[SCM] gawk branch, feature/minrx, updated. gawk-4.1.0-5859-g2db293a9

[Arnold Robbins]

This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "gawk".

The branch, feature/minrx has been updated
       via  2db293a977a7de1c1c023ac81378e0bec5a07c21 (commit)
      from  e5c9cb482b1f747447feefd19880375886b8cdad (commit)

Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.

- Log -----------------------------------------------------------------
http://git.sv.gnu.org/cgit/gawk.git/commit/?id=2db293a977a7de1c1c023ac81378e0bec5a07c21

commit 2db293a977a7de1c1c023ac81378e0bec5a07c21
Author: Arnold D. Robbins <arnold@skeeve.com>
Date:   Sun Nov 17 06:29:52 2024 +0200

    Update minrx.cpp.

diff --git a/support/ChangeLog b/support/ChangeLog
index 4fc3b69a..b8833aec 100644
--- a/support/ChangeLog
+++ b/support/ChangeLog
@@ -1,3 +1,7 @@
+2024-11-17         Arnold D. Robbins     <arnold@skeeve.com>
+
+       * minrx.cpp: Updated.
+
 2024-09-17         Arnold D. Robbins     <arnold@skeeve.com>
 
        * 5.3.1: Release tar made.
diff --git a/support/minrx.cpp b/support/minrx.cpp
index e21143b8..249e7115 100644
--- a/support/minrx.cpp
+++ b/support/minrx.cpp
@@ -439,6 +439,10 @@ struct Compile {
        WConv wconv;
        std::vector<CSet> csets;
        std::optional<std::size_t> dot;
+       std::optional<std::size_t> esc_s;
+       std::optional<std::size_t> esc_S;
+       std::optional<std::size_t> esc_w;
+       std::optional<std::size_t> esc_W;
        std::map<WChar, unsigned int> icmap;
        NInt nsub = 0;
        Compile(WConv::Encoding e, const char *bp, const char *ep, 
minrx_regcomp_flags_t flags): flags(flags), enc(e), wconv(e, bp, ep) { 
wconv.nextchr(); }
@@ -884,34 +888,46 @@ struct Compile {
                        case L's':
                                if ((flags & MINRX_REG_EXTENSIONS_GNU) == 0)
                                        goto normal;
-                               lhs.push_back({Node::CSet, {csets.size(), 0}, 
nstk});
-                               csets.emplace_back();
-                               cclass(csets.back(), "space");
+                               if (!esc_s.has_value()) {
+                                       esc_s = csets.size();
+                                       csets.emplace_back();
+                                       cclass(csets.back(), "space");
+                               }
+                               lhs.push_back({Node::CSet, {*esc_s, 0}, nstk});
                                break;
                        case L'S':
                                if ((flags & MINRX_REG_EXTENSIONS_GNU) == 0)
                                        goto normal;
-                               lhs.push_back({Node::CSet, {csets.size(), 0}, 
nstk});
-                               csets.emplace_back();
-                               cclass(csets.back(), "space");
-                               csets.back().invert();
+                               if (!esc_S.has_value()) {
+                                       esc_S = csets.size();
+                                       csets.emplace_back();
+                                       cclass(csets.back(), "space");
+                                       csets.back().invert();
+                               }
+                               lhs.push_back({Node::CSet, {*esc_S, 0}, nstk});
                                break;
                        case L'w':
                                if ((flags & MINRX_REG_EXTENSIONS_GNU) == 0)
                                        goto normal;
-                               lhs.push_back({Node::CSet, {csets.size(), 0}, 
nstk});
-                               csets.emplace_back();
-                               cclass(csets.back(), "alnum");
-                               csets.back().set(L'_');
+                               if (!esc_w.has_value()) {
+                                       esc_w = csets.size();
+                                       csets.emplace_back();
+                                       cclass(csets.back(), "alnum");
+                                       csets.back().set(L'_');
+                               }
+                               lhs.push_back({Node::CSet, {*esc_w, 0}, nstk});
                                break;
                        case L'W':
                                if ((flags & MINRX_REG_EXTENSIONS_GNU) == 0)
                                        goto normal;
-                               lhs.push_back({Node::CSet, {csets.size(), 0}, 
nstk});
-                               csets.emplace_back();
-                               cclass(csets.back(), "alnum");
-                               csets.back().set(L'_');
-                               csets.back().invert();
+                               if (!esc_W.has_value()) {
+                                       esc_W = csets.size();
+                                       csets.emplace_back();
+                                       cclass(csets.back(), "alnum");
+                                       csets.back().set(L'_');
+                                       csets.back().invert();
+                               }
+                               lhs.push_back({Node::CSet, {*esc_W, 0}, nstk});
                                break;
                        case WConv::End:
                                return {{}, 0, MINRX_REG_EESCAPE};

-----------------------------------------------------------------------

Summary of changes:
 support/ChangeLog |  4 ++++
 support/minrx.cpp | 48 ++++++++++++++++++++++++++++++++----------------
 2 files changed, 36 insertions(+), 16 deletions(-)


hooks/post-receive
-- 
gawk