csvrecord 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f60b9d15d91c6d20b625bb343d895ad750f43a81
-  data.tar.gz: 5510e7921a509fe40906de7f533f185bf244e8bd
+  metadata.gz: 77369b93b97cff13a7159870a4343cb22ad86dec
+  data.tar.gz: cbc687395deb700c55ed7ca79687da11a7fb8913
 SHA512:
-  metadata.gz: 9853722319a53c73469238440eb2c249cd8c3829711acbd35efc60996316f8d8e763d5f61decdc4e3186baebf13536c46c72217fd92f08e6d675b7a6c088568b
-  data.tar.gz: bd2922bf8c44a458abe70b5dceee9b405904f878eacdaf34a1454a2313c43517329d31841c2bc4faca5c6d3492220d9c5c3091115171046c087a2889a4415339
+  metadata.gz: f8d27de0a2c8e8ee2ddfcc024802845a6bce1f05dbc94aa1911fec1cc287837a5b5739e46e93cd5d6db6af678c6ad80e326ea09850c95bb342a27c5063d61fdc
+  data.tar.gz: 548b5db8a78788d5c5e624ed44420b961bf0668f9289c876825fb7f09314bc0281f42ca2eb7d6dba11ece65c58de985e6630889230652524f31481e2603cecf2

data/Manifest.txt

@@ -6,12 +6,10 @@ Rakefile
 lib/csvrecord.rb
 lib/csvrecord/base.rb
 lib/csvrecord/builder.rb
-lib/csvrecord/reader.rb
 lib/csvrecord/version.rb
 test/data/beer.csv
 test/data/beer11.csv
 test/helper.rb
-test/test_reader.rb
 test/test_record.rb
 test/test_record_auto.rb
 test/test_version.rb

data/Rakefile

@@ -14,9 +14,13 @@ Hoe.spec 'csvrecord' do
   self.email = 'wwwmake@googlegroups.com'
 
   # switch extension to .markdown for gihub formatting
-  self.readme_file = 'README.md'
+  self.readme_file  = 'README.md'
   self.history_file = 'HISTORY.md'
 
+  self.extra_deps = [
+     ['csvreader']
+   ]
+
   self.licenses = ['Public Domain']
 
   self.spec_extras = {

data/lib/csvrecord.rb

@@ -1,8 +1,8 @@
 # encoding: utf-8
 
-require 'csv'
-require 'json'
-require 'pp'
+###
+# 3rd party gems
+require 'csvreader'
 
 
 ###
@@ -10,8 +10,6 @@ require 'pp'
 require 'csvrecord/version' # let version always go first
 require 'csvrecord/base'
 require 'csvrecord/builder'
-require 'csvrecord/reader'
-
 
 
 puts CsvRecord.banner   # say hello

data/lib/csvrecord/version.rb

@@ -4,7 +4,7 @@
 module CsvRecord
 
   MAJOR = 0    ## todo: namespace inside version or something - why? why not??
-  MINOR = 3
+  MINOR = 4
   PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 

metadata

@@ -1,15 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: csvrecord
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-08-14 00:00:00.000000000 Z
+date: 2018-08-15 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: csvreader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -57,12 +71,10 @@ files:
 - lib/csvrecord.rb
 - lib/csvrecord/base.rb
 - lib/csvrecord/builder.rb
-- lib/csvrecord/reader.rb
 - lib/csvrecord/version.rb
 - test/data/beer.csv
 - test/data/beer11.csv
 - test/helper.rb
-- test/test_reader.rb
 - test/test_record.rb
 - test/test_record_auto.rb
 - test/test_version.rb

data/lib/csvrecord/reader.rb

@@ -1,188 +0,0 @@
-# encoding: utf-8
-
-
-module Csv    ## check: rename to CsvSettings / CsvPref / CsvGlobals or similar - why? why not???
-
-  ## STD_CSV_ENGINE = CSV   ## to avoid name confusion use longer name - why? why not? find a better name?
-  ## use __CSV__ or similar? or just ::CSV ??
-
-  class Configuration
-
-    puts "CSV::VERSION:"
-    puts CSV::VERSION
-
-    puts "builtin CSV::Converters:"
-    pp CSV::Converters
-
-    puts "CSV::DEFAULT_OPTIONS:"
-    pp CSV::DEFAULT_OPTIONS
-
-    ##  register our own converters
-    ## check if strip gets called for nil values too?
-    CSV::Converters[:strip] = ->(field) { field.strip }
-
-
-    attr_accessor :sep   ## col_sep (column separator)
-
-    def initialize
-      @sep = ','
-      ## note: do NOT add headers as global - should ALWAYS be explicit
-      ##   headers (true/false) - changes resultset and requires different processing!!!
-
-      self  ## return self for chaining
-    end
-
-    def blank?( line )
-      ## note:  blank line does NOT include "blank" with spaces only!!
-      ##          use BLANK_REGEX in skip_lines to clean-up/skip/remove/ignore
-      ##  see skip_blanks in default_options
-      line.empty?
-    end
-
-    ## lines starting with # (note: only leading spaces allowed)
-    COMMENTS_REGEX = /^\s*#/
-    BLANK_REGEX    = /^\s*$/   ## skip all whitespace lines - note: use "" or , for a blank record!!!
-    SKIP_REGEX = Regexp.union( COMMENTS_REGEX, BLANK_REGEX )
-
-    def skip?( line )
-      ## check if comment line - skip comments
-      ##  see skip_lines in default_options
-      line =~ SKIP_REGEX
-    end
-
-    ## built-in (default) options
-    ##  todo: find a better name?
-    def default_options
-      ## note:
-      ##   do NOT include sep character and
-      ##   do NOT include headers true/false here
-      ##
-      ##  make default sep its own "global" default config
-      ##   e.g. Csv.config.sep =
-
-      ## common options
-      ##   skip comments starting with #
-      ##   skip blank lines
-      ##   strip leading and trailing spaces
-      ##    NOTE/WARN:  leading and trailing spaces NOT allowed/working with double quoted values!!!!
-      defaults = {
-        skip_blanks: true,    ## note: skips lines with no whitespaces only!! (e.g. line with space is NOT blank!!)
-        skip_lines:  SKIP_REGEX,
-        :converters => :strip
-      }
-      defaults
-    end
-  end # class Configuration
-
-
-  ## lets you use
-  ##   Csv.configure do |config|
-  ##      config.sep = ','   ## or "/t"
-  ##   end
-
-  def self.configure
-    yield( config )
-  end
-
-  def self.config
-    @config ||= Configuration.new
-  end
-end   # module Csvv
-
-
-
-####
-## use our own wrapper
-
-class CsvReader
-
-  ####################
-  # helper methods
-  def self.unwrap( row_or_array )   ## unwrap row - find a better name? why? why not?
-    ## return row values as array of strings
-    if row_or_array.is_a?( CSV::Row )
-      row = row_or_array
-      row.fields   ## gets array of string of field values
-    else  ## assume "classic" array of strings
-      array = row_or_array
-    end
-  end
-
-
-
-  def self.foreach( path, sep: Csv.config.sep, headers: true )
-    csv_options = Csv.config.default_options.merge(
-                     headers: headers,
-                     col_sep: sep,
-                     external_encoding: 'utf-8'  ## note:  always (auto-)add utf-8 external encoding for now!!!
-    )
-
-    CSV.foreach( path, csv_options ) do |row|
-      yield( row )    ## check/todo: use block.call( row ) ## why? why not?
-    end
-  end
-
-
-  def self.read( path, sep: Csv.config.sep, headers: true )
-    ## note: use our own file.open
-    ##   always use utf-8 for now
-    ##    check/todo: add skip option bom too - why? why not?
-    txt = File.open( path, 'r:utf-8' )
-    parse( txt, sep: sep, headers: headers )
-  end
-
-  def self.parse( txt, sep: Csv.config.sep, headers: true )
-    csv_options = Csv.config.default_options.merge(
-                     headers: headers,
-                     col_sep: sep
-    )
-    ## pp csv_options
-    CSV.parse( txt, csv_options )
-  end
-
-  def self.parse_line( txt, sep: Csv.config.sep )
-    ## note: do NOT include headers option (otherwise single row gets skipped as first header row :-)
-    csv_options = Csv.config.default_options.merge(
-                    headers: false,  ## note: always turn off headers!!!!!!
-                    col_sep: sep
-    )
-    ## pp csv_options
-    CSV.parse_line( txt, csv_options )
-  end
-
-
-
-  def self.header( path, sep: Csv.config.sep )   ## use header or headers - or use both (with alias)?
-      # read first lines (only)
-      #  and parse with csv to get header from csv library itself
-      #
-      #  check - if there's an easier or built-in way for the csv library
-
-      ## readlines until
-      ##  - NOT a comments line or
-      ##  - NOT a blank line
-
-      lines = ''
-      File.open( path, 'r:utf-8' ) do |f|
-
-        ## todo/fix: how to handle empty files or files without headers?!
-
-        ## todo/check if readline includes \n\r too??
-        ## yes! - line include \n e.g.
-        ##   "Brewery,City,Name,Abv\n" or
-        ##   "#######\n#  try with some comments\n#   and blank lines even before header\n\nBrewery,City,Name,Abv\n"
-        loop do
-          line = f.readline
-          lines << line
-          break unless  Csv.config.skip?( line ) || Csv.config.blank?( line )
-        end
-      end
-
-      ## puts "lines:"
-      ## pp lines
-
-      ## note: do NOT use headers: true to get "plain" data array (no hash records)
-      ##   hash record does NOT work for single line/row
-      parse_line( lines, sep: sep )
-    end  # method self.header
-end # class CsvReader

data/test/test_reader.rb

@@ -1,119 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_reader.rb
-
-
-require 'helper'
-
-class TestReader < MiniTest::Test
-
-def test_read
-  puts "== read: beer.csv:"
-  table = CsvReader.read( "#{CsvRecord.test_data_dir}/beer.csv" )   ## returns CSV::Table
-
-  pp table.class.name
-  pp table
-  pp table.to_a   ## note: includes header (first row with column names)
-
-  table.each do |row|   ## note: will skip (NOT include) header row!!
-    pp row
-  end
-  puts "  #{table.size} rows"  ## note: again will skip (NOT include) header row in count!!!
-  assert_equal 6, table.size
-end
-
-def test_read_header_false
-  puts "== read (headers: false): beer.csv:"
-  data = CsvReader.read( "#{CsvRecord.test_data_dir}/beer.csv", headers: false )
-
-  pp data.class.name
-  pp data
-
-  data.each do |row|
-    pp row
-  end
-  puts "  #{data.size} rows"
-  assert_equal 7, data.size   ## note: include header row in count
-end
-
-
-def test_read11
-  puts "== read: beer11.csv:"
-  table = CsvReader.read( "#{CsvRecord.test_data_dir}/beer11.csv" )
-  pp table
-  pp table.to_a   ## note: includes header (first row with column names)
-
-  assert true
-end
-
-
-def test_parse_line
-  puts "== parse_line:"
-  row = CsvReader.parse_line( <<TXT )
-Augustiner Bräu München,                 München,  Edelstoff,      5.6%
-Bayerische Staatsbrauerei Weihenstephan, Freising, Hefe Weissbier, 5.4%
-TXT
-
-  pp row
-  assert_equal ['Augustiner Bräu München', 'München', 'Edelstoff', '5.6%'], row
-end
-
-def test_parse_line11
-  puts "== parse_line:"
-  row = CsvReader.parse_line( <<TXT )
-#######
-#  try with some comments
-#   and blank lines even before header
-
-Augustiner Bräu München,                 München,   Edelstoff,      5.6%
-Bayerische Staatsbrauerei Weihenstephan, Freising,  Hefe Weissbier, 5.4%
-TXT
-
-  pp row
-  assert_equal ['Augustiner Bräu München', 'München', 'Edelstoff', '5.6%'], row
-end
-
-def test_header
-  puts "== header: beer.csv:"
-  header = CsvReader.header( "#{CsvRecord.test_data_dir}/beer.csv" )
-  pp header
-  assert_equal ['Brewery','City','Name','Abv'], header
-end
-
-def test_header11
-  puts "== header: beer11.csv:"
-  header = CsvReader.header( "#{CsvRecord.test_data_dir}/beer11.csv" )
-  pp header
-  assert_equal ['Brewery','City','Name','Abv'], header
-end
-
-
-def test_foreach
-  puts "== foreach: beer.csv:"
-  CsvReader.foreach( "#{CsvRecord.test_data_dir}/beer.csv" ) do |row|
-    pp row
-    pp row.fields
-  end
-  assert true
-end
-
-def test_foreach11
-  puts "== foreach: beer11.csv:"
-  CsvReader.foreach( "#{CsvRecord.test_data_dir}/beer11.csv" ) do |row|
-    pp row
-    pp row.fields
-  end
-  assert true
-end
-
-def test_foreach_header_false
-  puts "== foreach (headers: false): beer11.csv:"
-  CsvReader.foreach( "#{CsvRecord.test_data_dir}/beer11.csv", headers: false ) do |row|
-    pp row      ## note: is Array (no .fields available!!!!!)
-  end
-  assert true
-end
-
-end # class TestReader