From ab60afb234704165a622b57e9ba0476d8d533074 Mon Sep 17 00:00:00 2001
From: James Molloy <jmolloy@google.com>
Date: Tue, 14 Aug 2018 01:16:45 -0700
Subject: [PATCH] [mlir] Allow C-style escapes in Lexer

This patch passes the raw, unescaped value through to the rest of the stack. Partial escaping is a total pain to deal with, so we either need to implement escaping properly (ideally using a third party library like absl, I don't think LLVM has one that can handle the proper gamut of escape codes) or don't escape. I chose the latter for this patch.

PiperOrigin-RevId: 208608945
---
 mlir/lib/Parser/Lexer.cpp | 6 ++++++
 mlir/lib/Parser/Token.cpp | 5 ++---
 mlir/test/IR/parser.mlir  | 8 ++++++++
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/mlir/lib/Parser/Lexer.cpp b/mlir/lib/Parser/Lexer.cpp
index 91fa8ad666af..885608a02737 100644
--- a/mlir/lib/Parser/Lexer.cpp
+++ b/mlir/lib/Parser/Lexer.cpp
@@ -323,6 +323,12 @@ Token Lexer::lexString(const char *tokStart) {
     case '\v':
     case '\f':
       return emitError(curPtr-1, "expected '\"' in string literal");
+    case '\\':
+      // Handle explicitly \" -> ".
+      // TODO(someone): define more escaping rules.
+      if (*curPtr == '"')
+        ++curPtr;
+      continue;
 
     default:
       continue;
diff --git a/mlir/lib/Parser/Token.cpp b/mlir/lib/Parser/Token.cpp
index 9fc2b2f40d18..2bce68153c27 100644
--- a/mlir/lib/Parser/Token.cpp
+++ b/mlir/lib/Parser/Token.cpp
@@ -81,9 +81,8 @@ Optional<unsigned> Token::getIntTypeBitwidth() const {
 /// Given a 'string' token, return its value, including removing the quote
 /// characters and unescaping the contents of the string.
 std::string Token::getStringValue() const {
-  // TODO: Handle escaping.
-
-  // Just drop the quotes off for now.
+  // Start by dropping the quotes.
+  // TODO: Un-escape the string here instead of passing through the raw content.
   return getSpelling().drop_front().drop_back().str();
 }
 
diff --git a/mlir/test/IR/parser.mlir b/mlir/test/IR/parser.mlir
index 30c6d457e56d..175127a5817b 100644
--- a/mlir/test/IR/parser.mlir
+++ b/mlir/test/IR/parser.mlir
@@ -315,3 +315,11 @@ bb0:
   "foo"(){bar: tensor<??f32>} : () -> ()
   return
 }
+
+// CHECK-LABEL: cfgfunc @stringquote
+cfgfunc @stringquote() -> () {
+bb0:
+// CHECK: "foo"() {bar: "a\"quoted\"string"} : () -> ()
+  "foo"(){bar: "a\"quoted\"string"} : () -> ()
+  return
+}