[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rGd9cea8d3a8ff: [C++20][Modules][HU 4/5] Handle pre-processed 
header units. (authored by iains).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

Files:
  clang/lib/Frontend/FrontendAction.cpp
  clang/lib/Sema/SemaModule.cpp
  clang/test/Modules/cxx20-hu-05.cpp


Index: clang/test/Modules/cxx20-hu-05.cpp
===
--- /dev/null
+++ clang/test/Modules/cxx20-hu-05.cpp
@@ -0,0 +1,32 @@
+// Test macro preservation in C++20 Header Units.
+
+// RUN: rm -rf %t
+// RUN: mkdir -p %t
+// RUN: split-file %s %t
+// RUN: cd %t
+
+// Produce a pre-processed file.
+// RUN: %clang_cc1 -std=c++20 -E -xc++-user-header hu-01.h -o hu-01.iih
+
+// consume that to produce the heder unit.
+// RUN: %clang_cc1 -std=c++20 -emit-header-unit \
+// RUN: -xc++-header-unit-header-cpp-output hu-01.iih -o hu-01.pcm
+
+// check that the header unit is named for the original file, not the .iih.
+// RUN: %clang_cc1 -std=c++20 -module-file-info hu-01.pcm | \
+// RUN: FileCheck --check-prefix=CHECK-HU %s -DTDIR=%t
+
+//--- hu-01.h
+#ifndef __GUARD
+#define __GUARD
+
+int baz(int);
+#define FORTYTWO 42
+
+#define SHOULD_NOT_BE_DEFINED -1
+#undef SHOULD_NOT_BE_DEFINED
+
+#endif // __GUARD
+
+// CHECK-HU:  == C++20 Module structure ==
+// CHECK-HU-NEXT:  Header Unit './hu-01.h' is the Primary Module at index #1
Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+// Unless the user overrides this, the module name is the name by which the
+// original file was known.
+if (CI.getLangOpts().ModuleName.empty())
+  CI.getLangOpts().ModuleName = std::string(PresumedInputFile);
+CI.getLangOpts().CurrentModule = CI.getLangOpts().ModuleName;
+  }
+
   // For module map files, we first parse the module map and synthesize a
   // "" buffer before more conventional processing.
   if (Input.getKind().getFormat() == InputKind::ModuleMap) {


Index: clang/test/Modules/cxx20-hu-05.cpp
===
--- /dev/null
+++ clang/test/Modules/cxx20-hu-05.cpp
@@ -0,0 +1,32 @@
+// Test macro preservation in C++20 Header Units.
+
+// RUN: rm -rf %t
+// RUN: mkdir -p %t
+// RUN: split-file %s %t
+// RUN: cd %t
+
+// Produce a pre-processed file.
+// RUN: %clang_cc1 -std=c++20 -E -xc++-user-header hu-01.h -o hu-01.iih
+
+// consume that to produce the heder unit.
+// RUN: %clang_cc1 -std=c++20 -emit-header-unit \
+// RUN: -xc++-header-unit-header-cpp-output hu-01.iih -o hu-01.pcm
+
+// check that the header unit is named for the original file, not the .iih.
+// RUN: %clang_cc1 -std=c++20 -module-file-info hu-01.pcm | \
+// RUN: FileCheck --check-prefix=CHECK-HU %s -DTDIR=%t
+
+//--- hu-01.h
+#ifndef __GUARD
+#define __GUARD
+
+int baz(int);
+#define 

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

iains updated this revision to Diff 418082.
iains added a comment.

rebased


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

Files:
  clang/lib/Frontend/FrontendAction.cpp
  clang/lib/Sema/SemaModule.cpp
  clang/test/Modules/cxx20-hu-05.cpp


Index: clang/test/Modules/cxx20-hu-05.cpp
===
--- /dev/null
+++ clang/test/Modules/cxx20-hu-05.cpp
@@ -0,0 +1,32 @@
+// Test macro preservation in C++20 Header Units.
+
+// RUN: rm -rf %t
+// RUN: mkdir -p %t
+// RUN: split-file %s %t
+// RUN: cd %t
+
+// Produce a pre-processed file.
+// RUN: %clang_cc1 -std=c++20 -E -xc++-user-header hu-01.h -o hu-01.iih
+
+// consume that to produce the heder unit.
+// RUN: %clang_cc1 -std=c++20 -emit-header-unit \
+// RUN: -xc++-header-unit-header-cpp-output hu-01.iih -o hu-01.pcm
+
+// check that the header unit is named for the original file, not the .iih.
+// RUN: %clang_cc1 -std=c++20 -module-file-info hu-01.pcm | \
+// RUN: FileCheck --check-prefix=CHECK-HU %s -DTDIR=%t
+
+//--- hu-01.h
+#ifndef __GUARD
+#define __GUARD
+
+int baz(int);
+#define FORTYTWO 42
+
+#define SHOULD_NOT_BE_DEFINED -1
+#undef SHOULD_NOT_BE_DEFINED
+
+#endif // __GUARD
+
+// CHECK-HU:  == C++20 Module structure ==
+// CHECK-HU-NEXT:  Header Unit './hu-01.h' is the Primary Module at index #1
Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+// Unless the user overrides this, the module name is the name by which the
+// original file was known.
+if (CI.getLangOpts().ModuleName.empty())
+  CI.getLangOpts().ModuleName = std::string(PresumedInputFile);
+CI.getLangOpts().CurrentModule = CI.getLangOpts().ModuleName;
+  }
+
   // For module map files, we first parse the module map and synthesize a
   // "" buffer before more conventional processing.
   if (Input.getKind().getFormat() == InputKind::ModuleMap) {


Index: clang/test/Modules/cxx20-hu-05.cpp
===
--- /dev/null
+++ clang/test/Modules/cxx20-hu-05.cpp
@@ -0,0 +1,32 @@
+// Test macro preservation in C++20 Header Units.
+
+// RUN: rm -rf %t
+// RUN: mkdir -p %t
+// RUN: split-file %s %t
+// RUN: cd %t
+
+// Produce a pre-processed file.
+// RUN: %clang_cc1 -std=c++20 -E -xc++-user-header hu-01.h -o hu-01.iih
+
+// consume that to produce the heder unit.
+// RUN: %clang_cc1 -std=c++20 -emit-header-unit \
+// RUN: -xc++-header-unit-header-cpp-output hu-01.iih -o hu-01.pcm
+
+// check that the header unit is named for the original file, not the .iih.
+// RUN: %clang_cc1 -std=c++20 -module-file-info hu-01.pcm | \
+// RUN: FileCheck --check-prefix=CHECK-HU %s -DTDIR=%t
+
+//--- hu-01.h
+#ifndef __GUARD
+#define __GUARD
+
+int baz(int);
+#define FORTYTWO 42
+
+#define SHOULD_NOT_BE_DEFINED -1
+#undef SHOULD_NOT_BE_DEFINED
+
+#endif // __GUARD
+
+// 

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Nathan Sidwell via Phabricator via cfe-commits]

urnathan added a comment.

yeah, gcc's preprocessor has peeking code to deal with this (more generally 
than modules)


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

iains updated this revision to Diff 416847.
iains added a comment.

rebased, added test.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

Files:
  clang/lib/Frontend/FrontendAction.cpp
  clang/lib/Sema/SemaModule.cpp
  clang/test/Modules/cxx20-hu-05.cpp


Index: clang/test/Modules/cxx20-hu-05.cpp
===
--- /dev/null
+++ clang/test/Modules/cxx20-hu-05.cpp
@@ -0,0 +1,32 @@
+// Test macro preservation in C++20 Header Units.
+
+// RUN: rm -rf %t
+// RUN: mkdir -p %t
+// RUN: split-file %s %t
+// RUN: cd %t
+
+// Produce a pre-processed file.
+// RUN: %clang_cc1 -std=c++20 -E -xc++-user-header hu-01.h -o hu-01.iih
+
+// consume that to produce the heder unit.
+// RUN: %clang_cc1 -std=c++20 -emit-header-unit \
+// RUN: -xc++-header-unit-header-cpp-output hu-01.iih -o hu-01.pcm
+
+// check that the header unit is named for the original file, not the .iih.
+// RUN: %clang_cc1 -std=c++20 -module-file-info hu-01.pcm | \
+// RUN: FileCheck --check-prefix=CHECK-HU %s -DTDIR=%t
+
+//--- hu-01.h
+#ifndef __GUARD
+#define __GUARD
+
+int baz(int);
+#define FORTYTWO 42
+
+#define SHOULD_NOT_BE_DEFINED -1
+#undef SHOULD_NOT_BE_DEFINED
+
+#endif // __GUARD
+
+// CHECK-HU:  == C++20 Module structure ==
+// CHECK-HU-NEXT:  Header Unit './hu-01.h' is the Primary Module at index #1
Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+// Unless the user overrides this, the module name is the name by which the
+// original file was known.
+if (CI.getLangOpts().ModuleName.empty())
+  CI.getLangOpts().ModuleName = std::string(PresumedInputFile);
+CI.getLangOpts().CurrentModule = CI.getLangOpts().ModuleName;
+  }
+
   // For module map files, we first parse the module map and synthesize a
   // "" buffer before more conventional processing.
   if (Input.getKind().getFormat() == InputKind::ModuleMap) {


Index: clang/test/Modules/cxx20-hu-05.cpp
===
--- /dev/null
+++ clang/test/Modules/cxx20-hu-05.cpp
@@ -0,0 +1,32 @@
+// Test macro preservation in C++20 Header Units.
+
+// RUN: rm -rf %t
+// RUN: mkdir -p %t
+// RUN: split-file %s %t
+// RUN: cd %t
+
+// Produce a pre-processed file.
+// RUN: %clang_cc1 -std=c++20 -E -xc++-user-header hu-01.h -o hu-01.iih
+
+// consume that to produce the heder unit.
+// RUN: %clang_cc1 -std=c++20 -emit-header-unit \
+// RUN: -xc++-header-unit-header-cpp-output hu-01.iih -o hu-01.pcm
+
+// check that the header unit is named for the original file, not the .iih.
+// RUN: %clang_cc1 -std=c++20 -module-file-info hu-01.pcm | \
+// RUN: FileCheck --check-prefix=CHECK-HU %s -DTDIR=%t
+
+//--- hu-01.h
+#ifndef __GUARD
+#define __GUARD
+
+int baz(int);
+#define FORTYTWO 42
+
+#define SHOULD_NOT_BE_DEFINED -1
+#undef SHOULD_NOT_BE_DEFINED
+
+#endif // __GUARD

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Chuanqi Xu via Phabricator via cfe-commits]

ChuanqiXu added a comment.

OK, I feel good if this one contains tests.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

iains added a comment.

In D121098#3384590 , @ChuanqiXu wrote:

> In D121098#3383835 , @iains wrote:
>
>>> I am a little bit confused for the intuition. Couldn't we just import the 
>>> pre-processed header? What's the problem? Could you elaborate on this?
>>
>> We cannot import a pre-processed file; the preprocessed file is still source 
>> code, not a CMI.
>
> But if I understand correctly, we are able to import a pre-processed file as 
> a header unit. Couldn't we?
>
> For example:
>
>   // cc -E foo.h > foo.preprocessed
>   import "foo.preprocessed"
>   ...
>
> Is this not acceptable?
>
>> In addition, the pre-processor output for a header unit requires further 
>> pre-processing on read.
>> This is because a header unit actually preserves some of the pre-processor 
>> information [macro definitions] (which would normally be discarded after 
>> phase 4).
>>
>> Header units are identifiable by a name (in common with GCC, we make the 
>> name == the path by which the header is specified) -- that name is 
>> intentionally not a  legal named module name (neither is it, in general, a 
>> legal identifier).
>
> So it doesn't eliminate my confusion. I guess there is some workflows that we 
> need to import a preprocessed header as header unit (and we need to find the 
> position of original file). Or in what circumstances, do we need to import a 
> pre-processed header as header unit?

A pre-processed header unit can only be used to build that header unit - just 
like a pre-processed c++ source is used to build an object for the original 
source file.

In this code, we are not considering importing the HU into another module - 
that can only be done once the HU is built as a CMI.

The pre-processed output has two immediate uses I could see:
 (1) traditionally, it can be helpful in debugging and problem reporting [since 
the included headers are flattened]
 (2) because we will have processed the directives, it might be useful for 
scanners that want to determine remaining dependencies.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Chuanqi Xu via Phabricator via cfe-commits]

ChuanqiXu added a comment.

In D121098#3383835 , @iains wrote:

>> I am a little bit confused for the intuition. Couldn't we just import the 
>> pre-processed header? What's the problem? Could you elaborate on this?
>
> We cannot import a pre-processed file; the preprocessed file is still source 
> code, not a CMI.

But if I understand correctly, we are able to import a pre-processed file as a 
header unit. Couldn't we?

For example:

  // cc -E foo.h > foo.preprocessed
  import "foo.preprocessed"
  ...

Is this not acceptable?

> In addition, the pre-processor output for a header unit requires further 
> pre-processing on read.
> This is because a header unit actually preserves some of the pre-processor 
> information [macro definitions] (which would normally be discarded after 
> phase 4).
>
> Header units are identifiable by a name (in common with GCC, we make the name 
> == the path by which the header is specified) -- that name is intentionally 
> not a  legal named module name (neither is it, in general, a legal 
> identifier).

So it doesn't eliminate my confusion. I guess there is some workflows that we 
need to import a preprocessed header as header unit (and we need to find the 
position of original file). Or in what circumstances, do we need to import a 
pre-processed header as header unit?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

iains added a comment.

In D121098#3378375 , @ChuanqiXu wrote:

> It lacks tests. This is not NFC, right?

Right, (there are tests with the next patch which introduces the mechanism for 
producing the pre-processed output) 
but, I will find a suitable one for this...

> ---
>
> I am a little bit confused for the intuition. Couldn't we just import the 
> pre-processed header? What's the problem? Could you elaborate on this?

We cannot import a pre-processed file; the preprocessed file is still source 
code, not a CMI.

In addition, the pre-processor output for a header unit requires further 
pre-processing on read.
This is because a header unit actually preserves some of the pre-processor 
information [macro definitions] (which would normally be discarded after phase 
4).

Header units are identifiable by a name (in common with GCC, we make the name 
== the path by which the header is specified) -- that name is intentionally not 
a  legal named module name (neither is it, in general, a legal identifier).


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Chuanqi Xu via Phabricator via cfe-commits]

ChuanqiXu added a comment.

It lacks tests. This is not NFC, right?

---

I am a little bit confused for the intuition. Couldn't we just import the 
pre-processed header? What's the problem? Could you elaborate on this?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

iains updated this revision to Diff 414891.
iains added a comment.

rebased.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

Files:
  clang/lib/Frontend/FrontendAction.cpp
  clang/lib/Sema/SemaModule.cpp


Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+// Unless the user overrides this, the module name is the name by which the
+// original file was known.
+if (CI.getLangOpts().ModuleName.empty())
+  CI.getLangOpts().ModuleName = std::string(PresumedInputFile);
+CI.getLangOpts().CurrentModule = CI.getLangOpts().ModuleName;
+  }
+
   // For module map files, we first parse the module map and synthesize a
   // "" buffer before more conventional processing.
   if (Input.getKind().getFormat() == InputKind::ModuleMap) {


Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

iains updated this revision to Diff 413612.
iains added a comment.

rebased


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121098/new/

https://reviews.llvm.org/D121098

Files:
  clang/lib/Frontend/FrontendAction.cpp
  clang/lib/Sema/SemaModule.cpp


Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+// Unless the user overrides this, the module name is the name by which the
+// original file was known.
+if (CI.getLangOpts().ModuleName.empty())
+  CI.getLangOpts().ModuleName = std::string(PresumedInputFile);
+CI.getLangOpts().CurrentModule = CI.getLangOpts().ModuleName;
+  }
+
   // For module map files, we first parse the module map and synthesize a
   // "" buffer before more conventional processing.
   if (Input.getKind().getFormat() == InputKind::ModuleMap) {


Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+

[PATCH] D121098: [C++20][Modules][HU 4/5] Handle pre-processed header units.

[Iain Sandoe via Phabricator via cfe-commits]

iains created this revision.
Herald added a project: All.
iains added reviewers: rsmith, urnathan, ChuanqiXu.
iains published this revision for review.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

We wish to support emitting a pre-processed output for an importable
header unit, that can be consumed to produce the same header units as
the original source.

This means that ee need to find the original filename used to produce
the re-preprocessed output, so that it can be assigned as the module
name.  This is peeked from the first line of the pre-processed source
when the action sets up the files.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D121098

Files:
  clang/lib/Frontend/FrontendAction.cpp
  clang/lib/Sema/SemaModule.cpp


Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules && Input.getKind().isHeaderUnit() &&
+  Input.getKind().isPreprocessed() && !usesPreprocessorOnly()) {
+// We have an input filename like foo.iih, but we want to find the right
+// module name (and original file, to build the map entry).
+// Check if the first line specifies the original source file name with a
+// linemarker.
+std::string PresumedInputFile = std::string(getCurrentFileOrBufferName());
+ReadOriginalFileName(CI, PresumedInputFile);
+// Unless the user overrides this, the module name is the name by which the
+// original file was known.
+if (CI.getLangOpts().ModuleName.empty())
+  CI.getLangOpts().ModuleName = std::string(PresumedInputFile);
+CI.getLangOpts().CurrentModule = CI.getLangOpts().ModuleName;
+  }
+
   // For module map files, we first parse the module map and synthesize a
   // "" buffer before more conventional processing.
   if (Input.getKind().getFormat() == InputKind::ModuleMap) {


Index: clang/lib/Sema/SemaModule.cpp
===
--- clang/lib/Sema/SemaModule.cpp
+++ clang/lib/Sema/SemaModule.cpp
@@ -109,10 +109,18 @@
 const_cast(getLangOpts()).CurrentModule = HUName.str();
   }
 
-  auto  = PP.getHeaderSearchInfo().getModuleMap();
   // TODO: Make the C++20 header lookup independent.
-  Module::Header H{getLangOpts().CurrentModule, getLangOpts().CurrentModule,
-   SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())};
+  // When the input is pre-processed source, we need a file ref to the original
+  // file for the header map.
+  auto F = SourceMgr.getFileManager().getFile(HUName);
+  // For the sake of error recovery (if someone has moved the original header
+  // after creating the pre-processed output) fall back to obtaining the file
+  // ref for the input file, which must be present.
+  if (!F)
+F = SourceMgr.getFileEntryForID(SourceMgr.getMainFileID());
+  assert(F && "failed to find the header unit source?");
+  Module::Header H{HUName.str(), HUName.str(), *F};
+  auto  = PP.getHeaderSearchInfo().getModuleMap();
   Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
   assert(Mod && "module creation should not fail");
   ModuleScopes.push_back({}); // No GMF
Index: clang/lib/Frontend/FrontendAction.cpp
===
--- clang/lib/Frontend/FrontendAction.cpp
+++ clang/lib/Frontend/FrontendAction.cpp
@@ -843,6 +843,21 @@
   if (!CI.InitializeSourceManager(Input))
 return false;
 
+  if (CI.getLangOpts().CPlusPlusModules