allow_invalid_utf16

boostorg · Apr 10, 2024 · dc95216 · dc95216
1 parent 9f85ed6
commit dc95216
Show file tree

Hide file tree

Showing 6 changed files with 265 additions and 70 deletions.
diff --git a/doc/qbk/io/parsing.qbk b/doc/qbk/io/parsing.qbk
@@ -103,6 +103,12 @@ with __parse_options__ is possible:
 
 [doc_parsing_6]
 
+When 'allow_invalid_utf16' is enabled, the parser will not throw an error in the case of
+illegal leading, trailing, or half a surrogate. Instead, it will replace the
+invalid UTF-16 code point(s) with the Unicode replacement character.
+
+[doc_parsing_15]
+
 [caution When enabling comment support take extra care not to drop whitespace
     when reading the input. For example, `std::getline` removes the
     endline characters from the string it produces.]

diff --git a/include/boost/json/basic_parser.hpp b/include/boost/json/basic_parser.hpp
@@ -407,30 +407,34 @@ class basic_parser
         std::integral_constant<bool, StackEmpty_> stack_empty,
         std::integral_constant<bool, AllowComments_> allow_comments,
         /*std::integral_constant<bool, AllowTrailing_>*/ bool allow_trailing,
-        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8);
+        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8,
+        bool allow_bad_utf16);
 
     template<bool AllowComments_/*,
         bool AllowTrailing_, bool AllowBadUTF8_*/>
     const char* resume_value(const char* p,
         std::integral_constant<bool, AllowComments_> allow_comments,
         /*std::integral_constant<bool, AllowTrailing_>*/ bool allow_trailing,
-        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8);
+        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8,
+        bool allow_bad_utf16);
 
     template<bool StackEmpty_, bool AllowComments_/*,
         bool AllowTrailing_, bool AllowBadUTF8_*/>
     const char* parse_object(const char* p,
         std::integral_constant<bool, StackEmpty_> stack_empty,
         std::integral_constant<bool, AllowComments_> allow_comments,
         /*std::integral_constant<bool, AllowTrailing_>*/ bool allow_trailing,
-        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8);
+        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8,
+        bool allow_bad_utf16);
 
     template<bool StackEmpty_, bool AllowComments_/*,
         bool AllowTrailing_, bool AllowBadUTF8_*/>
     const char* parse_array(const char* p,
         std::integral_constant<bool, StackEmpty_> stack_empty,
         std::integral_constant<bool, AllowComments_> allow_comments,
         /*std::integral_constant<bool, AllowTrailing_>*/ bool allow_trailing,
-        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8);
+        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8,
+        bool allow_bad_utf16);
 
     template<int Literal>
     const char* parse_literal(const char* p,
@@ -441,7 +445,8 @@ class basic_parser
     const char* parse_string(const char* p,
         std::integral_constant<bool, StackEmpty_> stack_empty,
         std::integral_constant<bool, IsKey_> is_key,
-        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8);
+        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8,
+        bool allow_bad_utf16);
 
     template<bool StackEmpty_, char First_, number_precision Numbers_>
     const char* parse_number(const char* p,
@@ -454,7 +459,8 @@ class basic_parser
     const char* parse_unescaped(const char* p,
         std::integral_constant<bool, StackEmpty_> stack_empty,
         std::integral_constant<bool, IsKey_> is_key,
-        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8);
+        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8,
+        bool allow_bad_utf16);
 
     template<bool StackEmpty_/*, bool IsKey_,
         bool AllowBadUTF8_*/>
@@ -463,7 +469,8 @@ class basic_parser
         std::size_t total,
         std::integral_constant<bool, StackEmpty_> stack_empty,
         /*std::integral_constant<bool, IsKey_>*/ bool is_key,
-        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8);
+        /*std::integral_constant<bool, AllowBadUTF8_>*/ bool allow_bad_utf8,
+        bool allow_bad_utf16);
 
     // intentionally private
     std::size_t