alarsyo/spot
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

help2man: work around some utf8 issues

Browse source 
help2man used characters in the range 0x80,...,0x84 to mark special
sections/characters during its processing, but those bytes where also
occurring in other utf-8 characters breaking the output.  For instance
the character '₁' ( a subscript 1), is encoded as "0xE2 0x82 0x81" in
utf-8.

* tools/help2man: Tell perl that input and output should be assumed to
be utf-8.  Also use "private-use codepoints" for those special
characters to avoid any future conflict.
This commit is contained in:
Alexandre Duret-Lutz 2024-04-03 17:47:18 +02:00
parent 27a0137208
commit a17d8a0501
1 changed files with 25 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

46
tools/help2man
View file

@ -2,7 +2,8 @@
# Generate a short man page from --help and --version output. # Generate a short man page from --help and --version output.
# Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2009, # Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2009,
# 2010, 2011, 2012, 2013, 2014, 2015, 2016 Free Software Foundation, Inc. # 2010, 2011, 2012, 2013, 2014, 2015, 2016 Free Software Foundation, Inc.
# Later modified by the Spot authors.
# This program is free software; you can redistribute it and/or modify # This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by # it under the terms of the GNU General Public License as published by
@ -26,6 +27,9 @@ use Getopt::Long;
use Text::ParseWords qw(shellwords); use Text::ParseWords qw(shellwords);
use Text::Tabs qw(expand); use Text::Tabs qw(expand);
use POSIX qw(strftime setlocale LC_ALL); use POSIX qw(strftime setlocale LC_ALL);
use utf8;
use open IN => ":encoding(UTF-8)";
binmode STDOUT, ":encoding(UTF-8)";
my $this_program = 'help2man'; my $this_program = 'help2man';
my $this_version = '1.47.4'; my $this_version = '1.47.4';
@ -405,10 +409,10 @@ s/\n\n+/\n\n/g;
s/([A-Za-z])-\n *([A-Za-z])/$1$2/g; s/([A-Za-z])-\n *([A-Za-z])/$1$2/g;
# Temporarily exchange leading dots, apostrophes and backslashes for # Temporarily exchange leading dots, apostrophes and backslashes for
# tokens. # tokens. \xE000..\xF8FF are so called "private-use codepoints".
s/^\./\x80/mg; s/^\./\xE080/mg;
s/^'/\x81/mg; s/^'/\xE081/mg;
s/\\/\x82/g; s/\\/\xE082/g;
# Translators: patterns are used to match common program output. In the source # Translators: patterns are used to match common program output. In the source
# these strings are all of the form of "my $PAT_something = _('...');" and are # these strings are all of the form of "my $PAT_something = _('...');" and are
@ -524,7 +528,7 @@ while (length)
{ {
$matched .= $& if %append_match; $matched .= $& if %append_match;
$indent = length ($4 || "$1$3"); $indent = length ($4 || "$1$3");
$content = ".TP\n\x84$2\n\x84$5\n"; $content = ".TP\n\xE084$2\n\xE084$5\n";
unless ($4) unless ($4)
{ {
# Indent may be different on second line. # Indent may be different on second line.
@ -536,7 +540,7 @@ while (length)
elsif (s/^ {1,10}([+-]\S.*)\n//) elsif (s/^ {1,10}([+-]\S.*)\n//)
{ {
$matched .= $& if %append_match; $matched .= $& if %append_match;
$content = ".HP\n\x84$1\n"; $content = ".HP\n\xE084$1\n";
$indent = 80; # not continued $indent = 80; # not continued
} }
@ -545,7 +549,7 @@ while (length)
{ {
$matched .= $& if %append_match; $matched .= $& if %append_match;
$indent = length ($4 || "$1$3"); $indent = length ($4 || "$1$3");
$content = ".TP\n\x84$2\n\x84$5\n"; $content = ".TP\n\xE084$2\n\xE084$5\n";
} }
# Indented paragraph. # Indented paragraph.
@ -553,7 +557,7 @@ while (length)
{ {
$matched .= $& if %append_match; $matched .= $& if %append_match;
$indent = length $1; $indent = length $1;
$content = ".IP\n\x84$2\n"; $content = ".IP\n\xE084$2\n";
} }
# Left justified paragraph. # Left justified paragraph.
@ -569,7 +573,7 @@ while (length)
while ($indent ? s/^ {$indent}(\S.*)\n// : s/^(\S.*)\n//) while ($indent ? s/^ {$indent}(\S.*)\n// : s/^(\S.*)\n//)
{ {
$matched .= $& if %append_match; $matched .= $& if %append_match;
$content .= "\x84$1\n"; $content .= "\xE084$1\n";
} }
# Move to next paragraph. # Move to next paragraph.
@ -578,9 +582,9 @@ while (length)
for ($content) for ($content)
{ {
# Leading dot and apostrophe protection. # Leading dot and apostrophe protection.
s/\x84\./\x80/g; s/\xE084\./\xE080/g;
s/\x84'/\x81/g; s/\xE084'/\xE081/g;
s/\x84//g; s/\xE084//g;
# Examples should be verbatim. # Examples should be verbatim.
unless ($sect eq _('EXAMPLES')) unless ($sect eq _('EXAMPLES'))
@ -603,7 +607,7 @@ while (length)
} }
# Escape remaining hyphens. # Escape remaining hyphens.
s/-/\x83/g; s/-/\xE083/g;
if ($sect eq _('COPYRIGHT')) if ($sect eq _('COPYRIGHT'))
{ {
@ -675,6 +679,7 @@ while (my ($sect, $text) = each %replace)
# Output header. # Output header.
print <<EOT; print <<EOT;
.\\" DO NOT MODIFY THIS FILE! It was generated by $this_program $this_version. .\\" DO NOT MODIFY THIS FILE! It was generated by $this_program $this_version.
.\\" -*- coding: utf-8 -*-
.TH $PROGRAM "$section" "$date" "$source" "$manual" .TH $PROGRAM "$section" "$date" "$source" "$manual"
EOT EOT
@ -699,14 +704,13 @@ for my $sect (@pre, (grep !$filter{$_}, @sections), @post)
{ {
# Replace leading dot, apostrophe, backslash and hyphen # Replace leading dot, apostrophe, backslash and hyphen
# tokens. # tokens.
s/\x80/\\&./g; s/\xE080/\\&./g;
s/\x81/\\&'/g; s/\xE081/\\&'/g;
s/\x82/\\e/g; s/\xE082/\\e/g;
s/\x83/\\-/g; s/\xE083/\\-/g;
# Convert some latin1 chars to troff equivalents # Convert some latin1 chars to troff equivalents
s/\xa0/\\ /g; # non-breaking space s/\xA0/\\ /g; # non-breaking space
print enc $_; print enc $_;
} }
} }
@ -756,7 +760,7 @@ sub convert_option
{ {
local $_ = '\fB' . shift; local $_ = '\fB' . shift;
s/-/\x83/g; s/-/\xE083/g;
if (s/\[=(.*)\]$/\\fR[=\\fI$1\\fR]/) if (s/\[=(.*)\]$/\\fR[=\\fI$1\\fR]/)
{ {
s/\|/\\fR|\\:\\fI/g; s/\|/\\fR|\\:\\fI/g;