Resolve conf

.github/scripts/badwords.pl

@@ -20,6 +20,29 @@
 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;
+    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>) {
@@ -30,7 +53,7 @@
     if($_ =~ /^---(.*)/) {
         push @whitelist, $1;
     }
-    elsif($_ =~ /^([^:=]*)([:=])(.*)/) {
+    elsif($_ =~ /^(.*)([:=])(.*)/) {
         my ($bad, $sep, $better)=($1, $2, $3);
         push @w, $bad;
         $alt{$bad} = $better;
@@ -50,7 +73,7 @@ sub file {
         my $in = $_;
         $l++;
         chomp $in;
-        if($in =~ /^    /) {
+        if($skip_indented && $in =~ /^    /) {
             next;
         }
         # remove the link part
@@ -67,8 +90,16 @@ sub file {
                ($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 " %4d | %s\n", $l, $in;
                 printf STDERR "      | %*s^%s\n", length($p), " ",
                     "~" x (length($w)-1);
                 printf STDERR " maybe use \"%s\" instead?\n", $alt{$w};
@@ -79,9 +110,11 @@ sub file {
     close(F);
 }
 
-my @files = @ARGV;
-
-foreach my $each (@files) {
+my @filemasks = @ARGV;
+open(my $git_ls_files, '-|', 'git', 'ls-files', '--', @filemasks) or die "Failed running git ls-files: $!";
+while(my $each = <$git_ls_files>) {
+    chomp $each;
     file($each);
 }
+close $git_ls_files;
 exit $errors;

.github/scripts/badwords.txt

@@ -3,64 +3,63 @@
 # SPDX-License-Identifier: curl
 #
 back-end:backend
-e-mail:email
+\be-mail[^/]:email
 run-time:runtime
 set-up:setup
 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
-internet\b=Internet
+ 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
-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
@@ -70,7 +69,11 @@ 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/cleancmd.pl

@@ -119,6 +119,10 @@ sub process {
     }
 }
 
-for my $f (@ARGV) {
+my @filemasks = @ARGV;
+open(my $git_ls_files, '-|', 'git', 'ls-files', '--', @filemasks) or die "Failed running git ls-files: $!";
+while(my $f = <$git_ls_files>) {
+    chomp $f;
     process($f);
 }
+close $git_ls_files;

.github/scripts/codespell.sh

@@ -7,7 +7,7 @@ set -eu
 
 cd "$(dirname "${0}")"/../..
 
-# shellcheck disable=SC2046
+git ls-files -z | xargs -0 -r \
 codespell \
   --skip '.github/scripts/pyspelling.words' \
   --skip '.github/scripts/typos.toml' \
@@ -16,4 +16,4 @@ codespell \
   --skip 'scripts/wcurl' \
   --ignore-regex '.*spellchecker:disable-line' \
   --ignore-words '.github/scripts/codespell-ignore.words' \
-  $(git ls-files)
+  --

.github/scripts/pyspelling.words

@@ -149,7 +149,6 @@ CSeq
 csh
 cshrc
 CTRL
-cURL
 CURLcode
 curldown
 CURLE
@@ -245,6 +244,7 @@ et
 etag
 ETag
 ETags
+exa
 exe
 executables
 EXPN
@@ -418,6 +418,7 @@ kerberos
 Keychain
 keychain
 KiB
+kibibyte
 kickstart
 Kirei
 Knauf
@@ -492,6 +493,7 @@ Mavrogiannopoulos
 Mbed
 mbedTLS
 md
+mebibyte
 Meglio
 memdebug
 MesaLink

.github/scripts/shellcheck.sh

@@ -3,7 +3,11 @@
 #
 # SPDX-License-Identifier: curl
 
-# shellcheck disable=SC2046
-shellcheck --exclude=1091 \
+set -eu
+
+cd "$(dirname "${0}")"/../..
+
+git grep -z -l -E '^#!(/usr/bin/env bash|/bin/sh|/bin/bash)' | xargs -0 -r \
+shellcheck --exclude=1091,2248 \
   --enable=avoid-nullary-conditions,deprecate-which \
-  $(grep -l -E '^#!(/usr/bin/env bash|/bin/sh|/bin/bash)' $(git ls-files))
+  --

.github/scripts/spacecheck.pl

@@ -88,11 +88,11 @@ sub eol_detect {
 
 my $issues = 0;
 
-open my $git_ls_files, '-|', 'git ls-files' or die "Failed running git ls-files: $!";
+open(my $git_ls_files, '-|', 'git ls-files') or die "Failed running git ls-files: $!";
 while(my $filename = <$git_ls_files>) {
     chomp $filename;
 
-    open my $fh, '<', $filename or die "Cannot open '$filename': $!";
+    open(my $fh, '<', $filename) or die "Cannot open '$filename': $!";
     my $content = do { local $/; <$fh> };
     close $fh;
 

.github/scripts/yamlcheck.sh

@@ -5,9 +5,11 @@
 
 set -eu
 
-# shellcheck disable=SC2046
+cd "$(dirname "${0}")"/../..
+
+git ls-files '*.yaml' '*.yml' -z | xargs -0 -r \
 yamllint \
   --format standard \
   --strict \
-  --config-data "$(dirname "$0")/yamlcheck.yaml" \
-  $(git ls-files '*.yaml' '*.yml')
+  --config-data .github/scripts/yamlcheck.yaml \
+  --

.github/workflows/checkdocs.yml

@@ -14,6 +14,7 @@ name: 'Docs'
       - '*/ci'
     paths:
       - '.github/workflows/checkdocs.yml'
+      - '.github/scripts/**'
       - '.github/scripts/mdlinkcheck'
       - '/scripts/**'
       - '**.md'
@@ -25,6 +26,7 @@ name: 'Docs'
       - '.github/workflows/checkdocs.yml'
       - '.github/scripts/**'
       - '.github/scripts/mdlinkcheck'
+      - '/scripts/**'
       - '**.md'
       - 'docs/*'
 
@@ -66,10 +68,10 @@ jobs:
   #          JSON
   #
   #      - name: 'trim headers off all *.md files'
-  #        run: git ls-files -z '*.md' | xargs -0 -n1 .github/scripts/trimmarkdownheader.pl
+  #        run: git ls-files '*.md' -z | xargs -0 -n1 .github/scripts/trimmarkdownheader.pl
   #
   #      - name: 'check prose'
-  #        run: git ls-files -z '*.md' | grep -Evz 'CHECKSRC\.md|DISTROS\.md|curl_mprintf\.md|CURLOPT_INTERFACE\.md|interface\.md' | xargs -0 proselint -- README
+  #        run: git ls-files '*.md' -z | grep -Evz 'CHECKSRC\.md|DISTROS\.md|curl_mprintf\.md|CURLOPT_INTERFACE\.md|interface\.md' | xargs -0 proselint -- README
   #
   #      # This is for CHECKSRC and files with aggressive exclamation mark needs
   #      - name: 'create second proselint config'
@@ -109,9 +111,7 @@ jobs:
           persist-credentials: false
 
       - name: 'trim all *.md files in docs/'
-        run: |
-          # shellcheck disable=SC2046
-          .github/scripts/cleancmd.pl $(find docs -name '*.md')
+        run: .github/scripts/cleancmd.pl 'docs/*.md'
 
       - name: 'install'
         run: |
@@ -140,9 +140,7 @@ jobs:
           persist-credentials: false
 
       - name: 'badwords'
-        run: |
-          # shellcheck disable=SC2046
-          .github/scripts/badwords.pl < .github/scripts/badwords.txt $(git ls-files '**.md') docs/TODO docs/KNOWN_BUGS packages/OS400/README.OS400
+        run: .github/scripts/badwords.pl '**.md' docs/TODO docs/KNOWN_BUGS packages/OS400/README.OS400 < .github/scripts/badwords.txt
 
       - name: 'verify synopsis'
         run: .github/scripts/verify-synopsis.pl docs/libcurl/curl*.md

.github/workflows/checksrc.yml

@@ -91,7 +91,7 @@ jobs:
       - name: 'pytype'
         run: |
           source ~/venv/bin/activate
-          find . -name '*.py' -exec pytype -j auto -k {} +
+          find . -name '*.py' -exec pytype -j auto -k -- {} +
 
       - name: 'ruff'
         run: |
@@ -103,10 +103,6 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 3
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
-        with:
-          persist-credentials: false
-
       - name: 'install pmccabe'
         run: |
           sudo rm -f /etc/apt/sources.list.d/microsoft-prod.list
@@ -115,9 +111,25 @@ jobs:
           sudo apt-get -o Dpkg::Use-Pty=0 install \
             pmccabe
 
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        with:
+          persist-credentials: false
+
       - name: 'check scores'
         run: ./scripts/top-complexity
 
+  xmllint:
+    name: 'xmllint'
+    runs-on: macos-latest
+    timeout-minutes: 1
+    steps:
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        with:
+          persist-credentials: false
+
+      - name: 'check'
+        run: git grep -z -i -l -E '^<\?xml' | xargs -0 -r xmllint >/dev/null
+
   miscchecks:
     name: 'misc checks'
     runs-on: ubuntu-latest
@@ -162,9 +174,7 @@ jobs:
       - name: 'yamlcheck'
         run: .github/scripts/yamlcheck.sh
 
-      # we allow some extra in source code
       - name: 'badwords'
         run: |
-          # shellcheck disable=SC2046
-          grep -Ev '(\\bwill| url | dir )' .github/scripts/badwords.txt | \
-          .github/scripts/badwords.pl $(git ls-files -- src lib include)
+          # 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