badwords: check indented lines in source code, fix fallouts

- badwords.pl: add `-a` option to check all lines in source code files.
  Before this patch indented lines were skipped (to avoid Markdown code
  fences.)
- GHA/checksrc: use `-a` when verifying the source code.
- GHA/checksrc: disable `So` and `But` rules for source code.
- GHA/checksrc: add docs/examples to the verified sources.
- badwords.txt: delete 4 duplicates.
- badwords.txt: group and sort contractions.
- badwords.txt: allow ` url = `, `DIR`, `<file name`.

Closes #19536

.github/scripts/badwords.pl

@@ -20,7 +20,12 @@ use warnings;
 my @whitelist;
 my %alt;
 my %exactcase;
+my $skip_indented = 1;
 
+if($ARGV[0] eq "-a") {
+    shift @ARGV;
+    $skip_indented = 0;
+}
 my %wl;
 if($ARGV[0] eq "-w") {
     shift @ARGV;
@@ -68,7 +73,7 @@ sub file {
         my $in = $_;
         $l++;
         chomp $in;
-        if($in =~ /^    /) {
+        if($skip_indented && $in =~ /^    /) {
             next;
         }
         # remove the link part

.github/scripts/badwords.txt

@@ -10,59 +10,56 @@ tool chain:toolchain
 tool-chain:toolchain
 wild-card:wildcard
 wild card:wildcard
+\bit's:it is
+aren't:are not
+can't:cannot
+could've:could have
+couldn't:could not
+didn't:did not
+doesn't:does not
+don't=do not
 i'm:I am
-you've:You have
-we've:we have
-we're:we are
-we'll:we will
-we'd:we would
-they've:They have
-they're:They are
-they'll:They will
+isn't:is not
+it'd:it would
+should've:should have
+that's:that is
+there's:there is
 they'd:They would
-you've:you have
+they'll:They will
+they're:They are
+they've:They have
+we'd:we would
+we'll:we will
+we're:we are
+we've:we have
+won't:will not
 you'd:you would
 you'll:you will
 you're:you are
-should've:should have
-don't=do not
-could've:could have
-doesn't:does not
-isn't:is not
-aren't:are not
+you've:you have
  a html: an html
  a http: an http
  a ftp: an ftp
  a IPv4: an IPv4
  a IPv6: an IPv6
- url =URL
+ url [^=]=URL
 [^/]internet\b=Internet
 isation:ization
-\bit's:it is
-it'd:it would
-there's:there is
 [^.]\. And: Rewrite it somehow?
 ^(And|So|But) = Rewrite it somehow?
 \. But: Rewrite it somehow?
 \. So : Rewrite without "so" ?
- dir [^=]:directory
+ dir [^=]=directory
+ 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
 \bpass phrase:passphrase
-didn't:did not
-doesn't:does not
-won't:will not
-couldn't:could not
 \bwill\b:rewrite to present tense
 \b32bit=32-bit
 \b64bit=64-bit

.github/workflows/checksrc.yml

@@ -174,6 +174,7 @@ jobs:
       - name: 'yamlcheck'
         run: .github/scripts/yamlcheck.sh
 
-      # we allow some extra in source code
       - name: 'badwords'
-        run: grep -Ev '(\\bwill)' .github/scripts/badwords.txt | .github/scripts/badwords.pl src lib include
+        run: |
+          # we allow some extra in source code
+          grep -Ev '(\\bwill| But: | So : )' .github/scripts/badwords.txt | .github/scripts/badwords.pl -a src lib include docs/examples