218 Commits

Author SHA1 Message Date
greg
fb26293157 More work 2018-03-10 23:06:15 -08:00
greg
c0289f238f Starting on macro work 2018-03-10 22:10:13 -08:00
greg
7afb9d47fc Minimal parser that actually does something 2018-03-10 20:26:40 -08:00
greg
2431a074b0 Starting out with minimal BNF
Just to test this idea, I'm going to start out with this simplified
BNF of just literals
2018-03-10 20:17:51 -08:00
greg
3bfd251a68 autoparser framework done 2018-03-10 20:05:27 -08:00
greg
a033c82d13 More boilerplate
Note: I need to make this boilerplate situation better
2018-03-10 18:26:26 -08:00
greg
c176c1c918 Autoparser - token output 2018-03-10 18:20:19 -08:00
greg
aa40b985f3 Experiment to automatically generate parser
Gonna give this a shot, automatically generate a recursive-descent
parser from BNF
2018-03-10 14:04:10 -08:00
greg
64a3705e35 Some changes necessary to handle non-interactive code 2018-03-09 00:50:24 -08:00
greg
7e23e40a2f Eval list literals 2018-03-08 12:42:05 -08:00
greg
4c88a7ada6 Parse list literals 2018-03-08 12:01:24 -08:00
greg
367719d408 Tighten some code 2018-03-08 00:32:19 -08:00
greg
2e80045750 Rename ReplOutput -> LanguageOutput 2018-03-07 22:07:13 -08:00
greg
35c67f73c3 Make directory for schala source files 2018-03-07 21:53:55 -08:00
greg
da9aa1e29d Index evaluation 2018-03-07 21:46:21 -08:00
greg
ca67f9b4fe Proper index exprs 2018-03-06 02:51:45 -08:00
greg
60cce3fe9c Some macro simplifications 2018-03-06 01:31:31 -08:00
greg
4eb22f94d0 Trying to make tests less verbose 2018-03-06 01:06:36 -08:00
greg
355c8170a4 Added test for lambda call 2018-03-06 00:56:19 -08:00
greg
e3671a579d Changed BNF grammar of call statements
To allow calling lambdas
2018-03-06 00:38:33 -08:00
greg
08ca48b2ba lambdas 2018-03-04 02:11:22 -08:00
greg
fea9b9575b Print output of tuples 2018-03-03 13:26:22 -08:00
greg
276dad56d7 Handle tuple literals in type system 2018-03-03 11:55:20 -08:00
greg
695e733584 Sum types in type schema 2018-03-03 11:52:07 -08:00
greg
9bfd751db6 Kill unused import 2018-03-03 11:32:38 -08:00
greg
b058e47d79 Kill some compiler warnings 2018-03-03 00:28:52 -08:00
greg
5be53dc847 Evaluator now only prints when a builtin print is called 2018-03-03 00:25:08 -08:00
greg
a0bea0d55a Kill comments 2018-03-02 23:33:01 -08:00
greg
9747374e8a Fix bug in delimited macro
Had to do with bad strictness testing.
2018-03-02 22:44:17 -08:00
greg
9ab1ca28f8 Improve tokenizer debug output 2018-03-02 22:11:25 -08:00
greg
66cd51a355 Cleanup 2018-03-02 21:59:14 -08:00
greg
1056be12e7 Include line count in token debug 2018-03-02 15:21:48 -08:00
greg
48e7c0be03 Munged types to make tokenizer compile 2018-03-02 15:15:12 -08:00
greg
6e82d1207e SOme work
WIP
2018-03-02 02:57:04 -08:00
greg
f0e7c9906e Fixed bug w/ lines in functions
Also improved debugging
2018-03-02 00:42:52 -08:00
greg
57c7858c87 Frame-aware lookups 2018-03-01 23:13:32 -08:00
greg
a105c84943 Kill debug 2018-03-01 22:54:03 -08:00
greg
2b8d63d9cc Better debugging for types 2018-03-01 22:32:38 -08:00
greg
c807c20292 Use UVars in type signatures of functions 2018-03-01 03:35:09 -08:00
greg
a643c8a792 Add history saving 2018-03-01 02:49:14 -08:00
greg
69200048fa Switch to rustyline library 2018-03-01 02:43:11 -08:00
greg
55e372a670 Introduced fresh type variable method 2018-02-28 05:45:20 -08:00
greg
c50626241e Continuing work 2018-02-27 03:01:05 -08:00
greg
232bec97a7 Re-added symbol table infra 2018-02-26 21:43:53 -08:00
greg
ce1d967f08 Some logic for function call inferring 2018-02-26 21:28:11 -08:00
greg
daa0062108 Starting on function application typechecking 2018-02-26 21:00:36 -08:00
greg
3e7c7a50b4 Move some code around 2018-02-26 19:57:46 -08:00
greg
2574a1b9c0 Function calls work 2018-02-26 19:55:27 -08:00
greg
c285ee182e Temporarily disable type-erroring
and tighten some code
2018-02-26 19:16:49 -08:00
greg
f7659a5598 Handle variable lookups 2018-02-26 18:23:10 -08:00
greg
1064d9993a Evaluate binding declarations 2018-02-26 18:18:42 -08:00
greg
0e3320e183 Separate Value and NamedStruct syntactic categories 2018-02-26 18:12:37 -08:00
greg
89a2be19f4 Fixed | 2018-02-26 02:27:36 -08:00
greg
d9e96398a4 More operator stuff 2018-02-26 02:21:21 -08:00
greg
a564ffa1ce Operator changes 2018-02-26 02:11:56 -08:00
greg
b3fff100d2 Fixed tests w/ respect to binop
There's a few unnecessary conversions of &str 's to Rc<String> and back
2018-02-24 17:50:57 -08:00
greg
cfd6df7ba5 Centralize data for prefix ops too 2018-02-24 17:43:26 -08:00
greg
bb2e1ae27a Added type information to binop definitions
Also started centralizing precedence there too
2018-02-24 17:37:23 -08:00
greg
4333563d03 Make sigil field private 2018-02-24 14:39:45 -08:00
greg
e7cabb2a79 Function evaluation work 2018-02-24 14:31:04 -08:00
greg
5da7c809b2 Give State a pointer to its parent
For function call lookups
2018-02-24 13:56:04 -08:00
greg
d229a57837 Finished initial BinOp/PrefixOp 2018-02-23 19:06:37 -08:00
greg
0dd8861f83 Starting to munge BinOp types
Incomplete, doesn't yet compile
2018-02-23 04:10:00 -08:00
greg
4ab900d601 ReplState -> State
Not everythign is a repl
2018-02-23 03:07:58 -08:00
greg
501b975fb6 Move bx! macro up to mod.rs
And make use of it in parser
2018-02-23 03:04:19 -08:00
greg
83315e97ac Move anno-to-type to a method on TypeName 2018-02-23 02:30:34 -08:00
greg
6259a0808c Fix tests too 2018-02-23 01:59:53 -08:00
greg
0c69476fd0 Separate tokenizing module
Parsing was getting too long
2018-02-23 01:58:06 -08:00
greg
1caccc6ae2 Some work on binops 2018-02-23 01:49:37 -08:00
greg
23af2b1455 Some more type-checking work 2018-02-22 19:59:53 -08:00
greg
61795b0331 More work on evaluating applications
for later testing + to kill a compiler warning
2018-02-22 03:34:36 -08:00
greg
a1b874c891 Fix traits, silence warnings 2018-02-22 03:26:32 -08:00
greg
e7103b925b type of a declaration should be Void, not Unit
I think this makes sense

Also kill some compiler warnings
2018-02-22 03:25:05 -08:00
greg
c35401da65 Types in bindings 2018-02-22 03:21:58 -08:00
greg
d51a9a73d7 Simplified match 2018-02-22 00:31:13 -08:00
greg
fddd43b86e Added trait declaration 2018-02-21 22:06:56 -08:00
greg
12f55fa844 More static type work 2018-02-21 18:12:46 -08:00
greg
bb0fb716e4 Finished basic constant type inference 2018-02-21 14:14:24 -08:00
greg
687d482853 More type implementing - WIP
This has a borrowing bug currently
2018-02-21 04:32:30 -08:00
greg
628eb28deb Fix some integer overflows with binary and hex 2018-02-21 03:52:16 -08:00
greg
4c8b4c8c71 Starting basic type stuff 2018-02-21 03:39:40 -08:00
greg
c674148772 Starting over with types 2018-02-21 02:35:09 -08:00
greg
7b4f69dce5 Additional TODO 2018-02-21 02:35:09 -08:00
greg
98caf1cac3 Add todo note 2018-02-20 17:56:13 -08:00
greg
457799e0f7 More type things 2018-02-12 01:45:36 -08:00
greg
681d767855 Type singletons test work 2018-02-12 00:51:53 -08:00
greg
ef4620e90a TypeSingletonName broken out 2018-02-12 00:25:48 -08:00
greg
1f2a4c706f Fix struct literals in if expressions
With special case-ing, sigh :( Also will need to do this for match
expressions but I'll cross that bridge when I come to it
2018-02-11 22:10:21 -08:00
greg
a452bccd1c Don't need clone() here 2018-02-11 16:45:26 -08:00
greg
eca2218f6a Kill separate is_digit method
I care about 10 vs 16 distinction
2018-02-11 16:43:51 -08:00
greg
83aedb0efb Hex parsing done 2018-02-11 16:35:38 -08:00
greg
76841de784 Save settings on ctrl-D 2018-02-11 16:28:17 -08:00
greg
c0574ff1ef Added a bunch of notes 2018-02-11 02:37:52 -08:00
greg
faa5c6ab42 Fix parse level calculation 2018-02-10 17:45:00 -08:00
greg
9c2d2190b0 Proper indentation of parser debug 2018-02-10 15:10:06 -08:00
greg
21511f5120 Move some code around 2018-02-08 01:15:27 -08:00
greg
8bd399f97a Better hex literals 2018-01-08 06:12:45 -08:00
greg
30a6d0929a Starting hex parsing 2018-01-08 05:57:36 -08:00
greg
bec8aedc22 Simplify some code 2018-01-08 05:21:04 -08:00
greg
1b642c6321 Assign a specific rocket version 2017-12-31 15:46:08 -08:00
greg
559306ffc8 unified BoolAtom 2017-12-30 23:19:42 -08:00
greg
540ffde4bc Rukka source file 2017-12-30 01:18:48 -08:00
greg
fa8d46e3d7 Print operation 2017-12-29 05:10:03 -08:00
greg
4598802999 Refactoring 2017-12-29 05:03:30 -08:00
greg
5ea83e2da6 Delete some unneeded code 2017-12-29 04:55:03 -08:00
greg
23c0f54042 Forgot to change name here 2017-12-29 04:52:47 -08:00
greg
8618de313b Name change
builtin -> primitive
2017-12-29 04:51:14 -08:00
greg
cd23b23a91 Get rid of some printlns 2017-12-29 04:46:19 -08:00
greg
e6475a1262 Implement lambda application 2017-12-29 03:57:27 -08:00
greg
e6f81b28f9 Plus and multiply 2017-12-25 23:10:16 -08:00
greg
c20d75faf1 Builtins - + 2017-12-24 23:48:13 -08:00
greg
85aabed344 Framework for multiple environments 2017-12-21 03:11:56 -08:00
greg
aa821e720a Apply wokr 2017-12-21 01:14:05 -08:00
greg
0e25720927 Fixing quote 2017-12-21 01:12:05 -08:00
greg
c101610cde Starting builtins 2017-12-20 22:56:24 -08:00
greg
1217f6e143 Lambda abstraction 2017-12-20 18:23:44 -08:00
greg
6f41167402 Kill this linker thing 2017-12-18 01:30:33 -08:00
greg
cf0af7e0c9 Flesh out TODO, README 2017-12-13 00:52:54 -08:00
greg
a7fd515e7b Add Rukka to README 2017-12-13 00:25:59 -08:00
greg
c6509338d8 Kill unused code 2017-12-12 02:57:19 -08:00
greg
192a6bf6e1 Some lambda work 2017-12-12 02:56:10 -08:00
greg
7e8c4267c2 Remove a unimplemented 2017-12-11 01:55:08 -08:00
greg
25527bbdf0 Add fn literal variant 2017-12-11 01:53:27 -08:00
greg
5e7aef1040 Even more concise 2017-12-10 19:01:44 -08:00
greg
3386fcc505 Refactoring 2017-12-10 18:44:21 -08:00
greg
18a839bb91 Starting lambdas 2017-12-10 03:58:44 -08:00
greg
92d641fca0 Make var methods better 2017-12-10 03:35:51 -08:00
greg
9b4499c5ac If expressions 2017-12-10 02:58:07 -08:00
greg
07e19cbfa2 Rukka - Variables 2017-12-09 19:08:08 -08:00
greg
2016fcab41 Add schala idea 2017-12-09 18:56:34 -08:00
greg
0e7b6f25b3 Can specify language name with -l in any case 2017-12-09 18:19:07 -08:00
greg
7e7aa55d6e Go directly to langauge by name 2017-12-09 13:38:55 -08:00
greg
cc79565fb3 Define half-working 2017-12-07 20:28:09 -08:00
greg
5659bab684 Language name in prompt 2017-12-07 20:08:31 -08:00
greg
405f91a770 Get rid of old import 2017-12-07 19:55:18 -08:00
greg
faed1d6f25 eq? 2017-12-07 19:54:53 -08:00
greg
f6d047e3b8 True and False primitives 2017-12-07 19:51:34 -08:00
greg
fcd980f148 Some primitive implementations 2017-12-07 19:48:48 -08:00
greg
c3919daa66 Fix pointer alias problem 2017-12-07 11:22:59 -08:00
greg
f8152f68ad Still tryign to make the pointer-munging work 2017-12-07 08:15:28 -08:00
greg
9273773bf4 This has broken sexp parsing 2017-12-04 04:56:29 -08:00
greg
844cef36c7 Fix print bug 2017-12-04 03:26:38 -08:00
greg
0e17e45f3e Convert to more lispish Cons 2017-12-04 03:23:55 -08:00
greg
18d8ca7bd5 Special forms list 2017-12-04 03:06:54 -08:00
greg
2ee14bf740 Unwraps 2017-12-04 03:02:38 -08:00
greg
502497687a Handle top-level empty list 2017-12-04 03:01:47 -08:00
greg
107897ec97 print list 2017-12-04 02:44:09 -08:00
greg
8534fb4118 Tighten code 2017-12-04 02:00:00 -08:00
greg
a1e38aba8e Some more code 2017-12-04 01:57:24 -08:00
greg
2f8ef99b08 Type simplification 2017-12-03 22:20:43 -08:00
greg
2bb55b6cca State for eval 2017-12-03 22:10:19 -08:00
greg
bcd70ff538 Numbers 2017-12-03 19:21:56 -08:00
greg
728393671f Fixed string parsing 2017-12-03 17:47:17 -08:00
greg
9c3e223e51 Strings partway working 2017-12-03 17:11:17 -08:00
greg
2738119f17 Quotes 2017-12-03 06:04:53 -08:00
greg
630ead289c Change Symbol -> Word for token 2017-12-01 03:00:42 -08:00
greg
485e869c90 Fix bug 2017-12-01 02:58:09 -08:00
greg
9e8a3d1f08 Tighten code 2017-12-01 02:39:17 -08:00
greg
b1da524a8f Intersperse 2017-12-01 02:36:52 -08:00
greg
787b6d51a4 Parsing correctly yay 2017-12-01 02:16:28 -08:00
greg
1dae4443cd Tokens 2017-11-30 22:37:49 -08:00
greg
210a45c92e Sexp parsing 2017-11-29 02:08:30 -08:00
greg
815e0401f2 Parses ( 2017-11-29 01:45:29 -08:00
greg
753247ee83 Some halfwritten stuff 2017-11-28 03:37:16 -08:00
greg
6223fc20f3 List datatype 2017-11-27 00:57:26 -08:00
greg
da928db351 Add a new language - Rukka
This is a (simple) lisp, partially for fun, partially for testing the
generic interfaces
2017-11-26 21:17:17 -08:00
greg
93d0cfe5b8 Make schala-lib::language private and reexport 2017-11-02 02:45:26 -07:00
greg
687b28d1d1 Take TokenError type out of schala-lib 2017-11-01 22:41:34 -07:00
greg
b62f618256 I don't need this syntax 2017-11-01 01:25:26 -07:00
greg
f25b76ea11 Kill some packages from schala bin 2017-11-01 01:23:54 -07:00
greg
6b2736348d Get rid of unused imports 2017-10-31 00:45:15 -07:00
greg
69d5f38ea1 Refactor into libs part II
woo it compiles
2017-10-30 22:18:02 -07:00
greg
a6f8616839 Halfway done to library-ifying schala 2017-10-30 20:06:20 -07:00
greg
cdcb55e3b8 PLIGenerators can be authoritative, not the instances themselves 2017-10-29 13:45:55 -07:00
greg
74ac26841f Some simplification 2017-10-29 12:27:24 -07:00
greg
8fd29b5090 Passing things along as generators 2017-10-29 04:09:10 -07:00
greg
5ebc96daa7 Don't need mutex, kill it 2017-10-29 04:04:54 -07:00
greg
277e039251 Finally removed schala dependency
Now need to clena up everything
2017-10-29 03:41:40 -07:00
greg
6e8f57e54f Okay this compiles
The secret (from #rust) appeared to be that Fn() needed to have + Send
explicitly annotated on it
2017-10-29 03:16:08 -07:00
greg
ae02391270 Working on solution to Rocket state problem 2017-10-27 00:30:28 -07:00
greg
9379485713 Some linker bullshit
I don't know why I needed to do this
2017-10-26 02:03:47 -07:00
greg
910522537c Splitting up some code
In preparation for splitting schala into crates
2017-10-23 20:51:08 -07:00
greg
98e1a5235a Some more structure in evaluator 2017-10-23 01:54:35 -07:00
greg
e054c4b27f Revert "Starting to split project into multiple crates"
This reverts commit e3b0f4a51e.
Bah, this was a bad idea, wrong way to do it
2017-10-23 00:45:01 -07:00
greg
e3b0f4a51e Starting to split project into multiple crates 2017-10-23 00:43:43 -07:00
greg
911f26e9c6 Halfway done with evaluating tuples 2017-10-23 00:22:25 -07:00
greg
677e3ae0a9 Add module keyword 2017-10-22 03:58:09 -07:00
greg
9611770bb3 Switch from request to superagent
For doing HTTP requests. Makes the js bundle a lot smaller.

Also I should do something about the fact that I now have to change the
js and also rebuild the rust binary to change code
2017-10-15 02:37:02 -07:00
greg
4c256cb5f7 Literal non-primitive values 2017-10-14 13:54:17 -07:00
greg
688e1c7f5d Starting work on literal non-primitve values 2017-10-13 18:56:02 -07:00
greg
26c9c72bcc Can eval custom data constructors now 2017-10-13 03:05:18 -07:00
greg
2d614aa17a Float literals, kill old code 2017-10-13 00:01:43 -07:00
greg
ecb2eb0f87 Some more primitive types + binop-checking 2017-10-12 23:59:52 -07:00
greg
4c4004d3ac Add required imports 2017-10-12 21:46:12 -07:00
greg
9b4a23c4f2 Some partial work on refactoring type infer fn 2017-10-12 20:14:33 -07:00
greg
936c168cef Add colored output to non-interactive 2017-10-12 10:43:54 -07:00
greg
db835f42aa Convert webapp to using included files 2017-10-12 02:13:55 -07:00
greg
cd5fc36c37 Fix type check macro to add symbol table 2017-10-11 16:43:04 -07:00
greg
d7a33c974e More work with unification 2017-10-11 02:33:46 -07:00
greg
b2288206d2 the evar table
TODO find a better way to represent this
2017-10-11 02:11:12 -07:00
greg
d962e2c27a Unify work 2017-10-11 02:03:50 -07:00
greg
4534c1d3d6 Move type-level func up 2017-10-11 01:55:45 -07:00
greg
f79dc0b1e3 Okay I am figuring things out about hindley-milner again 2017-10-11 01:50:04 -07:00
greg
4928fc0019 rename type_var to ty 2017-10-10 22:14:55 -07:00
greg
d735e45688 String and () types 2017-10-10 21:51:45 -07:00
greg
b4208b696d Change around some stuff 2017-10-10 21:23:24 -07:00
greg
ff3dbbcbc6 Change Variable to Value 2017-10-10 21:02:32 -07:00
greg
e3261be8a0 Partial handling of user defined types 2017-10-10 17:29:28 -07:00
greg
f131105b50 Starting to make unify actually work 2017-10-10 04:38:59 -07:00
greg
1089a33634 Convert unify to are types
b/c Type implements Clone
Maybe wanna kill this later for efficiency
2017-10-10 04:26:40 -07:00
greg
6c60794485 Have + do something different with strings
Needed to introduce polymorphism soon
2017-10-10 02:45:25 -07:00
greg
2f18529bcc Operator typing a little bit 2017-10-10 02:41:17 -07:00
greg
c68e09d89d Slight refactoring 2017-10-10 02:32:02 -07:00
greg
d9e8178a90 Renamed all the type-related types 2017-10-10 02:17:07 -07:00
greg
57536e6399 Move some type checking code around 2017-10-10 01:11:24 -07:00
greg
32e077c407 Merge branch 'master' of github.com:neunenak/schala 2017-10-10 01:09:27 -07:00
greg
33d0d49d30 Basic typing test 2017-10-09 12:26:25 -07:00
greg
76a9367284 String types 2017-10-09 11:42:53 -07:00
58 changed files with 3632 additions and 6960 deletions

1
.gitignore vendored
View File

@@ -2,4 +2,3 @@ Cargo.lock
target
.schala_repl
.schala_history
rusty-tags.vi

View File

@@ -5,11 +5,14 @@ authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
schala-repl = { path = "schala-repl" }
schala-lang = { path = "schala-lang/language" }
# maaru-lang = { path = "maaru" }
# rukka-lang = { path = "rukka" }
# robo-lang = { path = "robo" }
llvm-sys = "*"
take_mut = "0.1.3"
itertools = "0.5.8"
lazy_static = "0.2.8"
maplit = "*"
colored = "1.5"
schala-lib = { path = "schala-lib" }
[build-dependencies]
includedir_codegen = "0.2.0"

31
Grammar Normal file
View File

@@ -0,0 +1,31 @@
<program> := <statements> EOF
<statements> := <statement>
| <statement> SEP <statements>
<statement> := let <id> = <expr>
| <expr>
| <fn_block>
<fn_block> := fn <id> ( <arg_list> ) <statements> end
<arg_list> := e
| <id>
| <id> , <arg_list>
<expr> := if <expr> then <statements> end
| if <expr> then <statements> else <statements> end
| while <expr> SEP <statements> end
| ( <expr> )
| <binop>
<binop> := <simple_expr>
| <simple_expr> <id> <binop>
<simple_expr> := <id>
| <number>
| <string>

View File

@@ -1,920 +0,0 @@
{-# LANGUAGE GeneralizedNewtypeDeriving #-}
{-# LANGUAGE LambdaCase #-}
{-# LANGUAGE OverloadedLists #-}
{-# LANGUAGE OverloadedStrings #-}
-- | This module is an extensively documented walkthrough for typechecking a
-- basic functional language using the Hindley-Damas-Milner algorithm.
--
-- In the end, we'll be able to infer the type of expressions like
--
-- @
-- find (λx. (>) x 0)
-- :: [Integer] -> Either () Integer
-- @
--
-- It can be used in multiple different forms:
--
-- * The source is written in literate programming style, so you can almost
-- read it from top to bottom, minus some few references to later topics.
-- * /Loads/ of doctests (runnable and verified code examples) are included
-- * The code is runnable in GHCi, all definitions are exposed.
-- * A small main module that gives many examples of what you might try out in
-- GHCi is also included.
-- * The Haddock output yields a nice overview over the definitions given, with
-- a nice rendering of a truckload of Haddock comments.
module HindleyMilner where
import Control.Monad.Trans
import Control.Monad.Trans.Except
import Control.Monad.Trans.State
import Data.Map (Map)
import qualified Data.Map as M
import Data.Monoid
import Data.Set (Set)
import qualified Data.Set as S
import Data.String
import Data.Text (Text)
import qualified Data.Text as T
-- $setup
--
-- For running doctests:
--
-- >>> :set -XOverloadedStrings
-- >>> :set -XOverloadedLists
-- >>> :set -XLambdaCase
-- >>> import qualified Data.Text.IO as T
-- >>> let putPprLn = T.putStrLn . ppr
-- #############################################################################
-- #############################################################################
-- * Preliminaries
-- #############################################################################
-- #############################################################################
-- #############################################################################
-- ** Prettyprinting
-- #############################################################################
-- | A prettyprinter class. Similar to 'Show', but with a focus on having
-- human-readable output as opposed to being valid Haskell.
class Pretty a where
ppr :: a -> Text
-- #############################################################################
-- ** Names
-- #############################################################################
-- | A 'name' is an identifier in the language we're going to typecheck.
-- Variables on both the term and type level have 'Name's, for example.
newtype Name = Name Text
deriving (Eq, Ord, Show)
-- | >>> "lorem" :: Name
-- Name "lorem"
instance IsString Name where
fromString = Name . T.pack
-- | >>> putPprLn (Name "var")
-- var
instance Pretty Name where
ppr (Name n) = n
-- #############################################################################
-- ** Monotypes
-- #############################################################################
-- | A monotype is an unquantified/unparametric type, in other words it contains
-- no @forall@s. Monotypes are the inner building blocks of all types. Examples
-- of monotypes are @Int@, @a@, @a -> b@.
--
-- In formal notation, 'MType's are often called τ (tau) types.
data MType = TVar Name -- ^ @a@
| TFun MType MType -- ^ @a -> b@
| TConst Name -- ^ @Int@, @()@, …
-- Since we can't declare our own types in our simple type system
-- here, we'll hard-code certain basic ones so we can typecheck some
-- familar functions that use them later.
| TList MType -- ^ @[a]@
| TEither MType MType -- ^ @Either a b@
| TTuple MType MType -- ^ @(a,b)@
deriving Show
-- | >>> putPprLn (TFun (TEither (TVar "a") (TVar "b")) (TFun (TVar "c") (TVar "d")))
-- Either a b → c → d
--
-- Using the 'IsString' instance:
--
-- >>> putPprLn (TFun (TEither "a" "b") (TFun "c" "d"))
-- Either a b → c → d
instance Pretty MType where
ppr = go False
where
go _ (TVar name) = ppr name
go _ (TList a) = "[" <> ppr a <> "]"
go _ (TEither l r) = "Either " <> ppr l <> " " <> ppr r
go _ (TTuple a b) = "(" <> ppr a <> ", " <> ppr b <> ")"
go _ (TConst name) = ppr name
go parenthesize (TFun a b)
| parenthesize = "(" <> lhs <> "" <> rhs <> ")"
| otherwise = lhs <> "" <> rhs
where lhs = go True a
rhs = go False b
-- | >>> "var" :: MType
-- TVar (Name "var")
instance IsString MType where
fromString = TVar . fromString
-- | The free variables of an 'MType'. This is simply the collection of all the
-- individual type variables occurring inside of it.
--
-- __Example:__ The free variables of @a -> b@ are @a@ and @b@.
freeMType :: MType -> Set Name
freeMType = \case
TVar a -> [a]
TFun a b -> freeMType a <> freeMType b
TList a -> freeMType a
TEither l r -> freeMType l <> freeMType r
TTuple a b -> freeMType a <> freeMType b
TConst _ -> []
-- | Substitute all the contained type variables mentioned in the substitution,
-- and leave everything else alone.
instance Substitutable MType where
applySubst s = \case
TVar a -> let Subst s' = s
in M.findWithDefault (TVar a) a s'
TFun f x -> TFun (applySubst s f) (applySubst s x)
TList a -> TList (applySubst s a)
TEither l r -> TEither (applySubst s l) (applySubst s r)
TTuple a b -> TTuple (applySubst s a) (applySubst s b)
c@TConst {} -> c
-- #############################################################################
-- ** Polytypes
-- #############################################################################
-- | A polytype is a monotype universally quantified over a number of type
-- variables. In Haskell, all definitions have polytypes, but since the @forall@
-- is implicit they look a bit like monotypes, maybe confusingly so. For
-- example, the type of @1 :: Int@ is actually @forall <nothing>. Int@, and the
-- type of @id@ is @forall a. a -> a@, although GHC displays it as @a -> a@.
--
-- A polytype claims to work "for all imaginable type parameters", very similar
-- to how a lambda claims to work "for all imaginable value parameters". We can
-- insert a value into a lambda's parameter to evaluate it to a new value, and
-- similarly we'll later insert types into a polytype's quantified variables to
-- gain new types.
--
-- __Example:__ in a definition @id :: forall a. a -> a@, the @a@ after the
-- ∀ ("forall") is the collection of type variables, and @a -> a@ is the 'MType'
-- quantified over. When we have such an @id@, we also have its specialized
-- version @Int -> Int@ available. This process will be the topic of the type
-- inference/unification algorithms.
--
-- In formal notation, 'PType's are often called σ (sigma) types.
--
-- The purpose of having monotypes and polytypes is that we'd like to only have
-- universal quantification at the top level, restricting our language to rank-1
-- polymorphism, where type inferece is total (all types can be inferred) and
-- simple (only a handful of typing rules). Weakening this constraint would be
-- easy: if we allowed universal quantification within function types we would
-- get rank-N polymorphism. Taking it even further to allow it anywhere,
-- effectively replacing all occurrences of 'MType' with 'PType', yields
-- impredicative types. Both these extensions make the type system
-- *significantly* more complex though.
data PType = Forall (Set Name) MType -- ^ ∀{α}. τ
-- | >>> putPprLn (Forall ["a"] (TFun "a" "a"))
-- ∀a. a → a
instance Pretty PType where
ppr (Forall qs mType) = "" <> pprUniversals <> ". " <> ppr mType
where
pprUniversals
| S.null qs = ""
| otherwise = (T.intercalate " " . map ppr . S.toList) qs
-- | The free variables of a 'PType' are the free variables of the contained
-- 'MType', except those universally quantified.
--
-- >>> let sigma = Forall ["a"] (TFun "a" (TFun (TTuple "b" "a") "c"))
-- >>> putPprLn sigma
-- ∀a. a → (b, a) → c
-- >>> let display = T.putStrLn . T.intercalate ", " . foldMap (\x -> [ppr x])
-- >>> display (freePType sigma)
-- b, c
freePType :: PType -> Set Name
freePType (Forall qs mType) = freeMType mType `S.difference` qs
-- | Substitute all the free type variables.
instance Substitutable PType where
applySubst (Subst subst) (Forall qs mType) =
let qs' = M.fromSet (const ()) qs
subst' = Subst (subst `M.difference` qs')
in Forall qs (applySubst subst' mType)
-- #############################################################################
-- ** The environment
-- #############################################################################
-- | The environment consists of all the values available in scope, and their
-- associated polytypes. Other common names for it include "(typing) context",
-- and because of the commonly used symbol for it sometimes directly
-- \"Gamma"/@"Γ"@.
--
-- There are two kinds of membership in an environment,
--
-- - @∈@: an environment @Γ@ can be viewed as a set of @(value, type)@ pairs,
-- and we can test whether something is /literally contained/ by it via
-- x:σ ∈ Γ
-- - @⊢@, pronounced /entails/, describes all the things that are well-typed,
-- given an environment @Γ@. @Γ ⊢ x:τ@ can thus be seen as a judgement that
-- @x:τ@ is /figuratively contained/ in @Γ@.
--
-- For example, the environment @{x:Int}@ literally contains @x@, but given
-- this, it also entails @λy. x@, @λy z. x@, @let id = λy. y in id x@ and so on.
--
-- In Haskell terms, the environment consists of all the things you currently
-- have available, or that can be built by comining them. If you import the
-- Prelude, your environment entails
--
-- @
-- id → ∀a. a→a
-- map → ∀a b. (a→b) → [a] → [b]
-- putStrLn → ∀∅. String → IO ()
-- …
-- id map → ∀a b. (a→b) → [a] → [b]
-- map putStrLn → ∀∅. [String] -> [IO ()]
-- …
-- @
newtype Env = Env (Map Name PType)
-- | >>> :{
-- putPprLn (Env
-- [ ("id", Forall ["a"] (TFun "a" "a"))
-- , ("const", Forall ["a", "b"] (TFun "a" (TFun "b" "a"))) ])
-- :}
-- Γ = { const : ∀a b. a → b → a
-- , id : ∀a. a → a }
instance Pretty Env where
ppr (Env env) = "Γ = { " <> T.intercalate "\n , " pprBindings <> " }"
where
bindings = M.assocs env
pprBinding (name, pType) = ppr name <> " : " <> ppr pType
pprBindings = map pprBinding bindings
-- | The free variables of an 'Env'ironment are all the free variables of the
-- 'PType's it contains.
freeEnv :: Env -> Set Name
freeEnv (Env env) = let allPTypes = M.elems env
in S.unions (map freePType allPTypes)
-- | Performing a 'Subst'itution in an 'Env'ironment means performing that
-- substituion on all the contained 'PType's.
instance Substitutable Env where
applySubst s (Env env) = Env (M.map (applySubst s) env)
-- #############################################################################
-- ** Substitutions
-- #############################################################################
-- | A substitution is a mapping from type variables to 'MType's. Applying a
-- substitution means applying those replacements. For example, the substitution
-- @a -> Int@ applied to @a -> a@ yields the result @Int -> Int@.
--
-- A key concept behind Hindley-Milner is that once we dive deeper into an
-- expression, we learn more about our type variables. We might learn that @a@
-- has to be specialized to @b -> b@, and then later on that @b@ is actually
-- @Int@. Substitutions are an organized way of carrying this information along.
newtype Subst = Subst (Map Name MType)
-- | We're going to apply substitutions to a variety of other values that
-- somehow contain type variables, so we overload this application operation in
-- a class here.
--
-- Laws:
--
-- @
-- 'applySubst' 'mempty' ≡ 'id'
-- 'applySubst' (s1 '<>' s2) ≡ 'applySubst' s1 . 'applySubst' s2
-- @
class Substitutable a where
applySubst :: Subst -> a -> a
instance (Substitutable a, Substitutable b) => Substitutable (a,b) where
applySubst s (x,y) = (applySubst s x, applySubst s y)
-- | @'applySubst' s1 s2@ applies one substitution to another, replacing all the
-- bindings in the second argument @s2@ with their values mentioned in the first
-- one (@s1@).
instance Substitutable Subst where
applySubst s (Subst target) = Subst (fmap (applySubst s) target)
-- | >>> :{
-- putPprLn (Subst
-- [ ("a", TFun "b" "b")
-- , ("b", TEither "c" "d") ])
-- :}
-- { a > b → b
-- , b > Either c d }
instance Pretty Subst where
ppr (Subst s) = "{ " <> T.intercalate "\n, " [ ppr k <> " > " <> ppr v | (k,v) <- M.toList s ] <> " }"
-- | Combine two substitutions by applying all substitutions mentioned in the
-- first argument to the type variables contained in the second.
instance Monoid Subst where
-- Considering that all we can really do with a substitution is apply it, we
-- can use the one of 'Substitutable's laws to show that substitutions
-- combine associatively,
--
-- @
-- applySubst (compose s1 (compose s2 s3))
-- = applySubst s1 . applySubst (compose s2 s3)
-- = applySubst s1 . applySubst s2 . applySubst s3
-- = applySubst (compose s1 s2) . applySubst s3
-- = applySubst (compose (compose s1 s2) s3)
-- @
mappend subst1 subst2 = Subst (s1 `M.union` s2)
where
Subst s1 = subst1
Subst s2 = applySubst subst1 subst2
mempty = Subst M.empty
-- #############################################################################
-- #############################################################################
-- * Typechecking
-- #############################################################################
-- #############################################################################
-- $ Typechecking does two things:
--
-- 1. If two types are not immediately identical, attempt to 'unify' them
-- to get a type compatible with both of them
-- 2. 'infer' the most general type of a value by comparing the values in its
-- definition with the 'Env'ironment
-- #############################################################################
-- ** Inference context
-- #############################################################################
-- | The inference type holds a supply of unique names, and can fail with a
-- descriptive error if something goes wrong.
--
-- /Invariant:/ the supply must be infinite, or we might run out of names to
-- give to things.
newtype Infer a = Infer (ExceptT InferError (State [Name]) a)
deriving (Functor, Applicative, Monad)
-- | Errors that can happen during the type inference process.
data InferError =
-- | Two types that don't match were attempted to be unified.
--
-- For example, @a -> a@ and @Int@ do not unify.
--
-- >>> putPprLn (CannotUnify (TFun "a" "a") (TConst "Int"))
-- Cannot unify a → a with Int
CannotUnify MType MType
-- | A 'TVar' is bound to an 'MType' that already contains it.
--
-- The canonical example of this is @λx. x x@, where the first @x@
-- in the body has to have type @a -> b@, and the second one @a@. Since
-- they're both the same @x@, this requires unification of @a@ with
-- @a -> b@, which only works if @a = a -> b = (a -> b) -> b = …@, yielding
-- an infinite type.
--
-- >>> putPprLn (OccursCheckFailed "a" (TFun "a" "a"))
-- Occurs check failed: a already appears in a → a
| OccursCheckFailed Name MType
-- | The value of an unknown identifier was read.
--
-- >>> putPprLn (UnknownIdentifier "a")
-- Unknown identifier: a
| UnknownIdentifier Name
deriving Show
-- | >>> putPprLn (CannotUnify (TEither "a" "b") (TTuple "a" "b"))
-- Cannot unify Either a b with (a, b)
instance Pretty InferError where
ppr = \case
CannotUnify t1 t2 ->
"Cannot unify " <> ppr t1 <> " with " <> ppr t2
OccursCheckFailed name ty ->
"Occurs check failed: " <> ppr name <> " already appears in " <> ppr ty
UnknownIdentifier name ->
"Unknown identifier: " <> ppr name
-- | Evaluate a value in an 'Infer'ence context.
--
-- >>> let expr = EAbs "f" (EAbs "g" (EAbs "x" (EApp (EApp "f" "x") (EApp "g" "x"))))
-- >>> putPprLn expr
-- λf g x. f x (g x)
-- >>> let inferred = runInfer (infer (Env []) expr)
-- >>> let demonstrate = \case Right (_, ty) -> T.putStrLn (":: " <> ppr ty)
-- >>> demonstrate inferred
-- :: (c → e → f) → (c → e) → c → f
runInfer :: Infer a -- ^ Inference data
-> Either InferError a
runInfer (Infer inf) =
evalState (runExceptT inf) (map Name (infiniteSupply alphabet))
where
alphabet = map T.singleton ['a'..'z']
-- [a, b, c] ==> [a,b,c, a1,b1,c1, a2,b2,c2, …]
infiniteSupply supply = supply <> addSuffixes supply (1 :: Integer)
where
addSuffixes xs n = map (\x -> addSuffix x n) xs <> addSuffixes xs (n+1)
addSuffix x n = x <> T.pack (show n)
-- | Throw an 'InferError' in an 'Infer'ence context.
--
-- >>> case runInfer (throw (UnknownIdentifier "var")) of Left err -> putPprLn err
-- Unknown identifier: var
throw :: InferError -> Infer a
throw = Infer . throwE
-- #############################################################################
-- ** Unification
-- #############################################################################
-- $ Unification describes the process of making two different types compatible
-- by specializing them where needed. A desirable property to have here is being
-- able to find the most general unifier. Luckily, we'll be able to do that in
-- our type system.
-- | The unification of two 'MType's is the most general substituion that can be
-- applied to both of them in order to yield the same result.
--
-- >>> let m1 = TFun "a" "b"
-- >>> putPprLn m1
-- a → b
-- >>> let m2 = TFun "c" (TEither "d" "e")
-- >>> putPprLn m2
-- c → Either d e
-- >>> let inferSubst = unify (m1, m2)
-- >>> case runInfer inferSubst of Right subst -> putPprLn subst
-- { a > c
-- , b > Either d e }
unify :: (MType, MType) -> Infer Subst
unify = \case
(TFun a b, TFun x y) -> unifyBinary (a,b) (x,y)
(TVar v, x) -> v `bindVariableTo` x
(x, TVar v) -> v `bindVariableTo` x
(TConst a, TConst b) | a == b -> pure mempty
(TList a, TList b) -> unify (a,b)
(TEither a b, TEither x y) -> unifyBinary (a,b) (x,y)
(TTuple a b, TTuple x y) -> unifyBinary (a,b) (x,y)
(a, b) -> throw (CannotUnify a b)
where
-- Unification of binary type constructors, such as functions and Either.
-- Unification is first done for the first operand, and assuming the
-- required substitution, for the second one.
unifyBinary :: (MType, MType) -> (MType, MType) -> Infer Subst
unifyBinary (a,b) (x,y) = do
s1 <- unify (a, x)
s2 <- unify (applySubst s1 (b, y))
pure (s1 <> s2)
-- | Build a 'Subst'itution that binds a 'Name' of a 'TVar' to an 'MType'. The
-- resulting substitution should be idempotent, i.e. applying it more than once
-- to something should not be any different from applying it only once.
--
-- - In the simplest case, this just means building a substitution that just
-- does that.
-- - Substituting a 'Name' with a 'TVar' with the same name unifies a type
-- variable with itself, and the resulting substitution does nothing new.
-- - If the 'Name' we're trying to bind to an 'MType' already occurs in that
-- 'MType', the resulting substitution would not be idempotent: the 'MType'
-- would be replaced again, yielding a different result. This is known as the
-- Occurs Check.
bindVariableTo :: Name -> MType -> Infer Subst
bindVariableTo name (TVar v) | boundToSelf = pure mempty
where
boundToSelf = name == v
bindVariableTo name mType | name `occursIn` mType = throw (OccursCheckFailed name mType)
where
n `occursIn` ty = n `S.member` freeMType ty
bindVariableTo name mType = pure (Subst (M.singleton name mType))
-- #############################################################################
-- ** Type inference
-- #############################################################################
-- $ Type inference is the act of finding out a value's type by looking at the
-- environment it is in, in order to make it compatible with it.
--
-- In literature, the Hindley-Damas-Milner inference algorithm ("Algorithm W")
-- is often presented in the style of logical formulas, and below you'll find
-- that version along with code that actually does what they say.
--
-- These formulas look a bit like fractions, where the "numerator" is a
-- collection of premises, and the denominator is the consequence if all of them
-- hold.
--
-- __Example:__
--
-- @
-- Γ ⊢ even : Int → Bool Γ ⊢ 1 : Int
--
-- Γ ⊢ even 1 : Bool
-- @
--
-- means that if we have a value of type @Int -> Bool@ called "even" and a value
-- of type @Int@ called @1@, then we also have a value of type @Bool@ via
-- @even 1@ available to us.
--
-- The actual inference rules are polymorphic versions of this example, and
-- the code comments will explain each step in detail.
-- -----------------------------------------------------------------------------
-- *** The language: typed lambda calculus
-- -----------------------------------------------------------------------------
-- | The syntax tree of the language we'd like to typecheck. You can view it as
-- a close relative to simply typed lambda calculus, having only the most
-- necessary syntax elements.
--
-- Since 'ELet' is non-recursive, the usual fixed-point function
-- @fix : (a → a) → a@ can be introduced to allow recursive definitions.
data Exp = ELit Lit -- ^ True, 1
| EVar Name -- ^ @x@
| EApp Exp Exp -- ^ @f x@
| EAbs Name Exp -- ^ @λx. e@
| ELet Name Exp Exp -- ^ @let x = e in e'@ (non-recursive)
deriving Show
-- | Literals we'd like to support. Since we can't define new data types in our
-- simple type system, we'll have to hard-code the possible ones here.
data Lit = LBool Bool
| LInteger Integer
deriving Show
-- | >>> putPprLn (EAbs "f" (EAbs "g" (EAbs "x" (EApp (EApp "f" "x") (EApp "g" "x")))))
-- λf g x. f x (g x)
instance Pretty Exp where
ppr (ELit lit) = ppr lit
ppr (EVar name) = ppr name
ppr (EApp f x) = pprApp1 f <> " " <> pprApp2 x
where
pprApp1 = \case
eLet@ELet{} -> "(" <> ppr eLet <> ")"
eLet@EAbs{} -> "(" <> ppr eLet <> ")"
e -> ppr e
pprApp2 = \case
eApp@EApp{} -> "(" <> ppr eApp <> ")"
e -> pprApp1 e
ppr x@EAbs{} = pprAbs True x
where
pprAbs True (EAbs name expr) = "λ" <> ppr name <> pprAbs False expr
pprAbs False (EAbs name expr) = " " <> ppr name <> pprAbs False expr
pprAbs _ expr = ". " <> ppr expr
ppr (ELet name value body) =
"let " <> ppr name <> " = " <> ppr value <> " in " <> ppr body
-- | >>> putPprLn (LBool True)
-- True
--
-- >>> putPprLn (LInteger 127)
-- 127
instance Pretty Lit where
ppr = \case
LBool b -> showT b
LInteger i -> showT i
where
showT :: Show a => a -> Text
showT = T.pack . show
-- | >>> "var" :: Exp
-- EVar (Name "var")
instance IsString Exp where
fromString = EVar . fromString
-- -----------------------------------------------------------------------------
-- *** Some useful definitions
-- -----------------------------------------------------------------------------
-- | Generate a fresh 'Name' in a type 'Infer'ence context. An example use case
-- of this is η expansion, which transforms @f@ into @λx. f x@, where "x" is a
-- new name, i.e. unbound in the current context.
fresh :: Infer MType
fresh = drawFromSupply >>= \case
Right name -> pure (TVar name)
Left err -> throw err
where
drawFromSupply :: Infer (Either InferError Name)
drawFromSupply = Infer (do
s:upply <- lift get
lift (put upply)
pure (Right s) )
-- | Add a new binding to the environment.
--
-- The Haskell equivalent would be defining a new value, for example in module
-- scope or in a @let@ block. This corresponds to the "comma" operation used in
-- formal notation,
--
-- @
-- Γ, x:σ ≡ extendEnv Γ (x,σ)
-- @
extendEnv :: Env -> (Name, PType) -> Env
extendEnv (Env env) (name, pType) = Env (M.insert name pType env)
-- -----------------------------------------------------------------------------
-- *** Inferring the types of all language constructs
-- -----------------------------------------------------------------------------
-- | Infer the type of an 'Exp'ression in an 'Env'ironment, resulting in the
-- 'Exp's 'MType' along with a substitution that has to be done in order to reach
-- this goal.
--
-- This is widely known as /Algorithm W/.
infer :: Env -> Exp -> Infer (Subst, MType)
infer env = \case
ELit lit -> inferLit lit
EVar name -> inferVar env name
EApp f x -> inferApp env f x
EAbs x e -> inferAbs env x e
ELet x e e' -> inferLet env x e e'
-- | Literals such as 'True' and '1' have their types hard-coded.
inferLit :: Lit -> Infer (Subst, MType)
inferLit lit = pure (mempty, TConst litTy)
where
litTy = case lit of
LBool {} -> "Bool"
LInteger {} -> "Integer"
-- | Inferring the type of a variable is done via
--
-- @
-- x:σ ∈ Γ τ = instantiate(σ)
-- [Var]
-- Γ ⊢ x:τ
-- @
--
-- This means that if @Γ@ /literally contains/ (@∈@) a value, then it also
-- /entails it/ (@⊢@) in all its instantiations.
inferVar :: Env -> Name -> Infer (Subst, MType)
inferVar env name = do
sigma <- lookupEnv env name -- x:σ ∈ Γ
tau <- instantiate sigma -- τ = instantiate(σ)
-- ------------------
pure (mempty, tau) -- Γ ⊢ x:τ
-- | Look up the 'PType' of a 'Name' in the 'Env'ironment.
--
-- This checks whether @x:σ@ is /literally contained/ in @Γ@. For more details
-- about this, see the documentation of 'Env'.
--
-- To give a Haskell analogon, looking up @id@ when @Prelude@ is loaded, the
-- resulting 'PType' would be @id@'s type, namely @forall a. a -> a@.
lookupEnv :: Env -> Name -> Infer PType
lookupEnv (Env env) name = case M.lookup name env of
Just x -> pure x
Nothing -> throw (UnknownIdentifier name)
-- | Bind all quantified variables of a 'PType' to 'fresh' type variables.
--
-- __Example:__ instantiating @forall a. a -> b -> a@ results in the 'MType'
-- @c -> b -> c@, where @c@ is a fresh name (to avoid shadowing issues).
--
-- You can picture the 'PType' to be the prototype converted to an instantiated
-- 'MType', which can now be used in the unification process.
--
-- Another way of looking at it is by simply forgetting which variables were
-- quantified, carefully avoiding name clashes when doing so.
--
-- 'instantiate' can also be seen as the opposite of 'generalize', which we'll
-- need later to convert an 'MType' to a 'PType'.
instantiate :: PType -> Infer MType
instantiate (Forall qs t) = do
subst <- substituteAllWithFresh qs
pure (applySubst subst t)
where
-- For each given name, add a substitution from that name to a fresh type
-- variable to the result.
substituteAllWithFresh :: Set Name -> Infer Subst
substituteAllWithFresh xs = do
let freshSubstActions = M.fromSet (const fresh) xs
freshSubsts <- sequenceA freshSubstActions
pure (Subst freshSubsts)
-- | Function application captures the fact that if we have a function and an
-- argument we can give to that function, we also have the result value of the
-- result type available to us.
--
-- @
-- Γ ⊢ f : fτ Γ ⊢ x : xτ fxτ = fresh unify(fτ, xτ → fxτ)
-- [App]
-- Γ ⊢ f x : fxτ
-- @
--
-- This rule says that given a function and a value with a type, the function
-- type has to unify with a function type that allows the value type to be its
-- argument.
inferApp
:: Env
-> Exp -- ^ __f__ x
-> Exp -- ^ f __x__
-> Infer (Subst, MType)
inferApp env f x = do
(s1, fTau) <- infer env f -- f : fτ
(s2, xTau) <- infer (applySubst s1 env) x -- x : xτ
fxTau <- fresh -- fxτ = fresh
s3 <- unify (applySubst s2 fTau, TFun xTau fxTau) -- unify (fτ, xτ → fxτ)
let s = s3 <> s2 <> s1 -- --------------------
pure (s, applySubst s3 fxTau) -- f x : fxτ
-- | Lambda abstraction is based on the fact that when we introduce a new
-- variable, the resulting lambda maps from that variable's type to the type of
-- the body.
--
-- @
-- τ = fresh σ = ∀∅. τ Γ, x:σ ⊢ e:τ'
-- [Abs]
-- Γ ⊢ λx.e : τ→τ'
-- @
--
-- Here, @Γ, x:τ@ is @Γ@ extended by one additional mapping, namely @x:τ@.
--
-- Abstraction is typed by extending the environment by a new 'MType', and if
-- under this assumption we can construct a function mapping to a value of that
-- type, we can say that the lambda takes a value and maps to it.
inferAbs
:: Env
-> Name -- ^ λ__x__. e
-> Exp -- ^ λx. __e__
-> Infer (Subst, MType)
inferAbs env x e = do
tau <- fresh -- τ = fresh
let sigma = Forall [] tau -- σ = ∀∅. τ
env' = extendEnv env (x, sigma) -- Γ, x:σ
(s, tau') <- infer env' e -- … ⊢ e:τ'
-- ---------------
pure (s, TFun (applySubst s tau) tau') -- λx.e : τ→τ'
-- | A let binding allows extending the environment with new bindings in a
-- principled manner. To do this, we first have to typecheck the expression to
-- be introduced. The result of this is then generalized to a 'PType', since let
-- bindings introduce new polymorphic values, which are then added to the
-- environment. Now we can finally typecheck the body of the "in" part of the
-- let binding.
--
-- Note that in our simple language, let is non-recursive, but recursion can be
-- introduced as usual by adding a primitive @fix : (a → a) → a@ if desired.
--
-- @
-- Γ ⊢ e:τ σ = gen(Γ,τ) Γ, x:σ ⊢ e':τ'
-- [Let]
-- Γ ⊢ let x = e in e' : τ'
-- @
inferLet
:: Env
-> Name -- ^ let __x__ = e in e'
-> Exp -- ^ let x = __e__ in e'
-> Exp -- ^ let x = e in __e'__
-> Infer (Subst, MType)
inferLet env x e e' = do
(s1, tau) <- infer env e -- Γ ⊢ e:τ
let env' = applySubst s1 env
let sigma = generalize env' tau -- σ = gen(Γ,τ)
let env'' = extendEnv env' (x, sigma) -- Γ, x:σ
(s2, tau') <- infer env'' e' -- Γ ⊢ …
-- --------------------------
pure (s2 <> s1, tau') -- … let x = e in e' : τ'
-- | Generalize an 'MType' to a 'PType' by universally quantifying over all the
-- type variables contained in it, except those already free in the environment.
--
-- >>> let tau = TFun "a" (TFun "b" "a")
-- >>> putPprLn tau
-- a → b → a
-- >>> putPprLn (generalize (Env [("x", Forall [] "b")]) tau)
-- ∀a. a → b → a
--
-- In more formal notation,
--
-- @
-- gen(Γ,τ) = ∀{α}. τ
-- where {α} = free(τ) free(Γ)
-- @
--
-- 'generalize' can also be seen as the opposite of 'instantiate', which
-- converts a 'PType' to an 'MType'.
generalize :: Env -> MType -> PType
generalize env mType = Forall qs mType
where
qs = freeMType mType `S.difference` freeEnv env

185
Main.hs
View File

@@ -1,185 +0,0 @@
{-# LANGUAGE OverloadedLists #-}
{-# LANGUAGE OverloadedStrings #-}
module Main where
import qualified Data.Map as M
import Data.Monoid
import Data.Text (Text)
import qualified Data.Text.IO as T
import HindleyMilner
-- #############################################################################
-- #############################################################################
-- * Testing
-- #############################################################################
-- #############################################################################
-- #############################################################################
-- ** A small custom Prelude
-- #############################################################################
prelude :: Env
prelude = Env (M.fromList
[ ("(*)", Forall [] (tInteger ~> tInteger ~> tInteger))
, ("(+)", Forall [] (tInteger ~> tInteger ~> tInteger))
, ("(,)", Forall ["a","b"] ("a" ~> "b" ~> TTuple "a" "b"))
, ("(-)", Forall [] (tInteger ~> tInteger ~> tInteger))
, ("(.)", Forall ["a", "b", "c"] (("b" ~> "c") ~> ("a" ~> "b") ~> "a" ~> "c"))
, ("(<)", Forall [] (tInteger ~> tInteger ~> tBool))
, ("(<=)", Forall [] (tInteger ~> tInteger ~> tBool))
, ("(>)", Forall [] (tInteger ~> tInteger ~> tBool))
, ("(>=)", Forall [] (tInteger ~> tInteger ~> tBool))
, ("const", Forall ["a","b"] ("a" ~> "b" ~> "a"))
, ("Cont/>>=", Forall ["a"] ((("a" ~> "r") ~> "r") ~> ("a" ~> (("b" ~> "r") ~> "r")) ~> (("b" ~> "r") ~> "r")))
, ("find", Forall ["a","b"] (("a" ~> tBool) ~> TList "a" ~> tMaybe "a"))
, ("fix", Forall ["a"] (("a" ~> "a") ~> "a"))
, ("foldr", Forall ["a","b"] (("a" ~> "b" ~> "b") ~> "b" ~> TList "a" ~> "b"))
, ("id", Forall ["a"] ("a" ~> "a"))
, ("ifThenElse", Forall ["a"] (tBool ~> "a" ~> "a" ~> "a"))
, ("Left", Forall ["a","b"] ("a" ~> TEither "a" "b"))
, ("length", Forall ["a"] (TList "a" ~> tInteger))
, ("map", Forall ["a","b"] (("a" ~> "b") ~> TList "a" ~> TList "b"))
, ("reverse", Forall ["a"] (TList "a" ~> TList "a"))
, ("Right", Forall ["a","b"] ("b" ~> TEither "a" "b"))
, ("[]", Forall ["a"] (TList "a"))
, ("(:)", Forall ["a"] ("a" ~> TList "a" ~> TList "a"))
])
where
tBool = TConst "Bool"
tInteger = TConst "Integer"
tMaybe = TEither (TConst "()")
-- | Synonym for 'TFun' to make writing type signatures easier.
--
-- Instead of
--
-- @
-- Forall ["a","b"] (TFun "a" (TFun "b" "a"))
-- @
--
-- we can write
--
-- @
-- Forall ["a","b"] ("a" ~> "b" ~> "a")
-- @
(~>) :: MType -> MType -> MType
(~>) = TFun
infixr 9 ~>
-- #############################################################################
-- ** Run it!
-- #############################################################################
-- | Run type inference on a cuple of values
main :: IO ()
main = do
let inferAndPrint = T.putStrLn . (" " <>) . showType prelude
T.putStrLn "Well-typed:"
do
inferAndPrint (lambda ["x"] "x")
inferAndPrint (lambda ["f","g","x"] (apply "f" ["x", apply "g" ["x"]]))
inferAndPrint (lambda ["f","g","x"] (apply "f" [apply "g" ["x"]]))
inferAndPrint (lambda ["m", "k", "c"] (apply "m" [lambda ["x"] (apply "k" ["x", "c"])])) -- >>= for Cont
inferAndPrint (lambda ["f"] (apply "(.)" ["reverse", apply "map" ["f"]]))
inferAndPrint (apply "find" [lambda ["x"] (apply "(>)" ["x", int 0])])
inferAndPrint (apply "map" [apply "map" ["map"]])
inferAndPrint (apply "(*)" [int 1, int 2])
inferAndPrint (apply "foldr" ["(+)", int 0])
inferAndPrint (apply "map" ["length"])
inferAndPrint (apply "map" ["map"])
inferAndPrint (lambda ["x"] (apply "ifThenElse" [apply "(<)" ["x", int 0], int 0, "x"]))
inferAndPrint (lambda ["x"] (apply "fix" [lambda ["xs"] (apply "(:)" ["x", "xs"])]))
T.putStrLn "Ill-typed:"
do
inferAndPrint (apply "(*)" [int 1, bool True])
inferAndPrint (apply "foldr" [int 1])
inferAndPrint (lambda ["x"] (apply "x" ["x"]))
inferAndPrint (lambda ["x"] (ELet "xs" (apply "(:)" ["x", "xs"]) "xs"))
-- | Build multiple lambda bindings.
--
-- Instead of
--
-- @
-- EAbs "f" (EAbs "x" (EApp "f" "x"))
-- @
--
-- we can write
--
-- @
-- lambda ["f", "x"] (EApp "f" "x")
-- @
--
-- for
--
-- @
-- λf x. f x
-- @
lambda :: [Name] -> Exp -> Exp
lambda names expr = foldr EAbs expr names
-- | Apply a function to multiple arguments.
--
-- Instead of
--
-- @
-- EApp (EApp (EApp "f" "x") "y") "z")
-- @
--
-- we can write
--
-- @
-- apply "f" ["x", "y", "z"]
-- @
--
-- for
--
-- @
-- f x y z
-- @
apply :: Exp -> [Exp] -> Exp
apply = foldl EApp
-- | Construct an integer literal.
int :: Integer -> Exp
int = ELit . LInteger
-- | Construct a boolean literal.
bool :: Bool -> Exp
bool = ELit . LBool
-- | Convenience function to run type inference algorithm
showType :: Env -- ^ Starting environment, e.g. 'prelude'.
-> Exp -- ^ Expression to typecheck
-> Text -- ^ Text representation of the result. Contains an error
-- message on failure.
showType env expr =
case (runInfer . fmap (generalize (Env mempty) . uncurry applySubst) . infer env) expr of
Left err -> "Error inferring type of " <> ppr expr <>": " <> ppr err
Right ty -> ppr expr <> " :: " <> ppr ty

View File

@@ -1,24 +1,21 @@
# Schala - a programming language meta-interpreter
Schala is a Rust framework written to make it easy to create and experiment
with multipl toy programming languages. It provides a cross-language REPL and
provisions for tokenizing text, parsing tokens, evaluating an abstract syntax
tree, and other tasks that are common to all programming languages, as well as sharing state
between multiple programming languages.
Schala is a Rust framework written to make it easy to
create and experiment with toy programming languages. It provides
a common REPL, and a trait `ProgrammingLanguage` with provisions
for tokenizing text, parsing tokens, evaluating an abstract syntax tree,
and other tasks that are common to all programming languages.
Schala is implemented as a Rust library `schala-repl`, which provides a
function `start_repl`, meant to be used as entry point into a common REPL or
non-interactive environment. Clients are expected to invoke `start_repl` with a
vector of programming languages. Individual programming language
implementations are Rust types that implement the
`ProgrammingLanguageInterface` trait and store whatever persistent state is
relevant to that language.
Schala is implemented as a Rust library `schala_lib`, which provides a
`schala_main` function. This function serves as the main loop of the REPL, if run
interactively, or otherwise reads and interprets programming language source
files. It expects as input a vector of `PLIGenerator`, which is a type representing
a closure that returns a boxed trait object that implements the `ProgrammingLanguage` trait,
and stores any persistent state relevant to that programming language. The ability
to share state between different programming languages is in the works.
Run schala with: `cargo run`. This will drop you into a REPL environment. Type
`:help` for more information, or type in text in any supported programming
language (currently only schala-lang) to evaluate it in the REPL.
## History
## About
Schala started out life as an experiment in writing a Javascript-like
programming language that would never encounter any kind of runtime value
@@ -36,18 +33,18 @@ creating a language name confusingly close to Scala. The naming scheme for
languages implemented with the Schala meta-interpreter is Chrono Trigger
characters.
Schala and languages implemented with it are incomplete alpha software and are
not ready for public release.
Schala is incomplete alpha software and is not ready for public release.
## Languages implemented using the meta-interpreter
* The eponymous *Schala* language is a work-in-progress general purpose
programming language with static typing and algebraic data types. Its design
goals include having a very straightforward implemenation and being syntactically
minimal.
* The eponymous *Schala* language is an interpreted/compiled scripting langauge,
designed to be relatively simple, but with a reasonably sophisticated type
system.
* *Maaru* is a very simple dynamically-typed scripting language, with the semantics
that all runtime errors return a `null` value rather than fail.
* *Maaru* was the original Schala (since renamed to free up the name *Schala*
for the above language), a very simple dynamically-typed scripting language
such that all possible runtime errors result in null rather than program
failure.
* *Robo* is an experiment in creating a lazy, functional, strongly-typed language
much like Haskell
@@ -61,15 +58,6 @@ of learning how to write a programming language.
### Type-checking
https://skillsmatter.com/skillscasts/10868-inside-the-rust-compiler
https://www.youtube.com/watch?v=il3gD7XMdmA
http://dev.stephendiehl.com/fun/006_hindley_milner.html
https://rust-lang-nursery.github.io/rustc-guide/type-inference.html
https://eli.thegreenplace.net/2018/unification/
https://eli.thegreenplace.net/2018/type-inference/
http://smallcultfollowing.com/babysteps/blog/2017/03/25/unification-in-chalk-part-1/
http://reasonableapproximation.net/2019/05/05/hindley-milner.html
https://rickyhan.com/jekyll/update/2018/05/26/hindley-milner-tutorial-rust.html
### Evaluation
*Understanding Computation*, Tom Stuart, O'Reilly 2013
@@ -78,7 +66,6 @@ https://rickyhan.com/jekyll/update/2018/05/26/hindley-milner-tutorial-rust.html
### Parsing
http://journal.stuffwithstuff.com/2011/03/19/pratt-parsers-expression-parsing-made-easy/
https://soc.github.io/languages/unified-condition-syntax
[Crafting Interpreters](http://www.craftinginterpreters.com/)
@@ -87,5 +74,4 @@ http://blog.ulysse.io/2016/07/03/llvm-getting-started.html
###Rust resources
https://thefullsnack.com/en/rust-for-the-web.html
https://rocket.rs/guide/getting-started/

127
TODO.md
View File

@@ -1,123 +1,46 @@
# TODO items
## Typechecking
# TODO Items
- look at https://rickyhan.com/jekyll/update/2018/05/26/hindley-milner-tutorial-rust.html
* Share state between programming languages
- cf. the notation mentioned in the cardelli paper, the debug information for the `typechecking` pass should
print the generated type variable for every subexpression in an expression
* idea for Schala - scoped types - be able to define a quick enum type scoped to a function ro something, that only is meant to be used as a quick bespoke interface between two other things
- change 'trait' to 'interface'
- think about idris-related ideas of multiple implementations of a type for an interface (+ vs * impl for monoids, for preorder/inorder/postorder for Foldable)
-should have an Idris-like `cast To From` function
## Schala-lang syntax
-idea: the `type` declaration should have some kind of GADT-like syntax
-idea: I should make the BNF grammar part of the documentation...
- Idea: if you have a pattern-match where one variant has a variable and the other lacks it
instead of treating this as a type error, promote the bound variable to an option type
- Include extensible scala-style html"string ${var}" string interpolations
- A neat idea for pattern matching optimization would be if you could match on one of several things in a list
ex:
```if x {
is (comp, LHSPat, RHSPat) if comp in ["==, "<"] -> ...
}```
- Schala should have both currying *and* default arguments!
```fn a(b: Int, c:Int, d:Int = 1) -> Int
a(1,2) : Int
a(1,2,d=2): Int
a(_,1,3) : Int -> Int
a(1,2, c=_): Int -> Int
a(_,_,_) : Int -> Int -> Int -> Int
```
- scoped types - be able to define a quick enum type scoped to a function or other type for
something, that only is meant to be used as a quick bespoke interface between
two other things
ex.
```type enum {
* another idea, allow:
type enum {
type enum MySubVariant {
SubVariant1, SubVariant2, etc.
}
Variant1(MySubVariant),
Variant2(...),
}```
- inclusive/exclusive range syntax like .. vs ..=
## Compilation
-look into Inkwell for rust LLVM bindings
-https://cranelift.readthedocs.io/en/latest/?badge=latest<Paste>
## Other links of note
- https://nshipster.com/never/
-consult http://gluon-lang.org/book/embedding-api.html
## Playing around with conditional syntax ideas
- if/match playground
simple if
`if x == 1.0 { "a" } else { "b" }`
one comparison multiple targets:
`if x == { 1.0 -> "a", 2.0 -> "b", else -> "c" }`
different comparison operators/ method calls:
`if x { == 1.0 -> "a", eq NaN -> "n", .hella() -> "h", else -> "z" }`
pattern matching/introducing bindings:
`if alice { .age < 18 -> "18", is Person("Alice", age) -> "${age}", else -> "none" }`
pattern matching w/ if-let:
`if person is Person("Alice", age) { "${age}" } else { "nope" }`
-https://soc.github.io/languages/unified-condition-syntax syntax:
`if <cond-expr>" then <then-expr> else <else-expr>`
`if <half-expr> \n <rest-expr1> then <result1-expr> \n <rest-expr2> then <result-expr2> else <result3-expr>`
-and rest-exprs (or "targets") can have 'is' for pattern-matching, actually so can a full cond-expr
UNIFIED IF EXPRESSIONS FINAL WORK:
basic syntax:
`if_expr := if discriminator '{' (guard_expr)* '}'`
`guard_expr := pattern 'then' block_or_expr'`
`pattern := rhs | is_pattern`
`is_pattern := 'is' ???`
`rhs := expression | ???`
if the only two guard patterns are true and false, then the abbreviated syntax:
`'if' discriminator 'then' block_or_expr 'else' block_or_expr`
can replace `'if' discriminator '{' 'true' 'then' block_or_expr; 'false' 'then' block_or_expr '}'`
}
* idea for Schala: both currying *and* default arguments!
ex. fn a(b: Int, c:Int, d:Int = 1) -> Int
a(1,2) : Int
a(1,2,d=2): Int
a(_,1,3) : Int -> Int
a(1,2, c=_): Int -> Int
a(_,_,_) : Int -> Int -> Int -> Int
- AST : maybe replace the Expression type with "Ascription(TypeName, Box<Expression>) nodes??
- parser: add a "debug" field to the Parser struct for all debug-related things
-scala-style html"dfasfsadf${}" string interpolations!
*Compiler passes architecture
-ProgrammingLanguageInterface defines a evaluate_in_repl() and evaluate_no_repl() functions
-these take in a vec of CompilerPasses
struct CompilerPass {
name: String,
run: fn(PrevPass) -> NextPass
}
-change "Type...." names in parser.rs to "Anno..." for non-collision with names in typechecking.rs
-get rid of code pertaining to compilation specifically, have a more generation notion of "execution type"

View File

@@ -1,11 +0,0 @@
[package]
name = "maaru-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
itertools = "0.5.8"
take_mut = "0.1.3"
llvm-sys = "*"
schala-repl = { path = "../schala-repl" }

View File

@@ -1,78 +0,0 @@
#![feature(box_patterns)]
extern crate schala_repl;
mod tokenizer;
mod parser;
mod eval;
#[derive(Debug)]
pub struct TokenError {
pub msg: String,
}
impl TokenError {
pub fn new(msg: &str) -> TokenError {
TokenError { msg: msg.to_string() }
}
}
pub use self::eval::Evaluator as MaaruEvaluator;
pub struct Maaru<'a> {
evaluator: MaaruEvaluator<'a>
}
impl<'a> Maaru<'a> {
pub fn new() -> Maaru<'a> {
Maaru {
evaluator: MaaruEvaluator::new(None),
}
}
}
/*
fn execute_pipeline(&mut self, input: &str, options: &EvalOptions) -> Result<String, String> {
let mut output = UnfinishedComputation::default();
let tokens = match tokenizer::tokenize(input) {
Ok(tokens) => {
if let Some(_) = options.debug_passes.get("tokens") {
output.add_artifact(TraceArtifact::new("tokens", format!("{:?}", tokens)));
}
tokens
},
Err(err) => {
return output.finish(Err(format!("Tokenization error: {:?}\n", err.msg)))
}
};
let ast = match parser::parse(&tokens, &[]) {
Ok(ast) => {
if let Some(_) = options.debug_passes.get("ast") {
output.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast)));
}
ast
},
Err(err) => {
return output.finish(Err(format!("Parse error: {:?}\n", err.msg)))
}
};
let mut evaluation_output = String::new();
for s in self.evaluator.run(ast).iter() {
evaluation_output.push_str(s);
}
Ok(evaluation_output)
}
*/
/*
impl<'a> ProgrammingLanguageInterface for Maaru<'a> {
fn get_language_name(&self) -> String {
"Maaru".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("maaru")
}
}
*/

View File

@@ -1,11 +0,0 @@
[package]
name = "robo-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
itertools = "0.5.8"
take_mut = "0.1.3"
llvm-sys = "*"
schala-repl = { path = "../schala-repl" }

View File

@@ -1,11 +0,0 @@
[package]
name = "rukka-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
itertools = "0.5.8"
take_mut = "0.1.3"
llvm-sys = "*"
schala-repl = { path = "../schala-repl" }

View File

@@ -1,12 +0,0 @@
[package]
name = "schala-lang-codegen"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2018"
[lib]
proc-macro = true
[dependencies]
syn = { version = "0.15.12", features = ["full", "extra-traits", "fold"] }
quote = "0.6.8"

View File

@@ -1,50 +0,0 @@
#![feature(box_patterns)]
#![recursion_limit="128"]
extern crate proc_macro;
#[macro_use]
extern crate quote;
#[macro_use]
extern crate syn;
use self::proc_macro::TokenStream;
use self::syn::fold::Fold;
struct RecursiveDescentFn {
}
impl Fold for RecursiveDescentFn {
fn fold_item_fn(&mut self, mut i: syn::ItemFn) -> syn::ItemFn {
let box block = i.block;
let ref ident = i.ident;
let new_block: syn::Block = parse_quote! {
{
let next_token_before_parse = self.token_handler.peek();
let record = ParseRecord {
production_name: stringify!(#ident).to_string(),
next_token: format!("{}", next_token_before_parse.to_string_with_metadata()),
level: self.parse_level,
};
self.parse_level += 1;
self.parse_record.push(record);
let result = { #block };
if self.parse_level != 0 {
self.parse_level -= 1;
}
result
}
};
i.block = Box::new(new_block);
i
}
}
#[proc_macro_attribute]
pub fn recursive_descent_method(_attr: TokenStream, item: TokenStream) -> TokenStream {
let input: syn::ItemFn = parse_macro_input!(item as syn::ItemFn);
let mut folder = RecursiveDescentFn {};
let output = folder.fold_item_fn(input);
TokenStream::from(quote!(#output))
}

View File

@@ -1,17 +0,0 @@
[package]
name = "schala-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2018"
[dependencies]
itertools = "0.5.8"
take_mut = "0.1.3"
maplit = "*"
lazy_static = "0.2.8"
failure = "0.1.2"
ena = "0.11.0"
stopwatch = "0.0.7"
schala-lang-codegen = { path = "../codegen" }
schala-repl = { path = "../../schala-repl" }

View File

@@ -1,215 +0,0 @@
use std::rc::Rc;
use std::convert::From;
use crate::builtin::{BinOp, PrefixOp};
use crate::typechecking::TypeData;
#[derive(Clone, Debug, PartialEq)]
pub struct Meta<T> {
n: T,
source_map: SourceMap,
type_data: TypeData,
}
impl<T> Meta<T> {
pub fn new(n: T) -> Meta<T> {
Meta { n, source_map: SourceMap::default(), type_data: TypeData::new() }
}
pub fn node(&self) -> &T {
&self.n
}
}
//TODO this PartialEq is here to make tests work - find a way to make it not necessary
#[derive(Clone, Debug, Default, PartialEq)]
struct SourceMap {
}
impl From<Expression> for Meta<Expression> {
fn from(expr: Expression) -> Meta<Expression> {
Meta { n: expr, source_map: SourceMap::default(), type_data: TypeData::new() }
}
}
#[derive(Debug, PartialEq)]
pub struct AST(pub Vec<Meta<Statement>>);
#[derive(Debug, PartialEq, Clone)]
pub enum Statement {
ExpressionStatement(Meta<Expression>),
Declaration(Declaration),
}
pub type Block = Vec<Meta<Statement>>;
pub type ParamName = Rc<String>;
pub type FormalParam = (ParamName, Option<TypeIdentifier>);
#[derive(Debug, PartialEq, Clone)]
pub enum Declaration {
FuncSig(Signature),
FuncDecl(Signature, Block),
TypeDecl {
name: TypeSingletonName,
body: TypeBody,
mutable: bool
},
TypeAlias(Rc<String>, Rc<String>), //should have TypeSingletonName in it, or maybe just String, not sure
Binding {
name: Rc<String>,
constant: bool,
type_anno: Option<TypeIdentifier>,
expr: Meta<Expression>,
},
Impl {
type_name: TypeIdentifier,
interface_name: Option<TypeSingletonName>,
block: Vec<Declaration>,
},
Interface {
name: Rc<String>,
signatures: Vec<Signature>
}
}
#[derive(Debug, PartialEq, Clone)]
pub struct Signature {
pub name: Rc<String>,
pub operator: bool,
pub params: Vec<FormalParam>,
pub type_anno: Option<TypeIdentifier>,
}
#[derive(Debug, PartialEq, Clone)]
pub struct TypeBody(pub Vec<Variant>);
#[derive(Debug, PartialEq, Clone)]
pub enum Variant {
UnitStruct(Rc<String>),
TupleStruct(Rc<String>, Vec<TypeIdentifier>),
Record {
name: Rc<String>,
members: Vec<(Rc<String>, TypeIdentifier)>,
}
}
#[derive(Debug, PartialEq, Clone)]
pub struct Expression(pub ExpressionKind, pub Option<TypeIdentifier>);
#[derive(Debug, PartialEq, Clone)]
pub enum TypeIdentifier {
Tuple(Vec<TypeIdentifier>),
Singleton(TypeSingletonName)
}
#[derive(Debug, PartialEq, Clone)]
pub struct TypeSingletonName {
pub name: Rc<String>,
pub params: Vec<TypeIdentifier>,
}
#[derive(Debug, PartialEq, Clone)]
pub enum ExpressionKind {
NatLiteral(u64),
FloatLiteral(f64),
StringLiteral(Rc<String>),
BoolLiteral(bool),
BinExp(BinOp, Box<Meta<Expression>>, Box<Meta<Expression>>),
PrefixExp(PrefixOp, Box<Meta<Expression>>),
TupleLiteral(Vec<Meta<Expression>>),
Value(Rc<String>),
NamedStruct {
name: Rc<String>,
fields: Vec<(Rc<String>, Meta<Expression>)>,
},
Call {
f: Box<Meta<Expression>>,
arguments: Vec<Meta<Expression>>,
},
Index {
indexee: Box<Meta<Expression>>,
indexers: Vec<Meta<Expression>>,
},
IfExpression {
discriminator: Box<Discriminator>,
body: Box<IfExpressionBody>,
},
WhileExpression {
condition: Option<Box<Meta<Expression>>>,
body: Block,
},
ForExpression {
enumerators: Vec<Enumerator>,
body: Box<ForBody>,
},
Lambda {
params: Vec<FormalParam>,
type_anno: Option<TypeIdentifier>,
body: Block,
},
ListLiteral(Vec<Meta<Expression>>),
}
#[derive(Debug, PartialEq, Clone)]
pub enum Discriminator {
Simple(Expression),
BinOp(Expression, BinOp)
}
#[derive(Debug, PartialEq, Clone)]
pub enum IfExpressionBody {
SimpleConditional(Block, Option<Block>),
SimplePatternMatch(Pattern, Block, Option<Block>),
GuardList(Vec<GuardArm>)
}
#[derive(Debug, PartialEq, Clone)]
pub struct GuardArm {
pub guard: Guard,
pub body: Block,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Guard {
Pat(Pattern),
HalfExpr(HalfExpr)
}
#[derive(Debug, PartialEq, Clone)]
pub struct HalfExpr {
pub op: Option<BinOp>,
pub expr: ExpressionKind,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Pattern {
Ignored,
TuplePattern(Vec<Pattern>),
Literal(PatternLiteral),
TupleStruct(Rc<String>, Vec<Pattern>),
Record(Rc<String>, Vec<(Rc<String>, Pattern)>),
}
#[derive(Debug, PartialEq, Clone)]
pub enum PatternLiteral {
NumPattern {
neg: bool,
num: ExpressionKind,
},
StringPattern(Rc<String>),
BoolPattern(bool),
VarPattern(Rc<String>)
}
#[derive(Debug, PartialEq, Clone)]
pub struct Enumerator {
pub id: Rc<String>,
pub generator: Meta<Expression>,
}
#[derive(Debug, PartialEq, Clone)]
pub enum ForBody {
MonadicReturn(Meta<Expression>),
StatementBlock(Block),
}

View File

@@ -1,122 +0,0 @@
use std::rc::Rc;
use std::collections::HashMap;
use crate::tokenizing::TokenKind;
use crate::typechecking::{TypeConst, Type};
#[derive(Debug, PartialEq, Clone)]
pub struct BinOp {
sigil: Rc<String>
}
impl BinOp {
pub fn from_sigil(sigil: &str) -> BinOp {
BinOp { sigil: Rc::new(sigil.to_string()) }
}
pub fn sigil(&self) -> &Rc<String> {
&self.sigil
}
pub fn from_sigil_token(tok: &TokenKind) -> Option<BinOp> {
use self::TokenKind::*;
let s = match tok {
Operator(op) => op,
Period => ".",
Pipe => "|",
Slash => "/",
LAngleBracket => "<",
RAngleBracket => ">",
_ => return None
};
Some(BinOp::from_sigil(s))
}
pub fn get_type(&self) -> Result<Type, String> {
let s = self.sigil.as_str();
BINOPS.get(s).map(|x| x.0.clone()).ok_or(format!("Binop {} not found", s))
}
pub fn min_precedence() -> i32 {
i32::min_value()
}
pub fn get_precedence_from_token(op: &TokenKind) -> Option<i32> {
use self::TokenKind::*;
let s = match op {
Operator(op) => op,
Period => ".",
Pipe => "|",
Slash => "/",
LAngleBracket => "<",
RAngleBracket => ">",
_ => return None
};
let default = 10_000_000;
Some(BINOPS.get(s).map(|x| x.2.clone()).unwrap_or_else(|| {
default
}))
}
pub fn get_precedence(&self) -> i32 {
let s: &str = &self.sigil;
let default = 10_000_000;
BINOPS.get(s).map(|x| x.2.clone()).unwrap_or_else(|| {
default
})
}
}
#[derive(Debug, PartialEq, Clone)]
pub struct PrefixOp {
sigil: Rc<String>
}
impl PrefixOp {
pub fn from_sigil(sigil: &str) -> PrefixOp {
PrefixOp { sigil: Rc::new(sigil.to_string()) }
}
pub fn sigil(&self) -> &Rc<String> {
&self.sigil
}
pub fn is_prefix(op: &str) -> bool {
PREFIX_OPS.get(op).is_some()
}
pub fn get_type(&self) -> Result<Type, String> {
let s = self.sigil.as_str();
PREFIX_OPS.get(s).map(|x| x.0.clone()).ok_or(format!("Prefix op {} not found", s))
}
}
lazy_static! {
static ref PREFIX_OPS: HashMap<&'static str, (Type, ())> =
hashmap! {
"+" => (ty!(Nat -> Int), ()),
"-" => (ty!(Nat -> Int), ()),
"!" => (ty!(Bool -> Bool), ()),
};
}
/* the second tuple member is a placeholder for when I want to make evaluation rules tied to the
* binop definition */
//TODO some of these types are going to have to be adjusted
lazy_static! {
static ref BINOPS: HashMap<&'static str, (Type, (), i32)> =
hashmap! {
"+" => (ty!(Nat -> Nat -> Nat), (), 10),
"-" => (ty!(Nat -> Nat -> Nat), (), 10),
"*" => (ty!(Nat -> Nat -> Nat), (), 20),
"/" => (ty!(Nat -> Nat -> Float), (), 20),
"quot" => (ty!(Nat -> Nat -> Nat), (), 20),
"%" => (ty!(Nat -> Nat -> Nat), (), 20),
"++" => (ty!(StringT -> StringT -> StringT), (), 30),
"^" => (ty!(Nat -> Nat -> Nat), (), 20),
"&" => (ty!(Nat -> Nat -> Nat), (), 20),
"|" => (ty!(Nat -> Nat -> Nat), (), 20),
">" => (ty!(Nat -> Nat -> Bool), (), 20),
">=" => (ty!(Nat -> Nat -> Bool), (), 20),
"<" => (ty!(Nat -> Nat -> Bool), (), 20),
"<=" => (ty!(Nat -> Nat -> Bool), (), 20),
"==" => (ty!(Nat -> Nat -> Bool), (), 20),
"=" => (ty!(Unit), (), 20), //TODO not sure what the type of this should be b/c special fmr
"<=>" => (ty!(Nat -> Nat -> Ordering), (), 20), //TODO figure out how to treat Order
};
}

View File

@@ -1,747 +0,0 @@
use std::cell::RefCell;
use std::rc::Rc;
use std::fmt::Write;
use std::io;
use itertools::Itertools;
use crate::util::ScopeStack;
use crate::reduced_ast::{BoundVars, ReducedAST, Stmt, Expr, Lit, Func, Alternative, Subpattern};
use crate::symbol_table::{SymbolSpec, Symbol, SymbolTable};
pub struct State<'a> {
values: ScopeStack<'a, Rc<String>, ValueEntry>,
symbol_table_handle: Rc<RefCell<SymbolTable>>,
}
macro_rules! builtin_binding {
($name:expr, $values:expr) => {
$values.insert(Rc::new(format!($name)), ValueEntry::Binding { constant: true, val: Node::Expr(Expr::Func(Func::BuiltIn(Rc::new(format!($name))))) });
}
}
impl<'a> State<'a> {
pub fn new(symbol_table_handle: Rc<RefCell<SymbolTable>>) -> State<'a> {
let mut values = ScopeStack::new(Some(format!("global")));
builtin_binding!("print", values);
builtin_binding!("println", values);
builtin_binding!("getline", values);
State { values, symbol_table_handle }
}
pub fn debug_print(&self) -> String {
format!("Values: {:?}", self.values)
}
fn new_frame(&'a self, items: &'a Vec<Node>, bound_vars: &BoundVars) -> State<'a> {
let mut inner_state = State {
values: self.values.new_scope(None),
symbol_table_handle: self.symbol_table_handle.clone(),
};
for (bound_var, val) in bound_vars.iter().zip(items.iter()) {
if let Some(bv) = bound_var.as_ref() {
inner_state.values.insert(bv.clone(), ValueEntry::Binding { constant: true, val: val.clone() });
}
}
inner_state
}
}
#[derive(Debug, Clone)]
enum Node {
Expr(Expr),
PrimObject {
name: Rc<String>,
tag: usize,
items: Vec<Node>,
},
PrimTuple {
items: Vec<Node>
}
}
fn paren_wrapped_vec(terms: impl Iterator<Item=String>) -> String {
let mut buf = String::new();
write!(buf, "(").unwrap();
for term in terms.map(|e| Some(e)).intersperse(None) {
match term {
Some(e) => write!(buf, "{}", e).unwrap(),
None => write!(buf, ", ").unwrap(),
};
}
write!(buf, ")").unwrap();
buf
}
impl Node {
fn to_repl(&self) -> String {
match self {
Node::Expr(e) => e.to_repl(),
Node::PrimObject { name, items, .. } if items.len() == 0 => format!("{}", name),
Node::PrimObject { name, items, .. } => format!("{}{}", name, paren_wrapped_vec(items.iter().map(|x| x.to_repl()))),
Node::PrimTuple { items } => format!("{}", paren_wrapped_vec(items.iter().map(|x| x.to_repl()))),
}
}
fn is_true(&self) -> bool {
match self {
Node::Expr(Expr::Lit(crate::reduced_ast::Lit::Bool(true))) => true,
_ => false,
}
}
}
#[derive(Debug)]
enum ValueEntry {
Binding {
constant: bool,
val: /*FullyEvaluatedExpr*/ Node, //TODO make this use a subtype to represent fully evaluatedness
}
}
type EvalResult<T> = Result<T, String>;
impl Expr {
fn to_node(self) -> Node {
Node::Expr(self)
}
fn to_repl(&self) -> String {
use self::Lit::*;
use self::Func::*;
match self {
Expr::Lit(ref l) => match l {
Nat(n) => format!("{}", n),
Int(i) => format!("{}", i),
Float(f) => format!("{}", f),
Bool(b) => format!("{}", b),
StringLit(s) => format!("\"{}\"", s),
},
Expr::Func(f) => match f {
BuiltIn(name) => format!("<built-in function '{}'>", name),
UserDefined { name: None, .. } => format!("<function>"),
UserDefined { name: Some(name), .. } => format!("<function '{}'>", name),
},
Expr::Constructor {
type_name: _, name, arity, ..
} => if *arity == 0 {
format!("{}", name)
} else {
format!("<data constructor '{}'>", name)
},
Expr::Tuple(exprs) => paren_wrapped_vec(exprs.iter().map(|x| x.to_repl())),
_ => format!("{:?}", self),
}
}
fn replace_conditional_target_sigil(self, replacement: &Expr) -> Expr {
use self::Expr::*;
match self {
ConditionalTargetSigilValue => replacement.clone(),
Unit | Lit(_) | Func(_) | Val(_) | Constructor { .. } |
CaseMatch { .. } | UnimplementedSigilValue => self,
Tuple(exprs) => Tuple(exprs.into_iter().map(|e| e.replace_conditional_target_sigil(replacement)).collect()),
Call { f, args } => {
let new_args = args.into_iter().map(|e| e.replace_conditional_target_sigil(replacement)).collect();
Call { f, args: new_args }
},
Conditional { .. } => panic!("Dunno if I need this, but if so implement"),
Assign { .. } => panic!("I'm pretty sure I don't need this"),
}
}
}
impl<'a> State<'a> {
pub fn evaluate(&mut self, ast: ReducedAST, repl: bool) -> Vec<Result<String, String>> {
let mut acc = vec![];
// handle prebindings
for statement in ast.0.iter() {
self.prebinding(statement);
}
for statement in ast.0 {
match self.statement(statement) {
Ok(Some(ref output)) if repl => acc.push(Ok(output.to_repl())),
Ok(_) => (),
Err(error) => {
acc.push(Err(format!("Runtime error: {}", error)));
return acc;
},
}
}
acc
}
fn prebinding(&mut self, stmt: &Stmt) {
match stmt {
Stmt::PreBinding { name, func } => {
let v_entry = ValueEntry::Binding { constant: true, val: Node::Expr(Expr::Func(func.clone())) };
self.values.insert(name.clone(), v_entry);
},
Stmt::Expr(_expr) => {
//TODO have this support things like nested function defs
},
_ => ()
}
}
fn statement(&mut self, stmt: Stmt) -> EvalResult<Option<Node>> {
match stmt {
Stmt::Binding { name, constant, expr } => {
let val = self.expression(Node::Expr(expr))?;
self.values.insert(name.clone(), ValueEntry::Binding { constant, val });
Ok(None)
},
Stmt::Expr(expr) => Ok(Some(self.expression(expr.to_node())?)),
Stmt::PreBinding {..} | Stmt::Noop => Ok(None),
}
}
fn block(&mut self, stmts: Vec<Stmt>) -> EvalResult<Node> {
let mut ret = None;
for stmt in stmts {
ret = self.statement(stmt)?;
}
Ok(ret.unwrap_or(Node::Expr(Expr::Unit)))
}
fn expression(&mut self, node: Node) -> EvalResult<Node> {
use self::Expr::*;
match node {
t @ Node::PrimTuple { .. } => Ok(t),
obj @ Node::PrimObject { .. } => Ok(obj),
Node::Expr(expr) => match expr {
literal @ Lit(_) => Ok(Node::Expr(literal)),
Call { box f, args } => self.call_expression(f, args),
Val(v) => self.value(v),
Constructor { arity, ref name, tag, .. } if arity == 0 => Ok(Node::PrimObject { name: name.clone(), tag, items: vec![] }),
constructor @ Constructor { .. } => Ok(Node::Expr(constructor)),
func @ Func(_) => Ok(Node::Expr(func)),
Tuple(exprs) => {
let nodes = exprs.into_iter().map(|expr| self.expression(Node::Expr(expr))).collect::<Result<Vec<Node>,_>>()?;
Ok(Node::PrimTuple { items: nodes })
},
Conditional { box cond, then_clause, else_clause } => self.conditional(cond, then_clause, else_clause),
Assign { box val, box expr } => self.assign_expression(val, expr),
Unit => Ok(Node::Expr(Unit)),
CaseMatch { box cond, alternatives } => self.case_match_expression(cond, alternatives),
ConditionalTargetSigilValue => Ok(Node::Expr(ConditionalTargetSigilValue)),
UnimplementedSigilValue => Err(format!("Sigil value eval not implemented")),
}
}
}
fn call_expression(&mut self, f: Expr, args: Vec<Expr>) -> EvalResult<Node> {
use self::Expr::*;
match self.expression(Node::Expr(f))? {
Node::Expr(Constructor { type_name, name, tag, arity }) => self.apply_data_constructor(type_name, name, tag, arity, args),
Node::Expr(Func(f)) => self.apply_function(f, args),
other => return Err(format!("Tried to call {:?} which is not a function or data constructor", other)),
}
}
fn apply_data_constructor(&mut self, _type_name: Rc<String>, name: Rc<String>, tag: usize, arity: usize, args: Vec<Expr>) -> EvalResult<Node> {
if arity != args.len() {
return Err(format!("Data constructor {} requires {} args", name, arity));
}
let evaled_args = args.into_iter().map(|expr| self.expression(Node::Expr(expr))).collect::<Result<Vec<Node>,_>>()?;
//let evaled_args = vec![];
Ok(Node::PrimObject {
name: name.clone(),
items: evaled_args,
tag
})
}
fn apply_function(&mut self, f: Func, args: Vec<Expr>) -> EvalResult<Node> {
match f {
Func::BuiltIn(sigil) => Ok(Node::Expr(self.apply_builtin(sigil, args)?)),
Func::UserDefined { params, body, name } => {
if params.len() != args.len() {
return Err(format!("calling a {}-argument function with {} args", params.len(), args.len()))
}
let mut func_state = State {
values: self.values.new_scope(name.map(|n| format!("{}", n))),
symbol_table_handle: self.symbol_table_handle.clone(),
};
for (param, val) in params.into_iter().zip(args.into_iter()) {
let val = func_state.expression(Node::Expr(val))?;
func_state.values.insert(param, ValueEntry::Binding { constant: true, val });
}
// TODO figure out function return semantics
func_state.block(body)
}
}
}
fn apply_builtin(&mut self, name: Rc<String>, args: Vec<Expr>) -> EvalResult<Expr> {
use self::Expr::*;
use self::Lit::*;
let evaled_args: Result<Vec<Expr>, String> = args.into_iter().map(|arg| {
match self.expression(Node::Expr(arg)) {
Ok(Node::Expr(e)) => Ok(e),
Ok(Node::PrimTuple { .. }) => Err(format!("Trying to apply a builtin to a tuple")),
Ok(Node::PrimObject { .. }) => Err(format!("Trying to apply a builtin to a primitive object")),
Err(e) => Err(e)
}
}).collect();
let evaled_args = evaled_args?;
Ok(match (name.as_str(), evaled_args.as_slice()) {
/* binops */
("+", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l + r)),
("++", &[Lit(StringLit(ref s1)), Lit(StringLit(ref s2))]) => Lit(StringLit(Rc::new(format!("{}{}", s1, s2)))),
("-", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l - r)),
("*", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l * r)),
("/", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Float((l as f64)/ (r as f64))),
("quot", &[Lit(Nat(l)), Lit(Nat(r))]) => if r == 0 {
return Err(format!("divide by zero"));
} else {
Lit(Nat(l / r))
},
("%", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l % r)),
("^", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l ^ r)),
("&", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l & r)),
("|", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l | r)),
/* comparisons */
("==", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l == r)),
("==", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l == r)),
("==", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l == r)),
("==", &[Lit(Bool(l)), Lit(Bool(r))]) => Lit(Bool(l == r)),
("==", &[Lit(StringLit(ref l)), Lit(StringLit(ref r))]) => Lit(Bool(l == r)),
("<", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l < r)),
("<", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l < r)),
("<", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l < r)),
("<=", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l <= r)),
("<=", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l <= r)),
("<=", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l <= r)),
(">", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l > r)),
(">", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l > r)),
(">", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l > r)),
(">=", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l >= r)),
(">=", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l >= r)),
(">=", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l >= r)),
/* prefix ops */
("!", &[Lit(Bool(true))]) => Lit(Bool(false)),
("!", &[Lit(Bool(false))]) => Lit(Bool(true)),
("-", &[Lit(Nat(n))]) => Lit(Int(-1*(n as i64))),
("-", &[Lit(Int(n))]) => Lit(Int(-1*(n as i64))),
("+", &[Lit(Int(n))]) => Lit(Int(n)),
("+", &[Lit(Nat(n))]) => Lit(Nat(n)),
/* builtin functions */
("print", &[ref anything]) => {
print!("{}", anything.to_repl());
Expr::Unit
},
("println", &[ref anything]) => {
println!("{}", anything.to_repl());
Expr::Unit
},
("getline", &[]) => {
let mut buf = String::new();
io::stdin().read_line(&mut buf).expect("Error readling line in 'getline'");
Lit(StringLit(Rc::new(buf.trim().to_string())))
},
(x, args) => return Err(format!("bad or unimplemented builtin {:?} | {:?}", x, args)),
})
}
fn conditional(&mut self, cond: Expr, then_clause: Vec<Stmt>, else_clause: Vec<Stmt>) -> EvalResult<Node> {
let cond = self.expression(Node::Expr(cond))?;
Ok(match cond {
Node::Expr(Expr::Lit(Lit::Bool(true))) => self.block(then_clause)?,
Node::Expr(Expr::Lit(Lit::Bool(false))) => self.block(else_clause)?,
_ => return Err(format!("Conditional with non-boolean condition"))
})
}
fn assign_expression(&mut self, val: Expr, expr: Expr) -> EvalResult<Node> {
let name = match val {
Expr::Val(name) => name,
_ => return Err(format!("Trying to assign to a non-value")),
};
let constant = match self.values.lookup(&name) {
None => return Err(format!("Constant {} is undefined", name)),
Some(ValueEntry::Binding { constant, .. }) => constant.clone(),
};
if constant {
return Err(format!("trying to update {}, a non-mutable binding", name));
}
let val = self.expression(Node::Expr(expr))?;
self.values.insert(name.clone(), ValueEntry::Binding { constant: false, val });
Ok(Node::Expr(Expr::Unit))
}
fn guard_passes(&mut self, guard: &Option<Expr>, cond: &Node) -> EvalResult<bool> {
if let Some(ref guard_expr) = guard {
let guard_expr = match cond {
Node::Expr(ref e) => guard_expr.clone().replace_conditional_target_sigil(e),
_ => guard_expr.clone()
};
Ok(self.expression(guard_expr.to_node())?.is_true())
} else {
Ok(true)
}
}
fn case_match_expression(&mut self, cond: Expr, alternatives: Vec<Alternative>) -> EvalResult<Node> {
//TODO need to handle recursive subpatterns
let all_subpatterns_pass = |state: &mut State, subpatterns: &Vec<Option<Subpattern>>, items: &Vec<Node>| -> EvalResult<bool> {
if subpatterns.len() == 0 {
return Ok(true)
}
if items.len() != subpatterns.len() {
return Err(format!("Subpattern length isn't correct items {} subpatterns {}", items.len(), subpatterns.len()));
}
for (maybe_subp, cond) in subpatterns.iter().zip(items.iter()) {
if let Some(subp) = maybe_subp {
if !state.guard_passes(&subp.guard, &cond)? {
return Ok(false)
}
}
}
Ok(true)
};
let cond = self.expression(Node::Expr(cond))?;
for alt in alternatives {
// no matter what type of condition we have, ignore alternative if the guard evaluates false
if !self.guard_passes(&alt.guard, &cond)? {
continue;
}
match cond {
Node::PrimObject { ref tag, ref items, .. } => {
if alt.tag.map(|t| t == *tag).unwrap_or(true) {
let mut inner_state = self.new_frame(items, &alt.bound_vars);
if all_subpatterns_pass(&mut inner_state, &alt.subpatterns, items)? {
return inner_state.block(alt.item);
} else {
continue;
}
}
},
Node::PrimTuple { ref items } => {
let mut inner_state = self.new_frame(items, &alt.bound_vars);
if all_subpatterns_pass(&mut inner_state, &alt.subpatterns, items)? {
return inner_state.block(alt.item);
} else {
continue;
}
},
Node::Expr(ref _e) => {
if let None = alt.tag {
return self.block(alt.item)
}
}
}
}
Err(format!("{:?} failed pattern match", cond))
}
//TODO if I don't need to lookup by name here...
fn value(&mut self, name: Rc<String>) -> EvalResult<Node> {
use self::ValueEntry::*;
use self::Func::*;
//TODO add a layer of indirection here to talk to the symbol table first, and only then look up
//in the values table
let symbol_table = self.symbol_table_handle.borrow();
let value = symbol_table.lookup_by_name(&name);
Ok(match value {
Some(Symbol { name, spec, .. }) => match spec {
//TODO I'll need this type_name later to do a table lookup
SymbolSpec::DataConstructor { type_name: _type_name, type_args, .. } => {
if type_args.len() == 0 {
Node::PrimObject { name: name.clone(), tag: 0, items: vec![] }
} else {
return Err(format!("This data constructor thing not done"))
}
},
SymbolSpec::Func(_) => match self.values.lookup(&name) {
Some(Binding { val: Node::Expr(Expr::Func(UserDefined { name, params, body })), .. }) => {
Node::Expr(Expr::Func(UserDefined { name: name.clone(), params: params.clone(), body: body.clone() }))
},
_ => unreachable!(),
},
SymbolSpec::RecordConstructor { .. } => return Err(format!("This shouldn't be a record!")),
SymbolSpec::Binding => match self.values.lookup(&name) {
Some(Binding { val, .. }) => val.clone(),
None => return Err(format!("Symbol {} exists in symbol table but not in evaluator table", name))
}
},
//TODO ideally this should be returning a runtime error if this is ever None, but it's not
//handling all bindings correctly yet
//None => return Err(format!("Couldn't find value {}", name)),
None => match self.values.lookup(&name) {
Some(Binding { val, .. }) => val.clone(),
None => return Err(format!("Couldn't find value {}", name)),
}
})
}
}
#[cfg(test)]
mod eval_tests {
use std::cell::RefCell;
use std::rc::Rc;
use crate::symbol_table::SymbolTable;
use crate::eval::State;
fn evaluate_all_outputs(input: &str) -> Vec<Result<String, String>> {
let symbol_table = Rc::new(RefCell::new(SymbolTable::new()));
let mut state = State::new(symbol_table);
let ast = crate::util::quick_ast(input);
state.symbol_table_handle.borrow_mut().add_top_level_symbols(&ast).unwrap();
let reduced = ast.reduce(&state.symbol_table_handle.borrow());
let all_output = state.evaluate(reduced, true);
all_output
}
macro_rules! test_in_fresh_env {
($string:expr, $correct:expr) => {
{
let all_output = evaluate_all_outputs($string);
let ref output = all_output.last().unwrap();
assert_eq!(**output, Ok($correct.to_string()));
}
}
}
#[test]
fn test_basic_eval() {
test_in_fresh_env!("1 + 2", "3");
test_in_fresh_env!("let mut a = 1; a = 2", "Unit");
test_in_fresh_env!("let mut a = 1; a = 2; a", "2");
test_in_fresh_env!(r#"("a", 1 + 2)"#, r#"("a", 3)"#);
}
#[test]
fn function_eval() {
test_in_fresh_env!("fn oi(x) { x + 1 }; oi(4)", "5");
test_in_fresh_env!("fn oi(x) { x + 1 }; oi(1+2)", "4");
}
#[test]
fn scopes() {
let scope_ok = r#"
let a = 20
fn haha() {
let a = 10
a
}
haha()
"#;
test_in_fresh_env!(scope_ok, "10");
let scope_ok = r#"
let a = 20
fn haha() {
let a = 10
a
}
a
"#;
test_in_fresh_env!(scope_ok, "20");
}
#[test]
fn if_is_patterns() {
let source = r#"
type Option<T> = Some(T) | None
let x = Some(9); if x is Some(q) then { q } else { 0 }"#;
test_in_fresh_env!(source, "9");
let source = r#"
type Option<T> = Some(T) | None
let x = None; if x is Some(q) then { q } else { 0 }"#;
test_in_fresh_env!(source, "0");
}
#[test]
fn full_if_matching() {
let source = r#"
type Option<T> = Some(T) | None
let a = None
if a { is None -> 4, is Some(x) -> x }
"#;
test_in_fresh_env!(source, "4");
let source = r#"
type Option<T> = Some(T) | None
let a = Some(99)
if a { is None -> 4, is Some(x) -> x }
"#;
test_in_fresh_env!(source, "99");
let source = r#"
let a = 10
if a { is 10 -> "x", is 4 -> "y" }
"#;
test_in_fresh_env!(source, "\"x\"");
let source = r#"
let a = 10
if a { is 15 -> "x", is 10 -> "y" }
"#;
test_in_fresh_env!(source, "\"y\"");
}
#[test]
fn string_pattern() {
let source = r#"
let a = "foo"
if a { is "foo" -> "x", is _ -> "y" }
"#;
test_in_fresh_env!(source, "\"x\"");
}
#[test]
fn boolean_pattern() {
let source = r#"
let a = true
if a {
is true -> "x",
is false -> "y"
}
"#;
test_in_fresh_env!(source, "\"x\"");
}
#[test]
fn boolean_pattern_2() {
let source = r#"
let a = false
if a { is true -> "x", is false -> "y" }
"#;
test_in_fresh_env!(source, "\"y\"");
}
#[test]
fn ignore_pattern() {
let source = r#"
type Option<T> = Some(T) | None
if Some(10) {
is _ -> "hella"
}
"#;
test_in_fresh_env!(source, "\"hella\"");
}
#[test]
fn tuple_pattern() {
let source = r#"
if (1, 2) {
is (1, x) -> x,
is _ -> 99
}
"#;
test_in_fresh_env!(source, 2);
}
#[test]
fn tuple_pattern_2() {
let source = r#"
if (1, 2) {
is (10, x) -> x,
is (y, x) -> x + y
}
"#;
test_in_fresh_env!(source, 3);
}
#[test]
fn tuple_pattern_3() {
let source = r#"
if (1, 5) {
is (10, x) -> x,
is (1, x) -> x
}
"#;
test_in_fresh_env!(source, 5);
}
#[test]
fn tuple_pattern_4() {
let source = r#"
if (1, 5) {
is (10, x) -> x,
is (1, x) -> x,
}
"#;
test_in_fresh_env!(source, 5);
}
#[test]
fn prim_obj_pattern() {
let source = r#"
type Stuff = Mulch(Nat) | Jugs(Nat, String) | Mardok
let a = Mulch(20)
let b = Jugs(1, "haha")
let c = Mardok
let x = if a {
is Mulch(20) -> "x",
is _ -> "ERR"
}
let y = if b {
is Mulch(n) -> "ERR",
is Jugs(2, _) -> "ERR",
is Jugs(1, s) -> s,
is _ -> "ERR",
}
let z = if c {
is Jugs(_, _) -> "ERR",
is Mardok -> "NIGH",
is _ -> "ERR",
}
(x, y, z)
"#;
test_in_fresh_env!(source, r#"("x", "haha", "NIGH")"#);
}
#[test]
fn basic_lambda_syntax() {
let source = r#"
let q = \(x, y) { x * y }
let x = q(5,2)
let y = \(m, n, o) { m + n + o }(1,2,3)
(x, y)
"#;
test_in_fresh_env!(source, r"(10, 6)");
}
#[test]
fn lambda_syntax_2() {
let source = r#"
fn milta() {
\(x) { x + 33 }
}
milta()(10)
"#;
test_in_fresh_env!(source, "43");
}
}

View File

@@ -1,332 +0,0 @@
#![feature(trace_macros)]
#![feature(custom_attribute)]
//#![feature(unrestricted_attribute_tokens)]
#![feature(slice_patterns, box_patterns, box_syntax)]
//! `schala-lang` is where the Schala programming language is actually implemented.
//! It defines the `Schala` type, which contains the state for a Schala REPL, and implements
//! `ProgrammingLanguageInterface` and the chain of compiler passes for it.
extern crate itertools;
#[macro_use]
extern crate lazy_static;
#[macro_use]
extern crate maplit;
extern crate schala_repl;
#[macro_use]
extern crate schala_lang_codegen;
extern crate ena;
use stopwatch::Stopwatch;
use std::time::Duration;
use std::cell::RefCell;
use std::rc::Rc;
use std::collections::HashSet;
use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface,
ComputationRequest, ComputationResponse,
LangMetaRequest, LangMetaResponse, GlobalOutputStats,
DebugResponse, DebugAsk};
macro_rules! bx {
($e:expr) => { Box::new($e) }
}
#[macro_use]
mod util;
#[macro_use]
mod typechecking;
mod tokenizing;
mod ast;
mod parsing;
mod symbol_table;
mod builtin;
mod reduced_ast;
mod eval;
/// All bits of state necessary to parse and execute a Schala program are stored in this struct.
/// `state` represents the execution state for the AST-walking interpreter, the other fields
/// should be self-explanatory.
pub struct Schala {
source_reference: SourceReference,
state: eval::State<'static>,
symbol_table: Rc<RefCell<symbol_table::SymbolTable>>,
type_context: typechecking::TypeContext<'static>,
active_parser: Option<parsing::Parser>,
}
impl Schala {
fn handle_docs(&self, source: String) -> LangMetaResponse {
LangMetaResponse::Docs {
doc_string: format!("Schala item `{}` : <<Schala-lang documentation not yet implemented>>", source)
}
}
}
impl Schala {
/// Creates a new Schala environment *without* any prelude.
fn new_blank_env() -> Schala {
let symbols = Rc::new(RefCell::new(symbol_table::SymbolTable::new()));
Schala {
source_reference: SourceReference::new(),
symbol_table: symbols.clone(),
state: eval::State::new(symbols),
type_context: typechecking::TypeContext::new(),
active_parser: None,
}
}
/// Creates a new Schala environment with the standard prelude, which is defined as ordinary
/// Schala code in the file `prelude.schala`
pub fn new() -> Schala {
let prelude = include_str!("prelude.schala");
let mut s = Schala::new_blank_env();
let request = ComputationRequest { source: prelude, debug_requests: HashSet::default() };
s.run_computation(request);
s
}
fn handle_debug_immediate(&self, request: DebugAsk) -> DebugResponse {
use DebugAsk::*;
match request {
Timing => DebugResponse { ask: Timing, value: format!("Invalid") },
ByStage { stage_name } => match &stage_name[..] {
"symbol-table" => {
let value = self.symbol_table.borrow().debug_symbol_table();
DebugResponse {
ask: ByStage { stage_name: format!("symbol-table") },
value
}
},
s => {
DebugResponse {
ask: ByStage { stage_name: s.to_string() },
value: format!("Not-implemented")
}
}
}
}
}
}
fn tokenizing(input: &str, _handle: &mut Schala, comp: Option<&mut PassDebugArtifact>) -> Result<Vec<tokenizing::Token>, String> {
let tokens = tokenizing::tokenize(input);
comp.map(|comp| {
let token_string = tokens.iter().map(|t| t.to_string_with_metadata()).join(", ");
comp.add_artifact(token_string);
});
let errors: Vec<String> = tokens.iter().filter_map(|t| t.get_error()).collect();
if errors.len() == 0 {
Ok(tokens)
} else {
Err(format!("{:?}", errors))
}
}
fn parsing(input: Vec<tokenizing::Token>, handle: &mut Schala, comp: Option<&mut PassDebugArtifact>) -> Result<ast::AST, String> {
use crate::parsing::Parser;
let mut parser = match handle.active_parser.take() {
None => Parser::new(input),
Some(parser) => parser
};
let ast = parser.parse();
let _trace = parser.format_parse_trace();
comp.map(|_comp| {
/*
//TODO need to control which of these debug stages get added
let opt = comp.cur_debug_options.get(0).map(|s| s.clone());
match opt {
None => comp.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast))),
Some(ref s) if s == "compact" => comp.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast))),
Some(ref s) if s == "expanded" => comp.add_artifact(TraceArtifact::new("ast", format!("{:#?}", ast))),
Some(ref s) if s == "trace" => comp.add_artifact(TraceArtifact::new_parse_trace(trace)),
Some(ref x) => println!("Bad parsing debug option: {}", x),
};
*/
});
ast.map_err(|err| format_parse_error(err, handle))
}
fn format_parse_error(error: parsing::ParseError, handle: &mut Schala) -> String {
let line_num = error.token.line_num;
let ch = error.token.char_num;
let line_from_program = handle.source_reference.get_line(line_num);
let location_pointer = format!("{}^", " ".repeat(ch));
let line_num_digits = format!("{}", line_num).chars().count();
let space_padding = " ".repeat(line_num_digits);
format!(r#"
{error_msg}
{space_padding} |
{line_num} | {}
{space_padding} | {}
"#, line_from_program, location_pointer, error_msg=error.msg, space_padding=space_padding, line_num=line_num)
}
fn symbol_table(input: ast::AST, handle: &mut Schala, comp: Option<&mut PassDebugArtifact>) -> Result<ast::AST, String> {
let add = handle.symbol_table.borrow_mut().add_top_level_symbols(&input);
match add {
Ok(()) => {
let debug = handle.symbol_table.borrow().debug_symbol_table();
comp.map(|comp| comp.add_artifact(debug));
Ok(input)
},
Err(msg) => Err(msg)
}
}
fn typechecking(input: ast::AST, handle: &mut Schala, comp: Option<&mut PassDebugArtifact>) -> Result<ast::AST, String> {
let result = handle.type_context.typecheck(&input);
comp.map(|comp| {
comp.add_artifact(match result {
Ok(ty) => ty.to_string(),
Err(err) => format!("Type error: {}", err.msg)
});
});
Ok(input)
}
fn ast_reducing(input: ast::AST, handle: &mut Schala, comp: Option<&mut PassDebugArtifact>) -> Result<reduced_ast::ReducedAST, String> {
let ref symbol_table = handle.symbol_table.borrow();
let output = input.reduce(symbol_table);
comp.map(|comp| comp.add_artifact(format!("{:?}", output)));
Ok(output)
}
fn eval(input: reduced_ast::ReducedAST, handle: &mut Schala, comp: Option<&mut PassDebugArtifact>) -> Result<String, String> {
comp.map(|comp| comp.add_artifact(handle.state.debug_print()));
let evaluation_outputs = handle.state.evaluate(input, true);
let text_output: Result<Vec<String>, String> = evaluation_outputs
.into_iter()
.collect();
let eval_output: Result<String, String> = text_output
.map(|v| { v.into_iter().intersperse(format!("\n")).collect() });
eval_output
}
/// Represents lines of source code
struct SourceReference {
lines: Option<Vec<String>>
}
impl SourceReference {
fn new() -> SourceReference {
SourceReference { lines: None }
}
fn load_new_source(&mut self, source: &str) {
//TODO this is a lot of heap allocations - maybe there's a way to make it more efficient?
self.lines = Some(source.lines().map(|s| s.to_string()).collect()); }
fn get_line(&self, line: usize) -> String {
self.lines.as_ref().and_then(|x| x.get(line).map(|s| s.to_string())).unwrap_or(format!("NO LINE FOUND"))
}
}
#[derive(Default)]
struct PassDebugArtifact {
artifacts: Vec<String>
}
impl PassDebugArtifact {
fn add_artifact(&mut self, artifact: String) {
self.artifacts.push(artifact)
}
}
fn stage_names() -> Vec<&'static str> {
vec![
"tokenizing",
"parsing",
"symbol-table",
"typechecking",
"ast-reduction",
"ast-walking-evaluation"
]
}
impl ProgrammingLanguageInterface for Schala {
fn get_language_name(&self) -> String { format!("Schala") }
fn get_source_file_suffix(&self) -> String { format!("schala") }
fn run_computation(&mut self, request: ComputationRequest) -> ComputationResponse {
struct PassToken<'a> {
schala: &'a mut Schala,
stage_durations: &'a mut Vec<(String, Duration)>,
sw: &'a Stopwatch,
debug_requests: &'a HashSet<DebugAsk>,
debug_responses: &'a mut Vec<DebugResponse>,
}
fn output_wrapper<Input, Output, F>(n: usize, func: F, input: Input, tok: &mut PassToken) -> Result<Output, String>
where F: Fn(Input, &mut Schala, Option<&mut PassDebugArtifact>) -> Result<Output, String>
{
let stage_names = stage_names();
let mut debug_artifact = if tok.debug_requests.contains(&DebugAsk::ByStage { stage_name: stage_names[n].to_string() }) {
Some(PassDebugArtifact::default())
} else {
None
};
let output = func(input, tok.schala, debug_artifact.as_mut());
tok.stage_durations.push((stage_names[n].to_string(), tok.sw.elapsed()));
if let Some(artifact) = debug_artifact {
for value in artifact.artifacts.into_iter() {
let resp = DebugResponse {
ask: DebugAsk::ByStage { stage_name: stage_names[n].to_string() },
value,
};
tok.debug_responses.push(resp);
}
}
output
}
let ComputationRequest { source, debug_requests } = request;
self.source_reference.load_new_source(source);
let sw = Stopwatch::start_new();
let mut stage_durations = Vec::new();
let mut debug_responses = Vec::new();
let mut tok = PassToken { schala: self, stage_durations: &mut stage_durations, sw: &sw, debug_requests: &debug_requests, debug_responses: &mut debug_responses };
let main_output: Result<String, String> = Ok(source)
.and_then(|source| output_wrapper(0, tokenizing, source, &mut tok))
.and_then(|tokens| output_wrapper(1, parsing, tokens, &mut tok))
.and_then(|ast| output_wrapper(2, symbol_table, ast, &mut tok))
.and_then(|ast| output_wrapper(3, typechecking, ast, &mut tok))
.and_then(|ast| output_wrapper(4, ast_reducing, ast, &mut tok))
.and_then(|reduced_ast| output_wrapper(5, eval, reduced_ast, &mut tok));
let total_duration = sw.elapsed();
let global_output_stats = GlobalOutputStats {
total_duration, stage_durations
};
ComputationResponse {
main_output,
global_output_stats,
debug_responses,
}
}
fn request_meta(&mut self, request: LangMetaRequest) -> LangMetaResponse {
match request {
LangMetaRequest::StageNames => LangMetaResponse::StageNames(stage_names().iter().map(|s| s.to_string()).collect()),
LangMetaRequest::Docs { source } => self.handle_docs(source),
LangMetaRequest::ImmediateDebug(debug_request) =>
LangMetaResponse::ImmediateDebug(self.handle_debug_immediate(debug_request)),
LangMetaRequest::Custom { .. } => LangMetaResponse::Custom { kind: format!("not-implemented"), value: format!("") }
}
}
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,13 +0,0 @@
type Option<T> = Some(T) | None
type Color = Red | Green | Blue
type Ord = LT | EQ | GT
fn map(input: Option<T>, func: Func): Option<T> {
if input {
is Some(x) -> Some(func(x)),
is None -> None,
}
}

View File

@@ -1,397 +0,0 @@
use std::rc::Rc;
use crate::ast::*;
use crate::symbol_table::{Symbol, SymbolSpec, SymbolTable};
use crate::builtin::{BinOp, PrefixOp};
#[derive(Debug)]
pub struct ReducedAST(pub Vec<Stmt>);
#[derive(Debug, Clone)]
pub enum Stmt {
PreBinding {
name: Rc<String>,
func: Func,
},
Binding {
name: Rc<String>,
constant: bool,
expr: Expr,
},
Expr(Expr),
Noop,
}
#[derive(Debug, Clone)]
pub enum Expr {
Unit,
Lit(Lit),
Tuple(Vec<Expr>),
Func(Func),
Val(Rc<String>),
Constructor {
type_name: Rc<String>,
name: Rc<String>,
tag: usize,
arity: usize,
},
Call {
f: Box<Expr>,
args: Vec<Expr>,
},
Assign {
val: Box<Expr>,
expr: Box<Expr>,
},
Conditional {
cond: Box<Expr>,
then_clause: Vec<Stmt>,
else_clause: Vec<Stmt>,
},
ConditionalTargetSigilValue,
CaseMatch {
cond: Box<Expr>,
alternatives: Vec<Alternative>
},
UnimplementedSigilValue
}
pub type BoundVars = Vec<Option<Rc<String>>>; //remember that order matters here
#[derive(Debug, Clone)]
pub struct Alternative {
pub tag: Option<usize>,
pub subpatterns: Vec<Option<Subpattern>>,
pub guard: Option<Expr>,
pub bound_vars: BoundVars,
pub item: Vec<Stmt>,
}
#[derive(Debug, Clone)]
pub struct Subpattern {
pub tag: Option<usize>,
pub subpatterns: Vec<Option<Subpattern>>,
pub bound_vars: BoundVars,
pub guard: Option<Expr>,
}
#[derive(Debug, Clone)]
pub enum Lit {
Nat(u64),
Int(i64),
Float(f64),
Bool(bool),
StringLit(Rc<String>),
}
#[derive(Debug, Clone)]
pub enum Func {
BuiltIn(Rc<String>),
UserDefined {
name: Option<Rc<String>>,
params: Vec<Rc<String>>,
body: Vec<Stmt>,
}
}
impl AST {
pub fn reduce(&self, symbol_table: &SymbolTable) -> ReducedAST {
let mut output = vec![];
for statement in self.0.iter() {
output.push(statement.node().reduce(symbol_table));
}
ReducedAST(output)
}
}
impl Statement {
fn reduce(&self, symbol_table: &SymbolTable) -> Stmt {
use crate::ast::Statement::*;
match self {
ExpressionStatement(expr) => Stmt::Expr(expr.node().reduce(symbol_table)),
Declaration(decl) => decl.reduce(symbol_table),
}
}
}
fn reduce_block(block: &Block, symbol_table: &SymbolTable) -> Vec<Stmt> {
block.iter().map(|stmt| stmt.node().reduce(symbol_table)).collect()
}
impl Expression {
fn reduce(&self, symbol_table: &SymbolTable) -> Expr {
use crate::ast::ExpressionKind::*;
let ref input = self.0;
match input {
NatLiteral(n) => Expr::Lit(Lit::Nat(*n)),
FloatLiteral(f) => Expr::Lit(Lit::Float(*f)),
StringLiteral(s) => Expr::Lit(Lit::StringLit(s.clone())),
BoolLiteral(b) => Expr::Lit(Lit::Bool(*b)),
BinExp(binop, lhs, rhs) => binop.reduce(symbol_table, lhs, rhs),
PrefixExp(op, arg) => op.reduce(symbol_table, arg),
Value(name) => match symbol_table.lookup_by_name(name) {
Some(Symbol { spec: SymbolSpec::DataConstructor { index, type_args, type_name}, .. }) => Expr::Constructor {
type_name: type_name.clone(),
name: name.clone(),
tag: index.clone(),
arity: type_args.len(),
},
_ => Expr::Val(name.clone()),
},
Call { f, arguments } => Expr::Call {
f: Box::new(f.node().reduce(symbol_table)),
args: arguments.iter().map(|arg| arg.node().reduce(symbol_table)).collect(),
},
TupleLiteral(exprs) => Expr::Tuple(exprs.iter().map(|e| e.node().reduce(symbol_table)).collect()),
IfExpression { discriminator, body } => reduce_if_expression(discriminator, body, symbol_table),
Lambda { params, body, .. } => reduce_lambda(params, body, symbol_table),
NamedStruct { .. } => Expr::UnimplementedSigilValue,
Index { .. } => Expr::UnimplementedSigilValue,
WhileExpression { .. } => Expr::UnimplementedSigilValue,
ForExpression { .. } => Expr::UnimplementedSigilValue,
ListLiteral { .. } => Expr::UnimplementedSigilValue,
}
}
}
fn reduce_lambda(params: &Vec<FormalParam>, body: &Block, symbol_table: &SymbolTable) -> Expr {
Expr::Func(Func::UserDefined {
name: None,
params: params.iter().map(|param| param.0.clone()).collect(),
body: reduce_block(body, symbol_table),
})
}
fn reduce_if_expression(discriminator: &Discriminator, body: &IfExpressionBody, symbol_table: &SymbolTable) -> Expr {
let cond = Box::new(match *discriminator {
Discriminator::Simple(ref expr) => expr.reduce(symbol_table),
Discriminator::BinOp(ref _expr, ref _binop) => panic!("Can't yet handle binop discriminators")
});
match *body {
IfExpressionBody::SimpleConditional(ref then_clause, ref else_clause) => {
let then_clause = reduce_block(then_clause, symbol_table);
let else_clause = match else_clause {
None => vec![],
Some(stmts) => reduce_block(stmts, symbol_table),
};
Expr::Conditional { cond, then_clause, else_clause }
},
IfExpressionBody::SimplePatternMatch(ref pat, ref then_clause, ref else_clause) => {
let then_clause = reduce_block(then_clause, symbol_table);
let else_clause = match else_clause {
None => vec![],
Some(stmts) => reduce_block(stmts, symbol_table),
};
let alternatives = vec![
pat.to_alternative(then_clause, symbol_table),
Alternative {
tag: None,
subpatterns: vec![],
bound_vars: vec![],
guard: None,
item: else_clause
},
];
Expr::CaseMatch {
cond,
alternatives,
}
},
IfExpressionBody::GuardList(ref guard_arms) => {
let mut alternatives = vec![];
for arm in guard_arms {
match arm.guard {
Guard::Pat(ref p) => {
let item = reduce_block(&arm.body, symbol_table);
let alt = p.to_alternative(item, symbol_table);
alternatives.push(alt);
},
Guard::HalfExpr(HalfExpr { op: _, expr: _ }) => {
return Expr::UnimplementedSigilValue
}
}
}
Expr::CaseMatch { cond, alternatives }
}
}
}
/* ig var pat
* x is SomeBigOldEnum(_, x, Some(t))
*/
fn handle_symbol(symbol: Option<&Symbol>, inner_patterns: &Vec<Pattern>, symbol_table: &SymbolTable) -> Subpattern {
use self::Pattern::*;
let tag = symbol.map(|symbol| match symbol.spec {
SymbolSpec::DataConstructor { index, .. } => index.clone(),
_ => panic!("Symbol is not a data constructor - this should've been caught in type-checking"),
});
let bound_vars = inner_patterns.iter().map(|p| match p {
Literal(PatternLiteral::VarPattern(var)) => Some(var.clone()),
_ => None,
}).collect();
let subpatterns = inner_patterns.iter().map(|p| match p {
Ignored => None,
Literal(PatternLiteral::VarPattern(_)) => None,
Literal(other) => Some(other.to_subpattern(symbol_table)),
tp @ TuplePattern(_) => Some(tp.to_subpattern(symbol_table)),
ts @ TupleStruct(_, _) => Some(ts.to_subpattern(symbol_table)),
Record(..) => unimplemented!(),
}).collect();
let guard = None;
/*
let guard_equality_exprs: Vec<Expr> = subpatterns.iter().map(|p| match p {
Literal(lit) => match lit {
_ => unimplemented!()
},
_ => unimplemented!()
}).collect();
*/
Subpattern {
tag,
subpatterns,
guard,
bound_vars,
}
}
impl Pattern {
fn to_alternative(&self, item: Vec<Stmt>, symbol_table: &SymbolTable) -> Alternative {
let s = self.to_subpattern(symbol_table);
Alternative {
tag: s.tag,
subpatterns: s.subpatterns,
bound_vars: s.bound_vars,
guard: s.guard,
item
}
}
fn to_subpattern(&self, symbol_table: &SymbolTable) -> Subpattern {
use self::Pattern::*;
match self {
TupleStruct(name, inner_patterns) => {
let symbol = symbol_table.lookup_by_name(name).expect(&format!("Symbol {} not found", name));
handle_symbol(Some(symbol), inner_patterns, symbol_table)
},
TuplePattern(inner_patterns) => handle_symbol(None, inner_patterns, symbol_table),
Record(_name, _pairs) => {
unimplemented!()
},
Ignored => Subpattern { tag: None, subpatterns: vec![], guard: None, bound_vars: vec![] },
Literal(lit) => lit.to_subpattern(symbol_table),
}
}
}
impl PatternLiteral {
fn to_subpattern(&self, symbol_table: &SymbolTable) -> Subpattern {
use self::PatternLiteral::*;
match self {
NumPattern { neg, num } => {
let comparison = Expr::Lit(match (neg, num) {
(false, ExpressionKind::NatLiteral(n)) => Lit::Nat(*n),
(false, ExpressionKind::FloatLiteral(f)) => Lit::Float(*f),
(true, ExpressionKind::NatLiteral(n)) => Lit::Int(-1*(*n as i64)),
(true, ExpressionKind::FloatLiteral(f)) => Lit::Float(-1.0*f),
_ => panic!("This should never happen")
});
let guard = Some(Expr::Call {
f: Box::new(Expr::Func(Func::BuiltIn(Rc::new("==".to_string())))),
args: vec![comparison, Expr::ConditionalTargetSigilValue],
});
Subpattern {
tag: None,
subpatterns: vec![],
guard,
bound_vars: vec![],
}
},
StringPattern(s) => {
let guard = Some(Expr::Call {
f: Box::new(Expr::Func(Func::BuiltIn(Rc::new("==".to_string())))),
args: vec![Expr::Lit(Lit::StringLit(s.clone())), Expr::ConditionalTargetSigilValue]
});
Subpattern {
tag: None,
subpatterns: vec![],
guard,
bound_vars: vec![],
}
},
BoolPattern(b) => {
let guard = Some(if *b {
Expr::ConditionalTargetSigilValue
} else {
Expr::Call {
f: Box::new(Expr::Func(Func::BuiltIn(Rc::new("!".to_string())))),
args: vec![Expr::ConditionalTargetSigilValue]
}
});
Subpattern {
tag: None,
subpatterns: vec![],
guard,
bound_vars: vec![],
}
},
VarPattern(var) => match symbol_table.lookup_by_name(var) {
Some(symbol) => handle_symbol(Some(symbol), &vec![], symbol_table),
None => Subpattern {
tag: None,
subpatterns: vec![],
guard: None,
bound_vars: vec![Some(var.clone())],
}
}
}
}
}
impl Declaration {
fn reduce(&self, symbol_table: &SymbolTable) -> Stmt {
use self::Declaration::*;
match self {
Binding {name, constant, expr, .. } => Stmt::Binding { name: name.clone(), constant: *constant, expr: expr.node().reduce(symbol_table) },
FuncDecl(Signature { name, params, .. }, statements) => Stmt::PreBinding {
name: name.clone(),
func: Func::UserDefined {
name: Some(name.clone()),
params: params.iter().map(|param| param.0.clone()).collect(),
body: reduce_block(&statements, symbol_table),
}
},
TypeDecl { .. } => Stmt::Noop,
TypeAlias(_, _) => Stmt::Noop,
Interface { .. } => Stmt::Noop,
Impl { .. } => Stmt::Expr(Expr::UnimplementedSigilValue),
_ => Stmt::Expr(Expr::UnimplementedSigilValue)
}
}
}
impl BinOp {
fn reduce(&self, symbol_table: &SymbolTable, lhs: &Box<Meta<Expression>>, rhs: &Box<Meta<Expression>>) -> Expr {
if **self.sigil() == "=" {
Expr::Assign {
val: Box::new(lhs.node().reduce(symbol_table)),
expr: Box::new(rhs.node().reduce(symbol_table)),
}
} else {
let f = Box::new(Expr::Func(Func::BuiltIn(self.sigil().clone())));
Expr::Call { f, args: vec![lhs.node().reduce(symbol_table), rhs.node().reduce(symbol_table)]}
}
}
}
impl PrefixOp {
fn reduce(&self, symbol_table: &SymbolTable, arg: &Box<Meta<Expression>>) -> Expr {
let f = Box::new(Expr::Func(Func::BuiltIn(self.sigil().clone())));
Expr::Call { f, args: vec![arg.node().reduce(symbol_table)]}
}
}

View File

@@ -1,391 +0,0 @@
use std::collections::HashMap;
use std::collections::hash_map::Entry;
use std::rc::Rc;
use std::fmt;
use std::fmt::Write;
use crate::ast;
use crate::ast::{Meta, TypeBody, TypeSingletonName, Signature, Statement};
use crate::typechecking::TypeName;
type LineNumber = u32;
type SymbolTrackTable = HashMap<Rc<String>, LineNumber>;
#[derive(PartialEq, Eq, Hash, Debug)]
struct PathToSymbol(Vec<Rc<String>>);
#[derive(Debug, Clone)]
struct ScopeSegment {
scope_name: Rc<String>,
scope_type: ScopeSegmentKind,
}
#[derive(Debug, Clone)]
enum ScopeSegmentKind {
Function,
//Type,
}
//cf. p. 150 or so of Language Implementation Patterns
pub struct SymbolTable {
values: HashMap<PathToSymbol, Symbol>,
}
//TODO add various types of lookups here, maybe multiple hash tables internally?
impl SymbolTable {
pub fn new() -> SymbolTable {
SymbolTable {
values: HashMap::new(),
}
}
fn add_new_symbol(&mut self, name: &Rc<String>, scope_path: &Vec<ScopeSegment>, spec: SymbolSpec) {
let mut vec: Vec<Rc<String>> = scope_path.iter().map(|segment| segment.scope_name.clone()).collect();
vec.push(name.clone());
let symbol_path = PathToSymbol(vec);
let symbol = Symbol { name: name.clone(), scopes: scope_path.to_vec(), spec };
self.values.insert(symbol_path, symbol);
}
pub fn lookup_by_name(&self, name: &Rc<String>) -> Option<&Symbol> {
self.lookup_by_path(name, &vec![])
}
pub fn lookup_by_path(&self, name: &Rc<String>, path: &Vec<Rc<String>>) -> Option<&Symbol> {
let mut vec = path.clone();
vec.push(name.clone());
let symbol_path = PathToSymbol(vec);
self.values.get(&symbol_path)
}
}
#[derive(Debug)]
pub struct Symbol {
pub name: Rc<String>, //TODO does this need to be pub?
scopes: Vec<ScopeSegment>,
pub spec: SymbolSpec,
}
impl fmt::Display for Symbol {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "<Name: {}, Spec: {}>", self.name, self.spec)
}
}
#[derive(Debug)]
pub enum SymbolSpec {
Func(Vec<TypeName>),
DataConstructor {
index: usize,
type_name: Rc<String>,
type_args: Vec<Rc<String>>,
},
RecordConstructor {
fields: HashMap<Rc<String>, Rc<String>>
},
Binding
}
impl fmt::Display for SymbolSpec {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use self::SymbolSpec::*;
match self {
Func(type_names) => write!(f, "Func({:?})", type_names),
DataConstructor { index, type_name, type_args } => write!(f, "DataConstructor(idx: {})({:?} -> {})", index, type_args, type_name),
RecordConstructor { fields: _fields } => write!(f, "RecordConstructor( <fields> )"),
Binding => write!(f, "Binding"),
}
}
}
impl SymbolTable {
/* note: this adds names for *forward reference* but doesn't actually create any types. solve that problem
* later */
pub fn add_top_level_symbols(&mut self, ast: &ast::AST) -> Result<(), String> {
let mut scope_name_stack = Vec::new();
self.add_symbols_from_scope(&ast.0, &mut scope_name_stack)
}
fn add_symbols_from_scope<'a>(&'a mut self, statements: &Vec<Meta<Statement>>, scope_name_stack: &mut Vec<ScopeSegment>) -> Result<(), String> {
use self::ast::Declaration::*;
fn insert_and_check_duplicate_symbol(table: &mut SymbolTrackTable, name: &Rc<String>) -> Result<(), String> {
match table.entry(name.clone()) {
Entry::Occupied(o) => {
let line_number = o.get(); //TODO make this actually work
Err(format!("Duplicate definition: {}. It's already defined at {}", name, line_number))
},
Entry::Vacant(v) => {
let line_number = 0; //TODO should work
v.insert(line_number);
Ok(())
}
}
}
let mut seen_identifiers: SymbolTrackTable = HashMap::new();
for meta in statements.iter() {
let statement = meta.node();
if let Statement::Declaration(decl) = statement {
match decl {
FuncSig(ref signature) => {
insert_and_check_duplicate_symbol(&mut seen_identifiers, &signature.name)?;
self.add_function_signature(signature, scope_name_stack)?
}
FuncDecl(ref signature, ref body) => {
insert_and_check_duplicate_symbol(&mut seen_identifiers, &signature.name)?;
self.add_function_signature(signature, scope_name_stack)?;
scope_name_stack.push(ScopeSegment{
scope_name: signature.name.clone(),
scope_type: ScopeSegmentKind::Function,
});
let output = self.add_symbols_from_scope(body, scope_name_stack);
let _ = scope_name_stack.pop();
output?
},
TypeDecl { name, body, mutable } => {
insert_and_check_duplicate_symbol(&mut seen_identifiers, &name.name)?;
self.add_type_decl(name, body, mutable, scope_name_stack)?
},
Binding { name, .. } => {
insert_and_check_duplicate_symbol(&mut seen_identifiers, name)?;
self.add_new_symbol(name, scope_name_stack, SymbolSpec::Binding);
}
_ => ()
}
}
}
Ok(())
}
pub fn debug_symbol_table(&self) -> String {
let mut output = format!("Symbol table\n");
for (name, sym) in &self.values {
write!(output, "{:?} -> {}\n", name, sym).unwrap();
}
output
}
fn add_function_signature(&mut self, signature: &Signature, scope_name_stack: &mut Vec<ScopeSegment>) -> Result<(), String> {
let mut local_type_context = LocalTypeContext::new();
let types = signature.params.iter().map(|param| match param {
(_, Some(type_identifier)) => Rc::new(format!("{:?}", type_identifier)),
(_, None) => local_type_context.new_universal_type()
}).collect();
self.add_new_symbol(&signature.name, scope_name_stack, SymbolSpec::Func(types));
Ok(())
}
fn add_type_decl(&mut self, type_name: &TypeSingletonName, body: &TypeBody, _mutable: &bool, scope_name_stack: &mut Vec<ScopeSegment>) -> Result<(), String> {
use crate::ast::{TypeIdentifier, Variant};
let TypeBody(variants) = body;
let TypeSingletonName { name, .. } = type_name;
//scope_name_stack.push(name.clone()); //TODO adding this makes variants scoped under their
//type name and breaks a lot of things - don't add it until importing names works
//TODO figure out why _params isn't being used here
for (index, var) in variants.iter().enumerate() {
match var {
Variant::UnitStruct(variant_name) => {
let spec = SymbolSpec::DataConstructor {
index,
type_name: name.clone(),
type_args: vec![],
};
self.add_new_symbol(variant_name, scope_name_stack, spec);
},
Variant::TupleStruct(variant_name, tuple_members) => {
let type_args = tuple_members.iter().map(|type_name| match type_name {
TypeIdentifier::Singleton(TypeSingletonName { name, ..}) => name.clone(),
TypeIdentifier::Tuple(_) => unimplemented!(),
}).collect();
let spec = SymbolSpec::DataConstructor {
index,
type_name: name.clone(),
type_args
};
self.add_new_symbol(variant_name, scope_name_stack, spec);
},
//TODO if there is only one variant, and it is a record, it doesn't need to have an
//explicit name
Variant::Record { name, members: _members } => {
let fields = HashMap::new();
let spec = SymbolSpec::RecordConstructor { fields };
self.add_new_symbol(name, scope_name_stack, spec);
},
}
}
//scope_name_stack.pop();
Ok(())
}
}
struct LocalTypeContext {
state: u8
}
impl LocalTypeContext {
fn new() -> LocalTypeContext {
LocalTypeContext { state: 0 }
}
fn new_universal_type(&mut self) -> TypeName {
let n = self.state;
self.state += 1;
Rc::new(format!("{}", (('a' as u8) + n) as char))
}
}
#[cfg(test)]
mod symbol_table_tests {
use super::*;
use crate::util::quick_ast;
macro_rules! values_in_table {
//TODO multiple values
($source:expr, $single_value:expr) => {
{
let mut symbol_table = SymbolTable::new();
let ast = quick_ast($source);
symbol_table.add_top_level_symbols(&ast).unwrap();
match symbol_table.lookup_by_name($single_value) {
Some(_spec) => (),
None => panic!(),
};
}
}
}
#[test]
fn basic_symbol_table() {
values_in_table! { "let a = 10; fn b() { 20 }", &rc!(b) };
}
#[test]
fn no_duplicates() {
let source = r#"
fn a() { 1 }
fn b() { 2 }
fn a() { 3 }
"#;
let mut symbol_table = SymbolTable::new();
let ast = quick_ast(source);
let output = symbol_table.add_top_level_symbols(&ast).unwrap_err();
assert!(output.contains("Duplicate"))
}
#[test]
fn no_duplicates_2() {
let source = r#"
let a = 20;
let q = 39;
let a = 30;
"#;
let mut symbol_table = SymbolTable::new();
let ast = quick_ast(source);
let output = symbol_table.add_top_level_symbols(&ast).unwrap_err();
assert!(output.contains("Duplicate"))
}
#[test]
fn no_duplicates_3() {
let source = r#"
fn a() {
let a = 20
let b = 40
a + b
}
fn q() {
let x = 30
let x = 33
}
"#;
let mut symbol_table = SymbolTable::new();
let ast = quick_ast(source);
let output = symbol_table.add_top_level_symbols(&ast).unwrap_err();
assert!(output.contains("Duplicate"))
}
#[test]
fn dont_falsely_detect_duplicates() {
let source = r#"
let a = 20;
fn some_func() {
let a = 40;
77
}
let q = 39;
"#;
let mut symbol_table = SymbolTable::new();
let ast = quick_ast(source);
symbol_table.add_top_level_symbols(&ast).unwrap();
assert!(symbol_table.lookup_by_path(&rc!(a), &vec![]).is_some());
assert!(symbol_table.lookup_by_path(&rc!(a), &vec![rc!(some_func)]).is_some());
}
#[test]
fn enclosing_scopes() {
let source = r#"
fn outer_func(x) {
fn inner_func(arg) {
arg
}
x + inner_func(x)
}"#;
let mut symbol_table = SymbolTable::new();
let ast = quick_ast(source);
symbol_table.add_top_level_symbols(&ast).unwrap();
assert!(symbol_table.lookup_by_path(&rc!(outer_func), &vec![]).is_some());
assert!(symbol_table.lookup_by_path(&rc!(inner_func), &vec![rc!(outer_func)]).is_some());
}
#[test]
fn enclosing_scopes_2() {
let source = r#"
fn outer_func(x) {
fn inner_func(arg) {
arg
}
fn second_inner_func() {
fn another_inner_func() {
}
}
inner_func(x)
}"#;
let mut symbol_table = SymbolTable::new();
let ast = quick_ast(source);
symbol_table.add_top_level_symbols(&ast).unwrap();
println!("{}", symbol_table.debug_symbol_table());
assert!(symbol_table.lookup_by_path(&rc!(outer_func), &vec![]).is_some());
assert!(symbol_table.lookup_by_path(&rc!(inner_func), &vec![rc!(outer_func)]).is_some());
assert!(symbol_table.lookup_by_path(&rc!(second_inner_func), &vec![rc!(outer_func)]).is_some());
assert!(symbol_table.lookup_by_path(&rc!(another_inner_func), &vec![rc!(outer_func), rc!(second_inner_func)]).is_some());
}
#[test]
fn enclosing_scopes_3() {
let source = r#"
fn outer_func(x) {
fn inner_func(arg) {
arg
}
fn second_inner_func() {
fn another_inner_func() {
}
fn another_inner_func() {
}
}
inner_func(x)
}"#;
let mut symbol_table = SymbolTable::new();
let ast = quick_ast(source);
let output = symbol_table.add_top_level_symbols(&ast).unwrap_err();
assert!(output.contains("Duplicate"))
}
}

View File

@@ -1,472 +0,0 @@
use std::rc::Rc;
use std::fmt::Write;
use ena::unify::{UnifyKey, InPlaceUnificationTable, UnificationTable, EqUnifyValue};
use crate::ast::*;
use crate::util::ScopeStack;
use crate::builtin::{PrefixOp, BinOp};
#[derive(Debug, Clone, PartialEq)]
pub struct TypeData {
ty: Option<Type>
}
impl TypeData {
pub fn new() -> TypeData {
TypeData { ty: None }
}
}
pub type TypeName = Rc<String>;
pub struct TypeContext<'a> {
variable_map: ScopeStack<'a, Rc<String>, Type>,
unification_table: InPlaceUnificationTable<TypeVar>,
}
/// `InferResult` is the monad in which type inference takes place.
type InferResult<T> = Result<T, TypeError>;
#[derive(Debug, Clone)]
pub struct TypeError { pub msg: String }
impl TypeError {
fn new<A, T>(msg: T) -> InferResult<A> where T: Into<String> {
Err(TypeError { msg: msg.into() })
}
}
#[derive(Debug, Clone, PartialEq)]
pub enum Type {
Const(TypeConst),
Var(TypeVar),
Arrow {
params: Vec<Type>,
ret: Box<Type>
},
Compound {
ty_name: String,
args:Vec<Type>
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub struct TypeVar(usize);
impl UnifyKey for TypeVar {
type Value = Option<TypeConst>;
fn index(&self) -> u32 { self.0 as u32 }
fn from_index(u: u32) -> TypeVar { TypeVar(u as usize) }
fn tag() -> &'static str { "TypeVar" }
}
#[derive(Debug, Clone, PartialEq, Eq)]
pub enum TypeConst {
Unit,
Nat,
Int,
Float,
StringT,
Bool,
Ordering,
//UserDefined
}
impl TypeConst {
pub fn to_string(&self) -> String {
use self::TypeConst::*;
match self {
Unit => format!("()"),
Nat => format!("Nat"),
Int => format!("Int"),
Float => format!("Float"),
StringT => format!("String"),
Bool => format!("Bool"),
Ordering => format!("Ordering"),
}
}
}
impl EqUnifyValue for TypeConst { }
macro_rules! ty {
($type_name:ident) => { Type::Const(TypeConst::$type_name) };
($t1:ident -> $t2:ident) => { Type::Arrow { params: vec![ty!($t1)], ret: box ty!($t2) } };
($t1:ident -> $t2:ident -> $t3:ident) => { Type::Arrow { params: vec![ty!($t1), ty!($t2)], ret: box ty!($t3) } };
($type_list:ident, $ret_type:ident) => {
Type::Arrow {
params: $type_list,
ret: box $ret_type,
}
}
}
//TODO find a better way to capture the to/from string logic
impl Type {
pub fn to_string(&self) -> String {
use self::Type::*;
match self {
Const(c) => c.to_string(),
Var(v) => format!("t_{}", v.0),
Arrow { params, box ref ret } => {
if params.len() == 0 {
format!("-> {}", ret.to_string())
} else {
let mut buf = String::new();
for p in params.iter() {
write!(buf, "{} -> ", p.to_string()).unwrap();
}
write!(buf, "{}", ret.to_string()).unwrap();
buf
}
},
Compound { .. } => format!("<some compound type>")
}
}
fn from_string(string: &str) -> Option<Type> {
Some(match string {
"()" | "Unit" => ty!(Unit),
"Nat" => ty!(Nat),
"Int" => ty!(Int),
"Float" => ty!(Float),
"String" => ty!(StringT),
"Bool" => ty!(Bool),
"Ordering" => ty!(Ordering),
_ => return None
})
}
}
/*
/// `Type` is parameterized by whether the type variables can be just universal, or universal or
/// existential.
#[derive(Debug, Clone)]
enum Type<A> {
Var(A),
Const(TConst),
Arrow(Box<Type<A>>, Box<Type<A>>),
}
#[derive(Debug, Clone)]
enum TVar {
Univ(UVar),
Exist(ExistentialVar)
}
#[derive(Debug, Clone)]
struct UVar(Rc<String>);
#[derive(Debug, Clone)]
struct ExistentialVar(u32);
impl Type<UVar> {
fn to_tvar(&self) -> Type<TVar> {
match self {
Type::Var(UVar(name)) => Type::Var(TVar::Univ(UVar(name.clone()))),
Type::Const(ref c) => Type::Const(c.clone()),
Type::Arrow(a, b) => Type::Arrow(
Box::new(a.to_tvar()),
Box::new(b.to_tvar())
)
}
}
}
impl Type<TVar> {
fn skolemize(&self) -> Type<UVar> {
match self {
Type::Var(TVar::Univ(uvar)) => Type::Var(uvar.clone()),
Type::Var(TVar::Exist(_)) => Type::Var(UVar(Rc::new(format!("sk")))),
Type::Const(ref c) => Type::Const(c.clone()),
Type::Arrow(a, b) => Type::Arrow(
Box::new(a.skolemize()),
Box::new(b.skolemize())
)
}
}
}
impl TypeIdentifier {
fn to_monotype(&self) -> Type<UVar> {
match self {
TypeIdentifier::Tuple(_) => Type::Const(TConst::Nat),
TypeIdentifier::Singleton(TypeSingletonName { name, .. }) => {
match &name[..] {
"Nat" => Type::Const(TConst::Nat),
"Int" => Type::Const(TConst::Int),
"Float" => Type::Const(TConst::Float),
"Bool" => Type::Const(TConst::Bool),
"String" => Type::Const(TConst::StringT),
_ => Type::Const(TConst::Nat),
}
}
}
}
}
#[derive(Debug, Clone)]
enum TConst {
User(Rc<String>),
Unit,
Nat,
Int,
Float,
StringT,
Bool,
}
impl TConst {
fn user(name: &str) -> TConst {
TConst::User(Rc::new(name.to_string()))
}
}
*/
impl<'a> TypeContext<'a> {
pub fn new() -> TypeContext<'a> {
TypeContext {
variable_map: ScopeStack::new(None),
unification_table: UnificationTable::new(),
}
}
/*
fn new_env(&'a self, new_var: Rc<String>, ty: Type) -> TypeContext<'a> {
let mut new_context = TypeContext {
variable_map: self.variable_map.new_scope(None),
unification_table: UnificationTable::new(), //???? not sure if i want this
};
new_context.variable_map.insert(new_var, ty);
new_context
}
*/
fn get_type_from_name(&self, name: &TypeIdentifier) -> InferResult<Type> {
use self::TypeIdentifier::*;
Ok(match name {
Singleton(TypeSingletonName { name,.. }) => {
match Type::from_string(&name) {
Some(ty) => ty,
None => return TypeError::new(format!("Unknown type name: {}", name))
}
},
Tuple(_) => return TypeError::new("tuples aren't ready yet"),
})
}
/// `typecheck` is the entry into the type-inference system, accepting an AST as an argument
/// Following the example of GHC, the compiler deliberately does typechecking before de-sugaring
/// the AST to ReducedAST
pub fn typecheck(&mut self, ast: &AST) -> Result<Type, TypeError> {
let mut returned_type = Type::Const(TypeConst::Unit);
for statement in ast.0.iter() {
returned_type = self.statement(statement.node())?;
}
Ok(returned_type)
}
fn statement(&mut self, statement: &Statement) -> InferResult<Type> {
match statement {
Statement::ExpressionStatement(e) => self.expr(e.node()),
Statement::Declaration(decl) => self.decl(decl),
}
}
fn decl(&mut self, decl: &Declaration) -> InferResult<Type> {
use self::Declaration::*;
match decl {
Binding { name, expr, .. } => {
let ty = self.expr(expr.node())?;
self.variable_map.insert(name.clone(), ty);
},
_ => (),
}
Ok(ty!(Unit))
}
fn expr(&mut self, expr: &Expression) -> InferResult<Type> {
match expr {
Expression(expr_type, Some(anno)) => {
let t1 = self.expr_type(expr_type)?;
let t2 = self.get_type_from_name(anno)?;
self.unify(t2, t1)
},
Expression(expr_type, None) => self.expr_type(expr_type)
}
}
fn expr_type(&mut self, expr: &ExpressionKind) -> InferResult<Type> {
use self::ExpressionKind::*;
Ok(match expr {
NatLiteral(_) => ty!(Nat),
BoolLiteral(_) => ty!(Bool),
FloatLiteral(_) => ty!(Float),
StringLiteral(_) => ty!(StringT),
PrefixExp(op, expr) => self.prefix(op, expr.node())?,
BinExp(op, lhs, rhs) => self.binexp(op, lhs.node(), rhs.node())?,
IfExpression { discriminator, body } => self.if_expr(discriminator, body)?,
Value(val) => self.handle_value(val)?,
Call { box ref f, arguments } => self.call(f.node(), arguments)?,
Lambda { params, type_anno, body } => self.lambda(params, type_anno, body)?,
_ => ty!(Unit),
})
}
fn prefix(&mut self, op: &PrefixOp, expr: &Expression) -> InferResult<Type> {
let tf = match op.get_type() {
Ok(ty) => ty,
Err(e) => return TypeError::new(e)
};
let tx = self.expr(expr)?;
self.handle_apply(tf, vec![tx])
}
fn binexp(&mut self, op: &BinOp, lhs: &Expression, rhs: &Expression) -> InferResult<Type> {
let tf = match op.get_type() {
Ok(ty) => ty,
Err(e) => return TypeError::new(e),
};
let t_lhs = self.expr(lhs)?;
let t_rhs = self.expr(rhs)?; //TODO is this order a problem? not sure
self.handle_apply(tf, vec![t_lhs, t_rhs])
}
fn if_expr(&mut self, discriminator: &Discriminator, body: &IfExpressionBody) -> InferResult<Type> {
use self::Discriminator::*; use self::IfExpressionBody::*;
match (discriminator, body) {
(Simple(expr), SimpleConditional(then_clause, else_clause)) => self.handle_simple_if(expr, then_clause, else_clause),
_ => TypeError::new(format!("Complex conditionals not supported"))
}
}
fn handle_simple_if(&mut self, expr: &Expression, then_clause: &Block, else_clause: &Option<Block>) -> InferResult<Type> {
let t1 = self.expr(expr)?;
let t2 = self.block(then_clause)?;
let t3 = match else_clause {
Some(block) => self.block(block)?,
None => ty!(Unit)
};
let _ = self.unify(ty!(Bool), t1)?;
self.unify(t2, t3)
}
fn lambda(&mut self, params: &Vec<FormalParam>, type_anno: &Option<TypeIdentifier>, _body: &Block) -> InferResult<Type> {
let argument_types: InferResult<Vec<Type>> = params.iter().map(|param: &FormalParam| {
if let (_, Some(type_identifier)) = param {
self.get_type_from_name(type_identifier)
} else {
Ok(Type::Var(self.fresh_type_variable()))
}
}).collect();
let argument_types = argument_types?;
let ret_type = match type_anno.as_ref() {
Some(anno) => self.get_type_from_name(anno)?,
None => Type::Var(self.fresh_type_variable())
};
Ok(ty!(argument_types, ret_type))
}
fn call(&mut self, f: &Expression, args: &Vec<Meta<Expression>>) -> InferResult<Type> {
let tf = self.expr(f)?;
let arg_types: InferResult<Vec<Type>> = args.iter().map(|ex| self.expr(ex.node())).collect();
let arg_types = arg_types?;
self.handle_apply(tf, arg_types)
}
fn handle_apply(&mut self, tf: Type, args: Vec<Type>) -> InferResult<Type> {
Ok(match tf {
Type::Arrow { ref params, ret: box ref t_ret } if params.len() == args.len() => {
for (t_param, t_arg) in params.iter().zip(args.iter()) {
let _ = self.unify(t_param.clone(), t_arg.clone())?; //TODO I think this needs to reference a sub-scope
}
t_ret.clone()
},
Type::Arrow { .. } => return TypeError::new("Wrong length"),
_ => return TypeError::new(format!("Not a function"))
})
}
fn block(&mut self, block: &Block) -> InferResult<Type> {
let mut output = ty!(Unit);
for s in block.iter() {
let statement = s.node();
output = self.statement(statement)?;
}
Ok(output)
}
fn handle_value(&mut self, val: &Rc<String>) -> InferResult<Type> {
match self.variable_map.lookup(val) {
Some(ty) => Ok(ty.clone()),
None => TypeError::new(format!("Couldn't find variable: {}", val))
}
}
fn unify(&mut self, t1: Type, t2: Type) -> InferResult<Type> {
use self::Type::*;
match (t1, t2) {
(Const(ref c1), Const(ref c2)) if c1 == c2 => Ok(Const(c1.clone())), //choice of c1 is arbitrary I *think*
(a @ Var(_), b @ Const(_)) => self.unify(b, a),
(Const(ref c1), Var(ref v2)) => {
self.unification_table.unify_var_value(v2.clone(), Some(c1.clone()))
.or_else(|_| TypeError::new(format!("Couldn't unify {:?} and {:?}", Const(c1.clone()), Var(*v2))))?;
Ok(Const(c1.clone()))
},
(Var(v1), Var(v2)) => {
//TODO add occurs check
self.unification_table.unify_var_var(v1.clone(), v2.clone())
.or_else(|e| {
println!("Unify error: {:?}", e);
TypeError::new(format!("Two type variables {:?} and {:?} couldn't unify", v1, v2))
})?;
Ok(Var(v1.clone())) //arbitrary decision I think
},
(a, b) => TypeError::new(format!("{:?} and {:?} do not unify", a, b)),
}
}
fn fresh_type_variable(&mut self) -> TypeVar {
let new_type_var = self.unification_table.new_key(None);
new_type_var
}
}
#[cfg(test)]
mod typechecking_tests {
use super::*;
macro_rules! assert_type_in_fresh_context {
($string:expr, $type:expr) => {
let mut tc = TypeContext::new();
let ref ast = crate::util::quick_ast($string);
let ty = tc.typecheck(ast).unwrap();
assert_eq!(ty, $type)
}
}
#[test]
fn basic_test() {
assert_type_in_fresh_context!("1", ty!(Nat));
assert_type_in_fresh_context!(r#""drugs""#, ty!(StringT));
assert_type_in_fresh_context!("true", ty!(Bool));
assert_type_in_fresh_context!("-1", ty!(Int));
}
#[test]
fn operators() {
assert_type_in_fresh_context!("1 + 2", ty!(Nat));
assert_type_in_fresh_context!("-2", ty!(Int));
assert_type_in_fresh_context!("!true", ty!(Bool));
}
}

View File

@@ -1,55 +0,0 @@
use std::collections::HashMap;
use std::hash::Hash;
use std::cmp::Eq;
#[derive(Default, Debug)]
pub struct ScopeStack<'a, T: 'a, V: 'a> where T: Hash + Eq {
parent: Option<&'a ScopeStack<'a, T, V>>,
values: HashMap<T, V>,
scope_name: Option<String>
}
impl<'a, T, V> ScopeStack<'a, T, V> where T: Hash + Eq {
pub fn new(name: Option<String>) -> ScopeStack<'a, T, V> where T: Hash + Eq {
ScopeStack {
parent: None,
values: HashMap::new(),
scope_name: name
}
}
pub fn insert(&mut self, key: T, value: V) where T: Hash + Eq {
self.values.insert(key, value);
}
pub fn lookup(&self, key: &T) -> Option<&V> where T: Hash + Eq {
match (self.values.get(key), self.parent) {
(None, None) => None,
(None, Some(parent)) => parent.lookup(key),
(Some(value), _) => Some(value),
}
}
pub fn new_scope(&'a self, name: Option<String>) -> ScopeStack<'a, T, V> where T: Hash + Eq {
ScopeStack {
parent: Some(self),
values: HashMap::default(),
scope_name: name,
}
}
#[allow(dead_code)]
pub fn get_name(&self) -> Option<&String> {
self.scope_name.as_ref()
}
}
/// this is intended for use in tests, and does no error-handling whatsoever
#[allow(dead_code)]
pub fn quick_ast(input: &str) -> crate::ast::AST {
let tokens = crate::tokenizing::tokenize(input);
let mut parser = crate::parsing::Parser::new(tokens);
parser.parse().unwrap()
}
#[allow(unused_macros)]
macro_rules! rc {
($string:tt) => { Rc::new(stringify!($string).to_string()) }
}

View File

@@ -1,24 +1,25 @@
[package]
name = "schala-repl"
name = "schala-lib"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2018"
[dependencies]
llvm-sys = "70.0.2"
take_mut = "0.2.2"
llvm-sys = "*"
take_mut = "0.1.3"
itertools = "0.5.8"
getopts = "0.2.18"
getopts = "*"
lazy_static = "0.2.8"
maplit = "*"
colored = "1.7"
serde = "1.0.91"
serde_derive = "1.0.91"
serde_json = "1.0.15"
colored = "1.5"
serde = "1.0.15"
serde_derive = "1.0.15"
serde_json = "1.0.3"
rocket = "0.3.5"
rocket_codegen = "0.3.5"
rocket_contrib = "0.3.5"
phf = "0.7.12"
includedir = "0.2.0"
linefeed = "0.5.0"
regex = "0.2"
rustyline = "1.0.0"
[build-dependencies]
includedir_codegen = "0.2.0"

106
schala-lib/src/language.rs Normal file
View File

@@ -0,0 +1,106 @@
extern crate colored;
use self::colored::*;
pub struct LLVMCodeString(pub String);
#[derive(Debug, Default, Serialize, Deserialize)]
pub struct EvalOptions {
pub debug_tokens: bool,
pub debug_parse: bool,
pub debug_type: bool,
pub debug_symbol_table: bool,
pub show_llvm_ir: bool,
pub trace_evaluation: bool,
pub compile: bool,
}
#[derive(Debug, Default)]
pub struct LanguageOutput {
output: String,
artifacts: Vec<TraceArtifact>,
failed: bool,
}
impl LanguageOutput {
pub fn add_artifact(&mut self, artifact: TraceArtifact) {
self.artifacts.push(artifact);
}
pub fn add_output(&mut self, output: String) {
self.output = output;
}
pub fn to_string(&self) -> String {
let mut acc = String::new();
for line in self.artifacts.iter() {
acc.push_str(&line.debug_output.color(line.text_color).to_string());
acc.push_str(&"\n");
}
acc.push_str(&self.output);
acc
}
pub fn print_to_screen(&self) {
for line in self.artifacts.iter() {
let color = line.text_color;
let stage = line.stage_name.color(color).to_string();
let output = line.debug_output.color(color).to_string();
println!("{}: {}", stage, output);
}
println!("{}", self.output);
}
}
/*
//TODO I'll probably wanna implement this later
#[derive(Debug)]
pub struct CompilationOutput {
output: LLVMCodeString,
artifacts: Vec<TraceArtifact>,
}
*/
#[derive(Debug)]
pub struct TraceArtifact {
stage_name: String,
debug_output: String,
text_color: &'static str,
}
impl TraceArtifact {
pub fn new(stage: &str, debug: String) -> TraceArtifact {
let color = match stage {
"parse_trace" | "ast" => "red",
"tokens" => "green",
"type_check" => "magenta",
_ => "blue",
};
TraceArtifact { stage_name: stage.to_string(), debug_output: debug, text_color: color}
}
pub fn new_parse_trace(trace: Vec<String>) -> TraceArtifact {
let mut output = String::new();
for t in trace {
output.push_str(&t);
output.push_str("\n");
}
TraceArtifact { stage_name: "parse_trace".to_string(), debug_output: output, text_color: "red"}
}
}
pub trait ProgrammingLanguageInterface {
fn evaluate_in_repl(&mut self, input: &str, eval_options: &EvalOptions) -> LanguageOutput;
fn evaluate_noninteractive(&mut self, input: &str, eval_options: &EvalOptions) -> LanguageOutput {
self.evaluate_in_repl(input, eval_options)
}
fn get_language_name(&self) -> String;
fn get_source_file_suffix(&self) -> String;
fn compile(&mut self, _input: &str) -> LLVMCodeString {
LLVMCodeString("".to_string())
}
fn can_compile(&self) -> bool {
false
}
}

378
schala-lib/src/lib.rs Normal file
View File

@@ -0,0 +1,378 @@
#![feature(link_args)]
#![feature(advanced_slice_patterns, slice_patterns, box_patterns, box_syntax)]
#![feature(plugin)]
#![plugin(rocket_codegen)]
extern crate getopts;
extern crate rustyline;
extern crate itertools;
#[macro_use]
extern crate lazy_static;
#[macro_use]
extern crate maplit;
#[macro_use]
extern crate serde_derive;
extern crate serde_json;
extern crate rocket;
extern crate rocket_contrib;
extern crate includedir;
extern crate phf;
use std::path::Path;
use std::fs::File;
use std::io::{Read, Write};
use std::process::exit;
use std::default::Default;
use rustyline::error::ReadlineError;
use rustyline::Editor;
mod language;
mod webapp;
pub mod llvm_wrap;
include!(concat!(env!("OUT_DIR"), "/static.rs"));
pub use language::{ProgrammingLanguageInterface, EvalOptions, TraceArtifact, LanguageOutput, LLVMCodeString};
pub type PLIGenerator = Box<Fn() -> Box<ProgrammingLanguageInterface> + Send + Sync>;
pub fn schala_main(generators: Vec<PLIGenerator>) {
let languages: Vec<Box<ProgrammingLanguageInterface>> = generators.iter().map(|x| x()).collect();
let option_matches = program_options().parse(std::env::args()).unwrap_or_else(|e| {
println!("{:?}", e);
exit(1);
});
if option_matches.opt_present("list-languages") {
for lang in languages {
println!("{}", lang.get_language_name());
}
exit(1);
}
if option_matches.opt_present("help") {
println!("{}", program_options().usage("Schala metainterpreter"));
exit(0);
}
if option_matches.opt_present("webapp") {
webapp::web_main(generators);
exit(0);
}
let language_names: Vec<String> = languages.iter().map(|lang| {lang.get_language_name()}).collect();
let initial_index: usize =
option_matches.opt_str("lang")
.and_then(|lang| { language_names.iter().position(|x| { x.to_lowercase() == lang.to_lowercase() }) })
.unwrap_or(0);
let mut options = EvalOptions::default();
options.compile = match option_matches.opt_str("eval-style") {
Some(ref s) if s == "compile" => true,
_ => false
};
match option_matches.free[..] {
[] | [_] => {
let mut repl = Repl::new(languages, initial_index);
repl.options.show_llvm_ir = true; //TODO make this be configurable
repl.run();
}
[_, ref filename, _..] => {
run_noninteractive(filename, languages, options);
}
};
}
fn run_noninteractive(filename: &str, languages: Vec<Box<ProgrammingLanguageInterface>>, options: EvalOptions) {
let path = Path::new(filename);
let ext = path.extension().and_then(|e| e.to_str()).unwrap_or_else(|| {
println!("Source file lacks extension");
exit(1);
});
let mut language = Box::new(languages.into_iter().find(|lang| lang.get_source_file_suffix() == ext)
.unwrap_or_else(|| {
println!("Extension .{} not recognized", ext);
exit(1);
}));
let mut source_file = File::open(path).unwrap();
let mut buffer = String::new();
source_file.read_to_string(&mut buffer).unwrap();
if options.compile {
if !language.can_compile() {
panic!("Trying to compile a non-compileable language");
} else {
let llvm_bytecode = language.compile(&buffer);
compilation_sequence(llvm_bytecode, filename);
}
} else {
let output = language.evaluate_in_repl(&buffer, &options);
// if output.has_error....
}
}
struct Repl {
options: EvalOptions,
languages: Vec<Box<ProgrammingLanguageInterface>>,
current_language_index: usize,
interpreter_directive_sigil: char,
console: rustyline::Editor<()>,
}
impl Repl {
fn new(languages: Vec<Box<ProgrammingLanguageInterface>>, initial_index: usize) -> Repl {
let i = if initial_index < languages.len() { initial_index } else { 0 };
let console = Editor::<()>::new();
Repl {
options: Repl::get_options(),
languages: languages,
current_language_index: i,
interpreter_directive_sigil: '.',
console
}
}
fn get_options() -> EvalOptions {
File::open(".schala_repl")
.and_then(|mut file| {
let mut contents = String::new();
file.read_to_string(&mut contents)?;
Ok(contents)
})
.and_then(|contents| {
let options: EvalOptions = serde_json::from_str(&contents)?;
Ok(options)
}).unwrap_or(EvalOptions::default())
}
fn save_options(&self) {
let ref options = self.options;
let read = File::create(".schala_repl")
.and_then(|mut file| {
let buf = serde_json::to_string(options).unwrap();
file.write_all(buf.as_bytes())
});
if let Err(err) = read {
println!("Error saving .schala_repl file {}", err);
}
}
fn run(&mut self) {
println!("MetaInterpreter v 0.05");
self.console.get_history().load(".schala_history").unwrap_or(());
loop {
let language_name = self.languages[self.current_language_index].get_language_name();
let prompt_str = format!("{} >> ", language_name);
match self.console.readline(&prompt_str) {
Err(ReadlineError::Eof) | Err(ReadlineError::Interrupted) => break,
Err(e) => {
println!("Terminal read error: {}", e);
},
Ok(ref input) => {
self.console.add_history_entry(input);
if self.handle_interpreter_directive(input) {
continue;
}
let output = self.input_handler(input);
println!("=> {}", output);
}
_ => (),
}
}
self.console.get_history().save(".schala_history").unwrap_or(());
self.save_options();
println!("Exiting...");
}
fn input_handler(&mut self, input: &str) -> String {
let ref mut language = self.languages[self.current_language_index];
let interpreter_output = language.evaluate_in_repl(input, &self.options);
interpreter_output.to_string()
}
fn handle_interpreter_directive(&mut self, input: &str) -> bool {
match input.chars().nth(0) {
Some(ch) if ch == self.interpreter_directive_sigil => (),
_ => return false
}
let mut iter = input.chars();
iter.next();
let trimmed_sigil: &str = iter.as_str();
let commands: Vec<&str> = trimmed_sigil
.split_whitespace()
.collect();
let cmd: &str = match commands.get(0).clone() {
None => return true,
Some(s) => s
};
match cmd {
"exit" | "quit" => {
self.save_options();
exit(0)
},
"help" => {
println!("Commands:");
println!("exit | quit");
println!("lang(uage) [go|show|next|previous]");
println!("set [show|hide] [tokens|parse|symbols|eval|llvm]");
}
"lang" | "language" => {
match commands.get(1) {
Some(&"show") => {
for (i, lang) in self.languages.iter().enumerate() {
if i == self.current_language_index {
println!("* {}", lang.get_language_name());
} else {
println!("{}", lang.get_language_name());
}
}
},
Some(&"go") => {
match commands.get(2) {
None => println!("Must specify a language name"),
Some(&desired_name) => {
for (i, _) in self.languages.iter().enumerate() {
let lang_name = self.languages[i].get_language_name();
if lang_name.to_lowercase() == desired_name.to_lowercase() {
self.current_language_index = i;
println!("Switching to {}", self.languages[self.current_language_index].get_language_name());
return true;
}
}
println!("Language {} not found", desired_name);
}
}
},
Some(&"next") => {
self.current_language_index = (self.current_language_index + 1) % self.languages.len();
println!("Switching to {}", self.languages[self.current_language_index].get_language_name());
}
Some(&"prev") | Some(&"previous") => {
self.current_language_index = if self.current_language_index == 0 { self.languages.len() - 1 } else { self.current_language_index - 1 };
println!("Switching to {}", self.languages[self.current_language_index].get_language_name());
},
Some(e) => println!("Bad `lang` argument: {}", e),
None => println!("`lang` - valid arguments `show`, `next`, `prev`|`previous`"),
}
},
"set" => {
let show = match commands.get(1) {
Some(&"show") => true,
Some(&"hide") => false,
Some(e) => {
println!("Bad `set` argument: {}", e);
return true;
}
None => {
println!("`set` - valid arguments `show {{option}}`, `hide {{option}}`");
return true;
}
};
match commands.get(2) {
Some(&"tokens") => self.options.debug_tokens = show,
Some(&"parse") => self.options.debug_parse = show,
Some(&"symbols") => self.options.debug_symbol_table = show,
Some(&"eval") => {
//let ref mut language = self.languages[self.current_language_index];
//language.set_option("trace_evaluation", show);
},
Some(&"llvm") => self.options.show_llvm_ir = show,
Some(e) => {
println!("Bad `show`/`hide` argument: {}", e);
return true;
}
None => {
println!("`show`/`hide` requires an argument");
return true;
}
}
},
e => println!("Unknown command: {}", e)
}
return true;
}
}
pub fn compilation_sequence(llvm_code: LLVMCodeString, sourcefile: &str) {
use std::process::Command;
let ll_filename = "out.ll";
let obj_filename = "out.o";
let q: Vec<&str> = sourcefile.split('.').collect();
let bin_filename = match &q[..] {
&[name, "maaru"] => name,
_ => panic!("Bad filename {}", sourcefile),
};
let LLVMCodeString(llvm_str) = llvm_code;
println!("Compilation process finished for {}", ll_filename);
File::create(ll_filename)
.and_then(|mut f| f.write_all(llvm_str.as_bytes()))
.expect("Error writing file");
let llc_output = Command::new("llc")
.args(&["-filetype=obj", ll_filename, "-o", obj_filename])
.output()
.expect("Failed to run llc");
if !llc_output.status.success() {
println!("{}", String::from_utf8_lossy(&llc_output.stderr));
}
let gcc_output = Command::new("gcc")
.args(&["-o", bin_filename, &obj_filename])
.output()
.expect("failed to run gcc");
if !gcc_output.status.success() {
println!("{}", String::from_utf8_lossy(&gcc_output.stdout));
println!("{}", String::from_utf8_lossy(&gcc_output.stderr));
}
for filename in [obj_filename].iter() {
Command::new("rm")
.arg(filename)
.output()
.expect(&format!("failed to run rm {}", filename));
}
}
fn program_options() -> getopts::Options {
let mut options = getopts::Options::new();
options.optopt("s",
"eval-style",
"Specify whether to compile (if supported) or interpret the language. If not specified, the default is language-specific",
"[compile|interpret]"
);
options.optflag("",
"list-languages",
"Show a list of all supported languages");
options.optopt("l",
"lang",
"Start up REPL in a language",
"LANGUAGE");
options.optflag("h",
"help",
"Show help text");
options.optflag("w",
"webapp",
"Start up web interpreter");
options
}

279
schala-lib/src/llvm_wrap.rs Normal file
View File

@@ -0,0 +1,279 @@
#![allow(non_snake_case)]
#![allow(dead_code)]
extern crate llvm_sys;
use self::llvm_sys::{LLVMIntPredicate, LLVMRealPredicate};
use self::llvm_sys::prelude::*;
use self::llvm_sys::core;
use std::ptr;
use std::ffi::{CString, CStr};
use std::os::raw::c_char;
pub fn create_context() -> LLVMContextRef {
unsafe { core::LLVMContextCreate() }
}
pub fn module_create_with_name(name: &str) -> LLVMModuleRef {
unsafe {
let n = name.as_ptr() as *const _;
core::LLVMModuleCreateWithName(n)
}
}
pub fn CreateBuilderInContext(context: LLVMContextRef) -> LLVMBuilderRef {
unsafe { core::LLVMCreateBuilderInContext(context) }
}
pub fn AppendBasicBlockInContext(context: LLVMContextRef,
function: LLVMValueRef,
name: &str)
-> LLVMBasicBlockRef {
let c_name = CString::new(name).unwrap();
unsafe { core::LLVMAppendBasicBlockInContext(context, function, c_name.as_ptr()) }
}
pub fn AddFunction(module: LLVMModuleRef, name: &str, function_type: LLVMTypeRef) -> LLVMValueRef {
let c_name = CString::new(name).unwrap();
unsafe { core::LLVMAddFunction(module, c_name.as_ptr(), function_type) }
}
pub fn FunctionType(return_type: LLVMTypeRef,
mut param_types: Vec<LLVMTypeRef>,
is_var_rag: bool)
-> LLVMTypeRef {
let len = param_types.len();
unsafe {
let pointer = param_types.as_mut_ptr();
core::LLVMFunctionType(return_type,
pointer,
len as u32,
if is_var_rag { 1 } else { 0 })
}
}
pub fn GetNamedFunction(module: LLVMModuleRef,
name: &str) -> Option<LLVMValueRef> {
let c_name = CString::new(name).unwrap();
let ret = unsafe { core::LLVMGetNamedFunction(module, c_name.as_ptr()) };
if ret.is_null() {
None
} else {
Some(ret)
}
}
pub fn VoidTypeInContext(context: LLVMContextRef) -> LLVMTypeRef {
unsafe { core::LLVMVoidTypeInContext(context) }
}
pub fn DisposeBuilder(builder: LLVMBuilderRef) {
unsafe { core::LLVMDisposeBuilder(builder) }
}
pub fn DisposeModule(module: LLVMModuleRef) {
unsafe { core::LLVMDisposeModule(module) }
}
pub fn ContextDispose(context: LLVMContextRef) {
unsafe { core::LLVMContextDispose(context) }
}
pub fn PositionBuilderAtEnd(builder: LLVMBuilderRef, basic_block: LLVMBasicBlockRef) {
unsafe { core::LLVMPositionBuilderAtEnd(builder, basic_block) }
}
pub fn BuildRet(builder: LLVMBuilderRef, val: LLVMValueRef) -> LLVMValueRef {
unsafe { core::LLVMBuildRet(builder, val) }
}
pub fn BuildRetVoid(builder: LLVMBuilderRef) -> LLVMValueRef {
unsafe { core::LLVMBuildRetVoid(builder) }
}
pub fn DumpModule(module: LLVMModuleRef) {
unsafe { core::LLVMDumpModule(module) }
}
pub fn Int64TypeInContext(context: LLVMContextRef) -> LLVMTypeRef {
unsafe { core::LLVMInt64TypeInContext(context) }
}
pub fn ConstInt(int_type: LLVMTypeRef, n: u64, sign_extend: bool) -> LLVMValueRef {
unsafe { core::LLVMConstInt(int_type, n, if sign_extend { 1 } else { 0 }) }
}
pub fn BuildAdd(builder: LLVMBuilderRef,
lhs: LLVMValueRef,
rhs: LLVMValueRef,
reg_name: &str)
-> LLVMValueRef {
let name = CString::new(reg_name).unwrap();
unsafe { core::LLVMBuildAdd(builder, lhs, rhs, name.as_ptr()) }
}
pub fn BuildSub(builder: LLVMBuilderRef,
lhs: LLVMValueRef,
rhs: LLVMValueRef,
reg_name: &str)
-> LLVMValueRef {
let name = CString::new(reg_name).unwrap();
unsafe { core::LLVMBuildSub(builder, lhs, rhs, name.as_ptr()) }
}
pub fn BuildMul(builder: LLVMBuilderRef,
lhs: LLVMValueRef,
rhs: LLVMValueRef,
reg_name: &str)
-> LLVMValueRef {
let name = CString::new(reg_name).unwrap();
unsafe { core::LLVMBuildMul(builder, lhs, rhs, name.as_ptr()) }
}
pub fn BuildUDiv(builder: LLVMBuilderRef,
lhs: LLVMValueRef,
rhs: LLVMValueRef,
reg_name: &str)
-> LLVMValueRef {
let name = CString::new(reg_name).unwrap();
unsafe { core::LLVMBuildUDiv(builder, lhs, rhs, name.as_ptr()) }
}
pub fn BuildSRem(builder: LLVMBuilderRef,
lhs: LLVMValueRef,
rhs: LLVMValueRef,
reg_name: &str)
-> LLVMValueRef {
let name = CString::new(reg_name).unwrap();
unsafe { core::LLVMBuildSRem(builder, lhs, rhs, name.as_ptr()) }
}
pub fn BuildCondBr(builder: LLVMBuilderRef,
if_expr: LLVMValueRef,
then_expr: LLVMBasicBlockRef,
else_expr: LLVMBasicBlockRef) -> LLVMValueRef {
unsafe { core::LLVMBuildCondBr(builder, if_expr, then_expr, else_expr) }
}
pub fn BuildBr(builder: LLVMBuilderRef,
dest: LLVMBasicBlockRef) -> LLVMValueRef {
unsafe { core::LLVMBuildBr(builder, dest) }
}
pub fn GetInsertBlock(builder: LLVMBuilderRef) -> LLVMBasicBlockRef {
unsafe { core::LLVMGetInsertBlock(builder) }
}
pub fn BuildPhi(builder: LLVMBuilderRef, ty: LLVMTypeRef, name: &str) -> LLVMValueRef {
let name = CString::new(name).unwrap();
unsafe { core::LLVMBuildPhi(builder, ty, name.as_ptr()) }
}
pub fn SetValueName(value: LLVMValueRef, name: &str) {
let name = CString::new(name).unwrap();
unsafe {
core::LLVMSetValueName(value, name.as_ptr())
}
}
pub fn GetValueName(value: LLVMValueRef) -> String {
unsafe {
let name_ptr: *const c_char = core::LLVMGetValueName(value);
CStr::from_ptr(name_ptr).to_string_lossy().into_owned()
}
}
pub fn GetParams(function: LLVMValueRef) -> Vec<LLVMValueRef> {
let size = CountParams(function);
unsafe {
let mut container = Vec::with_capacity(size);
container.set_len(size);
core::LLVMGetParams(function, container.as_mut_ptr());
container
}
}
pub fn CountParams(function: LLVMValueRef) -> usize {
unsafe { core::LLVMCountParams(function) as usize }
}
pub fn BuildFCmp(builder: LLVMBuilderRef,
op: LLVMRealPredicate,
lhs: LLVMValueRef,
rhs: LLVMValueRef,
name: &str) -> LLVMValueRef {
let name = CString::new(name).unwrap();
unsafe { core::LLVMBuildFCmp(builder, op, lhs, rhs, name.as_ptr()) }
}
pub fn BuildZExt(builder: LLVMBuilderRef,
val: LLVMValueRef,
dest_type: LLVMTypeRef,
name: &str) -> LLVMValueRef {
let name = CString::new(name).unwrap();
unsafe { core::LLVMBuildZExt(builder, val, dest_type, name.as_ptr()) }
}
pub fn BuildUIToFP(builder: LLVMBuilderRef,
val: LLVMValueRef,
dest_type: LLVMTypeRef,
name: &str) -> LLVMValueRef {
let name = CString::new(name).unwrap();
unsafe { core::LLVMBuildUIToFP(builder, val, dest_type, name.as_ptr()) }
}
pub fn BuildICmp(builder: LLVMBuilderRef,
op: LLVMIntPredicate,
lhs: LLVMValueRef,
rhs: LLVMValueRef,
name: &str) -> LLVMValueRef {
let name = CString::new(name).unwrap();
unsafe { core::LLVMBuildICmp(builder, op, lhs, rhs, name.as_ptr()) }
}
pub fn GetBasicBlockParent(block: LLVMBasicBlockRef) -> LLVMValueRef {
unsafe { core::LLVMGetBasicBlockParent(block) }
}
pub fn GetBasicBlocks(function: LLVMValueRef) -> Vec<LLVMBasicBlockRef> {
let size = CountBasicBlocks(function);
unsafe {
let mut container = Vec::with_capacity(size);
container.set_len(size);
core::LLVMGetBasicBlocks(function, container.as_mut_ptr());
container
}
}
pub fn CountBasicBlocks(function: LLVMValueRef) -> usize {
unsafe { core::LLVMCountBasicBlocks(function) as usize }
}
pub fn PrintModuleToString(module: LLVMModuleRef) -> String {
unsafe {
let str_ptr: *const c_char = core::LLVMPrintModuleToString(module);
CStr::from_ptr(str_ptr).to_string_lossy().into_owned()
}
}
pub fn AddIncoming(phi_node: LLVMValueRef, mut incoming_values: Vec<LLVMValueRef>,
mut incoming_blocks: Vec<LLVMBasicBlockRef>) {
let count = incoming_blocks.len() as u32;
if incoming_values.len() as u32 != count {
panic!("Bad invocation of AddIncoming");
}
unsafe {
let vals = incoming_values.as_mut_ptr();
let blocks = incoming_blocks.as_mut_ptr();
core::LLVMAddIncoming(phi_node, vals, blocks, count)
}
}
pub fn PrintModuleToFile(module: LLVMModuleRef, filename: &str) -> LLVMBool {
let out_file = CString::new(filename).unwrap();
unsafe { core::LLVMPrintModuleToFile(module, out_file.as_ptr(), ptr::null_mut()) }
}

45
schala-lib/src/webapp.rs Normal file
View File

@@ -0,0 +1,45 @@
use rocket;
use rocket::State;
use rocket::response::Content;
use rocket::response::NamedFile;
use rocket::http::ContentType;
use rocket_contrib::Json;
use language::{ProgrammingLanguageInterface, EvalOptions};
use WEBFILES;
use ::PLIGenerator;
#[get("/")]
fn index() -> Content<String> {
let path = "static/index.html";
let html_contents = String::from_utf8(WEBFILES.get(path).unwrap().into_owned()).unwrap();
Content(ContentType::HTML, html_contents)
}
#[get("/bundle.js")]
fn js_bundle() -> Content<String> {
let path = "static/bundle.js";
let js_contents = String::from_utf8(WEBFILES.get(path).unwrap().into_owned()).unwrap();
Content(ContentType::JavaScript, js_contents)
}
#[derive(Debug, Serialize, Deserialize)]
struct Input {
source: String,
}
#[derive(Serialize, Deserialize)]
struct Output {
text: String,
}
#[post("/input", format = "application/json", data = "<input>")]
fn interpreter_input(input: Json<Input>, generators: State<Vec<PLIGenerator>>) -> Json<Output> {
let schala_gen = generators.get(0).unwrap();
let mut schala: Box<ProgrammingLanguageInterface> = schala_gen();
let code_output = schala.evaluate_in_repl(&input.source, &EvalOptions::default());
Json(Output { text: code_output.to_string() })
}
pub fn web_main(language_generators: Vec<PLIGenerator>) {
rocket::ignite().manage(language_generators).mount("/", routes![index, js_bundle, interpreter_input]).launch();
}

View File

@@ -1,71 +0,0 @@
use std::time;
use std::collections::HashSet;
pub trait ProgrammingLanguageInterface {
fn get_language_name(&self) -> String;
fn get_source_file_suffix(&self) -> String;
fn run_computation(&mut self, _request: ComputationRequest) -> ComputationResponse {
ComputationResponse {
main_output: Err(format!("Computation pipeline not implemented")),
global_output_stats: GlobalOutputStats::default(),
debug_responses: vec![],
}
}
fn request_meta(&mut self, _request: LangMetaRequest) -> LangMetaResponse {
LangMetaResponse::Custom { kind: format!("not-implemented"), value: format!("") }
}
}
pub struct ComputationRequest<'a> {
pub source: &'a str,
pub debug_requests: HashSet<DebugAsk>,
}
pub struct ComputationResponse {
pub main_output: Result<String, String>,
pub global_output_stats: GlobalOutputStats,
pub debug_responses: Vec<DebugResponse>,
}
#[derive(Default, Debug)]
pub struct GlobalOutputStats {
pub total_duration: time::Duration,
pub stage_durations: Vec<(String, time::Duration)>
}
#[derive(Debug, Clone, Hash, Eq, PartialEq, Deserialize, Serialize)]
pub enum DebugAsk {
Timing,
ByStage { stage_name: String },
}
pub struct DebugResponse {
pub ask: DebugAsk,
pub value: String
}
pub enum LangMetaRequest {
StageNames,
Docs {
source: String,
},
Custom {
kind: String,
value: String
},
ImmediateDebug(DebugAsk),
}
pub enum LangMetaResponse {
StageNames(Vec<String>),
Docs {
doc_string: String,
},
Custom {
kind: String,
value: String
},
ImmediateDebug(DebugResponse),
}

View File

@@ -1,92 +0,0 @@
#![feature(link_args)]
#![feature(slice_patterns, box_patterns, box_syntax, proc_macro_hygiene, decl_macro)]
#![feature(plugin)]
extern crate getopts;
extern crate linefeed;
extern crate itertools;
extern crate colored;
#[macro_use]
extern crate serde_derive;
extern crate serde_json;
extern crate includedir;
extern crate phf;
use std::collections::HashSet;
use std::path::Path;
use std::fs::File;
use std::io::Read;
use std::process::exit;
mod repl;
mod language;
pub use language::{ProgrammingLanguageInterface,
ComputationRequest, ComputationResponse,
LangMetaRequest, LangMetaResponse,
DebugResponse, DebugAsk, GlobalOutputStats};
include!(concat!(env!("OUT_DIR"), "/static.rs"));
const VERSION_STRING: &'static str = "0.1.0";
pub fn start_repl(langs: Vec<Box<dyn ProgrammingLanguageInterface>>) {
let options = command_line_options().parse(std::env::args()).unwrap_or_else(|e| {
println!("{:?}", e);
exit(1);
});
if options.opt_present("help") {
println!("{}", command_line_options().usage("Schala metainterpreter"));
exit(0);
}
match options.free[..] {
[] | [_] => {
let mut repl = repl::Repl::new(langs);
repl.run_repl();
}
[_, ref filename, _..] => {
run_noninteractive(filename, langs);
}
};
}
fn run_noninteractive(filename: &str, languages: Vec<Box<ProgrammingLanguageInterface>>) {
let path = Path::new(filename);
let ext = path.extension().and_then(|e| e.to_str()).unwrap_or_else(|| {
println!("Source file lacks extension");
exit(1);
});
let mut language = Box::new(languages.into_iter().find(|lang| lang.get_source_file_suffix() == ext)
.unwrap_or_else(|| {
println!("Extension .{} not recognized", ext);
exit(1);
}));
let mut source_file = File::open(path).unwrap();
let mut buffer = String::new();
source_file.read_to_string(&mut buffer).unwrap();
let request = ComputationRequest {
source: &buffer,
debug_requests: HashSet::new(),
};
let response = language.run_computation(request);
match response.main_output {
Ok(s) => println!("{}", s),
Err(s) => println!("{}", s)
};
}
fn command_line_options() -> getopts::Options {
let mut options = getopts::Options::new();
options.optflag("h",
"help",
"Show help text");
options.optflag("w",
"webapp",
"Start up web interpreter");
options
}

View File

@@ -1,126 +0,0 @@
use std::fmt::Write as FmtWrite;
use itertools::Itertools;
use crate::repl::Repl;
use crate::repl::old_command_tree::OldCommandTree;
use crate::language::{LangMetaRequest, LangMetaResponse, DebugAsk, DebugResponse};
pub fn directives_from_pass_names(pass_names: &Vec<String>) -> OldCommandTree {
let passes_directives: Vec<OldCommandTree> = pass_names.iter()
.map(|pass_name| { OldCommandTree::nonterm_no_further_tab_completions(pass_name, None) })
.collect();
OldCommandTree::Top(vec![
OldCommandTree::terminal("exit", Some("exit the REPL"), vec![], Box::new(|repl: &mut Repl, _cmds: &[&str]| {
repl.save_before_exit();
::std::process::exit(0)
})),
OldCommandTree::terminal("quit", Some("exit the REPL"), vec![], Box::new(|repl: &mut Repl, _cmds: &[&str]| {
repl.save_before_exit();
::std::process::exit(0)
})),
OldCommandTree::terminal("help", Some("Print this help message"), vec![], Box::new(|repl: &mut Repl, cmds: &[&str]| {
Some(repl.print_help_message(cmds))
})),
OldCommandTree::nonterm("debug",
Some("Configure debug information"),
vec![
OldCommandTree::terminal("list-passes", Some("List all registered compiler passes"), vec![], Box::new(|repl: &mut Repl, _cmds: &[&str]| {
let language_state = repl.get_cur_language_state();
let pass_names = match language_state.request_meta(LangMetaRequest::StageNames) {
LangMetaResponse::StageNames(names) => names,
_ => vec![],
};
let mut buf = String::new();
for pass in pass_names.iter().map(|name| Some(name)).intersperse(None) {
match pass {
Some(pass) => write!(buf, "{}", pass).unwrap(),
None => write!(buf, " -> ").unwrap(),
}
}
Some(buf)
})),
OldCommandTree::terminal("show-immediate", None, passes_directives.clone(),
Box::new(|repl: &mut Repl, cmds: &[&str]| {
let cur_state = repl.get_cur_language_state();
let stage_name = match cmds.get(1) {
Some(s) => s.to_string(),
None => return Some(format!("Must specify a thing to debug")),
};
let meta = LangMetaRequest::ImmediateDebug(DebugAsk::ByStage { stage_name: stage_name.clone() });
let response = match cur_state.request_meta(meta) {
LangMetaResponse::ImmediateDebug(DebugResponse { ask, value }) => {
if (ask != DebugAsk::ByStage { stage_name: stage_name }) {
return Some(format!("Didn't get debug stage requested"));
}
value
},
_ => return Some(format!("Invalid language meta response")),
};
Some(response)
})),
OldCommandTree::terminal("show", None, passes_directives.clone(), Box::new(|repl: &mut Repl, cmds: &[&str]| {
let stage_name = match cmds.get(0) {
Some(s) => s.to_string(),
None => return Some(format!("Must specify a stage to show")),
};
let ask = DebugAsk::ByStage { stage_name };
repl.options.debug_asks.insert(ask);
None
})),
OldCommandTree::terminal("hide", None, passes_directives.clone(), Box::new(|repl: &mut Repl, cmds: &[&str]| {
let stage_name = match cmds.get(0) {
Some(s) => s.to_string(),
None => return Some(format!("Must specify a stage to hide")),
};
let ask = DebugAsk::ByStage { stage_name };
repl.options.debug_asks.remove(&ask);
None
})),
OldCommandTree::nonterm("total-time", None, vec![
OldCommandTree::terminal("on", None, vec![], Box::new(|repl: &mut Repl, _: &[&str]| {
repl.options.show_total_time = true;
None
})),
OldCommandTree::terminal("off", None, vec![], Box::new(turn_off)),
]),
OldCommandTree::nonterm("stage-times", Some("Computation time per-stage"), vec![
OldCommandTree::terminal("on", None, vec![], Box::new(|repl: &mut Repl, _: &[&str]| {
repl.options.show_stage_times = true;
None
})),
OldCommandTree::terminal("off", None, vec![], Box::new(|repl: &mut Repl, _: &[&str]| {
repl.options.show_stage_times = false;
None
})),
])
]
),
OldCommandTree::nonterm("lang",
Some("switch between languages, or go directly to a langauge by name"),
vec![
OldCommandTree::nonterm_no_further_tab_completions("next", None),
OldCommandTree::nonterm_no_further_tab_completions("prev", None),
OldCommandTree::nonterm("go", None, vec![]),
]
),
OldCommandTree::terminal("doc", Some("Get language-specific help for an item"), vec![], Box::new(|repl: &mut Repl, cmds: &[&str]| {
cmds.get(0).map(|cmd| {
let source = cmd.to_string();
let meta = LangMetaRequest::Docs { source };
let cur_state = repl.get_cur_language_state();
match cur_state.request_meta(meta) {
LangMetaResponse::Docs { doc_string } => Some(doc_string),
_ => Some(format!("Invalid doc response"))
}
}).unwrap_or(Some(format!(":docs needs an argument")))
}))
])
}
fn turn_off(repl: &mut Repl, _cmds: &[&str]) -> Option<String> {
repl.options.show_total_time = false;
None
}

View File

@@ -1,302 +0,0 @@
use std::fmt::Write as FmtWrite;
use std::sync::Arc;
use std::collections::HashSet;
use colored::*;
use crate::language::{ProgrammingLanguageInterface,
ComputationRequest, ComputationResponse,
DebugAsk, LangMetaResponse, LangMetaRequest};
mod old_command_tree;
use self::old_command_tree::{OldCommandTree, BoxedCommandFunction};
mod repl_options;
use repl_options::ReplOptions;
mod directives;
use directives::directives_from_pass_names;
const HISTORY_SAVE_FILE: &'static str = ".schala_history";
const OPTIONS_SAVE_FILE: &'static str = ".schala_repl";
pub struct Repl {
interpreter_directive_sigil: char,
line_reader: ::linefeed::interface::Interface<::linefeed::terminal::DefaultTerminal>,
language_states: Vec<Box<ProgrammingLanguageInterface>>,
options: ReplOptions,
directives: OldCommandTree,
}
impl Repl {
pub fn new(mut initial_states: Vec<Box<ProgrammingLanguageInterface>>) -> Repl {
use linefeed::Interface;
let line_reader = Interface::new("schala-repl").unwrap();
let interpreter_directive_sigil = ':';
let pass_names = match initial_states[0].request_meta(LangMetaRequest::StageNames) {
LangMetaResponse::StageNames(names) => names,
_ => vec![],
};
Repl {
interpreter_directive_sigil,
line_reader,
language_states: initial_states,
options: ReplOptions::new(),
directives: directives_from_pass_names(&pass_names)
}
}
pub fn run_repl(&mut self) {
println!("Schala MetaInterpreter version {}", crate::VERSION_STRING);
println!("Type {}help for help with the REPL", self.interpreter_directive_sigil);
self.load_options();
self.handle_repl_loop();
self.save_before_exit();
println!("Exiting...");
}
fn load_options(&mut self) {
self.line_reader.load_history(HISTORY_SAVE_FILE).unwrap_or(());
match ReplOptions::load_from_file(OPTIONS_SAVE_FILE) {
Ok(options) => {
self.options = options;
},
Err(()) => ()
};
}
fn handle_repl_loop(&mut self) {
use linefeed::ReadResult::*;
loop {
self.update_line_reader();
match self.line_reader.read_line() {
Err(e) => {
println!("readline IO Error: {}", e);
break;
},
Ok(Eof) | Ok(Signal(_)) => break,
Ok(Input(ref input)) => {
self.line_reader.add_history_unique(input.to_string());
let output = match input.chars().nth(0) {
Some(ch) if ch == self.interpreter_directive_sigil => self.handle_interpreter_directive(input),
_ => Some(self.handle_input(input)),
};
if let Some(o) = output {
println!("=> {}", o);
}
}
}
}
}
fn update_line_reader(&mut self) {
let tab_complete_handler = TabCompleteHandler::new(self.interpreter_directive_sigil, self.get_directives());
self.line_reader.set_completer(Arc::new(tab_complete_handler)); //TODO fix this here
let prompt_str = format!(">> ");
self.line_reader.set_prompt(&prompt_str).unwrap();
}
fn save_before_exit(&self) {
self.line_reader.save_history(HISTORY_SAVE_FILE).unwrap_or(());
self.options.save_to_file(OPTIONS_SAVE_FILE);
}
fn get_function_from_directives<'a>(directives: &'a OldCommandTree, commands: &Vec<&str>) -> Result<(&'a BoxedCommandFunction, usize), String> {
let mut dir_pointer: &OldCommandTree = &directives;
let mut idx = 0;
loop {
match dir_pointer {
OldCommandTree::Top(subcommands) | OldCommandTree::NonTerminal { children: subcommands, .. } => {
let next_command = match commands.get(idx) {
Some(cmd) => cmd,
None => break Err(format!("Command requires arguments"))
};
idx += 1;
match subcommands.iter().find(|sc| sc.get_cmd() == *next_command) {
Some(command_tree) => {
dir_pointer = command_tree;
},
None => break Err(format!("Command {} not found", next_command))
};
},
OldCommandTree::Terminal { function, .. } => {
break Ok((function, idx));
},
}
}
}
fn handle_interpreter_directive(&mut self, input: &str) -> Option<String> {
let mut iter = input.chars();
iter.next();
let commands: Vec<&str> = iter
.as_str()
.split_whitespace()
.collect();
if commands.len() < 1 {
return None;
}
let directives = self.get_directives();
let result: Result<(&BoxedCommandFunction, _), String> = Repl::get_function_from_directives(&directives, &commands);
match result {
Ok((f, idx)) => f(self, &commands[idx..]),
Err(err) => Some(err.red().to_string())
}
}
fn print_help_message(&mut self, commands_passed_to_help: &[&str] ) -> String {
let mut buf = String::new();
let directives = match self.get_directives() {
OldCommandTree::Top(children) => children,
_ => panic!("Top-level OldCommandTree not Top")
};
match commands_passed_to_help {
[] => {
writeln!(buf, "MetaInterpreter options").unwrap();
writeln!(buf, "-----------------------").unwrap();
for directive in directives {
let trailer = " ";
writeln!(buf, "{}{}- {}", directive.get_cmd(), trailer, directive.get_help()).unwrap();
}
let ref lang = self.get_cur_language_state();
writeln!(buf, "").unwrap();
writeln!(buf, "Language-specific help for {}", lang.get_language_name()).unwrap();
writeln!(buf, "-----------------------").unwrap();
},
_ => {
writeln!(buf, "Command-specific help not available yet").unwrap();
}
};
buf
}
fn get_cur_language_state(&mut self) -> &mut Box<ProgrammingLanguageInterface> {
//TODO this is obviously not complete
&mut self.language_states[0]
}
fn handle_input(&mut self, input: &str) -> String {
let mut debug_requests = HashSet::new();
for ask in self.options.debug_asks.iter() {
debug_requests.insert(ask.clone());
}
let request = ComputationRequest {
source: input,
debug_requests,
};
let ref mut language_state = self.get_cur_language_state();
let response = language_state.run_computation(request);
self.handle_computation_response(response)
}
fn handle_computation_response(&mut self, response: ComputationResponse) -> String {
let mut buf = String::new();
if self.options.show_total_time {
buf.push_str(&format!("Total duration: {:?}\n", response.global_output_stats.total_duration));
}
if self.options.show_stage_times {
buf.push_str(&format!("{:?}\n", response.global_output_stats.stage_durations));
}
for debug_resp in response.debug_responses {
let stage_name = match debug_resp.ask {
DebugAsk::ByStage { stage_name } => stage_name,
_ => continue,
};
let s = format!("{} - {}\n", stage_name, debug_resp.value);
buf.push_str(&s);
}
buf.push_str(&match response.main_output {
Ok(s) => s,
Err(e) => format!("{} {}", "Error".red(), e)
});
buf
}
fn get_directives(&mut self) -> OldCommandTree {
let language_state = self.get_cur_language_state();
let pass_names = match language_state.request_meta(LangMetaRequest::StageNames) {
LangMetaResponse::StageNames(names) => names,
_ => vec![],
};
directives_from_pass_names(&pass_names)
}
}
struct TabCompleteHandler {
sigil: char,
top_level_commands: OldCommandTree,
}
use linefeed::complete::{Completion, Completer};
use linefeed::terminal::Terminal;
impl TabCompleteHandler {
fn new(sigil: char, top_level_commands: OldCommandTree) -> TabCompleteHandler {
TabCompleteHandler {
top_level_commands,
sigil,
}
}
}
impl<T: Terminal> Completer<T> for TabCompleteHandler {
fn complete(&self, word: &str, prompter: &::linefeed::prompter::Prompter<T>, start: usize, _end: usize) -> Option<Vec<Completion>> {
let line = prompter.buffer();
if !line.starts_with(self.sigil) {
return None;
}
let mut words = line[1..(if start == 0 { 1 } else { start })].split_whitespace();
let mut completions = Vec::new();
let mut command_tree: Option<&OldCommandTree> = Some(&self.top_level_commands);
loop {
match words.next() {
None => {
let top = match command_tree {
Some(OldCommandTree::Top(_)) => true,
_ => false
};
let word = if top { word.get(1..).unwrap() } else { word };
for cmd in command_tree.map(|x| x.get_children()).unwrap_or(vec![]).into_iter() {
if cmd.starts_with(word) {
completions.push(Completion {
completion: format!("{}{}", if top { ":" } else { "" }, cmd),
display: Some(cmd.to_string()),
suffix: ::linefeed::complete::Suffix::Some(' ')
})
}
}
break;
},
Some(s) => {
let new_ptr: Option<&OldCommandTree> = command_tree.and_then(|cm| match cm {
OldCommandTree::Top(children) => children.iter().find(|c| c.get_cmd() == s),
OldCommandTree::NonTerminal { children, .. } => children.iter().find(|c| c.get_cmd() == s),
OldCommandTree::Terminal { children, .. } => children.iter().find(|c| c.get_cmd() == s),
});
command_tree = new_ptr;
}
}
}
Some(completions)
}
}

View File

@@ -1,73 +0,0 @@
use super::Repl;
pub type BoxedCommandFunction = Box<(fn(&mut Repl, &[&str]) -> Option<String>)>;
/// A OldCommandTree is either a `Terminal` or a `NonTerminal`. When command parsing reaches the first
/// Terminal, it will execute the `BoxedCommandFunction` found there with any remaining arguments
#[derive(Clone)]
pub enum OldCommandTree {
Terminal {
name: String,
children: Vec<OldCommandTree>,
help_msg: Option<String>,
function: BoxedCommandFunction,
},
NonTerminal {
name: String,
children: Vec<OldCommandTree>,
help_msg: Option<String>,
},
Top(Vec<OldCommandTree>),
}
impl OldCommandTree {
pub fn nonterm_no_further_tab_completions(s: &str, help: Option<&str>) -> OldCommandTree {
OldCommandTree::NonTerminal {name: s.to_string(), help_msg: help.map(|x| x.to_string()), children: vec![] }
}
pub fn terminal(s: &str, help: Option<&str>, children: Vec<OldCommandTree>, function: BoxedCommandFunction) -> OldCommandTree {
OldCommandTree::Terminal {name: s.to_string(), help_msg: help.map(|x| x.to_string()), function, children }
}
pub fn nonterm(s: &str, help: Option<&str>, children: Vec<OldCommandTree>) -> OldCommandTree {
OldCommandTree::NonTerminal {
name: s.to_string(),
help_msg: help.map(|x| x.to_string()),
children,
}
}
/*
pub fn nonterm_with_function(s: &str, help: Option<&str>, children: Vec<OldCommandTree>, func: BoxedCommandFunction) -> OldCommandTree {
OldCommandTree::NonTerminal {
name: s.to_string(),
help_msg: help.map(|x| x.to_string()),
children,
function: Some(func),
}
}
*/
pub fn get_cmd(&self) -> &str {
match self {
OldCommandTree::Terminal { name, .. } => name.as_str(),
OldCommandTree::NonTerminal {name, ..} => name.as_str(),
OldCommandTree::Top(_) => "",
}
}
pub fn get_help(&self) -> &str {
match self {
OldCommandTree::Terminal { help_msg, ..} => help_msg.as_ref().map(|s| s.as_str()).unwrap_or(""),
OldCommandTree::NonTerminal { help_msg, .. } => help_msg.as_ref().map(|s| s.as_str()).unwrap_or(""),
OldCommandTree::Top(_) => ""
}
}
pub fn get_children(&self) -> Vec<&str> {
use OldCommandTree::*;
match self {
Terminal { children, .. } |
NonTerminal { children, .. } |
Top(children) => children.iter().map(|x| x.get_cmd()).collect()
}
}
}

View File

@@ -1,47 +0,0 @@
use crate::language::DebugAsk;
use std::io::{Read, Write};
use std::collections::HashSet;
use std::fs::File;
#[derive(Serialize, Deserialize)]
pub struct ReplOptions {
pub debug_asks: HashSet<DebugAsk>,
pub show_total_time: bool,
pub show_stage_times: bool,
}
impl ReplOptions {
pub fn new() -> ReplOptions {
ReplOptions {
debug_asks: HashSet::new(),
show_total_time: true,
show_stage_times: false,
}
}
pub fn save_to_file(&self, filename: &str) {
let res = File::create(filename)
.and_then(|mut file| {
let buf = crate::serde_json::to_string(self).unwrap();
file.write_all(buf.as_bytes())
});
if let Err(err) = res {
println!("Error saving {} file {}", filename, err);
}
}
pub fn load_from_file(filename: &str) -> Result<ReplOptions, ()> {
File::open(filename)
.and_then(|mut file| {
let mut contents = String::new();
file.read_to_string(&mut contents)?;
Ok(contents)
})
.and_then(|contents| {
let output: ReplOptions = crate::serde_json::from_str(&contents)?;
Ok(output)
})
.map_err(|_| ())
}
}

View File

@@ -1,11 +0,0 @@
let c = 10
fn add(a, b) {
let c = a + b
c
}
let mut b = 20
println(add(1,2))
println(c + b)

View File

@@ -0,0 +1,10 @@
fn main() {
const a = 10
const b = 20
a + b
}
print(main())
const xxx

View File

@@ -1,17 +0,0 @@
fn main() {
let a = 10
let b = 20
a + b
}
//this is a one-line comment
/* this is
a multiline
comment
*/
print(main())

View File

@@ -1,12 +0,0 @@
for n <- 1..=100 {
if n % 15 == 0 {
print("FizzBuzz")
} else if n % 5 == 0 {
print("Buzz")
} else if n % 3 == 0 {
print("Fizz")
} else {
print(n.to_string())
}
}

View File

@@ -1,114 +0,0 @@
fn main() {
//comments are C-style
/* nested comments /* are cool */ */
}
@annotations are with @-
// variable expressions
var a: I32 = 20
const b: String = 20
there(); can(); be(); multiple(); statements(); per_line();
//string interpolation
const yolo = "I have ${a + b} people in my house"
// let expressions ??? not sure if I want this
let a = 10, b = 20, c = 30 in a + b + c
//list literal
const q = [1,2,3,4]
//lambda literal
q.map({|item| item * 100 })
fn yolo(a: MyType, b: YourType): ReturnType<Param1, Param2> {
if a == 20 {
return "early"
}
var sex = 20
sex
}
/* for/while loop topics */
//infinite loop
while {
if x() { break }
...
}
//conditional loop
while conditionHolds() {
...
}
//iteration over a variable
for i <- [1..1000] {
} //return type is return type of block
//monadic decomposition
for {
a <- maybeInt();
s <- foo()
} return {
a + s
} //return type is Monad<return type of block>
/* end of for loops */
/* conditionals/pattern matching */
// "is" operator for "does this pattern match"
x is Some(t) // type bool
if x {
is Some(t) => {
},
is None => {
}
}
//syntax is, I guess, for <expr> <brace-block>, where <expr> is a bool, or a <arrow-expr>
// type level alises
typealias <name> = <other type> #maybe thsi should be 'alias'?
/*
what if type A = B meant that you could had to create A's with A(B), but when you used A's the interface was exactly like B's?
maybe introduce a 'newtype' keyword for this
*/
//declaring types of all stripes
type MyData = { a: i32, b: String }
type MyType = MyType
type Option<a> = None | Some(a)
type Signal = Absence | SimplePresence(i32) | ComplexPresence {a: i32, b: MyCustomData}
//traits
trait Bashable { }
trait Luggable {
fn lug(self, a: Option<Self>)
}
}
// lambdas
// ruby-style not rust-style
const a: X -> Y -> Z = {|x,y| }

View File

@@ -1,17 +1,105 @@
println(sua(4))
fn main() {
# comments are scripting-style
#{ but can also be
}# blocks
@annotations are with @-
# variable expressions
var a: I32 = 20
const b: String = 20
there(); can(); be(); multiple(); statements(); per_line();
#string interpolation
const yolo = "I have ${a + b} people in my house"
# let expressions ??? not sure if I want this
let a = 10, b = 20, c = 30 in a + b + c
#list literal
const q = [1,2,3,4]
#lambda literal ?? maybe? not sure how this should work
q.map(|item| { item * 100 })
fn yolo(a: MyType, b: YourType): ReturnType<Param1, Param2> {
if a == 20 {
return "early"
}
var sex = 20
sex
}
for {
# infinite loop
}
#iteration over a variable
for i <- [1..1000] {
} #return type is return type of block
#while loop
for a != 3 || fuckTard() {
break
} #return type is return type of block
#monadic decomposition
for {
a <- maybeInt();
s <- foo()
} return {
a + s
} #return type is Monad<return type of block>
# let statements too!!
for (a = 20
b = fuck) {
a + b
}
# pattern-matching
match <expr> {
Some(a) => {
},
None => {
},
}
#syntax is, I guess, for <expr> <brace-block>, where <expr> is a bool, or a <arrow-expr>
# type level alises
typealias <name> = <other type> #maybe thsi should be 'alias'?
#what if type A = B meant that you could had to create A's with A(B), but when you used A's the interface was exactly like B's?
# maybe introduce a 'newtype' keyword for this
#declaring types of all stripes
type MyData = { a: i32, b: String }
type MyType = MyType
type Option<a> = None | Some(a)
type Signal = Absence | SimplePresence(i32) | ComplexPresence {a: i32, b: MyCustomData}
#traits
trait Bashable { }
trait Luggable {
fn lug(self, a: Option<Self>)
}
fn sua(x): Int {
x + 10
}
//let a = getline()
/*
if a == "true" {
println("You typed true")
} else {
println("You typed something else")
}
*/
# lambdas
#
|x,y| { }() #is probably fine
const a = |x: Type, y|: RetType { <statementblock> }
const a: X -> Y -> Z = |x,y| { }

View File

@@ -0,0 +1,279 @@
extern crate llvm_sys;
use std::collections::HashMap;
use self::llvm_sys::prelude::*;
use self::llvm_sys::{LLVMIntPredicate};
use maaru_lang::parser::{AST, Statement, Function, Prototype, Expression, BinOp};
use schala_lib::LLVMCodeString;
use schala_lib::llvm_wrap as LLVMWrap;
type VariableMap = HashMap<String, LLVMValueRef>;
struct CompilationData {
context: LLVMContextRef,
module: LLVMModuleRef,
builder: LLVMBuilderRef,
variables: VariableMap,
main_function: LLVMValueRef,
current_function: Option<LLVMValueRef>,
}
pub fn compile_ast(ast: AST) -> LLVMCodeString {
println!("Compiling!");
let names: VariableMap = HashMap::new();
let context = LLVMWrap::create_context();
let module = LLVMWrap::module_create_with_name("example module");
let builder = LLVMWrap::CreateBuilderInContext(context);
let program_return_type = LLVMWrap::Int64TypeInContext(context);
let main_function_type = LLVMWrap::FunctionType(program_return_type, Vec::new(), false);
let main_function: LLVMValueRef = LLVMWrap::AddFunction(module, "main", main_function_type);
let mut data = CompilationData {
context: context,
builder: builder,
module: module,
variables: names,
main_function: main_function,
current_function: None,
};
let bb = LLVMWrap::AppendBasicBlockInContext(data.context, data.main_function, "entry");
LLVMWrap::PositionBuilderAtEnd(builder, bb);
let value = ast.codegen(&mut data);
LLVMWrap::BuildRet(builder, value);
let ret = LLVMWrap::PrintModuleToString(module);
// Clean up. Values created in the context mostly get cleaned up there.
LLVMWrap::DisposeBuilder(builder);
LLVMWrap::DisposeModule(module);
LLVMWrap::ContextDispose(context);
LLVMCodeString(ret)
}
trait CodeGen {
fn codegen(&self, &mut CompilationData) -> LLVMValueRef;
}
impl CodeGen for AST {
fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
let int_type = LLVMWrap::Int64TypeInContext(data.context);
let mut ret = LLVMWrap::ConstInt(int_type, 0, false);
for statement in self {
ret = statement.codegen(data);
}
ret
}
}
impl CodeGen for Statement {
fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
use self::Statement::*;
match self {
&ExprNode(ref expr) => expr.codegen(data),
&FuncDefNode(ref func) => func.codegen(data),
}
}
}
impl CodeGen for Function {
fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
/* should have a check here for function already being defined */
let function = self.prototype.codegen(data);
let ref body = self.body;
data.current_function = Some(function);
let return_type = LLVMWrap::Int64TypeInContext(data.context);
let mut ret = LLVMWrap::ConstInt(return_type, 0, false);
let block = LLVMWrap::AppendBasicBlockInContext(data.context, function, "entry");
LLVMWrap::PositionBuilderAtEnd(data.builder, block);
//insert function params into variables
for value in LLVMWrap::GetParams(function) {
let name = LLVMWrap::GetValueName(value);
data.variables.insert(name, value);
}
for expr in body {
ret = expr.codegen(data);
}
LLVMWrap::BuildRet(data.builder, ret);
// get basic block of main
let main_bb = LLVMWrap::GetBasicBlocks(data.main_function).get(0).expect("Couldn't get first block of main").clone();
LLVMWrap::PositionBuilderAtEnd(data.builder, main_bb);
data.current_function = None;
ret
}
}
impl CodeGen for Prototype {
fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
let num_args = self.parameters.len();
let return_type = LLVMWrap::Int64TypeInContext(data.context);
let mut arguments: Vec<LLVMTypeRef> = vec![];
for _ in 0..num_args {
arguments.push(LLVMWrap::Int64TypeInContext(data.context));
}
let function_type =
LLVMWrap::FunctionType(return_type,
arguments,
false);
let function = LLVMWrap::AddFunction(data.module,
&*self.name,
function_type);
let function_params = LLVMWrap::GetParams(function);
for (index, param) in function_params.iter().enumerate() {
let name = self.parameters.get(index).expect(&format!("Failed this check at index {}", index));
let new = *param;
LLVMWrap::SetValueName(new, name);
}
function
}
}
impl CodeGen for Expression {
fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
use self::BinOp::*;
use self::Expression::*;
let int_type = LLVMWrap::Int64TypeInContext(data.context);
let zero = LLVMWrap::ConstInt(int_type, 0, false);
match *self {
Variable(ref name) => *data.variables.get(&**name).expect(&format!("Can't find variable {}", name)),
BinExp(Assign, ref left, ref right) => {
if let Variable(ref name) = **left {
let new_value = right.codegen(data);
data.variables.insert((**name).clone(), new_value);
new_value
} else {
panic!("Bad variable assignment")
}
}
BinExp(ref op, ref left, ref right) => {
let lhs = left.codegen(data);
let rhs = right.codegen(data);
op.codegen_with_ops(data, lhs, rhs)
}
Number(ref n) => {
let native_val = *n as u64;
let int_value: LLVMValueRef = LLVMWrap::ConstInt(int_type, native_val, false);
int_value
}
Conditional(ref test, ref then_expr, ref else_expr) => {
let condition_value = test.codegen(data);
let is_nonzero =
LLVMWrap::BuildICmp(data.builder,
LLVMIntPredicate::LLVMIntNE,
condition_value,
zero,
"ifcond");
let func = LLVMWrap::GetBasicBlockParent(LLVMWrap::GetInsertBlock(data.builder));
let mut then_block =
LLVMWrap::AppendBasicBlockInContext(data.context, func, "then_block");
let mut else_block =
LLVMWrap::AppendBasicBlockInContext(data.context, func, "else_block");
let merge_block =
LLVMWrap::AppendBasicBlockInContext(data.context, func, "ifcont");
// add conditional branch to ifcond block
LLVMWrap::BuildCondBr(data.builder, is_nonzero, then_block, else_block);
// start inserting into then block
LLVMWrap::PositionBuilderAtEnd(data.builder, then_block);
// then-block codegen
let then_return = then_expr.codegen(data);
LLVMWrap::BuildBr(data.builder, merge_block);
// update then block b/c recursive codegen() call may have changed the notion of
// the current block
then_block = LLVMWrap::GetInsertBlock(data.builder);
// then do the same stuff again for the else branch
//
LLVMWrap::PositionBuilderAtEnd(data.builder, else_block);
let else_return = match *else_expr {
Some(ref e) => e.codegen(data),
None => zero,
};
LLVMWrap::BuildBr(data.builder, merge_block);
else_block = LLVMWrap::GetInsertBlock(data.builder);
LLVMWrap::PositionBuilderAtEnd(data.builder, merge_block);
let phi = LLVMWrap::BuildPhi(data.builder, int_type, "phinode");
let values = vec![then_return, else_return];
let blocks = vec![then_block, else_block];
LLVMWrap::AddIncoming(phi, values, blocks);
phi
}
Block(ref exprs) => {
let mut ret = zero;
for e in exprs.iter() {
ret = e.codegen(data);
}
ret
}
ref e => {
println!("Unimplemented {:?}", e);
unimplemented!()
}
}
}
}
impl BinOp {
fn codegen_with_ops(&self, data: &CompilationData, lhs: LLVMValueRef, rhs: LLVMValueRef) -> LLVMValueRef {
use self::BinOp::*;
macro_rules! simple_binop {
($fnname: expr, $name: expr) => {
$fnname(data.builder, lhs, rhs, $name)
}
}
let int_type = LLVMWrap::Int64TypeInContext(data.context);
match *self {
Add => simple_binop!(LLVMWrap::BuildAdd, "addtemp"),
Sub => simple_binop!(LLVMWrap::BuildSub, "subtemp"),
Mul => simple_binop!(LLVMWrap::BuildMul, "multemp"),
Div => simple_binop!(LLVMWrap::BuildUDiv, "divtemp"),
Mod => simple_binop!(LLVMWrap::BuildSRem, "remtemp"),
Less => {
let pred: LLVMValueRef =
LLVMWrap::BuildICmp(data.builder, LLVMIntPredicate::LLVMIntULT, lhs, rhs, "tmp");
LLVMWrap::BuildZExt(data.builder, pred, int_type, "temp")
}
Greater => {
let pred: LLVMValueRef =
LLVMWrap::BuildICmp(data.builder, LLVMIntPredicate::LLVMIntUGT, lhs, rhs, "tmp");
LLVMWrap::BuildZExt(data.builder, pred, int_type, "temp")
}
ref unknown => panic!("Bad operator {:?}", unknown),
}
}
}

View File

@@ -2,13 +2,13 @@ extern crate take_mut;
use std::collections::HashMap;
use std::collections::VecDeque;
use parser::{AST, Statement, Expression, Function, Callable, BinOp};
use maaru_lang::parser::{AST, Statement, Expression, Function, Callable, BinOp};
use std::rc::Rc;
use std::io::{Write, Stdout, BufWriter};
use std::convert::From;
use parser::Expression::*;
use parser::Statement::*;
use maaru_lang::parser::Expression::*;
use maaru_lang::parser::Statement::*;
type Reduction<T> = (T, Option<SideEffect>);

99
src/maaru_lang/mod.rs Normal file
View File

@@ -0,0 +1,99 @@
pub mod tokenizer;
pub mod parser;
pub mod eval;
pub mod compilation;
use schala_lib::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput, TraceArtifact, LLVMCodeString};
#[derive(Debug)]
pub struct TokenError {
pub msg: String,
}
impl TokenError {
pub fn new(msg: &str) -> TokenError {
TokenError { msg: msg.to_string() }
}
}
pub use self::eval::Evaluator as MaaruEvaluator;
pub struct Maaru<'a> {
evaluator: MaaruEvaluator<'a>
}
impl<'a> Maaru<'a> {
pub fn new() -> Maaru<'a> {
Maaru {
evaluator: MaaruEvaluator::new(None),
}
}
}
impl<'a> ProgrammingLanguageInterface for Maaru<'a> {
fn get_language_name(&self) -> String {
"Maaru".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("maaru")
}
fn evaluate_in_repl(&mut self, input: &str, options: &EvalOptions) -> LanguageOutput {
let mut output = LanguageOutput::default();
let tokens = match tokenizer::tokenize(input) {
Ok(tokens) => {
if options.debug_tokens {
output.add_artifact(TraceArtifact::new("tokens", format!("{:?}", tokens)));
}
tokens
},
Err(err) => {
output.add_output(format!("Tokenization error: {:?}\n", err.msg));
return output;
}
};
let ast = match parser::parse(&tokens, &[]) {
Ok(ast) => {
if options.debug_parse {
output.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast)));
}
ast
},
Err(err) => {
output.add_output(format!("Parse error: {:?}\n", err.msg));
return output;
}
};
let mut evaluation_output = String::new();
for s in self.evaluator.run(ast).iter() {
evaluation_output.push_str(s);
}
output.add_output(evaluation_output);
return output;
}
fn can_compile(&self) -> bool {
true
}
fn compile(&mut self, input: &str) -> LLVMCodeString {
let tokens = match tokenizer::tokenize(input) {
Ok(tokens) => tokens,
Err(err) => {
let msg = format!("Tokenization error: {:?}\n", err.msg);
panic!("{}", msg);
}
};
let ast = match parser::parse(&tokens, &[]) {
Ok(ast) => ast,
Err(err) => {
let msg = format!("Parse error: {:?}\n", err.msg);
panic!("{}", msg);
}
};
compilation::compile_ast(ast)
}
}

View File

@@ -1,5 +1,5 @@
use tokenizer::{Token, Kw, OpTok};
use tokenizer::Token::*;
use maaru_lang::tokenizer::{Token, Kw, OpTok};
use maaru_lang::tokenizer::Token::*;
use std::fmt;
use std::collections::VecDeque;

View File

@@ -5,7 +5,7 @@ use std::str::Chars;
use self::itertools::Itertools;
use std::rc::Rc;
use TokenError;
use maaru_lang::TokenError;
#[derive(Debug, Clone, PartialEq)]
pub enum Token {

View File

@@ -1,15 +1,29 @@
extern crate schala_repl;
#![feature(advanced_slice_patterns, slice_patterns, box_patterns, box_syntax)]
#![feature(plugin)]
extern crate itertools;
#[macro_use]
extern crate lazy_static;
#[macro_use]
extern crate maplit;
//extern crate maaru_lang;
//extern crate rukka_lang;
//extern crate robo_lang;
extern crate schala_lang;
use schala_repl::{ProgrammingLanguageInterface, start_repl};
mod schala_lang;
mod maaru_lang;
mod robo_lang;
mod rukka_lang;
extern crate schala_lib;
use schala_lib::{PLIGenerator, schala_main};
extern { }
fn main() {
let langs: Vec<Box<ProgrammingLanguageInterface>> = vec![Box::new(schala_lang::Schala::new())];
start_repl(langs);
let generators: Vec<PLIGenerator> = vec![
Box::new(|| { Box::new(schala_lang::Schala::new())}),
Box::new(|| { Box::new(schala_lang::autoparser::Schala::new())}),
Box::new(|| { Box::new(maaru_lang::Maaru::new())}),
Box::new(|| { Box::new(robo_lang::Robo::new())}),
Box::new(|| { Box::new(rukka_lang::Rukka::new())}),
];
schala_main(generators);
}

View File

@@ -1,10 +1,5 @@
#![feature(box_patterns)]
extern crate itertools;
extern crate schala_repl;
use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions};
use schala_lib::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput};
pub struct Robo {
}
@@ -154,5 +149,19 @@ impl ProgrammingLanguageInterface for Robo {
fn get_source_file_suffix(&self) -> String {
format!("robo")
}
fn evaluate_in_repl(&mut self, input: &str, _eval_options: &EvalOptions) -> LanguageOutput {
let mut output = LanguageOutput::default();
let tokens = match tokenize(input) {
Ok(tokens) => tokens,
Err(e) => {
output.add_output(format!("Tokenize error: {:?}", e));
return output;
}
};
output.add_output(format!("{:?}", tokens));
output
}
}

View File

@@ -1,10 +1,5 @@
#![feature(box_patterns)]
extern crate itertools;
extern crate schala_repl;
use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions};
use schala_lib::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput};
use std::iter::Peekable;
use std::vec::IntoIter;
use std::str::Chars;
@@ -72,6 +67,26 @@ impl ProgrammingLanguageInterface for Rukka {
fn get_source_file_suffix(&self) -> String {
format!("rukka")
}
fn evaluate_in_repl(&mut self, input: &str, _eval_options: &EvalOptions) -> LanguageOutput {
let mut output = LanguageOutput::default();
let sexps = match read(input) {
Err(err) => {
output.add_output(format!("Error: {}", err));
return output;
},
Ok(sexps) => sexps
};
let output_str: String = sexps.into_iter().enumerate().map(|(i, sexp)| {
match self.state.eval(sexp) {
Ok(result) => format!("{}: {}", i, result.print()),
Err(err) => format!("{} Error: {}", i, err),
}
}).intersperse(format!("\n")).collect();
output.add_output(output_str);
output
}
}
impl EvaluatorState {

View File

@@ -0,0 +1,133 @@
use schala_lib::{ProgrammingLanguageInterface, EvalOptions, TraceArtifact, LanguageOutput};
use itertools::Itertools;
use schala_lang::{tokenizing, parsing};
use self::tokenizing::*;
use self::parsing::*;
use schala_lang::tokenizing::TokenType::*;
struct AutoParser {
tokens: Vec<Token>,
}
/* BNF
* all terminals in this BNF refer to TokenType values
literal := Kw::True | Kw::False | StrLiteral | number_literal
number_literal := int_literal | float_literal
float_literal := digits float_continued
float_continued := ε | Period digits
int_literal := HexLiteral | nonhex_int
nonhex_int := BinNumberSigil+ digits
digits := (DigitGroup Underscore)+
*/
impl AutoParser {
fn new(tokens: Vec<Token>) -> AutoParser {
AutoParser { tokens: tokens.into_iter().rev().collect() }
}
fn peek(&mut self) -> TokenType {
self.tokens.last().map(|ref t| { t.token_type.clone() }).unwrap_or(TokenType::EOF)
}
fn next(&mut self) -> TokenType {
self.tokens.pop().map(|t| { t.token_type }).unwrap_or(TokenType::EOF)
}
fn parse(&mut self) -> (Result<AST, ParseError>, Vec<String>) {
let ast = self.program();
(ast, vec![])
}
fn program(&mut self) -> ParseResult<AST> {
let etype = self.literal()?;
Ok(AST(vec![Statement::ExpressionStatement(Expression(etype, None))]))
}
}
macro_rules! expand_match_var {
(($pat:pat => $e:expr)) => { $pat };
(nonterm ($pat:pat => $e:expr)) => { $pat };
}
macro_rules! expand_match_expr {
($self:ident, ($pat:pat => $e:expr)) => {
{ $self.next(); $e }
};
($self:ident, nonterm ($pat:pat => $e:expr)) => {
{ $self.next(); $e }
};
}
macro_rules! bnf_rule {
($self:ident, $type:ty, $rule:ident := $( $rule_clauses:tt )|*) => {
fn $rule(&mut $self) -> ParseResult<$type> {
Ok(match $self.peek() {
$(
expand_match_var!($rule_clauses) => expand_match_expr!($self, $rule_clauses),
)*
_ => return ParseError::new("Not found"),
})
}
};
}
impl AutoParser {
bnf_rule!(self, ExpressionType, literal :=
(Keyword(Kw::True) => ExpressionType::BoolLiteral(true)) |
(Keyword(Kw::False) => ExpressionType::BoolLiteral(false))
);
}
pub struct Schala { }
impl Schala {
pub fn new() -> Schala {
Schala { }
}
}
impl ProgrammingLanguageInterface for Schala {
fn get_language_name(&self) -> String {
"Schala-autoparser".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("schala")
}
fn evaluate_in_repl(&mut self, input: &str, options: &EvalOptions) -> LanguageOutput {
let mut output = LanguageOutput::default();
let tokens = tokenizing::tokenize(input);
if options.debug_tokens {
let token_string = tokens.iter().map(|t| format!("{:?}<L:{},C:{}>", t.token_type, t.offset.0, t.offset.1)).join(", ");
output.add_artifact(TraceArtifact::new("tokens", format!("{:?}", token_string)));
}
{
let token_errors: Vec<&String> = tokens.iter().filter_map(|t| t.get_error()).collect();
if token_errors.len() != 0 {
output.add_output(format!("Tokenization error: {:?}\n", token_errors));
return output;
}
}
let mut parser = AutoParser::new(tokens);
let ast = match parser.parse() {
(Ok(ast), trace) => {
if options.debug_parse {
output.add_artifact(TraceArtifact::new_parse_trace(trace));
output.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast)));
}
ast
},
(Err(err), trace) => {
output.add_artifact(TraceArtifact::new_parse_trace(trace));
output.add_output(format!("Parse error: {:?}\n", err.msg));
return output;
}
};
output.add_output(format!("{:?}", ast));
output
}
}

View File

@@ -0,0 +1,77 @@
use std::rc::Rc;
use std::collections::HashMap;
use schala_lang::typechecking::{Type, TypeResult, TConst};
use self::Type::*; use self::TConst::*;
#[derive(Debug, PartialEq, Clone)]
pub struct BinOp {
sigil: Rc<String>
}
impl BinOp {
pub fn from_sigil(sigil: &str) -> BinOp {
BinOp { sigil: Rc::new(sigil.to_string()) }
}
pub fn sigil(&self) -> &Rc<String> {
&self.sigil
}
pub fn get_type(&self) -> TypeResult<Type> {
let s = self.sigil.as_str();
BINOPS.get(s).map(|x| x.0.clone()).ok_or(format!("Binop {} not found", s))
}
pub fn min_precedence() -> i32 {
i32::min_value()
}
pub fn get_precedence(op: &str) -> i32 {
let default = 10_000_000;
BINOPS.get(op).map(|x| x.2.clone()).unwrap_or(default)
}
}
#[derive(Debug, PartialEq, Clone)]
pub struct PrefixOp {
sigil: Rc<String>
}
impl PrefixOp {
pub fn from_sigil(sigil: &str) -> PrefixOp {
PrefixOp { sigil: Rc::new(sigil.to_string()) }
}
pub fn sigil(&self) -> &Rc<String> {
&self.sigil
}
pub fn is_prefix(op: &str) -> bool {
PREFIX_OPS.get(op).is_some()
}
pub fn get_type(&self) -> TypeResult<Type> {
let s = self.sigil.as_str();
PREFIX_OPS.get(s).map(|x| x.0.clone()).ok_or(format!("Prefix op {} not found", s))
}
}
lazy_static! {
static ref PREFIX_OPS: HashMap<&'static str, (Type, ())> =
hashmap! {
"+" => (Func(bx!(Const(Int)), bx!(Const(Int))), ()),
"-" => (Func(bx!(Const(Int)), bx!(Const(Int))), ()),
"!" => (Func(bx!(Const(Bool)), bx!(Const(Bool))), ()),
};
}
/* the second tuple member is a placeholder for when I want to make evaluation rules tied to the
* binop definition */
lazy_static! {
static ref BINOPS: HashMap<&'static str, (Type, (), i32)> =
hashmap! {
"+" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 10),
"-" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 10),
"*" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"/" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Float))))), (), 20),
"//" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"%" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"++" => (Func(bx!(Const(StringT)), bx!(Func(bx!(Const(StringT)), bx!(Const(StringT))))), (), 30),
"^" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"&" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"|" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
};
}

317
src/schala_lang/eval.rs Normal file
View File

@@ -0,0 +1,317 @@
use std::collections::HashMap;
use std::rc::Rc;
use std::fmt::Write;
use itertools::Itertools;
use schala_lang::parsing::{AST, Statement, Declaration, Expression, Variant, ExpressionType};
use schala_lang::builtin::{BinOp, PrefixOp};
pub struct State<'a> {
parent_frame: Option<&'a State<'a>>,
values: HashMap<Rc<String>, ValueEntry>,
}
impl<'a> State<'a> {
fn insert(&mut self, name: Rc<String>, value: ValueEntry) {
self.values.insert(name, value);
}
fn lookup(&self, name: &Rc<String>) -> Option<&ValueEntry> {
match (self.values.get(name), self.parent_frame) {
(None, None) => None,
(None, Some(parent)) => parent.lookup(name),
(Some(value), _) => Some(value),
}
}
}
#[derive(Debug)]
enum ValueEntry {
Binding {
val: FullyEvaluatedExpr,
},
Function {
param_names: Vec<Rc<String>>,
body: Vec<Statement>,
}
}
type EvalResult<T> = Result<T, String>;
#[derive(Debug, PartialEq, Clone)]
enum FullyEvaluatedExpr {
UnsignedInt(u64),
SignedInt(i64),
Float(f64),
Str(String),
Bool(bool),
FuncLit(Rc<String>),
Custom {
string_rep: Rc<String>,
},
Tuple(Vec<FullyEvaluatedExpr>),
List(Vec<FullyEvaluatedExpr>)
}
impl FullyEvaluatedExpr {
fn to_string(&self) -> String {
use self::FullyEvaluatedExpr::*;
match self {
&UnsignedInt(ref n) => format!("{}", n),
&SignedInt(ref n) => format!("{}", n),
&Float(ref f) => format!("{}", f),
&Str(ref s) => format!("\"{}\"", s),
&Bool(ref b) => format!("{}", b),
&Custom { ref string_rep } => format!("{}", string_rep),
&Tuple(ref items) => {
let mut buf = String::new();
write!(buf, "(").unwrap();
for term in items.iter().map(|e| Some(e)).intersperse(None) {
match term {
Some(e) => write!(buf, "{}", e.to_string()).unwrap(),
None => write!(buf, ", ").unwrap(),
};
}
write!(buf, ")").unwrap();
buf
},
&FuncLit(ref name) => format!("<function {}>", name),
&List(ref items) => {
let mut buf = String::new();
write!(buf, "[").unwrap();
for term in items.iter().map(|e| Some(e)).intersperse(None) {
match term {
Some(e) => write!(buf, "{}", e.to_string()).unwrap(),
None => write!(buf, ", ").unwrap()
}
}
write!(buf, "]").unwrap();
buf
}
}
}
}
impl<'a> State<'a> {
pub fn new() -> State<'a> {
State { parent_frame: None, values: HashMap::new() }
}
pub fn new_with_parent(parent: &'a State<'a>) -> State<'a> {
State { parent_frame: Some(parent), values: HashMap::new() }
}
pub fn evaluate(&mut self, ast: AST) -> Vec<String> {
let mut acc = vec![];
for statement in ast.0 {
match self.eval_statement(statement) {
Ok(output) => {
if let Some(fully_evaluated) = output {
acc.push(fully_evaluated.to_string());
}
},
Err(error) => {
acc.push(format!("Eval error: {}", error));
return acc;
},
}
}
acc
}
}
impl<'a> State<'a> {
fn eval_statement(&mut self, statement: Statement) -> EvalResult<Option<FullyEvaluatedExpr>> {
Ok(match statement {
Statement::ExpressionStatement(expr) => Some(self.eval_expr(expr)?),
Statement::Declaration(decl) => { self.eval_decl(decl)?; None }
})
}
fn eval_decl(&mut self, decl: Declaration) -> EvalResult<()> {
use self::Declaration::*;
use self::Variant::*;
match decl {
FuncDecl(signature, statements) => {
let name = signature.name;
let param_names: Vec<Rc<String>> = signature.params.iter().map(|fp| fp.0.clone()).collect();
self.insert(name, ValueEntry::Function { body: statements.clone(), param_names });
},
TypeDecl(_name, body) => {
for variant in body.0.iter() {
match variant {
&UnitStruct(ref name) => self.insert(name.clone(),
ValueEntry::Binding { val: FullyEvaluatedExpr::Custom { string_rep: name.clone() } }),
&TupleStruct(ref _name, ref _args) => unimplemented!(),
&Record(ref _name, ref _fields) => unimplemented!(),
};
}
},
Binding { name, expr, ..} => {
let val = self.eval_expr(expr)?;
self.insert(name.clone(), ValueEntry::Binding { val });
},
_ => return Err(format!("Declaration evaluation not yet implemented"))
}
Ok(())
}
fn eval_expr(&mut self, expr: Expression) -> EvalResult<FullyEvaluatedExpr> {
use self::ExpressionType::*;
use self::FullyEvaluatedExpr::*;
let expr_type = expr.0;
match expr_type {
IntLiteral(n) => Ok(UnsignedInt(n)),
FloatLiteral(f) => Ok(Float(f)),
StringLiteral(s) => Ok(Str(s.to_string())),
BoolLiteral(b) => Ok(Bool(b)),
PrefixExp(op, expr) => self.eval_prefix_exp(op, expr),
BinExp(op, lhs, rhs) => self.eval_binexp(op, lhs, rhs),
Value(name) => self.eval_value(name),
TupleLiteral(expressions) => {
let mut evals = Vec::new();
for expr in expressions {
match self.eval_expr(expr) {
Ok(fully_evaluated) => evals.push(fully_evaluated),
error => return error,
}
}
Ok(Tuple(evals))
}
Call { f, arguments } => {
let mut evaled_arguments = Vec::new();
for arg in arguments.into_iter() {
evaled_arguments.push(self.eval_expr(arg)?);
}
self.eval_application(*f, evaled_arguments)
},
Index { box indexee, indexers } => {
let evaled = self.eval_expr(indexee)?;
match evaled {
Tuple(mut exprs) => {
let len = indexers.len();
if len == 1 {
let idx = indexers.into_iter().nth(0).unwrap();
match self.eval_expr(idx)? {
UnsignedInt(n) if (n as usize) < exprs.len() => Ok(exprs.drain(n as usize..).next().unwrap()),
UnsignedInt(n) => Err(format!("Index {} out of range", n)),
other => Err(format!("{:?} is not an unsigned integer", other)),
}
} else {
Err(format!("Tuple index must be one integer"))
}
},
_ => Err(format!("Bad index expression"))
}
},
ListLiteral(items) => Ok(List(items.into_iter().map(|item| self.eval_expr(item)).collect::<Result<Vec<_>,_>>()?)),
x => Err(format!("Unimplemented thing {:?}", x)),
}
}
fn eval_application(&mut self, f: Expression, arguments: Vec<FullyEvaluatedExpr>) -> EvalResult<FullyEvaluatedExpr> {
use self::ExpressionType::*;
match f {
Expression(Value(ref identifier), _) if self.is_builtin(identifier) => self.eval_builtin(identifier, arguments),
Expression(Value(identifier), _) => {
match self.lookup(&identifier) {
Some(&ValueEntry::Function { ref body, ref param_names }) => {
if arguments.len() != param_names.len() {
return Err(format!("Wrong number of arguments for the function"));
}
let mut new_state = State::new_with_parent(self);
let sub_ast = body.clone();
for (param, val) in param_names.iter().zip(arguments.into_iter()) {
new_state.insert(param.clone(), ValueEntry::Binding { val });
}
let mut ret: Option<FullyEvaluatedExpr> = None;
for statement in sub_ast.into_iter() {
ret = new_state.eval_statement(statement)?;
}
Ok(ret.unwrap_or(FullyEvaluatedExpr::Custom { string_rep: Rc::new("()".to_string()) }))
},
_ => Err(format!("Function {} not found", identifier)),
}
},
x => Err(format!("Trying to apply {:?} which is not a function", x)),
}
}
fn is_builtin(&self, name: &Rc<String>) -> bool {
match &name.as_ref()[..] {
"print" | "println" => true,
_ => false
}
}
fn eval_builtin(&mut self, name: &Rc<String>, args: Vec<FullyEvaluatedExpr>) -> EvalResult<FullyEvaluatedExpr> {
use self::FullyEvaluatedExpr::*;
match &name.as_ref()[..] {
"print" => {
for arg in args {
print!("{}", arg.to_string());
}
Ok(Tuple(vec![]))
},
"println" => {
for arg in args {
println!("{}", arg.to_string());
}
Ok(Tuple(vec![]))
},
_ => unreachable!()
}
}
fn eval_value(&mut self, name: Rc<String>) -> EvalResult<FullyEvaluatedExpr> {
use self::ValueEntry::*;
match self.lookup(&name) {
None => return Err(format!("Value {} not found", *name)),
Some(lookup) => match lookup {
&Binding { ref val } => Ok(val.clone()),
&Function { .. } => Ok(FullyEvaluatedExpr::FuncLit(name.clone()))
}
}
}
fn eval_binexp(&mut self, op: BinOp, lhs: Box<Expression>, rhs: Box<Expression>) -> EvalResult<FullyEvaluatedExpr> {
use self::FullyEvaluatedExpr::*;
let evaled_lhs = self.eval_expr(*lhs)?;
let evaled_rhs = self.eval_expr(*rhs)?;
let sigil = op.sigil();
//let sigil: &str = op.sigil().as_ref().as_str();
Ok(match (sigil.as_str(), evaled_lhs, evaled_rhs) {
("+", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l + r),
("++", Str(s1), Str(s2)) => Str(format!("{}{}", s1, s2)),
("-", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l - r),
("*", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l * r),
("/", UnsignedInt(l), UnsignedInt(r)) => Float((l as f64)/ (r as f64)),
("//", UnsignedInt(l), UnsignedInt(r)) => if r == 0 {
return Err(format!("Runtime error: divide by zero"));
} else {
UnsignedInt(l / r)
},
("%", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l % r),
("^", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l ^ r),
("&", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l & r),
("|", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l | r),
_ => return Err(format!("Runtime error: not yet implemented")),
})
}
fn eval_prefix_exp(&mut self, op: PrefixOp, expr: Box<Expression>) -> EvalResult<FullyEvaluatedExpr> {
use self::FullyEvaluatedExpr::*;
let evaled_expr = self.eval_expr(*expr)?;
let sigil = op.sigil();
Ok(match (sigil.as_str(), evaled_expr) {
("!", Bool(true)) => Bool(false),
("!", Bool(false)) => Bool(true),
("-", UnsignedInt(n)) => SignedInt(-1*(n as i64)),
("-", SignedInt(n)) => SignedInt(-1*(n as i64)),
("+", SignedInt(n)) => SignedInt(n),
("+", UnsignedInt(n)) => UnsignedInt(n),
_ => return Err(format!("Runtime error: not yet implemented")),
})
}
}

104
src/schala_lang/mod.rs Normal file
View File

@@ -0,0 +1,104 @@
use itertools::Itertools;
use schala_lib::{ProgrammingLanguageInterface, EvalOptions, TraceArtifact, LanguageOutput};
macro_rules! bx {
($e:expr) => { Box::new($e) }
}
pub mod autoparser;
mod builtin;
mod tokenizing;
mod parsing;
mod typechecking;
mod eval;
use self::typechecking::{TypeContext};
pub struct Schala {
state: eval::State<'static>,
type_context: TypeContext
}
impl Schala {
pub fn new() -> Schala {
Schala {
state: eval::State::new(),
type_context: TypeContext::new(),
}
}
}
impl ProgrammingLanguageInterface for Schala {
fn get_language_name(&self) -> String {
"Schala".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("schala")
}
fn evaluate_in_repl(&mut self, input: &str, options: &EvalOptions) -> LanguageOutput {
let mut output = LanguageOutput::default();
let tokens = tokenizing::tokenize(input);
if options.debug_tokens {
let token_string = tokens.iter().map(|t| format!("{:?}<L:{},C:{}>", t.token_type, t.offset.0, t.offset.1)).join(", ");
output.add_artifact(TraceArtifact::new("tokens", format!("{:?}", token_string)));
}
{
let token_errors: Vec<&String> = tokens.iter().filter_map(|t| t.get_error()).collect();
if token_errors.len() != 0 {
output.add_output(format!("Tokenization error: {:?}\n", token_errors));
return output;
}
}
let ast = match parsing::parse(tokens) {
(Ok(ast), trace) => {
if options.debug_parse {
output.add_artifact(TraceArtifact::new_parse_trace(trace));
output.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast)));
}
ast
},
(Err(err), trace) => {
output.add_artifact(TraceArtifact::new_parse_trace(trace));
output.add_output(format!("Parse error: {:?}\n", err.msg));
return output;
}
};
match self.type_context.add_top_level_types(&ast) {
Ok(()) => (),
Err(msg) => {
output.add_artifact(TraceArtifact::new("type_check", msg));
//return output
}
};
if options.debug_symbol_table {
let text = self.type_context.debug_symbol_table();
output.add_artifact(TraceArtifact::new("symbol_table", text));
}
match self.type_context.type_check_ast(&ast) {
Ok(ty) => {
output.add_artifact(TraceArtifact::new("type_check", format!("{:?}", ty)));
},
Err(msg) => {
output.add_artifact(TraceArtifact::new("type_check", msg));
/*
output.add_output(format!("Type error"));
return output;
*/
}
}
let evaluation_outputs = self.state.evaluate(ast);
let text_output: String = evaluation_outputs.into_iter().intersperse(format!("\n")).collect();
output.add_output(text_output);
return output;
}
}

1234
src/schala_lang/parsing.rs Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -5,17 +5,16 @@ use std::iter::{Iterator, Peekable};
use std::fmt;
#[derive(Debug, PartialEq, Clone)]
pub enum TokenKind {
pub enum TokenType {
Newline, Semicolon,
LParen, RParen,
LSquareBracket, RSquareBracket,
LAngleBracket, RAngleBracket,
LCurlyBrace, RCurlyBrace,
Pipe, Backslash,
Pipe,
Comma, Period, Colon, Underscore,
Slash,
Operator(Rc<String>),
DigitGroup(Rc<String>), HexLiteral(Rc<String>), BinNumberSigil,
@@ -27,9 +26,9 @@ pub enum TokenKind {
Error(String),
}
use self::TokenKind::*;
use self::TokenType::*;
impl fmt::Display for TokenKind {
impl fmt::Display for TokenType {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
&Operator(ref s) => write!(f, "Operator({})", **s),
@@ -45,15 +44,14 @@ impl fmt::Display for TokenKind {
#[derive(Debug, Clone, Copy, PartialEq)]
pub enum Kw {
If, Then, Else,
Is,
If, Else,
Func,
For, While,
Const, Let, In,
Mut,
For,
Match,
Var, Const, Let, In,
Return,
Alias, Type, SelfType, SelfIdent,
Interface, Impl,
Trait, Impl,
True, False,
Module
}
@@ -62,22 +60,20 @@ lazy_static! {
static ref KEYWORDS: HashMap<&'static str, Kw> =
hashmap! {
"if" => Kw::If,
"then" => Kw::Then,
"else" => Kw::Else,
"is" => Kw::Is,
"fn" => Kw::Func,
"for" => Kw::For,
"while" => Kw::While,
"match" => Kw::Match,
"var" => Kw::Var,
"const" => Kw::Const,
"let" => Kw::Let,
"in" => Kw::In,
"mut" => Kw::Mut,
"return" => Kw::Return,
"alias" => Kw::Alias,
"type" => Kw::Type,
"Self" => Kw::SelfType,
"self" => Kw::SelfIdent,
"interface" => Kw::Interface,
"trait" => Kw::Trait,
"impl" => Kw::Impl,
"true" => Kw::True,
"false" => Kw::False,
@@ -87,73 +83,49 @@ lazy_static! {
#[derive(Debug, Clone)]
pub struct Token {
pub kind: TokenKind,
pub line_num: usize,
pub char_num: usize
pub token_type: TokenType,
pub offset: (usize, usize),
}
impl Token {
pub fn get_error(&self) -> Option<String> {
match self.kind {
TokenKind::Error(ref s) => Some(s.clone()),
pub fn get_error(&self) -> Option<&String> {
match self.token_type {
TokenType::Error(ref s) => Some(s),
_ => None,
}
}
pub fn to_string_with_metadata(&self) -> String {
format!("{}(L:{},c:{})", self.kind, self.line_num, self.char_num)
}
pub fn get_kind(&self) -> TokenKind {
self.kind.clone()
format!("{}(L:{},c:{})", self.token_type, self.offset.0, self.offset.1)
}
}
const OPERATOR_CHARS: [char; 18] = ['!', '$', '%', '&', '*', '+', '-', '.', ':', '<', '>', '=', '?', '@', '^', '|', '~', '`'];
const OPERATOR_CHARS: [char; 19] = ['!', '$', '%', '&', '*', '+', '-', '.', '/', ':', '<', '>', '=', '?', '@', '^', '|', '~', '`'];
fn is_operator(c: &char) -> bool {
OPERATOR_CHARS.iter().any(|x| x == c)
}
type CharData = (usize, usize, char);
type CharIter<I: Iterator<Item=(usize,usize,char)>> = Peekable<I>;
pub fn tokenize(input: &str) -> Vec<Token> {
let mut tokens: Vec<Token> = Vec::new();
let mut input = input.lines().enumerate()
.intersperse((0, "\n"))
.flat_map(|(line_idx, ref line)| {
line.chars().enumerate().map(move |(ch_idx, ch)| (line_idx, ch_idx, ch))
})
.peekable();
}).peekable();
while let Some((line_num, char_num, c)) = input.next() {
let cur_tok_kind = match c {
'/' => match input.peek().map(|t| t.2) {
Some('/') => {
while let Some((line_idx, ch_idx, c)) = input.next() {
let cur_tok_type = match c {
'#' => {
if let Some(&(_, _, '{')) = input.peek() {
} else {
while let Some((_, _, c)) = input.next() {
if c == '\n' {
break;
}
}
continue;
},
Some('*') => {
input.next();
let mut comment_level = 1;
while let Some((_, _, c)) = input.next() {
if c == '*' && input.peek().map(|t| t.2) == Some('/') {
input.next();
comment_level -= 1;
} else if c == '/' && input.peek().map(|t| t.2) == Some('*') {
input.next();
comment_level += 1;
}
if comment_level == 0 {
break;
}
}
continue;
},
_ => Slash
}
continue;
},
c if c.is_whitespace() && c != '\n' => continue,
'\n' => Newline, ';' => Semicolon,
@@ -162,18 +134,17 @@ pub fn tokenize(input: &str) -> Vec<Token> {
'{' => LCurlyBrace, '}' => RCurlyBrace,
'[' => LSquareBracket, ']' => RSquareBracket,
'"' => handle_quote(&mut input),
'\\' => Backslash,
c if c.is_digit(10) => handle_digit(c, &mut input),
c if c.is_alphabetic() || c == '_' => handle_alphabetic(c, &mut input),
c if c.is_alphabetic() || c == '_' => handle_alphabetic(c, &mut input), //TODO I'll probably have to rewrite this if I care about types being uppercase, also type parameterization
c if is_operator(&c) => handle_operator(c, &mut input),
unknown => Error(format!("Unexpected character: {}", unknown)),
};
tokens.push(Token { kind: cur_tok_kind, line_num, char_num });
tokens.push(Token { token_type: cur_tok_type, offset: (line_idx, ch_idx) });
}
tokens
}
fn handle_digit(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
fn handle_digit<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut CharIter<I>) -> TokenType {
if c == '0' && input.peek().map_or(false, |&(_, _, c)| { c == 'x' }) {
input.next();
let rest: String = input.peeking_take_while(|&(_, _, ref c)| c.is_digit(16) || *c == '_').map(|(_, _, c)| { c }).collect();
@@ -188,7 +159,7 @@ fn handle_digit(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>) ->
}
}
fn handle_quote(input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
fn handle_quote<I: Iterator<Item=(usize,usize,char)>>(input: &mut CharIter<I>) -> TokenType {
let mut buf = String::new();
loop {
match input.next().map(|(_, _, c)| { c }) {
@@ -207,22 +178,22 @@ fn handle_quote(input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind
}
},
Some(c) => buf.push(c),
None => return TokenKind::Error(format!("Unclosed string")),
None => return TokenType::Error(format!("Unclosed string")),
}
}
TokenKind::StrLiteral(Rc::new(buf))
TokenType::StrLiteral(Rc::new(buf))
}
fn handle_alphabetic(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
fn handle_alphabetic<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut CharIter<I>) -> TokenType {
let mut buf = String::new();
buf.push(c);
if c == '_' && input.peek().map(|&(_, _, c)| { !c.is_alphabetic() }).unwrap_or(true) {
return TokenKind::Underscore
return TokenType::Underscore
}
loop {
match input.peek().map(|&(_, _, c)| { c }) {
Some(c) if c.is_alphanumeric() || c == '_' => {
Some(c) if c.is_alphanumeric() => {
input.next();
buf.push(c);
},
@@ -231,12 +202,12 @@ fn handle_alphabetic(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>
}
match KEYWORDS.get(buf.as_str()) {
Some(kw) => TokenKind::Keyword(*kw),
None => TokenKind::Identifier(Rc::new(buf)),
Some(kw) => TokenType::Keyword(*kw),
None => TokenType::Identifier(Rc::new(buf)),
}
}
fn handle_operator(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
fn handle_operator<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut CharIter<I>) -> TokenType {
match c {
'<' | '>' | '|' | '.' => {
let ref next = input.peek().map(|&(_, _, c)| { c });
@@ -254,34 +225,17 @@ fn handle_operator(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>)
};
let mut buf = String::new();
if c == '`' {
loop {
match input.peek().map(|&(_, _, c)| { c }) {
Some(c) if c.is_alphabetic() || c == '_' => {
input.next();
buf.push(c);
},
Some('`') => {
input.next();
break;
},
_ => break
}
}
} else {
buf.push(c);
loop {
match input.peek().map(|&(_, _, c)| { c }) {
Some(c) if is_operator(&c) => {
input.next();
buf.push(c);
},
_ => break
}
buf.push(c);
loop {
match input.peek().map(|&(_, _, c)| { c }) {
Some(c) if is_operator(&c) => {
input.next();
buf.push(c);
},
_ => break
}
}
TokenKind::Operator(Rc::new(buf))
TokenType::Operator(Rc::new(buf))
}
#[cfg(test)]
@@ -293,32 +247,18 @@ mod schala_tokenizer_tests {
macro_rules! ident { ($ident:expr) => { Identifier(Rc::new($ident.to_string())) } }
macro_rules! op { ($ident:expr) => { Operator(Rc::new($ident.to_string())) } }
#[test]
fn tokens() {
let a = tokenize("let a: A<B> = c ++ d");
let token_kinds: Vec<TokenKind> = a.into_iter().map(move |t| t.kind).collect();
assert_eq!(token_kinds, vec![Keyword(Let), ident!("a"), Colon, ident!("A"),
let token_types: Vec<TokenType> = a.into_iter().map(move |t| t.token_type).collect();
assert_eq!(token_types, vec![Keyword(Let), ident!("a"), Colon, ident!("A"),
LAngleBracket, ident!("B"), RAngleBracket, op!("="), ident!("c"), op!("++"), ident!("d")]);
}
#[test]
fn underscores() {
let token_kinds: Vec<TokenKind> = tokenize("4_8").into_iter().map(move |t| t.kind).collect();
assert_eq!(token_kinds, vec![digit!("4"), Underscore, digit!("8")]);
let token_kinds2: Vec<TokenKind> = tokenize("aba_yo").into_iter().map(move |t| t.kind).collect();
assert_eq!(token_kinds2, vec![ident!("aba_yo")]);
}
#[test]
fn comments() {
let token_kinds: Vec<TokenKind> = tokenize("1 + /* hella /* bro */ */ 2").into_iter().map(move |t| t.kind).collect();
assert_eq!(token_kinds, vec![digit!("1"), op!("+"), digit!("2")]);
}
#[test]
fn backtick_operators() {
let token_kinds: Vec<TokenKind> = tokenize("1 `plus` 2").into_iter().map(move |t| t.kind).collect();
assert_eq!(token_kinds, vec![digit!("1"), op!("plus"), digit!("2")]);
let token_types: Vec<TokenType> = tokenize("4_8").into_iter().map(move |t| t.token_type).collect();
assert_eq!(token_types, vec![digit!("4"), Underscore, digit!("8")]);
}
}

View File

@@ -2,7 +2,7 @@ use std::collections::HashMap;
use std::rc::Rc;
use parsing::{AST, Statement, Declaration, Signature, Expression, ExpressionType, Operation, Variant, TypeName, TypeSingletonName};
use schala_lang::parsing::{AST, Statement, Declaration, Signature, Expression, ExpressionType, Operation, Variant, TypeName, TypeSingletonName};
// from Niko's talk
/* fn type_check(expression, expected_ty) -> Ty {

View File

@@ -0,0 +1,254 @@
use std::rc::Rc;
use std::collections::HashMap;
use std::char;
use std::fmt;
use std::fmt::Write;
use itertools::Itertools;
use schala_lang::parsing;
pub struct TypeContext {
type_var_count: u64,
bindings: HashMap<Rc<String>, Type>,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Type {
Const(TConst),
Sum(Vec<Type>),
Func(Box<Type>, Box<Type>),
UVar(String),
EVar(u64),
Void
}
impl fmt::Display for Type {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use self::Type::*;
match self {
&Const(ref c) => write!(f, "{:?}", c),
&Sum(ref types) => {
write!(f, "(")?;
for item in types.iter().map(|ty| Some(ty)).intersperse(None) {
match item {
Some(ty) => write!(f, "{}", ty)?,
None => write!(f, ",")?,
};
}
write!(f, ")")
},
&Func(ref a, ref b) => write!(f, "{} -> {}", a, b),
&UVar(ref s) => write!(f, "{}_u", s),
&EVar(ref n) => write!(f, "{}_e", n),
&Void => write!(f, "Void")
}
}
}
#[derive(Default)]
struct UVarGenerator {
n: u32,
}
impl UVarGenerator {
fn new() -> UVarGenerator {
UVarGenerator::default()
}
fn next(&mut self) -> Type {
//TODO handle this in the case where someone wants to make a function with more than 26 variables
let s = format!("{}", unsafe { char::from_u32_unchecked(self.n + ('a' as u32)) });
self.n += 1;
Type::UVar(s)
}
}
#[derive(Debug, PartialEq, Clone)]
pub enum TConst {
Unit,
Int,
Float,
StringT,
Bool,
Custom(String),
}
impl parsing::TypeName {
fn to_type(&self) -> TypeResult<Type> {
use self::parsing::TypeSingletonName;
use self::parsing::TypeName::*;
use self::Type::*; use self::TConst::*;
Ok(match self {
&Tuple(_) => return Err(format!("Tuples not yet implemented")),
&Singleton(ref name) => match name {
&TypeSingletonName { ref name, .. } => match &name[..] {
"Int" => Const(Int),
"Float" => Const(Float),
"Bool" => Const(Bool),
"String" => Const(StringT),
n => Const(Custom(n.to_string()))
}
}
})
}
}
pub type TypeResult<T> = Result<T, String>;
impl TypeContext {
pub fn new() -> TypeContext {
TypeContext { bindings: HashMap::new(), type_var_count: 0 }
}
pub fn fresh(&mut self) -> Type {
let ret = self.type_var_count;
self.type_var_count += 1;
Type::EVar(ret)
}
}
impl TypeContext {
pub fn add_top_level_types(&mut self, ast: &parsing::AST) -> TypeResult<()> {
use self::parsing::TypeName;
use self::parsing::Declaration::*;
use self::Type::*;
for statement in ast.0.iter() {
if let &self::parsing::Statement::Declaration(ref decl) = statement {
match decl {
&FuncSig(ref signature) | &FuncDecl(ref signature, _) => {
let mut uvar_gen = UVarGenerator::new();
let mut ty: Type = signature.type_anno.as_ref().map(|name: &TypeName| name.to_type()).unwrap_or_else(|| {Ok(uvar_gen.next())} )?;
for &(_, ref type_name) in signature.params.iter().rev() {
let arg_type = type_name.as_ref().map(|name| name.to_type()).unwrap_or_else(|| {Ok(uvar_gen.next())} )?;
ty = Func(bx!(arg_type), bx!(ty));
}
self.bindings.insert(signature.name.clone(), ty);
},
_ => ()
}
}
}
Ok(())
}
pub fn debug_symbol_table(&self) -> String {
let mut output = format!("Symbols\n");
for (sym, ty) in &self.bindings {
write!(output, "{} : {}\n", sym, ty).unwrap();
}
output
}
}
impl TypeContext {
pub fn type_check_ast(&mut self, ast: &parsing::AST) -> TypeResult<Type> {
use self::Type::*; use self::TConst::*;
let mut ret_type = Const(Unit);
for statement in ast.0.iter() {
ret_type = self.type_check_statement(statement)?;
}
Ok(ret_type)
}
fn type_check_statement(&mut self, statement: &parsing::Statement) -> TypeResult<Type> {
use self::parsing::Statement::*;
match statement {
&ExpressionStatement(ref expr) => self.infer(expr),
&Declaration(ref decl) => self.add_declaration(decl),
}
}
fn add_declaration(&mut self, decl: &parsing::Declaration) -> TypeResult<Type> {
use self::parsing::Declaration::*;
use self::Type::*;
match decl {
&Binding { ref name, ref expr, .. } => {
let ty = self.infer(expr)?;
self.bindings.insert(name.clone(), ty);
},
_ => return Err(format!("other formats not done"))
}
Ok(Void)
}
fn infer(&mut self, expr: &parsing::Expression) -> TypeResult<Type> {
use self::parsing::Expression;
match expr {
&Expression(ref e, Some(ref anno)) => {
let anno_ty = anno.to_type()?;
let ty = self.infer_exprtype(&e)?;
self.unify(ty, anno_ty)
},
&Expression(ref e, None) => self.infer_exprtype(e)
}
}
fn infer_exprtype(&mut self, expr: &parsing::ExpressionType) -> TypeResult<Type> {
use self::parsing::ExpressionType::*;
use self::Type::*; use self::TConst::*;
match expr {
&IntLiteral(_) => Ok(Const(Int)),
&FloatLiteral(_) => Ok(Const(Float)),
&StringLiteral(_) => Ok(Const(StringT)),
&BoolLiteral(_) => Ok(Const(Bool)),
&BinExp(ref op, ref lhs, ref rhs) => { /* remember there are both the haskell convention talk and the write you a haskell ways to do this! */
match op.get_type()? {
Func(box t1, box Func(box t2, box t3)) => {
let lhs_ty = self.infer(lhs)?;
let rhs_ty = self.infer(rhs)?;
self.unify(t1, lhs_ty)?;
self.unify(t2, rhs_ty)?;
Ok(t3)
},
other => Err(format!("{:?} is not a binary function type", other))
}
},
&PrefixExp(ref op, ref expr) => match op.get_type()? {
Func(box t1, box t2) => {
let expr_ty = self.infer(expr)?;
self.unify(t1, expr_ty)?;
Ok(t2)
},
other => Err(format!("{:?} is not a prefix op function type", other))
},
&Value(ref name) => {
match self.bindings.get(name) {
Some(ty) => Ok(ty.clone()),
None => Err(format!("No binding found for variable: {}", name)),
}
},
&Call { ref f, ref arguments } => {
let mut tf = self.infer(f)?;
for arg in arguments.iter() {
match tf {
Func(box t, box rest) => {
let t_arg = self.infer(arg)?;
self.unify(t, t_arg)?;
tf = rest;
},
other => return Err(format!("Function call failed to unify; last type: {:?}", other)),
}
}
Ok(tf)
},
&TupleLiteral(ref expressions) => {
let mut types = vec![];
for expr in expressions {
types.push(self.infer(expr)?);
}
Ok(Sum(types))
},
/*
Index {
indexee: Box<Expression>,
indexers: Vec<Expression>,
},
IfExpression(Box<Expression>, Vec<Statement>, Option<Vec<Statement>>),
MatchExpression(Box<Expression>, Vec<MatchArm>),
ForExpression
*/
_ => Err(format!("Type not yet implemented"))
}
}
fn unify(&mut self, t1: Type, t2: Type) -> TypeResult<Type> {
use self::Type::*;// use self::TConst::*;
match (t1, t2) {
(Const(ref a), Const(ref b)) if a == b => Ok(Const(a.clone())),
(a, b) => Err(format!("Types {:?} and {:?} don't unify", a, b))
}
}
}