[llvm-ar] Support N [count] modifier

Summary:
GNU ar supports the 'N' count modifier for the extract (x) and delete (d) operations. When an archive contains multiple members with the same name, this can be used to extract (or delete) them individually. For example:

```
$ llvm-ar t archive.a
foo
foo
$ llvm-ar x archive.a
-> Writes foo twice, overwriting it the second time :( :(
$ llvm-ar xN 1 archive.a foo && mv foo foo.1
$ llvm-ar xN 2 archive.a foo && mv foo foo.2
-> Write foo twice, renaming it in between invocations to preserve all versions
```

Reviewers: ruiu, MaskRay

Reviewed By: ruiu, MaskRay

Subscribers: jdoerfert, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D59503

llvm-svn: 356466

diff --git a/llvm/test/tools/llvm-ar/count.test b/llvm/test/tools/llvm-ar/count.test
new file mode 100644 (file)
index 0000000..81b30bc
--- /dev/null
+++ b/llvm/test/tools/llvm-ar/count.test
@@ -0,0 +1,80 @@
+# Test the 'N' count parameter.
+
+# Get a temp clean cwd to extract into.
+RUN: rm -rf %t && mkdir -p %t && cd %t
+
+RUN: mkdir -p %t/x %t/y %t/z
+RUN: echo hello > %t/x/foo.txt
+RUN: echo cool  > %t/y/foo.txt
+RUN: echo world > %t/z/foo.txt
+RUN: echo fizz   > %t/x/bar.txt
+RUN: echo buzz   > %t/y/bar.txt
+RUN: echo fizbuz > %t/z/bar.txt
+RUN: llvm-ar rc %t/archive.a %t/x/foo.txt %t/y/foo.txt %t/z/foo.txt \
+RUN:     %t/x/bar.txt %t/y/bar.txt %t/z/bar.txt
+RUN: llvm-ar t %t/archive.a | FileCheck %s --check-prefix=LIST-MEMBERS
+
+# Make sure we set it up correctly.
+LIST-MEMBERS:      foo.txt
+LIST-MEMBERS-NEXT: foo.txt
+LIST-MEMBERS-NEXT: foo.txt
+LIST-MEMBERS-NEXT: bar.txt
+LIST-MEMBERS-NEXT: bar.txt
+LIST-MEMBERS-NEXT: bar.txt
+
+# Must be a number.
+RUN: not llvm-ar xN abc %t/archive.a foo.txt 2>&1 | FileCheck %s --check-prefix=ERR-NOT-NUM
+RUN: not llvm-ar xN 0x1 %t/archive.a foo.txt 2>&1 | FileCheck %s --check-prefix=ERR-NOT-NUM
+# Only three members named foo, so 1 <= N <= 3.
+RUN: not llvm-ar xN 0 %t/archive.a foo.txt 2>&1 | FileCheck %s --check-prefix=ERR-NOT-POS
+RUN: not llvm-ar xN 4 %t/archive.a foo.txt 2>&1 | FileCheck %s --check-prefix=ERR-NOT-FOUND
+# N only applies to x/d.
+RUN: not llvm-ar rN 1 %t/archive.a foo.txt 2>&1 | FileCheck %s --check-prefix=ERR-BAD-OP
+
+ERR-NOT-NUM:   error: Value for [count] must be numeric
+ERR-NOT-POS:   error: Value for [count] must be positive
+ERR-BAD-OP:    error: The 'N' modifier can only be specified with the 'x' or 'd' operations
+ERR-NOT-FOUND: error: 'foo.txt' was not found
+
+# Extract individual items.
+
+RUN: rm -f foo.txt bar.txt
+RUN: llvm-ar xN 1 %t/archive.a foo.txt bar.txt
+RUN: cat %t/foo.txt | FileCheck %s --check-prefix=FOO-1
+RUN: cat %t/bar.txt | FileCheck %s --check-prefix=BAR-1
+
+RUN: rm -f foo.txt bar.txt
+RUN: llvm-ar xN 2 %t/archive.a foo.txt bar.txt
+RUN: cat %t/foo.txt | FileCheck %s --check-prefix=FOO-2
+RUN: cat %t/bar.txt | FileCheck %s --check-prefix=BAR-2
+
+RUN: rm -f foo.txt bar.txt
+RUN: llvm-ar xN 3 %t/archive.a foo.txt bar.txt
+RUN: cat %t/foo.txt | FileCheck %s --check-prefix=FOO-3
+RUN: cat %t/bar.txt | FileCheck %s --check-prefix=BAR-3
+
+# Delete individual items.
+
+# Deleting the second member named foo means the new second member of the
+# archive is what used to be the third element.
+RUN: rm -f foo.txt bar.txt
+RUN: llvm-ar dN 2 %t/archive.a foo.txt
+RUN: llvm-ar xN 2 %t/archive.a foo.txt bar.txt
+RUN: cat %t/foo.txt | FileCheck %s --check-prefix=FOO-3
+RUN: cat %t/bar.txt | FileCheck %s --check-prefix=BAR-2
+
+# Deleting the first member from *both* archives means the new first member
+# named foo is the what used to be the third member, and the new first member
+# named bar is what used to be the second member.
+RUN: rm -f foo.txt bar.txt
+RUN: llvm-ar dN 1 %t/archive.a foo.txt bar.txt
+RUN: llvm-ar xN 1 %t/archive.a foo.txt bar.txt
+RUN: cat %t/foo.txt | FileCheck %s --check-prefix=FOO-3
+RUN: cat %t/bar.txt | FileCheck %s --check-prefix=BAR-2
+
+FOO-1: hello
+FOO-2: cool
+FOO-3: world
+BAR-1: fizz
+BAR-2: buzz
+BAR-3: fizbuz

diff --git a/llvm/tools/llvm-ar/llvm-ar.cpp b/llvm/tools/llvm-ar/llvm-ar.cpp
index 7d31103..04c2396 100644 (file)
--- a/llvm/tools/llvm-ar/llvm-ar.cpp
+++ b/llvm/tools/llvm-ar/llvm-ar.cpp
@@ -66,7 +66,7 @@ OPTIONS:
 const char ArHelp[] = R"(
 OVERVIEW: LLVM Archiver
 
-USAGE: llvm-ar [options] [-]<operation>[modifiers] [relpos] <archive> [files]
+USAGE: llvm-ar [options] [-]<operation>[modifiers] [relpos] [count] <archive> [files]
        llvm-ar -M [<mri-script]
 
 OPTIONS:
@@ -97,6 +97,7 @@ MODIFIERS:
   [i] - put [files] before [relpos] (same as [b])
   [l] - ignored for compatibility
   [L] - add archive's contents
+  [N] - use instance [count] of name
   [o] - preserve original dates
   [P] - use full names when matching (implied for thin archives)
   [s] - create an archive index (cf. ranlib)
@@ -187,6 +188,11 @@ static bool AddLibrary = false;      ///< 'L' modifier
 // one variable.
 static std::string RelPos;
 
+// Count parameter for 'N' modifier. This variable specifies which file should
+// match for extract/delete operations when there are multiple matches. This is
+// 1-indexed. A value of 0 is invalid, and implies 'N' is not used.
+static int CountParam = 0;
+
 // This variable holds the name of the archive file as given on the
 // command line.
 static std::string ArchiveName;
@@ -207,6 +213,19 @@ static void getRelPos() {
   PositionalArgs.erase(PositionalArgs.begin());
 }
 
+// Extract the parameter from the command line for the [count] argument
+// associated with the N modifier
+static void getCountParam() {
+  if (PositionalArgs.empty())
+    fail("Expected [count] for N modifier");
+  auto CountParamArg = StringRef(PositionalArgs[0]);
+  if (CountParamArg.getAsInteger(10, CountParam))
+    fail("Value for [count] must be numeric, got: " + CountParamArg);
+  if (CountParam < 1)
+    fail("Value for [count] must be positive, got: " + CountParamArg);
+  PositionalArgs.erase(PositionalArgs.begin());
+}
+
 // Get the archive file name from the command line
 static void getArchive() {
   if (PositionalArgs.empty())
@@ -336,6 +355,9 @@ static ArchiveOperation parseCommandLine() {
     case 'U':
       Deterministic = false;
       break;
+    case 'N':
+      getCountParam();
+      break;
     case 'T':
       Thin = true;
       // Thin archives store path names, so P should be forced.
@@ -371,11 +393,14 @@ static ArchiveOperation parseCommandLine() {
     fail("Only one operation may be specified");
   if (NumPositional > 1)
     fail("You may only specify one of a, b, and i modifiers");
-  if (AddAfter || AddBefore) {
+  if (AddAfter || AddBefore)
     if (Operation != Move && Operation != ReplaceOrInsert)
       fail("The 'a', 'b' and 'i' modifiers can only be specified with "
            "the 'm' or 'r' operations");
-  }
+  if (CountParam)
+    if (Operation != Extract && Operation != Delete)
+      fail("The 'N' modifier can only be specified with the 'x' or 'd' "
+           "operations");
   if (OriginalDates && Operation != Extract)
     fail("The 'o' modifier is only applicable to the 'x' operation");
   if (OnlyUpdate && Operation != ReplaceOrInsert)
@@ -513,6 +538,7 @@ static void performReadOperation(ArchiveOperation Operation,
     fail("extracting from a thin archive is not supported");
 
   bool Filter = !Members.empty();
+  StringMap<int> MemberCount;
   {
     Error Err = Error::success();
     for (auto &C : OldArchive->children(Err)) {
@@ -526,6 +552,8 @@ static void performReadOperation(ArchiveOperation Operation,
         });
         if (I == Members.end())
           continue;
+        if (CountParam && ++MemberCount[Name] != CountParam)
+          continue;
         Members.erase(I);
       }
 
@@ -627,10 +655,10 @@ enum InsertAction {
 static InsertAction computeInsertAction(ArchiveOperation Operation,
                                         const object::Archive::Child &Member,
                                         StringRef Name,
-                                        std::vector<StringRef>::iterator &Pos) {
+                                        std::vector<StringRef>::iterator &Pos,
+                                        StringMap<int> &MemberCount) {
   if (Operation == QuickAppend || Members.empty())
     return IA_AddOldMember;
-
   auto MI = find_if(
       Members, [Name](StringRef Path) { return Name == normalizePath(Path); });
 
@@ -639,8 +667,11 @@ static InsertAction computeInsertAction(ArchiveOperation Operation,
 
   Pos = MI;
 
-  if (Operation == Delete)
+  if (Operation == Delete) {
+    if (CountParam && ++MemberCount[Name] != CountParam)
+      return IA_AddOldMember;
     return IA_Delete;
+  }
 
   if (Operation == Move)
     return IA_MoveOldMember;
@@ -683,6 +714,7 @@ computeNewArchiveMembers(ArchiveOperation Operation,
   StringRef PosName = normalizePath(RelPos);
   if (OldArchive) {
     Error Err = Error::success();
+    StringMap<int> MemberCount;
     for (auto &Child : OldArchive->children(Err)) {
       int Pos = Ret.size();
       Expected<StringRef> NameOrErr = Child.getName();
@@ -698,7 +730,7 @@ computeNewArchiveMembers(ArchiveOperation Operation,
 
       std::vector<StringRef>::iterator MemberI = Members.end();
       InsertAction Action =
-          computeInsertAction(Operation, Child, Name, MemberI);
+          computeInsertAction(Operation, Child, Name, MemberI, MemberCount);
       switch (Action) {
       case IA_AddOldMember:
         addChildMember(Ret, Child, /*FlattenArchive=*/Thin);
@@ -715,7 +747,12 @@ computeNewArchiveMembers(ArchiveOperation Operation,
         addMember(Moved, *MemberI);
         break;
       }
-      if (MemberI != Members.end())
+      // When processing elements with the count param, we need to preserve the
+      // full members list when iterating over all archive members. For
+      // instance, "llvm-ar dN 2 archive.a member.o" should delete the second
+      // file named member.o it sees; we are not done with member.o the first
+      // time we see it in the archive.
+      if (MemberI != Members.end() && !CountParam)
         Members.erase(MemberI);
     }
     failIfError(std::move(Err));