Updated string escaping in the assembler.

Strings are now escaped correctly when assembling.
TODO dissassembler support for strange strings (newlines for example).

source/text.cpp

@@ -110,11 +110,23 @@ spv_result_t spvTextToLiteral(const char* textValue, spv_literal_t* pLiteral) {
     // TODO(dneto): Allow escaping.
     if (len < 2 || textValue[0] != '"' || textValue[len - 1] != '"')
       return SPV_FAILED_MATCH;
+    bool escaping = false;
+    size_t write_index = 0;
+    for(const char* val = textValue + 1; val != textValue + len - 1; ++val) {
+      if ((*val == '\\') && (!escaping)) {
+        escaping = true;
+      } else {
+        // Have to save space for the null-terminator
+        if (write_index >= sizeof(pLiteral->value.str) - 1)
+          return SPV_ERROR_OUT_OF_MEMORY;
+        pLiteral->value.str[write_index] = *val;
+        escaping = false;
+        ++write_index;
+      }
+    }
+
     pLiteral->type = SPV_LITERAL_TYPE_STRING;
-    // Need room for the null-terminator.
-    if (len >= sizeof(pLiteral->value.str)) return SPV_ERROR_OUT_OF_MEMORY;
-    strncpy(pLiteral->value.str, textValue + 1, len - 2);
-    pLiteral->value.str[len - 2] = 0;
+    pLiteral->value.str[write_index] = '\0';
   } else if (numPeriods == 1) {
     double d = std::strtod(textValue, nullptr);
     float f = (float)d;

source/text.h

@@ -54,10 +54,10 @@ typedef struct spv_literal_t {
     uint64_t u64;
     float f;
     double d;
-    // Allow room for the null terminator, and two surrounding quotes.
+    // Allow room for the null terminator
     // TODO(dneto): This is a very large array.  We should use a
     // different kind of container.
-    char str[SPV_LIMIT_LITERAL_STRING_BYTES_MAX + 3];
+    char str[SPV_LIMIT_LITERAL_STRING_BYTES_MAX + 1];
   } value;
 } spv_literal_t;
 

syntax.md

@@ -27,14 +27,16 @@ but the assembler does not enforce this rule.
 
 The opcode names and expected operands are described in section 3 of
 the SPIR-V specification.  An operand is one of:
-* a literal integer: A decimal integer, or a hexadecimal integer.
-  A hexadecimal integer is indicated by a leading `0x` or `0X`.  A hex
-  integer supplied for a signed integer value will be sign-extended.
-  For example, `0xffff` supplied as the literal for an `OpConstant`
-  on a signed 16-bit integer type will be interpreted as the value `-1`.
+* a literal integer: A decimal integer, or a hexadecimal integer
+  (indicated by a leading `0x`).
 * a literal floating point number.
-* a literal string, surrounded by double-quotes `"`. TODO: describe quoting and
-escaping rules.
+* a literal string.
+   * A literal string is everything following a double-quote `"` until the
+     following un-escaped double-quote, this includes special characters such as
+     newlines.
+   * A backslash `\` may be used to escape characters in the string. The `\`
+     may be used to escape a double-quote or a `\` but is simply ignored when
+     preceding any other character.
 * a named enumerated value, specific to that operand position.  For example,
 the `OpMemoryModel` takes a named Addressing Model operand (e.g. `Logical` or
 `Physical32`), and a named Memory Model operand (e.g. `Simple` or `OpenCL`).
@@ -154,11 +156,10 @@ instruction.)
 The assembler processes the tokens encountered in alternate parsing mode as
 follows:
 
-* If the token is a number literal, since context may be lost, the number
-  is interpreted as a 32-bit value and output as a single word.  In order to
-  specify multiple-word literals in alternate-parsing mode, further uses of
-  `!<integer>` tokens may be required.
-  All formats supported by `strtoul()` are accepted.
+* If the token is a number literal, it outputs that number as one or more words,
+  as defined in the SPIR-V specification for Literal Number.  The number must
+  fit within the unsigned 32-bit range.  All formats supported by `strtoul()`
+  are accepted.
 * If the token is a string literal, it outputs a sequence of words representing
   the string as defined in the SPIR-V specification for Literal String.
 * If the token is an ID, it outputs the ID's internal number.

test/TextLiteral.cpp

@@ -105,32 +105,37 @@ TEST(TextLiteral, BadString) {
   EXPECT_EQ(SPV_FAILED_MATCH, spvTextToLiteral("a\"", &l));
 }
 
-TEST(TextLiteral, GoodString) {
+class GoodStringTest
+    : public ::testing::TestWithParam<std::pair<const char*, const char*>> {};
+
+TEST_P(GoodStringTest, GoodStrings) {
   spv_literal_t l;
 
-  ASSERT_EQ(SPV_SUCCESS, spvTextToLiteral("\"-\"", &l));
+  ASSERT_EQ(SPV_SUCCESS, spvTextToLiteral(std::get<0>(GetParam()), &l));
   EXPECT_EQ(SPV_LITERAL_TYPE_STRING, l.type);
-  EXPECT_STREQ("-", l.value.str);
-
-  ASSERT_EQ(SPV_SUCCESS, spvTextToLiteral("\"--\"", &l));
-  EXPECT_EQ(SPV_LITERAL_TYPE_STRING, l.type);
-  EXPECT_STREQ("--", l.value.str);
-
-  ASSERT_EQ(SPV_SUCCESS, spvTextToLiteral("\"1-2\"", &l));
-  EXPECT_EQ(SPV_LITERAL_TYPE_STRING, l.type);
-  EXPECT_STREQ("1-2", l.value.str);
-
-  ASSERT_EQ(SPV_SUCCESS, spvTextToLiteral("\"123a\"", &l));
-  EXPECT_EQ(SPV_LITERAL_TYPE_STRING, l.type);
-  EXPECT_STREQ("123a", l.value.str);
-
-  ASSERT_EQ(SPV_SUCCESS, spvTextToLiteral("\"12.2.3\"", &l));
-  EXPECT_EQ(SPV_LITERAL_TYPE_STRING, l.type);
-  EXPECT_STREQ("12.2.3", l.value.str);
-
-  // TODO(dneto): escaping in strings is not supported yet.
+  EXPECT_STREQ(std::get<1>(GetParam()), l.value.str);
 }
 
+#define CASE(NAME) spv::Decoration##NAME, #NAME
+INSTANTIATE_TEST_CASE_P(
+    TextLiteral, GoodStringTest,
+    ::testing::ValuesIn(std::vector<std::pair<const char*, const char*>>{
+      {R"("-")", "-"},
+      {R"("--")", "--"},
+      {R"("1-2")", "1-2"},
+      {R"("123a")", "123a"},
+      {R"("12.2.3")", "12.2.3"},
+      {R"("\"")", "\""},
+      {R"("\\")", "\\"},
+      {"\"\\foo\nbar\"", "foo\nbar"},
+      {"\"\\foo\\\nbar\"", "foo\nbar"},
+      {"\"\U00E4BAB2\"", "\U00E4BAB2"},
+      {"\"\\\U00E4BAB2\"", "\U00E4BAB2"},
+      {"\"this \\\" and this \\\\ and \\\U00E4BAB2\"",
+        "this \" and this \\ and \U00E4BAB2"}
+    }));
+#undef CASE
+
 TEST(TextLiteral, StringTooLong) {
   spv_literal_t l;
   std::string too_long = std::string("\"") +