diff --git a/Changelog.md b/Changelog.md --- a/Changelog.md +++ b/Changelog.md @@ -1,5 +1,11 @@ # Changelog for `proto-lens` +## v0.7.1.0 +- Support GHC 9.0. +- Fixed parsing of UTF8 chars in text format proto string literals. +- Support all valid text format boolean field values +- Remove redundant (.&. 127) from putVarInt (#396) + ## v0.7.0.0 - Support GHC 8.10. - Add a method to `Data.ProtoLens.Message` for getting the `DescriptorProto` diff --git a/proto-lens-imports/google/protobuf/compiler/plugin.proto b/proto-lens-imports/google/protobuf/compiler/plugin.proto --- a/proto-lens-imports/google/protobuf/compiler/plugin.proto +++ b/proto-lens-imports/google/protobuf/compiler/plugin.proto @@ -45,11 +45,12 @@ // flag "--${NAME}_out" is passed to protoc. syntax = "proto2"; + package google.protobuf.compiler; option java_package = "com.google.protobuf.compiler"; option java_outer_classname = "PluginProtos"; -option go_package = "github.com/golang/protobuf/protoc-gen-go/plugin;plugin_go"; +option go_package = "google.golang.org/protobuf/types/pluginpb"; import "google/protobuf/descriptor.proto"; @@ -106,6 +107,16 @@ // exiting with a non-zero status code. optional string error = 1; + // A bitmask of supported features that the code generator supports. + // This is a bitwise "or" of values from the Feature enum. + optional uint64 supported_features = 2; + + // Sync with code_generator.h. + enum Feature { + FEATURE_NONE = 0; + FEATURE_PROTO3_OPTIONAL = 1; + } + // Represents a single generated file. message File { // The file name, relative to the output directory. The name must not @@ -162,6 +173,11 @@ // The file contents. optional string content = 15; + + // Information describing the file content being inserted. If an insertion + // point is used, this information will be appropriately offset and inserted + // into the code generation metadata for the generated files. + optional GeneratedCodeInfo generated_code_info = 16; } repeated File file = 15; } diff --git a/proto-lens-imports/google/protobuf/descriptor.proto b/proto-lens-imports/google/protobuf/descriptor.proto --- a/proto-lens-imports/google/protobuf/descriptor.proto +++ b/proto-lens-imports/google/protobuf/descriptor.proto @@ -40,7 +40,8 @@ syntax = "proto2"; package google.protobuf; -option go_package = "github.com/golang/protobuf/protoc-gen-go/descriptor;descriptor"; + +option go_package = "google.golang.org/protobuf/types/descriptorpb"; option java_package = "com.google.protobuf"; option java_outer_classname = "DescriptorProtos"; option csharp_namespace = "Google.Protobuf.Reflection"; @@ -59,8 +60,8 @@ // Describes a complete .proto file. message FileDescriptorProto { - optional string name = 1; // file name, relative to root of source tree - optional string package = 2; // e.g. "foo", "foo.bar", etc. + optional string name = 1; // file name, relative to root of source tree + optional string package = 2; // e.g. "foo", "foo.bar", etc. // Names of files imported by this file. repeated string dependency = 3; @@ -100,8 +101,8 @@ repeated EnumDescriptorProto enum_type = 4; message ExtensionRange { - optional int32 start = 1; - optional int32 end = 2; + optional int32 start = 1; // Inclusive. + optional int32 end = 2; // Exclusive. optional ExtensionRangeOptions options = 3; } @@ -115,8 +116,8 @@ // fields or extension ranges in the same message. Reserved ranges may // not overlap. message ReservedRange { - optional int32 start = 1; // Inclusive. - optional int32 end = 2; // Exclusive. + optional int32 start = 1; // Inclusive. + optional int32 end = 2; // Exclusive. } repeated ReservedRange reserved_range = 9; // Reserved field names, which may not be used by fields in the same message. @@ -128,6 +129,7 @@ // The parser stores options it doesn't recognize here. See above. repeated UninterpretedOption uninterpreted_option = 999; + // Clients can define custom options in extensions of this message. See above. extensions 1000 to max; } @@ -137,42 +139,42 @@ enum Type { // 0 is reserved for errors. // Order is weird for historical reasons. - TYPE_DOUBLE = 1; - TYPE_FLOAT = 2; + TYPE_DOUBLE = 1; + TYPE_FLOAT = 2; // Not ZigZag encoded. Negative numbers take 10 bytes. Use TYPE_SINT64 if // negative values are likely. - TYPE_INT64 = 3; - TYPE_UINT64 = 4; + TYPE_INT64 = 3; + TYPE_UINT64 = 4; // Not ZigZag encoded. Negative numbers take 10 bytes. Use TYPE_SINT32 if // negative values are likely. - TYPE_INT32 = 5; - TYPE_FIXED64 = 6; - TYPE_FIXED32 = 7; - TYPE_BOOL = 8; - TYPE_STRING = 9; + TYPE_INT32 = 5; + TYPE_FIXED64 = 6; + TYPE_FIXED32 = 7; + TYPE_BOOL = 8; + TYPE_STRING = 9; // Tag-delimited aggregate. // Group type is deprecated and not supported in proto3. However, Proto3 // implementations should still be able to parse the group wire format and // treat group fields as unknown fields. - TYPE_GROUP = 10; - TYPE_MESSAGE = 11; // Length-delimited aggregate. + TYPE_GROUP = 10; + TYPE_MESSAGE = 11; // Length-delimited aggregate. // New in version 2. - TYPE_BYTES = 12; - TYPE_UINT32 = 13; - TYPE_ENUM = 14; - TYPE_SFIXED32 = 15; - TYPE_SFIXED64 = 16; - TYPE_SINT32 = 17; // Uses ZigZag encoding. - TYPE_SINT64 = 18; // Uses ZigZag encoding. - }; + TYPE_BYTES = 12; + TYPE_UINT32 = 13; + TYPE_ENUM = 14; + TYPE_SFIXED32 = 15; + TYPE_SFIXED64 = 16; + TYPE_SINT32 = 17; // Uses ZigZag encoding. + TYPE_SINT64 = 18; // Uses ZigZag encoding. + } enum Label { // 0 is reserved for errors - LABEL_OPTIONAL = 1; - LABEL_REQUIRED = 2; - LABEL_REPEATED = 3; - }; + LABEL_OPTIONAL = 1; + LABEL_REQUIRED = 2; + LABEL_REPEATED = 3; + } optional string name = 1; optional int32 number = 3; @@ -211,6 +213,29 @@ optional string json_name = 10; optional FieldOptions options = 8; + + // If true, this is a proto3 "optional". When a proto3 field is optional, it + // tracks presence regardless of field type. + // + // When proto3_optional is true, this field must be belong to a oneof to + // signal to old proto3 clients that presence is tracked for this field. This + // oneof is known as a "synthetic" oneof, and this field must be its sole + // member (each proto3 optional field gets its own synthetic oneof). Synthetic + // oneofs exist in the descriptor only, and do not generate any API. Synthetic + // oneofs must be ordered after all "real" oneofs. + // + // For message fields, proto3_optional doesn't create any semantic change, + // since non-repeated message fields always track presence. However it still + // indicates the semantic detail of whether the user wrote "optional" or not. + // This can be useful for round-tripping the .proto file. For consistency we + // give message fields a synthetic oneof also, even though it is not required + // to track presence. This is especially important because the parser can't + // tell if a field is a message or an enum, so it must always create a + // synthetic oneof. + // + // Proto2 optional fields do not set this flag, because they already indicate + // optional with `LABEL_OPTIONAL`. + optional bool proto3_optional = 17; } // Describes a oneof. @@ -234,8 +259,8 @@ // is inclusive such that it can appropriately represent the entire int32 // domain. message EnumReservedRange { - optional int32 start = 1; // Inclusive. - optional int32 end = 2; // Inclusive. + optional int32 start = 1; // Inclusive. + optional int32 end = 2; // Inclusive. } // Range of reserved numeric values. Reserved numeric values may not be used @@ -276,9 +301,9 @@ optional MethodOptions options = 4; // Identifies if client streams multiple client messages - optional bool client_streaming = 5 [default=false]; + optional bool client_streaming = 5 [default = false]; // Identifies if server streams multiple server messages - optional bool server_streaming = 6 [default=false]; + optional bool server_streaming = 6 [default = false]; } @@ -314,7 +339,6 @@ // If this turns out to be popular, a web service will be set up // to automatically assign option numbers. - message FileOptions { // Sets the Java package where classes generated from this .proto will be @@ -337,7 +361,7 @@ // named by java_outer_classname. However, the outer class will still be // generated to contain the file's getDescriptor() method as well as any // top-level extensions defined in the file. - optional bool java_multiple_files = 10 [default=false]; + optional bool java_multiple_files = 10 [default = false]; // This option does nothing. optional bool java_generate_equals_and_hash = 20 [deprecated=true]; @@ -348,17 +372,17 @@ // Message reflection will do the same. // However, an extension field still accepts non-UTF-8 byte sequences. // This option has no effect on when used with the lite runtime. - optional bool java_string_check_utf8 = 27 [default=false]; + optional bool java_string_check_utf8 = 27 [default = false]; // Generated classes can be optimized for speed or code size. enum OptimizeMode { - SPEED = 1; // Generate complete code for parsing, serialization, - // etc. - CODE_SIZE = 2; // Use ReflectionOps to implement these methods. - LITE_RUNTIME = 3; // Generate code using MessageLite and the lite runtime. + SPEED = 1; // Generate complete code for parsing, serialization, + // etc. + CODE_SIZE = 2; // Use ReflectionOps to implement these methods. + LITE_RUNTIME = 3; // Generate code using MessageLite and the lite runtime. } - optional OptimizeMode optimize_for = 9 [default=SPEED]; + optional OptimizeMode optimize_for = 9 [default = SPEED]; // Sets the Go package where structs generated from this .proto will be // placed. If omitted, the Go package will be derived from the following: @@ -369,6 +393,7 @@ + // Should generic services be generated in each language? "Generic" services // are not specific to any particular RPC system. They are generated by the // main code generators in each language (without additional plugins). @@ -379,20 +404,20 @@ // that generate code specific to your particular RPC system. Therefore, // these default to false. Old code which depends on generic services should // explicitly set them to true. - optional bool cc_generic_services = 16 [default=false]; - optional bool java_generic_services = 17 [default=false]; - optional bool py_generic_services = 18 [default=false]; - optional bool php_generic_services = 42 [default=false]; + optional bool cc_generic_services = 16 [default = false]; + optional bool java_generic_services = 17 [default = false]; + optional bool py_generic_services = 18 [default = false]; + optional bool php_generic_services = 42 [default = false]; // Is this file deprecated? // Depending on the target platform, this can emit Deprecated annotations // for everything in the file, or it will be completely ignored; in the very // least, this is a formalization for deprecating files. - optional bool deprecated = 23 [default=false]; + optional bool deprecated = 23 [default = false]; // Enables the use of arenas for the proto messages in this file. This applies // only to generated classes for C++. - optional bool cc_enable_arenas = 31 [default=false]; + optional bool cc_enable_arenas = 31 [default = true]; // Sets the objective c class prefix which is prepended to all objective c @@ -417,10 +442,9 @@ // determining the namespace. optional string php_namespace = 41; - // Use this option to change the namespace of php generated metadata classes. - // Default is empty. When this option is empty, the proto file name will be used - // for determining the namespace. + // Default is empty. When this option is empty, the proto file name will be + // used for determining the namespace. optional string php_metadata_namespace = 44; // Use this option to change the package of ruby generated classes. Default @@ -428,6 +452,7 @@ // determining the ruby package. optional string ruby_package = 45; + // The parser stores options it doesn't recognize here. // See the documentation for the "Options" section above. repeated UninterpretedOption uninterpreted_option = 999; @@ -458,18 +483,18 @@ // // Because this is an option, the above two restrictions are not enforced by // the protocol compiler. - optional bool message_set_wire_format = 1 [default=false]; + optional bool message_set_wire_format = 1 [default = false]; // Disables the generation of the standard "descriptor()" accessor, which can // conflict with a field of the same name. This is meant to make migration // from proto1 easier; new code should avoid fields named "descriptor". - optional bool no_standard_descriptor_accessor = 2 [default=false]; + optional bool no_standard_descriptor_accessor = 2 [default = false]; // Is this message deprecated? // Depending on the target platform, this can emit Deprecated annotations // for the message, or it will be completely ignored; in the very least, // this is a formalization for deprecating messages. - optional bool deprecated = 3 [default=false]; + optional bool deprecated = 3 [default = false]; // Whether the message is an automatically generated map entry type for the // maps field. @@ -486,7 +511,7 @@ // // Implementations may choose not to generate the map_entry=true message, but // use a native map in the target language to hold the keys and values. - // The reflection APIs in such implementions still need to work as + // The reflection APIs in such implementations still need to work as // if the field is a repeated message field. // // NOTE: Do not set the option in .proto files. Always use the maps syntax @@ -497,6 +522,7 @@ reserved 8; // javalite_serializable reserved 9; // javanano_as_lite + // The parser stores options it doesn't recognize here. See above. repeated UninterpretedOption uninterpreted_option = 999; @@ -576,16 +602,16 @@ // implementation must either *always* check its required fields, or *never* // check its required fields, regardless of whether or not the message has // been parsed. - optional bool lazy = 5 [default=false]; + optional bool lazy = 5 [default = false]; // Is this field deprecated? // Depending on the target platform, this can emit Deprecated annotations // for accessors, or it will be completely ignored; in the very least, this // is a formalization for deprecating fields. - optional bool deprecated = 3 [default=false]; + optional bool deprecated = 3 [default = false]; // For Google-internal migration only. Do not use. - optional bool weak = 10 [default=false]; + optional bool weak = 10 [default = false]; // The parser stores options it doesn't recognize here. See above. @@ -615,7 +641,7 @@ // Depending on the target platform, this can emit Deprecated annotations // for the enum, or it will be completely ignored; in the very least, this // is a formalization for deprecating enums. - optional bool deprecated = 3 [default=false]; + optional bool deprecated = 3 [default = false]; reserved 5; // javanano_as_lite @@ -631,7 +657,7 @@ // Depending on the target platform, this can emit Deprecated annotations // for the enum value, or it will be completely ignored; in the very least, // this is a formalization for deprecating enum values. - optional bool deprecated = 1 [default=false]; + optional bool deprecated = 1 [default = false]; // The parser stores options it doesn't recognize here. See above. repeated UninterpretedOption uninterpreted_option = 999; @@ -651,7 +677,7 @@ // Depending on the target platform, this can emit Deprecated annotations // for the service, or it will be completely ignored; in the very least, // this is a formalization for deprecating services. - optional bool deprecated = 33 [default=false]; + optional bool deprecated = 33 [default = false]; // The parser stores options it doesn't recognize here. See above. repeated UninterpretedOption uninterpreted_option = 999; @@ -671,18 +697,18 @@ // Depending on the target platform, this can emit Deprecated annotations // for the method, or it will be completely ignored; in the very least, // this is a formalization for deprecating methods. - optional bool deprecated = 33 [default=false]; + optional bool deprecated = 33 [default = false]; // Is this method side-effect-free (or safe in HTTP parlance), or idempotent, // or neither? HTTP based RPC implementation may choose GET verb for safe // methods, and PUT verb for idempotent methods instead of the default POST. enum IdempotencyLevel { IDEMPOTENCY_UNKNOWN = 0; - NO_SIDE_EFFECTS = 1; // implies idempotent - IDEMPOTENT = 2; // idempotent, but may have side effects + NO_SIDE_EFFECTS = 1; // implies idempotent + IDEMPOTENT = 2; // idempotent, but may have side effects } - optional IdempotencyLevel idempotency_level = - 34 [default=IDEMPOTENCY_UNKNOWN]; + optional IdempotencyLevel idempotency_level = 34 + [default = IDEMPOTENCY_UNKNOWN]; // The parser stores options it doesn't recognize here. See above. repeated UninterpretedOption uninterpreted_option = 999; @@ -763,7 +789,7 @@ // beginning of the "extend" block and is shared by all extensions within // the block. // - Just because a location's span is a subset of some other location's span - // does not mean that it is a descendent. For example, a "group" defines + // does not mean that it is a descendant. For example, a "group" defines // both a type and a field in a single declaration. Thus, the locations // corresponding to the type and field and their components will overlap. // - Code which tries to interpret locations should probably be designed to @@ -794,14 +820,14 @@ // [ 4, 3, 2, 7 ] // this path refers to the whole field declaration (from the beginning // of the label to the terminating semicolon). - repeated int32 path = 1 [packed=true]; + repeated int32 path = 1 [packed = true]; // Always has exactly three or four elements: start line, start column, // end line (optional, otherwise assumed same as start line), end column. // These are packed into a single field for efficiency. Note that line // and column numbers are zero-based -- typically you will want to add // 1 to each before displaying to a user. - repeated int32 span = 2 [packed=true]; + repeated int32 span = 2 [packed = true]; // If this SourceCodeInfo represents a complete declaration, these are any // comments appearing before and after the declaration which appear to be @@ -866,7 +892,7 @@ message Annotation { // Identifies the element in the original source .proto file. This field // is formatted the same as SourceCodeInfo.Location.path. - repeated int32 path = 1 [packed=true]; + repeated int32 path = 1 [packed = true]; // Identifies the filesystem path to the original source .proto. optional string source_file = 2; diff --git a/proto-lens.cabal b/proto-lens.cabal --- a/proto-lens.cabal +++ b/proto-lens.cabal @@ -1,13 +1,11 @@ cabal-version: 1.12 --- This file has been generated from package.yaml by hpack version 0.33.0. +-- This file has been generated from package.yaml by hpack version 0.34.4. -- -- see: https://github.com/sol/hpack --- --- hash: d71629464ee51493ce31ad480ec5872af89ba3c917588b69a61484409a22896c name: proto-lens -version: 0.7.0.0 +version: 0.7.1.0 synopsis: A lens-based implementation of protocol buffers in Haskell. description: The proto-lens library provides an API for protocol buffers using modern Haskell language and library patterns. Specifically, it provides: . @@ -60,16 +58,16 @@ hs-source-dirs: src build-depends: - base >=4.10 && <4.15 + base >=4.10 && <4.16 , bytestring ==0.10.* , containers >=0.5 && <0.7 , deepseq ==1.4.* - , ghc-prim >=0.4 && <0.7 - , lens-family >=1.2 && <2.1 + , ghc-prim >=0.4 && <0.8 + , lens-family >=1.2 && <2.2 , parsec ==3.1.* , pretty ==1.1.* , primitive >=0.6 && <0.8 - , profunctors >=5.2 && <5.6 + , profunctors >=5.2 && <6.0 , tagged ==0.8.* , text ==1.2.* , transformers >=0.4 && <0.6 diff --git a/src/Data/ProtoLens/Encoding/Bytes.hs b/src/Data/ProtoLens/Encoding/Bytes.hs --- a/src/Data/ProtoLens/Encoding/Bytes.hs +++ b/src/Data/ProtoLens/Encoding/Bytes.hs @@ -51,7 +51,7 @@ import Control.Monad.Trans.Except (throwE, ExceptT) import Data.Bits import Data.ByteString (ByteString) -import Data.ByteString.Lazy.Builder as Builder +import Data.ByteString.Builder as Builder import qualified Data.ByteString.Builder.Internal as Internal import qualified Data.ByteString.Lazy as L import Data.Int (Int32, Int64) @@ -126,7 +126,7 @@ putVarInt :: Word64 -> Builder putVarInt n | n < 128 = Builder.word8 (fromIntegral n) - | otherwise = Builder.word8 (fromIntegral $ n .&. 127 .|. 128) + | otherwise = Builder.word8 (fromIntegral $ n .|. 128) <> putVarInt (n `shiftR` 7) getFixed32 :: Parser Word32 diff --git a/src/Data/ProtoLens/Service/Types.hs b/src/Data/ProtoLens/Service/Types.hs --- a/src/Data/ProtoLens/Service/Types.hs +++ b/src/Data/ProtoLens/Service/Types.hs @@ -23,8 +23,10 @@ , StreamingType (..) ) where -import Data.Kind (Constraint) +import qualified Data.ByteString as B +import Data.Kind (Constraint, Type) import Data.ProtoLens.Message (Message) +import Data.Proxy (Proxy(..)) import GHC.TypeLits @@ -53,6 +55,7 @@ type ServicePackage s :: Symbol type ServiceMethods s :: [Symbol] + packedServiceDescriptor :: Proxy s -> B.ByteString ------------------------------------------------------------------------------ -- | Data type to be used as a promoted type for 'MethodStreamingType'. @@ -82,8 +85,8 @@ , Message (MethodOutput s m) ) => HasMethodImpl s (m :: Symbol) where type MethodName s m :: Symbol - type MethodInput s m :: * - type MethodOutput s m :: * + type MethodInput s m :: Type + type MethodOutput s m :: Type type MethodStreamingType s m :: StreamingType diff --git a/src/Data/ProtoLens/TextFormat.hs b/src/Data/ProtoLens/TextFormat.hs --- a/src/Data/ProtoLens/TextFormat.hs +++ b/src/Data/ProtoLens/TextFormat.hs @@ -317,8 +317,8 @@ makeScalarValue DoubleField (Parser.DoubleValue x) = Right x makeScalarValue FloatField (Parser.DoubleValue x) = Right (realToFrac x) makeScalarValue BoolField (Parser.EnumValue x) - | x == "true" = Right True - | x == "false" = Right False + | x `elem` ["true", "True", "t"] = Right True + | x `elem` ["false", "False", "f"] = Right False | otherwise = Left $ "Unrecognized bool value " ++ show x makeScalarValue StringField (Parser.ByteStringValue x) = Right (Text.decodeUtf8 x) makeScalarValue BytesField (Parser.ByteStringValue x) = Right x diff --git a/src/Data/ProtoLens/TextFormat/Parser.hs b/src/Data/ProtoLens/TextFormat/Parser.hs --- a/src/Data/ProtoLens/TextFormat/Parser.hs +++ b/src/Data/ProtoLens/TextFormat/Parser.hs @@ -16,23 +16,23 @@ , parser ) where -import Data.ByteString (ByteString, pack) -import Data.Char (ord, isSpace) +import Control.Applicative ((<|>), many) +import Control.Monad (liftM, liftM2, mzero, unless) +import Data.ByteString (ByteString) +import Data.ByteString.Builder (Builder, char8, charUtf8, toLazyByteString, word8) +import Data.ByteString.Lazy (toStrict) +import Data.Char (digitToInt, isSpace) +import Data.Functor (($>)) import Data.Functor.Identity (Identity) import Data.List (intercalate) -import Data.Maybe (catMaybes) -import Data.Text.Lazy (Text) import qualified Data.Text as StrictText -import Data.Word (Word8) -import Numeric (readOct, readHex) +import Data.Text.Lazy (Text) import Text.Parsec (()) import Text.Parsec.Char (alphaNum, char, hexDigit, letter, octDigit, oneOf, satisfy) import Text.Parsec.Text.Lazy (Parser) -import Text.Parsec.Combinator (choice, eof, many1, optionMaybe, sepBy1) +import Text.Parsec.Combinator (choice, eof, many1, sepBy1) import Text.Parsec.Token hiding (octal) -import Control.Applicative ((<|>), many) -import Control.Monad (liftM, liftM2, mzero) -- | A 'TokenParser' for the protobuf text format. ptp :: GenTokenParser Text () Identity @@ -55,7 +55,6 @@ , caseSensitive = True } - type Message = [Field] data Field = Field Key Value @@ -131,39 +130,43 @@ protoStringLiteral :: Parser ByteString protoStringLiteral = do initialQuoteChar <- char '\'' <|> char '\"' - word8s <- many $ stringChar initialQuoteChar + let quoted = do + _ <- char '\\' + choice + [ char 'a' $> char8 '\a' + , char 'b' $> char8 '\b' + , char 'f' $> char8 '\f' + , char 'n' $> char8 '\n' + , char 'r' $> char8 '\r' + , char 't' $> char8 '\t' + , char 'v' $> char8 '\v' + , char '\\' $> char8 '\\' + , char '\'' $> char8 '\'' + , char '\"' $> char8 '\"' + , oneOf "xX" *> parse8BitToBuilder hexDigit 16 (1, 2) + , oneOf "uU" *> fail "Unicode in string literals not yet supported" + , parse8BitToBuilder octDigit 8 (1, 3) + ] + unquoted = charUtf8 <$> satisfy (/= initialQuoteChar) + builders <- many $ quoted <|> unquoted _ <- char initialQuoteChar - return $ pack word8s + return $ toStrict $ toLazyByteString $ mconcat builders where - stringChar :: Char -> Parser Word8 - stringChar quote = (nonEscape quote) <|> stringEscape - nonEscape quote = fmap (fromIntegral . ord) - $ satisfy (\c -> c `notElem` "\\" ++ [quote] && ord c < 256) - stringEscape = char '\\' >> (octal <|> hex <|> unicode <|> simple) - octal = do d0 <- octDigit - d1 <- optionMaybe octDigit - d2 <- optionMaybe octDigit - readMaybeDigits readOct [Just d0, d1, d2] - readMaybeDigits :: ReadS Word8 -> [Maybe Char] -> Parser Word8 - readMaybeDigits reader - = return . (\str -> let [(v, "")] = reader str in v) . catMaybes - hex = do _ <- oneOf "xX" - d0 <- hexDigit - d1 <- optionMaybe hexDigit - readMaybeDigits readHex [Just d0, d1] - unicode = oneOf "uU" >> fail "Unicode in string literals not yet supported" - simple = choice $ map charRet [ ('a', '\a') - , ('b', '\b') - , ('f', '\f') - , ('n', '\n') - , ('r', '\r') - , ('t', '\t') - , ('v', '\v') - , ('\\', '\\') - , ('\'', '\'') - , ('\"', '\"') - ] - where - charRet :: (Char, Char) -> Parser Word8 - charRet (escapeCh, ch) = do _ <- char escapeCh - return $ fromIntegral $ ord ch + -- | Apply a parser between 'min' and 'max' times, failing otherwise. + manyN :: Parser a -> (Int, Int) -> Parser [a] + manyN _ (_, 0) = return [] + manyN p (0, maX) = ((:) <$> p <*> manyN p (0, maX - 1)) <|> pure [] + manyN p (miN, maX) = (:) <$> p <*> manyN p (miN - 1, maX - 1) + + -- | Parse a number in 'base' with between 'min' and 'max' digits. + parseNum :: Parser Char -> Int -> (Int, Int) -> Parser Int + parseNum p base range = do + digits <- map digitToInt <$> manyN p range + return $ foldl (\a d -> a * base + d) 0 digits + + -- | Parse a number and return a builder for the 8-bit char it represents. + parse8BitToBuilder :: Parser Char -> Int -> (Int, Int) -> Parser Builder + parse8BitToBuilder p base range = do + value <- parseNum p base range + unless (value < 256) $ fail "Escaped number is not 8-bit" + return $ word8 $ fromIntegral value