module Sprockets::EncodingUtils
def base64(str)
str - String data
Public: Use base64 to encode data.
def base64(str) Base64.strict_encode64(str) end
def charlock_detect(str)
To enable this code path, require 'charlock_holmes'
Internal: Use Charlock Holmes to detect encoding.
def charlock_detect(str) if defined? CharlockHolmes::EncodingDetector if detected = CharlockHolmes::EncodingDetector.detect(str) str.force_encoding(detected[:encoding]) if detected[:encoding] end end str end
def deflate(str)
str - String data
Public: Use deflate to compress data.
def deflate(str) deflater = Zlib::Deflate.new( Zlib::BEST_COMPRESSION, -Zlib::MAX_WBITS, Zlib::MAX_MEM_LEVEL, Zlib::DEFAULT_STRATEGY ) deflater << str deflater.finish end
def detect(str)
str - ASCII-8BIT encoded String
environment's external encoding.
Attempts to parse any Unicode BOM otherwise falls back to the
Public: Basic string detecter.
def detect(str) str = detect_unicode_bom(str) # Attempt Charlock detection if str.encoding == Encoding::BINARY charlock_detect(str) end # Fallback to UTF-8 if str.encoding == Encoding::BINARY str.force_encoding(Encoding.default_external) end str end
def detect_css(str)
str - String.
Public: Detect and strip @charset from CSS style sheet.
def detect_css(str) str = detect_unicode_bom(str) if name = scan_css_charset(str) encoding = Encoding.find(name) str = str.dup str.force_encoding(encoding) len = "@charset \"#{name}\";".encode(encoding).size str.slice!(0, len) str end # Fallback to UTF-8 if str.encoding == Encoding::BINARY str.force_encoding(Encoding::UTF_8) end str end
def detect_html(str)
str - String.
Public: Detect charset from HTML document. Defaults to ISO-8859-1.
def detect_html(str) str = detect_unicode_bom(str) # Attempt Charlock detection if str.encoding == Encoding::BINARY charlock_detect(str) end # Fallback to ISO-8859-1 if str.encoding == Encoding::BINARY str.force_encoding(Encoding::ISO_8859_1) end str end
def detect_unicode(str)
str - ASCII-8BIT encoded String
Attempts to parse Unicode BOM and falls back to UTF-8.
Public: Detect Unicode string.
def detect_unicode(str) str = detect_unicode_bom(str) # Fallback to UTF-8 if str.encoding == Encoding::BINARY str.force_encoding(Encoding::UTF_8) end str end
def detect_unicode_bom(str)
Returns UTF 8/16/32 encoded String without BOM or the original String if
str - ASCII-8BIT encoded String
Public: Detect and strip BOM from possible unicode string.
def detect_unicode_bom(str) bom_bytes = str.byteslice(0, 4).bytes.to_a BOM.each do |encoding, bytes| if bom_bytes[0, bytes.size] == bytes str = str.dup str.force_encoding(Encoding::BINARY) str.slice!(0, bytes.size) str.force_encoding(encoding) return str end end return str end
def gzip(str)
str - String data
Public: Use gzip to compress data.
def gzip(str) io = StringIO.new gz = Zlib::GzipWriter.new(io, Zlib::BEST_COMPRESSION) gz.mtime = 1 gz << str gz.finish io.string end
def scan_css_charset(str)
str - ASCII-8BIT encoded String
Internal: Scan binary CSS string for @charset encoding name.
def scan_css_charset(str) buf = [] i = 0 str.each_byte.each do |byte| # Halt on line breaks break if byte == 0x0A || byte == 0x0D # Only ascii bytes next unless 0x0 < byte && byte <= 0xFF if i < CHARSET_SIZE elsif i == CHARSET_SIZE if buf == CHARSET_START buf = [] else break end elsif byte == 0x22 return buf.pack('C*') end buf << byte i += 1 end nil end
def unmarshaled_deflated(str, window_bits = -Zlib::MAX_WBITS)
window_bits - Integer deflate window size. See ZLib::Inflate.new()
str - Marshaled String
otherwise inflate the data an unmarshal.
Checks leading marshal header to see if the bytes are uncompressed
Internal: Unmarshal optionally deflated data.
def unmarshaled_deflated(str, window_bits = -Zlib::MAX_WBITS) major, minor = str[0], str[1] if major && major.ord == Marshal::MAJOR_VERSION && minor && minor.ord <= Marshal::MINOR_VERSION marshaled = str else begin marshaled = Zlib::Inflate.new(window_bits).inflate(str) rescue Zlib::DataError marshaled = str end end Marshal.load(marshaled) end