File: page_bench

package info (click to toggle)
ruby-pdf-reader 2.15.0-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 33,512 kB
  • sloc: ruby: 11,959; sh: 46; makefile: 11
file content (21 lines) | stat: -rw-r--r-- 410 bytes parent folder | download | duplicates (6) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
 
#!/usr/bin/env ruby

# text extraction is a handy benchmark of parsing/lexing performance, as 
# the full content stream of each page is processed.
#
# run like so:
#
#     ruby -Ilib tools/page_bench foo.pdf

require 'rubygems'
require 'pdf/reader'

reader = PDF::Reader.new(ARGV[0])

require "benchmark"

Benchmark.bm(1) do |x|
  reader.pages.each do |page|
    x.report(page.number) { page.text }
  end
end