--- unicode.orig/./debian/control	2023-06-03 02:42:31.349236466 +0300
+++ unicode.upd/./debian/control	2022-06-03 17:20:02.000000000 +0300
@@ -2,12 +2,13 @@ Source: unicode
 Section: utils
 Priority: optional
 Maintainer: Radovan Garabík <garabik@kassiopeia.juls.savba.sk>
-Build-Depends: debhelper (>= 4), dh-python
+Build-Depends: debhelper (>= 4), dh-python, python3
 Standards-Version: 4.3.0
 
 Package: unicode
 Architecture: all
 Depends: ${misc:Depends}, ${python3:Depends}
+Suggests: bzip2
 Recommends: unicode-data
 Description: display unicode character properties
  unicode is a simple command line utility that displays
--- unicode.orig/./debian/copyright	2023-06-03 02:42:31.349236466 +0300
+++ unicode.upd/./debian/copyright	2022-06-03 17:20:02.000000000 +0300
@@ -7,5 +7,5 @@ The sources and package can be downloade
 http://kassiopeia.juls.savba.sk/~garabik/software/unicode/
 
 
-Copyright: © 2003-2016 Radovan Garabík <garabik @ kassiopeia.juls.savba.sk>
+Copyright: © 2003-2022 Radovan Garabík <garabik @ kassiopeia.juls.savba.sk>
 released under GPL v3, see /usr/share/common-licenses/GPL
--- unicode.orig/./debian/changelog	2023-06-03 02:42:31.349236466 +0300
+++ unicode.upd/./debian/changelog	2022-06-03 17:20:02.000000000 +0300
@@ -1,3 +1,18 @@
+unicode (2.9-1) unstable; urgency=low
+
+  * better protection against changed/corrpupted data files (closes: #932846)
+
+ -- Radovan Garabík <garabik@kassiopeia.juls.savba.sk  Fri, 03 Jun 2022 16:09:26 +0200
+
+unicode (2.8-1) unstable; urgency=low
+
+  * display ASCII table (either traditional or the EU–UK Trade and Cooperation
+    Agreement version)
+  * tidy up manpage (closes: #972047) (closes:#972063)
+  * fix decoding paracode arguments (closes: #939196)
+
+ -- Radovan Garabík <garabik@kassiopeia.juls.savba.sk>  Wed, 30 Dec 2020 17:13:32 +0100
+
 unicode (2.7-1) unstable; urgency=low
 
   * add East Asian width
--- unicode.orig/./paracode.1	2023-06-03 02:42:31.350236467 +0300
+++ unicode.upd/./paracode.1	2022-06-03 17:20:02.000000000 +0300
@@ -4,46 +4,47 @@
 paracode \- command line Unicode conversion tool
 .SH SYNOPSIS
 .B paracode
-.RI [ -t tables ] 
+.RB [ \-t
+.IR tables ]
 string
 .SH DESCRIPTION
 This manual page documents the
 .B paracode
 command.
 .PP
-\fBparacode\fP exploits the full power of the Unicode standard to convert the text
-into visually similar stream of glyphs, while using completely different codepoints.
-It is an excellent didactic tool demonstrating the principles and advanced use of
-the Unicode standard.
+\fBparacode\fP exploits the full power of the Unicode standard to convert
+the text into visually similar stream of glyphs, while using completely
+different codepoints.
+It is an excellent didactic tool demonstrating the principles and advanced
+use of the Unicode standard.
 .PP
 \fBparacode\fP is a command line tool working as
 a filter, reading standard input in UTF-8 encoding and writing to
 standard output.
-
+.
 .SH OPTIONS
 .TP
 .BI \-t tables
-.BI \-\-tables
+.BI \-\-tables tables
 
 Use given list of conversion tables, separated by a plus sign.
 
 Special name 'all' selects all the tables.
 
-Note that selecting 'other', 'cyrillic_plus' and 'cherokee' tables (and 'all') 
+Note that selecting 'other', 'cyrillic_plus' and 'cherokee' tables (and 'all')
 makes use of rather esoteric characters, and not all fonts contain them.
 
-
 Special table 'mirror' uses quite different character substitution,
 is not selected automatically with 'all' and does not work well
 with anything except plain ascii alphabetical characters.
 
 Example:
 
-paracode -t cyrillic+greek+cherokee
+paracode \-t cyrillic+greek+cherokee
 
-paracode -t cherokee  <input >output
+paracode \-t cherokee  <input >output
 
-paracode -r -t mirror  <input >output
+paracode \-r \-t mirror  <input >output
 
 
 
@@ -60,16 +61,16 @@ other
 cherokee
 
 all
-
+.
 .TP
-.BI \-r
-
-Display text in reverse order after conversion, best used together with -t mirror.
+.B \-r
 
+Display text in reverse order after conversion,
+best used together with \-t mirror.
+.
 .SH SEE ALSO
-iconv(1)
-
-
+.BR iconv (1)
+.
 .SH AUTHOR
 Radovan Garab\('ik <garabik @ kassiopeia.juls.savba.sk>
 
--- unicode.orig/./unicode.1	2023-06-03 02:42:31.351236467 +0300
+++ unicode.upd/./unicode.1	2022-06-03 17:20:02.000000000 +0300
@@ -4,7 +4,7 @@
 unicode \- command line unicode database query tool
 .SH SYNOPSIS
 .B unicode
-.RI [ options ] 
+.RI [ options ]
 string
 .SH DESCRIPTION
 This manual page documents the
@@ -15,76 +15,76 @@ command.
 
 .SH OPTIONS
 .TP
-.BI \-h 
-.BI \-\-help 
+.B \-h
+.B \-\-help
 
 Show help and exit.
 
 .TP
-.BI \-x
-.BI \-\-hexadecimal
+.B \-x
+.B \-\-hexadecimal
 
-Assume 
+Assume
 .I string
-to be a hexadecimal number 
+to be a hexadecimal number
 
 .TP
-.BI \-d
-.BI \-\-decimal
+.B \-d
+.B \-\-decimal
 
-Assume 
+Assume
 .I string
-to be a decimal number 
+to be a decimal number
 
 .TP
-.BI \-o
-.BI \-\-octal
+.B \-o
+.B \-\-octal
 
-Assume 
+Assume
 .I string
-to be an octal number 
+to be an octal number
 
 .TP
-.BI \-b
-.BI \-\-binary
+.B \-b
+.B \-\-binary
 
-Assume 
+Assume
 .I string
-to be a binary number 
+to be a binary number
 
 .TP
-.BI \-r
-.BI \-\-regexp
+.B \-r
+.B \-\-regexp
 
-Assume 
+Assume
 .I string
 to be a regular expression
 
 .TP
-.BI \-s
-.BI \-\-string
+.B \-s
+.B \-\-string
 
-Assume 
+Assume
 .I string
 to be a sequence of characters
 
 .TP
-.BI \-a
-.BI \-\-auto
+.B \-a
+.B \-\-auto
 
 Try to guess type of
 .I string
 from one of the above (default)
 
 .TP
-.BI \-mMAXCOUNT
-.BI \-\-max=MAXCOUNT
+.BI \-m MAXCOUNT
+.BI \-\-max= MAXCOUNT
 
 Maximal number of codepoints to display, default: 20; use 0 for unlimited
 
 .TP
-.BI \-iCHARSET
-.BI \-\-io=IOCHARSET
+.BI \-i CHARSET
+.BI \-\-io= IOCHARSET
 
 I/O character set. For maximal pleasure, run \fBunicode\fP on UTF-8
 capable terminal and specify IOCHARSET to be UTF-8. \fBunicode\fP
@@ -92,8 +92,8 @@ tries to guess this value from your loca
 locale, you should not need to specify it.
 
 .TP
-.BI \-\-fcp=CHARSET
-.BI \-\-fromcp=CHARSET
+.BI \-\-fcp= CHARSET
+.BI \-\-fromcp= CHARSET
 
 Convert numerical arguments from this encoding, default: no conversion.
 Multibyte encodings are supported. This is ignored for non-numerical
@@ -101,19 +101,19 @@ arguments.
 
 
 .TP
-.BI \-cADDCHARSET
-.BI \-\-charset\-add=ADDCHARSET
+.BI \-c ADDCHARSET
+.BI \-\-charset\-add= ADDCHARSET
 
 Show hexadecimal reprezentation of displayed characters in this additional charset.
 
 .TP
-.BI \-CUSE_COLOUR
-.BI \-\-colour=USE_COLOUR
+.BI \-C USE_COLOUR
+.BI \-\-colour= USE_COLOUR
 
 USE_COLOUR is one of
-.I on
-.I off
-.I auto
+.B on
+.B off
+.B auto
 
 .B \-\-colour=on
 will use ANSI colour codes to colourise the output
@@ -121,50 +121,66 @@ will use ANSI colour codes to colourise
 .B \-\-colour=off
 won't use colours.
 
-.B \-\-colour=auto 
+.B \-\-colour=auto
 will test if standard output is a tty, and use colours only when it is.
 
-.BI \-\-color
+.B \-\-color
 is a synonym of
-.BI \-\-colour
+.B \-\-colour
 
 .TP
-.BI \-v
-.BI \-\-verbose
+.B \-v
+.B \-\-verbose
 
 Be more verbose about displayed characters, e.g. display Unihan information, if available.
 
 .TP
-.BI \-w
-.BI \-\-wikipedia
+.B \-w
+.B \-\-wikipedia
 
 Spawn browser pointing to English Wikipedia entry about the character.
 
 .TP
-.BI \-\-wt
-.BI \-\-wiktionary
+.B \-\-wt
+.B \-\-wiktionary
 
 Spawn browser pointing to English Wiktionary entry about the character.
 
 .TP
-.BI \-\-brief
+.B \-\-brief
 
 Display character information in brief format
 
 .TP
-.BI \-\-format=fmt
+.BI \-\-format= fmt
 
 Use your own format for character information display. See the README for details.
 
-
 .TP
-.BI \-\-list
+.B \-\-list
 
 List (approximately) all known encodings.
 
+.TP
+.B \-\-download
+
+Try to download UnicodeData.txt into ~/.unicode/
+
+.TP
+.B \-\-ascii
+
+Display ASCII table
+
+.TP
+.B \-\-brexit\-ascii
+.B \-\-brexit
+
+Display ASCII table (EU–UK Trade and Cooperation Agreement 2020 version)
+
+
 .SH USAGE
 
-\fBunicode\fP tries to guess the type of an argument. In particular, 
+\fBunicode\fP tries to guess the type of an argument. In particular,
 if the arguments looks like a valid hexadecimal representation of a
 Unicode codepoint, it will be considered to be such. Using
 
@@ -174,7 +190,7 @@ will display information about U+FACE CJ
 and it will not search for 'face' in character descriptions \- for the latter,
 use:
 
-\fBunicode\fP -r face
+\fBunicode\fP \-r face
 
 
 For example, you can use any of the following to display information
@@ -191,26 +207,26 @@ about  U+00E1 LATIN SMALL LETTER A WITH
 
 You can specify a range of characters as argumets, \fBunicode\fP will
 show these characters in nice tabular format, aligned to 256-byte boundaries.
-Use two dots ".." to indicate the range, e.g. 
+Use two dots ".." to indicate the range, e.g.
 
 \fBunicode\fP 0450..0520
 
 will display the whole cyrillic and hebrew blocks (characters from U+0400 to U+05FF)
 
-\fBunicode\fP 0400.. 
+\fBunicode\fP 0400..
 
 will display just characters from U+0400 up to U+04FF
 
-Use --fromcp to query codepoints from other encodings:
+Use \-\-fromcp to query codepoints from other encodings:
 
-\fBunicode\fP --fromcp cp1250 -d 200
+\fBunicode\fP \-\-fromcp cp1250 \-d 200
 
 Multibyte encodings are supported:
-\fBunicode\fP --fromcp big5 -x aff3
+\fBunicode\fP \-\-fromcp big5 \-x aff3
 
 and multi-char strings are supported, too:
 
-\fBunicode\fP --fromcp utf-8 -x c599c3adc5a5
+\fBunicode\fP \-\-fromcp utf-8 \-x c599c3adc5a5
 
 .SH BUGS
 Tabular format does not deal well with full-width, combining, control
--- unicode.orig/./unicode	2023-06-03 02:42:31.350236467 +0300
+++ unicode.upd/./unicode	2022-06-03 17:20:02.000000000 +0300
@@ -1,9 +1,10 @@
 #!/usr/bin/python3
 
-from __future__ import unicode_literals
+from __future__ import unicode_literals, print_function
 
-import os, glob, sys, unicodedata, locale, gzip, re, traceback, encodings, io, codecs
+import os, glob, sys, unicodedata, locale, gzip, re, traceback, encodings, io, codecs, shutil
 import webbrowser, textwrap, struct
+
 #from pprint import pprint
 
 # bz2 was introduced in 2.3, but we want this to work even if for some
@@ -31,6 +32,7 @@ if PY3:
     import subprocess as cmd
     from urllib.parse import quote as urlquote
     import io
+    from urllib.request import urlopen
 
     def out(*args):
         "pring args, converting them to output charset"
@@ -50,6 +52,7 @@ else: # python2
     import commands as cmd
 
     from urllib import quote as urlquote
+    from urllib import urlopen
 
     def out(*args):
         "pring args, converting them to output charset"
@@ -66,7 +69,7 @@ else: # python2
 
 from optparse import OptionParser
 
-VERSION='2.7'
+VERSION='2.9'
 
 
 # list of terminals that support bidi
@@ -230,9 +233,10 @@ def get_unicode_blocks_descriptions():
     for line in f:
         if line.startswith('#') or ';' not in line or '..' not in line:
             continue
-        ran, desc = line.split(';')
+        spl = line.split(';', 1)
+        ran, desc = spl
         desc = desc.strip()
-        low, high = ran.split('..')
+        low, high = ran.split('..', 1)
         low = int(low, 16)
         high = int(high, 16)
         unicodeblocks[ (low,high) ] = desc
@@ -256,7 +260,8 @@ def get_unicode_properties(ch):
         proplist = ['codepoint', 'name', 'category', 'combining', 'bidi', 'decomposition', 'dummy', 'digit_value', 'numeric_value', 'mirrored', 'unicode1name', 'iso_comment', 'uppercase', 'lowercase', 'titlecase']
         for i, prop in enumerate(proplist):
             if prop!='dummy':
-                properties[prop] = fields[i]
+                if i<len(fields):
+                    properties[prop] = fields[i]
         if properties['lowercase']:
             properties['lowercase'] = chr(int(properties['lowercase'], 16))
         if properties['uppercase']:
@@ -330,9 +335,12 @@ def get_unihan_properties_internal(ch):
             line = l.strip()
             if not line:
                 continue
-            char, key, value = line.strip().split('\t')
+            spl = line.strip().split('\t')
+            if len(spl) != 3:
+                continue
+            char, key, value = spl
             if int(char[2:], 16) == ch:
-                properties[key] = value.decode('utf-8')
+                properties[key] = value
             elif int(char[2:], 16)>ch:
                 break
     return properties
@@ -412,6 +420,41 @@ def OpenGzip(fname):
         fo = codecs.getreader('utf-8')(fo)
         return fo
 
+def get_unicode_cur_version():
+    # return current version of the Unicode standard, hardwired for now
+    return '14.0.0'
+
+def get_unicodedata_url():
+    unicode_version = get_unicode_cur_version()
+    url = 'http://www.unicode.org/Public/{}/ucd/UnicodeData.txt'.format(unicode_version)
+    return url
+
+def download_unicodedata():
+    url = get_unicodedata_url()
+    out('Downloading UnicodeData.txt from ', url, '\n')
+    HomeDir = os.path.expanduser('~/.unicode')
+    HomeUnicodeData = os.path.join(HomeDir, "UnicodeData.txt.gz")
+
+    # we want to minimize the chance of leaving a corrupted file around
+    tmp_file = HomeUnicodeData+'.tmp'
+    try:
+        if not os.path.exists(HomeDir):
+            os.makedirs(HomeDir)
+        response = urlopen(url)
+        r = response.getcode()
+        if r != 200:
+            # this is handled automatically in python3, the exception will be raised by urlopen
+            raise IOError('HTTP response code '+str(r))
+        if os.path.exists(HomeUnicodeData):
+            out(HomeUnicodeData, ' already exists, but downloading as requested\n')
+        out('downloading...')
+        shutil.copyfileobj(response, gzip.open(tmp_file, 'wb'))
+        shutil.move(tmp_file, HomeUnicodeData)
+        out(HomeUnicodeData, ' downloaded\n')
+    finally:
+        if os.path.exists(tmp_file):
+            os.remove(tmp_file)
+
 def GrepInNames(pattern, prefill_cache=False):
     f = None
     for name in UnicodeDataFileNames:
@@ -428,10 +471,12 @@ def GrepInNames(pattern, prefill_cache=F
 Cannot find UnicodeData.txt, please place it into
 /usr/share/unidata/UnicodeData.txt,
 /usr/share/unicode/UnicodeData.txt, ~/.unicode/ or current
-working directory (optionally you can gzip it).
+working directory (optionally you can gzip, bzip2 or xz it).
 Without the file, searching will be much slower.
 
-""" )
+You can donwload the file from {} (or replace {} with current Unicode version); or run {} --download
+
+""".format(get_unicodedata_url(), get_unicode_cur_version(), sys.argv[0]))
 
     if prefill_cache:
         if f:
@@ -635,7 +680,8 @@ def print_characters(clist, maxcount, fo
         if maxcount:
             counter += 1
         if counter > options.maxcount:
-            out("\nToo many characters to display, more than %s, use --max 0 (or other value) option to change it\n" % options.maxcount)
+            sys.stdout.flush()
+            sys.stderr.write("\nToo many characters to display, more than %s, use --max 0 (or other value) option to change it\n" % options.maxcount)
             return
         properties = get_unicode_properties(c)
         ordc = ord(c)
@@ -809,6 +855,49 @@ def is_range(s, typ):
 def unescape(s):
     return s.replace(r'\n', '\n')
 
+ascii_cc_names = ('NUL', 'SOH', 'STX', 'ETX', 'EOT', 'ENQ', 'ACK', 'BEL', 'BS', 'HT', 'LF', 'VT', 'FF', 'CR', 'SO', 'SI', 'DLE', 'DC1', 'DC2', 'DC3', 'DC4', 'NAK', 'SYN', 'ETB', 'CAN', 'EM', 'SUB', 'ESC', 'FS', 'GS', 'RS', 'US')
+
+def display_ascii_table():
+    print('Dec Hex    Dec Hex    Dec Hex  Dec Hex  Dec Hex  Dec Hex   Dec Hex   Dec Hex')
+    for row in range(0, 16):
+        for col in range(0, 8):
+            cp = 16*col+row
+            ch = chr(cp) if 32<=cp else ascii_cc_names[cp]
+            ch = 'DEL' if cp==127 else ch
+            frm = '{:3d} {:02X} {:2s}'
+            if cp < 32:
+                frm = '{:3d} {:02X} {:4s}'
+            elif cp >= 96:
+                frm = '{:4d} {:02X} {:2s}'
+            cell = frm.format(cp, cp, ch)
+            print(cell, end='')
+        print()
+
+brexit_ascii_diffs = {
+ 30: ' ',
+ 31: ' ',
+ 34: "'",
+123: '{}{',
+125: '}}',
+127: ' ',
+128: ' ',
+129: ' ',
+        }
+
+def display_brexit_ascii_table():
+    print(' + | 0    1    2    3    4    5    6    7    8    9')
+    print('---+-----------------------------------------------')
+    for row in range(30, 130, 10):
+        print('{:3d}'.format(row), end='|')
+        for col in range(0, 10):
+            cp = col+row
+            ch = brexit_ascii_diffs.get(cp, chr(cp))
+            cell = ' {:3s} '.format(ch)
+            print(cell, end='')
+        print()
+
+
+
 format_string_default = '''{yellow}{bold}U+{ordc:04X} {name}{default}
 {green}UTF-8:{default} {utf8} {green}UTF-16BE:{default} {utf16be} {green}Decimal:{default} {decimal} {green}Octal:{default} {octal}{opt_additional}
 {pchar}{opt_flipcase}{opt_uppercase}{opt_lowercase}
@@ -880,10 +969,22 @@ def main():
           action="store", dest="format_string", type="string",
           default=format_string_default,
           help="formatting string")
-    parser.add_option("--brief", "--terse",
+    parser.add_option("--brief", "--terse", "--br",
           action="store_const", dest="format_string",
           const='{pchar} U+{ordc:04X} {name}\n',
           help="Brief format")
+    parser.add_option("--download",
+          action="store_const", dest="download_unicodedata",
+          const=True,
+          help="Try to dowload UnicodeData.txt")
+    parser.add_option("--ascii",
+          action="store_const", dest="ascii_table",
+          const=True,
+          help="Display ASCII table")
+    parser.add_option("--brexit-ascii", "--brexit",
+          action="store_const", dest="brexit_ascii_table",
+          const=True,
+          help="Display ASCII table (EU-UK Trade and Cooperation Agreement version)")
 
     global options
     (options, arguments) = parser.parse_args()
@@ -899,6 +1000,18 @@ def main():
         print (textwrap.fill(' '.join(all_encodings)))
         sys.exit()
 
+    if options.ascii_table:
+        display_ascii_table()
+        sys.exit()
+
+    if options.brexit_ascii_table:
+        display_brexit_ascii_table()
+        sys.exit()
+
+    if options.download_unicodedata:
+        download_unicodedata()
+        sys.exit()
+
     if len(arguments)==0:
         parser.print_help()
         sys.exit()
--- unicode.orig/./setup.py	2023-06-03 02:42:31.350236467 +0300
+++ unicode.upd/./setup.py	2022-06-03 17:20:02.000000000 +0300
@@ -8,7 +8,7 @@ os.chdir(os.path.abspath(os.path.dirname
 
 
 setup(name='unicode',
-      version='2.7',
+      version='2.8',
       scripts=['unicode', 'paracode'],
 #      entry_points={'console_scripts': [
 #          'unicode = unicode:main',
--- unicode.orig/./paracode	2023-06-03 02:42:31.350236467 +0300
+++ unicode.upd/./paracode	2022-06-03 17:20:02.000000000 +0300
@@ -201,7 +201,7 @@ def main():
     (options, args) = parser.parse_args()
 
     if args:
-        to_convert = ' '.join(args).decode('utf-8')
+        to_convert = decode(' '.join(args), 'utf-8')
     else:
         to_convert = None
 
--- unicode.orig/./README	2023-06-03 02:42:31.349236466 +0300
+++ unicode.upd/./README	2022-06-03 17:20:02.000000000 +0300
@@ -4,7 +4,7 @@ To use unicode utility, you need:
  - python >=2.6 (str format() method is needed), preferrably wide
    unicode build, however, python3 is recommended
  - python optparse library (part of since python2.3)
- - UnicodeData.txt file (http://www.unicode.org/Public) which
+ - UnicodeData.txt file (http://www.unicode.org/Public/13.0.0/ucd/UnicodeData.txt; or replace 13.0.0 with current Unicode version) which
    you should put into /usr/share/unicode/, ~/.unicode/ or current
    working directory.
     - apt-get install unicode-data  # Debian