csvreader 1.1.3 → 1.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a920108ec183cff7c7cad8c0d967390b4f2bd38f
-  data.tar.gz: 2a32715b6e1eb3e83b3837de1d151169d8b3455f
+  metadata.gz: dd541a30e12622b666a01bc18b5ba80d93cbd1aa
+  data.tar.gz: 773aa117ae2b41bfce6a8cde5df1ed1df4eadeab
 SHA512:
-  metadata.gz: f2264455eda5136261628cc77de24494d9ea11bb116c9ca5e36495f4f4b90101356444c9da75c37b6d5b9419b57ce4a145830bd1d6919ce0cbdb2ef05673bfad
-  data.tar.gz: 9c539db1ccac369ae23113587e9d529a95de0b080f3c12687e237d46bea1bdbb157b57f7b2f61d72f637cd914aecb11fbd8daeec11ecb38f49b65669a004e774
+  metadata.gz: b4720613f00b591b3d419f03c06aef8d5e8bb274e4d35e7b1f12f6d14aadb64d1611c7822e3fdc0d2a63c60b653b79a64339aabfd107fb73b14a47bf646c7153
+  data.tar.gz: 3ce20e6925e81e80c6a61e03fd208d852741b7c8d3dd32d045f56b748844782a47810ce041eaa1a8d30f63f282c1655fc6939f7f0ff10294e25ec0be48ede043

data/Manifest.txt

@@ -14,6 +14,7 @@ lib/csvreader/parser_json.rb
 lib/csvreader/parser_std.rb
 lib/csvreader/parser_strict.rb
 lib/csvreader/parser_tab.rb
+lib/csvreader/parser_table.rb
 lib/csvreader/reader.rb
 lib/csvreader/reader_hash.rb
 lib/csvreader/version.rb
@@ -40,6 +41,7 @@ test/test_parser_numeric.rb
 test/test_parser_quotes.rb
 test/test_parser_strict.rb
 test/test_parser_tab.rb
+test/test_parser_table.rb
 test/test_reader.rb
 test/test_reader_converters.rb
 test/test_reader_hash.rb

data/README.md

@@ -8,8 +8,13 @@
 * forum :: [wwwmake](http://groups.google.com/group/wwwmake)
 
 
+
 ## What's News?
 
+**v1.1.4**  Added new "classic" table parser (see `ParserTable`) for supporting fields separated by (one or more) spaces
+e.g. `Csv.table.parse( txt )`.
+
+
 **v1.1.3**: Added built-in support for french single and double quotes / guillemets (`‹› «»`) to default parser ("The Right Way").
 Now you can use both, that is, single (`‹...›'` or `›...‹'`)
 or double (`«...»` or `»...«`).
@@ -38,7 +43,7 @@ for meta data, the first one "wins" - you CANNOT use both.
 
 
 **v1.1.0**: Added new fixed width field (fwf) parser (see `ParserFixed`) for supporting fields with fixed width (and no separator)
-e.g.`Csv.fixed.parse( txt, width: [8,-2,8,-3,32,-2,14] )`.
+e.g. `Csv.fixed.parse( txt, width: [8,-2,8,-3,32,-2,14] )`.
 
 
 **v1.0.3**: Added built-in support for an (optional) front matter (`---`) meta data block
@@ -396,6 +401,32 @@ Hacker-Pschorr Bräu,                      München,   Münchner Dunkel,  5.0%
 Staatliches Hofbräuhaus München,          München,   Hofbräu Oktoberfestbier, 6.3%
 ```
 
+Or use the ARFF (attribute-relation file format)-like alternative style with  `@`-directives
+inside comments (for easier backwards compatibility with old readers)
+for "meta data" in the header (before any records):
+
+```
+##########################
+# try with some comments
+#   and blank lines even before @-directives in header
+#
+# @RELATION Beer
+#
+# @ATTRIBUTE Brewery
+# @ATTRIBUTE City
+# @ATTRIBUTE Name
+# @ATTRIBUTE Abv
+
+Andechser Klosterbrauerei,Andechs,Doppelbock Dunkel,7%
+Augustiner Bräu München,München,Edelstoff,5.6%
+
+Bayerische Staatsbrauerei Weihenstephan,  Freising,  Hefe Weissbier,   5.4%
+Brauerei Spezial,                         Bamberg,   Rauchbier Märzen, 5.1%
+Hacker-Pschorr Bräu,                      München,   Münchner Dunkel,  5.0%
+Staatliches Hofbräuhaus München,          München,   Hofbräu Oktoberfestbier, 6.3%
+```
+
+
 
 ### Q: How can I change the default format / dialect?
 
@@ -535,42 +566,6 @@ Csv.fixed.parse( txt, width: [8,-2,8,-3,32,-2,14] )  # or Csv.fix or Csv.f
 ```
 
 
-Bonus: If the width is a string (not an array)
-(e.g. `'a8 a8 a32 Z*'` or `'A8 A8 A32 Z*'` and so on)
-than the fixed width field parser
-will use  `String#unpack` and the value of width as its format string spec.
-Example:
-
-``` ruby
-txt = <<TXT
-12345678123456781234567890123456789012345678901212345678901234
-TXT
-
-Csv.fixed.parse( txt, width: 'a8 a8 a32 Z*' )  # or Csv.fix or Csv.f
-# => [["12345678","12345678", "12345678901234567890123456789012", "12345678901234"]]
-
-txt = <<TXT
-John    Smith   john@example.com                1-888-555-6666
-Michele O'Reileymichele@example.com             1-333-321-8765
-TXT
-
-Csv.fixed.parse( txt, width: 'A8 A8 A32 Z*' )   # or Csv.fix or Csv.f
-# => [["John",    "Smith",    "john@example.com",    "1-888-555-6666"],
-#     ["Michele", "O'Reiley", "michele@example.com", "1-333-321-8765"]]
-
-# and so on
-```
-
-| String Directive | Returns | Meaning                 |
-|------------------|---------|-------------------------|
-| `A`              | String  | Arbitrary binary string (remove trailing nulls and ASCII spaces) |
-| `a`              | String  | Arbitrary binary string |
-| `Z`              | String  | Null-terminated string  |
-
-
-and many more. See the `String#unpack` documentation
-for the complete format spec and directives.
-
 
 
 

data/lib/csvreader/base.rb

@@ -19,6 +19,7 @@ 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_table'
 require 'csvreader/parser'
 require 'csvreader/converter'
 require 'csvreader/reader'
@@ -62,8 +63,8 @@ class Parser
                                                       null: "\\N" )
 
 
-  TAB     = ParserTab.new
-
+  TAB     = ParserTab.new      ## (strict) tab-separated
+  TABLE   = ParserTable.new    ## space-separated e.g /[ \t]+/
   FIXED   = ParserFixed.new
 
 
@@ -80,6 +81,7 @@ class Parser
   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
@@ -103,6 +105,7 @@ class CsvReader
 
 
   TAB   = Builder.new( Parser::TAB )
+  TABLE = Builder.new( Parser::TABLE )
   FIXED = Builder.new( Parser::FIXED )
 
 
@@ -119,6 +122,7 @@ class CsvReader
   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
@@ -141,6 +145,7 @@ class CsvHashReader
 
 
   TAB   = Builder.new( Parser::TAB )
+  TABLE = Builder.new( Parser::TABLE )
   FIXED = Builder.new( Parser::FIXED )
 
 
@@ -157,6 +162,7 @@ class CsvHashReader
   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

data/lib/csvreader/parser_table.rb

@@ -0,0 +1,89 @@
+# encoding: utf-8
+
+class CsvReader
+
+class ParserTable
+
+###################################
+## add simple logger with debug flag/switch
+#
+#  use Parser.debug = true   # to turn on
+#
+#  todo/fix: use logutils instead of std logger - why? why not?
+
+def self.build_logger()
+  l = Logger.new( STDOUT )
+  l.level = :info    ## set to :info on start; note: is 0 (debug) by default
+  l
+end
+def self.logger() @@logger ||= build_logger; end
+def logger()  self.class.logger; end
+
+
+
+
+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
+
+  if block_given?
+    parse_lines( input, &block )
+  else
+    records = []
+
+    parse_lines( input ) do |record|
+      records << record
+    end
+
+    records
+  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|
+
+    logger.debug  "line:"             if logger.debug?
+    logger.debug line.pretty_inspect  if logger.debug?
+
+
+    ##  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( '' )
+    line = line.strip         ## strip leading and trailing whitespaces (space/tab) too
+    logger.debug line.pretty_inspect    if logger.debug?
+
+    if line.empty?             ## skip blank lines
+      logger.debug "skip blank line"    if logger.debug?
+      next
+    end
+
+    if line.start_with?( "#" )  ## skip comment lines
+      logger.debug "skip comment line"   if logger.debug?
+      next
+    end
+
+    # note: string.split defaults to split by space (e.g. /\s+/) :-)
+    #          for  just make it "explicit" with /[ \t]+/
+
+    values = line.split( /[ \t]+/ )
+    logger.debug values.pretty_inspect   if logger.debug?
+
+    ## note: requires block - enforce? how? why? why not?
+    block.call( values )
+  end
+end # method parse_lines
+
+
+end # class ParserTable
+end # class CsvReader

data/lib/csvreader/version.rb

@@ -3,16 +3,24 @@
 
 class CsvReader   ## note: uses a class for now - change to module - why? why not?
 
-  MAJOR = 1    ## todo: namespace inside version or something - why? why not??
-  MINOR = 1
-  PATCH = 3
-  VERSION = [MAJOR,MINOR,PATCH].join('.')
+  module Version
+    MAJOR = 1    ## todo: namespace inside version or something - why? why not??
+    MINOR = 1
+    PATCH = 4
 
+    ## self.to_s  - why? why not?
+  end
+
+  VERSION = [Version::MAJOR,
+             Version::MINOR,
+             Version::PATCH].join('.')
 
-  def self.version
+  def self.version   ## keep (as an alternative to VERSION) - why? why not?
     VERSION
   end
 
+
+
   def self.banner
     "csvreader/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
   end

data/test/helper.rb

@@ -21,3 +21,4 @@ end
 ## CsvReader::ParserStd.logger.level    = :debug   ## turn on "global" logging
 ## CsvReader::ParserStrict.logger.level = :debug   ## turn on "global" logging
 ## CsvReader::ParserFixed.logger.level = :debug   ## turn on "global" logging
+CsvReader::ParserTable.logger.level = :debug   ## turn on "global" logging

data/test/test_parser_table.rb

@@ -0,0 +1,35 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_parser_table.rb
+
+
+require 'helper'
+
+class TestParserTable < MiniTest::Test
+
+
+def parser() CsvReader::Parser::TABLE;  end
+
+
+def test_contacts
+  records = [["aa", "bbb"],
+             ["cc", "dd", "ee"]]
+
+  assert_equal records, parser.parse( <<TXT )
+# space-separated with comments and blank lines
+
+ aa bbb
+cc    dd ee
+
+TXT
+
+   assert_equal records, parser.parse( <<TXT )
+ aa bbb
+cc    dd ee
+TXT
+end
+
+
+end # class TestParserTable

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csvreader
 version: !ruby/object:Gem::Version
-  version: 1.1.3
+  version: 1.1.4
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-10-24 00:00:00.000000000 Z
+date: 2018-10-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc
@@ -65,6 +65,7 @@ files:
 - lib/csvreader/parser_std.rb
 - lib/csvreader/parser_strict.rb
 - lib/csvreader/parser_tab.rb
+- lib/csvreader/parser_table.rb
 - lib/csvreader/reader.rb
 - lib/csvreader/reader_hash.rb
 - lib/csvreader/version.rb
@@ -91,6 +92,7 @@ files:
 - test/test_parser_quotes.rb
 - test/test_parser_strict.rb
 - test/test_parser_tab.rb
+- test/test_parser_table.rb
 - test/test_reader.rb
 - test/test_reader_converters.rb
 - test/test_reader_hash.rb