vll 0.0.3 → 0.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7b15751061629612b9ce0631e5ffce50cd1bc49d
-  data.tar.gz: 82be2cbd7eebb2dd8850954c5b0a94c4c1a517a8
+  metadata.gz: 8e835b8515174f40da85daa6a5fd92b94f0fc525
+  data.tar.gz: 2510a88faf49a449fc58fd70b5e6b970d5c7adbd
 SHA512:
-  metadata.gz: 07ae95011d219f39caf6dfbfbb4e141bfd37a42c1cf934830dff0d05713c09d0ea723b80ed163f349d2b6caf1ebdb867cb3f4fbdddb272d61b228109042b0414
-  data.tar.gz: 59fa7b009f937a2c70e6cdc080998a00dead8398a04f05dabaa9afe7808f4b19c2b9fe20f61306f0fa036db380325b2bd1310e54ba80c8fb703b49e513be8e6f
+  metadata.gz: c4ec9e6c335414131aad90f76edcc1d72d36a8fa99a90d5cf301e0f2a2c8cfcd9c14862a60f073b292e6e6366cf311d4b7eede81b3850c39019ce2ee955a1c4b
+  data.tar.gz: c15455c89ccf657803aae83979ece54d176910e2741e277b99fd3bec6773e96f85613d538c71f5f9d0d79e424114d68acb9e4fe6782989594558868934db3f38

data/bin/vl

@@ -2,10 +2,10 @@
 begin
 
 require 'optparse'
-require 'pp'
+require 'csv'
 
-options = {
-  :separator => /[,\t]/,
+$options = {
+  :separator => "",
   :padding => 1,
   :skip => 0,
   :comment => /^#/,
@@ -13,42 +13,46 @@ options = {
   :justify => 'l'
 }
 
+
 opts = OptionParser.new do |opts|
   opts.program_name = "(V)iew (L)arge table"
-  opts.version = "0.0.1"
-  opts.banner =  "Usage: vl FILENAME [options]"
+
+  opts.banner = "(V)iew (L)arge table: lightning fast table formatter"
+  opts.separator ''
+  opts.separator '   output to stdout:'
+  opts.separator '       vl FILENAME [options]'
+  opts.separator '   pipe to less:'
   opts.separator '       vll FILENAME [options]'
   opts.separator ''
   opts.separator 'Options:'
-  opts.separator '-' * 80
 
   opts.on('-s', '--separator [REGEX]',
-          'regex to match the separator',
-          '  default: [,\t]') do |s|
+          'char or string to match the separator',
+          '  default: "," (if csv, "\t")') do |s|
     begin
       options[:separator] = Regexp.new(s)
     rescue
       puts 'Warning: Problems encountered when processing the regex.'
-      puts "Warning: Default value \"#{options[:separator].source}\" is used."
+      puts "Warning: Default value \"#{$options[:separator].source}\" is used."
     end
   end
 
   opts.on('-p', '--padding [NUM_OF_SPACES]',
           'number of spaces that separate the columns',
           '  default: 1') do |p|
-    options[:padding] = p.to_i
+    $options[:padding] = p.to_i
   end
 
   opts.on('-k', '--skip [NUM_OF_LINES]',
           'number of top lines to skip',
           '  default: 0') do |k|
-    options[:skip] = k.to_i
+    $options[:skip] = k.to_i
   end
 
   opts.on('-p', '--probe-lines [NUM_OF_LINES]',
           'number of top lines used for fast estimation',
           '  default: 100') do |p|
-    options[:probe_lines] = p.to_i
+    $options[:probe_lines] = p.to_i
   end
 
   opts.on('-j', '--justify [CODE]',
@@ -57,10 +61,10 @@ opts = OptionParser.new do |opts|
           '  options: l = left, r = right, a = auto',
           '  default: l') do |j|
     if ['l', 'r', 'a'].include?(j[0])
-      options[:justify] = j[0]
+      $options[:justify] = j[0]
     else
       puts 'Warning: Unrecognized justify option.'
-      puts "Warning: Default value \"#{options[:justify]}\" is used"
+      puts "Warning: Default value \"#{$options[:justify]}\" is used"
     end
   end
           
@@ -68,80 +72,83 @@ opts = OptionParser.new do |opts|
           'regex to match lines to ignore',
           '  default: ^#') do |c|
     begin
-      options[:comment] = Regexp.new(c)
+      $options[:comment] = Regexp.new(c)
     rescue
       puts 'Warning: Problems encountered when processing the regex.'
-      puts "Warning: Default value \"#{options[:comment].source}\" is used."
+      puts "Warning: Default value \"#{$options[:comment].source}\" is used."
     end
   end
 end
 
 opts.parse!
 
-if ARGV.empty?
-  puts 'Error: No filename found.'
-  puts opts
-  abort
-else
-  file_name = ARGV[0]
+#default separator
+if $options[:separator] == ''
+  if ARGF.filename =~ /.*\.csv/
+    $options[:separator] = ','
+  else
+    $options[:separator] = "\t"
+  end
 end
 
-if !File.exists? file_name
-  abort "Error: file \"#{file_name}\" not found."
-end
 
-max_widths = []
 
-file = open file_name
+#------#
+# Main #
+#------#
+
+
+$max_widths = []
+
 
-file.each_line.with_index.reduce 0 do |pnum, (line, lnum)|
-  next pnum if lnum < options[:skip] or line =~ options[:comment]
-  line.chomp.split(options[:separator]).each_with_index do |c, i|
+#==== line caching ====#
+cached_lines = []
+ARGF.each_line.with_index.reduce 0 do |pnum, (line, lnum)|
+  cached_lines.push(line)
+  next pnum if lnum < $options[:skip] or line =~ $options[:comment]
+  CSV.parse_line(line, {:col_sep=>$options[:separator]}).each_with_index do |c, i|
     # -1 because it's possible that c is empty and i is out of range
-    if max_widths.fetch(i, -1) < c.length then max_widths[i] = c.length end
+    if $max_widths.fetch(i, -1) < c.length then $max_widths[i] = c.length end
   end
-  (pnum += 1) < options[:probe_lines] ? pnum : break
+  (pnum += 1) < $options[:probe_lines] ? pnum : break
 end
+#======================#
 
-#lnum = 0
-#options[:probe_lines].times do
-#  begin
-#    line = file.next rescue break
-#    lnum += 1
-#  end while lnum < options[:skip] or line =~ options[:comment]
-#  line.chomp.split(options[:separator]).each_with_index do |c, i|
-#    # -1 because it's possible that c is empty and i is out of range
-#    if max_widths.fetch(i, -1) < c.length then max_widths[i] = c.length end
-#  end
-#end
-  
-file.rewind
-
-file.each_line.with_index do |line, lnum|
-  if lnum < options[:skip] or line =~ options[:comment] then
+
+def print_line(line, lnum)
+  if lnum < $options[:skip] or line =~ $options[:comment] then
     print line
-    next
+    return
   end
-  line.chomp.split(options[:separator]).each_with_index do |c, i|
-    if max_widths.fetch(i, -1) < c.length then max_widths[i] = c.length end
-    case options[:justify]
+  CSV.parse_line(line, {:col_sep=>$options[:separator]}).each_with_index do |c, i|
+    if $max_widths.fetch(i, -1) < c.length then $max_widths[i] = c.length end
+    case $options[:justify]
     when 'l'
-      print c.ljust(max_widths[i] + options[:padding]) rescue break
+      print c.ljust($max_widths[i] + $options[:padding]) rescue break
     when 'r'
-      print c.rjust(max_widths[i] + options[:padding]) rescue break
+      print c.rjust($max_widths[i] + $options[:padding]) rescue break
     when 'a'
       begin
-        if Float(c) then print c.rjust(max_widths[i] + options[:padding]) end
+        if Float(c) then print c.rjust($max_widths[i] + $options[:padding]) end
       rescue
-        print c.ljust(max_widths[i] + options[:padding])
+        print c.ljust($max_widths[i] + $options[:padding])
       end
     end
   end
-  print "\n" rescue break
+  print "\n" rescue return
+end
+
+cached_lines.each.with_index do |line, lnum|
+  print_line(line, lnum)
+end
+
+ARGF.each_line.with_index do |line, lnum|
+  print_line(line, lnum)
 end
 
+
+
+
 rescue Interrupt
-  # avoid awkward system prompt
-  print "\n"
 
 end

data/bin/vll

@@ -1,3 +1,5 @@
 #!/usr/bin/env ruby
 
-exec "vl '#{ARGV.join("' '")}' | less -S"
+require 'shellwords'
+
+exec "vl #{ARGV.shelljoin} | less -S"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: vll
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - xzhu
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-11-12 00:00:00.000000000 Z
+date: 2015-01-13 00:00:00.000000000 Z
 dependencies: []
 description: Nicely format columns of a large CSV/TSV file according to their content
   width, using first few lines as estimation thus extremely fast. Customizable.
@@ -42,9 +42,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.2
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: "(V)iew (L)arge table. Format large table in a split of a second"
 test_files: []
-has_rdoc: