Sha256: 14bed31d801450202f95abe9c705ed444613cf23349dc8225219992ca5f19352
Contents?: true
Size: 927 Bytes
Versions: 9
Compression:
Stored size: 927 Bytes
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)
pdf = [pdfs].flatten.first
cmd = "pdfinfo #{pdf} 2>&1"
result = `#{cmd}`.chomp
raise ExtractionFailed, result if $? != 0
match = result.match(MATCHERS[key])
answer = match && match[1]
answer = answer.to_i if answer && key == :length
answer
end
end
end
Version data entries
9 entries across 9 versions & 1 rubygems