Sha256: 0f1933d071c9589c4f66b146c444eff9ff561a63875d604f3c9b5c2c95d2821e
Contents?: true
Size: 471 Bytes
Versions: 23
Compression:
Stored size: 471 Bytes
Contents
#!/usr/bin/env ruby
# coding: utf-8
# Extract an (imperfect) array of paragraphs divided somewhat
# arbitrarily on line length.
require 'pdf/reader'
reader = PDF::Reader.new('somefile.pdf')
paragraph = ""
paragraphs = []
reader.pages.each do |page|
lines = page.text.scan(/^.+/)
lines.each do |line|
if line.length > 55
paragraph += " #{line}"
else
paragraph += " #{line}"
paragraphs << paragraph
paragraph = ""
end
end
end
Version data entries
23 entries across 22 versions & 2 rubygems