[llvm] 44f399c - [FileCheck] Add a literal check directive modifier

Jacques Pienaar via llvm-commits llvm-commits at lists.llvm.org
Fri Dec 18 17:26:52 PST 2020


Author: Jacques Pienaar
Date: 2020-12-18T17:26:15-08:00
New Revision: 44f399ccc12e27d20bae1ea7e712ef7f71e2ff3a

URL: https://github.com/llvm/llvm-project/commit/44f399ccc12e27d20bae1ea7e712ef7f71e2ff3a
DIFF: https://github.com/llvm/llvm-project/commit/44f399ccc12e27d20bae1ea7e712ef7f71e2ff3a.diff

LOG: [FileCheck] Add a literal check directive modifier

Introduce CHECK modifiers that change the behavior of the CHECK
directive. Also add a LITERAL modifier for cases where matching could
end requiring escaping strings interpreted as regex where only
literal/fixed string matching is desired (making the CHECK's more
difficult to write/fragile and difficult to interpret).

Added: 
    llvm/test/FileCheck/check-literal.txt

Modified: 
    llvm/docs/CommandGuide/FileCheck.rst
    llvm/include/llvm/FileCheck/FileCheck.h
    llvm/lib/FileCheck/FileCheck.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/docs/CommandGuide/FileCheck.rst b/llvm/docs/CommandGuide/FileCheck.rst
index bf8147abf0a3..398cce1f8a8c 100644
--- a/llvm/docs/CommandGuide/FileCheck.rst
+++ b/llvm/docs/CommandGuide/FileCheck.rst
@@ -660,6 +660,30 @@ simply uniquely match a single line in the file being verified.
 
 ``CHECK-LABEL:`` directives cannot contain variable definitions or uses.
 
+Directive modifiers
+~~~~~~~~~~~~~~~~~~~
+
+A directive modifier can be append to a directive by following the directive
+with ``{<modifier>}`` where the only supported value for ``<modifier>`` is
+``LITERAL``.
+
+The ``LITERAL`` directive modifier can be used to perform a literal match. The
+modifier results in the directive not recognizing any syntax to perform regex
+matching, variable capture or any substitutions. This is useful when the text
+to match would require excessive escaping otherwise. For example, the
+following will perform literal matches rather than considering these as
+regular expressions:
+
+.. code-block:: text
+
+   Input: [[[10, 20]], [[30, 40]]]
+   Output %r10: [[10, 20]]
+   Output %r10: [[30, 40]]
+
+   ; CHECK{LITERAL}: [[[10, 20]], [[30, 40]]]
+   ; CHECK-DAG{LITERAL}: [[30, 40]]
+   ; CHECK-DAG{LITERAL}: [[10, 20]]
+
 FileCheck Regex Matching Syntax
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

diff  --git a/llvm/include/llvm/FileCheck/FileCheck.h b/llvm/include/llvm/FileCheck/FileCheck.h
index b10db710ef38..b44ab025694b 100644
--- a/llvm/include/llvm/FileCheck/FileCheck.h
+++ b/llvm/include/llvm/FileCheck/FileCheck.h
@@ -17,6 +17,7 @@
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Regex.h"
 #include "llvm/Support/SourceMgr.h"
+#include <bitset>
 #include <string>
 #include <vector>
 
@@ -64,12 +65,23 @@ enum FileCheckKind {
   CheckBadCount
 };
 
+enum FileCheckKindModifier {
+  /// Modifies directive to perform literal match.
+  ModifierLiteral = 0,
+
+  // The number of modifier.
+  Size
+};
+
 class FileCheckType {
   FileCheckKind Kind;
   int Count; ///< optional Count for some checks
+  /// Modifers for the check directive.
+  std::bitset<FileCheckKindModifier::Size> Modifiers;
 
 public:
-  FileCheckType(FileCheckKind Kind = CheckNone) : Kind(Kind), Count(1) {}
+  FileCheckType(FileCheckKind Kind = CheckNone)
+      : Kind(Kind), Count(1), Modifiers() {}
   FileCheckType(const FileCheckType &) = default;
   FileCheckType &operator=(const FileCheckType &) = default;
 
@@ -78,8 +90,19 @@ class FileCheckType {
   int getCount() const { return Count; }
   FileCheckType &setCount(int C);
 
+  bool isLiteralMatch() const {
+    return Modifiers[FileCheckKindModifier::ModifierLiteral];
+  }
+  FileCheckType &setLiteralMatch(bool Literal = true) {
+    Modifiers.set(FileCheckKindModifier::ModifierLiteral, Literal);
+    return *this;
+  }
+
   // \returns a description of \p Prefix.
   std::string getDescription(StringRef Prefix) const;
+
+  // \returns a description of \p Modifiers.
+  std::string getModifiersDescription() const;
 };
 } // namespace Check
 

diff  --git a/llvm/lib/FileCheck/FileCheck.cpp b/llvm/lib/FileCheck/FileCheck.cpp
index d6fda5b36e69..c6a5b69e2055 100644
--- a/llvm/lib/FileCheck/FileCheck.cpp
+++ b/llvm/lib/FileCheck/FileCheck.cpp
@@ -917,6 +917,12 @@ bool Pattern::parsePattern(StringRef PatternStr, StringRef Prefix,
     return false;
   }
 
+  // If literal check, set fixed string.
+  if (CheckTy.isLiteralMatch()) {
+    FixedStr = PatternStr;
+    return false;
+  }
+
   // Check to see if this is a fixed string, or if it has regex pieces.
   if (!MatchFullLinesHere &&
       (PatternStr.size() < 2 || (PatternStr.find("{{") == StringRef::npos &&
@@ -1588,26 +1594,43 @@ Check::FileCheckType &Check::FileCheckType::setCount(int C) {
   return *this;
 }
 
+std::string Check::FileCheckType::getModifiersDescription() const {
+  if (Modifiers.none())
+    return "";
+  std::string Ret;
+  raw_string_ostream OS(Ret);
+  OS << '{';
+  if (isLiteralMatch())
+    OS << "LITERAL";
+  OS << '}';
+  return OS.str();
+}
+
 std::string Check::FileCheckType::getDescription(StringRef Prefix) const {
+  // Append directive modifiers.
+  auto WithModifiers = [this, Prefix](StringRef Str) -> std::string {
+    return (Prefix + Str + getModifiersDescription()).str();
+  };
+
   switch (Kind) {
   case Check::CheckNone:
     return "invalid";
   case Check::CheckPlain:
     if (Count > 1)
-      return Prefix.str() + "-COUNT";
-    return std::string(Prefix);
+      return WithModifiers("-COUNT");
+    return WithModifiers("");
   case Check::CheckNext:
-    return Prefix.str() + "-NEXT";
+    return WithModifiers("-NEXT");
   case Check::CheckSame:
-    return Prefix.str() + "-SAME";
+    return WithModifiers("-SAME");
   case Check::CheckNot:
-    return Prefix.str() + "-NOT";
+    return WithModifiers("-NOT");
   case Check::CheckDAG:
-    return Prefix.str() + "-DAG";
+    return WithModifiers("-DAG");
   case Check::CheckLabel:
-    return Prefix.str() + "-LABEL";
+    return WithModifiers("-LABEL");
   case Check::CheckEmpty:
-    return Prefix.str() + "-EMPTY";
+    return WithModifiers("-EMPTY");
   case Check::CheckComment:
     return std::string(Prefix);
   case Check::CheckEOF:
@@ -1625,23 +1648,45 @@ FindCheckType(const FileCheckRequest &Req, StringRef Buffer, StringRef Prefix) {
   if (Buffer.size() <= Prefix.size())
     return {Check::CheckNone, StringRef()};
 
-  char NextChar = Buffer[Prefix.size()];
-
-  StringRef Rest = Buffer.drop_front(Prefix.size() + 1);
-
+  StringRef Rest = Buffer.drop_front(Prefix.size());
   // Check for comment.
   if (llvm::is_contained(Req.CommentPrefixes, Prefix)) {
-    if (NextChar == ':')
+    if (Rest.consume_front(":"))
       return {Check::CheckComment, Rest};
     // Ignore a comment prefix if it has a suffix like "-NOT".
     return {Check::CheckNone, StringRef()};
   }
 
-  // Verify that the : is present after the prefix.
-  if (NextChar == ':')
+  auto ConsumeModifiers = [&](Check::FileCheckType Ret)
+      -> std::pair<Check::FileCheckType, StringRef> {
+    if (Rest.consume_front(":"))
+      return {Ret, Rest};
+    if (!Rest.consume_front("{"))
+      return {Check::CheckNone, StringRef()};
+
+    // Parse the modifiers, speparated by commas.
+    do {
+      // Allow whitespace in modifiers list.
+      Rest = Rest.ltrim();
+      if (Rest.consume_front("LITERAL"))
+        Ret.setLiteralMatch();
+      else
+        return {Check::CheckNone, Rest};
+      // Allow whitespace in modifiers list.
+      Rest = Rest.ltrim();
+    } while (Rest.consume_front(","));
+    if (!Rest.consume_front("}:"))
+      return {Check::CheckNone, Rest};
+    return {Ret, Rest};
+  };
+
+  // Verify that the prefix is followed by directive modifiers or a colon.
+  if (Rest.consume_front(":"))
     return {Check::CheckPlain, Rest};
+  if (Rest.front() == '{')
+    return ConsumeModifiers(Check::CheckPlain);
 
-  if (NextChar != '-')
+  if (!Rest.consume_front("-"))
     return {Check::CheckNone, StringRef()};
 
   if (Rest.consume_front("COUNT-")) {
@@ -1651,29 +1696,12 @@ FindCheckType(const FileCheckRequest &Req, StringRef Buffer, StringRef Prefix) {
       return {Check::CheckBadCount, Rest};
     if (Count <= 0 || Count > INT32_MAX)
       return {Check::CheckBadCount, Rest};
-    if (!Rest.consume_front(":"))
+    if (Rest.front() != ':' && Rest.front() != '{')
       return {Check::CheckBadCount, Rest};
-    return {Check::FileCheckType(Check::CheckPlain).setCount(Count), Rest};
+    return ConsumeModifiers(
+        Check::FileCheckType(Check::CheckPlain).setCount(Count));
   }
 
-  if (Rest.consume_front("NEXT:"))
-    return {Check::CheckNext, Rest};
-
-  if (Rest.consume_front("SAME:"))
-    return {Check::CheckSame, Rest};
-
-  if (Rest.consume_front("NOT:"))
-    return {Check::CheckNot, Rest};
-
-  if (Rest.consume_front("DAG:"))
-    return {Check::CheckDAG, Rest};
-
-  if (Rest.consume_front("LABEL:"))
-    return {Check::CheckLabel, Rest};
-
-  if (Rest.consume_front("EMPTY:"))
-    return {Check::CheckEmpty, Rest};
-
   // You can't combine -NOT with another suffix.
   if (Rest.startswith("DAG-NOT:") || Rest.startswith("NOT-DAG:") ||
       Rest.startswith("NEXT-NOT:") || Rest.startswith("NOT-NEXT:") ||
@@ -1681,6 +1709,24 @@ FindCheckType(const FileCheckRequest &Req, StringRef Buffer, StringRef Prefix) {
       Rest.startswith("EMPTY-NOT:") || Rest.startswith("NOT-EMPTY:"))
     return {Check::CheckBadNot, Rest};
 
+  if (Rest.consume_front("NEXT"))
+    return ConsumeModifiers(Check::CheckNext);
+
+  if (Rest.consume_front("SAME"))
+    return ConsumeModifiers(Check::CheckSame);
+
+  if (Rest.consume_front("NOT"))
+    return ConsumeModifiers(Check::CheckNot);
+
+  if (Rest.consume_front("DAG"))
+    return ConsumeModifiers(Check::CheckDAG);
+
+  if (Rest.consume_front("LABEL"))
+    return ConsumeModifiers(Check::CheckLabel);
+
+  if (Rest.consume_front("EMPTY"))
+    return ConsumeModifiers(Check::CheckEmpty);
+
   return {Check::CheckNone, Rest};
 }
 

diff  --git a/llvm/test/FileCheck/check-literal.txt b/llvm/test/FileCheck/check-literal.txt
new file mode 100644
index 000000000000..abef08293bda
--- /dev/null
+++ b/llvm/test/FileCheck/check-literal.txt
@@ -0,0 +1,62 @@
+; RUN: FileCheck -check-prefix=A -input-file %s %s
+
+;; This tests the LITERAL directive modifier.
+
+The result is "5371, 5372, 5373, 5374"
+
+The result is "[[[5371]], [[5372]], [[5373]], [[5374]]]"
+[[[5375]], [[5376]],
+[[[5377]], [[5378]],
+{{there you go.*}}
+
+[[10]]
+[[20]]
+[[50]]
+
+;; These should all not match.
+; A{}: 5371, 5372,
+; A{LITERAL} 5371, 5372,
+; A{LITERAL 5371, 5372,
+; A{LITERAL,} 5371, 5372,
+; A{, LITERAL} 5371, 5372,
+
+; A: 5371, 5372,
+; A-SAME: 5373, 5374
+; A{LITERAL}: [[[5371]], [[5372]],
+; A-SAME{LITERAL}: [[5373]], [[5374]]]
+
+;; Modifier list allows whitespace.
+; A{  LITERAL  }: [[[5375]], [[5376]],
+;; Modifiers are combined into a set and repetition is allowed.
+; A{LITERAL , LITERAL}: [[[5377]], [[5378]],
+
+; A-NEXT{LITERAL}: {{there you go.*}}
+; A-NOT{LITERAL}: [[50]]
+; A-DAG{LITERAL}: [[20]]
+; A-DAG{LITERAL}: [[10]]
+; A{LITERAL}: [[50]]
+
+; RUN: %ProtectFileCheckOutput \
+; RUN: not FileCheck %s --input-file %s --check-prefix=INVALID 2>&1 | \
+; RUN:   FileCheck %s --check-prefix=CHECK-INVALID
+
+;; Ensure invalid modifier skipped.
+
+; INVALID{BADMODIFIER}: 6371, 6372,
+; CHECK-INVALID: no check strings found with prefix 'INVALID
+
+; RUN: %ProtectFileCheckOutput \
+; RUN: not FileCheck %s --input-file %s --check-prefix=CHECK-ERRNOT 2>&1 | \
+; RUN:   FileCheck %s --check-prefix=ERRNOT
+
+;; This ensures a failure is correctly reported when a NOT directive with a
+;; LITERAL modifier matches.
+
+[[a]]
+[[b]]
+[[c]]
+
+; CHECK-ERRNOT{LITERAL}: [[a]]
+; CHECK-ERRNOT-NOT{LITERAL}: [[b]]
+; CHECK-ERRNOT{LITERAL}: [[c]]
+; ERRNOT: no match expected


        


More information about the llvm-commits mailing list