[llvm-objcopy] Add support for shell wildcards

Summary: GNU objcopy accepts the --wildcard flag to allow wildcard matching on symbol-related flags. (Note: it's implicitly true for section flags).

The basic syntax is to allow *, ?, \, and [] which work similarly to how they work in a shell. Additionally, starting a wildcard with ! causes that wildcard to prevent it from matching a flag.

Use an updated GlobPattern in libSupport to handle these patterns. It does not fully match the `fnmatch` used by GNU objcopy since named character classes (e.g. `[[:digit:]]`) are not supported, but this should support most existing use cases (mostly just `*` is what's used anyway).

Reviewers: jhenderson, MaskRay, evgeny777, espindola, alexshap

Reviewed By: MaskRay

Subscribers: nickdesaulniers, emaste, arichardson, hiraditya, jakehehrlich, abrachet, seiya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D66613

llvm-svn: 375169

4 files changed, 179 insertions, 49 deletions

diff --git a/llvm/tools/llvm-objcopy/CommonOpts.td b/llvm/tools/llvm-objcopy/CommonOpts.td
index 597163e..e8c092b4 100644
--- a/llvm/tools/llvm-objcopy/CommonOpts.td
+++ b/llvm/tools/llvm-objcopy/CommonOpts.td
@@ -111,3 +111,13 @@ def version : Flag<["--"], "version">,
 def V : Flag<["-"], "V">,
         Alias<version>,
         HelpText<"Alias for --version">;
+
+def wildcard
+    : Flag<["--"], "wildcard">,
+      HelpText<"Allow wildcard syntax for symbol-related flags. Incompatible "
+               "with --regex. Allows using '*' to match any number of "
+               "characters, '?' to match any single character, '\' to escape "
+               "special characters, and '[]' to define character classes. "
+               "Wildcards beginning with '!' will prevent a match, for example "
+               "\"-N '*' -N '!x'\" will strip all symbols except for \"x\".">;
+def w : Flag<["-"], "w">, Alias<wildcard>, HelpText<"Alias for --wildcard">;
diff --git a/llvm/tools/llvm-objcopy/CopyConfig.cpp b/llvm/tools/llvm-objcopy/CopyConfig.cpp
index 952b3a7..c805631 100644
--- a/llvm/tools/llvm-objcopy/CopyConfig.cpp
+++ b/llvm/tools/llvm-objcopy/CopyConfig.cpp
@@ -260,8 +260,10 @@ getOutputTargetInfoByTargetName(StringRef TargetName) {
   return {TargetInfo{Format, MI}};
 }
 
-static Error addSymbolsFromFile(NameMatcher &Symbols, BumpPtrAllocator &Alloc,
-                                StringRef Filename, bool UseRegex) {
+static Error
+addSymbolsFromFile(NameMatcher &Symbols, BumpPtrAllocator &Alloc,
+                   StringRef Filename, MatchStyle MS,
+                   llvm::function_ref<Error(Error)> ErrorCallback) {
   StringSaver Saver(Alloc);
   SmallVector<StringRef, 16> Lines;
   auto BufOrErr = MemoryBuffer::getFile(Filename);
@@ -274,21 +276,46 @@ static Error addSymbolsFromFile(NameMatcher &Symbols, BumpPtrAllocator &Alloc,
     // it's not empty.
     auto TrimmedLine = Line.split('#').first.trim();
     if (!TrimmedLine.empty())
-      Symbols.addMatcher({Saver.save(TrimmedLine), UseRegex});
+      if (Error E = Symbols.addMatcher(NameOrPattern::create(
+              Saver.save(TrimmedLine), MS, ErrorCallback)))
+        return E;
   }
 
   return Error::success();
 }
 
-NameOrRegex::NameOrRegex(StringRef Pattern, bool IsRegex) {
-  if (!IsRegex) {
-    Name = Pattern;
-    return;
-  }
+Expected<NameOrPattern>
+NameOrPattern::create(StringRef Pattern, MatchStyle MS,
+                      llvm::function_ref<Error(Error)> ErrorCallback) {
+  switch (MS) {
+  case MatchStyle::Literal:
+    return NameOrPattern(Pattern);
+  case MatchStyle::Wildcard: {
+    SmallVector<char, 32> Data;
+    bool IsPositiveMatch = true;
+    if (Pattern[0] == '!') {
+      IsPositiveMatch = false;
+      Pattern = Pattern.drop_front();
+    }
+    Expected<GlobPattern> GlobOrErr = GlobPattern::create(Pattern);
+
+    // If we couldn't create it as a glob, report the error, but try again with
+    // a literal if the error reporting is non-fatal.
+    if (!GlobOrErr) {
+      if (Error E = ErrorCallback(GlobOrErr.takeError()))
+        return std::move(E);
+      return create(Pattern, MatchStyle::Literal, ErrorCallback);
+    }
 
-  SmallVector<char, 32> Data;
-  R = std::make_shared<Regex>(
-      ("^" + Pattern.ltrim('^').rtrim('$') + "$").toStringRef(Data));
+    return NameOrPattern(std::make_shared<GlobPattern>(*GlobOrErr),
+                         IsPositiveMatch);
+  }
+  case MatchStyle::Regex: {
+    SmallVector<char, 32> Data;
+    return NameOrPattern(std::make_shared<Regex>(
+        ("^" + Pattern.ltrim('^').rtrim('$') + "$").toStringRef(Data)));
+  }
+  }
 }
 
 static Error addSymbolsToRenameFromFile(StringMap<StringRef> &SymbolsToRename,
@@ -338,7 +365,9 @@ static void printHelp(const opt::OptTable &OptTable, raw_ostream &OS,
 // ParseObjcopyOptions returns the config and sets the input arguments. If a
 // help flag is set then ParseObjcopyOptions will print the help messege and
 // exit.
-Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) {
+Expected<DriverConfig>
+parseObjcopyOptions(ArrayRef<const char *> ArgsArr,
+                    llvm::function_ref<Error(Error)> ErrorCallback) {
   DriverConfig DC;
   ObjcopyOptTable T;
   unsigned MissingArgumentIndex, MissingArgumentCount;
@@ -387,7 +416,18 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) {
         errc::invalid_argument,
         "--target cannot be used with --input-target or --output-target");
 
-  bool UseRegex = InputArgs.hasArg(OBJCOPY_regex);
+  if (InputArgs.hasArg(OBJCOPY_regex) && InputArgs.hasArg(OBJCOPY_wildcard))
+    return createStringError(errc::invalid_argument,
+                             "--regex and --wildcard are incompatible");
+
+  MatchStyle SectionMatchStyle = InputArgs.hasArg(OBJCOPY_regex)
+                                     ? MatchStyle::Regex
+                                     : MatchStyle::Wildcard;
+  MatchStyle SymbolMatchStyle = InputArgs.hasArg(OBJCOPY_regex)
+                                    ? MatchStyle::Regex
+                                    : InputArgs.hasArg(OBJCOPY_wildcard)
+                                          ? MatchStyle::Wildcard
+                                          : MatchStyle::Literal;
   StringRef InputFormat, OutputFormat;
   if (InputArgs.hasArg(OBJCOPY_target)) {
     InputFormat = InputArgs.getLastArgValue(OBJCOPY_target);
@@ -541,11 +581,17 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) {
   }
 
   for (auto Arg : InputArgs.filtered(OBJCOPY_remove_section))
-    Config.ToRemove.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.ToRemove.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SectionMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_keep_section))
-    Config.KeepSection.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.KeepSection.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SectionMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_only_section))
-    Config.OnlySection.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.OnlySection.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SectionMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_add_section)) {
     StringRef ArgValue(Arg->getValue());
     if (!ArgValue.contains('='))
@@ -583,46 +629,68 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) {
   if (Config.DiscardMode == DiscardType::All)
     Config.StripDebug = true;
   for (auto Arg : InputArgs.filtered(OBJCOPY_localize_symbol))
-    Config.SymbolsToLocalize.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.SymbolsToLocalize.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_localize_symbols))
     if (Error E = addSymbolsFromFile(Config.SymbolsToLocalize, DC.Alloc,
-                                     Arg->getValue(), UseRegex))
+                                     Arg->getValue(), SymbolMatchStyle,
+                                     ErrorCallback))
       return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_keep_global_symbol))
-    Config.SymbolsToKeepGlobal.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.SymbolsToKeepGlobal.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_keep_global_symbols))
     if (Error E = addSymbolsFromFile(Config.SymbolsToKeepGlobal, DC.Alloc,
-                                     Arg->getValue(), UseRegex))
+                                     Arg->getValue(), SymbolMatchStyle,
+                                     ErrorCallback))
       return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_globalize_symbol))
-    Config.SymbolsToGlobalize.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.SymbolsToGlobalize.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_globalize_symbols))
     if (Error E = addSymbolsFromFile(Config.SymbolsToGlobalize, DC.Alloc,
-                                     Arg->getValue(), UseRegex))
+                                     Arg->getValue(), SymbolMatchStyle,
+                                     ErrorCallback))
       return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_weaken_symbol))
-    Config.SymbolsToWeaken.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.SymbolsToWeaken.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_weaken_symbols))
     if (Error E = addSymbolsFromFile(Config.SymbolsToWeaken, DC.Alloc,
-                                     Arg->getValue(), UseRegex))
+                                     Arg->getValue(), SymbolMatchStyle,
+                                     ErrorCallback))
       return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_strip_symbol))
-    Config.SymbolsToRemove.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.SymbolsToRemove.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_strip_symbols))
     if (Error E = addSymbolsFromFile(Config.SymbolsToRemove, DC.Alloc,
-                                     Arg->getValue(), UseRegex))
+                                     Arg->getValue(), SymbolMatchStyle,
+                                     ErrorCallback))
       return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_strip_unneeded_symbol))
-    Config.UnneededSymbolsToRemove.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E =
+            Config.UnneededSymbolsToRemove.addMatcher(NameOrPattern::create(
+                Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_strip_unneeded_symbols))
     if (Error E = addSymbolsFromFile(Config.UnneededSymbolsToRemove, DC.Alloc,
-                                     Arg->getValue(), UseRegex))
+                                     Arg->getValue(), SymbolMatchStyle,
+                                     ErrorCallback))
       return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_keep_symbol))
-    Config.SymbolsToKeep.addMatcher({Arg->getValue(), UseRegex});
+    if (Error E = Config.SymbolsToKeep.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_keep_symbols))
-    if (Error E = addSymbolsFromFile(Config.SymbolsToKeep, DC.Alloc,
-                                     Arg->getValue(), UseRegex))
+    if (Error E =
+            addSymbolsFromFile(Config.SymbolsToKeep, DC.Alloc, Arg->getValue(),
+                               SymbolMatchStyle, ErrorCallback))
       return std::move(E);
   for (auto Arg : InputArgs.filtered(OBJCOPY_add_symbol))
     Config.SymbolsToAdd.push_back(Arg->getValue());
@@ -688,7 +756,7 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) {
 // exit.
 Expected<DriverConfig>
 parseStripOptions(ArrayRef<const char *> ArgsArr,
-                  std::function<Error(Error)> ErrorCallback) {
+                  llvm::function_ref<Error(Error)> ErrorCallback) {
   StripOptTable T;
   unsigned MissingArgumentIndex, MissingArgumentCount;
   llvm::opt::InputArgList InputArgs =
@@ -726,7 +794,17 @@ parseStripOptions(ArrayRef<const char *> ArgsArr,
         "multiple input files cannot be used in combination with -o");
 
   CopyConfig Config;
-  bool UseRegexp = InputArgs.hasArg(STRIP_regex);
+
+  if (InputArgs.hasArg(STRIP_regex) && InputArgs.hasArg(STRIP_wildcard))
+    return createStringError(errc::invalid_argument,
+                             "--regex and --wildcard are incompatible");
+  MatchStyle SectionMatchStyle =
+      InputArgs.hasArg(STRIP_regex) ? MatchStyle::Regex : MatchStyle::Wildcard;
+  MatchStyle SymbolMatchStyle = InputArgs.hasArg(STRIP_regex)
+                                    ? MatchStyle::Regex
+                                    : InputArgs.hasArg(STRIP_wildcard)
+                                          ? MatchStyle::Wildcard
+                                          : MatchStyle::Literal;
   Config.AllowBrokenLinks = InputArgs.hasArg(STRIP_allow_broken_links);
   Config.StripDebug = InputArgs.hasArg(STRIP_strip_debug);
 
@@ -744,16 +822,24 @@ parseStripOptions(ArrayRef<const char *> ArgsArr,
   Config.KeepFileSymbols = InputArgs.hasArg(STRIP_keep_file_symbols);
 
   for (auto Arg : InputArgs.filtered(STRIP_keep_section))
-    Config.KeepSection.addMatcher({Arg->getValue(), UseRegexp});
+    if (Error E = Config.KeepSection.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SectionMatchStyle, ErrorCallback)))
+      return std::move(E);
 
   for (auto Arg : InputArgs.filtered(STRIP_remove_section))
-    Config.ToRemove.addMatcher({Arg->getValue(), UseRegexp});
+    if (Error E = Config.ToRemove.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SectionMatchStyle, ErrorCallback)))
+      return std::move(E);
 
   for (auto Arg : InputArgs.filtered(STRIP_strip_symbol))
-    Config.SymbolsToRemove.addMatcher({Arg->getValue(), UseRegexp});
+    if (Error E = Config.SymbolsToRemove.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
 
   for (auto Arg : InputArgs.filtered(STRIP_keep_symbol))
-    Config.SymbolsToKeep.addMatcher({Arg->getValue(), UseRegexp});
+    if (Error E = Config.SymbolsToKeep.addMatcher(NameOrPattern::create(
+            Arg->getValue(), SymbolMatchStyle, ErrorCallback)))
+      return std::move(E);
 
   if (!InputArgs.hasArg(STRIP_no_strip_all) && !Config.StripDebug &&
       !Config.StripUnneeded && Config.DiscardMode == DiscardType::None &&
diff --git a/llvm/tools/llvm-objcopy/CopyConfig.h b/llvm/tools/llvm-objcopy/CopyConfig.h
index 745af0ce..55a55d3 100644
--- a/llvm/tools/llvm-objcopy/CopyConfig.h
+++ b/llvm/tools/llvm-objcopy/CopyConfig.h
@@ -19,6 +19,7 @@
 #include "llvm/Object/ELFTypes.h"
 #include "llvm/Support/Allocator.h"
 #include "llvm/Support/Error.h"
+#include "llvm/Support/GlobPattern.h"
 #include "llvm/Support/Regex.h"
 // Necessary for llvm::DebugCompressionType::None
 #include "llvm/Target/TargetOptions.h"
@@ -88,28 +89,58 @@ enum class DiscardType {
   Locals, // --discard-locals (-X)
 };
 
-class NameOrRegex {
+enum class MatchStyle {
+  Literal,  // Default for symbols.
+  Wildcard, // Default for sections, or enabled with --wildcard (-w).
+  Regex,    // Enabled with --regex.
+};
+
+class NameOrPattern {
   StringRef Name;
   // Regex is shared between multiple CopyConfig instances.
   std::shared_ptr<Regex> R;
+  std::shared_ptr<GlobPattern> G;
+  bool IsPositiveMatch = true;
+
+  NameOrPattern(StringRef N) : Name(N) {}
+  NameOrPattern(std::shared_ptr<Regex> R) : R(R) {}
+  NameOrPattern(std::shared_ptr<GlobPattern> G, bool IsPositiveMatch)
+      : G(G), IsPositiveMatch(IsPositiveMatch) {}
 
 public:
-  NameOrRegex(StringRef Pattern, bool IsRegex);
-  bool operator==(StringRef S) const { return R ? R->match(S) : Name == S; }
+  // ErrorCallback is used to handle recoverable errors. An Error returned
+  // by the callback aborts the parsing and is then returned by this function.
+  static Expected<NameOrPattern>
+  create(StringRef Pattern, MatchStyle MS,
+         llvm::function_ref<Error(Error)> ErrorCallback);
+
+  bool isPositiveMatch() const { return IsPositiveMatch; }
+  bool operator==(StringRef S) const {
+    return R ? R->match(S) : G ? G->match(S) : Name == S;
+  }
   bool operator!=(StringRef S) const { return !operator==(S); }
 };
 
 // Matcher that checks symbol or section names against the command line flags
 // provided for that option.
 class NameMatcher {
-  std::vector<NameOrRegex> Matchers;
+  std::vector<NameOrPattern> PosMatchers;
+  std::vector<NameOrPattern> NegMatchers;
 
 public:
-  void addMatcher(NameOrRegex Matcher) {
-    Matchers.push_back(std::move(Matcher));
+  Error addMatcher(Expected<NameOrPattern> Matcher) {
+    if (!Matcher)
+      return Matcher.takeError();
+    if (Matcher->isPositiveMatch())
+      PosMatchers.push_back(std::move(*Matcher));
+    else
+      NegMatchers.push_back(std::move(*Matcher));
+    return Error::success();
+  }
+  bool matches(StringRef S) const {
+    return is_contained(PosMatchers, S) && !is_contained(NegMatchers, S);
   }
-  bool matches(StringRef S) const { return is_contained(Matchers, S); }
-  bool empty() const { return Matchers.empty(); }
+  bool empty() const { return PosMatchers.empty() && NegMatchers.empty(); }
 };
 
 // Configuration for copying/stripping a single file.
@@ -214,8 +245,11 @@ struct DriverConfig {
 
 // ParseObjcopyOptions returns the config and sets the input arguments. If a
 // help flag is set then ParseObjcopyOptions will print the help messege and
-// exit.
-Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr);
+// exit. ErrorCallback is used to handle recoverable errors. An Error returned
+// by the callback aborts the parsing and is then returned by this function.
+Expected<DriverConfig>
+parseObjcopyOptions(ArrayRef<const char *> ArgsArr,
+                    llvm::function_ref<Error(Error)> ErrorCallback);
 
 // ParseStripOptions returns the config and sets the input arguments. If a
 // help flag is set then ParseStripOptions will print the help messege and
@@ -223,7 +257,7 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr);
 // by the callback aborts the parsing and is then returned by this function.
 Expected<DriverConfig>
 parseStripOptions(ArrayRef<const char *> ArgsArr,
-                  std::function<Error(Error)> ErrorCallback);
+                  llvm::function_ref<Error(Error)> ErrorCallback);
 
 } // namespace objcopy
 } // namespace llvm
diff --git a/llvm/tools/llvm-objcopy/llvm-objcopy.cpp b/llvm/tools/llvm-objcopy/llvm-objcopy.cpp
index db6d751..a68210f 100644
--- a/llvm/tools/llvm-objcopy/llvm-objcopy.cpp
+++ b/llvm/tools/llvm-objcopy/llvm-objcopy.cpp
@@ -335,7 +335,7 @@ int main(int argc, char **argv) {
 
   Expected<DriverConfig> DriverConfig =
       IsStrip ? parseStripOptions(Args, reportWarning)
-              : parseObjcopyOptions(Args);
+              : parseObjcopyOptions(Args, reportWarning);
   if (!DriverConfig) {
     logAllUnhandledErrors(DriverConfig.takeError(),
                           WithColor::error(errs(), ToolName));