NAME

SYNOPSIS

 Standard options:

    --version       print version information and exit
    --help          this message
    --man           full manpage
    --debug         add some debugging output

 Character mode options:

            Without a specified encoding, utf8 is assumed
            unless file has encoding extension.

    --verbose   -v  show full character names like \N{EN DASH}

    --hex       -x  use singleton \x{...} esapes instead of \N{U+XXX}

    --encoding  -E  specify encoding for all input files

    --html      -H  show HTML entities (add --verbose for names)
    --xml       -X  show XML entities

  Binary mode options:

    --bytes     -b  binary file in hex
    --octal     -0  binary file in octal

  Other options:

    --endings       -n   place $ at EOL so trailing spaces visible
    --backslash     -t   use backslash escapes for unprintable ASCII
    --fix-newlines  -l   consider any Unicode linebreak sequence as EOL
    --unbuffer      -u   flush each output line

DESCRIPTION

Use --endings or "-e" to cat like "cat -e" and add a dollar at the end of each line so trailing spaces become apparent.

Use --backslash or "-t" to show tabs and other ASCII control codes as backslash escapes.

By default, uniquote converts each such code points into the form "\N{U+hex}", making code point 962 appear as "\N{U+3C2}". The --hex option instead shows eligible points in backslash-X notation, so code point 962 would be displayed as "\x{3C2}".

The --verbose option instead displays eligible code points by name. Code point 962 would then be shown as "\N{GREEK SMALL LETTER FINAL SIGMA}".

The --xml and --html options show code point using numeric entities. Adding --verbose to --html will use named HTML entities where available.

EXAMPLES

  $ perl -E 'say "ascii:\tnayeeve fassodd"'                                                     > /tmp/nf.ascii
  $ perl -E 'binmode(STDOUT, "encoding(macroman)")||die; say "macroman:\tna\xEFve fa\xE7ade"'   > /tmp/nf.macroman
  $ perl -E 'binmode(STDOUT, "encoding(utf8)")||die;     say "utf8:\tna\xEFve fa\xE7ade"'       > /tmp/nf.utf8
  $ perl -E 'binmode(STDOUT, "encoding(utf16)")||die;    say "utf16:\tna\xEFve fa\xE7ade"'      > /tmp/nf.utf16
  $ perl -E 'binmode(STDOUT, "encoding(utf32)")||die;    say "utf32:\tna\xEFve fa\xE7ade"'      > /tmp/nf.utf32
  $ perl -E 'binmode(STDOUT, "encoding(latin1)")||die;   say "latin1:\tna\xEFve fa\xE7ade"'     > /tmp/nf.latin1
  $ perl -E 'binmode(STDOUT, "encoding(cp1252)")||die;   say "cp1252:\tna\xEFve fa\xE7ade"'     > /tmp/nf.cp1252


  $ wc -c /tmp/nf*
      23 /tmp/nf.ascii
      21 /tmp/nf.cp1252
      21 /tmp/nf.latin1
      23 /tmp/nf.macroman
      42 /tmp/nf.utf16
      84 /tmp/nf.utf32
      21 /tmp/nf.utf8
     235 total

  $ uniquote /tmp/nf.*
ascii:\N{U+09}nayeeve fassodd
cp1252:\N{U+09}na\N{U+EF}ve fa\N{U+E7}ade
latin1:\N{U+09}na\N{U+EF}ve fa\N{U+E7}ade
macroman:\N{U+09}na\N{U+EF}ve fa\N{U+E7}ade
utf16:\N{U+09}na\N{U+EF}ve fa\N{U+E7}ade
utf32:\N{U+09}na\N{U+EF}ve fa\N{U+E7}ade
utf8:\N{U+09}na\N{U+EF}ve fa\N{U+E7}ade

  $ uniquote --backslash --endings /tmp/nf.*
ascii:\tnayeeve fassodd$
cp1252:\tna\N{U+EF}ve fa\N{U+E7}ade$
latin1:\tna\N{U+EF}ve fa\N{U+E7}ade$
macroman:\tna\N{U+EF}ve fa\N{U+E7}ade$
utf16:\tna\N{U+EF}ve fa\N{U+E7}ade$
utf32:\tna\N{U+EF}ve fa\N{U+E7}ade$
utf8:\tna\N{U+EF}ve fa\N{U+E7}ade$

  $ uniquote --verbose /tmp/nf.*
ascii:\N{CHARACTER TABULATION}nayeeve fassodd
cp1252:\N{CHARACTER TABULATION}na\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
latin1:\N{CHARACTER TABULATION}na\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
macroman:\N{CHARACTER TABULATION}na\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
utf16:\N{CHARACTER TABULATION}na\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
utf32:\N{CHARACTER TABULATION}na\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
utf8:\N{CHARACTER TABULATION}na\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade

  $ uniquote --binary /tmp/nf.*
ascii:\x09nayeeve fassodd
cp1252:\x09na\xEFve fa\xE7ade
latin1:\x09na\xEFve fa\xE7ade
macroman:\x09na\x95ve fa\x8Dade
\xFE\xFF\x00u\x00t\x00f\x001\x006\x00:\x00\x09\x00n\x00a\x00\xEF\x00v\x00e\x00 \x00f\x00a\x00\xE7\x00a\x00d\x00e\x00
\x00\x00\xFE\xFF\x00\x00\x00u\x00\x00\x00t\x00\x00\x00f\x00\x00\x003\x00\x00\x002\x00\x00\x00:\x00\x00\x00\x09\x00\x00\x00n\x00\x00\x00a\x00\x00\x00\xEF\x00\x00\x00v\x00\x00\x00e\x00\x00\x00 \x00\x00\x00f\x00\x00\x00a\x00\x00\x00\xE7\x00\x00\x00a\x00\x00\x00d\x00\x00\x00e\x00\x00\x00
utf8:\x09na\xC3\xAFve fa\xC3\xA7ade

  $ uniquote --xml /tmp/nf.*
ascii:	nayeeve fassodd
cp1252:	naïve façade
latin1:	naïve façade
macroman:	naïve façade
utf16:	naïve façade
utf32:	naïve façade
utf8:	naïve façade

  $ uniquote --html /tmp/nf.*
ascii:	nayeeve fassodd
cp1252:	naïve façade
latin1:	naïve façade
macroman:	naïve façade
utf16:	naïve façade
utf32:	naïve façade
utf8:	naïve façade

  $ uniquote --html --verbose /tmp/nf.*
ascii:	nayeeve fassodd
cp1252:	naïve façade
latin1:	naïve façade
macroman:	naïve façade
utf16:	naïve façade
utf32:	naïve façade
utf8:	naïve façade

  $ uniquote --backslash --encoding latin1   --verbose /tmp/nf.*
ascii:\tnayeeve fassodd
cp1252:\tna\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
latin1:\tna\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
macroman:\tna\N{MESSAGE WAITING}ve fa\N{REVERSE LINE FEED}ade
\N{LATIN SMALL LETTER THORN}\N{LATIN SMALL LETTER Y WITH DIAERESIS}\0u\0t\0f\01\06\0:\0\t\0n\0a\0\N{LATIN SMALL LETTER I WITH DIAERESIS}\0v\0e\0 \0f\0a\0\N{LATIN SMALL LETTER C WITH CEDILLA}\0a\0d\0e\0
\0\0\N{LATIN SMALL LETTER THORN}\N{LATIN SMALL LETTER Y WITH DIAERESIS}\0\0\0u\0\0\0t\0\0\0f\0\0\03\0\0\02\0\0\0:\0\0\0\t\0\0\0n\0\0\0a\0\0\0\N{LATIN SMALL LETTER I WITH DIAERESIS}\0\0\0v\0\0\0e\0\0\0 \0\0\0f\0\0\0a\0\0\0\N{LATIN SMALL LETTER C WITH CEDILLA}\0\0\0a\0\0\0d\0\0\0e\0\0\0
utf8:\tna\N{LATIN CAPITAL LETTER A WITH TILDE}\N{MACRON}ve fa\N{LATIN CAPITAL LETTER A WITH TILDE}\N{SECTION SIGN}ade

  $ uniquote --backslash --encoding cp1252   --verbose /tmp/nf.*
ascii:\tnayeeve fassodd
uniquote: cp1252 "\x8D" does not map to Unicode at /tmp/nf.macroman line 0
cp1252:\tna\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
latin1:\tna\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
\N{LATIN SMALL LETTER THORN}\N{LATIN SMALL LETTER Y WITH DIAERESIS}\0u\0t\0f\01\06\0:\0\t\0n\0a\0\N{LATIN SMALL LETTER I WITH DIAERESIS}\0v\0e\0 \0f\0a\0\N{LATIN SMALL LETTER C WITH CEDILLA}\0a\0d\0e\0
\0\0\N{LATIN SMALL LETTER THORN}\N{LATIN SMALL LETTER Y WITH DIAERESIS}\0\0\0u\0\0\0t\0\0\0f\0\0\03\0\0\02\0\0\0:\0\0\0\t\0\0\0n\0\0\0a\0\0\0\N{LATIN SMALL LETTER I WITH DIAERESIS}\0\0\0v\0\0\0e\0\0\0 \0\0\0f\0\0\0a\0\0\0\N{LATIN SMALL LETTER C WITH CEDILLA}\0\0\0a\0\0\0d\0\0\0e\0\0\0
utf8:\tna\N{LATIN CAPITAL LETTER A WITH TILDE}\N{MACRON}ve fa\N{LATIN CAPITAL LETTER A WITH TILDE}\N{SECTION SIGN}ade

  $ uniquote --backslash --encoding macroman --verbose /tmp/nf.*
ascii:\tnayeeve fassodd
cp1252:\tna\N{LATIN CAPITAL LETTER O WITH CIRCUMFLEX}ve fa\N{LATIN CAPITAL LETTER A WITH ACUTE}ade
latin1:\tna\N{LATIN CAPITAL LETTER O WITH CIRCUMFLEX}ve fa\N{LATIN CAPITAL LETTER A WITH ACUTE}ade
macroman:\tna\N{LATIN SMALL LETTER I WITH DIAERESIS}ve fa\N{LATIN SMALL LETTER C WITH CEDILLA}ade
\N{OGONEK}\N{CARON}\0u\0t\0f\01\06\0:\0\t\0n\0a\0\N{LATIN CAPITAL LETTER O WITH CIRCUMFLEX}\0v\0e\0 \0f\0a\0\N{LATIN CAPITAL LETTER A WITH ACUTE}\0a\0d\0e\0
\0\0\N{OGONEK}\N{CARON}\0\0\0u\0\0\0t\0\0\0f\0\0\03\0\0\02\0\0\0:\0\0\0\t\0\0\0n\0\0\0a\0\0\0\N{LATIN CAPITAL LETTER O WITH CIRCUMFLEX}\0\0\0v\0\0\0e\0\0\0 \0\0\0f\0\0\0a\0\0\0\N{LATIN CAPITAL LETTER A WITH ACUTE}\0\0\0a\0\0\0d\0\0\0e\0\0\0
utf8:\tna\N{SQUARE ROOT}\N{LATIN CAPITAL LETTER O WITH STROKE}ve fa\N{SQUARE ROOT}\N{LATIN SMALL LETTER SHARP S}ade

ERRORS

Errors include inaccessible files, bogus encodings, and contents that do not match a specified encoding.

BUGS

SEE ALSO

HISTORY

AUTHOR

COPYRIGHT AND LICENCE

This program is free software; you may redistribute it and/or modify it under the same terms as Perl itself.