data/lib/csvreader/parser_yaml.rb

@@ -0,0 +1,24 @@
+# encoding: utf-8
+
+
+class CsvReader
+
+class ParserYaml
+
+def parse( data, **kwargs, &block )
+  ## note: kwargs NOT used for now (but required for "protocol/interface" by other parsers)
+
+  ## note: input: required each_line (string or io/file for example)
+  ## assume data is a string or io/file handle
+  csv = CsvYaml.new( data )
+
+  if block_given?
+    csv.each( &block )
+  else
+    csv.to_a
+  end
+end ## method parse
+
+
+end # class ParserYaml
+end # class CsvReader

data/lib/csvreader/reader_hash.rb

@@ -6,6 +6,8 @@ class CsvHashReader
 ## add convenience shortcuts / aliases for CsvReader support classes
 Parser      = CsvReader::Parser
 ParserFixed = CsvReader::ParserFixed
+ParserJson  = CsvReader::ParserJson
+ParserYaml  = CsvReader::ParserYaml
 Converter   = CsvReader::Converter
 
 

data/lib/csvreader/version.rb

@@ -6,7 +6,7 @@ class CsvReader   ## note: uses a class for now - change to module - why? why no
   module Version
     MAJOR = 1    ## todo: namespace inside version or something - why? why not??
     MINOR = 2
-    PATCH = 2
+    PATCH = 3
 
     ## self.to_s  - why? why not?
   end

data/test/helper.rb

@@ -13,7 +13,7 @@ require 'csvreader'
 ## add test_data_dir helper
 class CsvReader
   def self.test_data_dir
-    "#{root}/test/data"
+    "#{root}/datasets"
   end
 end
 

metadata

@@ -1,15 +1,57 @@
 --- !ruby/object:Gem::Specification
 name: csvreader
 version: !ruby/object:Gem::Version
-  version: 1.2.2
+  version: 1.2.3
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-11-19 00:00:00.000000000 Z
+date: 2018-11-24 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: tabreader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.1
+- !ruby/object:Gem::Dependency
+  name: csvyaml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.0
+- !ruby/object:Gem::Dependency
+  name: csvjson
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -54,6 +96,16 @@ files:
 - Manifest.txt
 - README.md
 - Rakefile
+- datasets/beer.csv
+- datasets/beer11.csv
+- datasets/cars11.csv
+- datasets/cities11.csv
+- datasets/customers11.csv
+- datasets/iris.attrib.csv
+- datasets/iris11.csv
+- datasets/lcc.attrib.csv
+- datasets/shakespeare.csv
+- datasets/test.csv
 - lib/csvreader.rb
 - lib/csvreader/base.rb
 - lib/csvreader/buffer.rb
@@ -66,19 +118,10 @@ files:
 - lib/csvreader/parser_strict.rb
 - lib/csvreader/parser_tab.rb
 - lib/csvreader/parser_table.rb
+- lib/csvreader/parser_yaml.rb
 - lib/csvreader/reader.rb
 - lib/csvreader/reader_hash.rb
 - lib/csvreader/version.rb
-- test/data/beer.csv
-- test/data/beer11.csv
-- test/data/cars11.csv
-- test/data/cities11.csv
-- test/data/customers11.csv
-- test/data/iris.attrib.csv
-- test/data/iris11.csv
-- test/data/lcc.attrib.csv
-- test/data/shakespeare.csv
-- test/data/test.csv
 - test/helper.rb
 - test/test_buffer.rb
 - test/test_converter.rb