Sha256: 7355d9f1dfd01c09014134bee82c9d8d895d0353d5084a34f39542bf51a5bcb9
Contents?: true
Size: 791 Bytes
Versions: 11
Compression:
Stored size: 791 Bytes
Contents
class FormatParser::PDFParser
include FormatParser::IOUtils
# First 9 bytes of a PDF should be in this format, according to:
#
# https://stackoverflow.com/questions/3108201/detect-if-pdf-file-is-correct-header-pdf
#
# There are however exceptions, which are left out for now.
#
PDF_MARKER = /%PDF-[12]\.[0-8]{1}/
PDF_CONTENT_TYPE = 'application/pdf'
def likely_match?(filename)
filename =~ /\.(pdf|ai)$/i
end
def call(io)
io = FormatParser::IOConstraint.new(io)
header = safe_read(io, 9)
return unless header =~ PDF_MARKER
FormatParser::Document.new(format: :pdf, content_type: PDF_CONTENT_TYPE)
rescue FormatParser::IOUtils::InvalidRead
nil
end
FormatParser.register_parser new, natures: :document, formats: :pdf, priority: 3
end
Version data entries
11 entries across 11 versions & 1 rubygems