# This is file "utf-8_test.sed"
#
# It's used by the "sed" utility program
# to convert XML-encoded filenames to UTF-8

# Match longest strings first

# Three-byte encodings:

# En dash
s/%[Ee]2%80%93/–/g

# Em dash
s/%[Ee]2%80%94/—/g

# Horizontal ellipsis
s/%[Ee]2%80%[Aa]6/…/g

# Less-than-or-equal sign
s/%[Ee]2%89%[Aa]4/≤/g

# Euro symbol
s/%[Ee]2%82%[Aa][Cc]/€/g

# Two-byte encodings:

# Non-break space
s/%[Cc]2%[Aa]0/⎵/g

# Lowercase a with acute accent
s/%[Cc]3%[Aa]1/á/g

# Lowercase a with umlaut (a.k.a. diaeresis)
s/%[Cc]3%[Aa]4/ä/g

# Lowercase e with acute accent
s/%[Cc]3%[Aa]9/é/g

# Lowercase i with acute accent
s/%[Cc]3%[Aa]D/í/g

# Lowercase o with acute accent
s/%[Cc]3%[Bb]3/ó/g

# Lowercase n with tilde
s/%[Cc]3%[Bb]1/ñ/g

# Lowercase c with acute accent 
s/%[Cc]4%87/ć/g

# Lowercase o with long accent (a.k.a. macron)
s/%[Cc]5%8[Dd]/ō/g

# One-byte encodings:

# "And" sign (a.k.a. ampersand)
s/&/\&/g

# Space
s/%20/ /g

# Sharp (or pound) sign
s/%23/#/g

# Percent sign
s/%25/%/g

# Left square bracket
s/%5[Bb]/[/g

# Right square bracket
s/%5[Dd]/]/g

# End of file "utf-8_test.sed"