[llvm-rc] Allow string table values split into multiple string literals

This can practically easily be a product of combining strings with
macros in resource files.

This fixes mstorsjo/llvm-mingw#140.

As string literals within llvm-rc are handled as StringRefs, each
referencing an uninterpreted slice of the input file, with actual
interpretation of the input string (codepage handling, unescaping etc)
done only right before writing them out to disk, it's hard to
concatenate them other than just bundling them up in a vector,
without rearchitecting a large part of llvm-rc.

This matches how the same already is supported in VersionInfoValue,
with a std::vector<IntOrString> Values.

MS rc.exe only supports concatenated string literals in version info
values (already supported), string tables (implemented in this patch)
and user data resources (easily implemented in a separate patch, but
hasn't been requested by any end user yet), while GNU windres supports
string immediates split into multiple strings anywhere (e.g. like
(100 ICON "myicon" ".ico"). Not sure if concatenation in other
statements actually is used in the wild though, in resource files
normally built by GNU windres.

Differential Revision: https://reviews.llvm.org/D85183

Author: mstorsjo

llvm/test/tools/llvm-rc/Inputs/tag-stringtable-basic.rc

@@ -13,8 +13,8 @@ STRINGTABLE {
 STRINGTABLE
 VERSION 100
 LANGUAGE 4, 7 {
-  16 "hello"
-  17 "world"
+  16 "hel" "lo"
+  17 "wor" L"ld"
 }
 
 STRINGTABLE

llvm/tools/llvm-rc/ResourceFileWriter.cpp

@@ -1246,7 +1246,8 @@ Error ResourceFileWriter::visitStringTableBundle(const RCResource *Res) {
 }
 
 Error ResourceFileWriter::insertStringIntoBundle(
-    StringTableInfo::Bundle &Bundle, uint16_t StringID, StringRef String) {
+    StringTableInfo::Bundle &Bundle, uint16_t StringID,
+    const std::vector<StringRef> &String) {
   uint16_t StringLoc = StringID & 15;
   if (Bundle.Data[StringLoc])
     return createError("Multiple STRINGTABLE strings located under ID " +
@@ -1261,13 +1262,15 @@ Error ResourceFileWriter::writeStringTableBundleBody(const RCResource *Base) {
     // The string format is a tiny bit different here. We
     // first output the size of the string, and then the string itself
     // (which is not null-terminated).
-    bool IsLongString;
     SmallVector<UTF16, 128> Data;
-    RETURN_IF_ERROR(processString(Res->Bundle.Data[ID].getValueOr(StringRef()),
-                                  NullHandlingMethod::CutAtDoubleNull,
-                                  IsLongString, Data, Params.CodePage));
-    if (AppendNull && Res->Bundle.Data[ID])
-      Data.push_back('\0');
+    if (Res->Bundle.Data[ID]) {
+      bool IsLongString;
+      for (StringRef S : *Res->Bundle.Data[ID])
+        RETURN_IF_ERROR(processString(S, NullHandlingMethod::CutAtDoubleNull,
+                                      IsLongString, Data, Params.CodePage));
+      if (AppendNull)
+        Data.push_back('\0');
+    }
     RETURN_IF_ERROR(
         checkNumberFits<uint16_t>(Data.size(), "STRINGTABLE string size"));
     writeInt<uint16_t>(Data.size());

llvm/tools/llvm-rc/ResourceFileWriter.h

@@ -103,7 +103,7 @@ class ResourceFileWriter : public Visitor {
     using BundleKey = std::pair<uint16_t, uint16_t>;
     // Each bundle is in fact an array of 16 strings.
     struct Bundle {
-      std::array<Optional<StringRef>, 16> Data;
+      std::array<Optional<std::vector<StringRef>>, 16> Data;
       ObjectInfo DeclTimeInfo;
       uint16_t MemoryFlags;
       Bundle(const ObjectInfo &Info, uint16_t Flags)
@@ -157,7 +157,8 @@ class ResourceFileWriter : public Visitor {
   Error visitStringTableBundle(const RCResource *);
   Error writeStringTableBundleBody(const RCResource *);
   Error insertStringIntoBundle(StringTableInfo::Bundle &Bundle,
-                               uint16_t StringID, StringRef String);
+                               uint16_t StringID,
+                               const std::vector<StringRef> &String);
 
   // User defined resource
   Error writeUserDefinedBody(const RCResource *);

llvm/tools/llvm-rc/ResourceScriptParser.cpp

@@ -698,8 +698,14 @@ RCParser::ParseType RCParser::parseStringTableResource() {
     // between, however we strictly adhere to the single statement definition.
     ASSIGN_OR_RETURN(IDResult, readInt());
     consumeOptionalType(Kind::Comma);
+
+    std::vector<StringRef> Strings;
     ASSIGN_OR_RETURN(StrResult, readString());
-    Table->addString(*IDResult, *StrResult);
+    Strings.push_back(*StrResult);
+    while (isNextTokenKind(Kind::String))
+      Strings.push_back(read().value());
+
+    Table->addStrings(*IDResult, std::move(Strings));
   }
 
   return std::move(Table);

llvm/tools/llvm-rc/ResourceScriptStmt.cpp

@@ -118,8 +118,12 @@ raw_ostream &MenuResource::log(raw_ostream &OS) const {
 raw_ostream &StringTableResource::log(raw_ostream &OS) const {
   OS << "StringTable:\n";
   OptStatements->log(OS);
-  for (const auto &String : Table)
-    OS << "  " << String.first << " => " << String.second << "\n";
+  for (const auto &String : Table) {
+    OS << "  " << String.first << " =>";
+    for (const auto &S : String.second)
+      OS << " " << S;
+    OS << "\n";
+  }
   return OS;
 }
 

llvm/tools/llvm-rc/ResourceScriptStmt.h

@@ -583,12 +583,12 @@ class MenuResource : public OptStatementsRCResource {
 // Ref: msdn.microsoft.com/en-us/library/windows/desktop/aa381050(v=vs.85).aspx
 class StringTableResource : public OptStatementsRCResource {
 public:
-  std::vector<std::pair<uint32_t, StringRef>> Table;
+  std::vector<std::pair<uint32_t, std::vector<StringRef>>> Table;
 
   StringTableResource(OptionalStmtList &&List, uint16_t Flags)
       : OptStatementsRCResource(std::move(List), Flags) {}
-  void addString(uint32_t ID, StringRef String) {
-    Table.emplace_back(ID, String);
+  void addStrings(uint32_t ID, std::vector<StringRef> &&Strings) {
+    Table.emplace_back(ID, Strings);
   }
   raw_ostream &log(raw_ostream &) const override;
   Twine getResourceTypeName() const override { return "STRINGTABLE"; }