Generics.hs 29.9 KB
Newer Older
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
1
{-# LANGUAGE Trustworthy            #-}
2
{-# LANGUAGE CPP                    #-}
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
3 4 5 6 7 8 9
{-# LANGUAGE NoImplicitPrelude      #-}
{-# LANGUAGE TypeSynonymInstances   #-}
{-# LANGUAGE TypeOperators          #-}
{-# LANGUAGE KindSignatures         #-}
{-# LANGUAGE TypeFamilies           #-}
{-# LANGUAGE StandaloneDeriving     #-}
{-# LANGUAGE DeriveGeneric          #-}
10
{-# LANGUAGE PolyKinds              #-}
11
{-# LANGUAGE MagicHash              #-}
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
12

13 14 15
-----------------------------------------------------------------------------
-- |
-- Module      :  GHC.Generics
dreixel's avatar
dreixel committed
16
-- Copyright   :  (c) Universiteit Utrecht 2010-2011, University of Oxford 2012-2013
17
-- License     :  see libraries/base/LICENSE
18
--
19 20 21 22
-- Maintainer  :  libraries@haskell.org
-- Stability   :  internal
-- Portability :  non-portable
--
23
-- @since 4.6.0.0
24
--
dreixel's avatar
dreixel committed
25
-- If you're using @GHC.Generics@, you should consider using the
26
-- <http://hackage.haskell.org/package/generic-deriving> package, which
dreixel's avatar
dreixel committed
27
-- contains many useful generic functions.
28

jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
29
module GHC.Generics  (
dreixel's avatar
dreixel committed
30 31 32 33
-- * Introduction
--
-- |
--
Gabor Greif's avatar
Gabor Greif committed
34
-- Datatype-generic functions are based on the idea of converting values of
dreixel's avatar
dreixel committed
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
-- a datatype @T@ into corresponding values of a (nearly) isomorphic type @'Rep' T@.
-- The type @'Rep' T@ is
-- built from a limited set of type constructors, all provided by this module. A
-- datatype-generic function is then an overloaded function with instances
-- for most of these type constructors, together with a wrapper that performs
-- the mapping between @T@ and @'Rep' T@. By using this technique, we merely need
-- a few generic instances in order to implement functionality that works for any
-- representable type.
--
-- Representable types are collected in the 'Generic' class, which defines the
-- associated type 'Rep' as well as conversion functions 'from' and 'to'.
-- Typically, you will not define 'Generic' instances by hand, but have the compiler
-- derive them for you.

-- ** Representing datatypes
--
-- |
--
-- The key to defining your own datatype-generic functions is to understand how to
-- represent datatypes using the given set of type constructors.
--
-- Let us look at an example first:
--
-- @
-- data Tree a = Leaf a | Node (Tree a) (Tree a)
--   deriving 'Generic'
-- @
--
-- The above declaration (which requires the language pragma @DeriveGeneric@)
-- causes the following representation to be generated:
--
-- @
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
67
-- instance 'Generic' (Tree a) where
dreixel's avatar
dreixel committed
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
--   type 'Rep' (Tree a) =
--     'D1' D1Tree
--       ('C1' C1_0Tree
--          ('S1' 'NoSelector' ('Par0' a))
--        ':+:'
--        'C1' C1_1Tree
--          ('S1' 'NoSelector' ('Rec0' (Tree a))
--           ':*:'
--           'S1' 'NoSelector' ('Rec0' (Tree a))))
--   ...
-- @
--
-- /Hint:/ You can obtain information about the code being generated from GHC by passing
-- the @-ddump-deriv@ flag. In GHCi, you can expand a type family such as 'Rep' using
-- the @:kind!@ command.
--
#if 0
-- /TODO:/ Newer GHC versions abandon the distinction between 'Par0' and 'Rec0' and will
-- use 'Rec0' everywhere.
--
#endif
-- This is a lot of information! However, most of it is actually merely meta-information
-- that makes names of datatypes and constructors and more available on the type level.
--
-- Here is a reduced representation for 'Tree' with nearly all meta-information removed,
-- for now keeping only the most essential aspects:
--
-- @
-- instance 'Generic' (Tree a) where
--   type 'Rep' (Tree a) =
--     'Par0' a
--     ':+:'
--     ('Rec0' (Tree a) ':*:' 'Rec0' (Tree a))
-- @
--
-- The @Tree@ datatype has two constructors. The representation of individual constructors
-- is combined using the binary type constructor ':+:'.
--
-- The first constructor consists of a single field, which is the parameter @a@. This is
-- represented as @'Par0' a@.
--
-- The second constructor consists of two fields. Each is a recursive field of type @Tree a@,
-- represented as @'Rec0' (Tree a)@. Representations of individual fields are combined using
-- the binary type constructor ':*:'.
--
-- Now let us explain the additional tags being used in the complete representation:
--
--    * The @'S1' 'NoSelector'@ indicates that there is no record field selector associated with
--      this field of the constructor.
--
--    * The @'C1' C1_0Tree@ and @'C1' C1_1Tree@ invocations indicate that the enclosed part is
--      the representation of the first and second constructor of datatype @Tree@, respectively.
--      Here, @C1_0Tree@ and @C1_1Tree@ are datatypes generated by the compiler as part of
--      @deriving 'Generic'@. These datatypes are proxy types with no values. They are useful
--      because they are instances of the type class 'Constructor'. This type class can be used
--      to obtain information about the constructor in question, such as its name
--      or infix priority.
--
--    * The @'D1' D1Tree@ tag indicates that the enclosed part is the representation of the
--      datatype @Tree@. Again, @D1Tree@ is a datatype generated by the compiler. It is a
--      proxy type, and is useful by being an instance of class 'Datatype', which
--      can be used to obtain the name of a datatype, the module it has been defined in, and
--      whether it has been defined using @data@ or @newtype@.

-- ** Derived and fundamental representation types
--
-- |
--
-- There are many datatype-generic functions that do not distinguish between positions that
-- are parameters or positions that are recursive calls. There are also many datatype-generic
-- functions that do not care about the names of datatypes and constructors at all. To keep
-- the number of cases to consider in generic functions in such a situation to a minimum,
-- it turns out that many of the type constructors introduced above are actually synonyms,
-- defining them to be variants of a smaller set of constructors.

-- *** Individual fields of constructors: 'K1'
--
-- |
--
-- The type constructors 'Par0' and 'Rec0' are variants of 'K1':
--
-- @
-- type 'Par0' = 'K1' 'P'
-- type 'Rec0' = 'K1' 'R'
-- @
--
-- Here, 'P' and 'R' are type-level proxies again that do not have any associated values.

-- *** Meta information: 'M1'
--
-- |
--
-- The type constructors 'S1', 'C1' and 'D1' are all variants of 'M1':
--
-- @
-- type 'S1' = 'M1' 'S'
-- type 'C1' = 'M1' 'C'
-- type 'D1' = 'M1' 'D'
-- @
--
168
-- The types 'S', 'C' and 'D' are once again type-level proxies, just used to create
dreixel's avatar
dreixel committed
169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267
-- several variants of 'M1'.

-- *** Additional generic representation type constructors
--
-- |
--
-- Next to 'K1', 'M1', ':+:' and ':*:' there are a few more type constructors that occur
-- in the representations of other datatypes.

-- **** Empty datatypes: 'V1'
--
-- |
--
-- For empty datatypes, 'V1' is used as a representation. For example,
--
-- @
-- data Empty deriving 'Generic'
-- @
--
-- yields
--
-- @
-- instance 'Generic' Empty where
--   type 'Rep' Empty = 'D1' D1Empty 'V1'
-- @

-- **** Constructors without fields: 'U1'
--
-- |
--
-- If a constructor has no arguments, then 'U1' is used as its representation. For example
-- the representation of 'Bool' is
--
-- @
-- instance 'Generic' Bool where
--   type 'Rep' Bool =
--     'D1' D1Bool
--       ('C1' C1_0Bool 'U1' ':+:' 'C1' C1_1Bool 'U1')
-- @

-- *** Representation of types with many constructors or many fields
--
-- |
--
-- As ':+:' and ':*:' are just binary operators, one might ask what happens if the
-- datatype has more than two constructors, or a constructor with more than two
-- fields. The answer is simple: the operators are used several times, to combine
-- all the constructors and fields as needed. However, users /should not rely on
-- a specific nesting strategy/ for ':+:' and ':*:' being used. The compiler is
-- free to choose any nesting it prefers. (In practice, the current implementation
-- tries to produce a more or less balanced nesting, so that the traversal of the
-- structure of the datatype from the root to a particular component can be performed
-- in logarithmic rather than linear time.)

-- ** Defining datatype-generic functions
--
-- |
--
-- A datatype-generic function comprises two parts:
--
--    1. /Generic instances/ for the function, implementing it for most of the representation
--       type constructors introduced above.
--
--    2. A /wrapper/ that for any datatype that is in `Generic`, performs the conversion
--       between the original value and its `Rep`-based representation and then invokes the
--       generic instances.
--
-- As an example, let us look at a function 'encode' that produces a naive, but lossless
-- bit encoding of values of various datatypes. So we are aiming to define a function
--
-- @
-- encode :: 'Generic' a => a -> [Bool]
-- @
--
-- where we use 'Bool' as our datatype for bits.
--
-- For part 1, we define a class @Encode'@. Perhaps surprisingly, this class is parameterized
-- over a type constructor @f@ of kind @* -> *@. This is a technicality: all the representation
-- type constructors operate with kind @* -> *@ as base kind. But the type argument is never
-- being used. This may be changed at some point in the future. The class has a single method,
-- and we use the type we want our final function to have, but we replace the occurrences of
-- the generic type argument @a@ with @f p@ (where the @p@ is any argument; it will not be used).
--
-- > class Encode' f where
-- >   encode' :: f p -> [Bool]
--
-- With the goal in mind to make @encode@ work on @Tree@ and other datatypes, we now define
-- instances for the representation type constructors 'V1', 'U1', ':+:', ':*:', 'K1', and 'M1'.

-- *** Definition of the generic representation types
--
-- |
--
-- In order to be able to do this, we need to know the actual definitions of these types:
--
-- @
-- data    'V1'        p                       -- lifted version of Empty
-- data    'U1'        p = 'U1'                  -- lifted version of ()
-- data    (':+:') f g p = 'L1' (f p) | 'R1' (g p) -- lifted version of 'Either'
268
-- data    (':*:') f g p = (f p) ':*:' (g p)     -- lifted version of (,)
dreixel's avatar
dreixel committed
269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
-- newtype 'K1'    i c p = 'K1' { 'unK1' :: c }    -- a container for a c
-- newtype 'M1'  i t f p = 'M1' { 'unM1' :: f p }  -- a wrapper
-- @
--
-- So, 'U1' is just the unit type, ':+:' is just a binary choice like 'Either',
-- ':*:' is a binary pair like the pair constructor @(,)@, and 'K1' is a value
-- of a specific type @c@, and 'M1' wraps a value of the generic type argument,
-- which in the lifted world is an @f p@ (where we do not care about @p@).

-- *** Generic instances
--
-- |
--
-- The instance for 'V1' is slightly awkward (but also rarely used):
--
-- @
-- instance Encode' 'V1' where
--   encode' x = undefined
-- @
--
-- There are no values of type @V1 p@ to pass (except undefined), so this is
-- actually impossible. One can ask why it is useful to define an instance for
-- 'V1' at all in this case? Well, an empty type can be used as an argument to
-- a non-empty type, and you might still want to encode the resulting type.
-- As a somewhat contrived example, consider @[Empty]@, which is not an empty
-- type, but contains just the empty list. The 'V1' instance ensures that we
-- can call the generic function on such types.
--
-- There is exactly one value of type 'U1', so encoding it requires no
-- knowledge, and we can use zero bits:
--
-- @
-- instance Encode' 'U1' where
--   encode' 'U1' = []
-- @
--
-- In the case for ':+:', we produce 'False' or 'True' depending on whether
-- the constructor of the value provided is located on the left or on the right:
--
-- @
-- instance (Encode' f, Encode' g) => Encode' (f ':+:' g) where
--   encode' ('L1' x) = False : encode' x
--   encode' ('R1' x) = True  : encode' x
-- @
--
-- In the case for ':*:', we append the encodings of the two subcomponents:
--
-- @
-- instance (Encode' f, Encode' g) => Encode' (f ':*:' g) where
--   encode' (x ':*:' y) = encode' x ++ encode' y
-- @
--
-- The case for 'K1' is rather interesting. Here, we call the final function
-- 'encode' that we yet have to define, recursively. We will use another type
-- class 'Encode' for that function:
--
-- @
-- instance (Encode c) => Encode' ('K1' i c) where
--   encode' ('K1' x) = encode x
-- @
--
-- Note how 'Par0' and 'Rec0' both being mapped to 'K1' allows us to define
-- a uniform instance here.
--
-- Similarly, we can define a uniform instance for 'M1', because we completely
-- disregard all meta-information:
--
-- @
-- instance (Encode' f) => Encode' ('M1' i t f) where
--   encode' ('M1' x) = encode' x
-- @
--
-- Unlike in 'K1', the instance for 'M1' refers to 'encode'', not 'encode'.

-- *** The wrapper and generic default
--
-- |
--
-- We now define class 'Encode' for the actual 'encode' function:
--
-- @
-- class Encode a where
--   encode :: a -> [Bool]
--   default encode :: ('Generic' a) => a -> [Bool]
--   encode x = encode' ('from' x)
-- @
--
-- The incoming 'x' is converted using 'from', then we dispatch to the
-- generic instances using 'encode''. We use this as a default definition
-- for 'encode'. We need the 'default encode' signature because ordinary
-- Haskell default methods must not introduce additional class constraints,
-- but our generic default does.
--
-- Defining a particular instance is now as simple as saying
--
-- @
-- instance (Encode a) => Encode (Tree a)
-- @
--
#if 0
-- /TODO:/ Add usage example?
--
#endif
-- The generic default is being used. In the future, it will hopefully be
-- possible to use @deriving Encode@ as well, but GHC does not yet support
-- that syntax for this situation.
--
-- Having 'Encode' as a class has the advantage that we can define
-- non-generic special cases, which is particularly useful for abstract
-- datatypes that have no structural representation. For example, given
-- a suitable integer encoding function 'encodeInt', we can define
--
-- @
-- instance Encode Int where
--   encode = encodeInt
-- @

-- *** Omitting generic instances
--
-- |
--
-- It is not always required to provide instances for all the generic
-- representation types, but omitting instances restricts the set of
-- datatypes the functions will work for:
--
--    * If no ':+:' instance is given, the function may still work for
--      empty datatypes or datatypes that have a single constructor,
--      but will fail on datatypes with more than one constructor.
--
--    * If no ':*:' instance is given, the function may still work for
--      datatypes where each constructor has just zero or one field,
--      in particular for enumeration types.
--
--    * If no 'K1' instance is given, the function may still work for
--      enumeration types, where no constructor has any fields.
--
--    * If no 'V1' instance is given, the function may still work for
--      any datatype that is not empty.
--
--    * If no 'U1' instance is given, the function may still work for
--      any datatype where each constructor has at least one field.
--
-- An 'M1' instance is always required (but it can just ignore the
-- meta-information, as is the case for 'encode' above).
#if 0
-- *** Using meta-information
--
-- |
--
-- TODO
#endif
-- ** Generic constructor classes
--
-- |
--
-- Datatype-generic functions as defined above work for a large class
-- of datatypes, including parameterized datatypes. (We have used 'Tree'
-- as our example above, which is of kind @* -> *@.) However, the
-- 'Generic' class ranges over types of kind @*@, and therefore, the
-- resulting generic functions (such as 'encode') must be parameterized
-- by a generic type argument of kind @*@.
--
-- What if we want to define generic classes that range over type
-- constructors (such as 'Functor', 'Traversable', or 'Foldable')?

-- *** The 'Generic1' class
--
-- |
--
-- Like 'Generic', there is a class 'Generic1' that defines a
-- representation 'Rep1' and conversion functions 'from1' and 'to1',
-- only that 'Generic1' ranges over types of kind @* -> *@.
-- The 'Generic1' class is also derivable.
--
-- The representation 'Rep1' is ever so slightly different from 'Rep'.
-- Let us look at 'Tree' as an example again:
--
-- @
-- data Tree a = Leaf a | Node (Tree a) (Tree a)
--   deriving 'Generic1'
-- @
--
-- The above declaration causes the following representation to be generated:
--
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
453
-- instance 'Generic1' Tree where
dreixel's avatar
dreixel committed
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535
--   type 'Rep1' Tree =
--     'D1' D1Tree
--       ('C1' C1_0Tree
--          ('S1' 'NoSelector' 'Par1')
--        ':+:'
--        'C1' C1_1Tree
--          ('S1' 'NoSelector' ('Rec1' Tree)
--           ':*:'
--           'S1' 'NoSelector' ('Rec1' Tree)))
--   ...
--
-- The representation reuses 'D1', 'C1', 'S1' (and thereby 'M1') as well
-- as ':+:' and ':*:' from 'Rep'. (This reusability is the reason that we
-- carry around the dummy type argument for kind-@*@-types, but there are
-- already enough different names involved without duplicating each of
-- these.)
--
-- What's different is that we now use 'Par1' to refer to the parameter
-- (and that parameter, which used to be @a@), is not mentioned explicitly
-- by name anywhere; and we use 'Rec1' to refer to a recursive use of @Tree a@.

-- *** Representation of @* -> *@ types
--
-- |
--
-- Unlike 'Par0' and 'Rec0', the 'Par1' and 'Rec1' type constructors do not
-- map to 'K1'. They are defined directly, as follows:
--
-- @
-- newtype 'Par1'   p = 'Par1' { 'unPar1' ::   p } -- gives access to parameter p
-- newtype 'Rec1' f p = 'Rec1' { 'unRec1' :: f p } -- a wrapper
-- @
--
-- In 'Par1', the parameter @p@ is used for the first time, whereas 'Rec1' simply
-- wraps an application of @f@ to @p@.
--
-- Note that 'K1' (in the guise of 'Rec0') can still occur in a 'Rep1' representation,
-- namely when the datatype has a field that does not mention the parameter.
--
-- The declaration
--
-- @
-- data WithInt a = WithInt Int a
--   deriving 'Generic1'
-- @
--
-- yields
--
-- @
-- class 'Rep1' WithInt where
--   type 'Rep1' WithInt =
--     'D1' D1WithInt
--       ('C1' C1_0WithInt
--         ('S1' 'NoSelector' ('Rec0' Int)
--          ':*:'
--          'S1' 'NoSelector' 'Par1'))
-- @
--
-- If the parameter @a@ appears underneath a composition of other type constructors,
-- then the representation involves composition, too:
--
-- @
-- data Rose a = Fork a [Rose a]
-- @
--
-- yields
--
-- @
-- class 'Rep1' Rose where
--   type 'Rep1' Rose =
--     'D1' D1Rose
--       ('C1' C1_0Rose
--         ('S1' 'NoSelector' 'Par1'
--          ':*:'
--          'S1' 'NoSelector' ([] ':.:' 'Rec1' Rose)
-- @
--
-- where
--
-- @
-- newtype (':.:') f g p = 'Comp1' { 'unComp1' :: f (g p) }
-- @
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594

-- *** Representation of unlifted types
--
-- |
--
-- If one were to attempt to derive a Generic instance for a datatype with an
-- unlifted argument (for example, 'Int#'), one might expect the occurrence of
-- the 'Int#' argument to be marked with @'Rec0' 'Int#'@. This won't work,
-- though, since 'Int#' is of kind @#@ and 'Rec0' expects a type of kind @*@.
-- In fact, polymorphism over unlifted types is disallowed completely.
--
-- One solution would be to represent an occurrence of 'Int#' with 'Rec0 Int'
-- instead. With this approach, however, the programmer has no way of knowing
-- whether the 'Int' is actually an 'Int#' in disguise.
--
-- Instead of reusing 'Rec0', a separate data family 'URec' is used to mark
-- occurrences of common unlifted types:
--
-- @
-- data family URec a p
--
-- data instance 'URec' ('Ptr' ()) p = 'UAddr'   { 'uAddr#'   :: 'Addr#'   }
-- data instance 'URec' 'Char'     p = 'UChar'   { 'uChar#'   :: 'Char#'   }
-- data instance 'URec' 'Double'   p = 'UDouble' { 'uDouble#' :: 'Double#' }
-- data instance 'URec' 'Int'      p = 'UFloat'  { 'uFloat#'  :: 'Float#'  }
-- data instance 'URec' 'Float'    p = 'UInt'    { 'uInt#'    :: 'Int#'    }
-- data instance 'URec' 'Word'     p = 'UWord'   { 'uWord#'   :: 'Word#'   }
-- @
--
-- Several type synonyms are provided for convenience:
--
-- @
-- type 'UAddr'   = 'URec' ('Ptr' ())
-- type 'UChar'   = 'URec' 'Char'
-- type 'UDouble' = 'URec' 'Double'
-- type 'UFloat'  = 'URec' 'Float'
-- type 'UInt'    = 'URec' 'Int'
-- type 'UWord'   = 'URec' 'Word'
-- @
--
-- The declaration
--
-- @
-- data IntHash = IntHash Int#
--   deriving 'Generic'
-- @
--
-- yields
--
-- @
-- instance 'Generic' IntHash where
--   type 'Rep' IntHash =
--     'D1' D1IntHash
--       ('C1' C1_0IntHash
--         ('S1' 'NoSelector' 'UInt'))
-- @
--
-- Currently, only the six unlifted types listed above are generated, but this
-- may be extended to encompass more unlifted types in the future.
dreixel's avatar
dreixel committed
595 596 597 598 599 600 601 602 603 604 605 606
#if 0
-- *** Limitations
--
-- |
--
-- /TODO/
--
-- /TODO:/ Also clear up confusion about 'Rec0' and 'Rec1' not really indicating recursion.
--
#endif
-----------------------------------------------------------------------------

jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
607 608 609 610
  -- * Generic representation types
    V1, U1(..), Par1(..), Rec1(..), K1(..), M1(..)
  , (:+:)(..), (:*:)(..), (:.:)(..)

611 612 613 614 615
  -- ** Unboxed representation types
  , URec(..)
  , type UAddr, type UChar, type UDouble
  , type UFloat, type UInt, type UWord

jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
616 617 618 619 620 621 622 623 624 625 626 627 628 629
  -- ** Synonyms for convenience
  , Rec0, Par0, R, P
  , D1, C1, S1, D, C, S

  -- * Meta-information
  , Datatype(..), Constructor(..), Selector(..), NoSelector
  , Fixity(..), Associativity(..), Arity(..), prec

  -- * Generic type classes
  , Generic(..), Generic1(..)

  ) where

-- We use some base types
630 631
import GHC.Prim ( Addr#, Char#, Double#, Float#, Int#, Word# )
import GHC.Ptr ( Ptr )
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
632 633 634 635 636
import GHC.Types
import Data.Maybe ( Maybe(..) )
import Data.Either ( Either(..) )

-- Needed for instances
637
import GHC.Classes ( Eq, Ord )
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
638 639
import GHC.Read ( Read )
import GHC.Show ( Show )
640
import Data.Proxy
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
641 642 643 644 645 646

--------------------------------------------------------------------------------
-- Representation types
--------------------------------------------------------------------------------

-- | Void: used for datatypes without constructors
647
data V1 (p :: *)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
648 649

-- | Unit: used for constructors without arguments
650
data U1 (p :: *) = U1
651
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
652 653 654

-- | Used for marking occurrences of the parameter
newtype Par1 p = Par1 { unPar1 :: p }
655
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
656 657

-- | Recursive calls of kind * -> *
658
newtype Rec1 f (p :: *) = Rec1 { unRec1 :: f p }
659
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
660 661

-- | Constants, additional parameters and recursion of kind *
662
newtype K1 (i :: *) c (p :: *) = K1 { unK1 :: c }
663
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
664 665

-- | Meta-information (constructor names, etc.)
666
newtype M1 (i :: *) (c :: *) f (p :: *) = M1 { unM1 :: f p }
667
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
668 669 670

-- | Sums: encode choice between constructors
infixr 5 :+:
671
data (:+:) f g (p :: *) = L1 (f p) | R1 (g p)
672
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
673 674 675

-- | Products: encode multiple arguments to constructors
infixr 6 :*:
676
data (:*:) f g (p :: *) = f p :*: g p
677
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
678 679 680

-- | Composition of functors
infixr 7 :.:
681
newtype (:.:) f (g :: * -> *) (p :: *) = Comp1 { unComp1 :: f (g p) }
682
  deriving (Eq, Ord, Read, Show, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
683

684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
-- | Constants of kind @#@
data family URec (a :: *) (p :: *)

-- | Used for marking occurrences of 'Addr#'
data instance URec (Ptr ()) p = UAddr { uAddr# :: Addr# }
  deriving (Eq, Ord, Generic)

-- | Used for marking occurrences of 'Char#'
data instance URec Char p = UChar { uChar# :: Char# }
  deriving (Eq, Ord, Show, Generic)

-- | Used for marking occurrences of 'Double#'
data instance URec Double p = UDouble { uDouble# :: Double# }
  deriving (Eq, Ord, Show, Generic)

-- | Used for marking occurrences of 'Float#'
data instance URec Float p = UFloat { uFloat# :: Float# }
  deriving (Eq, Ord, Show, Generic)

-- | Used for marking occurrences of 'Int#'
data instance URec Int p = UInt { uInt# :: Int# }
  deriving (Eq, Ord, Show, Generic)

-- | Used for marking occurrences of 'Word#'
data instance URec Word p = UWord { uWord# :: Word# }
  deriving (Eq, Ord, Show, Generic)

-- | Type synonym for 'URec': 'Addr#'
type UAddr   = URec (Ptr ())
-- | Type synonym for 'URec': 'Char#'
type UChar   = URec Char
-- | Type synonym for 'URec': 'Double#'
type UDouble = URec Double
-- | Type synonym for 'URec': 'Float#'
type UFloat  = URec Float
-- | Type synonym for 'URec': 'Int#'
type UInt    = URec Int
-- | Type synonym for 'URec': 'Word#'
type UWord   = URec Word

jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
724 725 726 727 728 729 730 731 732
-- | Tag for K1: recursion (of kind *)
data R
-- | Tag for K1: parameters (other than the last)
data P

-- | Type synonym for encoding recursion (of kind *)
type Rec0  = K1 R
-- | Type synonym for encoding parameters (other than the last)
type Par0  = K1 P
733 734
{-# DEPRECATED Par0 "'Par0' is no longer used; use 'Rec0' instead" #-} -- deprecated in 7.6
{-# DEPRECATED P "'P' is no longer used; use 'R' instead" #-} -- deprecated in 7.6
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752

-- | Tag for M1: datatype
data D
-- | Tag for M1: constructor
data C
-- | Tag for M1: record selector
data S

-- | Type synonym for encoding meta-information for datatypes
type D1 = M1 D

-- | Type synonym for encoding meta-information for constructors
type C1 = M1 C

-- | Type synonym for encoding meta-information for record selectors
type S1 = M1 S

-- | Class for datatypes that represent datatypes
753
class Datatype (d :: *) where
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
754
  -- | The name of the datatype (unqualified)
755
  datatypeName :: t d (f :: * -> *) (a :: *) -> [Char]
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
756
  -- | The fully-qualified name of the module where the type is declared
757
  moduleName   :: t d (f :: * -> *) (a :: *) -> [Char]
758
  -- | The package name of the module where the type is declared
759
  packageName :: t d (f :: * -> *) (a :: *) -> [Char]
760
  -- | Marks if the datatype is actually a newtype
761
  isNewtype    :: t d (f :: * -> *) (a :: *) -> Bool
762
  isNewtype _ = False
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
763 764 765


-- | Class for datatypes that represent records
766
class Selector (s :: *) where
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
767
  -- | The name of the selector
768
  selName :: t s (f :: * -> *) (a :: *) -> [Char]
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
769 770 771 772 773 774 775

-- | Used for constructor fields without a name
data NoSelector

instance Selector NoSelector where selName _ = ""

-- | Class for datatypes that represent data constructors
776
class Constructor (c :: *) where
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
777
  -- | The name of the constructor
778
  conName :: t c (f :: * -> *) (a :: *) -> [Char]
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
779 780

  -- | The fixity of the constructor
781
  conFixity :: t c (f :: * -> *) (a :: *) -> Fixity
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
782 783 784
  conFixity _ = Prefix

  -- | Marks if this constructor is a record
785
  conIsRecord :: t c (f :: * -> *) (a :: *) -> Bool
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
786 787 788 789 790
  conIsRecord _ = False


-- | Datatype to represent the arity of a tuple.
data Arity = NoArity | Arity Int
791
  deriving (Eq, Show, Ord, Read, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
792 793 794 795

-- | Datatype to represent the fixity of a constructor. An infix
-- | declaration directly corresponds to an application of 'Infix'.
data Fixity = Prefix | Infix Associativity Int
796
  deriving (Eq, Show, Ord, Read, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
797 798 799 800 801 802 803 804 805 806

-- | Get the precedence of a fixity value.
prec :: Fixity -> Int
prec Prefix      = 10
prec (Infix _ n) = n

-- | Datatype to represent the associativity of a constructor
data Associativity = LeftAssociative
                   | RightAssociative
                   | NotAssociative
807
  deriving (Eq, Show, Ord, Read, Generic)
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
808 809 810 811 812 813 814 815 816 817 818 819

-- | Representable types of kind *.
-- This class is derivable in GHC with the DeriveGeneric flag on.
class Generic a where
  -- | Generic representation type
  type Rep a :: * -> *
  -- | Convert from the datatype to its representation
  from  :: a -> (Rep a) x
  -- | Convert from the representation to the datatype
  to    :: (Rep a) x -> a


820 821
-- | Representable types of kind * -> *.
-- This class is derivable in GHC with the DeriveGeneric flag on.
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862
class Generic1 f where
  -- | Generic representation type
  type Rep1 f :: * -> *
  -- | Convert from the datatype to its representation
  from1  :: f a -> (Rep1 f) a
  -- | Convert from the representation to the datatype
  to1    :: (Rep1 f) a -> f a


--------------------------------------------------------------------------------
-- Derived instances
--------------------------------------------------------------------------------
deriving instance Generic [a]
deriving instance Generic (Maybe a)
deriving instance Generic (Either a b)
deriving instance Generic Bool
deriving instance Generic Ordering
deriving instance Generic ()
deriving instance Generic ((,) a b)
deriving instance Generic ((,,) a b c)
deriving instance Generic ((,,,) a b c d)
deriving instance Generic ((,,,,) a b c d e)
deriving instance Generic ((,,,,,) a b c d e f)
deriving instance Generic ((,,,,,,) a b c d e f g)

deriving instance Generic1 []
deriving instance Generic1 Maybe
deriving instance Generic1 (Either a)
deriving instance Generic1 ((,) a)
deriving instance Generic1 ((,,) a b)
deriving instance Generic1 ((,,,) a b c)
deriving instance Generic1 ((,,,,) a b c d)
deriving instance Generic1 ((,,,,,) a b c d e)
deriving instance Generic1 ((,,,,,,) a b c d e f)

--------------------------------------------------------------------------------
-- Primitive representations
--------------------------------------------------------------------------------

-- Int
data D_Int
863
data C_Int
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
864 865 866 867

instance Datatype D_Int where
  datatypeName _ = "Int"
  moduleName   _ = "GHC.Int"
868
  packageName  _ = "base"
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
869

870
instance Constructor C_Int where
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
871 872 873
  conName _ = "" -- JPM: I'm not sure this is the right implementation...

instance Generic Int where
874
  type Rep Int = D1 D_Int (C1 C_Int (S1 NoSelector (Rec0 Int)))
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
875 876 877 878 879 880
  from x = M1 (M1 (M1 (K1 x)))
  to (M1 (M1 (M1 (K1 x)))) = x


-- Float
data D_Float
881
data C_Float
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
882 883 884 885

instance Datatype D_Float where
  datatypeName _ = "Float"
  moduleName   _ = "GHC.Float"
886
  packageName  _ = "base"
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
887

888
instance Constructor C_Float where
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
889 890 891
  conName _ = "" -- JPM: I'm not sure this is the right implementation...

instance Generic Float where
892
  type Rep Float = D1 D_Float (C1 C_Float (S1 NoSelector (Rec0 Float)))
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
893 894 895 896 897 898
  from x = M1 (M1 (M1 (K1 x)))
  to (M1 (M1 (M1 (K1 x)))) = x


-- Double
data D_Double
899
data C_Double
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
900 901 902 903

instance Datatype D_Double where
  datatypeName _ = "Double"
  moduleName   _ = "GHC.Float"
904
  packageName  _ = "base"
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
905

906
instance Constructor C_Double where
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
907 908 909
  conName _ = "" -- JPM: I'm not sure this is the right implementation...

instance Generic Double where
910
  type Rep Double = D1 D_Double (C1 C_Double (S1 NoSelector (Rec0 Double)))
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
911 912 913 914 915 916
  from x = M1 (M1 (M1 (K1 x)))
  to (M1 (M1 (M1 (K1 x)))) = x


-- Char
data D_Char
917
data C_Char
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
918 919 920 921

instance Datatype D_Char where
  datatypeName _ = "Char"
  moduleName   _ = "GHC.Base"
922
  packageName  _ = "base"
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
923

924
instance Constructor C_Char where
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
925 926 927
  conName _ = "" -- JPM: I'm not sure this is the right implementation...

instance Generic Char where
928
  type Rep Char = D1 D_Char (C1 C_Char (S1 NoSelector (Rec0 Char)))
jpm@cs.ox.ac.uk's avatar
jpm@cs.ox.ac.uk committed
929 930
  from x = M1 (M1 (M1 (K1 x)))
  to (M1 (M1 (M1 (K1 x)))) = x
931 932

deriving instance Generic (Proxy t)