Compare commits

..

252 Commits

Author SHA1 Message Date
greg
38eeec5718 Use lib flag to get debug 2018-04-28 20:44:42 -07:00
greg
431c0fdf8c Starting to try and annotate real compiler passes 2018-04-28 15:46:11 -07:00
greg
9015cbee21 More experimentation 2018-04-28 15:35:04 -07:00
greg
bf7533cdbe Some experimentation 2018-04-28 03:31:53 -07:00
greg
2c79984678 Starting codegen work 2018-04-28 00:08:16 -07:00
greg
82cfd3f03d Adding proc macro for codegen
This should hopefully make the compiler pass thing I want to do possible
2018-04-27 02:19:09 -07:00
greg
9547275355 Backtick operators supported in tokenizing 2018-04-25 03:01:41 -07:00
greg
2dae8d6629 Show artifacts on failure 2018-04-24 23:11:04 -07:00
greg
056ca1c162 TODO note 2018-04-24 20:31:17 -07:00
greg
00ace0b682 Put this stuff back
More complicated to separate out repl than I thought
2018-04-24 20:31:17 -07:00
greg
5fcf0815c0 Start refactoring how interpreter options are split up 2018-04-24 20:31:17 -07:00
greg
748250d383 Swap sigil from . to : 2018-04-24 20:31:17 -07:00
greg
87cc14356d Want to change 'trait' to 'interface' 2018-04-24 20:31:17 -07:00
greg
7004960434 Fix history adding 2018-04-24 20:31:17 -07:00
greg
f5aff0b276 Trait -> Interface 2018-04-24 16:30:17 -07:00
greg
1d6f104b12 Kill old advanced_slice_patterns 2018-04-03 23:24:21 -07:00
greg
c11ae3b50d Debug stages from command line 2018-03-27 00:50:31 -07:00
greg
7f21b70e3f Make REPL interpreter return a value 2018-03-25 00:11:18 -07:00
greg
0b2e2cf68b Kill unused items in schala-repl 2018-03-24 23:28:00 -07:00
greg
1129d97603 Start killing old code in language 2018-03-24 19:02:16 -07:00
greg
e9c538da49 Fix interspersing of newlines in tokenizer infra 2018-03-24 18:38:28 -07:00
greg
3295242115 Show err output when evaluating non-interactively 2018-03-24 17:27:54 -07:00
greg
4bea717e72 Colored repl command output 2018-03-24 15:14:24 -07:00
greg
20f879d68d Hook schala function up to debug booleans
Not sure if I like this API, but eh, it's what I've got
2018-03-24 13:41:54 -07:00
greg
20cf877d21 Add back color 2018-03-24 13:20:10 -07:00
greg
df51a1e04a rename schala_main -> repl_main 2018-03-23 19:04:32 -07:00
greg
1c7574150e Add version string 2018-03-23 18:56:09 -07:00
greg
36b3f58f77 Get rid of all top-level dependencies 2018-03-23 18:48:15 -07:00
greg
f181e2f284 move schala into separate crate 2018-03-23 18:43:43 -07:00
greg
34086b3b2b Color in terminal error output 2018-03-22 03:39:42 -07:00
greg
fd4f5e17df Move robo to separate crate 2018-03-21 01:46:11 -07:00
greg
8ca5a77174 Move rukka to crate 2018-03-21 01:43:43 -07:00
greg
78a250bcba Move maaru into separate crate 2018-03-20 23:29:56 -07:00
greg
31fc751799 Rename schala-lib -> schala-repl 2018-03-20 21:17:46 -07:00
greg
e99479ffcc Removed (for now) LLVMCodeString 2018-03-20 21:13:34 -07:00
greg
6fcc7ded59 new thing compiles 2018-03-20 20:29:57 -07:00
greg
de073a6d9b Switch over schala to new system 2018-03-19 22:57:54 -07:00
greg
638afd47cc Update schala example code 2018-03-17 23:38:37 -07:00
greg
5ab7c2d254 Nested comments 2018-03-17 22:25:43 -07:00
greg
7a606980cb Changing comments to use //, /* 2018-03-17 19:12:58 -07:00
greg
ad8d2b22cd Starting to improve infrastrucutre for lang output
To make repl vs non-repl output better
2018-03-11 14:53:08 -07:00
greg
57f56168c5 Hacky fix for displaying error output non-interactively 2018-03-11 12:56:51 -07:00
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
68 changed files with 3855 additions and 12328 deletions

2
.gitignore vendored
View File

@ -1,4 +1,4 @@
Cargo.lock
target target
.schala_repl .schala_repl
.schala_history .schala_history
rusty-tags.vi

1258
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@ -2,17 +2,15 @@
name = "schala" name = "schala"
version = "0.1.0" version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"] authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2018"
resolver = "2"
[dependencies] [dependencies]
getopts = "0.2.21"
schala-repl = { path = "schala-repl" } schala-repl = { path = "schala-repl" }
schala-codegen = { path = "schala-codegen" }
maaru-lang = { path = "maaru" }
rukka-lang = { path = "rukka" }
robo-lang = { path = "robo" }
schala-lang = { path = "schala-lang" } schala-lang = { path = "schala-lang" }
# maaru-lang = { path = "maaru" }
# rukka-lang = { path = "rukka" }
# robo-lang = { path = "robo" }
[build-dependencies] [build-dependencies]
includedir_codegen = "0.2.0" 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

@ -1,46 +1,21 @@
# Schala - a programming language meta-interpreter # Schala - a programming language meta-interpreter
Schala is a Rust framework written to make it easy to create and experiment Schala is a Rust framework written to make it easy to
with multiple toy programming languages. It provides a cross-language REPL and create and experiment with toy programming languages. It provides
provisions for tokenizing text, parsing tokens, evaluating an abstract syntax a common REPL, and a trait `ProgrammingLanguage` with provisions
tree, and other tasks that are common to all programming languages, as well as for tokenizing text, parsing tokens, evaluating an abstract syntax tree,
sharing state between multiple programming languages. and other tasks that are common to all programming languages.
Schala is implemented as a Rust library `schala-repl`, which provides a `Repl` Schala is implemented as a Rust library `schala_lib`, which provides a
data structure that takes in a value implementing the `schala_main` function. This function serves as the main loop of the REPL, if run
`ProgrammingLanguageInterface` trait. Individual programming language interactively, or otherwise reads and interprets programming language source
implementations are Rust types that implement `ProgrammingLanguageInterface` files. It expects as input a vector of `PLIGenerator`, which is a type representing
and store whatever persistent state is relevant to that language. 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.
## About
## Running
Run schala with the normal `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.
### Examples
Try running the following `schala-lang` code example in the REPL:
```
>> 1 + 1
(Total time)=> 736.368µs
=> 2
>> fn foo(x) { x + 10 }
(Total time)=> 772.496µs
=>
>> foo(0)
(Total time)=> 593.591µs
=> 10
>> 5 + foo(1)
(Total time)=> 1.119916ms
=> 16
>>
```
## History
Schala started out life as an experiment in writing a Javascript-like Schala started out life as an experiment in writing a Javascript-like
programming language that would never encounter any kind of runtime value programming language that would never encounter any kind of runtime value
@ -58,18 +33,18 @@ creating a language name confusingly close to Scala. The naming scheme for
languages implemented with the Schala meta-interpreter is Chrono Trigger languages implemented with the Schala meta-interpreter is Chrono Trigger
characters. characters.
Schala and languages implemented with it are incomplete alpha software and are Schala is incomplete alpha software and is not ready for public release.
not ready for public release.
## Languages implemented using the meta-interpreter ## Languages implemented using the meta-interpreter
* The eponymous *Schala* language is a work-in-progress general purpose * The eponymous *Schala* language is an interpreted/compiled scripting langauge,
programming language with static typing and algebraic data types. Its design designed to be relatively simple, but with a reasonably sophisticated type
goals include having a very straightforward implemenation and being syntactically system.
minimal.
* *Maaru* is a very simple dynamically-typed scripting language, with the semantics * *Maaru* was the original Schala (since renamed to free up the name *Schala*
that all runtime errors return a `null` value rather than fail. 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 * *Robo* is an experiment in creating a lazy, functional, strongly-typed language
much like Haskell much like Haskell
@ -81,30 +56,22 @@ much like Haskell
Here's a partial list of resources I've made use of in the process Here's a partial list of resources I've made use of in the process
of learning how to write a programming language. of learning how to write a programming language.
### General
* http://thume.ca/2019/04/18/writing-a-compiler-in-rust/
### Type-checking ### Type-checking
* https://skillsmatter.com/skillscasts/10868-inside-the-rust-compiler 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 ### Evaluation
*Understanding Computation*, Tom Stuart, O'Reilly 2013
* _Understanding Computation_, Tom Stuart, O'Reilly 2013 *Basics of Compiler Design*, Torben Mogensen
* _Basics of Compiler Design_, Torben Mogensen
### Parsing ### Parsing
* http://journal.stuffwithstuff.com/2011/03/19/pratt-parsers-expression-parsing-made-easy/ 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/) [Crafting Interpreters](http://www.craftinginterpreters.com/)
### LLVM ### LLVM
* http://blog.ulysse.io/2016/07/03/llvm-getting-started.html 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/

217
TODO.md
View File

@ -1,106 +1,29 @@
# Immediate TODOs / General Code Cleanup
## Parsing # TODO Items
* cf. https://siraben.dev/2022/03/22/tree-sitter-linter.html write a tree-sitter parser for Schala
* Create a macro system, perhaps c.f. Crystal's?
* Macro system should be able to implement:
* printf-style variadic arguments
* something like the Rust/Haskell `Derive` construct
* doing useful things with all variants of an enum
* (e.g. what https://matklad.github.io//2022/03/26/self-modifying-code.html tries to solve)
## Testing - sketch of an idea for the REPL:
-each compiler pass should be a (procedural?) macro like
compiler_pass!("parse", dataproducts: ["ast", "parse_tree"], {
match parsing::parse(INPUT) {
Ok(
PASS.add_artifact(
}
* Make an automatic (macro-based?) system for numbering compiler errors, this should be every type of error -should have an Idris-like `cast To From` function
## Symbols - REPL:
- want to be able to do things like `:doc Identifier`, and have the language load up these definitions to the REPL
* Add some good printf-debugging impls for SymbolTable-related items
* the symbol table should probably *only* be for global definitions (maybe rename it to reflect this?)
* dealing with variable lookup w/in functions/closures should probably happen in AST -> ReducedAST
* b/c that's where we go from a string name to a canonical ID (for e.g. 2nd param in 3rd enclosing scope)
* In fact to prove this works, the symbol table shoudl _parallelize_ the process of checking subscopes for local items
* Old notes on a plan of attack:
1. modify visitor so it can handle scopes
-this is needed both to handle import scope correctly
-and also to support making FQSNs aware of function parameters
2. Once FQSNs are aware of function parameters, most of the Rc<String> things in eval.rs can go away
## Typechecking
* make a type to represent types rather than relying on string comparisons
* look at https://rickyhan.com/jekyll/update/2018/05/26/hindley-milner-tutorial-rust.html
## General code cleanup
* standardize on an error type that isn't String
* implement a visitor pattern for the use of scope_resolver
* maybe implement this twice: 1) the value-returning, no-default one in the haoyi blogpost,
* look at
* https://gitlab.haskell.org/ghc/ghc/wikis/pattern-synonyms
* the non-value-returning, default one like in rustc (cf. https://github.com/rust-unofficial/patterns/blob/master/patterns/visitor.md)
# Longer-term Ideas * 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)
## Language Syntax * Share state between programming languages
* the `type` declaration should have some kind of GADT-like syntax * 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
* syntactic sugar for typestates? (cf. https://rustype.github.io/notes/notes/rust-typestate-series/rust-typestate-part-1.html )
* use `let` sigil to indicate a variable in a pattern explicitly:
``` * another idea, allow:
q is MyStruct(let a, Chrono::Trigga) then {
// a is in scope here
}
```
* 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
* what if there was something like React jsx syntas built in? i.e. a way to
automatically transform some kind of markup into a function call, cf. `<h1
prop="arg">` -> h1(prop=arg)
* implement and test open/use statements
* 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 { type enum {
type enum MySubVariant { type enum MySubVariant {
SubVariant1, SubVariant2, etc. SubVariant1, SubVariant2, etc.
@ -108,106 +31,34 @@ type enum {
Variant1(MySubVariant), Variant1(MySubVariant),
Variant2(...), Variant2(...),
} }
```
* inclusive/exclusive range syntax like .. vs ..=
* Nameable patterns/ pattern synonyms cf. https://gitlab.haskell.org/ghc/ghc/-/wikis/pattern-synonyms
## Typechecking
* cf. the notation mentioned in the cardelli paper, the debug information for the `typechecking` pass should * idea for Schala: both currying *and* default arguments!
* print the generated type variable for every subexpression in an expression ex. fn a(b: Int, c:Int, d:Int = 1) -> Int
* think about idris-related ideas of multiple implementations of a type for an interface (+ vs * impl for monoids, for preorder/inorder/postorder for Foldable) a(1,2) : Int
* should have an Idris-like `cast To From` function a(1,2,d=2): Int
a(_,1,3) : Int -> Int
* something like the swift `Never` type ( https://nshipster.com/never/ ) in the stdlib a(1,2, c=_): Int -> Int
a(_,_,_) : Int -> Int -> Int -> Int
## Compilation
* look into Inkwell for rust LLVM bindings
* https://cranelift.readthedocs.io/en/latest/?badge=latest<Paste>
* look at https://gluon-lang.org/doc/nightly/book/embedding-api.html - 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!
# Syntax Playground *Compiler passes architecture
## Trying if-syntax again -ProgrammingLanguageInterface defines a evaluate_in_repl() and evaluate_no_repl() functions
-these take in a vec of CompilerPasses
``` struct CompilerPass {
//simple if expr name: String,
if x == 10 then "a" else "z" run: fn(PrevPass) -> NextPass
//complex if expr
if x == 10 then {
let a = 1
let b = 2
a + b
} else {
55
} }
// different comparison ops -change "Type...." names in parser.rs to "Anno..." for non-collision with names in typechecking.rs
if x {
== 1 then "a"
.isPrime() then "b"
else "c"
}
/* for now disallow `if x == { 1 then ... }`, b/c hard to parse
//simple pattern-matching
if x is Person("Ivan", age) then age else 0
//match-block equivalent
if x {
is Person("Ivan", _) then "Ivan"
is Person(_, age) if age > 13 then "barmitzvah'd"
else "foo"
}
```
## (OLD) 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 '}'`
-get rid of code pertaining to compilation specifically, have a more generation notion of "execution type"

279
maaru/src/compilation.rs Normal file
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 parser::{AST, Statement, Function, Prototype, Expression, BinOp};
use schala_repl::LLVMCodeString;
use schala_repl::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

@ -5,6 +5,9 @@ extern crate schala_repl;
mod tokenizer; mod tokenizer;
mod parser; mod parser;
mod eval; mod eval;
mod compilation;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput, TraceArtifact};
#[derive(Debug)] #[derive(Debug)]
pub struct TokenError { pub struct TokenError {
@ -31,42 +34,6 @@ impl<'a> Maaru<'a> {
} }
} }
/*
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> { impl<'a> ProgrammingLanguageInterface for Maaru<'a> {
fn get_language_name(&self) -> String { fn get_language_name(&self) -> String {
"Maaru".to_string() "Maaru".to_string()
@ -74,5 +41,66 @@ impl<'a> ProgrammingLanguageInterface for Maaru<'a> {
fn get_source_file_suffix(&self) -> String { fn get_source_file_suffix(&self) -> String {
format!("maaru") 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.ast {
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;
}
/* TODO make this work with new framework */
/*
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

@ -4,7 +4,7 @@ extern crate itertools;
extern crate schala_repl; extern crate schala_repl;
use itertools::Itertools; use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions}; use schala_repl::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput};
pub struct Robo { pub struct Robo {
} }
@ -154,5 +154,19 @@ impl ProgrammingLanguageInterface for Robo {
fn get_source_file_suffix(&self) -> String { fn get_source_file_suffix(&self) -> String {
format!("robo") 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

@ -4,7 +4,7 @@ extern crate itertools;
extern crate schala_repl; extern crate schala_repl;
use itertools::Itertools; use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions}; use schala_repl::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput};
use std::iter::Peekable; use std::iter::Peekable;
use std::vec::IntoIter; use std::vec::IntoIter;
use std::str::Chars; use std::str::Chars;
@ -72,6 +72,26 @@ impl ProgrammingLanguageInterface for Rukka {
fn get_source_file_suffix(&self) -> String { fn get_source_file_suffix(&self) -> String {
format!("rukka") 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 { impl EvaluatorState {

View File

@ -1,2 +0,0 @@
[toolchain]
channel = "nightly"

View File

@ -1,8 +0,0 @@
max_width = 110
use_small_heuristics = "max"
imports_indent = "block"
imports_granularity = "crate"
group_imports = "stdexternalcrate"
match_arm_blocks = false
where_single_line = true

12
schala-codegen/Cargo.toml Normal file
View File

@ -0,0 +1,12 @@
[package]
name = "schala-codegen"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
quote = "0.5.2"
syn = { version = "0.13.1", features = ["full", "extra-traits"] }
[lib]
proc-macro = true

95
schala-codegen/src/lib.rs Normal file
View File

@ -0,0 +1,95 @@
#![feature(proc_macro)]
extern crate proc_macro;
#[macro_use]
extern crate syn;
#[macro_use]
extern crate quote;
use proc_macro::TokenStream;
use syn::{Expr, Lit, ExprLit};
use syn::punctuated::Punctuated;
use syn::synom::Synom;
fn get_string_args(input: Expr) -> Vec<String> {
let mut contained_strings = Vec::new();
match input {
Expr::Array(array) => {
for item in array.elems {
if let Expr::Lit(ExprLit { lit: Lit::Str(s), ..}) = item {
contained_strings.push(s.value());
} else {
panic!("Non-string-literal input to compiler_pass_sequence");
}
}
},
_ => panic!("Non-array input to compiler_pass_sequence"),
}
contained_strings
}
#[proc_macro]
pub fn compiler_pass_sequence(input: TokenStream) -> TokenStream {
/*
for token_tree in input {
//println!("ITEM: {:?}", token_tree.kind);
match token_tree.kind {
TokenNode::Literal(l) => println!("{:?}", l),
_ => ()
}
}
*/
let input: Expr = syn::parse(input).unwrap();
let stages = get_string_args(input);
let from_macro = format!("{:?}", stages);
let output = quote! {
fn new_execute(&mut self, input: &str, _options: &EvalOptions) -> FinishedComputation {
let evaluation = UnfinishedComputation::default();
evaluation.output(Err(#from_macro.to_string()))
}
};
output.into()
}
/* #[compiler_pass(<name of pass>*/
#[proc_macro_attribute]
pub fn compiler_pass(metadata: TokenStream, function: TokenStream) -> TokenStream {
//println!("FROM MACRO: {}", function);
println!("Compiler pass metadata: {}", metadata);
function
}
#[cfg(test)]
mod tests {
#[test]
fn it_works() {
assert_eq!(2 + 2, 4);
}
}
/* in Rocket
*
#[get("/")]
fn hi() -> &'static str {
"hello"
}
GETS MAPPED TO:
static hi_info = RouteInfo {
name: "hi",
method: Method::Get,
path: "/",
handler: hi_route,
}
fn hi_route(req: &Request) -> Outcome {
let responder = hi();
Outcome::from(req, responder);
}
*/

View File

@ -2,26 +2,12 @@
name = "schala-lang" name = "schala-lang"
version = "0.1.0" version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"] authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2021"
[dependencies] [dependencies]
itertools = "0.10" itertools = "0.5.8"
take_mut = "0.2.2" take_mut = "0.1.3"
failure = "0.1.5" maplit = "*"
ena = "0.11.0" lazy_static = "0.2.8"
stopwatch = "0.0.7"
derivative = "2.2.0"
colored = "1.8"
radix_trie = "0.1.5"
assert_matches = "1.5"
#peg = "0.7.0"
peg = "0.8.1"
nom = "7.1.0"
nom_locate = "4.0.0"
schala-repl = { path = "../schala-repl" } schala-repl = { path = "../schala-repl" }
schala-codegen = { path = "../schala-codegen" }
[dev-dependencies]
test-case = "1.2.0"
pretty_assertions = "1.0.0"

View File

@ -1,22 +0,0 @@
let _SCHALA_VERSION = "0.1.0"
type Option<T> = Some(T) | None
type Ord = LT | EQ | GT
@register_builtin(print)
fn print(arg) { }
@register_builtin(println)
fn println(arg) { }
@register_builtin(getline)
fn getline(arg) { }
fn map(input: Option<T>, func: Func): Option<T> {
if input {
is Option::Some(x) then Option::Some(func(x))
is Option::None then Option::None
}
}
type Complicated = Sunrise | Metal { black: bool, norwegian: bool } | Fella(String, Int)

View File

@ -1,345 +0,0 @@
#![allow(clippy::upper_case_acronyms)]
#![allow(clippy::enum_variant_names)]
use std::{
convert::{AsRef, From},
fmt,
rc::Rc,
};
mod operators;
mod visitor;
mod visualize;
pub use operators::{BinOp, PrefixOp};
pub use visitor::*;
use crate::{
derivative::Derivative,
identifier::{define_id_kind, Id},
parsing::Location,
util::delim_wrapped,
};
define_id_kind!(ASTItem);
pub type ItemId = Id<ASTItem>;
#[derive(Derivative, Debug)]
#[derivative(PartialEq)]
pub struct AST {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub statements: Block,
}
impl fmt::Display for AST {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}", visualize::render_ast(self))
}
}
#[derive(Derivative, Debug, Clone)]
#[derivative(PartialEq)]
pub struct Statement<K> {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
#[derivative(PartialEq = "ignore")]
pub location: Location,
pub kind: K,
}
#[derive(Debug, PartialEq, Clone)]
pub enum StatementKind {
Expression(Expression),
Declaration(Declaration),
Import(ImportSpecifier),
Flow(FlowControl),
}
#[derive(Debug, Clone, PartialEq)]
pub enum FlowControl {
Continue,
Break,
Return(Option<Expression>),
}
#[derive(Debug, Clone, PartialEq, Default)]
pub struct Block {
pub statements: Vec<Statement<StatementKind>>,
}
impl From<Vec<Statement<StatementKind>>> for Block {
fn from(statements: Vec<Statement<StatementKind>>) -> Self {
Self { statements }
}
}
impl From<Statement<StatementKind>> for Block {
fn from(statement: Statement<StatementKind>) -> Self {
Self { statements: vec![statement] }
}
}
impl AsRef<[Statement<StatementKind>]> for Block {
fn as_ref(&self) -> &[Statement<StatementKind>] {
self.statements.as_ref()
}
}
pub type ParamName = Rc<String>;
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct QualifiedName {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub components: Vec<Rc<String>>,
}
impl fmt::Display for QualifiedName {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match &self.components[..] {
[] => write!(f, "[<empty>]"),
[name] => write!(f, "{}", name),
[name, rest @ ..] => {
write!(f, "{}", name)?;
for c in rest {
write!(f, "::{}", c)?;
}
Ok(())
}
}
}
}
#[derive(Debug, PartialEq, Clone)]
pub struct FormalParam {
pub name: ParamName,
pub default: Option<Expression>,
pub anno: Option<TypeIdentifier>,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Declaration {
FuncSig(Signature),
FuncDecl(Signature, Block),
TypeDecl {
name: TypeSingletonName,
body: TypeBody,
mutable: bool,
},
//TODO TypeAlias `original` needs to be a more complex type definition
TypeAlias {
alias: Rc<String>,
original: Rc<String>,
},
Binding {
name: Rc<String>,
constant: bool,
type_anno: Option<TypeIdentifier>,
expr: Expression,
},
Impl {
type_name: TypeIdentifier,
interface_name: Option<TypeSingletonName>,
block: Vec<Statement<Declaration>>,
},
Interface {
name: Rc<String>,
signatures: Vec<Signature>,
},
//TODO need to limit the types of statements that can be annotated
Annotation {
name: Rc<String>,
arguments: Vec<Expression>,
inner: Box<Statement<StatementKind>>,
},
Module {
name: Rc<String>,
items: Block,
},
}
#[derive(Debug, PartialEq, Clone)]
pub struct Signature {
pub name: Rc<String>,
pub operator: bool,
pub params: Vec<FormalParam>,
pub type_anno: Option<TypeIdentifier>,
}
//TODO I can probably get rid of TypeBody
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub enum TypeBody {
Variants(Vec<Variant>),
ImmediateRecord {
#[derivative(PartialEq = "ignore")]
id: ItemId,
fields: Vec<(Rc<String>, TypeIdentifier)>,
},
}
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct Variant {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub name: Rc<String>,
pub kind: VariantKind,
}
#[derive(Debug, PartialEq, Clone)]
pub enum VariantKind {
UnitStruct,
TupleStruct(Vec<TypeIdentifier>),
Record(Vec<(Rc<String>, TypeIdentifier)>),
}
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct Expression {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub kind: ExpressionKind,
//TODO this should only allow singletons, not tuples
pub type_anno: Option<TypeIdentifier>,
}
impl Expression {
pub fn new(id: ItemId, kind: ExpressionKind) -> Expression {
Expression { id, kind, type_anno: None }
}
}
#[derive(Debug, PartialEq, Clone)]
pub enum TypeIdentifier {
Tuple(Vec<TypeIdentifier>),
Singleton(TypeSingletonName),
}
impl fmt::Display for TypeIdentifier {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
TypeIdentifier::Tuple(items) =>
write!(f, "{}", delim_wrapped('(', ')', items.iter().map(|item| item.to_string()))),
TypeIdentifier::Singleton(tsn) => {
write!(f, "{}", tsn.name)?;
if !tsn.params.is_empty() {
write!(f, "{}", delim_wrapped('<', '>', tsn.params.iter().map(|item| item.to_string())))?;
}
Ok(())
}
}
}
}
#[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 { prefix: Option<Rc<String>>, s: Rc<String> },
BoolLiteral(bool),
BinExp(BinOp, Box<Expression>, Box<Expression>),
PrefixExp(PrefixOp, Box<Expression>),
TupleLiteral(Vec<Expression>),
Value(QualifiedName),
SelfValue,
NamedStruct { name: QualifiedName, fields: Vec<(Rc<String>, Expression)> },
Call { f: Box<Expression>, arguments: Vec<InvocationArgument> },
Index { indexee: Box<Expression>, indexers: Vec<Expression> },
IfExpression { discriminator: Option<Box<Expression>>, body: Box<IfExpressionBody> },
WhileExpression { condition: Option<Box<Expression>>, body: Block },
ForExpression { enumerators: Vec<Enumerator>, body: Box<ForBody> },
Lambda { params: Vec<FormalParam>, type_anno: Option<TypeIdentifier>, body: Block },
Access { name: Rc<String>, expr: Box<Expression> },
ListLiteral(Vec<Expression>),
}
#[derive(Debug, PartialEq, Clone)]
pub enum InvocationArgument {
Positional(Expression),
Keyword { name: Rc<String>, expr: Expression },
Ignored,
}
#[derive(Debug, PartialEq, Clone)]
pub enum IfExpressionBody {
SimpleConditional { then_case: Block, else_case: Option<Block> },
SimplePatternMatch { pattern: Pattern, then_case: Block, else_case: Option<Block> },
CondList(Vec<ConditionArm>),
}
#[derive(Debug, PartialEq, Clone)]
pub struct ConditionArm {
pub condition: Condition,
pub guard: Option<Expression>,
pub body: Block,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Condition {
Pattern(Pattern),
TruncatedOp(BinOp, Expression),
//Expression(Expression), //I'm pretty sure I don't actually want this
Else,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Pattern {
Ignored,
TuplePattern(Vec<Pattern>),
Literal(PatternLiteral),
TupleStruct(QualifiedName, Vec<Pattern>),
Record(QualifiedName, Vec<(Rc<String>, Pattern)>),
VarOrName(QualifiedName),
}
#[derive(Debug, PartialEq, Clone)]
pub enum PatternLiteral {
NumPattern { neg: bool, num: ExpressionKind },
StringPattern(Rc<String>),
BoolPattern(bool),
}
#[derive(Debug, PartialEq, Clone)]
pub struct Enumerator {
pub identifier: Rc<String>,
pub generator: Expression,
pub assignment: bool, //true if `=`, false if `<-`
}
#[derive(Debug, PartialEq, Clone)]
pub enum ForBody {
MonadicReturn(Expression),
StatementBlock(Block),
}
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct ImportSpecifier {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub path_components: Vec<Rc<String>>,
pub imported_names: ImportedNames,
}
#[derive(Debug, PartialEq, Clone)]
pub enum ImportedNames {
All,
LastOfPath,
List(Vec<Rc<String>>),
}
#[derive(Debug, PartialEq, Clone)]
pub struct ModuleSpecifier {
pub name: Rc<String>,
pub contents: Block,
}

View File

@ -1,61 +0,0 @@
use std::rc::Rc;
#[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) -> &str {
&self.sigil
}
}
#[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) -> &str {
&self.sigil
}
pub fn min_precedence() -> i32 {
i32::min_value()
}
pub fn get_precedence(&self) -> i32 {
binop_precedences(self.sigil.as_ref())
}
}
fn binop_precedences(s: &str) -> i32 {
let default = 10_000_000;
match s {
"+" => 10,
"-" => 10,
"*" => 20,
"/" => 20,
"%" => 20,
"++" => 30,
"^" => 30,
"&" => 20,
"|" => 20,
">" => 20,
">=" => 20,
"<" => 20,
"<=" => 20,
"==" => 40,
"<=>" => 30,
"=" => 5, // Assignment shoudl have highest precedence
_ => default,
}
}

View File

@ -1,202 +0,0 @@
use crate::ast::*;
#[derive(Debug)]
pub enum Recursion {
Continue,
Stop,
}
pub trait ASTVisitor: Sized {
fn expression(&mut self, _expression: &Expression) -> Recursion {
Recursion::Continue
}
fn declaration(&mut self, _declaration: &Declaration, _id: &ItemId) -> Recursion {
Recursion::Continue
}
fn import(&mut self, _import: &ImportSpecifier) -> Recursion {
Recursion::Continue
}
fn pattern(&mut self, _pat: &Pattern) -> Recursion {
Recursion::Continue
}
}
pub fn walk_ast<V: ASTVisitor>(v: &mut V, ast: &AST) {
walk_block(v, &ast.statements);
}
pub fn walk_block<V: ASTVisitor>(v: &mut V, block: &Block) {
use StatementKind::*;
for statement in block.statements.iter() {
match statement.kind {
StatementKind::Expression(ref expr) => {
walk_expression(v, expr);
}
Declaration(ref decl) => {
walk_declaration(v, decl, &statement.id);
}
Import(ref import_spec) => {
v.import(import_spec);
}
Flow(ref flow_control) =>
if let FlowControl::Return(Some(ref retval)) = flow_control {
walk_expression(v, retval);
},
}
}
}
pub fn walk_declaration<V: ASTVisitor>(v: &mut V, decl: &Declaration, id: &ItemId) {
use Declaration::*;
if let Recursion::Continue = v.declaration(decl, id) {
match decl {
FuncDecl(_sig, block) => {
walk_block(v, block);
}
Binding { name: _, constant: _, type_anno: _, expr } => {
walk_expression(v, expr);
}
Module { name: _, items } => {
walk_block(v, items);
}
_ => (),
};
}
}
pub fn walk_expression<V: ASTVisitor>(v: &mut V, expr: &Expression) {
use ExpressionKind::*;
if let Recursion::Continue = v.expression(expr) {
match &expr.kind {
NatLiteral(_)
| FloatLiteral(_)
| StringLiteral { .. }
| BoolLiteral(_)
| Value(_)
| SelfValue => (),
BinExp(_, lhs, rhs) => {
walk_expression(v, lhs);
walk_expression(v, rhs);
}
PrefixExp(_, arg) => {
walk_expression(v, arg);
}
TupleLiteral(exprs) =>
for expr in exprs {
walk_expression(v, expr);
},
NamedStruct { name: _, fields } =>
for (_, expr) in fields.iter() {
walk_expression(v, expr);
},
Call { f, arguments } => {
walk_expression(v, f);
for arg in arguments.iter() {
match arg {
InvocationArgument::Positional(expr) | InvocationArgument::Keyword { expr, .. } =>
walk_expression(v, expr),
_ => (),
}
}
}
Index { indexee, indexers } => {
walk_expression(v, indexee);
for indexer in indexers.iter() {
walk_expression(v, indexer);
}
}
IfExpression { discriminator, body } => {
if let Some(d) = discriminator.as_ref() {
walk_expression(v, d);
}
walk_if_expr_body(v, body.as_ref());
}
WhileExpression { condition, body } => {
if let Some(d) = condition.as_ref() {
walk_expression(v, d);
}
walk_block(v, body);
}
ForExpression { enumerators, body } => {
for enumerator in enumerators {
walk_expression(v, &enumerator.generator);
}
match body.as_ref() {
ForBody::MonadicReturn(expr) => walk_expression(v, expr),
ForBody::StatementBlock(block) => walk_block(v, block),
};
}
Lambda { params: _, type_anno: _, body } => {
walk_block(v, body);
}
Access { name: _, expr } => {
walk_expression(v, expr);
}
ListLiteral(exprs) =>
for expr in exprs {
walk_expression(v, expr);
},
};
}
}
pub fn walk_if_expr_body<V: ASTVisitor>(v: &mut V, body: &IfExpressionBody) {
use IfExpressionBody::*;
match body {
SimpleConditional { then_case, else_case } => {
walk_block(v, then_case);
if let Some(block) = else_case.as_ref() {
walk_block(v, block)
}
}
SimplePatternMatch { pattern, then_case, else_case } => {
walk_pattern(v, pattern);
walk_block(v, then_case);
if let Some(block) = else_case.as_ref() {
walk_block(v, block)
}
}
CondList(arms) =>
for arm in arms {
match arm.condition {
Condition::Pattern(ref pat) => {
walk_pattern(v, pat);
}
Condition::TruncatedOp(ref _binop, ref expr) => {
walk_expression(v, expr);
}
Condition::Else => (),
}
if let Some(ref guard) = arm.guard {
walk_expression(v, guard);
}
walk_block(v, &arm.body);
},
}
}
pub fn walk_pattern<V: ASTVisitor>(v: &mut V, pat: &Pattern) {
use Pattern::*;
if let Recursion::Continue = v.pattern(pat) {
match pat {
TuplePattern(patterns) =>
for pat in patterns {
walk_pattern(v, pat);
},
TupleStruct(_, patterns) =>
for pat in patterns {
walk_pattern(v, pat);
},
Record(_, name_and_patterns) =>
for (_, pat) in name_and_patterns {
walk_pattern(v, pat);
},
_ => (),
};
}
}

View File

@ -1,282 +0,0 @@
#![allow(clippy::single_char_add_str)]
use std::fmt::Write;
use super::{
Block, Declaration, Expression, ExpressionKind, FlowControl, ImportSpecifier, InvocationArgument,
Signature, Statement, StatementKind, AST,
};
const LEVEL: usize = 2;
fn do_indent(n: usize, buf: &mut String) {
for _ in 0..n {
buf.push(' ');
}
}
fn newline(buf: &mut String) {
buf.push('\n');
}
pub(super) fn render_ast(ast: &AST) -> String {
let AST { statements, .. } = ast;
let mut buf = "(AST\n".to_string();
render_block(statements, LEVEL, &mut buf);
buf.push(')');
buf
}
fn render_statement(stmt: &Statement<StatementKind>, indent: usize, buf: &mut String) {
use StatementKind::*;
do_indent(indent, buf);
match stmt.kind {
Expression(ref expr) => render_expression(expr, indent, buf),
Declaration(ref decl) => render_declaration(decl, indent, buf),
Import(ref spec) => render_import(spec, indent, buf),
Flow(ref flow_control) => render_flow_control(flow_control, indent, buf),
}
}
fn render_expression(expr: &Expression, indent: usize, buf: &mut String) {
use ExpressionKind::*;
buf.push_str("(Expr ");
match &expr.kind {
SelfValue => write!(buf, "(SelfValue)").unwrap(),
NatLiteral(n) => buf.push_str(&format!("(NatLiteral {})", n)),
FloatLiteral(f) => buf.push_str(&format!("(FloatLiteral {})", f)),
StringLiteral { s, prefix } => buf.push_str(&format!("(StringLiteral prefix: {:?} {})", prefix, s)),
BoolLiteral(b) => buf.push_str(&format!("(BoolLiteral {})", b)),
BinExp(binop, lhs, rhs) => {
let new_indent = indent + LEVEL;
buf.push_str(&format!("Binop {}\n", binop.sigil()));
do_indent(new_indent, buf);
render_expression(lhs, new_indent, buf);
newline(buf);
do_indent(new_indent, buf);
render_expression(rhs, new_indent, buf);
newline(buf);
do_indent(indent, buf);
}
PrefixExp(prefix, expr) => {
let new_indent = indent + LEVEL;
buf.push_str(&format!("PrefixOp {}\n", prefix.sigil()));
do_indent(new_indent, buf);
render_expression(expr, new_indent, buf);
newline(buf);
do_indent(indent, buf);
}
TupleLiteral(..) => (),
Value(name) => {
buf.push_str(&format!("Value {})", name));
}
NamedStruct { name: _, fields: _ } => (),
Call { f, arguments } => {
let new_indent = indent + LEVEL;
buf.push_str("Call ");
render_expression(f, new_indent, buf);
newline(buf);
for arg in arguments {
do_indent(new_indent, buf);
match arg {
InvocationArgument::Positional(expr) => render_expression(expr, new_indent, buf),
InvocationArgument::Keyword { .. } => buf.push_str("<keyword>"),
InvocationArgument::Ignored => buf.push_str("<ignored>"),
}
newline(buf);
do_indent(indent, buf);
}
}
Index { .. } => buf.push_str("<index>"),
IfExpression { .. } => buf.push_str("<if-expr>"),
WhileExpression { .. } => buf.push_str("<while-expr>"),
ForExpression { .. } => buf.push_str("<for-expr>"),
Lambda { params, type_anno: _, body } => {
let new_indent = indent + LEVEL;
buf.push_str("Lambda ");
newline(buf);
do_indent(new_indent, buf);
buf.push_str("(Args ");
for p in params {
buf.push_str(&format!("{} ", p.name));
}
buf.push(')');
newline(buf);
do_indent(new_indent, buf);
buf.push_str("(Body ");
newline(buf);
render_block(body, new_indent + LEVEL, buf);
do_indent(new_indent, buf);
buf.push(')');
newline(buf);
do_indent(indent, buf);
}
Access { .. } => buf.push_str("<access-expr>"),
ListLiteral(..) => buf.push_str("<list-literal>"),
}
buf.push(')');
}
fn render_declaration(decl: &Declaration, indent: usize, buf: &mut String) {
use Declaration::*;
buf.push_str("(Decl ");
match decl {
FuncSig(ref sig) => render_signature(sig, indent, buf),
FuncDecl(ref sig, ref block) => {
let indent = indent + LEVEL;
buf.push_str("Function");
newline(buf);
do_indent(indent, buf);
render_signature(sig, indent, buf);
newline(buf);
do_indent(indent, buf);
buf.push_str("(Body");
newline(buf);
render_block(block, indent + LEVEL, buf);
do_indent(indent, buf);
buf.push_str(")");
newline(buf);
}
TypeDecl { name: _, body: _, .. } => {
buf.push_str("<type-decl>");
}
TypeAlias { alias: _, original: _ } => {
buf.push_str("<type-alias>");
}
Binding { name, constant: _, type_anno: _, expr } => {
let new_indent = indent + LEVEL;
buf.push_str(&format!("Binding {}", name));
newline(buf);
do_indent(new_indent, buf);
render_expression(expr, new_indent, buf);
newline(buf);
}
Module { name, items: _ } => {
write!(buf, "(Module {} <body>)", name).unwrap();
}
_ => (), /*
Impl { type_name: TypeIdentifier, interface_name: Option<TypeSingletonName>, block: Vec<Declaration> },
Interface { name: Rc<String>, signatures: Vec<Signature> },
Annotation { name: Rc<String>, arguments: Vec<Expression> },
*/
}
do_indent(indent, buf);
buf.push(')');
}
fn render_block(block: &Block, indent: usize, buf: &mut String) {
for stmt in block.statements.iter() {
render_statement(stmt, indent, buf);
newline(buf);
}
}
fn render_signature(sig: &Signature, _indent: usize, buf: &mut String) {
buf.push_str(&format!("(Signature {} )", sig.name));
}
fn render_import(_import: &ImportSpecifier, _indent: usize, buf: &mut String) {
buf.push_str("(Import <some import>)");
}
fn render_flow_control(flow: &FlowControl, _indent: usize, buf: &mut String) {
use FlowControl::*;
match flow {
Return(ref _expr) => write!(buf, "return <expr>").unwrap(),
Break => write!(buf, "break").unwrap(),
Continue => write!(buf, "continue").unwrap(),
}
}
#[cfg(test)]
mod test {
use super::render_ast;
use crate::util::quick_ast;
#[test]
fn test_visualization() {
let ast = quick_ast(
r#"
fn test(x) {
let m = 9
1 * 4 <> m |> somemod::output(x)
}
let quincy = \(no, yes, maybe) {
let a = 10
yes * no + a
}
let b = 54
test(b) == 3
"#,
);
let expected_output = r#"(AST
(Decl Function
(Signature test )
(Body
(Decl Binding m
(Expr (NatLiteral 9))
)
(Expr Binop *
(Expr (NatLiteral 1))
(Expr Binop |>
(Expr Binop <>
(Expr (NatLiteral 4))
(Expr Value m))
)
(Expr Call (Expr Value somemod::output))
(Expr Value x))
)
)
)
)
)
(Decl Binding quincy
(Expr Lambda
(Args no yes maybe )
(Body
(Decl Binding a
(Expr (NatLiteral 10))
)
(Expr Binop +
(Expr Binop *
(Expr Value yes))
(Expr Value no))
)
(Expr Value a))
)
)
)
)
(Decl Binding b
(Expr (NatLiteral 54))
)
(Expr Binop ==
(Expr Call (Expr Value test))
(Expr Value b))
)
(Expr (NatLiteral 3))
)
)"#;
let rendered = render_ast(&ast);
assert_eq!(rendered, expected_output);
}
}

View File

@ -1,130 +1,77 @@
use std::{convert::TryFrom, str::FromStr}; use std::rc::Rc;
use std::collections::HashMap;
use crate::{ use typechecking::{Type, TypeResult, TConst};
ast::{BinOp, PrefixOp}, use self::Type::*; use self::TConst::*;
type_inference::Type,
};
/// "Builtin" computational operations with some kind of semantics, mostly mathematical operations. #[derive(Debug, PartialEq, Clone)]
#[derive(Debug, Clone, Copy, PartialEq)] pub struct BinOp {
pub enum Builtin { sigil: Rc<String>
Add,
Increment,
Subtract,
Negate,
Multiply,
Divide,
Quotient,
Modulo,
Exponentiation,
BitwiseAnd,
BitwiseOr,
BooleanAnd,
BooleanOr,
BooleanNot,
Equality,
LessThan,
LessThanOrEqual,
GreaterThan,
GreaterThanOrEqual,
Comparison,
IOPrint,
IOPrintLn,
IOGetLine,
Assignment,
Concatenate,
NotEqual,
} }
impl Builtin { impl BinOp {
#[allow(dead_code)] pub fn from_sigil(sigil: &str) -> BinOp {
pub fn get_type(&self) -> Type { BinOp { sigil: Rc::new(sigil.to_string()) }
use Builtin::*; }
match self { pub fn sigil(&self) -> &Rc<String> {
Add => ty!(Nat -> Nat -> Nat), &self.sigil
Subtract => ty!(Nat -> Nat -> Nat), }
Multiply => ty!(Nat -> Nat -> Nat), pub fn get_type(&self) -> TypeResult<Type> {
Divide => ty!(Nat -> Nat -> Float), let s = self.sigil.as_str();
Quotient => ty!(Nat -> Nat -> Nat), BINOPS.get(s).map(|x| x.0.clone()).ok_or(format!("Binop {} not found", s))
Modulo => ty!(Nat -> Nat -> Nat), }
Exponentiation => ty!(Nat -> Nat -> Nat), pub fn min_precedence() -> i32 {
BitwiseAnd => ty!(Nat -> Nat -> Nat), i32::min_value()
BitwiseOr => ty!(Nat -> Nat -> Nat), }
BooleanAnd => ty!(Bool -> Bool -> Bool), pub fn get_precedence(op: &str) -> i32 {
BooleanOr => ty!(Bool -> Bool -> Bool), let default = 10_000_000;
BooleanNot => ty!(Bool -> Bool), BINOPS.get(op).map(|x| x.2.clone()).unwrap_or(default)
Equality => ty!(Nat -> Nat -> Bool), }
LessThan => ty!(Nat -> Nat -> Bool),
LessThanOrEqual => ty!(Nat -> Nat -> Bool),
GreaterThan => ty!(Nat -> Nat -> Bool),
GreaterThanOrEqual => ty!(Nat -> Nat -> Bool),
Comparison => ty!(Nat -> Nat -> Ordering),
IOPrint => ty!(Unit),
IOPrintLn => ty!(Unit),
IOGetLine => ty!(StringT),
Assignment => ty!(Unit),
Concatenate => ty!(StringT -> StringT -> StringT),
Increment => ty!(Nat -> Int),
Negate => ty!(Nat -> Int),
NotEqual => ty!(Nat -> Nat -> Bool),
}
}
} }
impl TryFrom<&BinOp> for Builtin { #[derive(Debug, PartialEq, Clone)]
type Error = (); pub struct PrefixOp {
sigil: Rc<String>
fn try_from(binop: &BinOp) -> Result<Self, Self::Error> {
FromStr::from_str(binop.sigil())
}
} }
impl TryFrom<&PrefixOp> for Builtin { impl PrefixOp {
type Error = (); pub fn from_sigil(sigil: &str) -> PrefixOp {
PrefixOp { sigil: Rc::new(sigil.to_string()) }
fn try_from(prefix_op: &PrefixOp) -> Result<Self, Self::Error> { }
use Builtin::*; pub fn sigil(&self) -> &Rc<String> {
&self.sigil
match prefix_op.sigil() { }
"+" => Ok(Increment), pub fn is_prefix(op: &str) -> bool {
"-" => Ok(Negate), PREFIX_OPS.get(op).is_some()
"!" => Ok(BooleanNot), }
_ => Err(()), 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))), ()),
};
} }
impl FromStr for Builtin { /* the second tuple member is a placeholder for when I want to make evaluation rules tied to the
type Err = (); * binop definition */
lazy_static! {
fn from_str(s: &str) -> Result<Self, Self::Err> { static ref BINOPS: HashMap<&'static str, (Type, (), i32)> =
use Builtin::*; hashmap! {
Ok(match s { "+" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 10),
"+" => Add, "-" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 10),
"-" => Subtract, "*" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"*" => Multiply, "/" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Float))))), (), 20),
"/" => Divide, "//" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20), //TODO change this to `quot`
"quot" => Quotient, "%" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"%" => Modulo, "++" => (Func(bx!(Const(StringT)), bx!(Func(bx!(Const(StringT)), bx!(Const(StringT))))), (), 30),
"++" => Concatenate, "^" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"^" => Exponentiation, "&" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"&" => BitwiseAnd, "|" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
"&&" => BooleanAnd, };
"|" => BitwiseOr,
"||" => BooleanOr,
"!" => BooleanNot,
">" => GreaterThan,
">=" => GreaterThanOrEqual,
"<" => LessThan,
"<=" => LessThanOrEqual,
"==" => Equality,
"!=" => NotEqual,
"=" => Assignment,
"<=>" => Comparison,
"print" => IOPrint,
"println" => IOPrintLn,
"getline" => IOGetLine,
_ => return Err(()),
})
}
} }

View File

@ -1,79 +0,0 @@
use crate::{
parsing::{Location, ParseError},
schala::{SourceReference, Stage},
symbol_table::SymbolError,
type_inference::TypeError,
};
pub struct SchalaError {
errors: Vec<Error>,
}
impl SchalaError {
pub(crate) fn display(&self) -> String {
match self.errors[0] {
Error::Parse(ref parse_err) => parse_err.to_string(),
Error::Standard { ref text, .. } => text.as_ref().cloned().unwrap_or_default(),
}
}
#[allow(dead_code)]
pub(crate) fn from_type_error(err: TypeError) -> Self {
Self {
errors: vec![Error::Standard { location: None, text: Some(err.msg), stage: Stage::Typechecking }],
}
}
pub(crate) fn from_symbol_table(symbol_errs: Vec<SymbolError>) -> Self {
//TODO this could be better
let errors = symbol_errs
.into_iter()
.map(|_symbol_err| Error::Standard {
location: None,
text: Some("symbol table error".to_string()),
stage: Stage::Symbols,
})
.collect();
Self { errors }
}
pub(crate) fn from_string(text: String, stage: Stage) -> Self {
Self { errors: vec![Error::Standard { location: None, text: Some(text), stage }] }
}
pub(crate) fn from_parse_error(parse_error: ParseError, source_reference: &SourceReference) -> Self {
let formatted_parse_error = format_parse_error(parse_error, source_reference);
Self { errors: vec![Error::Parse(formatted_parse_error)] }
}
}
#[allow(dead_code)]
enum Error {
Standard { location: Option<Location>, text: Option<String>, stage: Stage },
Parse(String),
}
fn format_parse_error(error: ParseError, source_reference: &SourceReference) -> String {
let offset = error.location.offset;
let (line_start, line_num, line_from_program) = source_reference.get_line(offset);
let ch = offset - line_start;
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,
)
}

317
schala-lang/src/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 parsing::{AST, Statement, Declaration, Expression, Variant, ExpressionType};
use 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<Result<String, 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(Ok(fully_evaluated.to_string()));
}
},
Err(error) => {
acc.push(Err(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")),
})
}
}

View File

@ -1,75 +0,0 @@
use std::{
fmt::{self, Debug},
hash::Hash,
marker::PhantomData,
};
pub trait IdKind: Debug + Copy + Clone + Hash + PartialEq + Eq + Default {
fn tag() -> &'static str;
}
/// A generalized abstract identifier type of up to 2^32-1 entries.
#[derive(Debug, Copy, Clone, Hash, PartialEq, Eq, Default)]
pub struct Id<T>
where T: IdKind
{
idx: u32,
t: PhantomData<T>,
}
impl<T> Id<T>
where T: IdKind
{
fn new(n: u32) -> Self {
Self { idx: n, t: PhantomData }
}
#[allow(dead_code)]
pub fn as_u32(&self) -> u32 {
self.idx
}
}
impl<T> fmt::Display for Id<T>
where T: IdKind
{
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}:{}", self.idx, T::tag())
}
}
#[derive(Debug)]
pub struct IdStore<T>
where T: IdKind
{
last_idx: u32,
t: PhantomData<T>,
}
impl<T> IdStore<T>
where T: IdKind
{
pub fn new() -> Self {
Self { last_idx: 0, t: PhantomData }
}
pub fn fresh(&mut self) -> Id<T> {
let idx = self.last_idx;
self.last_idx += 1;
Id::new(idx)
}
}
macro_rules! define_id_kind {
($name:ident) => {
#[derive(Debug, Copy, Clone, Hash, PartialEq, Eq, Default)]
pub struct $name;
impl crate::identifier::IdKind for $name {
fn tag() -> &'static str {
stringify!($name)
}
}
};
}
pub(crate) use define_id_kind;

View File

@ -1,31 +1,127 @@
#![feature(trace_macros)] #![feature(slice_patterns, box_patterns, box_syntax)]
//#![feature(unrestricted_attribute_tokens)] #![feature(proc_macro)]
#![feature(box_patterns, iter_intersperse)] extern crate itertools;
#[macro_use]
extern crate lazy_static;
#[macro_use]
extern crate maplit;
//! `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 derivative;
extern crate schala_repl; extern crate schala_repl;
extern crate schala_codegen;
#[macro_use] use std::collections::HashMap;
mod util; use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions, TraceArtifact, UnfinishedComputation, FinishedComputation};
#[macro_use] macro_rules! bx {
mod type_inference; ($e:expr) => { Box::new($e) }
}
mod ast;
mod parsing;
#[macro_use]
mod symbol_table;
mod builtin; mod builtin;
mod error;
mod reduced_ir;
mod tree_walk_eval;
#[macro_use]
mod identifier;
mod schala; mod tokenizing;
mod parsing;
mod typechecking;
mod eval;
pub use schala::{Schala, SchalaConfig}; use self::typechecking::{TypeContext};
/* TODO eventually custom-derive ProgrammingLanguageInterface with compiler passes as options */
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 {
schala_codegen::compiler_pass_sequence!(["tokenize", "parse", "yolo"]);
fn get_language_name(&self) -> String {
"Schala".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("schala")
}
fn execute(&mut self, input: &str, options: &EvalOptions) -> FinishedComputation {
let mut evaluation = UnfinishedComputation::default();
//tokenzing
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(", ");
evaluation.add_artifact(TraceArtifact::new("tokens", token_string));
}
{
let token_errors: Vec<&String> = tokens.iter().filter_map(|t| t.get_error()).collect();
if token_errors.len() != 0 {
return evaluation.output(Err(format!("Tokenization error: {:?}\n", token_errors)));
}
}
// parsing
let ast = match parsing::parse(tokens) {
(Ok(ast), trace) => {
if options.debug.parse_tree {
evaluation.add_artifact(TraceArtifact::new_parse_trace(trace));
}
if options.debug.ast {
evaluation.add_artifact(TraceArtifact::new("ast", format!("{:#?}", ast)));
}
ast
},
(Err(err), trace) => {
if options.debug.parse_tree {
evaluation.add_artifact(TraceArtifact::new_parse_trace(trace));
}
return evaluation.output(Err(format!("Parse error: {:?}\n", err.msg)));
}
};
//symbol table
match self.type_context.add_top_level_types(&ast) {
Ok(()) => (),
Err(msg) => {
if options.debug.type_checking {
evaluation.add_artifact(TraceArtifact::new("type_check", msg));
}
}
};
//typechecking
match self.type_context.type_check_ast(&ast) {
Ok(ty) => {
if options.debug.type_checking {
evaluation.add_artifact(TraceArtifact::new("type_check", format!("{:?}", ty)));
}
},
Err(msg) => evaluation.add_artifact(TraceArtifact::new("type_check", msg)),
};
let text = self.type_context.debug_symbol_table();
if options.debug.symbol_table {
evaluation.add_artifact(TraceArtifact::new("symbol_table", text));
}
let evaluation_outputs = self.state.evaluate(ast);
let text_output: Result<Vec<String>, String> = evaluation_outputs
.into_iter()
.collect();
let eval_output = text_output
.map(|v| { v.into_iter().intersperse(format!("\n")).collect() });
evaluation.output(eval_output)
}
}

1235
schala-lang/src/parsing.rs Normal file

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -1,126 +0,0 @@
#![allow(clippy::upper_case_acronyms)]
pub mod combinator;
mod peg_parser;
mod test;
use std::{cell::RefCell, fmt, rc::Rc};
use combinator::Span;
#[cfg(test)]
use crate::ast::{Block, Expression};
use crate::{
ast::{ASTItem, AST},
identifier::{Id, IdStore},
};
pub(crate) type StoreRef = Rc<RefCell<IdStore<ASTItem>>>;
pub struct Parser {
id_store: StoreRef,
use_combinator: bool,
}
impl Parser {
pub(crate) fn new() -> Self {
let id_store: IdStore<ASTItem> = IdStore::new();
Self { id_store: Rc::new(RefCell::new(id_store)), use_combinator: true }
}
pub(crate) fn parse(&mut self, input: &str) -> Result<AST, ParseError> {
if self.use_combinator {
self.parse_comb(input)
} else {
self.parse_peg(input)
}
}
pub(crate) fn parse_peg(&mut self, input: &str) -> Result<AST, ParseError> {
peg_parser::schala_parser::program(input, self).map_err(ParseError::from_peg)
}
pub(crate) fn parse_comb(&mut self, input: &str) -> Result<AST, ParseError> {
let span = Span::new_extra(input, self.id_store.clone());
convert(input, combinator::program(span))
}
#[cfg(test)]
fn expression(&mut self, input: &str) -> Result<Expression, ParseError> {
peg_parser::schala_parser::expression(input, self).map_err(ParseError::from_peg)
}
#[cfg(test)]
fn expression_comb(&mut self, input: &str) -> Result<Expression, ParseError> {
let span = Span::new_extra(input, self.id_store.clone());
convert(input, combinator::expression(span))
}
#[cfg(test)]
fn block(&mut self, input: &str) -> Result<Block, ParseError> {
peg_parser::schala_parser::block(input, self).map_err(ParseError::from_peg)
}
#[cfg(test)]
fn block_comb(&mut self, input: &str) -> Result<Block, ParseError> {
let span = Span::new_extra(input, self.id_store.clone());
convert(input, combinator::block(span))
}
fn fresh(&mut self) -> Id<ASTItem> {
self.id_store.borrow_mut().fresh()
}
}
fn convert<'a, O>(input: &'a str, result: combinator::ParseResult<'a, O>) -> Result<O, ParseError> {
use nom::{error::VerboseError, Finish};
match result.finish() {
Ok((rest, output)) => {
if rest.fragment() != &"" {
return Err(ParseError {
location: Default::default(),
msg: format!("Bad parse state, remaining text: `{}`", rest.fragment()),
});
}
Ok(output)
}
Err(err) => {
let err = VerboseError {
errors: err.errors.into_iter().map(|(sp, kind)| (*sp.fragment(), kind)).collect(),
};
let msg = nom::error::convert_error(input, err);
Err(ParseError { msg, location: (0).into() })
}
}
}
/// Represents a parsing error
#[derive(Debug)]
pub struct ParseError {
pub msg: String,
pub location: Location,
}
impl ParseError {
fn from_peg(err: peg::error::ParseError<peg::str::LineCol>) -> Self {
let msg = err.to_string();
Self { msg, location: err.location.offset.into() }
}
}
#[derive(Debug, Clone, Copy, PartialEq, Default)]
pub struct Location {
pub(crate) offset: usize,
}
impl From<usize> for Location {
fn from(offset: usize) -> Self {
Self { offset }
}
}
impl fmt::Display for Location {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}", self.offset)
}
}

View File

@ -1,567 +0,0 @@
use std::rc::Rc;
use super::Parser;
use crate::ast::*;
fn rc_string(s: &str) -> Rc<String> {
Rc::new(s.to_string())
}
enum ExtendedPart<'a> {
Index(Vec<Expression>),
Accessor(&'a str),
Call(Vec<InvocationArgument>),
}
peg::parser! {
pub grammar schala_parser() for str {
rule whitespace() = [' ' | '\t' ]
rule whitespace_or_newline() = [' ' | '\t' | '\n' ]
rule _ = quiet!{ (block_comment() / line_comment() / whitespace())* }
rule __ = quiet!{ (block_comment() / line_comment() / whitespace_or_newline())* }
rule block_comment() = "/*" (block_comment() / !"*/" [_])* "*/"
rule line_comment() = "//" (!['\n'] [_])* &"\n"
pub rule program(parser: &mut Parser) -> AST =
__ statements:(statement(parser) ** (delimiter()+) ) __ { AST { id: parser.fresh(), statements: statements.into() } }
rule delimiter() = (";" / "\n")+
//Note - this is a hack, ideally the rule `rule block() -> Block = "{" _ items:(statement() **
//delimiter()) _ "}" { items.into() }` would've worked, but it doesn't.
pub rule block(parser: &mut Parser) -> Block =
"{" __ items:(statement(parser) ** delimiter()) delimiter()? __ "}" { items.into() } /
"{" __ stmt:statement(parser) __ "}" { vec![stmt].into() }
rule block_item(parser: &mut Parser) -> Statement<StatementKind> =
_ stmt:statement(parser) _ delimiter()+ { stmt }
rule statement(parser: &mut Parser) -> Statement<StatementKind> =
_ pos:position!() kind:statement_kind(parser) _ { Statement { id: parser.fresh(), location: pos.into(), kind } }
rule statement_kind(parser: &mut Parser) -> StatementKind =
__ import:import(parser) { StatementKind::Import(import) } /
__ decl:declaration(parser) { StatementKind::Declaration(decl) } /
__ flow:flow(parser) { StatementKind::Flow(flow) } /
__ expr:expression(parser) { StatementKind::Expression(expr) }
rule flow(parser: &mut Parser) -> FlowControl =
"continue" { FlowControl::Continue } /
"break" { FlowControl::Break } /
"return" _ expr:expression(parser)? { FlowControl::Return(expr) }
//TODO add the ability to rename and exclude imports
rule import(parser: &mut Parser) -> ImportSpecifier =
"import" _ path_components:path_components() suffix:import_suffix()? {
ImportSpecifier {
id: parser.fresh(),
path_components,
imported_names: suffix.unwrap_or(ImportedNames::LastOfPath)
}
}
rule path_components() -> Vec<Rc<String>> =
"::"? name:identifier() rest:path_component()* {
let mut items = vec![rc_string(name)];
items.extend(rest.into_iter().map(rc_string));
items
}
rule path_component() -> &'input str = "::" ident:identifier() { ident }
rule import_suffix() -> ImportedNames =
"::*" { ImportedNames::All } /
"::{" __ names:(identifier() ** (_ "," _)) __ "}" {?
if names.is_empty() {
Err("import groups must have at least one item")
} else {
Ok(ImportedNames::List(names.into_iter().map(rc_string).collect()))
}
}
rule declaration(parser: &mut Parser) -> Declaration =
binding(parser) / type_decl(parser) / annotation(parser) / func(parser) / interface(parser) /
implementation(parser) / module(parser)
rule module(parser: &mut Parser) -> Declaration =
"module" _ name:identifier() _ items:block(parser) { Declaration::Module { name: rc_string(name), items } }
rule implementation(parser: &mut Parser) -> Declaration =
"impl" _ interface:type_singleton_name() _ "for" _ type_name:type_identifier() _ block:decl_block(parser) {
Declaration::Impl { type_name, interface_name: Some(interface), block }
} /
"impl" _ type_name:type_identifier() _ block:decl_block(parser) {
Declaration::Impl { type_name, interface_name: None, block }
}
rule decl_block(parser: &mut Parser) -> Vec<Statement<Declaration>> =
"{" __ decls:(func_declaration_stmt(parser) ** (delimiter()+)) delimiter()? __ "}" { decls }
rule func_declaration_stmt(parser: &mut Parser) -> Statement<Declaration> =
pos:position!() decl:func_declaration(parser) { Statement { id: parser.fresh(), location: pos.into(), kind: decl } }
rule interface(parser: &mut Parser) -> Declaration =
"interface" _ name:identifier() _ signatures:signature_block(parser) { Declaration::Interface { name: rc_string(name), signatures } }
rule signature_block(parser: &mut Parser) -> Vec<Signature> =
"{" __ signatures:(func_signature(parser) ** (delimiter()+)) __ "}" { signatures }
rule func(parser: &mut Parser) -> Declaration =
decl:func_declaration(parser) { decl } /
sig:func_signature(parser) { Declaration::FuncSig(sig) }
rule func_declaration(parser: &mut Parser) -> Declaration =
_ sig:func_signature(parser) __ body:block(parser) { Declaration::FuncDecl(sig, body) }
rule func_signature(parser: &mut Parser) -> Signature =
_ "fn" _ name:identifier() "(" _ params:formal_params(parser) _ ")" _ type_anno:type_anno()? { Signature {
name: rc_string(name), operator: false, params, type_anno
} } /
_ "fn" _ "(" op:operator() ")" _ "(" _ params:formal_params(parser) _ ")" _ type_anno:type_anno()? { Signature {
name: rc_string(op), operator: true, params, type_anno
} }
rule formal_params(parser: &mut Parser) -> Vec<FormalParam> =
params:(formal_param(parser) ** (_ "," _)) {? if params.len() < 256 { Ok(params) } else {
Err("function-too-long") }
}
rule formal_param(parser: &mut Parser) -> FormalParam =
name:identifier() _ anno:type_anno()? _ "=" expr:expression(parser) { FormalParam { name: rc_string(name),
default: Some(expr), anno } } /
name:identifier() _ anno:type_anno()? { FormalParam { name: rc_string(name), default: None, anno } }
rule annotation(parser: &mut Parser) -> Declaration =
"@" name:identifier() args:annotation_args(parser)? delimiter()+ _ inner:statement(parser) { Declaration::Annotation {
name: rc_string(name), arguments: if let Some(args) = args { args } else { vec![] }, inner: Box::new(inner) }
}
rule annotation_args(parser: &mut Parser) -> Vec<Expression> =
"(" _ args:(expression(parser) ** (_ "," _)) _ ")" { args }
rule binding(parser: &mut Parser) -> Declaration =
"let" _ mutable:"mut"? _ ident:identifier() _ type_anno:type_anno()? _ "=" _ expr:expression(parser) {
Declaration::Binding { name: Rc::new(ident.to_string()), constant: mutable.is_none(),
type_anno, expr }
}
rule type_decl(parser: &mut Parser) -> Declaration =
"type" _ "alias" _ alias:type_alias() { alias } /
"type" _ mutable:"mut"? _ name:type_singleton_name() _ "=" _ body:type_body(parser) {
Declaration::TypeDecl { name, body, mutable: mutable.is_some() }
}
rule type_singleton_name() -> TypeSingletonName =
name:identifier() params:type_params()? { TypeSingletonName {
name: rc_string(name), params: if let Some(params) = params { params } else { vec![] }
} }
rule type_params() -> Vec<TypeIdentifier> =
"<" _ idents:(type_identifier() ** (_ "," _)) _ ">" { idents }
rule type_identifier() -> TypeIdentifier =
"(" _ items:(type_identifier() ** (_ "," _)) _ ")" { TypeIdentifier::Tuple(items) } /
singleton:type_singleton_name() { TypeIdentifier::Singleton(singleton) }
rule type_body(parser: &mut Parser) -> TypeBody =
"{" _ items:(record_variant_item() ** (__ "," __)) __ "}" { TypeBody::ImmediateRecord { id: parser.fresh(), fields: items } } /
variants:(variant_spec(parser) ** (__ "|" __)) { TypeBody::Variants(variants) }
rule variant_spec(parser: &mut Parser) -> Variant =
name:identifier() __ "{" __ typed_identifier_list:(record_variant_item() ** (__ "," __)) __ ","? __ "}" { Variant {
id: parser.fresh(), name: rc_string(name), kind: VariantKind::Record(typed_identifier_list)
} } /
name:identifier() "(" tuple_members:(type_identifier() ++ (__ "," __)) ")" { Variant {
id: parser.fresh(), name: rc_string(name), kind: VariantKind::TupleStruct(tuple_members) } } /
name:identifier() { Variant { id: parser.fresh(), name: rc_string(name), kind: VariantKind::UnitStruct } }
rule record_variant_item() -> (Rc<String>, TypeIdentifier) =
name:identifier() _ ":" _ ty:type_identifier() { (rc_string(name), ty) }
rule type_alias() -> Declaration =
alias:identifier() _ "=" _ name:identifier() { Declaration::TypeAlias { alias: rc_string(alias), original: rc_string(name), } }
rule type_anno() -> TypeIdentifier =
":" _ identifier:type_identifier() { identifier }
pub rule expression(parser: &mut Parser) -> Expression =
__ kind:expression_kind(true, parser) _ type_anno:type_anno()? { Expression { id: parser.fresh(), type_anno, kind } }
rule expression_no_struct(parser: &mut Parser) -> Expression =
__ kind:expression_kind(false, parser) { Expression { id: parser.fresh(), type_anno: None, kind } }
rule expression_kind(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
precedence_expr(struct_ok, parser)
rule precedence_expr(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
first:prefix_expr(struct_ok, parser) _ next:(precedence_continuation(struct_ok, parser))* {
let next = next.into_iter().map(|(sigil, expr)| (BinOp::from_sigil(sigil), expr)).collect();
BinopSequence { first, next }.do_precedence(parser)
}
rule precedence_continuation(struct_ok: bool, parser: &mut Parser) -> (&'input str, ExpressionKind) =
op:operator() _ expr:prefix_expr(struct_ok, parser) _ { (op, expr) }
rule prefix_expr(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
prefix:prefix()? expr:extended_expr(struct_ok, parser) {
if let Some(p) = prefix {
let expr = Expression::new(parser.fresh(), expr);
let prefix = PrefixOp::from_sigil(p);
ExpressionKind::PrefixExp(prefix, Box::new(expr))
} else {
expr
}
}
rule prefix() -> &'input str =
$(['+' | '-' | '!' ])
//TODO make the definition of operators more complex
rule operator() -> &'input str =
quiet!{!"*/" s:$( ['+' | '-' | '*' | '/' | '%' | '<' | '>' | '=' | '!' | '$' | '&' | '|' | '?' | '^' | '`']+ ) { s } } /
expected!("operator")
rule extended_expr(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
primary:primary(struct_ok, parser) parts:(extended_expr_part(parser)*) {
let mut expression = Expression::new(parser.fresh(), primary);
for part in parts.into_iter() {
let kind = match part {
ExtendedPart::Index(indexers) => {
ExpressionKind::Index { indexee: Box::new(expression), indexers }
},
ExtendedPart::Accessor(name) => {
let name = rc_string(name);
ExpressionKind::Access { name, expr: Box::new(expression) }
},
ExtendedPart::Call(arguments) => {
ExpressionKind::Call { f: Box::new(expression), arguments }
}
};
expression = Expression::new(parser.fresh(), kind);
}
expression.kind
}
rule extended_expr_part(parser: &mut Parser) -> ExtendedPart<'input> =
indexers:index_part(parser) { ExtendedPart::Index(indexers) } /
arguments:call_part(parser) { ExtendedPart::Call(arguments) } /
"." name:identifier() { ExtendedPart::Accessor(name) }
rule index_part(parser: &mut Parser) -> Vec<Expression> =
"[" indexers:(expression(parser) ++ ",") "]" { indexers }
rule call_part(parser: &mut Parser) -> Vec<InvocationArgument> =
"(" arguments:(invocation_argument(parser) ** ",") ")" { arguments }
rule invocation_argument(parser: &mut Parser) -> InvocationArgument =
_ "_" _ { InvocationArgument::Ignored } /
_ ident:identifier() _ "=" _ expr:expression(parser) { InvocationArgument::Keyword {
name: Rc::new(ident.to_string()),
expr
} } /
_ expr:expression(parser) _ { InvocationArgument::Positional(expr) }
rule primary(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
while_expr(parser) / for_expr(parser) / float_literal() / nat_literal() / bool_literal() /
string_literal() / paren_expr(parser) /
list_expr(parser) / if_expr(parser) / lambda_expr(parser) /
item:named_struct(parser) {? if struct_ok { Ok(item) } else { Err("no-struct-allowed") } } /
identifier_expr(parser)
rule lambda_expr(parser: &mut Parser) -> ExpressionKind =
r#"\"# __ "(" _ params:formal_params(parser) _ ")" _ type_anno:(type_anno()?) _ body:block(parser) {
ExpressionKind::Lambda { params, type_anno, body }
} /
r#"\"# param:formal_param(parser) _ type_anno:(type_anno()?) _ body:block(parser) {
ExpressionKind::Lambda { params: vec![param], type_anno, body }
}
rule for_expr(parser: &mut Parser) -> ExpressionKind =
"for" _ enumerators:for_enumerators(parser) _ body:for_body(parser) {
ExpressionKind::ForExpression { enumerators, body }
}
rule for_enumerators(parser: &mut Parser) -> Vec<Enumerator> =
"{" _ enumerators:(enumerator(parser) ++ ",") _ "}" { enumerators } /
enumerator:enumerator(parser) { vec![enumerator] }
//TODO add guards, etc.
rule enumerator(parser: &mut Parser) -> Enumerator =
ident:identifier() _ "<-" _ generator:expression_no_struct(parser) {
Enumerator { identifier: Rc::new(ident.to_string()), generator, assignment: false }
} /
//TODO need to distinguish these two cases in AST
ident:identifier() _ "=" _ generator:expression_no_struct(parser) {
Enumerator { identifier: Rc::new(ident.to_string()), generator, assignment: true }
}
rule for_body(parser: &mut Parser) -> Box<ForBody> =
"return" _ expr:expression(parser) { Box::new(ForBody::MonadicReturn(expr)) } /
body:block(parser) { Box::new(ForBody::StatementBlock(body)) }
rule while_expr(parser: &mut Parser) -> ExpressionKind =
"while" _ cond:expression_kind(false, parser)? _ body:block(parser) {
ExpressionKind::WhileExpression {
condition: cond.map(|kind| Box::new(Expression::new(parser.fresh(), kind))),
body,
}
}
rule identifier_expr(parser: &mut Parser) -> ExpressionKind =
qn:qualified_identifier(parser) { ExpressionKind::Value(qn) }
rule named_struct(parser: &mut Parser) -> ExpressionKind =
name:qualified_identifier(parser) _ fields:record_block(parser) {
ExpressionKind::NamedStruct {
name,
fields: fields.into_iter().map(|(n, exp)| (Rc::new(n.to_string()), exp)).collect(),
}
}
//TODO support anonymous structs and Elm-style update syntax for structs
rule record_block(parser: &mut Parser) -> Vec<(&'input str, Expression)> =
"{" _ entries:(record_entry(parser) ** ",") _ "}" { entries }
rule record_entry(parser: &mut Parser) -> (&'input str, Expression) =
_ name:identifier() _ ":" _ expr:expression(parser) _ { (name, expr) }
rule qualified_identifier(parser: &mut Parser) -> QualifiedName =
names:(identifier() ++ "::") { QualifiedName { id: parser.fresh(), components: names.into_iter().map(|name| Rc::new(name.to_string())).collect() } }
//TODO improve the definition of identifiers
rule identifier() -> &'input str =
!(reserved() !(ident_continuation())) text:$(['a'..='z' | 'A'..='Z' | '_'] ident_continuation()*) { text }
rule ident_continuation() -> &'input str =
text:$(['a'..='z' | 'A'..='Z' | '0'..='9' | '_'])
rule reserved() = "if" / "then" / "else" / "is" / "fn" / "for" / "while" / "let" / "in" / "mut" / "return" /
"break" / "alias" / "type" / "self" / "Self" / "interface" / "impl" / "true" / "false" / "module" / "import"
rule if_expr(parser: &mut Parser) -> ExpressionKind =
"if" _ discriminator:(expression(parser)?) _ body:if_expr_body(parser) {
ExpressionKind::IfExpression {
discriminator: discriminator.map(Box::new),
body: Box::new(body),
}
}
rule if_expr_body(parser: &mut Parser) -> IfExpressionBody =
cond_block(parser) / simple_pattern_match(parser) / simple_conditional(parser)
rule simple_conditional(parser: &mut Parser) -> IfExpressionBody =
"then" _ then_case:expr_or_block(parser) _ else_case:else_case(parser) {
IfExpressionBody::SimpleConditional { then_case, else_case }
}
rule simple_pattern_match(parser: &mut Parser) -> IfExpressionBody =
"is" _ pattern:pattern(parser) _ "then" _ then_case:expr_or_block(parser) _ else_case:else_case(parser) {
IfExpressionBody::SimplePatternMatch { pattern, then_case, else_case }
}
rule cond_block(parser: &mut Parser) -> IfExpressionBody =
"{" __ cond_arms:(cond_arm(parser) ++ (delimiter()+)) __ "}" { IfExpressionBody::CondList(cond_arms) }
rule cond_arm(parser: &mut Parser) -> ConditionArm =
_ "else" _ body:expr_or_block(parser) { ConditionArm { condition: Condition::Else, guard: None, body } } /
_ condition:condition(parser) _ guard:condition_guard(parser) _ "then" _ body:expr_or_block(parser)
{ ConditionArm { condition, guard, body } }
rule condition(parser: &mut Parser) -> Condition =
"is" _ pat:pattern(parser) { Condition::Pattern(pat) } /
op:operator() _ expr:expression(parser) { Condition::TruncatedOp(BinOp::from_sigil(op), expr) }
rule condition_guard(parser: &mut Parser) -> Option<Expression> =
("if" _ expr:expression(parser) { expr } )?
rule expr_or_block(parser: &mut Parser) -> Block = block(parser) / pos:position!() ex:expression(parser) {
Statement {
id: parser.fresh() , location: pos.into(),
kind: StatementKind::Expression(ex)
}.into()
}
rule else_case(parser: &mut Parser) -> Option<Block> =
("else" _ eorb:expr_or_block(parser) { eorb })?
rule pattern(parser: &mut Parser) -> Pattern =
"(" _ variants:(pattern(parser) ++ ",") _ ")" { Pattern::TuplePattern(variants) } /
_ pat:simple_pattern(parser) { pat }
rule simple_pattern(parser: &mut Parser) -> Pattern =
pattern_literal() /
qn:qualified_identifier(parser) "(" members:(pattern(parser) ** ",") ")" {
Pattern::TupleStruct(qn, members)
} /
qn:qualified_identifier(parser) _ "{" _ items:(record_pattern_entry(parser) ** ",") "}" _ {
let items = items.into_iter().map(|(name, pat)| (Rc::new(name.to_string()), pat)).collect();
Pattern::Record(qn, items)
} /
qn:qualified_identifier(parser) { Pattern::VarOrName(qn) }
rule record_pattern_entry(parser: &mut Parser) -> (&'input str, Pattern) =
_ name:identifier() _ ":" _ pat:pattern(parser) _ { (name, pat) } /
_ name:identifier() _ {
let qn = QualifiedName {
id: parser.fresh(),
components: vec![Rc::new(name.to_string())],
};
(name, Pattern::VarOrName(qn))
}
rule pattern_literal() -> Pattern =
"true" { Pattern::Literal(PatternLiteral::BoolPattern(true)) } /
"false" { Pattern::Literal(PatternLiteral::BoolPattern(false)) } /
s:bare_string_literal() { Pattern::Literal(PatternLiteral::StringPattern(Rc::new(s))) } /
sign:("-"?) num:(float_literal() / nat_literal()) {
let neg = sign.is_some();
Pattern::Literal(PatternLiteral::NumPattern { neg, num })
} /
"_" { Pattern::Ignored }
rule list_expr(parser: &mut Parser) -> ExpressionKind =
"[" exprs:(expression(parser) ** ",") "]" {
let mut exprs = exprs;
ExpressionKind::ListLiteral(exprs)
}
rule paren_expr(parser: &mut Parser) -> ExpressionKind =
"(" exprs:(expression(parser) ** ",") ")" {
let mut exprs = exprs;
match exprs.len() {
1 => exprs.pop().unwrap().kind,
_ => ExpressionKind::TupleLiteral(exprs),
}
}
rule string_literal() -> ExpressionKind =
prefix:identifier()? s:bare_string_literal(){ ExpressionKind::StringLiteral{ s: Rc::new(s),
prefix: prefix.map(rc_string)
} }
rule bare_string_literal() -> String =
"\"" chars:string_component()* "\"" { chars.into_iter().collect::<String>() }
rule string_component() -> char =
!(r#"""# / r#"\"#) ch:$([_]) { ch.chars().next().unwrap() } /
r#"\u{"# value:$(['0'..='9' | 'a'..='f' | 'A'..='F']+) "}" { char::from_u32(u32::from_str_radix(value, 16).unwrap()).unwrap() } /
r#"\n"# { '\n' } / r#"\t"# { '\t' } / r#"\""# { '"' } / r#"\\"# { '\\' } /
expected!("Valid escape sequence")
rule bool_literal() -> ExpressionKind =
"true" { ExpressionKind::BoolLiteral(true) } / "false" { ExpressionKind::BoolLiteral(false) }
rule nat_literal() -> ExpressionKind =
bin_literal() / hex_literal() / unmarked_literal()
rule unmarked_literal() -> ExpressionKind =
digits:digits() { let n = digits.chars().filter(|ch| *ch != '_').collect::<String>().parse().unwrap(); ExpressionKind::NatLiteral(n) }
rule bin_literal() -> ExpressionKind =
"0b" digits:bin_digits() {? parse_binary(digits).map(ExpressionKind::NatLiteral) }
rule hex_literal() -> ExpressionKind =
"0x" digits:hex_digits() {? parse_hex(digits).map(ExpressionKind::NatLiteral) }
rule float_literal() -> ExpressionKind =
ds:$( digits() "." digits()? / "." digits() ) { ExpressionKind::FloatLiteral(ds.parse().unwrap()) }
rule digits() -> &'input str = $((digit_group() "_"*)+)
rule bin_digits() -> &'input str = $((bin_digit_group() "_"*)+)
rule hex_digits() -> &'input str = $((hex_digit_group() "_"*)+)
rule digit_group() -> &'input str = $(['0'..='9']+)
rule bin_digit_group() -> &'input str = $(['0' | '1']+)
rule hex_digit_group() -> &'input str = $(['0'..='9' | 'a'..='f' | 'A'..='F']+)
}
}
fn parse_binary(digits: &str) -> Result<u64, &'static str> {
let mut result: u64 = 0;
let mut multiplier = 1;
for d in digits.chars().rev() {
match d {
'1' => result += multiplier,
'0' => (),
'_' => continue,
_ => unreachable!(),
}
multiplier = match multiplier.checked_mul(2) {
Some(m) => m,
None => return Err("Binary expression will overflow"),
}
}
Ok(result)
}
fn parse_hex(digits: &str) -> Result<u64, &'static str> {
let mut result: u64 = 0;
let mut multiplier: u64 = 1;
for d in digits.chars().rev() {
if d == '_' {
continue;
}
match d.to_digit(16) {
Some(n) => result += n as u64 * multiplier,
None => return Err("Internal parser error: invalid hex digit"),
}
multiplier = match multiplier.checked_mul(16) {
Some(m) => m,
None => return Err("Hexadecimal expression will overflow"),
}
}
Ok(result)
}
#[derive(Debug)]
struct BinopSequence {
first: ExpressionKind,
next: Vec<(BinOp, ExpressionKind)>,
}
impl BinopSequence {
fn do_precedence(self, parser: &mut Parser) -> ExpressionKind {
fn helper(
precedence: i32,
lhs: ExpressionKind,
rest: &mut Vec<(BinOp, ExpressionKind)>,
parser: &mut Parser,
) -> Expression {
let mut lhs = Expression::new(parser.fresh(), lhs);
while let Some((next_op, next_rhs)) = rest.pop() {
let new_precedence = next_op.get_precedence();
if precedence >= new_precedence {
rest.push((next_op, next_rhs));
break;
}
let rhs = helper(new_precedence, next_rhs, rest, parser);
lhs = Expression::new(
parser.fresh(),
ExpressionKind::BinExp(next_op, Box::new(lhs), Box::new(rhs)),
);
}
lhs
}
let mut as_stack = self.next.into_iter().rev().collect();
helper(BinOp::min_precedence(), self.first, &mut as_stack, parser).kind
}
}

File diff suppressed because it is too large Load Diff

View File

@ -1,484 +0,0 @@
use std::{collections::HashMap, rc::Rc, str::FromStr};
use crate::{
ast,
builtin::Builtin,
symbol_table::{DefId, SymbolSpec, SymbolTable},
type_inference::{TypeContext, TypeId},
};
mod test;
mod types;
pub use types::*;
pub fn reduce(ast: &ast::AST, symbol_table: &SymbolTable, type_context: &TypeContext) -> ReducedIR {
let reducer = Reducer::new(symbol_table, type_context);
reducer.reduce(ast)
}
struct Reducer<'a, 'b> {
symbol_table: &'a SymbolTable,
functions: HashMap<DefId, FunctionDefinition>,
type_context: &'b TypeContext,
}
impl<'a, 'b> Reducer<'a, 'b> {
fn new(symbol_table: &'a SymbolTable, type_context: &'b TypeContext) -> Self {
Self { symbol_table, functions: HashMap::new(), type_context }
}
fn reduce(mut self, ast: &ast::AST) -> ReducedIR {
// First reduce all functions
// TODO once this works, maybe rewrite it using the Visitor
for statement in ast.statements.statements.iter() {
self.top_level_definition(statement);
}
// Then compute the entrypoint statements (which may reference previously-computed
// functions by ID)
let mut entrypoint = vec![];
for statement in ast.statements.statements.iter() {
let ast::Statement { id: item_id, kind, .. } = statement;
match &kind {
ast::StatementKind::Expression(expr) => {
entrypoint.push(Statement::Expression(self.expression(expr)));
}
ast::StatementKind::Declaration(ast::Declaration::Binding {
name: _,
constant,
expr,
..
}) => {
let symbol = self.symbol_table.lookup_symbol(item_id).unwrap();
entrypoint.push(Statement::Binding {
id: symbol.def_id(),
constant: *constant,
expr: self.expression(expr),
});
}
_ => (),
}
}
ReducedIR { functions: self.functions, entrypoint }
}
fn top_level_definition(&mut self, statement: &ast::Statement<ast::StatementKind>) {
let ast::Statement { id: item_id, kind, .. } = statement;
match kind {
ast::StatementKind::Expression(_expr) => {
//TODO expressions can in principle contain definitions, but I won't worry
//about it now
}
ast::StatementKind::Declaration(decl) => match decl {
ast::Declaration::FuncDecl(_, statements) => {
self.insert_function_definition(item_id, statements);
}
ast::Declaration::Impl { type_name: _, interface_name: _, block } =>
for item in block {
if let ast::Statement {
id: item_id,
kind: ast::Declaration::FuncDecl(_, statements),
..
} = item
{
self.insert_function_definition(item_id, statements);
}
},
_ => (),
},
// Imports should have already been processed by the symbol table and are irrelevant
// for this representation.
ast::StatementKind::Import(..) => (),
ast::StatementKind::Flow(..) => {
//TODO this should be an error
}
}
}
fn function_internal_statement(
&mut self,
statement: &ast::Statement<ast::StatementKind>,
) -> Option<Statement> {
let ast::Statement { id: item_id, kind, .. } = statement;
match kind {
ast::StatementKind::Expression(expr) => Some(Statement::Expression(self.expression(expr))),
ast::StatementKind::Declaration(decl) => match decl {
ast::Declaration::FuncDecl(_, statements) => {
self.insert_function_definition(item_id, statements);
None
}
ast::Declaration::Binding { constant, expr, .. } => {
let symbol = self.symbol_table.lookup_symbol(item_id).unwrap();
Some(Statement::Binding {
id: symbol.def_id(),
constant: *constant,
expr: self.expression(expr),
})
}
_ => None,
},
ast::StatementKind::Import(_) => None,
ast::StatementKind::Flow(ast::FlowControl::Return(expr)) =>
if let Some(expr) = expr {
Some(Statement::Return(self.expression(expr)))
} else {
Some(Statement::Return(Expression::unit()))
},
ast::StatementKind::Flow(ast::FlowControl::Break) => Some(Statement::Break),
ast::StatementKind::Flow(ast::FlowControl::Continue) => Some(Statement::Continue),
}
}
fn insert_function_definition(&mut self, item_id: &ast::ItemId, statements: &ast::Block) {
let symbol = self.symbol_table.lookup_symbol(item_id).unwrap();
let function_def = FunctionDefinition { body: self.function_internal_block(statements) };
self.functions.insert(symbol.def_id(), function_def);
}
//TODO this needs to be type-aware to work correctly
fn lookup_method(&mut self, name: &str) -> Option<DefId> {
for (def_id, function) in self.functions.iter() {
let symbol = self.symbol_table.lookup_symbol_by_def(def_id)?;
println!("Def Id: {} symbol: {:?}", def_id, symbol);
if symbol.local_name() == name {
return Some(*def_id);
}
}
None
}
fn expression(&mut self, expr: &ast::Expression) -> Expression {
use crate::ast::ExpressionKind::*;
match &expr.kind {
SelfValue => Expression::Lookup(Lookup::SelfParam),
NatLiteral(n) => Expression::Literal(Literal::Nat(*n)),
FloatLiteral(f) => Expression::Literal(Literal::Float(*f)),
//TODO implement handling string literal prefixes
StringLiteral { s, prefix: _ } => Expression::Literal(Literal::StringLit(s.clone())),
BoolLiteral(b) => Expression::Literal(Literal::Bool(*b)),
BinExp(binop, lhs, rhs) => self.binop(binop, lhs, rhs),
PrefixExp(op, arg) => self.prefix(op, arg),
Value(qualified_name) => self.value(qualified_name),
Call { f, arguments } => {
let f = self.expression(f);
let args = arguments.iter().map(|arg| self.invocation_argument(arg)).collect();
//TODO need to have full type availability at this point to do this method lookup
//correctly
if let Expression::Access { name, expr } = f {
let def_id = self.lookup_method(&name).unwrap();
let method = Expression::Lookup(Lookup::Function(def_id));
Expression::CallMethod { f: Box::new(method), args, self_expr: expr }
} else {
Expression::Call { f: Box::new(f), args }
}
}
TupleLiteral(exprs) => Expression::Tuple(exprs.iter().map(|e| self.expression(e)).collect()),
IfExpression { discriminator, body } =>
self.reduce_if_expression(discriminator.as_ref().map(|x| x.as_ref()), body),
Lambda { params, body, .. } => Expression::Callable(Callable::Lambda {
arity: params.len() as u8,
body: self.function_internal_block(body),
}),
NamedStruct { name, fields } => {
let symbol = match self.symbol_table.lookup_symbol(&name.id) {
Some(symbol) => symbol,
None => return Expression::ReductionError(format!("No symbol found for {}", name)),
};
let (tag, type_id) = match symbol.spec() {
SymbolSpec::RecordConstructor { tag, type_id } => (tag, type_id),
e => return Expression::ReductionError(format!("Bad symbol for NamedStruct: {:?}", e)),
};
let field_order = compute_field_orderings(self.type_context, &type_id, tag).unwrap();
let mut field_map = HashMap::new();
for (name, expr) in fields.iter() {
field_map.insert(name.as_ref(), expr);
}
let mut ordered_args = vec![];
for field in field_order.iter() {
let expr = match field_map.get(&field) {
Some(expr) => expr,
None =>
return Expression::ReductionError(format!(
"Field {} not specified for record {}",
field, name
)),
};
ordered_args.push(self.expression(expr));
}
let constructor =
Expression::Callable(Callable::RecordConstructor { type_id, tag, field_order });
Expression::Call { f: Box::new(constructor), args: ordered_args }
}
Index { indexee, indexers } => self.reduce_index(indexee.as_ref(), indexers.as_slice()),
WhileExpression { condition, body } => {
let cond = Box::new(if let Some(condition) = condition {
self.expression(condition)
} else {
Expression::Literal(Literal::Bool(true))
});
let statements = self.function_internal_block(body);
Expression::Loop { cond, statements }
}
ForExpression { .. } => Expression::ReductionError("For expr not implemented".to_string()),
ListLiteral(items) => Expression::List(items.iter().map(|item| self.expression(item)).collect()),
Access { name, expr } =>
Expression::Access { name: name.as_ref().to_string(), expr: Box::new(self.expression(expr)) },
}
}
//TODO figure out the semantics of multiple indexers - for now, just ignore them
fn reduce_index(&mut self, indexee: &ast::Expression, indexers: &[ast::Expression]) -> Expression {
if indexers.len() != 1 {
return Expression::ReductionError("Invalid index expression".to_string());
}
let indexee = self.expression(indexee);
let indexer = self.expression(&indexers[0]);
Expression::Index { indexee: Box::new(indexee), indexer: Box::new(indexer) }
}
fn reduce_if_expression(
&mut self,
discriminator: Option<&ast::Expression>,
body: &ast::IfExpressionBody,
) -> Expression {
use ast::IfExpressionBody::*;
let cond = Box::new(match discriminator {
Some(expr) => self.expression(expr),
None => return Expression::ReductionError("blank cond if-expr not supported".to_string()),
});
match body {
SimpleConditional { then_case, else_case } => {
let then_clause = self.function_internal_block(then_case);
let else_clause = match else_case.as_ref() {
None => vec![],
Some(stmts) => self.function_internal_block(stmts),
};
Expression::Conditional { cond, then_clause, else_clause }
}
SimplePatternMatch { pattern, then_case, else_case } => {
let alternatives = vec![
Alternative {
pattern: match pattern.reduce(self.symbol_table) {
Ok(p) => p,
Err(e) => return Expression::ReductionError(format!("Bad pattern: {:?}", e)),
},
item: self.function_internal_block(then_case),
},
Alternative {
pattern: Pattern::Ignored,
item: match else_case.as_ref() {
Some(else_case) => self.function_internal_block(else_case),
None => vec![],
},
},
];
Expression::CaseMatch { cond, alternatives }
}
CondList(ref condition_arms) => {
let mut alternatives = vec![];
for arm in condition_arms {
match arm.condition {
ast::Condition::Pattern(ref pat) => {
let alt = Alternative {
pattern: match pat.reduce(self.symbol_table) {
Ok(p) => p,
Err(e) =>
return Expression::ReductionError(format!("Bad pattern: {:?}", e)),
},
item: self.function_internal_block(&arm.body),
};
alternatives.push(alt);
}
ast::Condition::TruncatedOp(_, _) =>
return Expression::ReductionError("case-expression-trunc-op".to_string()),
ast::Condition::Else =>
return Expression::ReductionError("case-expression-else".to_string()),
}
}
Expression::CaseMatch { cond, alternatives }
}
}
}
fn invocation_argument(&mut self, invoc: &ast::InvocationArgument) -> Expression {
use crate::ast::InvocationArgument::*;
match invoc {
Positional(ex) => self.expression(ex),
Keyword { .. } => Expression::ReductionError("Keyword arguments not supported".to_string()),
Ignored => Expression::ReductionError("Ignored arguments not supported".to_string()),
}
}
fn function_internal_block(&mut self, block: &ast::Block) -> Vec<Statement> {
block.statements.iter().filter_map(|stmt| self.function_internal_statement(stmt)).collect()
}
fn prefix(&mut self, prefix: &ast::PrefixOp, arg: &ast::Expression) -> Expression {
let builtin: Option<Builtin> = TryFrom::try_from(prefix).ok();
match builtin {
Some(op) => Expression::Call {
f: Box::new(Expression::Callable(Callable::Builtin(op))),
args: vec![self.expression(arg)],
},
None => {
//TODO need this for custom prefix ops
Expression::ReductionError("User-defined prefix ops not supported".to_string())
}
}
}
fn binop(&mut self, binop: &ast::BinOp, lhs: &ast::Expression, rhs: &ast::Expression) -> Expression {
use Expression::ReductionError;
let operation = Builtin::from_str(binop.sigil()).ok();
match operation {
Some(Builtin::Assignment) => {
let lval = match &lhs.kind {
ast::ExpressionKind::Value(qualified_name) => {
if let Some(symbol) = self.symbol_table.lookup_symbol(&qualified_name.id) {
symbol.def_id()
} else {
return ReductionError(format!("Couldn't look up name: {:?}", qualified_name));
}
}
_ => return ReductionError("Trying to assign to a non-name".to_string()),
};
Expression::Assign { lval, rval: Box::new(self.expression(rhs)) }
}
Some(op) => Expression::Call {
f: Box::new(Expression::Callable(Callable::Builtin(op))),
args: vec![self.expression(lhs), self.expression(rhs)],
},
//TODO handle a user-defined operation
None => ReductionError("User-defined operations not supported".to_string()),
}
}
fn value(&mut self, qualified_name: &ast::QualifiedName) -> Expression {
use SymbolSpec::*;
let symbol = match self.symbol_table.lookup_symbol(&qualified_name.id) {
Some(s) => s,
None =>
return Expression::ReductionError(format!("No symbol found for name: `{}`", qualified_name)),
};
let def_id = symbol.def_id();
match symbol.spec() {
Builtin(b) => Expression::Callable(Callable::Builtin(b)),
Func { .. } => Expression::Lookup(Lookup::Function(def_id)),
GlobalBinding => Expression::Lookup(Lookup::GlobalVar(def_id)),
LocalVariable => Expression::Lookup(Lookup::LocalVar(def_id)),
FunctionParam(n) => Expression::Lookup(Lookup::Param(n)),
DataConstructor { tag, type_id } =>
Expression::Callable(Callable::DataConstructor { type_id, tag }),
RecordConstructor { .. } => Expression::ReductionError(format!(
"The symbol for value {:?} is unexpectdly a RecordConstructor",
qualified_name
)),
}
}
}
impl ast::Pattern {
fn reduce(&self, symbol_table: &SymbolTable) -> Result<Pattern, PatternError> {
Ok(match self {
ast::Pattern::Ignored => Pattern::Ignored,
ast::Pattern::TuplePattern(subpatterns) => {
let items: Result<Vec<Pattern>, PatternError> =
subpatterns.iter().map(|pat| pat.reduce(symbol_table)).into_iter().collect();
let items = items?;
Pattern::Tuple { tag: None, subpatterns: items }
}
ast::Pattern::Literal(lit) => Pattern::Literal(match lit {
ast::PatternLiteral::NumPattern { neg, num } => match (neg, num) {
(false, ast::ExpressionKind::NatLiteral(n)) => Literal::Nat(*n),
(false, ast::ExpressionKind::FloatLiteral(f)) => Literal::Float(*f),
(true, ast::ExpressionKind::NatLiteral(n)) => Literal::Int(-(*n as i64)),
(true, ast::ExpressionKind::FloatLiteral(f)) => Literal::Float(-f),
(_, e) =>
return Err(format!("Internal error, unexpected pattern literal: {:?}", e).into()),
},
ast::PatternLiteral::StringPattern(s) => Literal::StringLit(s.clone()),
ast::PatternLiteral::BoolPattern(b) => Literal::Bool(*b),
}),
ast::Pattern::TupleStruct(name, subpatterns) => {
let symbol = symbol_table.lookup_symbol(&name.id).unwrap();
if let SymbolSpec::DataConstructor { tag, type_id: _ } = symbol.spec() {
let items: Result<Vec<Pattern>, PatternError> =
subpatterns.iter().map(|pat| pat.reduce(symbol_table)).into_iter().collect();
let items = items?;
Pattern::Tuple { tag: Some(tag), subpatterns: items }
} else {
return Err(
"Internal error, trying to match something that's not a DataConstructor".into()
);
}
}
ast::Pattern::VarOrName(name) => {
let symbol = symbol_table.lookup_symbol(&name.id).unwrap();
match symbol.spec() {
SymbolSpec::DataConstructor { tag, type_id: _ } =>
Pattern::Tuple { tag: Some(tag), subpatterns: vec![] },
SymbolSpec::LocalVariable => {
let def_id = symbol.def_id();
Pattern::Binding(def_id)
}
spec => return Err(format!("Unexpected VarOrName symbol: {:?}", spec).into()),
}
}
ast::Pattern::Record(name, specified_members) => {
let symbol = symbol_table.lookup_symbol(&name.id).unwrap();
if let SymbolSpec::RecordConstructor { tag, type_id: _ } = symbol.spec() {
//TODO do this computation from the type_id
/*
if specified_members.iter().any(|(member, _)| !members.contains_key(member)) {
return Err(format!("Unknown key in record pattern").into());
}
*/
let subpatterns: Result<Vec<(Rc<String>, Pattern)>, PatternError> = specified_members
.iter()
.map(|(name, pat)| {
pat.reduce(symbol_table).map(|reduced_pat| (name.clone(), reduced_pat))
})
.into_iter()
.collect();
let subpatterns = subpatterns?;
Pattern::Record { tag, subpatterns }
} else {
return Err(format!("Unexpected Record pattern symbol: {:?}", symbol.spec()).into());
}
}
})
}
}
/// Given the type context and a variant, compute what order the fields on it were stored.
/// This needs to be public until type-checking is fully implemented because the type information
/// is only available at runtime.
pub fn compute_field_orderings(
type_context: &TypeContext,
type_id: &TypeId,
tag: u32,
) -> Option<Vec<String>> {
// Eventually, the ReducedIR should decide what field ordering is optimal.
// For now, just do it alphabetically.
let record_members = type_context.lookup_record_members(type_id, tag)?;
let mut field_order: Vec<String> =
record_members.iter().map(|(field, _type_id)| field).cloned().collect();
field_order.sort_unstable();
Some(field_order)
}

View File

@ -1,61 +0,0 @@
#![cfg(test)]
use super::*;
use crate::{symbol_table::SymbolTable, type_inference::TypeContext};
fn build_ir(input: &str) -> ReducedIR {
let ast = crate::util::quick_ast(input);
let mut symbol_table = SymbolTable::new();
let mut type_context = TypeContext::new();
symbol_table.process_ast(&ast, &mut type_context).unwrap();
let reduced = reduce(&ast, &symbol_table, &type_context);
reduced.debug(&symbol_table);
reduced
}
#[test]
fn test_ir() {
let src = r#"
let global_one = 10 + 20
let global_two = "the string hello"
fn a_function(i, j, k) {
fn nested(x) {
x + 10
}
i + j * nested(k)
}
fn another_function(e) {
let local_var = 420
e * local_var
}
another_function()
"#;
let reduced = build_ir(src);
assert_eq!(reduced.functions.len(), 3);
}
#[test]
fn test_methods() {
let src = r#"
type Thing = Thing
impl Thing {
fn a_method() {
20
}
}
let a = Thing
4 + a.a_method()
"#;
let reduced = build_ir(src);
assert_eq!(reduced.functions.len(), 1);
}

View File

@ -1,137 +0,0 @@
use std::{collections::HashMap, convert::From, rc::Rc};
use crate::{
builtin::Builtin,
symbol_table::{DefId, SymbolTable},
type_inference::TypeId,
};
//TODO most of these Clone impls only exist to support function application, because the
//tree-walking evaluator moves the reduced IR members.
/// The reduced intermediate representation consists of a list of function definitions, and a block
/// of entrypoint statements. In a repl or script context this can be an arbitrary list of
/// statements, in an executable context will likely just be a pointer to the main() function.
#[derive(Debug)]
pub struct ReducedIR {
pub functions: HashMap<DefId, FunctionDefinition>,
pub entrypoint: Vec<Statement>,
}
impl ReducedIR {
#[allow(dead_code)]
pub fn debug(&self, symbol_table: &SymbolTable) {
println!("Reduced IR:");
println!("Functions:");
println!("-----------");
for (id, callable) in self.functions.iter() {
let name = &symbol_table.lookup_symbol_by_def(id).unwrap().local_name();
println!("{}({}) -> {:?}", id, name, callable);
}
println!();
println!("Entrypoint:");
println!("-----------");
for stmt in self.entrypoint.iter() {
println!("{:?}", stmt);
}
println!("-----------");
}
}
#[derive(Debug, Clone)]
pub enum Statement {
Expression(Expression),
Binding { id: DefId, constant: bool, expr: Expression },
Return(Expression),
Continue,
Break,
}
#[derive(Debug, Clone)]
pub enum Expression {
Literal(Literal),
Tuple(Vec<Expression>),
List(Vec<Expression>),
Lookup(Lookup),
Assign { lval: DefId, rval: Box<Expression> },
Access { name: String, expr: Box<Expression> },
Callable(Callable),
Call { f: Box<Expression>, args: Vec<Expression> },
CallMethod { f: Box<Expression>, args: Vec<Expression>, self_expr: Box<Expression> },
Conditional { cond: Box<Expression>, then_clause: Vec<Statement>, else_clause: Vec<Statement> },
CaseMatch { cond: Box<Expression>, alternatives: Vec<Alternative> },
Loop { cond: Box<Expression>, statements: Vec<Statement> },
Index { indexee: Box<Expression>, indexer: Box<Expression> },
ReductionError(String),
}
impl Expression {
pub fn unit() -> Self {
Expression::Tuple(vec![])
}
}
#[derive(Debug)]
pub struct FunctionDefinition {
pub body: Vec<Statement>,
}
#[derive(Debug, Clone)]
pub enum Callable {
Builtin(Builtin),
UserDefined(DefId),
Lambda { arity: u8, body: Vec<Statement> },
DataConstructor { type_id: TypeId, tag: u32 },
RecordConstructor { type_id: TypeId, tag: u32, field_order: Vec<String> },
}
#[derive(Debug, Clone)]
pub enum Lookup {
LocalVar(DefId),
GlobalVar(DefId),
Function(DefId),
Param(u8),
SelfParam,
}
#[derive(Debug, Clone, PartialEq)]
pub enum Literal {
Nat(u64),
Int(i64),
Float(f64),
Bool(bool),
StringLit(Rc<String>),
}
#[derive(Debug, Clone)]
pub struct Alternative {
pub pattern: Pattern,
pub item: Vec<Statement>,
}
#[derive(Debug, Clone)]
pub enum Pattern {
Tuple { subpatterns: Vec<Pattern>, tag: Option<u32> },
Record { tag: u32, subpatterns: Vec<(Rc<String>, Pattern)> },
Literal(Literal),
Ignored,
Binding(DefId),
}
#[allow(dead_code)]
#[derive(Debug)]
pub struct PatternError {
msg: String,
}
impl From<&str> for PatternError {
fn from(s: &str) -> Self {
Self { msg: s.to_string() }
}
}
impl From<String> for PatternError {
fn from(msg: String) -> Self {
Self { msg }
}
}

View File

@ -1,210 +0,0 @@
use schala_repl::{
ComputationRequest, ComputationResponse, GlobalOutputStats, LangMetaRequest, LangMetaResponse,
ProgrammingLanguageInterface,
};
use stopwatch::Stopwatch;
use crate::{error::SchalaError, parsing, reduced_ir, symbol_table, tree_walk_eval, type_inference};
/// All the state necessary to parse and execute a Schala program are stored in this struct.
pub struct Schala<'a> {
/// Holds a reference to the original source code, parsed into line and character
source_reference: SourceReference,
//state: eval::State<'static>,
/// Keeps track of symbols and scopes
symbol_table: symbol_table::SymbolTable,
/// Contains information for type-checking
type_context: type_inference::TypeContext,
/// Schala Parser
active_parser: parsing::Parser,
/// Execution state for AST-walking interpreter
eval_state: tree_walk_eval::State<'a>,
timings: Vec<(&'static str, std::time::Duration)>,
}
/*
impl Schala {
//TODO implement documentation for language items
/*
fn handle_docs(&self, source: String) -> LangMetaResponse {
LangMetaResponse::Docs {
doc_string: format!("Schala item `{}` : <<Schala-lang documentation not yet implemented>>", source)
}
}
*/
}
*/
impl<'a> Schala<'a> {
/// Creates a new Schala environment *without* any prelude.
fn new_blank_env() -> Schala<'a> {
Schala {
source_reference: SourceReference::new(),
symbol_table: symbol_table::SymbolTable::new(),
type_context: type_inference::TypeContext::new(),
active_parser: parsing::Parser::new(),
eval_state: tree_walk_eval::State::new(),
timings: Vec::new(),
}
}
/// Creates a new Schala environment with the standard prelude, which is defined as ordinary
/// Schala code in the file `prelude.schala`
#[allow(clippy::new_without_default)]
pub fn new() -> Schala<'a> {
let prelude = include_str!("../source-files/prelude.schala");
let mut env = Schala::new_blank_env();
let response = env.run_pipeline(prelude, SchalaConfig::default());
if let Err(err) = response {
panic!("Error in prelude, panicking: {}", err.display());
}
env
}
/// This is where the actual action of interpreting/compilation happens.
/// Note: this should eventually use a query-based system for parallelization, cf.
/// https://rustc-dev-guide.rust-lang.org/overview.html
fn run_pipeline(&mut self, source: &str, config: SchalaConfig) -> Result<String, SchalaError> {
self.timings = vec![];
let sw = Stopwatch::start_new();
self.source_reference.load_new_source(source);
let ast = self
.active_parser
.parse(source)
.map_err(|err| SchalaError::from_parse_error(err, &self.source_reference))?;
self.timings.push(("parsing", sw.elapsed()));
let sw = Stopwatch::start_new();
//Perform all symbol table work
self.symbol_table
.process_ast(&ast, &mut self.type_context)
.map_err(SchalaError::from_symbol_table)?;
self.timings.push(("symbol_table", sw.elapsed()));
// Typechecking
let _overall_type = self.type_context.typecheck(&ast).map_err(SchalaError::from_type_error);
let sw = Stopwatch::start_new();
let reduced_ir = reduced_ir::reduce(&ast, &self.symbol_table, &self.type_context);
self.timings.push(("reduced_ir", sw.elapsed()));
let sw = Stopwatch::start_new();
let evaluation_outputs = self.eval_state.evaluate(reduced_ir, &self.type_context, config.repl);
self.timings.push(("tree-walking-evaluation", sw.elapsed()));
let text_output: Result<Vec<String>, String> = evaluation_outputs.into_iter().collect();
let text_output: Result<Vec<String>, SchalaError> =
text_output.map_err(|err| SchalaError::from_string(err, Stage::Evaluation));
let eval_output: String =
text_output.map(|v| Iterator::intersperse(v.into_iter(), "\n".to_owned()).collect())?;
Ok(eval_output)
}
}
/// Represents lines of source code
pub(crate) struct SourceReference {
last_source: Option<String>,
/// Offsets in *bytes* (not chars) representing a newline character
newline_offsets: Vec<usize>,
}
impl SourceReference {
pub(crate) fn new() -> SourceReference {
SourceReference { last_source: None, newline_offsets: vec![] }
}
pub(crate) fn load_new_source(&mut self, source: &str) {
self.newline_offsets = vec![];
for (offset, ch) in source.as_bytes().iter().enumerate() {
if *ch == b'\n' {
self.newline_offsets.push(offset);
}
}
self.last_source = Some(source.to_string());
}
// (line_start, line_num, the string itself)
pub fn get_line(&self, line: usize) -> (usize, usize, String) {
if self.newline_offsets.is_empty() {
return (0, 0, self.last_source.as_ref().cloned().unwrap());
}
//TODO make sure this is utf8-safe
let start_idx = match self.newline_offsets.binary_search(&line) {
Ok(index) | Err(index) => index,
};
let last_source = self.last_source.as_ref().unwrap();
let start = self.newline_offsets[start_idx];
let end = self.newline_offsets.get(start_idx + 1).cloned().unwrap_or_else(|| last_source.len());
let slice = &last_source.as_bytes()[start..end];
(start, start_idx, std::str::from_utf8(slice).unwrap().to_string())
}
}
#[allow(dead_code)]
#[derive(Clone, Copy, Debug)]
pub(crate) enum Stage {
Parsing,
Symbols,
ScopeResolution,
Typechecking,
AstReduction,
Evaluation,
}
fn stage_names() -> Vec<&'static str> {
vec!["parsing", "symbol-table", "typechecking", "ast-reduction", "ast-walking-evaluation"]
}
#[derive(Default, Clone)]
pub struct SchalaConfig {
pub repl: bool,
}
impl<'a> ProgrammingLanguageInterface for Schala<'a> {
//TODO flesh out Config
type Config = SchalaConfig;
fn language_name() -> String {
"Schala".to_owned()
}
fn source_file_suffix() -> String {
"schala".to_owned()
}
fn run_computation(&mut self, request: ComputationRequest<Self::Config>) -> ComputationResponse {
let ComputationRequest { source, debug_requests: _, config: _ } = request;
let sw = Stopwatch::start_new();
let main_output =
self.run_pipeline(source, request.config).map_err(|schala_err| schala_err.display());
let total_duration = sw.elapsed();
let stage_durations: Vec<_> = std::mem::take(&mut self.timings)
.into_iter()
.map(|(label, duration)| (label.to_string(), duration))
.collect();
let global_output_stats = GlobalOutputStats { total_duration, stage_durations };
ComputationResponse { main_output, global_output_stats, debug_responses: vec![] }
}
fn request_meta(&mut self, request: LangMetaRequest) -> LangMetaResponse {
match request {
LangMetaRequest::StageNames =>
LangMetaResponse::StageNames(stage_names().iter().map(|s| s.to_string()).collect()),
_ => LangMetaResponse::Custom { kind: "not-implemented".to_string(), value: "".to_string() },
}
}
}

View File

@ -1,65 +0,0 @@
use std::{fmt, rc::Rc};
/// Fully-qualified symbol name
#[derive(Debug, Clone, Eq, PartialEq, Hash, PartialOrd, Ord)]
pub struct Fqsn {
//TODO Fqsn's need to be cheaply cloneable
pub scopes: Vec<ScopeSegment>,
}
impl Fqsn {
pub fn from_scope_stack(scopes: &[ScopeSegment], new_name: Rc<String>) -> Self {
let mut v = Vec::new();
for s in scopes {
v.push(s.clone());
}
v.push(ScopeSegment::Name(new_name));
Fqsn { scopes: v }
}
pub fn extend(&self, new_item: &str) -> Self {
let mut new = self.clone();
new.scopes.push(ScopeSegment::Name(Rc::new(new_item.to_string())));
new
}
#[allow(dead_code)]
pub fn from_strs(strs: &[&str]) -> Fqsn {
let mut scopes = vec![];
for s in strs {
scopes.push(ScopeSegment::Name(Rc::new(s.to_string())));
}
Fqsn { scopes }
}
pub fn last_elem(&self) -> Rc<String> {
let ScopeSegment::Name(name) = self.scopes.last().unwrap();
name.clone()
}
}
impl fmt::Display for Fqsn {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let delim = "::";
let Fqsn { scopes } = self;
write!(f, "FQSN<{}", scopes[0])?;
for item in scopes[1..].iter() {
write!(f, "{}{}", delim, item)?;
}
write!(f, ">")
}
}
//TODO eventually this should use ItemId's to avoid String-cloning
/// One segment within a scope.
#[derive(Debug, Clone, Eq, PartialEq, Hash, PartialOrd, Ord)]
pub enum ScopeSegment {
Name(Rc<String>),
}
impl fmt::Display for ScopeSegment {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let ScopeSegment::Name(name) = self;
write!(f, "{}", name)
}
}

View File

@ -1,244 +0,0 @@
#![allow(clippy::enum_variant_names)]
use std::{
collections::{hash_map::Entry, HashMap},
fmt,
rc::Rc,
};
use crate::{
ast,
ast::ItemId,
builtin::Builtin,
parsing::Location,
type_inference::{TypeContext, TypeId},
};
mod populator;
use populator::SymbolTablePopulator;
mod fqsn;
pub use fqsn::{Fqsn, ScopeSegment};
mod resolver;
mod symbol_trie;
use symbol_trie::SymbolTrie;
mod test;
use crate::identifier::{define_id_kind, Id, IdStore};
define_id_kind!(DefItem);
pub type DefId = Id<DefItem>;
#[allow(dead_code)]
#[derive(Debug, Clone)]
pub enum SymbolError {
DuplicateName { prev_name: Fqsn, location: Location },
DuplicateVariant { type_fqsn: Fqsn, name: String },
DuplicateRecord { type_fqsn: Fqsn, location: Location, record: String, member: String },
UnknownAnnotation { name: String },
BadAnnotation { name: String, msg: String },
BadImplBlockEntry,
}
#[allow(dead_code)]
#[derive(Debug)]
struct NameSpec<K> {
location: Location,
kind: K,
}
#[derive(Debug)]
enum NameKind {
Module,
Function,
Binding,
}
#[derive(Debug)]
enum TypeKind {
Function,
Constructor,
}
/// Keeps track of what names were used in a given namespace.
struct NameTable<K> {
table: HashMap<Fqsn, NameSpec<K>>,
}
impl<K> NameTable<K> {
fn new() -> Self {
Self { table: HashMap::new() }
}
fn register(&mut self, name: Fqsn, spec: NameSpec<K>) -> Result<(), SymbolError> {
match self.table.entry(name.clone()) {
Entry::Occupied(o) =>
Err(SymbolError::DuplicateName { prev_name: name, location: o.get().location }),
Entry::Vacant(v) => {
v.insert(spec);
Ok(())
}
}
}
}
//cf. p. 150 or so of Language Implementation Patterns
pub struct SymbolTable {
def_id_store: IdStore<DefItem>,
/// Used for import resolution.
symbol_trie: SymbolTrie,
/// These tables are responsible for preventing duplicate names.
fq_names: NameTable<NameKind>, //Note that presence of two tables implies that a type and other binding with the same name can co-exist
types: NameTable<TypeKind>,
id_to_def: HashMap<ItemId, DefId>,
def_to_symbol: HashMap<DefId, Rc<Symbol>>,
}
impl SymbolTable {
/// Create a new, empty SymbolTable
pub fn new() -> Self {
Self {
def_id_store: IdStore::new(),
symbol_trie: SymbolTrie::new(),
fq_names: NameTable::new(),
types: NameTable::new(),
id_to_def: HashMap::new(),
def_to_symbol: HashMap::new(),
}
}
/// The main entry point into the symbol table. This will traverse the AST in several
/// different ways and populate subtables with information that will be used further in the
/// compilation process.
pub fn process_ast(
&mut self,
ast: &ast::AST,
type_context: &mut TypeContext,
) -> Result<(), Vec<SymbolError>> {
let mut populator = SymbolTablePopulator { type_context, table: self };
let errs = populator.populate_definition_tables(ast);
if !errs.is_empty() {
return Err(errs);
}
// Walks the AST, matching the ID of an identifier used in some expression to
// the corresponding Symbol.
let mut resolver = resolver::ScopeResolver::new(self);
resolver.resolve(ast);
Ok(())
}
pub fn lookup_symbol(&self, id: &ItemId) -> Option<&Symbol> {
let def = self.id_to_def.get(id)?;
self.def_to_symbol.get(def).map(|s| s.as_ref())
}
pub fn lookup_symbol_by_def(&self, def: &DefId) -> Option<&Symbol> {
self.def_to_symbol.get(def).map(|s| s.as_ref())
}
#[allow(dead_code)]
pub fn debug(&self) {
println!("Symbol table:");
println!("----------------");
for (id, def) in self.id_to_def.iter() {
if let Some(symbol) = self.def_to_symbol.get(def) {
println!("{} => {}: {}", id, def, symbol);
} else {
println!("{} => {} <NO SYMBOL FOUND>", id, def);
}
}
}
/// Register a new mapping of a fully-qualified symbol name (e.g. `Option::Some`)
/// to a Symbol, a descriptor of what that name refers to.
fn add_symbol(&mut self, id: &ItemId, fqsn: Fqsn, spec: SymbolSpec) {
let def_id = self.def_id_store.fresh();
let local_name = fqsn.last_elem();
let symbol = Rc::new(Symbol { fully_qualified_name: fqsn.clone(), local_name, spec, def_id });
self.symbol_trie.insert(&fqsn, def_id);
self.id_to_def.insert(*id, def_id);
self.def_to_symbol.insert(def_id, symbol);
}
fn populate_single_builtin(&mut self, fqsn: Fqsn, builtin: Builtin) {
let def_id = self.def_id_store.fresh();
let spec = SymbolSpec::Builtin(builtin);
let local_name = fqsn.last_elem();
let symbol = Rc::new(Symbol { fully_qualified_name: fqsn.clone(), local_name, spec, def_id });
self.symbol_trie.insert(&fqsn, def_id);
self.def_to_symbol.insert(def_id, symbol);
}
}
#[allow(dead_code)]
#[derive(Debug, Clone)]
pub struct Symbol {
fully_qualified_name: Fqsn,
local_name: Rc<String>,
spec: SymbolSpec,
def_id: DefId,
}
impl Symbol {
pub fn local_name(&self) -> &str {
self.local_name.as_ref()
}
pub fn def_id(&self) -> DefId {
self.def_id
}
pub fn spec(&self) -> SymbolSpec {
self.spec.clone()
}
}
impl fmt::Display for Symbol {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "<Local name: {}, {}, Spec: {}>", self.local_name(), self.fully_qualified_name, self.spec)
}
}
//TODO - I think I eventually want to draw a distinction between true global items
//i.e. global vars, and items whose definitions are scoped. Right now there's a sense
//in which Func, DataConstructor, RecordConstructor, and GlobalBinding are "globals",
//whereas LocalVarible and FunctionParam have local scope. But right now, they all
//get put into a common table, and all get DefId's from a common source.
//
//It would be good if individual functions could in parallel look up their own
//local vars without interfering with other lookups. Also some type definitions
//should be scoped in a similar way.
//
//Also it makes sense that non-globals should not use DefId's, particularly not
//function parameters (even though they are currently assigned).
#[derive(Debug, Clone)]
pub enum SymbolSpec {
Builtin(Builtin),
Func { method: Option<crate::ast::TypeSingletonName> },
DataConstructor { tag: u32, type_id: TypeId },
RecordConstructor { tag: u32, type_id: TypeId },
GlobalBinding, //Only for global variables, not for function-local ones or ones within a `let` scope context
LocalVariable,
FunctionParam(u8),
}
impl fmt::Display for SymbolSpec {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use self::SymbolSpec::*;
match self {
Builtin(b) => write!(f, "Builtin: {:?}", b),
Func { .. } => write!(f, "Func"),
DataConstructor { tag, type_id } => write!(f, "DataConstructor(tag: {}, type: {})", tag, type_id),
RecordConstructor { type_id, tag, .. } =>
write!(f, "RecordConstructor(tag: {})(<members> -> {})", tag, type_id),
GlobalBinding => write!(f, "GlobalBinding"),
LocalVariable => write!(f, "Local variable"),
FunctionParam(n) => write!(f, "Function param: {}", n),
}
}
}

View File

@ -1,352 +0,0 @@
use std::{
collections::{hash_map::Entry, HashMap, HashSet},
rc::Rc,
str::FromStr,
};
use super::{Fqsn, NameKind, NameSpec, ScopeSegment, SymbolError, SymbolSpec, SymbolTable, TypeKind};
use crate::{
ast::{
Declaration, Expression, ExpressionKind, ItemId, Statement, StatementKind, TypeBody,
TypeSingletonName, Variant, VariantKind, AST,
},
builtin::Builtin,
parsing::Location,
type_inference::{self, PendingType, TypeBuilder, TypeContext, VariantBuilder},
};
pub(super) struct SymbolTablePopulator<'a> {
pub(super) type_context: &'a mut TypeContext,
pub(super) table: &'a mut SymbolTable,
}
impl<'a> SymbolTablePopulator<'a> {
/* note: this adds names for *forward reference* but doesn't actually create any types. solve that problem
* later */
fn add_symbol(&mut self, id: &ItemId, fqsn: Fqsn, spec: SymbolSpec) {
self.table.add_symbol(id, fqsn, spec)
}
/// This function traverses the AST and adds symbol table entries for
/// constants, functions, types, and modules defined within. This simultaneously
/// checks for dupicate definitions (and returns errors if discovered), and sets
/// up name tables that will be used by further parts of the compiler
pub fn populate_definition_tables(&mut self, ast: &AST) -> Vec<SymbolError> {
let mut scope_stack = vec![];
self.add_from_scope(ast.statements.as_ref(), &mut scope_stack, false)
}
fn add_from_scope(
&mut self,
statements: &[Statement<StatementKind>],
scope_stack: &mut Vec<ScopeSegment>,
function_scope: bool,
) -> Vec<SymbolError> {
let mut errors = vec![];
for statement in statements {
let Statement { id, kind, location } = statement;
let location = *location;
if let Err(err) = self.add_single_statement(id, kind, location, scope_stack, function_scope) {
errors.push(err);
} else {
let decl = match kind {
StatementKind::Declaration(decl) => decl,
_ => continue,
};
// If there's an error with a name, don't recurse into subscopes of that name
let recursive_errs = match decl {
Declaration::FuncDecl(signature, body) => {
let new_scope = ScopeSegment::Name(signature.name.clone());
scope_stack.push(new_scope);
let output = self.add_from_scope(body.as_ref(), scope_stack, true);
scope_stack.pop();
output
}
Declaration::Module { name, items } => {
let new_scope = ScopeSegment::Name(name.clone());
scope_stack.push(new_scope);
let output = self.add_from_scope(items.as_ref(), scope_stack, false);
scope_stack.pop();
output
}
Declaration::TypeDecl { name, body, mutable } => {
let type_fqsn = Fqsn::from_scope_stack(scope_stack, name.name.clone());
self.add_type_members(name, body, mutable, location, type_fqsn)
}
Declaration::Impl { type_name, interface_name: _, block } => {
let mut errors = vec![];
let new_scope = ScopeSegment::Name(Rc::new(format!("<impl-block>{}", type_name)));
scope_stack.push(new_scope);
for decl_stmt in block.iter() {
let Statement { id, kind, location } = decl_stmt;
let location = *location;
match kind {
decl @ Declaration::FuncDecl(signature, body) => {
let output =
self.add_single_declaration(id, decl, location, scope_stack, true);
if let Err(e) = output {
errors.push(e);
};
let new_scope = ScopeSegment::Name(signature.name.clone());
scope_stack.push(new_scope);
let output = self.add_from_scope(body.as_ref(), scope_stack, true);
scope_stack.pop();
errors.extend(output.into_iter());
}
_other => errors.push(SymbolError::BadImplBlockEntry),
};
}
scope_stack.pop();
errors
}
_ => vec![],
};
errors.extend(recursive_errs.into_iter());
}
}
errors
}
fn add_single_statement(
&mut self,
id: &ItemId,
kind: &StatementKind,
location: Location,
scope_stack: &[ScopeSegment],
function_scope: bool,
) -> Result<(), SymbolError> {
match kind {
StatementKind::Declaration(decl) =>
self.add_single_declaration(id, decl, location, scope_stack, function_scope),
_ => return Ok(()),
}
}
fn add_single_declaration(
&mut self,
id: &ItemId,
decl: &Declaration,
location: Location,
scope_stack: &[ScopeSegment],
function_scope: bool,
) -> Result<(), SymbolError> {
match decl {
Declaration::FuncSig(signature) => {
let fq_function = Fqsn::from_scope_stack(scope_stack, signature.name.clone());
self.table
.fq_names
.register(fq_function.clone(), NameSpec { location, kind: NameKind::Function })?;
self.table
.types
.register(fq_function.clone(), NameSpec { location, kind: TypeKind::Function })?;
self.add_symbol(id, fq_function, SymbolSpec::Func { method: None });
}
Declaration::FuncDecl(signature, ..) => {
let fn_name = &signature.name;
let fq_function = Fqsn::from_scope_stack(scope_stack, fn_name.clone());
self.table
.fq_names
.register(fq_function.clone(), NameSpec { location, kind: NameKind::Function })?;
self.table
.types
.register(fq_function.clone(), NameSpec { location, kind: TypeKind::Function })?;
self.add_symbol(id, fq_function, SymbolSpec::Func { method: None });
}
Declaration::TypeDecl { name, .. } => {
let fq_type = Fqsn::from_scope_stack(scope_stack, name.name.clone());
self.table.types.register(fq_type, NameSpec { location, kind: TypeKind::Constructor })?;
}
//TODO handle type aliases
Declaration::TypeAlias { .. } => (),
Declaration::Binding { name, .. } => {
let fq_binding = Fqsn::from_scope_stack(scope_stack, name.clone());
self.table
.fq_names
.register(fq_binding.clone(), NameSpec { location, kind: NameKind::Binding })?;
if !function_scope {
self.add_symbol(id, fq_binding, SymbolSpec::GlobalBinding);
}
}
//TODO implement interfaces
Declaration::Interface { .. } => (),
Declaration::Impl { .. } => (),
Declaration::Module { name, .. } => {
let fq_module = Fqsn::from_scope_stack(scope_stack, name.clone());
self.table.fq_names.register(fq_module, NameSpec { location, kind: NameKind::Module })?;
}
Declaration::Annotation { name, arguments, inner } => {
let inner = inner.as_ref();
self.add_single_statement(
&inner.id,
&inner.kind,
inner.location,
scope_stack,
function_scope,
)?;
self.process_annotation(name.as_ref(), arguments.as_slice(), scope_stack, inner)?;
}
}
Ok(())
}
fn process_annotation(
&mut self,
name: &str,
arguments: &[Expression],
scope_stack: &[ScopeSegment],
inner: &Statement<StatementKind>,
) -> Result<(), SymbolError> {
if name == "register_builtin" {
if let Statement {
id: _,
location: _,
kind: StatementKind::Declaration(Declaration::FuncDecl(sig, _)),
} = inner
{
let fqsn = Fqsn::from_scope_stack(scope_stack, sig.name.clone());
let builtin_name = match arguments {
[Expression { kind: ExpressionKind::Value(qname), .. }]
if qname.components.len() == 1 =>
qname.components[0].clone(),
_ =>
return Err(SymbolError::BadAnnotation {
name: name.to_string(),
msg: "Bad argument for register_builtin".to_string(),
}),
};
let builtin =
Builtin::from_str(builtin_name.as_str()).map_err(|_| SymbolError::BadAnnotation {
name: name.to_string(),
msg: format!("Invalid builtin: {}", builtin_name),
})?;
self.table.populate_single_builtin(fqsn, builtin);
Ok(())
} else {
Err(SymbolError::BadAnnotation {
name: name.to_string(),
msg: "register_builtin not annotating a function".to_string(),
})
}
} else {
Err(SymbolError::UnknownAnnotation { name: name.to_string() })
}
}
fn add_type_members(
&mut self,
type_name: &TypeSingletonName,
type_body: &TypeBody,
_mutable: &bool,
location: Location,
type_fqsn: Fqsn,
) -> Vec<SymbolError> {
let (variants, immediate_variant) = match type_body {
TypeBody::Variants(variants) => (variants.clone(), false),
TypeBody::ImmediateRecord { id, fields } => (
vec![Variant {
id: *id,
name: type_name.name.clone(),
kind: VariantKind::Record(fields.clone()),
}],
true,
),
};
// Check for duplicates before registering any types with the TypeContext
let mut seen_variants = HashSet::new();
let mut errors = vec![];
for variant in variants.iter() {
if seen_variants.contains(&variant.name) {
errors.push(SymbolError::DuplicateVariant {
type_fqsn: type_fqsn.clone(),
name: variant.name.as_ref().to_string(),
})
}
seen_variants.insert(variant.name.clone());
if let VariantKind::Record(ref members) = variant.kind {
let mut seen_members = HashMap::new();
for (member_name, _) in members.iter() {
match seen_members.entry(member_name.as_ref()) {
Entry::Occupied(o) => {
let location = *o.get();
errors.push(SymbolError::DuplicateRecord {
type_fqsn: type_fqsn.clone(),
location,
record: variant.name.as_ref().to_string(),
member: member_name.as_ref().to_string(),
});
}
//TODO eventually this should track meaningful locations
Entry::Vacant(v) => {
v.insert(location);
}
}
}
}
}
if !errors.is_empty() {
return errors;
}
let mut type_builder = TypeBuilder::new(type_name.name.as_ref());
let mut variant_name_map = HashMap::new();
for variant in variants.iter() {
let Variant { name, kind, id } = variant;
variant_name_map.insert(name.clone(), id);
let mut variant_builder = VariantBuilder::new(name.as_ref());
match kind {
VariantKind::UnitStruct => (),
VariantKind::TupleStruct(items) =>
for type_identifier in items {
let pending: PendingType = type_identifier.into();
variant_builder.add_member(pending);
},
VariantKind::Record(members) =>
for (field_name, type_identifier) in members.iter() {
let pending: PendingType = type_identifier.into();
variant_builder.add_record_member(field_name.as_ref(), pending);
},
}
type_builder.add_variant(variant_builder);
}
let type_id = self.type_context.register_type(type_builder);
let type_definition = self.type_context.lookup_type(&type_id).unwrap();
// This index is guaranteed to be the correct tag
for (index, variant) in type_definition.variants.iter().enumerate() {
let id = variant_name_map.get(&variant.name).unwrap();
let tag = index as u32;
let spec = match &variant.members {
type_inference::VariantMembers::Unit => SymbolSpec::DataConstructor { tag, type_id },
type_inference::VariantMembers::Tuple(..) => SymbolSpec::DataConstructor { tag, type_id },
type_inference::VariantMembers::Record(..) => SymbolSpec::RecordConstructor { tag, type_id },
};
self.table.add_symbol(id, type_fqsn.extend(&variant.name), spec);
}
if immediate_variant {
let variant = &type_definition.variants[0];
let id = variant_name_map.get(&variant.name).unwrap();
let spec = SymbolSpec::RecordConstructor { tag: 0, type_id };
self.table.add_symbol(id, type_fqsn, spec);
}
vec![]
}
}

View File

@ -1,253 +0,0 @@
use std::rc::Rc;
use crate::{
ast::*,
symbol_table::{Fqsn, ScopeSegment, SymbolSpec, SymbolTable},
util::ScopeStack,
};
#[derive(Debug)]
enum NameType {
//TODO eventually this needs to support closures
Param(u8),
LocalVariable(ItemId),
LocalFunction(ItemId),
Import(Fqsn),
}
type LexScope<'a> = ScopeStack<'a, Rc<String>, NameType, ScopeType>;
#[derive(Debug)]
enum ScopeType {
Function { name: Rc<String> },
Lambda,
PatternMatch,
ImplBlock,
//TODO add some notion of a let-like scope?
}
pub struct ScopeResolver<'a> {
symbol_table: &'a mut super::SymbolTable,
lexical_scopes: LexScope<'a>,
}
impl<'a> ScopeResolver<'a> {
pub fn new(symbol_table: &'a mut SymbolTable) -> Self {
let lexical_scopes = ScopeStack::new(None);
Self { symbol_table, lexical_scopes }
}
pub fn resolve(&mut self, ast: &AST) {
walk_ast(self, ast);
}
/// This method correctly modifies the id_to_def table (ItemId) to have the appropriate
/// mappings.
fn lookup_name_in_scope(&mut self, name: &QualifiedName) {
//TODO this method badly needs attention
let QualifiedName { id, components } = name;
let local_name = components.first().unwrap().clone();
let name_type = self.lexical_scopes.lookup(&local_name);
let fqsn = Fqsn { scopes: components.iter().map(|name| ScopeSegment::Name(name.clone())).collect() };
let def_id = self.symbol_table.symbol_trie.lookup(&fqsn);
//TODO handle a "partial" qualified name, and also handle it down in the pattern-matching
//section
if components.len() == 1 {
match name_type {
Some(NameType::Import(fqsn)) => {
let def_id = self.symbol_table.symbol_trie.lookup(fqsn);
if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
Some(NameType::Param(n)) => {
let spec = SymbolSpec::FunctionParam(*n);
//TODO need to come up with a better solution for local variable FQSNs
let lscope = ScopeSegment::Name(Rc::new("<local-param>".to_string()));
let fqsn = Fqsn { scopes: vec![lscope, ScopeSegment::Name(local_name.clone())] };
self.symbol_table.add_symbol(id, fqsn, spec);
}
Some(NameType::LocalFunction(item_id)) => {
let def_id = self.symbol_table.id_to_def.get(item_id);
if let Some(def_id) = def_id {
let def_id = *def_id;
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
Some(NameType::LocalVariable(item_id)) => {
let def_id = self.symbol_table.id_to_def.get(item_id);
if let Some(def_id) = def_id {
let def_id = *def_id;
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
None =>
if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
},
}
} else if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
}
impl<'a> ASTVisitor for ScopeResolver<'a> {
// Import statements bring in a bunch of local names that all map to a specific FQSN.
// FQSNs map to a Symbol (or this is an error), Symbols have a DefId. So for every
// name we import, we map a local name (a string) to a NameType::ImportedDefinition(DefId).
fn import(&mut self, import_spec: &ImportSpecifier) -> Recursion {
let ImportSpecifier { ref path_components, ref imported_names, .. } = &import_spec;
match imported_names {
ImportedNames::All => {
let prefix =
Fqsn { scopes: path_components.iter().map(|c| ScopeSegment::Name(c.clone())).collect() };
let members = self.symbol_table.symbol_trie.get_children(&prefix);
for fqsn in members.into_iter() {
self.lexical_scopes.insert(fqsn.last_elem(), NameType::Import(fqsn));
}
}
ImportedNames::LastOfPath => {
let fqsn =
Fqsn { scopes: path_components.iter().map(|c| ScopeSegment::Name(c.clone())).collect() };
self.lexical_scopes.insert(fqsn.last_elem(), NameType::Import(fqsn));
}
ImportedNames::List(ref names) => {
let fqsn_prefix: Vec<ScopeSegment> =
path_components.iter().map(|c| ScopeSegment::Name(c.clone())).collect();
for name in names.iter() {
let mut scopes = fqsn_prefix.clone();
scopes.push(ScopeSegment::Name(name.clone()));
let fqsn = Fqsn { scopes };
self.lexical_scopes.insert(fqsn.last_elem(), NameType::Import(fqsn));
}
}
};
Recursion::Continue
}
fn declaration(&mut self, declaration: &Declaration, id: &ItemId) -> Recursion {
let cur_function_name = match self.lexical_scopes.get_name() {
//TODO this needs to be a fqsn
Some(ScopeType::Function { name }) => Some(name.clone()),
_ => None,
};
match declaration {
Declaration::FuncDecl(signature, block) => {
let param_names = signature.params.iter().map(|param| param.name.clone());
//TODO I'm 90% sure this is right, until I get to closures
//let mut new_scope = self.lexical_scopes.new_scope(Some(ScopeType::Function { name: signature.name.clone() }));
//TODO this will recurse unwantedly into scopes; need to pop an outer function
//scope off first before going into a non-closure scope
let mut new_scope =
ScopeStack::new(Some(ScopeType::Function { name: signature.name.clone() }));
for (n, param) in param_names.enumerate() {
new_scope.insert(param, NameType::Param(n as u8));
}
self.lexical_scopes.insert(signature.name.clone(), NameType::LocalFunction(*id));
let mut new_resolver =
ScopeResolver { symbol_table: self.symbol_table, lexical_scopes: new_scope };
walk_block(&mut new_resolver, block);
Recursion::Stop
}
Declaration::Binding { name, .. } => {
if let Some(fn_name) = cur_function_name {
// We are within a function scope
let fqsn =
Fqsn { scopes: vec![ScopeSegment::Name(fn_name), ScopeSegment::Name(name.clone())] };
self.symbol_table.add_symbol(id, fqsn, SymbolSpec::LocalVariable);
self.lexical_scopes.insert(name.clone(), NameType::LocalVariable(*id));
}
Recursion::Continue
}
Declaration::Impl { block, .. } => {
let new_scope = ScopeStack::new(Some(ScopeType::ImplBlock));
let mut new_resolver =
ScopeResolver { symbol_table: self.symbol_table, lexical_scopes: new_scope };
for stmt in block.iter() {
walk_declaration(&mut new_resolver, &stmt.kind, &stmt.id);
}
Recursion::Stop
}
_ => Recursion::Continue,
}
}
fn expression(&mut self, expression: &Expression) -> Recursion {
use ExpressionKind::*;
match &expression.kind {
Value(name) => {
self.lookup_name_in_scope(name);
}
NamedStruct { name, fields: _ } => {
self.lookup_name_in_scope(name);
}
Lambda { params, body, .. } => {
let param_names = params.iter().map(|param| param.name.clone());
//TODO need to properly handle closure scope, this is currently broken
//let mut new_scope = self.lexical_scopes.new_scope(Some(ScopeType::Function { name: signature.name.clone() }));
let mut new_scope = ScopeStack::new(Some(ScopeType::Lambda));
for (n, param) in param_names.enumerate() {
new_scope.insert(param, NameType::Param(n as u8));
}
let mut new_resolver =
ScopeResolver { symbol_table: self.symbol_table, lexical_scopes: new_scope };
walk_block(&mut new_resolver, body);
return Recursion::Stop;
}
IfExpression { discriminator, body } => {
if let Some(d) = discriminator.as_ref() {
walk_expression(self, d);
}
let mut resolver = ScopeResolver {
lexical_scopes: self.lexical_scopes.new_scope(Some(ScopeType::PatternMatch)),
symbol_table: self.symbol_table,
};
walk_if_expr_body(&mut resolver, body);
return Recursion::Stop;
}
_ => (),
}
Recursion::Continue
}
fn pattern(&mut self, pat: &Pattern) -> Recursion {
use Pattern::*;
match pat {
Literal(..) | Ignored | TuplePattern(..) => (),
TupleStruct(name, _) | Record(name, _) => {
self.lookup_name_in_scope(name);
}
//TODO this isn't really the right syntax for a VarOrName
VarOrName(QualifiedName { id, components }) => {
if components.len() == 1 {
//TODO need a better way to construct a FQSN from a QualifiedName
let local_name: Rc<String> = components[0].clone();
let lscope = ScopeSegment::Name(Rc::new("<local-case-match>".to_string()));
let fqsn = Fqsn { scopes: vec![lscope, ScopeSegment::Name(local_name.clone())] };
self.symbol_table.add_symbol(id, fqsn, SymbolSpec::LocalVariable);
self.lexical_scopes.insert(local_name, NameType::LocalVariable(*id));
} else {
let fqsn = Fqsn {
scopes: components.iter().map(|name| ScopeSegment::Name(name.clone())).collect(),
};
let def_id = self.symbol_table.symbol_trie.lookup(&fqsn);
if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
}
};
Recursion::Continue
}
}

View File

@ -1,70 +0,0 @@
use std::{
collections::hash_map::DefaultHasher,
hash::{Hash, Hasher},
};
use radix_trie::{Trie, TrieCommon, TrieKey};
use super::{DefId, Fqsn, ScopeSegment};
#[derive(Debug)]
pub struct SymbolTrie(Trie<Fqsn, DefId>);
impl TrieKey for Fqsn {
fn encode_bytes(&self) -> Vec<u8> {
let mut hasher = DefaultHasher::new();
let mut output = vec![];
for segment in self.scopes.iter() {
let ScopeSegment::Name(s) = segment;
s.as_bytes().hash(&mut hasher);
output.extend_from_slice(&hasher.finish().to_be_bytes());
}
output
}
}
impl SymbolTrie {
pub fn new() -> SymbolTrie {
SymbolTrie(Trie::new())
}
pub fn insert(&mut self, fqsn: &Fqsn, def_id: DefId) {
self.0.insert(fqsn.clone(), def_id);
}
pub fn lookup(&self, fqsn: &Fqsn) -> Option<DefId> {
self.0.get(fqsn).cloned()
}
pub fn get_children(&self, fqsn: &Fqsn) -> Vec<Fqsn> {
let subtrie = match self.0.subtrie(fqsn) {
Some(s) => s,
None => return vec![],
};
let output: Vec<Fqsn> = subtrie.keys().filter(|cur_key| **cur_key != *fqsn).cloned().collect();
output
}
}
#[cfg(test)]
mod test {
use super::*;
use crate::symbol_table::Fqsn;
fn make_fqsn(strs: &[&str]) -> Fqsn {
Fqsn::from_strs(strs)
}
#[test]
fn test_trie_insertion() {
let id = DefId::default();
let mut trie = SymbolTrie::new();
trie.insert(&make_fqsn(&["unrelated", "thing"]), id);
trie.insert(&make_fqsn(&["outer", "inner"]), id);
trie.insert(&make_fqsn(&["outer", "inner", "still_inner"]), id);
let children = trie.get_children(&make_fqsn(&["outer", "inner"]));
assert_eq!(children.len(), 1);
}
}

View File

@ -1,314 +0,0 @@
#![cfg(test)]
use assert_matches::assert_matches;
use super::*;
use crate::util::quick_ast;
fn add_symbols(src: &str) -> (SymbolTable, Result<(), Vec<SymbolError>>) {
let ast = quick_ast(src);
let mut symbol_table = SymbolTable::new();
let mut type_context = crate::type_inference::TypeContext::new();
let result = symbol_table.process_ast(&ast, &mut type_context);
(symbol_table, result)
}
fn make_fqsn(strs: &[&str]) -> Fqsn {
Fqsn::from_strs(strs)
}
#[test]
fn basic_symbol_table() {
let src = "let a = 10; fn b() { 20 }";
let (symbols, _) = add_symbols(src);
fn make_fqsn(strs: &[&str]) -> Fqsn {
Fqsn::from_strs(strs)
}
symbols.fq_names.table.get(&make_fqsn(&["b"])).unwrap();
let src = "type Option<T> = Some(T) | None";
let (symbols, _) = add_symbols(src);
symbols.types.table.get(&make_fqsn(&["Option"])).unwrap();
}
#[test]
fn no_function_definition_duplicates() {
let source = r#"
fn a() { 1 }
fn b() { 2 }
fn a() { 3 }
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name, ..}
] if prev_name == &Fqsn::from_strs(&["a"])
);
}
#[test]
fn no_variable_definition_duplicates() {
let source = r#"
let x = 9
let a = 20
let q = 39
let a = 30
let x = 34
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
SymbolError::DuplicateName { prev_name: pn2, ..}
] if pn1 == &Fqsn::from_strs(&["a"]) && pn2 == &Fqsn::from_strs(&["x"])
);
}
#[test]
fn no_type_definition_duplicates() {
let source = r#"
let x = 9
type Food = Japchae | Burrito | Other
type Food = GoodJapchae | Breadfruit
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
let err = &errs[0];
match err {
SymbolError::DuplicateName { location: _, prev_name } => {
assert_eq!(prev_name, &Fqsn::from_strs(&["Food"]));
//TODO restore this Location test
//assert_eq!(location, &Location { line_num: 2, char_num: 2 });
}
_ => panic!(),
}
}
#[test]
fn no_variant_duplicates() {
let source = r#"
type Panda = FoolsGold | Kappa(i32) | Remix | Kappa | Thursday | Remix
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_eq!(errs.len(), 2);
assert_matches!(&errs[0], SymbolError::DuplicateVariant {
type_fqsn, name } if *type_fqsn == Fqsn::from_strs(&["Panda"]) &&
name == "Kappa");
assert_matches!(&errs[1], SymbolError::DuplicateVariant {
type_fqsn, name } if *type_fqsn == Fqsn::from_strs(&["Panda"]) &&
name == "Remix");
}
#[test]
fn no_variable_definition_duplicates_in_function() {
let source = r#"
fn a() {
let a = 20
let b = 40
a + b
}
fn q() {
let a = 29
let x = 30
let x = 33
}
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
] if pn1 == &Fqsn::from_strs(&["q", "x"])
);
}
#[test]
fn dont_falsely_detect_duplicates() {
let source = r#"
let a = 20;
fn some_func() {
let a = 40;
77
}
let q = 39
"#;
let (symbols, _) = add_symbols(source);
assert!(symbols.fq_names.table.get(&make_fqsn(&["a"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["some_func", "a"])).is_some());
}
#[test]
fn enclosing_scopes() {
let source = r#"
fn outer_func(x) {
fn inner_func(arg) {
arg
}
x + inner_func(x)
}"#;
let (symbols, _) = add_symbols(source);
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func", "inner_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 (symbols, _) = add_symbols(source);
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func", "inner_func"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func", "second_inner_func"])).is_some());
assert!(symbols
.fq_names
.table
.get(&make_fqsn(&["outer_func", "second_inner_func", "another_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 (_, output) = add_symbols(source);
let _err = output.unwrap_err();
}
#[test]
fn modules() {
let source = r#"
module stuff {
fn item() {
}
}
fn item()
"#;
let (symbols, _) = add_symbols(source);
symbols.fq_names.table.get(&make_fqsn(&["stuff"])).unwrap();
symbols.fq_names.table.get(&make_fqsn(&["item"])).unwrap();
symbols.fq_names.table.get(&make_fqsn(&["stuff", "item"])).unwrap();
}
#[test]
fn duplicate_modules() {
let source = r#"
module q {
fn foo() { 4 }
}
module a {
fn foo() { 334 }
}
module a {
fn sarat() { 39 }
fn foo() { 256.1 }
}
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
] if pn1 == &Fqsn::from_strs(&["a"])
);
}
#[test]
fn duplicate_struct_members() {
let source = r#"
type Tarak = Tarak {
loujet: i32
,
mets: i32,
mets: i32
,
}
"#;
let (_, output) = add_symbols(source);
let errs = dbg!(output.unwrap_err());
assert_matches!(&errs[..], [
SymbolError::DuplicateRecord {
type_fqsn, member, record, ..},
] if type_fqsn == &Fqsn::from_strs(&["Tarak"]) && member == "mets" && record == "Tarak"
);
}
#[test]
fn method_definition_added_to_symbol_table() {
let source = r#"
type Foo = { x: Int, y: Int }
impl Foo {
fn hella() {
let a = 50
self.x + a
}
}
"#;
let (symbols, _) = add_symbols(source);
symbols.debug();
assert!(symbols.fq_names.table.get(&make_fqsn(&["<impl-block>Foo", "hella"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["<impl-block>Foo", "hella", "a"])).is_some());
}
#[test]
fn duplicate_method_definitions_detected() {
let source = r#"
type Foo = { x: Int, y: Int }
impl Foo {
fn hella() {
self.x + 50
}
fn hella() {
self.x + 40
}
}
"#;
let (_symbols, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
] if pn1 == &Fqsn::from_strs(&["<impl-block>Foo", "hella"]));
}

View File

@ -0,0 +1,314 @@
use itertools::Itertools;
use std::collections::HashMap;
use std::rc::Rc;
use std::iter::{Iterator, Peekable};
use std::fmt;
use ::schala_codegen;
#[derive(Debug, PartialEq, Clone)]
pub enum TokenType {
Newline, Semicolon,
LParen, RParen,
LSquareBracket, RSquareBracket,
LAngleBracket, RAngleBracket,
LCurlyBrace, RCurlyBrace,
Pipe,
Comma, Period, Colon, Underscore,
Slash,
Operator(Rc<String>),
DigitGroup(Rc<String>), HexLiteral(Rc<String>), BinNumberSigil,
StrLiteral(Rc<String>),
Identifier(Rc<String>),
Keyword(Kw),
EOF,
Error(String),
}
use self::TokenType::*;
impl fmt::Display for TokenType {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
&Operator(ref s) => write!(f, "Operator({})", **s),
&DigitGroup(ref s) => write!(f, "DigitGroup({})", s),
&HexLiteral(ref s) => write!(f, "HexLiteral({})", s),
&StrLiteral(ref s) => write!(f, "StrLiteral({})", s),
&Identifier(ref s) => write!(f, "Identifier({})", s),
&Error(ref s) => write!(f, "Error({})", s),
other => write!(f, "{:?}", other),
}
}
}
#[derive(Debug, Clone, Copy, PartialEq)]
pub enum Kw {
If, Else,
Func,
For,
Match,
Var, Const, Let, In,
Return,
Alias, Type, SelfType, SelfIdent,
Interface, Impl,
True, False,
Module
}
lazy_static! {
static ref KEYWORDS: HashMap<&'static str, Kw> =
hashmap! {
"if" => Kw::If,
"else" => Kw::Else,
"fn" => Kw::Func,
"for" => Kw::For,
"match" => Kw::Match,
"var" => Kw::Var,
"const" => Kw::Const,
"let" => Kw::Let,
"in" => Kw::In,
"return" => Kw::Return,
"alias" => Kw::Alias,
"type" => Kw::Type,
"Self" => Kw::SelfType,
"self" => Kw::SelfIdent,
"interface" => Kw::Interface,
"impl" => Kw::Impl,
"true" => Kw::True,
"false" => Kw::False,
"module" => Kw::Module,
};
}
#[derive(Debug, Clone)]
pub struct Token {
pub token_type: TokenType,
pub offset: (usize, usize),
}
impl Token {
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.token_type, self.offset.0, self.offset.1)
}
}
const OPERATOR_CHARS: [char; 18] = ['!', '$', '%', '&', '*', '+', '-', '.', ':', '<', '>', '=', '?', '@', '^', '|', '~', '`'];
fn is_operator(c: &char) -> bool {
OPERATOR_CHARS.iter().any(|x| x == c)
}
type CharIter<I: Iterator<Item=(usize,usize,char)>> = Peekable<I>;
#[schala_codegen::compiler_pass = "tokenization"]
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();
while let Some((line_idx, ch_idx, c)) = input.next() {
let cur_tok_type = match c {
'/' => match input.peek().map(|t| t.2) {
Some('/') => {
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
},
c if c.is_whitespace() && c != '\n' => continue,
'\n' => Newline, ';' => Semicolon,
':' => Colon, ',' => Comma,
'(' => LParen, ')' => RParen,
'{' => LCurlyBrace, '}' => RCurlyBrace,
'[' => LSquareBracket, ']' => RSquareBracket,
'"' => handle_quote(&mut input),
c if c.is_digit(10) => handle_digit(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 { token_type: cur_tok_type, offset: (line_idx, ch_idx) });
}
tokens
}
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();
HexLiteral(Rc::new(rest))
} else if c == '0' && input.peek().map_or(false, |&(_, _, c)| { c == 'b' }) {
input.next();
BinNumberSigil
} else {
let mut buf = c.to_string();
buf.extend(input.peeking_take_while(|&(_, _, ref c)| c.is_digit(10)).map(|(_, _, c)| { c }));
DigitGroup(Rc::new(buf))
}
}
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 }) {
Some('"') => break,
Some('\\') => {
let next = input.peek().map(|&(_, _, c)| { c });
if next == Some('n') {
input.next();
buf.push('\n')
} else if next == Some('"') {
input.next();
buf.push('"');
} else if next == Some('t') {
input.next();
buf.push('\t');
}
},
Some(c) => buf.push(c),
None => return TokenType::Error(format!("Unclosed string")),
}
}
TokenType::StrLiteral(Rc::new(buf))
}
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 TokenType::Underscore
}
loop {
match input.peek().map(|&(_, _, c)| { c }) {
Some(c) if c.is_alphanumeric() => {
input.next();
buf.push(c);
},
_ => break,
}
}
match KEYWORDS.get(buf.as_str()) {
Some(kw) => TokenType::Keyword(*kw),
None => TokenType::Identifier(Rc::new(buf)),
}
}
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 });
if !next.map(|n| { is_operator(&n) }).unwrap_or(false) {
return match c {
'<' => LAngleBracket,
'>' => RAngleBracket,
'|' => Pipe,
'.' => Period,
_ => unreachable!(),
}
}
},
_ => (),
};
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
}
}
}
TokenType::Operator(Rc::new(buf))
}
#[cfg(test)]
mod schala_tokenizer_tests {
use super::*;
use super::Kw::*;
macro_rules! digit { ($ident:expr) => { DigitGroup(Rc::new($ident.to_string())) } }
macro_rules! ident { ($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_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_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")]);
}
#[test]
fn comments() {
let token_types: Vec<TokenType> = tokenize("1 + /* hella /* bro */ */ 2").into_iter().map(move |t| t.token_type).collect();
assert_eq!(token_types, vec![digit!("1"), op!("+"), digit!("2")]);
}
#[test]
fn backtick_operators() {
let token_types: Vec<TokenType> = tokenize("1 `plus` 2").into_iter().map(move |t| t.token_type).collect();
assert_eq!(token_types, vec![digit!("1"), op!("plus"), digit!("2")]);
}
}

View File

@ -1,513 +0,0 @@
use std::rc::Rc;
use super::{EvalResult, Memory, MemoryValue, Primitive, State};
use crate::{
builtin::Builtin,
reduced_ir::{
Alternative, Callable, Expression, FunctionDefinition, Literal, Lookup, Pattern, ReducedIR, Statement,
},
type_inference::TypeContext,
util::ScopeStack,
};
#[derive(Debug)]
enum StatementOutput {
Primitive(Primitive),
Nothing,
}
#[derive(Debug, Clone, Copy)]
enum LoopControlFlow {
Break,
Continue,
}
pub struct Evaluator<'a, 'b> {
type_context: &'b TypeContext,
state: &'b mut State<'a>,
early_returning: bool,
loop_control: Option<LoopControlFlow>,
}
impl<'a, 'b> Evaluator<'a, 'b> {
pub(crate) fn new(state: &'b mut State<'a>, type_context: &'b TypeContext) -> Self {
Self { state, type_context, early_returning: false, loop_control: None }
}
pub fn evaluate(&mut self, reduced: ReducedIR, repl: bool) -> Vec<Result<String, String>> {
let mut acc = vec![];
for (def_id, function) in reduced.functions.into_iter() {
let mem = (&def_id).into();
self.state.memory.insert(mem, MemoryValue::Function(function));
}
for statement in reduced.entrypoint.into_iter() {
match self.statement(statement) {
Ok(StatementOutput::Primitive(output)) if repl =>
acc.push(Ok(output.to_repl(self.type_context))),
Ok(_) => (),
Err(error) => {
acc.push(Err(error.msg));
return acc;
}
}
}
acc
}
fn block(&mut self, statements: Vec<Statement>) -> EvalResult<Primitive> {
let mut retval = None;
for stmt in statements.into_iter() {
match self.statement(stmt)? {
StatementOutput::Nothing => (),
StatementOutput::Primitive(prim) => {
retval = Some(prim);
}
};
if self.early_returning {
break;
}
if self.loop_control.is_some() {
break;
}
}
Ok(if let Some(ret) = retval { ret } else { self.expression(Expression::unit())? })
}
fn statement(&mut self, stmt: Statement) -> EvalResult<StatementOutput> {
match stmt {
Statement::Binding { ref id, expr, constant: _ } => {
let evaluated = self.expression(expr)?;
self.state.memory.insert(id.into(), evaluated.into());
Ok(StatementOutput::Nothing)
}
Statement::Expression(expr) => {
let evaluated = self.expression(expr)?;
Ok(StatementOutput::Primitive(evaluated))
}
Statement::Return(expr) => {
let evaluated = self.expression(expr)?;
self.early_returning = true;
Ok(StatementOutput::Primitive(evaluated))
}
Statement::Break => {
self.loop_control = Some(LoopControlFlow::Break);
Ok(StatementOutput::Nothing)
}
Statement::Continue => {
self.loop_control = Some(LoopControlFlow::Continue);
Ok(StatementOutput::Nothing)
}
}
}
fn expression(&mut self, expression: Expression) -> EvalResult<Primitive> {
Ok(match expression {
Expression::Literal(lit) => Primitive::Literal(lit),
Expression::Tuple(items) => Primitive::Tuple(
items
.into_iter()
.map(|expr| self.expression(expr))
.collect::<EvalResult<Vec<Primitive>>>()?,
),
Expression::List(items) => Primitive::List(
items
.into_iter()
.map(|expr| self.expression(expr))
.collect::<EvalResult<Vec<Primitive>>>()?,
),
Expression::Lookup(kind) => match kind {
Lookup::Function(ref id) => {
let mem = id.into();
match self.state.memory.lookup(&mem) {
// This just checks that the function exists in "memory" by ID, we don't
// actually retrieve it until `apply_function()`
Some(MemoryValue::Function(_)) => Primitive::Callable(Callable::UserDefined(*id)),
x => return Err(format!("Function not found for id: {} : {:?}", id, x).into()),
}
}
Lookup::Param(n) => {
let mem = n.into();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Primitive(prim)) => prim.clone(),
e => return Err(format!("Param lookup error, got {:?}", e).into()),
}
}
Lookup::SelfParam => {
let mem = Memory::self_param();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Primitive(prim)) => prim.clone(),
e => return Err(format!("SelfParam lookup error, got {:?}", e).into()),
}
}
Lookup::LocalVar(ref id) | Lookup::GlobalVar(ref id) => {
let mem = id.into();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Primitive(expr)) => expr.clone(),
_ =>
return Err(
format!("Nothing found for local/gloval variable lookup {}", id).into()
),
}
}
},
Expression::Assign { ref lval, box rval } => {
let mem = lval.into();
let evaluated = self.expression(rval)?;
println!("Inserting {:?} into {:?}", evaluated, mem);
self.state.memory.insert(mem, MemoryValue::Primitive(evaluated));
Primitive::unit()
}
Expression::Call { box f, args } => self.call_expression(f, args, None)?,
Expression::CallMethod { box f, args, box self_expr } =>
self.call_expression(f, args, Some(self_expr))?,
Expression::Callable(Callable::DataConstructor { type_id, tag }) => {
let arity = self.type_context.lookup_variant_arity(&type_id, tag).unwrap();
if arity == 0 {
Primitive::Object { type_id, tag, items: vec![], ordered_fields: None }
} else {
Primitive::Callable(Callable::DataConstructor { type_id, tag })
}
}
Expression::Callable(func) => Primitive::Callable(func),
Expression::Conditional { box cond, then_clause, else_clause } => {
let cond = self.expression(cond)?;
match cond {
Primitive::Literal(Literal::Bool(true)) => self.block(then_clause)?,
Primitive::Literal(Literal::Bool(false)) => self.block(else_clause)?,
v => return Err(format!("Non-boolean value {:?} in if-statement", v).into()),
}
}
Expression::CaseMatch { box cond, alternatives } =>
self.case_match_expression(cond, alternatives)?,
Expression::Index { box indexee, box indexer } => {
let indexee = self.expression(indexee)?;
let indexer = self.expression(indexer)?;
match (indexee, indexer) {
(Primitive::List(items), Primitive::Literal(Literal::Nat(n))) =>
match items.get(n as usize) {
Some(item) => item.clone(),
None => return Err(format!("Invalid index {} for this value", n).into()),
},
_ => return Err("Invalid index type".to_string().into()),
}
}
Expression::Loop { box cond, statements } => self.loop_expression(cond, statements)?,
Expression::ReductionError(e) => return Err(e.into()),
Expression::Access { name, box expr } => {
let expr = self.expression(expr)?;
match expr {
Primitive::Object { items, ordered_fields: Some(ordered_fields), .. } => {
let idx = match ordered_fields.iter().position(|s| s == &name) {
Some(idx) => idx,
None => return Err(format!("Field `{}` not found", name).into()),
};
let item = match items.get(idx) {
Some(item) => item,
None => return Err(format!("Field lookup `{}` failed", name).into()),
};
item.clone()
}
e =>
return Err(
format!("Trying to do a field lookup on a non-object value: {:?}", e).into()
),
}
}
})
}
fn loop_expression(&mut self, cond: Expression, statements: Vec<Statement>) -> EvalResult<Primitive> {
let existing = self.loop_control;
let output = self.loop_expression_inner(cond, statements);
self.loop_control = existing;
output
}
fn loop_expression_inner(
&mut self,
cond: Expression,
statements: Vec<Statement>,
) -> EvalResult<Primitive> {
loop {
let cond = self.expression(cond.clone())?;
println!("COND: {:?}", cond);
match cond {
Primitive::Literal(Literal::Bool(true)) => (),
Primitive::Literal(Literal::Bool(false)) => break,
e => return Err(format!("Loop condition evaluates to non-boolean: {:?}", e).into()),
};
//TODO eventually loops shoudl be able to return something
let _output = self.block(statements.clone())?;
match self.loop_control {
None => (),
Some(LoopControlFlow::Continue) => {
self.loop_control = None;
}
Some(LoopControlFlow::Break) => {
break;
}
}
}
Ok(Primitive::unit())
}
fn case_match_expression(
&mut self,
cond: Expression,
alternatives: Vec<Alternative>,
) -> EvalResult<Primitive> {
fn matches(scrut: &Primitive, pat: &Pattern, scope: &mut ScopeStack<Memory, MemoryValue>) -> bool {
match pat {
Pattern::Ignored => true,
Pattern::Binding(ref def_id) => {
let mem = def_id.into();
scope.insert(mem, MemoryValue::Primitive(scrut.clone())); //TODO make sure this doesn't cause problems with nesting
true
}
Pattern::Literal(pat_literal) =>
if let Primitive::Literal(scrut_literal) = scrut {
pat_literal == scrut_literal
} else {
false
},
Pattern::Tuple { subpatterns, tag } => match tag {
None => match scrut {
Primitive::Tuple(items) if items.len() == subpatterns.len() => items
.iter()
.zip(subpatterns.iter())
.all(|(item, subpat)| matches(item, subpat, scope)),
_ => false, //TODO should be a type error
},
Some(pattern_tag) => match scrut {
//TODO should test type_ids for runtime type checking, once those work
Primitive::Object { tag, items, .. }
if tag == pattern_tag && items.len() == subpatterns.len() =>
items
.iter()
.zip(subpatterns.iter())
.all(|(item, subpat)| matches(item, subpat, scope)),
_ => false,
},
},
Pattern::Record { tag: pattern_tag, subpatterns } => match scrut {
//TODO several types of possible error here
Primitive::Object { tag, items, ordered_fields: Some(ordered_fields), .. }
if tag == pattern_tag =>
subpatterns.iter().all(|(field_name, subpat)| {
let idx = ordered_fields
.iter()
.position(|field| field.as_str() == field_name.as_ref())
.unwrap();
let item = &items[idx];
matches(item, subpat, scope)
}),
_ => false,
},
}
}
let cond = self.expression(cond)?;
for alt in alternatives.into_iter() {
let mut new_scope = self.state.memory.new_scope(None);
if matches(&cond, &alt.pattern, &mut new_scope) {
let mut new_state = State { memory: new_scope };
let mut evaluator = Evaluator::new(&mut new_state, self.type_context);
let output = evaluator.block(alt.item);
self.early_returning = evaluator.early_returning;
return output;
}
}
Err("No valid match in match expression".into())
}
//TODO need to do something with self_expr to make method invocations actually work
fn call_expression(
&mut self,
f: Expression,
args: Vec<Expression>,
self_expr: Option<Expression>,
) -> EvalResult<Primitive> {
let func = match self.expression(f)? {
Primitive::Callable(func) => func,
other => return Err(format!("Trying to call non-function value: {:?}", other).into()),
};
match func {
Callable::Builtin(builtin) => self.apply_builtin(builtin, args),
Callable::UserDefined(def_id) => {
let mem = (&def_id).into();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Function(FunctionDefinition { body })) => {
let body = body.clone(); //TODO ideally this clone would not happen
self.apply_function(body, args, self_expr)
}
e => Err(format!("Error looking up function with id {}: {:?}", def_id, e).into()),
}
}
Callable::Lambda { arity, body } => {
if arity as usize != args.len() {
return Err(format!(
"Lambda expression requries {} arguments, only {} provided",
arity,
args.len()
)
.into());
}
self.apply_function(body, args, None)
}
Callable::DataConstructor { type_id, tag } => {
let arity = self.type_context.lookup_variant_arity(&type_id, tag).unwrap();
if arity as usize != args.len() {
return Err(format!(
"Constructor expression requries {} arguments, only {} provided",
arity,
args.len()
)
.into());
}
let mut items: Vec<Primitive> = vec![];
for arg in args.into_iter() {
items.push(self.expression(arg)?);
}
Ok(Primitive::Object { type_id, tag, items, ordered_fields: None })
}
Callable::RecordConstructor { type_id, tag, field_order } => {
//TODO maybe I'll want to do a runtime check of the evaluated fields
/*
let record_members = self.type_context.lookup_record_members(type_id, tag)
.ok_or(format!("Runtime record lookup for: {} {} not found", type_id, tag).into())?;
*/
let mut items: Vec<Primitive> = vec![];
for arg in args.into_iter() {
items.push(self.expression(arg)?);
}
Ok(Primitive::Object { type_id, tag, items, ordered_fields: Some(field_order) })
}
}
}
fn apply_builtin(&mut self, builtin: Builtin, args: Vec<Expression>) -> EvalResult<Primitive> {
use Builtin::*;
use Literal::*;
use Primitive::Literal as Lit;
let evaled_args: EvalResult<Vec<Primitive>> =
args.into_iter().map(|arg| self.expression(arg)).collect();
let evaled_args = evaled_args?;
Ok(match (builtin, evaled_args.as_slice()) {
/* builtin functions */
(IOPrint, &[ref anything]) => {
print!("{}", anything.to_repl(self.type_context));
Primitive::Tuple(vec![])
}
(IOPrintLn, &[ref anything]) => {
println!("{}", anything.to_repl(self.type_context));
Primitive::Tuple(vec![])
}
(IOGetLine, &[]) => {
let mut buf = String::new();
std::io::stdin().read_line(&mut buf).expect("Error readling line in 'getline'");
StringLit(Rc::new(buf.trim().to_string())).into()
}
/* Binops */
(binop, &[ref lhs, ref rhs]) => match (binop, lhs, rhs) {
// TODO need a better way of handling these literals
(Add, Lit(Nat(l)), Lit(Nat(r))) => Nat(l + r).into(),
(Add, Lit(Int(l)), Lit(Int(r))) => Int(l + r).into(),
(Add, Lit(Nat(l)), Lit(Int(r))) => Int((*l as i64) + (*r as i64)).into(),
(Add, Lit(Int(l)), Lit(Nat(r))) => Int((*l as i64) + (*r as i64)).into(),
(Concatenate, Lit(StringLit(ref s1)), Lit(StringLit(ref s2))) =>
StringLit(Rc::new(format!("{}{}", s1, s2))).into(),
(Subtract, Lit(Nat(l)), Lit(Nat(r))) => Nat(l - r).into(),
(Multiply, Lit(Nat(l)), Lit(Nat(r))) => Nat(l * r).into(),
(Divide, Lit(Nat(l)), Lit(Nat(r))) => Float((*l as f64) / (*r as f64)).into(),
(Quotient, Lit(Nat(l)), Lit(Nat(r))) =>
if *r == 0 {
return Err("Divide-by-zero error".into());
} else {
Nat(l / r).into()
},
(Modulo, Lit(Nat(l)), Lit(Nat(r))) => Nat(l % r).into(),
(Exponentiation, Lit(Nat(l)), Lit(Nat(r))) => Nat(l ^ r).into(),
(BitwiseAnd, Lit(Nat(l)), Lit(Nat(r))) => Nat(l & r).into(),
(BitwiseOr, Lit(Nat(l)), Lit(Nat(r))) => Nat(l | r).into(),
/* comparisons */
(Equality, Lit(Nat(l)), Lit(Nat(r))) => Bool(l == r).into(),
(Equality, Lit(Int(l)), Lit(Int(r))) => Bool(l == r).into(),
(Equality, Lit(Float(l)), Lit(Float(r))) => Bool(l == r).into(),
(Equality, Lit(Bool(l)), Lit(Bool(r))) => Bool(l == r).into(),
(Equality, Lit(StringLit(ref l)), Lit(StringLit(ref r))) => Bool(l == r).into(),
(NotEqual, Lit(Nat(l)), Lit(Nat(r))) => Bool(l != r).into(),
(NotEqual, Lit(Int(l)), Lit(Int(r))) => Bool(l != r).into(),
(NotEqual, Lit(Float(l)), Lit(Float(r))) => Bool(l != r).into(),
(NotEqual, Lit(Bool(l)), Lit(Bool(r))) => Bool(l != r).into(),
(NotEqual, Lit(StringLit(ref l)), Lit(StringLit(ref r))) => Bool(l != r).into(),
(LessThan, Lit(Nat(l)), Lit(Nat(r))) => Bool(l < r).into(),
(LessThan, Lit(Int(l)), Lit(Int(r))) => Bool(l < r).into(),
(LessThan, Lit(Float(l)), Lit(Float(r))) => Bool(l < r).into(),
(LessThanOrEqual, Lit(Nat(l)), Lit(Nat(r))) => Bool(l <= r).into(),
(LessThanOrEqual, Lit(Int(l)), Lit(Int(r))) => Bool(l <= r).into(),
(LessThanOrEqual, Lit(Float(l)), Lit(Float(r))) => Bool(l <= r).into(),
(GreaterThan, Lit(Nat(l)), Lit(Nat(r))) => Bool(l > r).into(),
(GreaterThan, Lit(Int(l)), Lit(Int(r))) => Bool(l > r).into(),
(GreaterThan, Lit(Float(l)), Lit(Float(r))) => Bool(l > r).into(),
(GreaterThanOrEqual, Lit(Nat(l)), Lit(Nat(r))) => Bool(l >= r).into(),
(GreaterThanOrEqual, Lit(Int(l)), Lit(Int(r))) => Bool(l >= r).into(),
(GreaterThanOrEqual, Lit(Float(l)), Lit(Float(r))) => Bool(l >= r).into(),
(binop, lhs, rhs) =>
return Err(format!("Invalid binop expression {:?} {:?} {:?}", lhs, binop, rhs).into()),
},
(prefix, &[ref arg]) => match (prefix, arg) {
(BooleanNot, Lit(Bool(true))) => Bool(false),
(BooleanNot, Lit(Bool(false))) => Bool(true),
(Negate, Lit(Nat(n))) => Int(-(*n as i64)),
(Negate, Lit(Int(n))) => Int(-(*n as i64)),
(Negate, Lit(Float(f))) => Float(-(*f as f64)),
(Increment, Lit(Int(n))) => Int(*n),
(Increment, Lit(Nat(n))) => Nat(*n),
_ => return Err("No valid prefix op".into()),
}
.into(),
(x, args) => return Err(format!("bad or unimplemented builtin {:?} | {:?}", x, args).into()),
})
}
fn apply_function(
&mut self,
body: Vec<Statement>,
args: Vec<Expression>,
self_expr: Option<Expression>,
) -> EvalResult<Primitive> {
let self_expr = if let Some(expr) = self_expr { Some(self.expression(expr)?) } else { None };
let mut evaluated_args: Vec<Primitive> = vec![];
for arg in args.into_iter() {
evaluated_args.push(self.expression(arg)?);
}
let mut frame_state = State { memory: self.state.memory.new_scope(None) };
let mut evaluator = Evaluator::new(&mut frame_state, self.type_context);
if let Some(evaled) = self_expr {
let mem = Memory::self_param();
evaluator.state.memory.insert(mem, MemoryValue::Primitive(evaled));
}
for (n, evaled) in evaluated_args.into_iter().enumerate() {
let n = n as u8;
let mem = n.into();
evaluator.state.memory.insert(mem, MemoryValue::Primitive(evaled));
}
evaluator.block(body)
}
}

View File

@ -1,173 +0,0 @@
use std::{convert::From, fmt::Write};
use crate::{
reduced_ir::{Callable, Expression, FunctionDefinition, Literal, ReducedIR},
symbol_table::DefId,
type_inference::{TypeContext, TypeId},
util::{delim_wrapped, ScopeStack},
};
mod evaluator;
mod test;
type EvalResult<T> = Result<T, RuntimeError>;
#[derive(Debug)]
pub struct State<'a> {
memory: ScopeStack<'a, Memory, MemoryValue>,
}
//TODO - eh, I dunno, maybe it doesn't matter exactly how memory works in the tree-walking
//evaluator
#[derive(Debug, PartialEq, Eq, Hash, Clone)]
enum Memory {
Index(u32),
}
impl Memory {
fn self_param() -> Self {
Memory::Index(3_999_999)
}
}
// This is for function param lookups, and is a hack
impl From<u8> for Memory {
fn from(n: u8) -> Self {
Memory::Index(4_000_000 + (n as u32))
}
}
impl From<&DefId> for Memory {
fn from(id: &DefId) -> Self {
Self::Index(id.as_u32())
}
}
#[derive(Debug)]
struct RuntimeError {
msg: String,
}
impl From<String> for RuntimeError {
fn from(msg: String) -> Self {
Self { msg }
}
}
impl From<&str> for RuntimeError {
fn from(msg: &str) -> Self {
Self { msg: msg.to_string() }
}
}
impl RuntimeError {
#[allow(dead_code)]
fn get_msg(&self) -> String {
format!("Runtime error: {}", self.msg)
}
}
/// Anything that can be stored in memory; that is, a function definition, or a fully-evaluated
/// program value.
#[derive(Debug)]
enum MemoryValue {
Function(FunctionDefinition),
Primitive(Primitive),
}
impl From<Primitive> for MemoryValue {
fn from(prim: Primitive) -> Self {
Self::Primitive(prim)
}
}
#[derive(Debug)]
enum RuntimeValue {
Expression(Expression),
Evaluated(Primitive),
}
impl From<Expression> for RuntimeValue {
fn from(expr: Expression) -> Self {
Self::Expression(expr)
}
}
impl From<Primitive> for RuntimeValue {
fn from(prim: Primitive) -> Self {
Self::Evaluated(prim)
}
}
/// A fully-reduced value
#[derive(Debug, Clone)]
enum Primitive {
Tuple(Vec<Primitive>),
List(Vec<Primitive>),
Literal(Literal),
Callable(Callable),
Object { type_id: TypeId, tag: u32, ordered_fields: Option<Vec<String>>, items: Vec<Primitive> },
}
impl Primitive {
fn to_repl(&self, type_context: &TypeContext) -> String {
match self {
Primitive::Object { type_id, items, tag, ordered_fields: _ } if items.is_empty() =>
type_context.variant_local_name(type_id, *tag).unwrap().to_string(),
Primitive::Object { type_id, items, tag, ordered_fields: None } => {
format!(
"{}{}",
type_context.variant_local_name(type_id, *tag).unwrap(),
delim_wrapped('(', ')', items.iter().map(|item| item.to_repl(type_context)))
)
}
Primitive::Object { type_id, items, tag, ordered_fields: Some(fields) } => {
let mut buf = format!("{} {{ ", type_context.variant_local_name(type_id, *tag).unwrap());
for item in fields.iter().zip(items.iter()).map(Some).intersperse(None) {
match item {
Some((name, val)) => write!(buf, "{}: {}", name, val.to_repl(type_context)).unwrap(),
None => write!(buf, ", ").unwrap(),
}
}
write!(buf, " }}").unwrap();
buf
}
Primitive::Literal(lit) => match lit {
Literal::Nat(n) => format!("{}", n),
Literal::Int(i) => format!("{}", i),
Literal::Float(f) => format!("{}", f),
Literal::Bool(b) => format!("{}", b),
Literal::StringLit(s) => format!("\"{}\"", s),
},
Primitive::Tuple(terms) => delim_wrapped('(', ')', terms.iter().map(|x| x.to_repl(type_context))),
Primitive::List(terms) => delim_wrapped('[', ']', terms.iter().map(|x| x.to_repl(type_context))),
Primitive::Callable(..) => "<some-callable>".to_string(),
}
}
fn unit() -> Self {
Primitive::Tuple(vec![])
}
}
impl From<Literal> for Primitive {
fn from(lit: Literal) -> Self {
Primitive::Literal(lit)
}
}
impl<'a> State<'a> {
pub fn new() -> Self {
Self { memory: ScopeStack::new(Some("global".to_string())) }
}
pub fn evaluate(
&mut self,
reduced: ReducedIR,
type_context: &TypeContext,
repl: bool,
) -> Vec<Result<String, String>> {
let mut evaluator = evaluator::Evaluator::new(self, type_context);
evaluator.evaluate(reduced, repl)
}
}

View File

@ -1,564 +0,0 @@
#![cfg(test)]
use pretty_assertions::assert_eq;
use test_case::test_case;
use crate::{
symbol_table::SymbolTable,
tree_walk_eval::{evaluator::Evaluator, State},
type_inference::TypeContext,
};
fn evaluate_input(input: &str) -> Result<String, String> {
let ast = crate::util::quick_ast(input);
let mut symbol_table = SymbolTable::new();
let mut type_context = TypeContext::new();
symbol_table.process_ast(&ast, &mut type_context).unwrap();
let reduced_ir = crate::reduced_ir::reduce(&ast, &symbol_table, &type_context);
reduced_ir.debug(&symbol_table);
println!("========");
symbol_table.debug();
let mut state = State::new();
let mut evaluator = Evaluator::new(&mut state, &type_context);
let mut outputs = evaluator.evaluate(reduced_ir, true);
outputs.pop().unwrap()
}
fn eval_assert(input: &str, expected: &str) {
assert_eq!(evaluate_input(input), Ok(expected.to_string()));
}
fn eval_assert_failure(input: &str, expected: &str) {
assert_eq!(evaluate_input(input), Err(expected.to_string()));
}
#[test]
fn test_basic_eval() {
eval_assert("1 + 2", "3");
eval_assert("let mut a = 1; a = 2", "()");
eval_assert("let mut a = 1; a = a + 2; a", "3");
}
#[test]
fn op_eval() {
eval_assert("-13", "-13");
eval_assert("10 - 2", "8");
}
#[test]
fn function_eval() {
eval_assert("fn oi(x) { x + 1 }; oi(4)", "5");
eval_assert("fn oi(x) { x + 1 }; oi(1+2)", "4");
}
#[test]
fn scopes() {
let scope_ok = r#"
let a = 20
fn haha() {
let something = 38
let a = 10
a
}
haha()
"#;
eval_assert(scope_ok, "10");
let scope_ok = r#"
let a = 20
fn queque() {
let a = 10
a
}
a
"#;
eval_assert(scope_ok, "20");
}
#[test]
fn eval_scopes_2() {
eval_assert(
r#"
fn trad() {
let a = 10
fn jinner() {
let b = 20
b
}
a + jinner()
}
trad()"#,
"30",
);
let err = "No symbol found for name: `a`";
eval_assert_failure(
r#"
fn trad() {
let a = 10
fn inner() {
let b = 20
a + b
}
inner()
}
trad()
"#,
err,
);
}
#[test]
fn adt_output_1() {
let source = r#"
type Option<T> = Some(T) | None
let a = Option::None
let b = Option::Some(10)
(b, a)
"#;
eval_assert(source, "(Some(10), None)");
}
#[test]
fn adt_output_2() {
let source = r#"
type Gobble = Unknown | Rufus { a: Int, torrid: Nat }
let b = Gobble::Rufus { a: 3, torrid: 99 }
b
"#;
eval_assert(source, "Rufus { a: 3, torrid: 99 }");
let source = r#"
type Gobble = Unknown | Rufus { a: Int, torrid: Nat }
let b = Gobble::Rufus { torrid: 3, a: 84 }
b
"#;
eval_assert(source, "Rufus { a: 84, torrid: 3 }");
let source = r#"
type Gobble = Unknown | Rufus { a: Int, torrid: Nat }
let b = Gobble::Rufus { a: 84 }
b
"#;
eval_assert_failure(source, "Field torrid not specified for record Gobble::Rufus");
}
#[test]
fn basic_if_statement() {
let source = r#"
let a = 10
let b = 10
if a == b then { 69 } else { 420 }
"#;
eval_assert(source, "69");
}
#[test]
fn basic_patterns_1() {
let source = r#"
let x = 10
let a = if x is 10 then { 255 } else { 256 }
let b = if 23 is 99 then { 255 } else { 256 }
let c = if true is false then { 9 } else { 10 }
let d = if "xxx" is "yyy" then { 20 } else { 30 }
(a, b, c, d)
"#;
eval_assert(source, "(255, 256, 10, 30)");
}
#[test_case("sanchez", "1")]
#[test_case("mouri", "2")]
#[test_case("hella", "3")]
#[test_case("cyrus", "4")]
fn basic_patterns_2(input: &str, expected: &str) {
let mut source = format!(r#"let x = "{}""#, input);
source.push_str(
r#"
if x {
is "sanchez" then 1
is "mouri" then 2
is "hella" then 3
is _ then 4
}
"#,
);
eval_assert(&source, expected);
}
#[test_case(r#"(45, "panda", false, 2.2)"#, r#""yes""#)]
#[test_case(r#"(99, "panda", false, -2.45)"#, r#""maybe""#)]
fn tuple_patterns(input: &str, expected: &str) {
let mut source = format!("let x = {}", input);
source.push_str(
r#"
if x {
is (45, "pablo", _, 28.4) then "no"
is (_, "panda", _, 2.2) then "yes"
is _ then "maybe"
}"#,
);
eval_assert(&source, expected);
}
#[test]
fn record_patterns_1() {
let source = r#"
type Ara = Kueh { a: Int, b: String } | Morbuk
let alpha = Ara::Kueh { a: 10, b: "sanchez" }
if alpha {
is Ara::Kueh { a, b } then (b, a)
is _ then ("nooo", 8888)
}"#;
eval_assert(source, r#"("sanchez", 10)"#);
}
#[test]
fn record_patterns_2() {
let source = r#"
type Ara = Kueh { a: Int, b: String } | Morbuk
let alpha = Ara::Kueh { a: 10, b: "sanchez" }
if alpha {
is Ara::Kueh { a, b: le_value } then (le_value, (a*2))
is _ then ("nooo", 8888)
}"#;
eval_assert(source, r#"("sanchez", 20)"#);
}
#[test]
fn record_patterns_3() {
let source = r#"
type Vstsavlobs = { tkveni: Int, b: Ia }
type Ia = { sitqva: Int, ghmerts: String }
let b = Vstsavlobs { tkveni: 3, b: Ia::Ia { sitqva: 5, ghmerts: "ooo" } }
if b {
is Vstsavlobs::Vstsavlobs { tkveni: _, b: Ia::Ia { sitqva, ghmerts } } then sitqva
is _ then 5000
}"#;
eval_assert(source, "5");
}
#[test]
fn if_is_patterns() {
let source = r#"
type Option<T> = Some(T) | None
let q = "a string"
let x = Option::Some(9); if x is Option::Some(q) then { q } else { 0 }"#;
eval_assert(source, "9");
let source = r#"
type Option<T> = Some(T) | None
let q = "a string"
let outer = 2
let x = Option::None; if x is Option::Some(q) then { q } else { -2 + outer }"#;
eval_assert(source, "0");
}
#[test]
fn full_if_matching() {
let source = r#"
type Option<T> = Some(T) | None
let a = Option::None
if a { is Option::None then 4; is Option::Some(x) then x }
"#;
eval_assert(source, "4");
let source = r#"
type Option<T> = Some(T) | None
let sara = Option::Some(99)
if sara { is Option::None then 1 + 3; is Option::Some(x) then x }
"#;
eval_assert(source, "99");
let source = r#"
let a = 10
if a { is 10 then "x"; is 4 then "y" }
"#;
eval_assert(source, "\"x\"");
let source = r#"
let a = 10
if a { is 15 then "x"; is 10 then "y" }
"#;
eval_assert(source, "\"y\"");
}
//TODO - I can probably cut down some of these
#[test]
fn string_pattern() {
let source = r#"
let a = "foo"
if a { is "foo" then "x"; is _ then "y" }
"#;
eval_assert(source, "\"x\"");
}
#[test]
fn boolean_pattern() {
let source = r#"
let a = true
if a {
is true then "x"
is false then "y"
}
"#;
eval_assert(source, "\"x\"");
}
#[test]
fn boolean_pattern_2() {
let source = r#"
let a = false
if a { is true then "x"; is false then "y" }
"#;
eval_assert(source, "\"y\"");
}
#[test]
fn ignore_pattern() {
let source = r#"
type Option<T> = Some(T) | None
if Option::Some(10) {
is _ then "hella"
}
"#;
eval_assert(source, "\"hella\"");
}
#[test]
fn tuple_pattern() {
let source = r#"
if (1, 2) {
is (1, x) then x;
is _ then 99
}
"#;
eval_assert(source, "2");
}
#[test]
fn tuple_pattern_2() {
let source = r#"
if (1, 2) {
is (10, x) then x
is (y, x) then x + y
}
"#;
eval_assert(source, "3");
}
#[test]
fn tuple_pattern_3() {
let source = r#"
if (1, 5) {
is (10, x) then x
is (1, x) then x
}
"#;
eval_assert(source, "5");
}
#[test]
fn tuple_pattern_4() {
let source = r#"
if (1, 5) {
is (10, x) then x
is (1, x) then x
}
"#;
eval_assert(source, "5");
}
#[test]
fn prim_obj_pattern() {
let source = r#"
type Stuff = Mulch(Nat) | Jugs(Nat, String) | Mardok
let a = Stuff::Mulch(20)
let b = Stuff::Jugs(1, "haha")
let c = Stuff::Mardok
let x = if a {
is Stuff::Mulch(20) then "x"
is _ then "ERR"
}
let y = if b {
is Stuff::Mulch(n) then "ERR"
is Stuff::Jugs(2, _) then "ERR"
is Stuff::Jugs(1, s) then s
is _ then "ERR"
}
let z = if c {
is Stuff::Jugs(_, _) then "ERR"
is Stuff::Mardok then "NIGH"
is _ then "ERR"
}
(x, y, z)
"#;
eval_assert(source, r#"("x", "haha", "NIGH")"#);
}
#[test]
fn basic_lambda_evaluation_1() {
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)
"#;
eval_assert(source, r"(10, 6)");
}
#[test]
fn basic_lambda_evaluation_2() {
let source = r#"
fn milta() {
\(x) { x + 33 }
}
milta()(10)
"#;
eval_assert(source, "43");
}
#[test]
fn import_all() {
let source = r#"
type Option<T> = Some(T) | None
import Option::*
let x = Some(9); if x is Some(q) then { q } else { 0 }"#;
eval_assert(source, "9");
}
#[test]
fn accessors() {
let source = r#"
type Klewos = { a: Int, b: String }
let value = Klewos::Klewos { a: 50, b: "nah" }
(value.a, value.b)
"#;
eval_assert(source, r#"(50, "nah")"#);
}
#[test]
fn early_return() {
let source = r#"
fn chnurmek(a: Int): Int {
if a == 5 then {
return 9999;
}
return (a + 2);
}
(chnurmek(5), chnurmek(0))
"#;
eval_assert(source, r#"(9999, 2)"#);
let source = r#"
fn marbuk(a: Int, b: Int): (Int, Int) {
if a == 5 then {
if b == 6 then {
return (50, 50);
}
return (a, b + 1)
}
(a * 100, b * 100)
}
let x = marbuk(1, 1)
let y = marbuk(5, 1)
let z = marbuk(5, 6)
(x, y, z)
"#;
eval_assert(source, "((100, 100), (5, 2), (50, 50))");
}
#[test]
fn loops() {
let source = r#"
let mut a = 0
let mut count = 0
while a != 5 {
a = a + 1
count = count + 100
}
count
"#;
eval_assert(source, "500");
}
#[test]
fn loops_2() {
let source = r#"
let mut a = 0
let mut acc = 0
while a < 10 {
acc = acc + 1
a = a + 1
// Without this continue, the output would be 20
if a == 5 then {
continue
}
acc = acc + 1
}
acc"#;
eval_assert(source, "19");
}
#[test]
fn list_literals() {
eval_assert(
r#"
let a = [7, 8, 9]
a
"#,
"[7, 8, 9]",
);
eval_assert(
r#"
let a = [7, 8, 9]
fn foo() { return 2 }
(a[0], a[foo()])
"#,
"(7, 9)",
);
}
#[test]
fn eval_method() {
let src = r#"
type Thing = Thing
impl Thing {
fn a_method() {
20
}
}
let a = Thing::Thing
4 + a.a_method()
"#;
eval_assert(src, "24");
}

View File

@ -1,227 +0,0 @@
use std::{collections::HashMap, convert::From};
use crate::{
ast::{TypeIdentifier, AST},
identifier::{define_id_kind, Id, IdStore},
};
define_id_kind!(TypeItem);
pub type TypeId = Id<TypeItem>;
pub struct TypeContext {
defined_types: HashMap<TypeId, DefinedType>,
type_id_store: IdStore<TypeItem>,
}
impl TypeContext {
pub fn new() -> Self {
Self { defined_types: HashMap::new(), type_id_store: IdStore::new() }
}
pub fn register_type(&mut self, builder: TypeBuilder) -> TypeId {
let type_id = self.type_id_store.fresh();
let mut pending_variants = vec![];
for variant_builder in builder.variants.into_iter() {
let members = variant_builder.members;
if members.is_empty() {
pending_variants.push(Variant { name: variant_builder.name, members: VariantMembers::Unit });
continue;
}
let record_variant = matches!(members.get(0).unwrap(), VariantMemberBuilder::KeyVal(..));
if record_variant {
let pending_members = members.into_iter().map(|var| match var {
VariantMemberBuilder::KeyVal(name, ty) => (name, ty),
_ => panic!("Compiler internal error: variant mismatch"),
});
//TODO make this mapping meaningful
let type_ids = pending_members
.into_iter()
.map(|(name, _ty_id)| (name, self.type_id_store.fresh()))
.collect();
pending_variants
.push(Variant { name: variant_builder.name, members: VariantMembers::Record(type_ids) });
} else {
let pending_members = members.into_iter().map(|var| match var {
VariantMemberBuilder::Pending(pending_type) => pending_type,
_ => panic!("Compiler internal error: variant mismatch"),
});
//TODO make this mapping meaningful
let type_ids = pending_members.into_iter().map(|_ty_id| self.type_id_store.fresh()).collect();
pending_variants
.push(Variant { name: variant_builder.name, members: VariantMembers::Tuple(type_ids) });
}
}
// Eventually, I will want to have a better way of determining which numeric tag goes with
// which variant. For now, just sort them alphabetically.
pending_variants.sort_unstable_by(|a, b| a.name.cmp(&b.name));
let defined = DefinedType { name: builder.name, variants: pending_variants };
self.defined_types.insert(type_id, defined);
type_id
}
pub fn variant_local_name(&self, type_id: &TypeId, tag: u32) -> Option<&str> {
self.defined_types
.get(type_id)
.and_then(|defined| defined.variants.get(tag as usize))
.map(|variant| variant.name.as_ref())
}
pub fn lookup_variant_arity(&self, type_id: &TypeId, tag: u32) -> Option<u32> {
self.defined_types.get(type_id).and_then(|defined| defined.variants.get(tag as usize)).map(
|variant| match &variant.members {
VariantMembers::Unit => 0,
VariantMembers::Tuple(items) => items.len() as u32,
VariantMembers::Record(items) => items.len() as u32,
},
)
}
pub fn lookup_record_members(&self, type_id: &TypeId, tag: u32) -> Option<&[(String, TypeId)]> {
self.defined_types.get(type_id).and_then(|defined| defined.variants.get(tag as usize)).and_then(
|variant| match &variant.members {
VariantMembers::Record(items) => Some(items.as_ref()),
_ => None,
},
)
}
pub fn lookup_type(&self, type_id: &TypeId) -> Option<&DefinedType> {
self.defined_types.get(type_id)
}
//TODO return some kind of overall type later?
pub fn typecheck(&mut self, ast: &AST) -> Result<(), TypeError> {
Ok(())
}
}
/// A type defined in program source code, as opposed to a builtin.
#[allow(dead_code)]
#[derive(Debug)]
pub struct DefinedType {
pub name: String,
// the variants are in this list according to tag order
pub variants: Vec<Variant>,
}
#[derive(Debug)]
pub struct Variant {
pub name: String,
pub members: VariantMembers,
}
#[derive(Debug)]
pub enum VariantMembers {
Unit,
// Should be non-empty
Tuple(Vec<TypeId>),
Record(Vec<(String, TypeId)>),
}
/// Represents a type mentioned as a member of another type during the type registration process.
/// It may not have been registered itself in the relevant context.
#[allow(dead_code)]
#[derive(Debug)]
pub struct PendingType {
inner: TypeIdentifier,
}
impl From<&TypeIdentifier> for PendingType {
fn from(type_identifier: &TypeIdentifier) -> Self {
Self { inner: type_identifier.clone() }
}
}
#[derive(Debug)]
pub struct TypeBuilder {
name: String,
variants: Vec<VariantBuilder>,
}
impl TypeBuilder {
pub fn new(name: &str) -> Self {
Self { name: name.to_string(), variants: vec![] }
}
pub fn add_variant(&mut self, vb: VariantBuilder) {
self.variants.push(vb);
}
}
#[derive(Debug)]
pub struct VariantBuilder {
name: String,
members: Vec<VariantMemberBuilder>,
}
impl VariantBuilder {
pub fn new(name: &str) -> Self {
Self { name: name.to_string(), members: vec![] }
}
pub fn add_member(&mut self, member_ty: PendingType) {
self.members.push(VariantMemberBuilder::Pending(member_ty));
}
// You can't call this and `add_member` on the same fn, there should be a runtime error when
// that's detected.
pub fn add_record_member(&mut self, name: &str, ty: PendingType) {
self.members.push(VariantMemberBuilder::KeyVal(name.to_string(), ty));
}
}
#[derive(Debug)]
enum VariantMemberBuilder {
Pending(PendingType),
KeyVal(String, PendingType),
}
#[derive(Debug, Clone)]
pub struct TypeError {
pub msg: String,
}
#[allow(dead_code)]
#[derive(Debug, Clone, PartialEq, Eq)]
pub enum TypeConst {
Unit,
Nat,
Int,
Float,
StringT,
Bool,
Ordering,
}
#[allow(dead_code)]
#[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> },
}
macro_rules! ty {
($type_name:ident) => {
Type::Const(crate::type_inference::TypeConst::$type_name)
};
($t1:ident -> $t2:ident) => {
Type::Arrow { params: vec![ty!($t1)], ret: Box::new(ty!($t2)) }
};
($t1:ident -> $t2:ident -> $t3:ident) => {
Type::Arrow { params: vec![ty!($t1), ty!($t2)], ret: Box::new(ty!($t3)) }
};
($type_list:ident, $ret_type:ident) => {
Type::Arrow { params: $type_list, ret: Box::new($ret_type) }
};
}

View File

@ -1,522 +1,254 @@
use std::rc::Rc; use std::rc::Rc;
use std::convert::TryFrom; use std::collections::HashMap;
use std::char;
use std::fmt; use std::fmt;
use std::fmt::Write;
use ena::unify::{UnifyKey, InPlaceUnificationTable, UnificationTable, EqUnifyValue}; use itertools::Itertools;
use crate::builtin::Builtin; use parsing;
use crate::ast::*;
use crate::util::ScopeStack;
use crate::util::deref_optional_box;
pub struct TypeContext {
#[derive(Debug, Clone, PartialEq)] type_var_count: u64,
pub struct TypeData { bindings: HashMap<Rc<String>, Type>,
ty: Option<Type>
} }
impl TypeData { #[derive(Debug, PartialEq, Clone)]
#[allow(dead_code)]
pub fn new() -> TypeData {
TypeData { ty: None }
}
}
//TODO need to hook this into the actual typechecking system somehow
#[derive(Debug, Clone)]
pub struct TypeId {
local_name: Rc<String>
}
impl TypeId {
//TODO this is definitely incomplete
pub fn lookup_name(name: &str) -> TypeId {
TypeId {
local_name: Rc::new(name.to_string())
}
}
pub fn local_name(&self) -> &str {
self.local_name.as_ref()
}
}
impl fmt::Display for TypeId {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "TypeId:{}", self.local_name)
}
}
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() })
}
}
#[allow(dead_code)] // avoids warning from Compound
#[derive(Debug, Clone, PartialEq)]
pub enum Type { 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 {
/*
#[allow(dead_code)]
pub fn to_string(&self) -> String {
use self::TypeConst::*;
match self {
Unit => "()".to_string(),
Nat => "Nat".to_string(),
Int => "Int".to_string(),
Float => "Float".to_string(),
StringT => "String".to_string(),
Bool => "Bool".to_string(),
Ordering => "Ordering".to_string(),
}
}
*/
}
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 {
/*
#[allow(dead_code)]
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.is_empty() {
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 { .. } => "<some compound type>".to_string()
}
}
*/
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), Const(TConst),
Arrow(Box<Type<A>>, Box<Type<A>>), Sum(Vec<Type>),
Func(Box<Type>, Box<Type>),
UVar(String),
EVar(u64),
Void
} }
#[derive(Debug, Clone)] impl fmt::Display for Type {
enum TVar { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
Univ(UVar), use self::Type::*;
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 { match self {
Type::Var(UVar(name)) => Type::Var(TVar::Univ(UVar(name.clone()))), &Const(ref c) => write!(f, "{:?}", c),
Type::Const(ref c) => Type::Const(c.clone()), &Sum(ref types) => {
Type::Arrow(a, b) => Type::Arrow( write!(f, "(")?;
Box::new(a.to_tvar()), for item in types.iter().map(|ty| Some(ty)).intersperse(None) {
Box::new(b.to_tvar()) match item {
) Some(ty) => write!(f, "{}", ty)?,
} None => write!(f, ",")?,
} };
}
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),
} }
} 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(Debug, Clone)] #[derive(Default)]
enum TConst { struct UVarGenerator {
User(Rc<String>), 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, Unit,
Nat,
Int, Int,
Float, Float,
StringT, StringT,
Bool, Bool,
Custom(String),
} }
impl TConst { impl parsing::TypeName {
fn user(name: &str) -> TConst { fn to_type(&self) -> TypeResult<Type> {
TConst::User(Rc::new(name.to_string())) 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")),
impl<'a> TypeContext<'a> { &Singleton(ref name) => match name {
pub fn new() -> TypeContext<'a> { &TypeSingletonName { ref name, .. } => match &name[..] {
TypeContext { "Int" => Const(Int),
variable_map: ScopeStack::new(None), "Float" => Const(Float),
unification_table: UnificationTable::new(), "Bool" => Const(Bool),
} "String" => Const(StringT),
} n => Const(Custom(n.to_string()))
/*
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.statements.statements.iter() {
returned_type = self.statement(statement)?;
}
Ok(returned_type)
}
fn statement(&mut self, statement: &Statement) -> InferResult<Type> {
match &statement.kind {
StatementKind::Expression(e) => self.expr(e),
StatementKind::Declaration(decl) => self.decl(decl),
StatementKind::Import(_) => Ok(ty!(Unit)),
StatementKind::Module(_) => Ok(ty!(Unit)),
}
}
fn decl(&mut self, decl: &Declaration) -> InferResult<Type> {
use self::Declaration::*;
if let Binding { name, expr, .. } = decl {
let ty = self.expr(expr)?;
self.variable_map.insert(name.clone(), ty);
}
Ok(ty!(Unit))
}
fn invoc(&mut self, invoc: &InvocationArgument) -> InferResult<Type> {
use InvocationArgument::*;
match invoc {
Positional(expr) => self.expr(expr),
_ => Ok(ty!(Nat)) //TODO this is wrong
}
}
fn expr(&mut self, expr: &Expression) -> InferResult<Type> {
match expr {
Expression { kind, type_anno: Some(anno), .. } => {
let t1 = self.expr_type(kind)?;
let t2 = self.get_type_from_name(anno)?;
self.unify(t2, t1)
},
Expression { kind, type_anno: None, .. } => self.expr_type(kind)
}
}
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)?,
BinExp(op, lhs, rhs) => self.binexp(op, lhs, rhs)?,
IfExpression { discriminator, body } => self.if_expr(deref_optional_box(discriminator), &**body)?,
Value(val) => self.handle_value(val)?,
Call { box ref f, arguments } => self.call(f, 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 builtin: Option<Builtin> = TryFrom::try_from(op).ok();
let tf = match builtin.map(|b| b.get_type()) {
Some(ty) => ty,
None => return TypeError::new("no type found")
};
let tx = self.expr(expr)?;
self.handle_apply(tf, vec![tx])
}
fn binexp(&mut self, op: &BinOp, lhs: &Expression, rhs: &Expression) -> InferResult<Type> {
let builtin: Option<Builtin> = TryFrom::try_from(op).ok();
let tf = match builtin.map(|b| b.get_type()) {
Some(ty) => ty,
None => return TypeError::new("no type found"),
};
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: Option<&Expression>, body: &IfExpressionBody) -> InferResult<Type> {
use self::IfExpressionBody::*;
match (discriminator, body) {
(Some(expr), SimpleConditional{ then_case, else_case }) => self.handle_simple_if(expr, then_case, else_case),
_ => TypeError::new("Complex conditionals not supported".to_string())
}
}
#[allow(clippy::ptr_arg)]
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)
}
#[allow(clippy::ptr_arg)]
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 FormalParam { anno: 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: &[ InvocationArgument ]) -> InferResult<Type> {
let tf = self.expr(f)?;
let arg_types: InferResult<Vec<Type>> = args.iter().map(|ex| self.invoc(ex)).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("Not a function".to_string())
}) })
} }
}
#[allow(clippy::ptr_arg)] pub type TypeResult<T> = Result<T, String>;
fn block(&mut self, block: &Block) -> InferResult<Type> {
let mut output = ty!(Unit); impl TypeContext {
for statement in block.statements.iter() { pub fn new() -> TypeContext {
output = self.statement(statement)?; TypeContext { bindings: HashMap::new(), type_var_count: 0 }
}
Ok(output)
} }
pub fn fresh(&mut self) -> Type {
fn handle_value(&mut self, val: &QualifiedName) -> InferResult<Type> { let ret = self.type_var_count;
let QualifiedName { components: vec, .. } = val; self.type_var_count += 1;
let var = &vec[0]; Type::EVar(ret)
match self.variable_map.lookup(var) {
Some(ty) => Ok(ty.clone()),
None => TypeError::new(format!("Couldn't find variable: {}", &var)),
}
} }
}
fn unify(&mut self, t1: Type, t2: Type) -> InferResult<Type> { 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::*; 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) { match (t1, t2) {
(Const(ref c1), Const(ref c2)) if c1 == c2 => Ok(Const(c1.clone())), //choice of c1 is arbitrary I *think* (Const(ref a), Const(ref b)) if a == b => Ok(Const(a.clone())),
(a @ Var(_), b @ Const(_)) => self.unify(b, a), (a, b) => Err(format!("Types {:?} and {:?} don't unify", a, b))
(Const(ref c1), Var(ref v2)) => {
self.unification_table.unify_var_value(*v2, 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, v2)
.or_else(|e| {
println!("Unify error: {:?}", e);
TypeError::new(format!("Two type variables {:?} and {:?} couldn't unify", v1, v2))
})?;
Ok(Var(v1)) //arbitrary decision I think
},
(a, b) => TypeError::new(format!("{:?} and {:?} do not unify", a, b)),
} }
} }
fn fresh_type_variable(&mut self) -> TypeVar {
self.unification_table.new_key(None)
}
} }
#[cfg(test)]
mod typechecking_tests {
use super::*;
macro_rules! assert_type_in_fresh_context {
($string:expr, $type:expr) => {
let mut tc = TypeContext::new();
let ast = &crate::util::quick_ast($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));
}
#[test]
fn operators() {
//TODO fix these with new operator regime
/*
assert_type_in_fresh_context!("-1", ty!(Int));
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

@ -1,85 +0,0 @@
use std::{cmp::Eq, collections::HashMap, fmt::Write, hash::Hash};
/// Utility function for printing a comma-delimited list of things
pub(crate) fn delim_wrapped(lhs: char, rhs: char, terms: impl Iterator<Item = String>) -> String {
let mut buf = String::new();
write!(buf, "{}", lhs).unwrap();
for term in terms.map(Some).intersperse(None) {
match term {
Some(e) => write!(buf, "{}", e).unwrap(),
None => write!(buf, ", ").unwrap(),
};
}
write!(buf, "{}", rhs).unwrap();
buf
}
#[derive(Default, Debug)]
pub struct ScopeStack<'a, T: 'a, V: 'a, N = String>
where T: Hash + Eq
{
parent: Option<&'a ScopeStack<'a, T, V, N>>,
values: HashMap<T, V>,
scope_name: Option<N>,
}
impl<'a, T, V, N> ScopeStack<'a, T, V, N>
where T: Hash + Eq
{
pub fn new(scope_name: Option<N>) -> Self
where T: Hash + Eq {
ScopeStack { parent: None, values: HashMap::new(), scope_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, scope_name: Option<N>) -> Self
where T: Hash + Eq {
ScopeStack { parent: Some(self), values: HashMap::default(), scope_name }
}
#[allow(dead_code)]
pub fn lookup_with_scope(&self, key: &T) -> Option<(&V, Option<&N>)>
where T: Hash + Eq {
match (self.values.get(key), self.parent) {
(None, None) => None,
(None, Some(parent)) => parent.lookup_with_scope(key),
(Some(value), _) => Some((value, self.scope_name.as_ref())),
}
}
pub fn get_name(&self) -> Option<&N> {
self.scope_name.as_ref()
}
}
/// Quickly create an AST from a string, with no error checking. For test use only
#[cfg(test)]
pub fn quick_ast(input: &str) -> crate::ast::AST {
let mut parser = crate::parsing::Parser::new();
let output = parser.parse(input);
match output {
Ok(output) => output,
Err(err) => {
println!("Parse error: {}", err.msg);
panic!();
}
}
}
#[allow(unused_macros)]
macro_rules! rc {
($string:tt) => {
Rc::new(stringify!($string).to_string())
};
}

View File

@ -2,22 +2,24 @@
name = "schala-repl" name = "schala-repl"
version = "0.1.0" version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"] authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2021"
[dependencies] [dependencies]
llvm-sys = "70.0.2" llvm-sys = "*"
take_mut = "0.2.2" take_mut = "0.1.3"
itertools = "0.10" itertools = "0.5.8"
getopts = "*"
lazy_static = "0.2.8" lazy_static = "0.2.8"
maplit = "*" maplit = "*"
colored = "1.8" colored = "1.5"
serde = "1.0" serde = "1.0.15"
serde_derive = "1.0" serde_derive = "1.0.15"
serde_json = "1.0" serde_json = "1.0.3"
rocket = "0.3.5"
rocket_codegen = "0.3.5"
rocket_contrib = "0.3.5"
phf = "0.7.12" phf = "0.7.12"
includedir = "0.2.0" includedir = "0.2.0"
linefeed = "0.6.0" rustyline = "1.0.0"
regex = "0.2"
[build-dependencies] [build-dependencies]
includedir_codegen = "0.2.0" includedir_codegen = "0.2.0"

View File

@ -3,5 +3,8 @@ extern crate includedir_codegen;
use includedir_codegen::Compression; use includedir_codegen::Compression;
fn main() { fn main() {
includedir_codegen::start("WEBFILES").dir("../static", Compression::Gzip).build("static.rs").unwrap(); includedir_codegen::start("WEBFILES")
.dir("../static", Compression::Gzip)
.build("static.rs")
.unwrap();
} }

View File

@ -1,116 +0,0 @@
use colored::*;
use crate::{
directive_actions::DirectiveAction, language::ProgrammingLanguageInterface, InterpreterDirectiveOutput,
Repl,
};
/// A CommandTree is either a `Terminal` or a `NonTerminal`. When command parsing reaches the first
/// Terminal, it will use the `DirectiveAction` found there to find an appropriate function to execute,
/// and then execute it with any remaining arguments
#[derive(Clone)]
pub enum CommandTree {
Terminal {
name: String,
children: Vec<CommandTree>,
help_msg: Option<String>,
action: DirectiveAction,
},
NonTerminal {
name: String,
children: Vec<CommandTree>,
help_msg: Option<String>,
action: DirectiveAction,
},
Top(Vec<CommandTree>),
}
impl CommandTree {
pub fn nonterm_no_further_tab_completions(s: &str, help: Option<&str>) -> CommandTree {
CommandTree::NonTerminal {
name: s.to_string(),
help_msg: help.map(|x| x.to_string()),
children: vec![],
action: DirectiveAction::Null,
}
}
pub fn terminal(
s: &str,
help: Option<&str>,
children: Vec<CommandTree>,
action: DirectiveAction,
) -> CommandTree {
CommandTree::Terminal { name: s.to_string(), help_msg: help.map(|x| x.to_string()), children, action }
}
pub fn nonterm(s: &str, help: Option<&str>, children: Vec<CommandTree>) -> CommandTree {
CommandTree::NonTerminal {
name: s.to_string(),
help_msg: help.map(|x| x.to_string()),
children,
action: DirectiveAction::Null,
}
}
pub fn get_cmd(&self) -> &str {
match self {
CommandTree::Terminal { name, .. } => name.as_str(),
CommandTree::NonTerminal { name, .. } => name.as_str(),
CommandTree::Top(_) => "",
}
}
pub fn get_help(&self) -> &str {
match self {
CommandTree::Terminal { help_msg, .. } =>
help_msg.as_ref().map(|s| s.as_str()).unwrap_or("<no help text provided>"),
CommandTree::NonTerminal { help_msg, .. } =>
help_msg.as_ref().map(|s| s.as_str()).unwrap_or("<no help text provided>"),
CommandTree::Top(_) => "",
}
}
pub fn get_children(&self) -> &Vec<CommandTree> {
use CommandTree::*;
match self {
Terminal { children, .. } | NonTerminal { children, .. } | Top(children) => children,
}
}
pub fn get_subcommands(&self) -> Vec<&str> {
self.get_children().iter().map(|x| x.get_cmd()).collect()
}
pub fn perform<L: ProgrammingLanguageInterface>(
&self,
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
let mut dir_pointer: &CommandTree = self;
let mut idx = 0;
let res: Result<(DirectiveAction, usize), String> = loop {
match dir_pointer {
CommandTree::Top(subcommands) | CommandTree::NonTerminal { children: subcommands, .. } => {
let next_command = match arguments.get(idx) {
Some(cmd) => cmd,
None => break Err("Command requires arguments".to_owned()),
};
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)),
};
}
CommandTree::Terminal { action, .. } => {
break Ok((action.clone(), idx));
}
}
};
match res {
Ok((action, idx)) => action.perform(repl, &arguments[idx..]),
Err(err) => Some(err.red().to_string()),
}
}
}

View File

@ -1,77 +0,0 @@
use std::fmt::Write as FmtWrite;
use crate::{
help::help,
language::{LangMetaRequest, LangMetaResponse, ProgrammingLanguageInterface},
InterpreterDirectiveOutput, Repl,
};
#[derive(Debug, Clone)]
pub enum DirectiveAction {
Null,
Help,
QuitProgram,
ListPasses,
TotalTime(bool),
StageTime(bool),
Doc,
}
impl DirectiveAction {
pub fn perform<L: ProgrammingLanguageInterface>(
&self,
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
use DirectiveAction::*;
match self {
Null => None,
Help => help(repl, arguments),
QuitProgram => {
repl.save_before_exit();
::std::process::exit(0)
}
ListPasses => {
let pass_names = match repl.language_state.request_meta(LangMetaRequest::StageNames) {
LangMetaResponse::StageNames(names) => names,
_ => vec![],
};
let mut buf = String::new();
for pass in pass_names.iter().map(Some).intersperse(None) {
match pass {
Some(pass) => write!(buf, "{}", pass).unwrap(),
None => write!(buf, " -> ").unwrap(),
}
}
Some(buf)
}
TotalTime(value) => {
repl.options.show_total_time = *value;
None
}
StageTime(value) => {
repl.options.show_stage_times = *value;
None
}
Doc => doc(repl, arguments),
}
}
}
fn doc<L: ProgrammingLanguageInterface>(
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
arguments
.get(0)
.map(|cmd| {
let source = cmd.to_string();
let meta = LangMetaRequest::Docs { source };
match repl.language_state.request_meta(meta) {
LangMetaResponse::Docs { doc_string } => Some(doc_string),
_ => Some("Invalid doc response".to_owned()),
}
})
.unwrap_or_else(|| Some(":docs needs an argument".to_owned()))
}

View File

@ -1,68 +0,0 @@
use crate::{command_tree::CommandTree, directive_actions::DirectiveAction};
pub fn directives_from_pass_names(pass_names: &[String]) -> CommandTree {
let passes_directives: Vec<CommandTree> = pass_names
.iter()
.map(|pass_name| {
if pass_name == "parsing" {
CommandTree::nonterm(
pass_name,
None,
vec![
CommandTree::nonterm_no_further_tab_completions("compact", None),
CommandTree::nonterm_no_further_tab_completions("expanded", None),
CommandTree::nonterm_no_further_tab_completions("trace", None),
],
)
} else {
CommandTree::nonterm_no_further_tab_completions(pass_name, None)
}
})
.collect();
CommandTree::Top(get_list(&passes_directives, true))
}
fn get_list(passes_directives: &[CommandTree], include_help: bool) -> Vec<CommandTree> {
use DirectiveAction::*;
vec![
CommandTree::terminal("exit", Some("exit the REPL"), vec![], QuitProgram),
//TODO there should be an alias for this
CommandTree::terminal("quit", Some("exit the REPL"), vec![], QuitProgram),
CommandTree::terminal(
"help",
Some("Print this help message"),
if include_help { get_list(passes_directives, false) } else { vec![] },
Help,
),
CommandTree::nonterm(
"debug",
Some("Configure debug information"),
vec![
CommandTree::terminal(
"list-passes",
Some("List all registered compiler passes"),
vec![],
ListPasses,
),
CommandTree::nonterm(
"total-time",
None,
vec![
CommandTree::terminal("on", None, vec![], TotalTime(true)),
CommandTree::terminal("off", None, vec![], TotalTime(false)),
],
),
CommandTree::nonterm(
"stage-times",
Some("Computation time per-stage"),
vec![
CommandTree::terminal("on", None, vec![], StageTime(true)),
CommandTree::terminal("off", None, vec![], StageTime(false)),
],
),
],
),
CommandTree::terminal("doc", Some("Get language-specific help for an item"), vec![], Doc),
]
}

View File

@ -1,63 +0,0 @@
use std::fmt::Write as FmtWrite;
use colored::*;
use crate::{
command_tree::CommandTree, language::ProgrammingLanguageInterface, InterpreterDirectiveOutput, Repl,
};
pub fn help<L: ProgrammingLanguageInterface>(
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
match arguments {
[] => global_help(repl),
commands => {
let dirs = repl.get_directives();
Some(match get_directive_from_commands(commands, &dirs) {
None => format!("Directive `{}` not found", commands.last().unwrap()),
Some(dir) => {
let mut buf = String::new();
let cmd = dir.get_cmd();
let children = dir.get_children();
writeln!(buf, "`{}` - {}", cmd, dir.get_help()).unwrap();
for sub in children.iter() {
writeln!(buf, "\t`{} {}` - {}", cmd, sub.get_cmd(), sub.get_help()).unwrap();
}
buf
}
})
}
}
}
fn get_directive_from_commands<'a>(commands: &[&str], dirs: &'a CommandTree) -> Option<&'a CommandTree> {
let mut directive_list = dirs.get_children();
let mut matched_directive = None;
for cmd in commands {
let found = directive_list.iter().find(|directive| directive.get_cmd() == *cmd);
if let Some(dir) = found {
directive_list = dir.get_children();
}
matched_directive = found;
}
matched_directive
}
fn global_help<L: ProgrammingLanguageInterface>(repl: &mut Repl<L>) -> InterpreterDirectiveOutput {
let mut buf = String::new();
writeln!(buf, "{} version {}", "Schala REPL".bright_red().bold(), crate::VERSION_STRING).unwrap();
writeln!(buf, "-----------------------").unwrap();
for directive in repl.get_directives().get_children() {
writeln!(buf, "{}{} - {}", repl.sigil, directive.get_cmd(), directive.get_help()).unwrap();
}
writeln!(buf).unwrap();
writeln!(buf, "Language-specific help for {}", <L as ProgrammingLanguageInterface>::language_name())
.unwrap();
writeln!(buf, "-----------------------").unwrap();
Some(buf)
}

View File

@ -1,56 +1,181 @@
use std::{collections::HashSet, time}; use std::collections::HashMap;
use colored::*;
use std::fmt::Write;
pub struct LLVMCodeString(pub String);
#[derive(Debug, Default, Serialize, Deserialize)]
pub struct EvalOptions {
pub debug: DebugOptions,
pub execution_method: ExecutionMethod
}
#[derive(Debug, Serialize, Deserialize)]
pub enum ExecutionMethod {
Compile,
Interpret,
}
impl Default for ExecutionMethod {
fn default() -> ExecutionMethod {
ExecutionMethod::Interpret
}
}
#[derive(Debug, Default, Serialize, Deserialize)]
pub struct DebugOptions {
pub tokens: bool,
pub parse_tree: bool,
pub ast: bool,
pub type_checking: bool,
pub symbol_table: bool,
pub evaluation: bool,
pub llvm_ir: bool,
}
#[derive(Debug, Default)]
pub struct LanguageOutput {
output: String,
artifacts: Vec<TraceArtifact>,
pub 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);
}
}
#[derive(Debug, Default)]
pub struct UnfinishedComputation {
artifacts: HashMap<String, TraceArtifact>,
}
#[derive(Debug)]
pub struct FinishedComputation {
artifacts: HashMap<String, TraceArtifact>,
text_output: Result<String, String>,
}
impl UnfinishedComputation {
pub fn add_artifact(&mut self, artifact: TraceArtifact) {
self.artifacts.insert(artifact.stage_name.clone(), artifact);
}
pub fn output(self, output: Result<String, String>) -> FinishedComputation {
FinishedComputation {
artifacts: self.artifacts,
text_output: output
}
}
}
impl FinishedComputation {
pub fn to_repl(&self) -> String {
let mut buf = String::new();
for stage in ["tokens", "parse_trace", "ast", "symbol_table", "type_check"].iter() {
if let Some(artifact) = self.artifacts.get(&stage.to_string()) {
let color = artifact.text_color;
let stage = stage.color(color).bold();
let output = artifact.debug_output.color(color);
write!(&mut buf, "{}: {}\n", stage, output).unwrap();
}
}
match self.text_output {
Ok(ref output) => write!(&mut buf, "{}", output).unwrap(),
Err(ref err) => write!(&mut buf, "{} {}", "Error: ".red().bold(), err).unwrap(),
}
buf
}
pub fn to_noninteractive(&self) -> Option<String> {
match self.text_output {
Ok(_) => {
let mut buf = String::new();
for stage in ["tokens", "parse_trace", "ast", "symbol_table", "type_check"].iter() {
if let Some(artifact) = self.artifacts.get(&stage.to_string()) {
let color = artifact.text_color;
let stage = stage.color(color).bold();
let output = artifact.debug_output.color(color);
write!(&mut buf, "{}: {}\n", stage, output).unwrap();
}
}
if buf == "" { None } else { Some(buf) }
},
Err(ref s) => Some(format!("{} {}", "Error: ".red().bold(), s))
}
}
}
#[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 { pub trait ProgrammingLanguageInterface {
type Config: Default + Clone; /* old */
fn language_name() -> String; fn evaluate_in_repl(&mut self, _: &str, _: &EvalOptions) -> LanguageOutput {
fn source_file_suffix() -> String; LanguageOutput { output: format!("Defunct"), artifacts: vec![], failed: false }
}
/* old */
fn run_computation(&mut self, _request: ComputationRequest<Self::Config>) -> ComputationResponse; fn new_execute(&mut self, input: &str, _options: &EvalOptions) -> FinishedComputation {
FinishedComputation { artifacts: HashMap::new(), text_output: Err(format!("NOT DONE")) }
}
fn request_meta(&mut self, _request: LangMetaRequest) -> LangMetaResponse { fn execute(&mut self, _input: &str, _eval_options: &EvalOptions) -> FinishedComputation {
LangMetaResponse::Custom { kind: "not-implemented".to_owned(), value: format!("") } FinishedComputation { artifacts: HashMap::new(), text_output: Err(format!("REPL evaluation not implemented")) }
} }
} fn get_language_name(&self) -> String;
fn get_source_file_suffix(&self) -> String;
pub struct ComputationRequest<'a, T> { fn handle_custom_interpreter_directives(&mut self, commands: &Vec<&str>) -> Option<String> {
pub source: &'a str, None
pub config: T, }
pub debug_requests: HashSet<DebugAsk>, fn custom_interpreter_directives_help(&self) -> String {
} format!(">> No custom interpreter directives specified <<")
}
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, token: Option<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

@ -1,249 +1,391 @@
#![feature(box_patterns, proc_macro_hygiene, decl_macro, iter_intersperse)] #![feature(link_args)]
#![feature(slice_patterns, box_patterns, box_syntax)]
#![feature(plugin)]
#![plugin(rocket_codegen)]
extern crate getopts;
extern crate rustyline;
extern crate itertools;
extern crate colored;
#[macro_use] #[macro_use]
extern crate serde_derive; extern crate serde_derive;
extern crate serde_json;
extern crate rocket;
extern crate rocket_contrib;
extern crate includedir; extern crate includedir;
extern crate phf; extern crate phf;
extern crate serde_json;
mod command_tree; use std::path::Path;
use std::fs::File;
use std::io::{Read, Write};
use std::process::exit;
use std::default::Default;
use std::fmt::Write as FmtWrite;
use rustyline::error::ReadlineError;
use rustyline::Editor;
use self::colored::*;
mod language; mod language;
use self::command_tree::CommandTree; mod webapp;
mod repl_options; pub mod llvm_wrap;
use repl_options::ReplOptions;
mod directive_actions;
mod directives;
use directives::directives_from_pass_names;
mod help;
mod response;
use std::{collections::HashSet, sync::Arc};
use colored::*; const VERSION_STRING: &'static str = "0.1.0";
pub use language::{
ComputationRequest, ComputationResponse, DebugAsk, DebugResponse, GlobalOutputStats, LangMetaRequest,
LangMetaResponse, ProgrammingLanguageInterface,
};
use response::ReplResponse;
include!(concat!(env!("OUT_DIR"), "/static.rs")); include!(concat!(env!("OUT_DIR"), "/static.rs"));
const VERSION_STRING: &str = "0.1.0";
const HISTORY_SAVE_FILE: &str = ".schala_history"; pub use language::{LLVMCodeString, ProgrammingLanguageInterface, EvalOptions, ExecutionMethod, TraceArtifact, LanguageOutput, FinishedComputation, UnfinishedComputation};
const OPTIONS_SAVE_FILE: &str = ".schala_repl"; pub type PLIGenerator = Box<Fn() -> Box<ProgrammingLanguageInterface> + Send + Sync>;
type InterpreterDirectiveOutput = Option<String>; pub fn repl_main(generators: Vec<PLIGenerator>) {
let languages: Vec<Box<ProgrammingLanguageInterface>> = generators.iter().map(|x| x()).collect();
pub struct Repl<L: ProgrammingLanguageInterface> { let option_matches = program_options().parse(std::env::args()).unwrap_or_else(|e| {
/// If this is the first character typed by a user into the repl, the following println!("{:?}", e);
/// will be interpreted as a directive to the REPL rather than a command in the exit(1);
/// running programming language. });
sigil: char,
line_reader: ::linefeed::interface::Interface<::linefeed::terminal::DefaultTerminal>, if option_matches.opt_present("list-languages") {
language_state: L, for lang in languages {
options: ReplOptions, 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 mut options = EvalOptions::default();
if let Some(ref ltrs) = option_matches.opt_str("debug") {
options.debug.tokens = ltrs.contains("l");
options.debug.ast = ltrs.contains("a");
options.debug.parse_tree = ltrs.contains("r");
options.debug.symbol_table = ltrs.contains("s");
}
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);
options.execution_method = match option_matches.opt_str("eval-style") {
Some(ref s) if s == "compile" => ExecutionMethod::Compile,
_ => ExecutionMethod::Interpret,
};
match option_matches.free[..] {
[] | [_] => {
let mut repl = Repl::new(languages, initial_index);
repl.run();
}
[_, ref filename, _..] => {
run_noninteractive(filename, languages, options);
}
};
} }
#[derive(Clone)] fn run_noninteractive(filename: &str, languages: Vec<Box<ProgrammingLanguageInterface>>, options: EvalOptions) {
enum PromptStyle { let path = Path::new(filename);
Normal, let ext = path.extension().and_then(|e| e.to_str()).unwrap_or_else(|| {
Multiline, 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();
match options.execution_method {
ExecutionMethod::Compile => {
/*
let llvm_bytecode = language.compile(&buffer);
compilation_sequence(llvm_bytecode, filename);
*/
panic!("Not ready to go yet");
},
ExecutionMethod::Interpret => {
let output = language.execute(&buffer, &options);
output.to_noninteractive().map(|text| println!("{}", text));
}
}
} }
impl<L: ProgrammingLanguageInterface> Repl<L> { struct Repl {
pub fn new(initial_state: L) -> Self { options: EvalOptions,
use linefeed::Interface; languages: Vec<Box<ProgrammingLanguageInterface>>,
let line_reader = Interface::new("schala-repl").unwrap(); current_language_index: usize,
let sigil = ':'; interpreter_directive_sigil: char,
console: rustyline::Editor<()>,
}
Repl { sigil, line_reader, language_state: initial_state, options: ReplOptions::new() } 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
} }
}
pub fn run_repl(&mut self, config: L::Config) { fn get_options() -> EvalOptions {
println!("Schala meta-interpeter version {}", VERSION_STRING); File::open(".schala_repl")
println!("Type {} for help with the REPL", format!("{}help", self.sigil).bright_green().bold()); .and_then(|mut file| {
self.load_options(); let mut contents = String::new();
self.handle_repl_loop(config); file.read_to_string(&mut contents)?;
self.save_before_exit(); Ok(contents)
println!("Exiting..."); })
.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 load_options(&mut self) { fn run(&mut self) {
self.line_reader.load_history(HISTORY_SAVE_FILE).unwrap_or(()); println!("Schala MetaInterpreter version {}", VERSION_STRING);
match ReplOptions::load_from_file(OPTIONS_SAVE_FILE) { println!("Type {}help for help with the REPL", self.interpreter_directive_sigil);
Ok(options) => {
self.options = options; 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) => {
let output = match input.chars().nth(0) {
Some(ch) if ch == self.interpreter_directive_sigil => self.handle_interpreter_directive(input),
_ => {
self.console.get_history().add(input);
Some(self.input_handler(input))
} }
Err(e) => eprintln!("{}", e), };
if let Some(o) = output {
println!("=> {}", o);
}
} }
}
} }
self.console.get_history().save(".schala_history").unwrap_or(());
self.save_options();
println!("Exiting...");
}
fn handle_repl_loop(&mut self, config: L::Config) { fn input_handler(&mut self, input: &str) -> String {
use linefeed::ReadResult::*; let ref mut language = self.languages[self.current_language_index];
let interpreter_output = language.new_execute(input, &self.options);
interpreter_output.to_repl()
}
'main: loop { fn handle_interpreter_directive(&mut self, input: &str) -> Option<String> {
macro_rules! match_or_break { let mut iter = input.chars();
($line:expr) => { iter.next();
match $line { let commands: Vec<&str> = iter
Err(e) => { .as_str()
println!("readline IO Error: {}", e); .split_whitespace()
break 'main; .collect();
}
Ok(Eof) | Ok(Signal(_)) => break 'main, let cmd: &str = match commands.get(0).clone() {
Ok(Input(ref input)) => input, None => return None,
} Some(s) => s
}; };
match cmd {
"exit" | "quit" => {
self.save_options();
exit(0)
},
"lang" | "language" => match commands.get(1) {
Some(&"show") => {
let mut buf = String::new();
for (i, lang) in self.languages.iter().enumerate() {
write!(buf, "{}{}\n", if i == self.current_language_index { "* "} else { "" }, lang.get_language_name()).unwrap();
}
Some(buf)
},
Some(&"go") => match commands.get(2) {
None => Some(format!("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;
return Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()));
}
} }
self.update_line_reader(); Some(format!("Language {} not found", desired_name))
let line = self.line_reader.read_line(); }
let input: &str = match_or_break!(line); },
Some(&"next") | Some(&"n") => {
self.current_language_index = (self.current_language_index + 1) % self.languages.len();
Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()))
},
Some(&"previous") | Some(&"p") | Some(&"prev") => {
self.current_language_index = if self.current_language_index == 0 { self.languages.len() - 1 } else { self.current_language_index - 1 };
Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()))
},
Some(e) => Some(format!("Bad `lang(uage)` argument: {}", e)),
None => Some(format!("Valid arguments for `lang(uage)` are `show`, `next`|`n`, `previous`|`prev`|`n`"))
},
"help" => {
let mut buf = String::new();
let ref lang = self.languages[self.current_language_index];
self.line_reader.add_history_unique(input.to_string()); writeln!(buf, "MetaInterpreter options").unwrap();
let mut chars = input.chars().peekable(); writeln!(buf, "-----------------------").unwrap();
let repl_responses = match chars.next() { writeln!(buf, "exit | quit - exit the REPL").unwrap();
Some(ch) if ch == self.sigil => writeln!(buf, "lang [prev|next|go <name> |show] - toggle to previous or next language, go to a specific language by name, or show all languages").unwrap();
if chars.peek() == Some(&'{') { writeln!(buf, "Language-specific help for {}", lang.get_language_name()).unwrap();
let mut buf = String::new(); writeln!(buf, "-----------------------").unwrap();
buf.push_str(input.get(2..).unwrap()); writeln!(buf, "{}", lang.custom_interpreter_directives_help()).unwrap();
'multiline: loop { Some(buf)
self.set_prompt(PromptStyle::Multiline); },
let new_line = self.line_reader.read_line(); "set" => {
let new_input = match_or_break!(new_line); let show = match commands.get(1) {
if new_input.starts_with(":}") { Some(&"show") => true,
break 'multiline; Some(&"hide") => false,
} else { Some(e) => {
buf.push_str(new_input); return Some(format!("Bad `set` argument: {}", e));
buf.push('\n'); }
} None => {
} return Some(format!("`set` - valid arguments `show {{option}}`, `hide {{option}}`"));
self.handle_input(&buf, &config) }
} else {
if let Some(output) = self.handle_interpreter_directive(input.get(1..).unwrap()) {
println!("{}", output);
}
continue;
},
_ => self.handle_input(input, &config),
};
for repl_response in repl_responses.iter() {
println!("{}", repl_response);
}
}
}
fn update_line_reader(&mut self) {
let tab_complete_handler = TabCompleteHandler::new(self.sigil, self.get_directives());
self.line_reader.set_completer(Arc::new(tab_complete_handler)); //TODO fix this here
self.set_prompt(PromptStyle::Normal);
}
fn set_prompt(&mut self, prompt_style: PromptStyle) {
let prompt_str = match prompt_style {
PromptStyle::Normal => ">> ",
PromptStyle::Multiline => ">| ",
}; };
match commands.get(2) {
self.line_reader.set_prompt(prompt_str).unwrap(); Some(&"tokens") => self.options.debug.tokens = show,
} Some(&"parse") => self.options.debug.parse_tree = show,
Some(&"ast") => self.options.debug.ast = show,
fn save_before_exit(&self) { Some(&"symbols") => self.options.debug.symbol_table = show,
self.line_reader.save_history(HISTORY_SAVE_FILE).unwrap_or(()); Some(&"llvm") => self.options.debug.llvm_ir = show,
self.options.save_to_file(OPTIONS_SAVE_FILE); Some(e) => return Some(format!("Bad `show`/`hide` argument: {}", e)),
} None => return Some(format!("`show`/`hide` requires an argument")),
fn handle_interpreter_directive(&mut self, input: &str) -> InterpreterDirectiveOutput {
let arguments: Vec<&str> = input.split_whitespace().collect();
if arguments.is_empty() {
return None;
}
let directives = self.get_directives();
directives.perform(self, &arguments)
}
fn handle_input(&mut self, input: &str, config: &L::Config) -> Vec<ReplResponse> {
let mut debug_requests = HashSet::new();
for ask in self.options.debug_asks.iter() {
debug_requests.insert(ask.clone());
}
let request = ComputationRequest { source: input, config: config.clone(), debug_requests };
let response = self.language_state.run_computation(request);
response::handle_computation_response(response, &self.options)
}
fn get_directives(&mut self) -> CommandTree {
let pass_names = match self.language_state.request_meta(LangMetaRequest::StageNames) {
LangMetaResponse::StageNames(names) => names,
_ => vec![],
}; };
None
},
"options" => {
let ref d = self.options.debug;
let tokens = if d.tokens { "true".green() } else { "false".red() };
let parse_tree = if d.parse_tree { "true".green() } else { "false".red() };
let ast = if d.ast { "true".green() } else { "false".red() };
let symbol_table = if d.symbol_table { "true".green() } else { "false".red() };
Some(format!(r#"Debug:
tokens: {}, parse: {}, ast: {}, symbols: {}"#, tokens, parse_tree, ast, symbol_table))
},
e => self.languages[self.current_language_index]
.handle_custom_interpreter_directives(&commands)
.or(Some(format!("Unknown command: {}", e)))
}
}
}
directives_from_pass_names(&pass_names) /*
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));
} }
} }
*/
struct TabCompleteHandler { fn program_options() -> getopts::Options {
sigil: char, let mut options = getopts::Options::new();
top_level_commands: CommandTree, options.optopt("s",
} "eval-style",
"Specify whether to compile (if supported) or interpret the language. If not specified, the default is language-specific",
use linefeed::{ "[compile|interpret]"
complete::{Completer, Completion}, );
terminal::Terminal, options.optflag("",
}; "list-languages",
"Show a list of all supported languages");
impl TabCompleteHandler { options.optopt("l",
fn new(sigil: char, top_level_commands: CommandTree) -> TabCompleteHandler { "lang",
TabCompleteHandler { top_level_commands, sigil } "Start up REPL in a language",
} "LANGUAGE");
} options.optflag("h",
"help",
impl<T: Terminal> Completer<T> for TabCompleteHandler { "Show help text");
fn complete( options.optflag("w",
&self, "webapp",
word: &str, "Start up web interpreter");
prompter: &::linefeed::prompter::Prompter<T>, options.optopt("d",
start: usize, "debug",
_end: usize, "Debug a stage (l = tokenizer, a = AST, r = parse trace, s = symbol table)",
) -> Option<Vec<Completion>> { "[l|a|r|s]");
let line = prompter.buffer(); options
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<&CommandTree> = Some(&self.top_level_commands);
loop {
match words.next() {
None => {
let top = matches!(command_tree, Some(CommandTree::Top(_)));
let word = if top { word.get(1..).unwrap() } else { word };
for cmd in command_tree.map(|x| x.get_subcommands()).unwrap_or_default().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<&CommandTree> = command_tree.and_then(|cm| match cm {
CommandTree::Top(children) => children.iter().find(|c| c.get_cmd() == s),
CommandTree::NonTerminal { children, .. } =>
children.iter().find(|c| c.get_cmd() == s),
CommandTree::Terminal { children, .. } => children.iter().find(|c| c.get_cmd() == s),
});
command_tree = new_ptr;
}
}
}
Some(completions)
}
} }

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()) }
}

View File

@ -1,43 +0,0 @@
use std::{
collections::HashSet,
fs::File,
io::{self, Read, Write},
};
use crate::language::DebugAsk;
#[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 {
eprintln!("Error saving {} file {}", filename, err);
}
}
pub fn load_from_file(filename: &str) -> Result<ReplOptions, io::Error> {
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)
})
}
}

View File

@ -1,74 +0,0 @@
use std::{fmt, fmt::Write};
use colored::*;
use crate::{
language::{ComputationResponse, DebugAsk},
ReplOptions,
};
pub struct ReplResponse {
label: Option<String>,
text: String,
color: Option<Color>,
}
impl fmt::Display for ReplResponse {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let mut buf = String::new();
if let Some(ref label) = self.label {
write!(buf, "({})", label).unwrap();
}
write!(buf, "=> {}", self.text).unwrap();
write!(
f,
"{}",
match self.color {
Some(c) => buf.color(c),
None => buf.normal(),
}
)
}
}
pub fn handle_computation_response(
response: ComputationResponse,
options: &ReplOptions,
) -> Vec<ReplResponse> {
let mut responses = vec![];
if options.show_total_time {
responses.push(ReplResponse {
label: Some("Total time".to_string()),
text: format!("{:?}", response.global_output_stats.total_duration),
color: None,
});
}
if options.show_stage_times {
responses.push(ReplResponse {
label: Some("Stage times".to_string()),
text: format!("{:?}", response.global_output_stats.stage_durations),
color: None,
});
}
for debug_resp in response.debug_responses {
let stage_name = match debug_resp.ask {
DebugAsk::ByStage { stage_name, .. } => stage_name,
_ => continue,
};
responses.push(ReplResponse {
label: Some(stage_name.to_string()),
text: debug_resp.value,
color: Some(Color::Red),
});
}
responses.push(match response.main_output {
Ok(s) => ReplResponse { label: None, text: s, color: None },
Err(e) => ReplResponse { label: Some("Error".to_string()), text: e, color: Some(Color::Red) },
});
responses
}

44
schala-repl/src/webapp.rs Normal file
View File

@ -0,0 +1,44 @@
use rocket;
use rocket::State;
use rocket::response::Content;
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

@ -1,11 +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 +1,12 @@
fn main() {
const a = 10
const b = 20
a + b
}
//foo
print(main())

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

@ -1,115 +0,0 @@
fn main() {
//comments are C-style
/* nested comments /* are cool */ */
}
@annotations use the @ sigil
// variable expressions
//variable declaration works like Rust
let a: I32 = 20
let mut b: String = 20
there(); can(); be(); multiple(); statements(); per_line();
//string interpolation
// maybe
let yolo = "I have ${a + b} people in my house"
// let expressions
let a = 10, b = 20, c = 30 in a + b + c
//list literal
let q = [1,2,3,4]
//lambda literal - uses haskell-ish syntax
q.map(\(item) { item * 100 })
fn yolo(a: MyType, b: YourType): ReturnType<Param1, Param2> {
if a == 20 {
return "early"
}
}
/* for/while loop topics */
//TODO I can probably get away with having one of `for`, `while`
//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` functions as an operator asking "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
type alias <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 } // shorthand special-case for `type MyData = 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 TODO I probably want to rename this
trait Bashable { }
trait Luggable {
fn lug(self, a: Option<Self>)
}
}
// lambdas - maybe I want to use ruby-style (not rust style) syntax
// e.g.
// Also TODO Nix uses `X: Y: Z` for in its value-level syntax, why can't I?
let a: X -> Y -> Z = {|x,y| }

View File

@ -1,17 +1,105 @@
println(sua(4)) fn main() {
//comments are C-style
/* nested comments /* are cool */ */
fn sua(x): Int {
x + 10
} }
@annotations are with @-
//let a = getline() // 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 {
//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'?
/* /*
if a == "true" { 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?
println("You typed true") maybe introduce a 'newtype' keyword for this
} else { */
println("You typed something else")
//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

@ -1,71 +1,20 @@
use std::{collections::HashSet, fs::File, io::Read, path::PathBuf, process::exit}; extern crate schala_repl;
use schala_lang::{Schala, SchalaConfig}; extern crate maaru_lang;
use schala_repl::{ComputationRequest, ProgrammingLanguageInterface, Repl}; extern crate rukka_lang;
extern crate robo_lang;
extern crate schala_lang;
use schala_repl::{PLIGenerator, repl_main};
extern { }
//TODO specify multiple langs, and have a way to switch between them
fn main() { fn main() {
let args: Vec<String> = std::env::args().collect(); let generators: Vec<PLIGenerator> = vec![
let matches = command_line_options().parse(&args[1..]).unwrap_or_else(|e| { Box::new(|| { Box::new(schala_lang::Schala::new())}),
eprintln!("Error parsing options: {}", e); Box::new(|| { Box::new(maaru_lang::Maaru::new())}),
exit(1); Box::new(|| { Box::new(robo_lang::Robo::new())}),
}); Box::new(|| { Box::new(rukka_lang::Rukka::new())}),
];
if matches.opt_present("help") { repl_main(generators);
println!("{}", command_line_options().usage("Schala metainterpreter"));
exit(0);
}
if matches.free.is_empty() {
let state = Schala::new();
let mut repl = Repl::new(state);
let config = SchalaConfig { repl: true };
repl.run_repl(config);
} else {
let paths: Vec<PathBuf> = matches.free.iter().map(PathBuf::from).collect();
//TODO handle more than one file
let filename = &paths[0];
let extension = filename.extension().and_then(|e| e.to_str()).unwrap_or_else(|| {
eprintln!("Source file `{}` has no extension.", filename.display());
exit(1);
});
//TODO this proably should be a macro for every supported language
if extension == Schala::source_file_suffix() {
let config = SchalaConfig { repl: false };
run_noninteractive(paths, Schala::new(), config);
} else {
eprintln!("Extension .{} not recognized", extension);
exit(1);
}
}
} }
pub fn run_noninteractive<L: ProgrammingLanguageInterface>(
filenames: Vec<PathBuf>,
mut language: L,
config: L::Config,
) {
// for now, ony do something with the first filename
let filename = &filenames[0];
let mut source_file = File::open(filename).unwrap();
let mut buffer = String::new();
source_file.read_to_string(&mut buffer).unwrap();
let request = ComputationRequest { source: &buffer, config, debug_requests: HashSet::new() };
let response = language.run_computation(request);
match response.main_output {
Ok(s) => println!("{}", s),
Err(s) => eprintln!("{}", 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
}