[flang-commits] [flang] [flang] Handle more use cases reported for issues/79590 (PR #79628)

[Peter Klausler via flang-commits]

https://github.com/klausler updated https://github.com/llvm/llvm-project/pull/79628

>From 41c46f9e7ece59561af6c6869cfed74f54ae997b Mon Sep 17 00:00:00 2001
From: Peter Klausler <pklausler at nvidia.com>
Date: Fri, 26 Jan 2024 10:21:23 -0800
Subject: [PATCH] [flang] Handle more use cases reported for issues/79590

I implemented legacy "token pasting" via line continuation for

  call prefix&
    &MACRO&
    &suffix(1)

in a recent patch; this patch addresses the related cases

  call prefix&
    &MACRO&
    &(1)

and

  call &
    &MACRO&
    &suffix(1)

and

  call prefix&
    &MACRO

Fixes the latest https://github.com/llvm/llvm-project/issues/79590.
---
 flang/lib/Parser/prescan.cpp       | 20 +++++++++++++++-----
 flang/test/Preprocessing/pp005.F   |  6 +++---
 flang/test/Preprocessing/pp006.F   |  6 +++---
 flang/test/Preprocessing/pp105.F90 |  6 +++---
 flang/test/Preprocessing/pp106.F90 |  6 +++---
 flang/test/Preprocessing/pp134.F90 | 18 ++++++++++++++++--
 6 files changed, 43 insertions(+), 19 deletions(-)

diff --git a/flang/lib/Parser/prescan.cpp b/flang/lib/Parser/prescan.cpp
index f7f22177a7d0bf..e9b23172ed2e28 100644
--- a/flang/lib/Parser/prescan.cpp
+++ b/flang/lib/Parser/prescan.cpp
@@ -630,9 +630,11 @@ bool Prescanner::NextToken(TokenSequence &tokens) {
     preventHollerith_ = false;
   } else if (IsLegalInIdentifier(*at_)) {
     int parts{1};
+    const char *afterLast{nullptr};
     do {
       EmitChar(tokens, *at_);
       ++at_, ++column_;
+      afterLast = at_;
       if (SkipToNextSignificantCharacter() && IsLegalIdentifierStart(*at_)) {
         tokens.CloseToken();
         ++parts;
@@ -640,12 +642,20 @@ bool Prescanner::NextToken(TokenSequence &tokens) {
     } while (IsLegalInIdentifier(*at_));
     if (parts >= 3) {
       // Subtlety: When an identifier is split across three or more continuation
-      // lines, its parts are kept as distinct pp-tokens so that macro
-      // operates on them independently.  This trick accommodates the historic
-      // practice of using line continuation for token pasting after
-      // replacement.
+      // lines (or two continuation lines, immediately preceded or followed
+      // by '&' free form continuation line markers, its parts are kept as
+      // distinct pp-tokens so that macro operates on them independently.
+      // This trick accommodates the historic practice of using line
+      // continuation for token pasting after replacement.
     } else if (parts == 2) {
-      tokens.ReopenLastToken();
+      if ((start > start_ && start[-1] == '&') ||
+          (afterLast < limit_ && (*afterLast == '&' || *afterLast == '\n'))) {
+        // call &                call foo&        call foo&
+        //   &MACRO&      OR       &MACRO&   OR     &MACRO
+        //   &foo(...)             &(...)
+      } else {
+        tokens.ReopenLastToken();
+      }
     }
     if (InFixedFormSource()) {
       SkipSpaces();
diff --git a/flang/test/Preprocessing/pp005.F b/flang/test/Preprocessing/pp005.F
index e4483b404c3673..a8d7394cb12d38 100644
--- a/flang/test/Preprocessing/pp005.F
+++ b/flang/test/Preprocessing/pp005.F
@@ -1,11 +1,11 @@
 ! RUN: %flang -E %s 2>&1 | FileCheck %s
-! CHECK: res = 777
+! CHECK: res = (777)
 * KWM split across continuation, implicit padding
       integer, parameter :: KWM = 666
 #define KWM 777
       integer :: res
-      res = KW
-     +M
+      res = (KW
+     +M)
       if (res .eq. 777) then
         print *, 'pp005.F yes'
       else
diff --git a/flang/test/Preprocessing/pp006.F b/flang/test/Preprocessing/pp006.F
index f526ad31733efa..e45dcf9c18e196 100644
--- a/flang/test/Preprocessing/pp006.F
+++ b/flang/test/Preprocessing/pp006.F
@@ -1,12 +1,12 @@
 ! RUN: %flang -E %s 2>&1 | FileCheck %s
-! CHECK: res = 777
+! CHECK: res = (777)
 * ditto, but with intervening *comment line
       integer, parameter :: KWM = 666
 #define KWM 777
       integer :: res
-      res = KW
+      res = (KW
 *comment
-     +M
+     +M)
       if (res .eq. 777) then
         print *, 'pp006.F yes'
       else
diff --git a/flang/test/Preprocessing/pp105.F90 b/flang/test/Preprocessing/pp105.F90
index b4f73da6fa24c0..e861e9688d2c54 100644
--- a/flang/test/Preprocessing/pp105.F90
+++ b/flang/test/Preprocessing/pp105.F90
@@ -1,11 +1,11 @@
 ! RUN: %flang -E %s 2>&1 | FileCheck %s
-! CHECK: res = 777
+! CHECK: res = (777)
 ! KWM call name split across continuation, with leading &
       integer, parameter :: KWM = 666
 #define KWM 777
       integer :: res
-      res = KW&
-&M
+      res = (KW&
+&M)
       if (res .eq. 777) then
         print *, 'pp105.F90 yes'
       else
diff --git a/flang/test/Preprocessing/pp106.F90 b/flang/test/Preprocessing/pp106.F90
index 556d779048f6c9..a450807f0bd214 100644
--- a/flang/test/Preprocessing/pp106.F90
+++ b/flang/test/Preprocessing/pp106.F90
@@ -1,11 +1,11 @@
 ! RUN: %flang -E %s 2>&1 | FileCheck %s
-! CHECK: res = 777
+! CHECK: res = (777)
 ! ditto, with & ! comment
       integer, parameter :: KWM = 666
 #define KWM 777
       integer :: res
-      res = KW& ! comment
-&M
+      res = (KW& ! comment
+&M)
       if (res .eq. 777) then
         print *, 'pp106.F90 yes'
       else
diff --git a/flang/test/Preprocessing/pp134.F90 b/flang/test/Preprocessing/pp134.F90
index 01e7b010d426ec..bc34767224fa03 100644
--- a/flang/test/Preprocessing/pp134.F90
+++ b/flang/test/Preprocessing/pp134.F90
@@ -1,9 +1,23 @@
 ! RUN: %flang -E %s 2>&1 | FileCheck %s
-! CHECK: print *, ADC
+! CHECK: print *, ADC, 1
+! CHECK: print *, AD, 1
+! CHECK: print *, DC, 1
+! CHECK: print *, AD
+! CHECK: print *, AB
 #define B D
 implicit none
 real ADC
 print *, A&
   &B&
-  &C
+  &C, 1
+print *, A&
+  &B&
+  &, 1
+print *, &
+  &B&
+  &C, 1
+print *, A&
+  &B
+print *, A&
+  &B ! but not this
 end