branch master updated: ASCII spaces only

[Gavin D. Smith]

This is an automated email from the git hooks/post-receive script.

gavin pushed a commit to branch master
in repository texinfo.

The following commit(s) were added to refs/heads/master by this push:
     new 02cc29ac51 ASCII spaces only
02cc29ac51 is described below

commit 02cc29ac514d0b47066897a6e01781b03c709e60
Author: Gavin Smith <gavinsmith0123@gmail.com>
AuthorDate: Mon Jan 17 20:14:19 2022 +0000

    ASCII spaces only
    
    * tp/Texinfo/XS/xspara.c (xspara_add_text): Call isspace instead
    of iswspace to match change in ParagraphNonXS.pm.
    * tp/Texinfo/Convert/Plaintext.pm (_protect_sentence_ends):
    Remove special handling of \x{202f} and \x{00a0}, using \a flag
    instead.
---
 ChangeLog                       | 10 ++++++++++
 tp/Texinfo/Convert/Plaintext.pm | 10 ++++------
 tp/Texinfo/XS/xspara.c          |  4 ++--
 3 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 562ec3da46..37812d3144 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,13 @@
+2022-01-17  Gavin Smith  <gavinsmith0123@gmail.com>
+
+       ASCII spaces only
+
+       * tp/Texinfo/XS/xspara.c (xspara_add_text): Call isspace instead
+       of iswspace to match change in ParagraphNonXS.pm.
+       * tp/Texinfo/Convert/Plaintext.pm (_protect_sentence_ends):
+       Remove special handling of \x{202f} and \x{00a0}, using \a flag
+       instead.
+
 2022-01-17  Gavin Smith  <gavinsmith0123@gmail.com>
 
        * tp/Texinfo/Convert/ParagraphNonXS.pm (add_text): Simplify regexp
diff --git a/tp/Texinfo/Convert/Plaintext.pm b/tp/Texinfo/Convert/Plaintext.pm
index 2e2d41243e..ab56d25e32 100644
--- a/tp/Texinfo/Convert/Plaintext.pm
+++ b/tp/Texinfo/Convert/Plaintext.pm
@@ -542,20 +542,18 @@ sub _protect_sentence_ends ($) {
   my $text = shift;
   # Avoid suppressing end of sentence, by inserting a control character
   # in front of the full stop.  The choice of BS for this is arbitrary.
-  $text =~ s/(?<=[^[:upper:]])
+  $text =~ s/(?<=[^\p{Upper}])
              (?=[$end_sentence][$after_punctuation]*(?:\s|$))
-             /\x08/gx;
+             /\x08/xag;
 
   # Also insert a control character at end of string, to protect a full stop 
   # that may follow later.
 
-  #$text =~ s/(?<=[^[:upper:]][$after_punctuation]*)$/\x08/;
+  #$text =~ s/(?<=[^\p{Upper}\s][$after_punctuation]*)$/\x08/a;
   # Perl doesn't support "variable length lookbehind"
 
   $text = reverse $text;
-  $text =~ s/^(?=[$after_punctuation]*
-                 (?:[^[:upper:]\s]|[\x{202f}\x{00a0}]))
-            /\x08/x;
+  $text =~ s/^(?=[$after_punctuation]*(?:[^\p{Upper}\s]))/\x08/xa;
   $text = reverse $text;
 
   return $text;
diff --git a/tp/Texinfo/XS/xspara.c b/tp/Texinfo/XS/xspara.c
index 83c76fba48..4664c6b50a 100644
--- a/tp/Texinfo/XS/xspara.c
+++ b/tp/Texinfo/XS/xspara.c
@@ -185,6 +185,7 @@ mbrtowc (wchar_t * __restrict__ pwc, const char * 
__restrict__ mbs, size_t n,
     }
 }
 
+/* NOTE - not used at present */
 int
 iswspace (wint_t wc)
 {
@@ -866,8 +867,7 @@ xspara_add_text (char *text)
           continue;
         }
 
-      /* 00A0 and 202F are non-breaking spaces in Unicode. */
-      if (iswspace (wc) && wc != L'\x00a0' && wc != L'\x202f')
+      if (isspace (*p))
         {
           state.last_letter = L'\0';