censive 0.5 → 0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3de2789bb1678210e42d6fb3c4987b91c70b18765cc417c336db6f6f1eb969a7
-  data.tar.gz: 6ffdf0f664df8978b9b44cacbdc81a3c664c95d48a1d0c940dd8634fd51fc3e2
+  metadata.gz: 8a757fa8bbc5ddf364889e4b7feca2001f3784e8d0b2ff70a1b0349691a34aae
+  data.tar.gz: 68dced562eb0dc9b7ad300447091ceb74c04a55201e88cc9fffbe1ba3bbc534d
 SHA512:
-  metadata.gz: d64e1980813c2e7231637a3f7386c583892f6deee14991412075e559ac0d97118900d6f42d9722dc36db2c9195d909fb8dbd3dc1f9914ab1b493f4a46f9eacd0
-  data.tar.gz: 0bb17da4415090f1d6235d594f03a604be3b594142e9add762eeaa1d25048942e64d7d99f2e1310566c03a7011e2457f87ce137f293c414d175a47bc4f6d5a8f
+  metadata.gz: c48d7e2bd3d1a7baa5fb2fae7b0553de665737849e9a50721f704a1a1f67c758c545dfe53d21f32ce386b20ea21f04c67ee8d765bf20653774b9475ebb60711f
+  data.tar.gz: 411d59006ebcb6a07161186b56f73a8dcc73beeaecbe14e786ad237935c62fd6ef0631483c8f297399098b0dea2387863f7be8c878568e0558804e5bd20b55ee

data/README.md

@@ -1,6 +1,6 @@
 # censive
 
-A quick and lightweight CVS handling library for Ruby
+A quick and lightweight CSV handling library for Ruby
 
 ## Writing CSV
 

data/censive.gemspec

@@ -2,13 +2,13 @@
 
 Gem::Specification.new do |s|
   s.name        = "censive"
-  s.version     = "0.5"
+  s.version     = "0.7"
   s.author      = "Steve Shreeve"
   s.email       = "steve.shreeve@gmail.com"
-  s.summary     = "A quick and lightweight CVS handling library for Ruby"
-  s.description = "A quick and lightweight CVS handling library for Ruby"
+  s.summary     = "A quick and lightweight CSV handling library for Ruby"
+  s.description = "A quick and lightweight CSV handling library for Ruby"
   s.homepage    = "https://github.com/shreeve/censive"
   s.license     = "MIT"
   s.files       = `git ls-files`.split("\n") - %w[.gitignore]
-  s.executables = `cd bin && git ls-files .`.split("\n")
+  s.executables = `(cd bin 2>&1) > /dev/null && git ls-files .`.split("\n")
 end

data/lib/censive.rb

@@ -33,17 +33,34 @@ class Censive < StringScanner
     end
   end
 
-  def initialize(str=nil, sep: ',', quote: '"', out: nil, mode: :compact)
+  def initialize(str=nil,
+    sep:   ','     , # column separator character
+    quote: '"'     , # quote character
+
+    drop:  false   , # enable to drop trailing separators
+    eol:   "\n"    , # desired line endings for exports
+    mode:  :compact, # export mode: compact or full
+    out:   nil     , # output IO/file
+    relax: false   , # relax parsing of quotes
+
+    **opts           # grab bag
+  )
     super(str || '')
     reset
+
     @sep   = sep  .freeze
     @quote = quote.freeze
+
+    @drop  = drop
+    @eol   = eol.freeze
+    @mode  = mode
+    @out   = out
+    @relax = relax
+
     @es    = ""   .freeze
     @cr    = "\r" .freeze
     @lf    = "\n" .freeze
-    @out   = out
     @esc   = (@quote * 2).freeze
-    @mode  = mode
   end
 
   def reset(str=nil)
@@ -81,7 +98,12 @@ class Censive < StringScanner
           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"
+          else
+            if @relax
+              match << @quote + @char
+            else
+              bomb "invalid character after quote"
+            end
           end
         end
         match
@@ -99,7 +121,7 @@ class Censive < StringScanner
   end
 
   def bomb(msg)
-    abort "#{File.basename($0)}: #{msg} at character #{pos} near '#{string[pos-4,7]}'"
+    abort "\n#{File.basename($0)}: #{msg} at character #{pos} near '#{string[pos-4,7]}'"
   end
 
   # ==[ Parser ]==
@@ -124,7 +146,7 @@ class Censive < StringScanner
 
   # ==[ Helpers ]==
 
-  # grok returns 2 (seps and quotes), 1 (seps only), 0 (neither)
+  # grok returns: 2 for seps and quotes, 1 for seps only, and 0 for neither
   def grok(str)
     if pos = str.index(/(#{@quote})|#{@sep}/o)
       $1 ? 2 : str.index(/#{@quote}/o, pos) ? 2 : 1
@@ -156,11 +178,11 @@ class Censive < StringScanner
       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/,'')
+    # drop trailing seps, if specified
+    out.gsub!(/#{s}+\z/,'') if @drop
 
-    #!# TODO: allow these line endings to be configurable
-    @out << out + @lf
+    # write output, using desired line endings
+    @out << out + @eol
   end
 
   def each
@@ -177,17 +199,71 @@ class Censive < StringScanner
   end
 end
 
+__END__
+
 # ==[ Playground... ]==
 
+STDOUT.sync = true
+
+require 'fileutils'
+
+ARGV << "101.csv"
+
+rand = `LC_ALL=C tr -dc a-zA-Z0-9 < /dev/random | head -c12`
+
+rows = []
+cols = []
+coun = 0
+full = 0
+
+ARGV.each do |path|
+  File.file?(path) or next
+
+  print "Processing #{path.inspect}"
+
+  rows.clear
+  cols.clear
+  seen = 0
+  coun += 1
+
+  dest = "#{path}-#{rand}"
+
+  begin
+    Censive.writer(dest) do |file|
+      Censive.new(File.read(path), relax: true).each do |cols|
+        cols.each {|cell| cell && cell.size >= 3 && cell.sub!(/\A="/, '') && cell.sub!(/"\z/, '') }
+        file << cols
+        seen += 1
+        print "." if (seen % 1e5) == 0
+      end
+    end
+    FileUtils.mv(dest, path)
+    full += (seen - 1)
+    puts " (#{seen - 1} rows of data)"
+  rescue
+    puts " - unable to process (#{$!})"
+    FileUtils.rm_f(dest)
+  end
+end
+
+puts "Processed #{coun} files with a total of #{full} rows of data" if coun > 1
+
+__END__
+,"CHUI, LOK HANG "BENNY",   =>   ,"""CHUI, LOK HANG ""BENNY""",
+
+,"..............."B
+
+__END__
+
+
 data = File.read('1.csv')
 
-Censive.writer('out.csv', sep: ',', quote: "'", mode: :compact) do |out|
+Censive.writer('out.csv', sep: ',', quote: "'") do |out|
   Censive.new(data).each do |row|
     out << row
   end
 end
 
-#
 # ARGV << "z.csv" if ARGV.empty?
 #
 # case 1

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: censive
 version: !ruby/object:Gem::Version
-  version: '0.5'
+  version: '0.7'
 platform: ruby
 authors:
 - Steve Shreeve
@@ -10,7 +10,7 @@ bindir: bin
 cert_chain: []
 date: 2023-01-31 00:00:00.000000000 Z
 dependencies: []
-description: A quick and lightweight CVS handling library for Ruby
+description: A quick and lightweight CSV handling library for Ruby
 email: steve.shreeve@gmail.com
 executables: []
 extensions: []
@@ -43,5 +43,5 @@ requirements: []
 rubygems_version: 3.4.5
 signing_key:
 specification_version: 4
-summary: A quick and lightweight CVS handling library for Ruby
+summary: A quick and lightweight CSV handling library for Ruby
 test_files: []