[groff] 10/11: [grog]: Use more careful matching patterns.

[G. Branden Robinson]

gbranden pushed a commit to branch master
in repository groff.

commit 6a9ebdea349db669c71440394dd2ed04b4c62c15
Author: G. Branden Robinson <g.branden.robinson@gmail.com>
AuthorDate: Sat Jul 31 19:56:34 2021 +1000

    [grog]: Use more careful matching patterns.
    
    * src/utils/grog/grog.pl (do_line): When matching macro/request names,
      accept any non-whitespace character (Perl: \S) instead of just a
      word-constituent character (Perl: \w), since roff identifiers can
      contain unusual characters (refer(1) and groff_me(7) illustrate some
      real-world cases).
---
 ChangeLog              | 8 ++++++++
 src/utils/grog/grog.pl | 8 ++++----
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index de6c4d2..78bc8bf 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,13 @@
 2021-07-31  G. Branden Robinson <g.branden.robinson@gmail.com>
 
+       * src/utils/grog/grog.pl (do_line): When matching macro/request
+       names, accept any non-whitespace character (Perl: \S) instead of
+       just a word-constituent character (Perl: \w), since roff
+       identifiers can contain unusual characters (refer(1) and
+       groff_me(7) illustrate some real-world cases).
+
+2021-07-31  G. Branden Robinson <g.branden.robinson@gmail.com>
+
        * src/utils/grog/grog.pl: Refactor macro package inference.
          - Stop manually populating `Groff` hash.  (It's itching for a
            rename.)
diff --git a/src/utils/grog/grog.pl b/src/utils/grog/grog.pl
index c083982..b2c9b5b 100644
--- a/src/utils/grog/grog.pl
+++ b/src/utils/grog/grog.pl
@@ -309,7 +309,7 @@ sub do_line {
   my $boundary = '\\b';
   $boundary = '' if ($use_compatibility_mode);
 
-  if ($line =~ /^\.(\w\w)$boundary/ || $line =~ /^\.(\[)/) {
+  if ($line =~ /^\.(\S\S)$boundary/ || $line =~ /^\.(\[)/) {
     my $macro = $1;
     # groff identifiers can have extremely weird characters in them.
     # The ones we care about are conventionally named, but me(7)
@@ -333,17 +333,17 @@ sub do_line {
   # Split control line into a request or macro call and its arguments.
 
   # Handle single-letter macro names.
-  if ($line =~ /^\.(\w)(\s+(.*))?$/) {
+  if ($line =~ /^\.(\S)(\s+(.*))?$/) {
     $command = $1;
     $args = $2;
   # Handle two-letter macro/request names in compatibility mode.
   } elsif ($use_compatibility_mode) {
-    $line =~ /^\.(\w\w)\s*(.*)$/;
+    $line =~ /^\.(\S\S)\s*(.*)$/;
     $command = $1;
     $args = $2;
   # Handle multi-letter macro/request names in groff mode.
   } else {
-    $line =~ /^\.(\w+)(\s+(.*))?$/;
+    $line =~ /^\.(\S+)(\s+(.*))?$/;
     $command = $1;
     $args = $3;
   }