badwords: re-sync with curl-www, fix issues found

Also:
- replace `manpage` with `man page`, add to `badwords.txt`.
- badwords.pl: import `-w` feature from curl-www, syncing the two
  scripts fully.
- badwords.txt: import missing items from curl-www, syncing the two
  files fully.
- pyspelling.words: drop `cURL` allowed word.

Closes #19468

.github/scripts/badwords.pl

@@ -21,6 +21,24 @@ my @whitelist;
 my %alt;
 my %exactcase;
 
+my %wl;
+if($ARGV[0] eq "-w") {
+    shift @ARGV;
+    my $file = shift @ARGV;
+    open(W, "<$file");
+    while(<W>) {
+        if(/^#/) {
+            # allow #-comments
+            next;
+        }
+        if(/^([^:]*):(\d+):(.*)/) {
+            $wl{"$1:$2:$3"}=1;
+            #print STDERR "whitelisted $1:$2:$3\n";
+        }
+    }
+    close(W);
+}
+
 my @w;
 while(<STDIN>) {
     chomp;
@@ -30,7 +48,7 @@ while(<STDIN>) {
     if($_ =~ /^---(.*)/) {
         push @whitelist, $1;
     }
-    elsif($_ =~ /^([^:=]*)([:=])(.*)/) {
+    elsif($_ =~ /^(.*)([:=])(.*)/) {
         my ($bad, $sep, $better)=($1, $2, $3);
         push @w, $bad;
         $alt{$bad} = $better;
@@ -67,6 +85,14 @@ sub file {
                ($in =~ /^(.*)$w/ && $case) ) {
                 my $p = $1;
                 my $c = length($p)+1;
+
+                my $ch = "$f:$l:$w";
+                if($wl{$ch}) {
+                    # whitelisted
+                    print STDERR "$ch found but whitelisted\n";
+                    next;
+                }
+
                 print STDERR  "$f:$l:$c: error: found bad word \"$w\"\n";
                 printf STDERR " %4d | $in\n", $l;
                 printf STDERR "      | %*s^%s\n", length($p), " ",

.github/scripts/badwords.txt

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: curl
 #
 back-end:backend
-e-mail:email
+\be-mail[^/]:email
 run-time:runtime
 set-up:setup
 tool chain:toolchain
@@ -36,7 +36,7 @@ aren't:are not
  a IPv4: an IPv4
  a IPv6: an IPv6
  url =URL
-internet\b=Internet
+[^/]internet\b=Internet
 isation:ization
 \bit's:it is
 it'd:it would
@@ -47,12 +47,14 @@ there's:there is
 \. So : Rewrite without "so" ?
  dir :directory
 sub-director:subdirector
+you'd:you would
+you'll:you will
 can't:cannot
 that's:that is
 web page:webpage
 host name\b:hostname
 host names\b:hostnames
-file name\b:filename
+[^;]file name\b:filename
 file names\b:filenames
 \buser name\b:username
 \buser names\b:usernames
@@ -70,7 +72,11 @@ couldn't:could not
 32-bits:32 bits or 32-bit
 \bvery\b:rephrase using an alternative word
 \bCurl\b=curl
+\bcURL\b=curl
 \bLibcurl\b=libcurl
+\bLibCurl\b=libcurl
 ---WWW::Curl
 ---NET::Curl
 ---Curl Corporation
+\bmanpages[^./&:-]:man pages
+\bmanpage[^si./&:-]:man page

.github/scripts/pyspelling.words

@@ -149,7 +149,6 @@ CSeq
 csh
 cshrc
 CTRL
-cURL
 CURLcode
 curldown
 CURLE