Sha256: 65a207f90b7701c8cc8ce776125440d12db72e0d25d8f2adf12d0281341e0fc2
Contents?: true
Size: 1.47 KB
Versions: 14
Compression:
Stored size: 1.47 KB
Contents
module Docsplit
# Delegates to **pdfinfo** in order to extract information about a PDF file.
class InfoExtractor
# Regex matchers for different bits of information.
MATCHERS = {
:author => /^Author:\s+([^\n]+)/,
:date => /^CreationDate:\s+([^\n]+)/,
:creator => /^Creator:\s+([^\n]+)/,
:keywords => /^Keywords:\s+([^\n]+)/,
:producer => /^Producer:\s+([^\n]+)/,
:subject => /^Subject:\s+([^\n]+)/,
:title => /^Title:\s+([^\n]+)/,
:length => /^Pages:\s+([^\n]+)/,
}
# Pull out a single datum from a pdf.
def extract(key, pdfs, opts)
extract_all(pdfs, opts)[key]
end
def extract_all(pdfs, opts)
pdf = [pdfs].flatten.first
cmd = "pdfinfo #{ESCAPE[pdf]} 2>&1"
result = `#{cmd}`.chomp
raise ExtractionFailed, result if $? != 0
# ruby 1.8 (iconv) and 1.9 (String#encode) :
if String.method_defined?(:encode)
result.encode!('UTF-8', 'binary', :invalid => :replace, :undef => :replace, :replace => "") unless result.valid_encoding?
else
require 'iconv' unless defined?(Iconv)
ic = Iconv.new('UTF-8//IGNORE','UTF-8')
result = ic.iconv(result)
end
info = {}
MATCHERS.each do |key, matcher|
match = result.match(matcher)
answer = match && match[1]
if answer
answer = answer.to_i if key == :length
info[key] = answer
end
end
info
end
end
end
Version data entries
14 entries across 14 versions & 5 rubygems