censive 0.1 → 0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 78a04712f2c737b263765b117a0614bddeda6e4c233409827ed900983b061a64
-  data.tar.gz: e42610ad444e4b4ed9db374f1ee1764c97619fa54235c3bb18e537513804f940
+  metadata.gz: 99c4cd0527e02e78f1fc12c95eda569b23849940d105a6e79442e7eb56623384
+  data.tar.gz: 173aa495f225aa40c1a75686eea8f98e91828cf03e92ab1fee43aba92c27ccfe
 SHA512:
-  metadata.gz: 294e8879052426037bbaed072171ecb8ca0abff47156a4a1d51a3f4531229a6f755ae7db4f8e5dfb7422ad25edf1e145d497bd39d99e46d895cdf6adb4988edc
-  data.tar.gz: d087b32edd1e467143a1e785bd1aa89d2e096920027185ff2dc07a275317b034521b1143f962774270040ae57b079c3a61fa045d10e79f194312787125527fa0
+  metadata.gz: 10010211f2d2f50f075b6ffff16517bea7a9c821cfb9143ea38ca6cce4323a9aa5c59529f84d96f9ed7077aa1fd93418312fa084774f7f34027fd436e7dc9f49
+  data.tar.gz: 61fbef5d03f87a0f92f0c1456699d2489d9f13a1fc4ae1dbb7f1f7196b1e7f10b2f94429cc8e18d23e7edca458189bdb535da833ab4c1968bcb1ace92d9f409f

data/README.md

@@ -1,3 +1,19 @@
 # censive
 
 A quick and lightweight CVS handling library for Ruby
+
+## Writing CSV
+
+```ruby
+require 'censive'
+
+# read in a comma-separated csv file
+data = File.read('data.csv')
+
+# write out a tab-separated tsv file
+Censive.writer('out.tsv', sep: "\t") do |out|
+  Censive.new(data).each do |row|
+    out << row
+  end
+end
+```

data/censive.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name        = "censive"
-  s.version     = "0.1"
+  s.version     = "0.4"
   s.author      = "Steve Shreeve"
   s.email       = "steve.shreeve@gmail.com"
   s.summary     = "A quick and lightweight CVS handling library for Ruby"

data/lib/censive.rb

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
 # ==============================================================================
-# censive - A quick and lightweight CVS handling library for Ruby
+# censive - A quick and lightweight CSV handling library for Ruby
 #
 # Author: Steve Shreeve (steve.shreeve@gmail.com)
 #   Date: Jan 30, 2023
@@ -10,7 +10,15 @@
 #
 # 1. Faster than Ruby's default CSV library
 # 2. Lightweight code base with streamlined method calls
-# 3. Eventually support IO streaming
+#
+# To consider:
+#
+# 1. Option to support IO streaming
+# 2. Option to strip whitespace
+# 3. Option to change output line endings
+# 4. Option to force quotes in output
+# 5. Option to allow reading excel CSV (="Text" for cells)
+# 6. Confirm file encodings such as UTF-8, UTF-16, etc.
 #
 # NOTE: Only getch and scan_until advance strscan's position
 # ==============================================================================
@@ -18,20 +26,34 @@
 require 'strscan'
 
 class Censive < StringScanner
-  def initialize(...)
-    super
+
+  def self.writer(path, **opts)
+    File.open(path, 'w') do |file|
+      yield new(out: file, **opts)
+    end
+  end
+
+  def initialize(str=nil, sep: ',', quote: '"', out: nil, mode: :compact)
+    super(str || '')
     reset
-    @sep   = ',' .freeze # make this a param
-    @quote = '"' .freeze # make this a param
-    @es    = ""  .freeze
-    @cr    = "\r".freeze
-    @lf    = "\n".freeze
+    @sep   = sep  .freeze
+    @quote = quote.freeze
+    @es    = ""   .freeze
+    @cr    = "\r" .freeze
+    @lf    = "\n" .freeze
+    @out   = out
+    @esc   = (@quote * 2).freeze
+    @mode  = mode
   end
 
-  def reset
-    super
+  def reset(str=nil)
+    self.string = str if str
+    super()
     @char  = string[pos]
     @flag  = nil
+
+    @rows  = nil
+    @cols  = @cells = 0
   end
 
   # ==[ Lexer ]==
@@ -56,7 +78,7 @@ class Censive < StringScanner
           getch # consume the quote (optimized by not calling next_char)
           match << (scan_until(/(?=#{@quote})/o) or bomb "unclosed quote")
           case next_char
-          when @sep        then next_char; break
+          when @sep        then @flag = @es; next_char; break
           when @quote      then match << @quote
           when @cr,@lf,nil then break
           else bomb "unexpected character after quote"
@@ -71,20 +93,19 @@ class Censive < StringScanner
     else # consume_unquoted_cell
       match = scan_until(/(?=#{@sep}|#{@cr}|#{@lf}|\z)/o) or bomb "unexpected character"
       @char = string[pos]
-      @char == @sep and next_char
+      @char == @sep and @flag = @es and next_char
       match
     end
   end
 
   def bomb(msg)
-    abort "censive: #{msg} at character #{pos} near '#{string[pos-4,7]}'"
+    abort "#{File.basename($0)}: #{msg} at character #{pos} near '#{string[pos-4,7]}'"
   end
 
   # ==[ Parser ]==
 
   def parse
-    @rows = []
-    @cols = @cells = 0
+    @rows ||= []
     while row = next_row
       @rows << row
       size = row.size
@@ -103,6 +124,50 @@ class Censive < StringScanner
 
   # ==[ Helpers ]==
 
+  # grok returns 2 (seps and quotes), 1 (seps only), 0 (neither)
+  def grok(str)
+    if pos = str.index(/(#{@quote})|#{@sep}/o)
+      $1 ? 2 : str.index(/#{@quote}/o, pos) ? 2 : 1
+    else
+      0
+    end
+  end
+
+  def <<(row)
+    @out or return super
+
+    # most compact export format
+    s,q = @sep, @quote
+    out = case @mode
+    when :compact
+      case grok(row.join)
+      when 0 then row
+      when 1 then row.map {|col| col.include?(s) ? "#{q}#{col}#{q}" : col }
+      else
+        row.map do |col|
+          case grok(col)
+          when 0 then col
+          when 1 then "#{q}#{col}#{q}"
+          else        "#{q}#{col.gsub(q, @esc)}#{q}"
+          end
+        end
+      end
+    when :full
+      row.map {|col| "#{q}#{col.gsub(q, @esc)}#{q}" }
+    end.join(s)
+
+    #!# TODO: allow an option to remove trailing seps in the output
+    # out.gsub!(/#{s}+\z/,'')
+
+    #!# TODO: allow these line endings to be configurable
+    @out << out + @lf
+  end
+
+  def each
+    @rows ||= parse
+    @rows.each {|row| yield row }
+  end
+
   def stats
     wide = string.size.to_s.size
     puts "%#{wide}d rows"    % @rows.size
@@ -112,22 +177,31 @@ class Censive < StringScanner
   end
 end
 
-# ==[ Test it out... ]==
+# ==[ Playground... ]==
 
-ARGV << "z.csv" if ARGV.empty?
+data = File.read('1.csv')
 
-case 1
-when 1
-  path = ARGV.first
-  data = File.read(path)
-when 2
-  data = DATA.gets("\n\n").rstrip
+Censive.writer('out.csv', sep: ',', quote: "'", mode: :compact) do |out|
+  Censive.new(data).each do |row|
+    out << row
+  end
 end
 
-STDOUT.sync = true
-
-csv = Censive.new(data)
-
-data.size > 1e6 ? csv.parse : csv.parse.each {|cols| p cols }
-
-csv.stats
+#
+# ARGV << "z.csv" if ARGV.empty?
+#
+# case 1
+# when 1
+#   path = ARGV.first
+#   data = File.read(path)
+# when 2
+#   data = DATA.gets("\n\n").rstrip
+# end
+#
+# STDOUT.sync = true
+#
+# csv = Censive.new(data)
+#
+# data.size > 1e6 ? csv.parse : csv.parse.each {|cols| p cols }
+#
+# csv.stats

data/test/a-uses-tabs-and-single-quotes-and-no-trailing-newline.csv

@@ -0,0 +1,3 @@
+age	name
+5	'Mike the ''man!'''
+10	Tommy

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: censive
 version: !ruby/object:Gem::Version
-  version: '0.1'
+  version: '0.4'
 platform: ruby
 authors:
 - Steve Shreeve
@@ -20,6 +20,7 @@ files:
 - README.md
 - censive.gemspec
 - lib/censive.rb
+- test/a-uses-tabs-and-single-quotes-and-no-trailing-newline.csv
 homepage: https://github.com/shreeve/censive
 licenses:
 - MIT