diff options
| author | 2026-10-14 08:29:46 +0330 | |
|---|---|---|
| committer | 2026-10-14 08:29:46 +0330 | |
| commit | 1c53304d03414890af0da7432d1aea87e754a14a (patch) | |
| tree | 97190d86cf548c9bc63f68c86a4d2a4f09809713 /src/lib | |
| parent | a (diff) | |
feat: grow memory limits, add icon/actor libraries, overhaul LSP diagnostics
Compiler and VM
- make every memory map limit dynamic and adjustable at both build time and
runtime, including compiler tables, stacks, and every execution region
- reserve and grow tables, operand and return stacks, frame segments, and
image-building output without relocating live code or globals
- rename i/o and string helpers consistently (puts -> put_s, putn -> put_n,
scat -> cat_s) across compiler, runtime, examples, tests, and docs
- recast and consume values assigned to globals from inside functions
- allow fixed and const together, add typed closure returns (fn:t(...)),
multi-include syntax (include rt, run, core;), and recurse type inference
- never infer string literals as word, anywhere, as argument, variable, or
return type
- draft docs/BORROW.md: a borrow checker less intrusive than Rust's but more
intelligent
LSP and editor integration
- require explicit includes and give every toolchain area its own namespace
(rt, lsp, run, core)
- hover for built-in types, inferred types, values known at hover time, array
and pointer lifetime/size, library names in include statements, and inferred
lifetimes with explanations
- honor /* */ comments as documentation for variables and arguments, and stop
misattributing section headers or trailing comments as variable hints
- stream diagnostics and cancel stale requests on change
- jump to definition and references, including cross-file
- quick fixes with automatic library import, and namespace completion
Hints and diagnostics
- render hints as blue squigglies by default, with hints on/small/off per file
- suppress magic-number hints via a preceding /* */ comment, and say so
- warn on unused arguments; allow multiple _ discards in parameters, pattern
matching, and tagged enums, warning if a _ is actually used
- rewrite hint and comment prose in professional compiler-doc register
Libraries
- add icon.zc: run-time self-modification, find/replace syntax, type and block
edits, and step-through inspection of locals and globals
- add actor.zc: async actors with Actor<I,O>, implicit this, spawn/recv/send,
injected into the compiler machinery at include time rather than built in
Tooling and docs
- reorganize sources, tests, and designs into subdirectories
- unify windows entry points in tinyvm.bat and add a matching tinyvm.sh
- add --help across the toolchain
- polish the learning guide, stdlib docs, and design notes
Tests
- add accept, reject, and regression coverage across the compiler, LSP,
- runtime, icon, actors, threads, formatting, and the toolchain contracts,
plus fuzzers and property tests
Diffstat (limited to 'src/lib')
| -rw-r--r-- | src/lib/actor.zc | 280 | ||||
| -rw-r--r-- | src/lib/icon.zc | 623 | ||||
| -rw-r--r-- | src/lib/std.zc | 327 |
3 files changed, 1141 insertions, 89 deletions
diff --git a/src/lib/actor.zc b/src/lib/actor.zc new file mode 100644 index 0000000..29fd600 --- /dev/null +++ b/src/lib/actor.zc @@ -0,0 +1,280 @@ +namespace actor; +include rt, run; + +// stream entries are raw words: integer payloads never acquire heap ownership. +unchecked word vector() { return rt.dnew(1, 0, 0); } +unchecked int append(word vector, word value) { + rt.dgrow(vector, vector[0] + 1); vector[2][vector[0]] = value; vector[0]++; return 0; +} +unchecked int find(word refs, word value) { + int i = 0; while (i < refs[0]) { if (refs[2][i] == value) return i; i++; } return -1; +} +unchecked int size(word type) { return type[1]; } +unchecked int packed(word type) { if (type[0] == 1 || type[0] == 12) return type[5]; return 0; } + +// encode pointer graphs with identity records; decoding creates fresh objects. +// typed fields determine references, so an integer equal to a heap address +// remains an integer. repeated references and cycles preserve identity. +unchecked int encode(word data, word refs, word address, word type) { + int kind = type[0], i = 0, offset, bytes, n, id; word pointer, element; + if (kind == 8) { + while (i < type[3]) { + element = type[4][i * 3 + 1]; offset = type[4][i * 3 + 2]; + if (offset < 0) { bytes = packed(element); n = 0; int k = 0; while (k < bytes) { n |= rt.ld8(rt.addr_b(address) - offset - 1 + k) << (k * 8); k++; } append(data, n); } + else encode(data, refs, address + offset, element); + i++; + } + return 0; + } + if (kind == 6) { + element = type[4]; bytes = packed(element); + while (i < type[3]) { + if (bytes) { n = 0; int k = 0; while (k < bytes) { n |= rt.ld8(rt.addr_b(address) + i * bytes + k) << (k * 8); k++; } append(data, n); } + else encode(data, refs, address + i * size(element), element); + i++; + } + return 0; + } + if (kind != 5 && kind != 11 && kind != 13 && kind != 7) { append(data, *address); return 0; } + pointer = *address; + if (!pointer) { append(data, 0); if (kind == 7) append(data, 0); return 0; } + if (kind == 7 && rt.callable_code(pointer)) { append(data, 0); append(data, pointer); return 0; } + id = find(refs, pointer); + if (id >= 0) { append(data, id + 1); return 0; } + id = refs[0]; append(refs, pointer); append(data, 0 - id - 1); + if (kind == 11) { + n = pointer[0]; append(data, n); element = type[4]; bytes = packed(element); + while (i < n) { + if (bytes) { int k = 0; int value = 0; while (k < bytes) { value |= rt.ld8(rt.addr_b(pointer[2]) + i * bytes + k) << (k * 8); k++; } append(data, value); } + else encode(data, refs, pointer[2] + i * size(element), element); + i++; + } + return 0; + } + if (kind == 13) { n = rt.len_s(pointer); append(data, n); while (i < n) { append(data, rt.at_s(pointer, i)); i++; } return 0; } + if (kind == 7) { + element = pointer[-1]; n = pointer[-5] - rt.HDR; + append(data, n); append(data, element); encode(data, refs, pointer, element); return 0; + } + element = type[4]; bytes = packed(element); + if (rt.isobj(pointer)) n = pointer[-5] - rt.HDR; + else if (element[0] == 2) n = rt.len_w(pointer) + 1; + else n = size(element); + append(data, n); + if (bytes || size(element) <= 0) { while (i < n) { append(data, pointer[i]); i++; } } + else { while (i + size(element) <= n) { encode(data, refs, pointer + i, element); i += size(element); } } + return 0; +} +unchecked word take(word frame) { word result = frame[0][2][frame[1]]; frame[1]++; return result; } +unchecked int decode(word frame, word refs, word address, word type) { + int kind = type[0], i = 0, offset, bytes, n, id; word pointer, element; + if (kind == 8) { + while (i < type[3]) { + element = type[4][i * 3 + 1]; offset = type[4][i * 3 + 2]; + if (offset < 0) { bytes = packed(element); word value = take(frame); int k = 0; while (k < bytes) { rt.st8(rt.addr_b(address) - offset - 1 + k, value >> (k * 8)); k++; } } + else decode(frame, refs, address + offset, element); + i++; + } + return 0; + } + if (kind == 6) { + element = type[4]; bytes = packed(element); + while (i < type[3]) { + if (bytes) { word value = take(frame); int k = 0; while (k < bytes) { rt.st8(rt.addr_b(address) + i * bytes + k, value >> (k * 8)); k++; } } + else decode(frame, refs, address + i * size(element), element); + i++; + } + return 0; + } + if (kind != 5 && kind != 11 && kind != 13 && kind != 7) { *address = take(frame); return 0; } + id = take(frame); + if (!id) { if (kind == 7) *address = take(frame); else *address = 0; return 0; } + if (id > 0) { *address = refs[2][id - 1]; return 0; } + n = take(frame); + if (kind == 11) { + element = type[4]; bytes = packed(element); + if (bytes) pointer = rt.dnew(0 - bytes, n, type); else pointer = rt.dnew(size(element), n, type); + append(refs, pointer); *address = pointer; + while (i < n) { + if (bytes) { word value = take(frame); int k = 0; while (k < bytes) { rt.st8(rt.addr_b(pointer[2]) + i * bytes + k, value >> (k * 8)); k++; } } + else decode(frame, refs, pointer[2] + i * size(element), element); + i++; + } + return 0; + } + if (kind == 13) { + pointer = rt.new((n + 7) / 8 + 1); pointer[0] = n; append(refs, pointer); *address = pointer; + while (i < n) { rt.st8(rt.addr_b(pointer + 1) + i, take(frame)); i++; } return 0; + } + if (kind == 7) { element = take(frame); pointer = rt.new_t(n, element); append(refs, pointer); *address = pointer; decode(frame, refs, pointer, element); return 0; } + pointer = rt.new_t(n, type[4]); append(refs, pointer); *address = pointer; + element = type[4]; bytes = packed(element); + if (bytes || size(element) <= 0) { while (i < n) { pointer[i] = take(frame); i++; } } + else { while (i + size(element) <= n) { decode(frame, refs, pointer + i, element); i += size(element); } } + return 0; +} +unchecked int write_message(int fd, word address, word type) { + word data = vector(), refs = vector(); int count; + encode(data, refs, address, type); count = data[0]; + int result = rt.syscall(44, fd, &count, 1); + if (result >= 0) result = rt.syscall(44, fd, data[2], count); + rt.free(refs); rt.free(data); return result; +} +unchecked int read_message(int fd, word address, word type) { + int count = 0; word data, refs, frame[2]; + if (rt.syscall(45, fd, &count, 1) < 0 || count < 0 || count > 1048576) return -1; + data = rt.dnew(1, count, 0); refs = vector(); frame[0] = data; frame[1] = 0; + if (rt.syscall(45, fd, data[2], count) < 0) { rt.free(refs); rt.free(data); return -1; } + decode(frame, refs, address, type); rt.free(refs); rt.free(data); return 0; +} + +int busy, worker; +type Dispatcher = fn(); +Dispatcher[?] dispatchers; +unchecked int dispatch() { + if (busy || worker || !dispatchers) return 0; + busy = 1; int i = 0; + while (i < len(dispatchers)) { if (dispatchers[i]) dispatchers[i](); i++; } + busy = 0; return 0; +} + +// declared actors expose a typed handle method and receive their own endpoint. +// lowering lives in this imported source; the compiler only dispatches callbacks. +unchecked int declaration_parameters(word type) { + if (type[0] != run.TY_GEN) return 0; + rt.put_c('<'); int i = 0; + while (i < type[3]) { if (i) rt.put_c(','); rt.put_s(type[6][i]); i++; } + rt.put_c('>'); return 0; +} +unchecked int declaration_type(word type) { rt.put_s(type[2]); declaration_parameters(type); return 0; } +unchecked int declaration_method(word type, char* method) { + rt.put_s("unchecked fn "); rt.put_s(type[2]); rt.put_c('.'); rt.put_s(method); declaration_parameters(type); rt.put_c('('); declaration_type(type); rt.put_s("* this"); return 0; +} +unchecked int parse_actor() { + int symbol = run.kw_struct(); word type = run.sval[symbol], signature, fields, oldfields; + int handler, count, mode, length, capacity; word output, previous_grow; char* buffer; + if (type[0] == run.TY_GEN && rt.eq_w(type[2], "actor.Actor")) return 0; + handler = run.methof(type, run.intern("handle")); + if (handler < 0) { run.serr("an actor declaration requires handle(input) with a typed result"); return 0; } + signature = run.stype[handler]; + if (!signature || signature[3] != 2) { run.serr("an actor handle method requires one input parameter"); return 0; } + int generic = type[0] == run.TY_GEN, stride = 3 - generic; + count = type[3]; if (generic) count = type[5]; int field_index = 0; + while (field_index < count) { if (type[4][field_index * stride] == run.intern("__mailbox")) { run.serr("__mailbox is reserved for actor state"); return 0; } field_index++; } + oldfields = type[4]; fields = run.talloc((count + 1) * stride + 1); + rt.copy_w(fields, oldfields, count * stride); fields[count * stride] = run.intern("__mailbox"); + fields[count * stride + 1] = run.tword; + if (generic) type[5]++; else { fields[count * stride + 2] = type[1]; type[3]++; type[1]++; } + type[4] = fields; + buffer = rt.new(16384); mode = rt.outmode; output = rt.outbuf; length = rt.outn; capacity = rt.outcap; previous_grow = rt.outgrow; + rt.outgrow = 0; rt.outmode = 2; rt.outbuf = buffer; rt.outn = 0; rt.outcap = 16383; + declaration_method(type, "spawn"); rt.put_s(") { if (this.__mailbox) return -1; actor.Actor<"); + run.tprint(signature[8]); rt.put_s(","); run.tprint(signature[4]); rt.put_s(">* endpoint = rt.new(actor.Actor<"); + run.tprint(signature[8]); rt.put_s(","); run.tprint(signature[4]); rt.put_s(">); this.__mailbox = endpoint; return endpoint.spawn(fn("); + run.tprint(signature[8]); rt.put_s(" message) { return this.handle(message); }); } "); + int index = 0; + while (index < 5) { + if (index == 0) declaration_method(type, "send"); else if (index == 1) declaration_method(type, "recv"); else if (index == 2) declaration_method(type, "await"); else if (index == 3) declaration_method(type, "close"); else declaration_method(type, "poll"); + if (index == 0) { rt.put_s(","); run.tprint(signature[8]); rt.put_s(" message"); } + if (index == 1) { rt.put_s(",int("); run.tprint(signature[4]); rt.put_s(").d callback"); } + rt.put_s(") { actor.Actor<"); run.tprint(signature[8]); rt.put_s(","); run.tprint(signature[4]); rt.put_s(">* endpoint = this.__mailbox as actor.Actor<"); + run.tprint(signature[8]); rt.put_s(","); run.tprint(signature[4]); rt.put_s(">*; if (!endpoint) return -1; return endpoint."); + if (index == 0) rt.put_s("send(message);"); else if (index == 1) rt.put_s("recv(callback);"); else if (index == 2) rt.put_s("await();"); else if (index == 3) rt.put_s("close();"); else rt.put_s("poll();"); + rt.put_s(" } "); index++; + } + buffer[rt.outn] = 0; rt.outgrow = previous_grow; rt.outmode = mode; rt.outbuf = output; rt.outn = length; rt.outcap = capacity; + word tokens = run.tokens(buffer); + if (generic) { + int position = 0, variable; + while (position < tokens[0]) { + variable = 0; + while (variable < run.ntl) { + word descriptor = run.typelist[variable]; + if (descriptor[0] == run.TY_VAR && descriptor[3] < type[3] && tokens[1 + position * 3] == run.T_ID && tokens[2 + position * 3] == descriptor[2]) tokens[2 + position * 3] = type[6][descriptor[3]]; + variable++; + } + position++; + } + } + word lowered = rt.new(tokens[0] * 3 + 1); int read = 0, written = 0; + while (read < tokens[0]) { + if (read > 0 && tokens[2 + (read - 1) * 3] == run.s_fn && read + 2 < tokens[0] && tokens[2 + (read + 1) * 3] == run.s_dot) { + lowered[1 + written * 3] = run.T_ID; lowered[2 + written * 3] = run.methname(tokens[2 + read * 3], tokens[2 + (read + 2) * 3]); lowered[3 + written * 3] = tokens[3 + read * 3]; read += 3; + } else { rt.copy_w(lowered + 1 + written * 3, tokens + 1 + read * 3, 3); read++; } + written++; + } + lowered[0] = written; run.compile_list_context(lowered, 1, run.module_name, run.module_imports); rt.free(lowered); rt.free(tokens); rt.free(buffer); return 0; +} +run.syntax("actor", actor.parse_actor); + +actor Actor<I, O> { + O(I) handler; + int(O) receiver; + int fd, process, pending, closed, dispatcher_index; + + // threads receive a private vm snapshot and an owned channel endpoint. + unchecked fn spawn(O(I).d callback) { + if (this.process || this.closed || !callback) return -1; + this.handler = callback; + worker = 1; + this.process = rt.syscall(51, fn() { + worker = 1; + while (1) { + I message; O result; + if (read_message(this.fd, &message, typeof(I)) < 0) break; + result = this.handler(message); + if (write_message(this.fd, &result, typeof(O)) < 0) break; + } + return 0; + } as word, &this.fd, 0); + if (this.process < 0) { worker = 0; return -1; } + worker = 0; + if (!dispatchers) dispatchers = rt.new(Dispatcher[?]); + this.dispatcher_index = len(dispatchers); + push(dispatchers, fn:word() { this.poll(); return 0; }); + return 0; + } + + // sends a snapshot; the worker executes it asynchronously on its own cpu. + unchecked fn send(I message) { + if (this.process <= 0 || this.closed) return -1; + if (write_message(this.fd, &message, typeof(I)) < 0) { this.close(); return -1; } + this.pending++; return 0; + } + + // registration does not wait; statement callbacks deliver ready replies. + unchecked fn recv(int(O).d callback) { + if (this.closed || !callback) return -1; + this.receiver = callback; this.poll(); return 0; + } + + unchecked fn poll() { + O result; + if (!this.receiver || this.closed || this.process <= 0) return 0; + int previous_busy = busy; busy = 1; + while (!this.closed && this.pending > 0 && rt.syscall(46, this.fd, 0, 0) > 0) { + if (read_message(this.fd, &result, typeof(O)) < 0) { busy = previous_busy; this.close(); return -1; } + this.pending--; this.receiver(result); + } + busy = previous_busy; return 0; + } + + // waits until every submitted message has reached the registered receiver. + unchecked fn await() { + if (!this.receiver && this.pending) return -1; + while (this.pending > 0 && !this.closed) { + if (rt.syscall(46, this.fd, -1, 0) < 0 || this.poll() < 0) return -1; + } + return 0; + } + + unchecked fn close() { + if (this.closed) return 0; + this.closed = 1; + if (this.process > 0 && dispatchers) dispatchers[this.dispatcher_index] = 0; + if (this.process > 0) rt.syscall(52, this.process, 1, 0); + this.handler = 0; this.receiver = 0; return 0; + } +} + +run.statement_hook(actor.dispatch); diff --git a/src/lib/icon.zc b/src/lib/icon.zc new file mode 100644 index 0000000..646a832 --- /dev/null +++ b/src/lib/icon.zc @@ -0,0 +1,623 @@ +namespace icon; +include rt, run; + +// structured runtime transformations of compiler token lists. +// token storage follows run.tokens: count, then kind, value and source line. +// edits create independent lists; publication recompiles a function only after +// delimiter validation. captures match complete balanced token ranges. + +int icon_error; + +int icon_eq(word* a, int ai, word* b, int bi, int n) { + int i = 0; + while (i < n) { + if (a[1 + (ai + i) * 3] != b[1 + (bi + i) * 3] || a[2 + (ai + i) * 3] != b[2 + (bi + i) * 3]) return 0; + i++; + } + return 1; +} +int icon_value(word* q, int i) { if (i < 0 || i >= q[0]) return 0; return q[2 + i * 3]; } +int icon_kind(word* q, int i) { if (i < 0 || i >= q[0]) return 0; return q[1 + i * 3]; } +int icon_is(word* q, int i, char* s) { + int kind = run.T_OP; if (s[0] >= 'a' && s[0] <= 'z') kind = run.T_ID; + return icon_kind(q, i) == kind && icon_value(q, i) == run.intern(s); +} +int icon_open(int v) { return v == run.intern("(") || v == run.intern("[") || v == run.intern("{"); } +int icon_close(int v) { return v == run.intern(")") || v == run.intern("]") || v == run.intern("}"); } +int icon_pair(int a, int b) { + return (a == run.intern("(") && b == run.intern(")")) || (a == run.intern("[") && b == run.intern("]")) || (a == run.intern("{") && b == run.intern("}")); +} +int icon_declaration(word* q, int start, int binding) { + int first = icon_value(q, start), i = start; + if (icon_kind(q, start) != run.T_ID || (first != run.intern("let") && first != run.intern("const") && !run.istypename(first))) return 0; + while (i < binding) { if (icon_is(q, i, "(") || icon_is(q, i, "=")) return 0; i++; } + return binding > start; +} +// locate a simple declaration at a statement boundary, including nested blocks. +// result records [type start, binding position, semicolon, statement start]. +int icon_locate_declaration(word* q, int id, word* result) { + int start = 0, i, depth, v, binding, comma, type_start; + while (start < q[0]) { + if (start && !icon_is(q, start - 1, ";") && !icon_is(q, start - 1, "{") && !icon_is(q, start - 1, "}")) { start++; continue; } + type_start = start; if (icon_is(q, type_start, "const")) type_start++; + if (icon_kind(q, type_start) != run.T_ID || (!icon_is(q, type_start, "let") && !run.istypename(icon_value(q, type_start)))) { start++; continue; } + i = type_start; depth = 0; binding = -1; comma = 0; + while (i < q[0]) { + v = icon_value(q, i); + if (!depth && v == id && icon_kind(q, i) == run.T_ID && binding < 0 && icon_declaration(q, type_start, i) && (icon_is(q, i + 1, "=") || icon_is(q, i + 1, ";") || icon_is(q, i + 1, ",") || icon_is(q, i + 1, "("))) binding = i; + if (icon_kind(q, i) == run.T_OP) { + if (icon_open(v)) depth++; + else if (icon_close(v)) { if (!depth) break; depth--; } + if (!depth && v == run.intern(",")) comma = 1; + if (!depth && v == run.intern(";")) { + if (binding >= 0) { + if (comma || icon_is(q, binding + 1, "(")) return 0; + result[0] = type_start; result[1] = binding; result[2] = i; result[3] = start; return 1; + } + break; + } + } + i++; + } + start++; + } + return 0; +} +int icon_balanced(word* q, int a, int b) { + word* stack = rt.new(b - a + 1); int n = 0, i = a, v, valid = 1; + while (i < b) { + v = icon_value(q, i); + if (icon_kind(q, i) == run.T_OP) { + if (icon_open(v)) { stack[n] = v; n++; } + else if (icon_close(v)) { if (!n || !icon_pair(stack[n - 1], v)) { valid = 0; break; } n--; } + } + i++; + } + if (n) valid = 0; + rt.free(stack); + return valid; +} +word* .u icon_slice(word* q, int a, int b) { + word* r = rt.new(1 + (b - a) * 3); int i = 0; r[0] = b - a; + while (i < (b - a) * 3) { r[1 + i] = q[1 + a * 3 + i]; i++; } + return r; +} +word* .u icon_splice(word* q, int a, int b, word* insert) { + int n = q[0] - (b - a) + insert[0], i = 0, j = 0; + word* r = rt.new(1 + n * 3); r[0] = n; + while (i < a * 3) { r[1 + j] = q[1 + i]; i++; j++; } + i = 0; while (i < insert[0] * 3) { r[1 + j] = insert[1 + i]; i++; j++; } + i = b * 3; while (i < q[0] * 3) { r[1 + j] = q[1 + i]; i++; j++; } + return r; +} +// capture classes use integer literals, identifiers, expressions, statements +// or blocks. a named capture records its exact token range for substitution. +int icon_class(int name) { + if (name == run.intern("int")) return 1; + if (name == run.intern("name")) return 2; + if (name == run.intern("expr")) return 3; + if (name == run.intern("stmt")) return 4; + if (name == run.intern("block")) return 5; + return 0; +} +int icon_pattern(word* q) { + int i = 0; + if (!q || q[0] <= 0 || !icon_balanced(q, 0, q[0])) return 0; + while (i < q[0]) { + if (icon_is(q, i, "$")) { + if (icon_kind(q, i + 1) != run.T_ID || !icon_class(icon_value(q, i + 1))) return 0; + i += 2; + if (icon_is(q, i, ":")) { if (icon_kind(q, i + 1) != run.T_ID || icon_class(icon_value(q, i + 1))) return 0; i += 2; } + } else i++; + } + return 1; +} +int icon_precedence(int name) { + if (name == run.intern("||")) return 1; + if (name == run.intern("&&")) return 2; + if (name == run.intern("|")) return 3; + if (name == run.intern("^")) return 4; + if (name == run.intern("&")) return 5; + if (name == run.intern("==") || name == run.intern("!=")) return 6; + if (name == run.intern("<") || name == run.intern("<=") || name == run.intern(">") || name == run.intern(">=")) return 7; + if (name == run.intern("<<") || name == run.intern(">>")) return 8; + if (name == run.intern("+") || name == run.intern("-")) return 9; + if (name == run.intern("*") || name == run.intern("/") || name == run.intern("%")) return 10; + return 0; +} +// recognize expression structure before matching a variable-length capture. +// this excludes statement keywords and incomplete operator sequences. +int icon_expression(word* q, int start, int end, int minimum) { + int i = start, v, kind, priority, next; + if (i >= end) return -1; + v = icon_value(q, i); kind = icon_kind(q, i); + if (kind == run.T_OP && (v == run.intern("!") || v == run.intern("~") || v == run.intern("+") || v == run.intern("-") || v == run.intern("*") || v == run.intern("&"))) { + i = icon_expression(q, i + 1, end, 11); if (i < 0) return -1; + } else if (icon_is(q, i, "(")) { + i = icon_expression(q, i + 1, end, 1); if (i < 0 || !icon_is(q, i, ")")) return -1; i++; + } else if (kind == run.T_NUM || kind == run.T_FLT || kind == run.T_STR || kind == run.T_BSTR || kind == run.T_ID) { + if (kind == run.T_ID && (v == run.intern("return") || v == run.intern("let") || v == run.intern("if") || v == run.intern("while") || v == run.intern("for") || v == run.intern("else") || v == run.intern("break") || v == run.intern("continue") || v == run.intern("do") || v == run.intern("switch") || v == run.intern("const"))) return -1; + i++; + } else return -1; + while (i < end) { + if (icon_is(q, i, "(") || icon_is(q, i, "[")) { + v = icon_value(q, i); i++; + if (v != run.intern("(") || !icon_is(q, i, ")")) { + while (1) { + i = icon_expression(q, i, end, 1); if (i < 0) return -1; + if (v == run.intern("(") && icon_is(q, i, ",")) { i++; continue; } break; + } + } + if (i >= end || icon_kind(q, i) != run.T_OP || !icon_pair(v, icon_value(q, i))) return -1; i++; continue; + } + if (icon_is(q, i, ".")) { if (i + 1 >= end || icon_kind(q, i + 1) != run.T_ID) return -1; i += 2; continue; } + if (icon_is(q, i, "++") || icon_is(q, i, "--")) { i++; continue; } + if (minimum == 1 && icon_is(q, i, "?")) { + i = icon_expression(q, i + 1, end, 1); if (i < 0 || !icon_is(q, i, ":")) return -1; + i = icon_expression(q, i + 1, end, 1); if (i < 0) return -1; continue; + } + priority = 0; if (icon_kind(q, i) == run.T_OP) priority = icon_precedence(icon_value(q, i)); if (!priority || priority < minimum) break; + next = icon_expression(q, i + 1, end, priority + 1); if (next < 0) return -1; i = next; + } + return i; +} +int icon_range(word* q, int a, int b, int kind) { + if (a < 0 || a >= b || b > q[0]) return 0; + if (kind == 1) return b == a + 1 && icon_kind(q, a) == run.T_NUM; + if (kind == 2) return b == a + 1 && icon_kind(q, a) == run.T_ID; + if (kind == 3) return icon_expression(q, a, b, 1) == b; + if (kind == 5) return icon_is(q, a, "{") && icon_mate(q, a) == b - 1; + if (kind == 4) return icon_statement_end(q, a) == b; + return icon_expression(q, a, b, 1) == b; +} +// recursively match a pattern with backtracking at balanced capture boundaries. +// captures contain count followed by [name, start, end, class] records. +int icon_match(word* q, int at, word* p, int pi, word* caps) { + int kind, name, next, end, old, i; + if (pi == p[0]) return at + 1; + if (at >= q[0]) return 0; + if (!icon_is(p, pi, "$")) { + if (!icon_eq(q, at, p, pi, 1)) return 0; + return icon_match(q, at + 1, p, pi + 1, caps); + } + if (pi + 1 >= p[0]) return 0; + name = icon_value(p, pi + 1); kind = icon_class(name); next = pi + 2; + if (!kind) return 0; + if (icon_is(p, next, ":")) { name = icon_value(p, next + 1); next += 2; if (!name) return 0; } + else name = 0; + old = caps[0]; end = at + 1; + if (kind == 4) end = icon_statement_end(q, at); + if (kind == 5) { if (!icon_is(q, at, "{")) return 0; end = icon_mate(q, at) + 1; } + if (end <= at) return 0; + while (end <= q[0]) { + if (icon_range(q, at, end, kind)) { + i = 0; + while (i < old) { + if (name && caps[1 + i * 4] == name) { + if (end - at != caps[3 + i * 4] - caps[2 + i * 4] || !icon_eq(q, at, q, caps[2 + i * 4], end - at)) break; + } + i++; + } + if (i == old) { + caps[0] = old + 1; caps[1 + old * 4] = name; caps[2 + old * 4] = at; caps[3 + old * 4] = end; caps[4 + old * 4] = kind; + i = icon_match(q, end, p, next, caps); + if (i) return i; + caps[0] = old; + } + } + if (kind != 3) break; + end++; + } + return 0; +} +int icon_capture(word* caps, int name, int ordinal) { + int c = 0, kind = icon_class(name), k = 0; + while (c < caps[0]) { + if (!kind) { if (caps[1 + c * 4] == name) return c + 1; } + else if (caps[4 + c * 4] == kind) { if (k == ordinal) return c + 1; k++; } + c++; + } + return 0; +} +word* .u icon_expand(word* q, word* replacement, word* caps) { + int n = 0, i = 0, j = 0, c, name, kind, k, seen[6], a, b; + k = 0; while (k < 6) { seen[k] = 0; k++; } + while (i < replacement[0]) { + if (icon_is(replacement, i, "$")) { + if (icon_kind(replacement, i + 1) != run.T_ID) { icon_error = 3; return 0; } + name = icon_value(replacement, i + 1); kind = icon_class(name); c = icon_capture(caps, name, seen[kind]); + if (!c) { icon_error = 3; return 0; } c--; + n += caps[3 + c * 4] - caps[2 + c * 4]; if (kind) seen[kind]++; i += 2; + } else { n++; i++; } + } + word* r = rt.new(1 + n * 3); i = 0; + k = 0; while (k < 6) { seen[k] = 0; k++; } + while (i < replacement[0]) { + if (icon_is(replacement, i, "$")) { + name = icon_value(replacement, i + 1); kind = icon_class(name); c = icon_capture(caps, name, seen[kind]) - 1; + if (kind) seen[kind]++; + a = caps[2 + c * 4] * 3; b = caps[3 + c * 4] * 3; + while (a < b) { r[1 + j] = q[1 + a]; a++; j++; } + i += 2; + } else { + k = 0; while (k < 3) { r[1 + j] = replacement[1 + i * 3 + k]; j++; k++; } i++; + } + } + r[0] = j / 3; + if (!icon_balanced(r, 0, r[0])) { rt.free(r); icon_error = 1; return 0; } + return r; +} + +// resumable frames retain their own token list and explicit binding maps. +// [tokens, position, state, result, error, locals, globals, blocks, steps]. + +// locate a binding in a frame map by its interned name. +int icon_binding(word map, int name) { + while (map) { if (map[0] == name) return map; map = map[2]; } + return 0; +} +int icon_read(word binding) { if (binding[3]) return *binding[3]; return binding[1]; } +int icon_store(word*.m frame, int column, int name, int value) { + word entry = icon_binding(frame[column], name); + if (!entry) { + word* node = rt.new(4); node[0] = name; node[1] = value; node[2] = frame[column]; node[3] = 0; frame[column] = node; return value; + } + entry[1] = value; if (entry[3]) *entry[3] = value; return value; +} +int icon_declare(word*.m frame, int name, int value) { + word* node = rt.new(4); node[0] = name; node[1] = value; node[2] = frame[5]; node[3] = 0; frame[5] = node; return value; +} +int icon_fail(word frame) { frame[2] = 2; frame[4] = 5; icon_error = 5; return 0; } +int icon_end(word* q, int start) { + int depth = 0, i = start, v; + while (i < q[0]) { + v = icon_value(q, i); + if (icon_kind(q, i) == run.T_OP) { + if (icon_open(v)) depth++; + else if (icon_close(v)) { if (!depth) return i; depth--; } + if (!depth && v == run.intern(";")) return i; + } + i++; + } + return i; +} +int icon_mate(word* q, int start) { + int depth = 1, i = start + 1, v; + while (i < q[0]) { + v = icon_value(q, i); + if (icon_kind(q, i) == run.T_OP) { + if (icon_open(v)) depth++; else if (icon_close(v)) depth--; + if (!depth) return i; + } + i++; + } + return -1; +} +// find one statement boundary; control-flow captures require braced bodies. +int icon_statement_end(word* q, int start) { + int close, end; + if (icon_is(q, start, "{")) { close = icon_mate(q, start); if (close < 0) return -1; return close + 1; } + if (icon_is(q, start, "if") || icon_is(q, start, "while")) { + if (!icon_is(q, start + 1, "(")) return -1; + close = icon_mate(q, start + 1); + if (close < 0 || !icon_is(q, close + 1, "{")) return -1; + end = icon_mate(q, close + 1); if (end < 0) return -1; end++; + if (icon_is(q, start, "if") && icon_is(q, end, "else")) { + if (!icon_is(q, end + 1, "{")) return -1; + close = icon_mate(q, end + 1); if (close < 0) return -1; return close + 1; + } + return end; + } + end = icon_end(q, start); + if (!icon_is(q, end, ";")) return -1; + return end + 1; +} +// construct a compiler return body in one allocation, retaining source lines. +word* .u icon_eval_tokens(word* q, int start, int end) { + int count = end - start; + word* expr = rt.new(7 + count * 3); expr[0] = count + 2; + expr[1] = run.T_ID; expr[2] = run.intern("return"); expr[3] = 1; + if (count) rt.copy_w(expr + 4, q + 1 + start * 3, count * 3); + expr[4 + count * 3] = run.T_OP; expr[5 + count * 3] = run.intern(";"); expr[6 + count * 3] = 1; + return expr; +} +// scalar frame substitution cannot preserve lvalue operations or implicit +// program-global reads. reject these before compiling or executing a range. +int icon_frame_expression(word frame, int start, int end) { + word* q = frame[0]; int i = start, s; word binding; + if (!icon_range(q, start, end, 3)) return 0; + while (i < end) { + if (icon_is(q, i, "++") || icon_is(q, i, "--")) return 0; + if (icon_kind(q, i) == run.T_ID && !icon_is(q, i - 1, ".")) { + binding = icon_binding(frame[5], icon_value(q, i)); + if (!binding) binding = icon_binding(frame[6], icon_value(q, i)); + if (!binding) { + s = run.lookups(icon_value(q, i)); + if (s < 0 || (run.skind[s] != run.K_FN && run.skind[s] != run.K_CONST)) return 0; + } + } + i++; + } + return 1; +} +int icon_frame_eval(word frame, int start, int end) { + word* expr = icon_eval_tokens(frame[0], start, end); + int i = 1; word binding; + while (i < expr[0] - 1) { + if (icon_kind(expr, i) == run.T_ID && !icon_is(expr, i - 1, ".")) { + binding = icon_binding(frame[5], icon_value(expr, i)); + if (!binding) binding = icon_binding(frame[6], icon_value(expr, i)); + if (binding) { expr[1 + i * 3] = run.T_NUM; expr[2 + i * 3] = icon_read(binding); } + } + i++; + } + int result = run.eval(expr); rt.free(expr); return result; +} +int icon_block(word*.m frame, int open, int resume) { + int close = icon_mate(frame[0], open); + if (close < 0) return icon_fail(frame); + word block = rt.new(4); block[0] = close; block[1] = resume; block[2] = frame[7]; block[3] = frame[5]; frame[7] = block; frame[1] = open + 1; return 1; +} + +struct icon { + // the last transformation status: 0 success, 1 invalid delimiters, + // 2 invalid range or declaration, 3 unresolved replacement capture, + // 4 unavailable function metadata, 5 unsupported stepping syntax, + // 6 rejected function publication. + static int error() { return icon_error; } + // check token delimiters without compiling or executing the list. + static int validate(word* q) { icon_error = 0; if (!q || q[0] < 0 || !icon_balanced(q, 0, q[0])) { icon_error = 1; return 0; } return 1; } + // return an independent token list with [start, end) replaced by insert. + static word* .u splice(word* q, int start, int end, word* insert) { + icon_error = 0; + if (!q || !insert || q[0] < 0 || insert[0] < 0 || start < 0 || end < start || end > q[0]) { icon_error = 2; return 0; } + word* r = icon_splice(q, start, end, insert); + if (!icon_balanced(r, 0, r[0])) { rt.free(r); icon_error = 1; return 0; } + return r; + } + // replace each nonoverlapping pattern match. inserted tokens are not + // searched again. the input and templates remain unchanged. + static word* .u rewrite(word* q, word* pattern, word* replacement) { + icon_error = 0; + if (!q || q[0] < 0 || !replacement || replacement[0] < 0 || !icon_pattern(pattern) || !icon_balanced(q, 0, q[0])) { icon_error = 1; return 0; } + word* result = icon_slice(q, 0, q[0]); word* caps = rt.new(1 + pattern[0] * 4); word* insert, next; + int at = 0, end; + while (at < result[0]) { + caps[0] = 0; end = icon_match(result, at, pattern, 0, caps); + if (!end) { at++; continue; } + insert = icon_expand(result, replacement, caps); + if (!insert) { rt.free(result); rt.free(caps); return 0; } + next = icon_splice(result, at, end - 1, insert); at += insert[0]; + rt.free(insert); rt.free(result); result = next; + } + rt.free(caps); return result; + } + // transform retained function tokens and publish the compiled replacement. + // references to the original entry continue to use the published version. + static int find_replace(word function, word* pattern, word* replacement) { + icon_error = 0; + if (!replacement || replacement[0] < 0 || !icon_pattern(pattern)) { icon_error = 1; return 0; } + word* q = run.function_tokens(function); + if (!q) { icon_error = 4; return 0; } + word* caps = rt.new(1 + pattern[0] * 4); int i = 0, end, count = 0; + while (i < q[0]) { caps[0] = 0; end = icon_match(q, i, pattern, 0, caps); if (end) { count++; i = end - 1; } else i++; } + rt.free(caps); + if (!count) { rt.free(q); return 0; } + word* changed = icon.rewrite(q, pattern, replacement); rt.free(q); + if (!changed) return 0; + int published = run.replace_function(function, changed); rt.free(changed); + if (!published) { icon_error = 6; return 0; } + return count; + } + // remove a complete declaration statement containing the requested name. + // declarations containing multiple bindings are rejected to preserve them. + static word* .u undeclare(word* q, char* name) { + icon_error = 0; + int declaration[4]; + if (!q || q[0] < 0 || !name || !icon_locate_declaration(q, run.intern(name), declaration)) { icon_error = 2; return 0; } + word* empty = rt.new(1); empty[0] = 0; + word* result = icon.splice(q, declaration[3], declaration[2] + 1, empty); rt.free(empty); return result; + } + // change the type of the first simple declaration of name. + static word* .u change_type(word* q, char* name, word* type) { + icon_error = 0; + int declaration[4]; + if (!q || q[0] < 0 || !name || !icon_locate_declaration(q, run.intern(name), declaration)) { icon_error = 2; return 0; } + return icon.splice(q, declaration[0], declaration[1], type); + } + // insert a scoped statement block at the given token boundary. + static word* .u insert_block(word* q, int at, word* body) { + icon_error = 0; + if (!q || !body || body[0] < 0 || at < 0 || at > q[0]) { icon_error = 2; return 0; } + word* block = rt.new(7 + body[0] * 3); int i = 0; block[0] = body[0] + 2; + block[1] = run.T_OP; block[2] = run.intern("{"); block[3] = 1; + while (i < body[0] * 3) { block[4 + i] = body[1 + i]; i++; } + block[4 + i] = run.T_OP; block[5 + i] = run.intern("}"); block[6 + i] = 1; + word* result = icon.splice(q, at, at, block); rt.free(block); return result; + } + // evaluate a selected expression using the compiler rather than a text + // evaluator. the range must contain one complete expression. + static int calculate(word* q, int start, int end) { + icon_error = 0; + if (!q || start < 0 || end > q[0] || !icon_range(q, start, end, 3)) { icon_error = 2; return 0; } + word* expr = icon_eval_tokens(q, start, end); + int value = run.eval(expr); rt.free(expr); return value; + } + // start a resumable evaluation with independent tokens and binding storage. + // stepping executes statements through the compiler; no native frame is + // suspended or inspected. scalar bindings are visible between statements. + static word* .u begin(word* q) { + if (!icon.validate(q)) { icon_error = 1; return 0; } + word* frame = rt.new(9); int i = 0; while (i < 9) { frame[i] = 0; i++; } frame[0] = icon_slice(q, 0, q[0]); return frame; + } + // create an explicit frame from a function's retained body. argument values + // are supplied through set_local before stepping starts. + static word* .u begin_function(int function) { + word* q = run.function_tokens(function); + if (!q) { icon_error = 4; return 0; } + word* frame = icon.begin(q); rt.free(q); return frame; + } + // set an isolated global binding, or update storage explicitly bound to it. + static int set_global(word frame, char* name, int value) { icon_error = 0; return icon_store(frame, 6, run.intern(name), value); } + // update the innermost local binding, creating a binding when absent. + static int set_local(word frame, char* name, int value) { icon_error = 0; return icon_store(frame, 5, run.intern(name), value); } + // bind one existing scalar global explicitly. reads observe its current + // value, and subsequent frame assignments update its program storage. + static int bind_global(word frame, char* name) { + int s = run.lookups(name); icon_error = 0; + if (s < 0 || run.skind[s] != run.K_GVAR) { icon_error = 2; return 0; } + word type = run.stype[s]; + if (type && type != run.tint && type != run.tword) { icon_error = 2; return 0; } + icon_store(frame, 6, run.intern(name), *run.sval[s]); + word binding = icon_binding(frame[6], run.intern(name)); binding[3] = run.sval[s]; return 1; + } + // read the innermost local binding; a missing binding sets status 2. + static int local(word frame, char* name) { icon_error = 0; word b = icon_binding(frame[5], run.intern(name)); if (!b) { icon_error = 2; return 0; } return icon_read(b); } + // read an isolated or explicitly connected global binding. + static int global(word frame, char* name) { icon_error = 0; word b = icon_binding(frame[6], run.intern(name)); if (!b) { icon_error = 2; return 0; } return icon_read(b); } + // frame state: 0 resumable, 1 complete, 2 unsupported statement. + static int state(word frame) { return frame[2]; } + // the returned value after completion; zero before a return is executed. + static int result(word frame) { return frame[3]; } + // token index of the next statement or control-flow decision. + static int position(word frame) { return frame[1]; } + // number of executed statements and control-flow decisions. + static int steps(word frame) { return frame[8]; } + // number of retained local binding records, including active shadowed records. + static int local_count(word frame) { word b = frame[5]; int n = 0; while (b) { n++; b = b[2]; } return n; } + // interned name of a local record; zero when index is outside the map. + static char* local_name(word frame, int index) { word b = frame[5]; while (b && index > 0) { index--; b = b[2]; } if (!b || index < 0) return 0; return b[0]; } + // execute one statement or control-flow decision. returns 1 after progress, + // 0 after completion or an unsupported statement. blocks, if and while + // require braces; declarations contain one scalar binding. + static int step(word frame) { + if (!frame || frame[2]) return 0; + icon_error = 0; + word* q = frame[0]; int at = frame[1], end, name, value, column = 5, v, close, open, alternate; + word block, binding; + while (frame[7] && at == frame[7][0]) { + block = frame[7]; + while (frame[5] != block[3]) { binding = frame[5]; frame[5] = binding[2]; rt.free(binding); } + at = block[1]; frame[7] = block[2]; rt.free(block); frame[1] = at; + } + if (at >= q[0]) { frame[2] = 1; return 0; } + frame[8]++; + if (icon_is(q, at, ";")) { frame[1] = at + 1; return 1; } + if (icon_is(q, at, "{")) { close = icon_mate(q, at); return icon_block(frame, at, close + 1); } + if (icon_is(q, at, "if") || icon_is(q, at, "while")) { + if (!icon_is(q, at + 1, "(")) return icon_fail(frame); + close = icon_mate(q, at + 1); open = close + 1; + if (close < 0 || !icon_is(q, open, "{")) return icon_fail(frame); + end = icon_mate(q, open); if (end < 0) return icon_fail(frame); + alternate = end + 1; + if (icon_is(q, at, "if") && icon_is(q, alternate, "else")) { + if (!icon_is(q, alternate + 1, "{")) return icon_fail(frame); + } + if (!icon_frame_expression(frame, at + 2, close)) return icon_fail(frame); + value = icon_frame_eval(frame, at + 2, close); + if (icon_is(q, at, "while")) { if (value) return icon_block(frame, open, at); frame[1] = end + 1; return 1; } + if (icon_is(q, alternate, "else")) { + close = icon_mate(q, alternate + 1); + if (value) return icon_block(frame, open, close + 1); + return icon_block(frame, alternate + 1, close + 1); + } + if (value) return icon_block(frame, open, end + 1); + frame[1] = end + 1; return 1; + } + end = icon_end(q, at); + if (end >= q[0] || !icon_is(q, end, ";")) return icon_fail(frame); + if (icon_is(q, at, "return")) { + frame[3] = 0; + if (end > at + 1) { if (!icon_frame_expression(frame, at + 1, end)) return icon_fail(frame); frame[3] = icon_frame_eval(frame, at + 1, end); } + frame[1] = end + 1; frame[2] = 1; return 1; + } + if (icon_is(q, at, "let") || icon_is(q, at, "int") || icon_is(q, at, "word")) { + if (icon_kind(q, at + 1) != run.T_ID) return icon_fail(frame); + name = icon_value(q, at + 1); value = 0; + if (end > at + 2) { if (!icon_is(q, at + 2, "=") || !icon_frame_expression(frame, at + 3, end)) return icon_fail(frame); value = icon_frame_eval(frame, at + 3, end); } + icon_declare(frame, name, value); frame[1] = end + 1; return 1; + } + name = icon_value(q, at); binding = icon_binding(frame[5], name); + if (!binding) { binding = icon_binding(frame[6], name); column = 6; } + if (binding && icon_kind(q, at) == run.T_ID) { + v = icon_value(q, at + 1); + if (end == at + 2 && (v == run.intern("++") || v == run.intern("--"))) { + value = icon_read(binding) + 1; if (v == run.intern("--")) value = icon_read(binding) - 1; + } else { + if (v != run.intern("=") && v != run.intern("+=") && v != run.intern("-=") && v != run.intern("*=") && v != run.intern("/=")) return icon_fail(frame); + if (!icon_frame_expression(frame, at + 2, end)) return icon_fail(frame); + value = icon_frame_eval(frame, at + 2, end); + if (v == run.intern("+=")) value = icon_read(binding) + value; + if (v == run.intern("-=")) value = icon_read(binding) - value; + if (v == run.intern("*=")) value = icon_read(binding) * value; + if (v == run.intern("/=")) value = icon_read(binding) / value; + } + icon_store(frame, column, name, value); frame[1] = end + 1; return 1; + } + return icon_fail(frame); + } + // execute at most budget statements. returning 0 leaves the frame resumable; + // callers can inspect bindings, edit them, then continue with another budget. + static int resume(word frame, int budget) { while (budget > 0 && !frame[2]) { icon.step(frame); budget--; } return frame[2]; } + // release a frame and all storage it owns. + static int close(.d frame) { + word b, next; int column = 5; + while (column <= 7) { b = frame[column]; while (b) { next = b[2]; rt.free(b); b = next; } column++; } + rt.free(frame[0]); rt.free(frame); return 0; + } +} + +// public entry points for the icon namespace. + +// status of the most recent transformation or binding operation; see docs/ICON.md. +int error() { return icon.icon.error(); } +// check delimiter structure only; does not compile or execute tokens. +int validate(word* q) { return icon.icon.validate(q); } +// return a new token list with [start, end) replaced; caller owns the result. +word* .u splice(word* q, int start, int end, word* insert) { return icon.icon.splice(q, start, end, insert); } +// return a new list with nonoverlapping matches replaced; inputs remain unchanged. +word* .u rewrite(word* q, word* pattern, word* replacement) { return icon.icon.rewrite(q, pattern, replacement); } +// publish a transformed function body; returns matches, or 0 on no match or failure. +int find_replace(word function, word* pattern, word* replacement) { return icon.icon.find_replace(function, pattern, replacement); } +// remove the first complete single-binding declaration named name; caller owns the result. +word* .u undeclare(word* q, char* name) { return icon.icon.undeclare(q, name); } +// replace the type prefix of the first simple declaration named name; caller owns the result. +word* .u change_type(word* q, char* name, word* type) { return icon.icon.change_type(q, name, type); } +// insert a scoped block containing body at token boundary at; caller owns the result. +word* .u insert_block(word* q, int at, word* body) { return icon.icon.insert_block(q, at, body); } +// compile and evaluate the expression in [start, end); expression calls retain their effects. +int calculate(word* q, int start, int end) { return icon.icon.calculate(q, start, end); } +// create a frame with copied tokens and isolated bindings; caller closes the frame. +word* .u begin(word* q) { return icon.icon.begin(q); } +// create a frame from retained function tokens; set arguments as locals before stepping. +word* .u begin_function(int function) { return icon.icon.begin_function(function); } +// set an isolated global binding, creating it when absent; returns the stored value. +int set_global(word frame, char* name, int value) { return icon.icon.set_global(frame, name, value); } +// set the innermost local binding, creating it when absent; returns the stored value. +int set_local(word frame, char* name, int value) { return icon.icon.set_local(frame, name, value); } +// connect an int or word program global to the frame; later frame writes update it. +int bind_global(word frame, char* name) { return icon.icon.bind_global(frame, name); } +// read a local binding; missing names return 0 and set error status 2. +int local(word frame, char* name) { return icon.icon.local(frame, name); } +// read a frame global binding; missing names return 0 and set error status 2. +int global(word frame, char* name) { return icon.icon.global(frame, name); } +// return frame state: 0 resumable, 1 complete, or 2 unsupported statement. +int state(word frame) { return icon.icon.state(frame); } +// return the value produced by return, or 0 before a return is executed. +int result(word frame) { return icon.icon.result(frame); } +// return the token index of the next statement or control-flow decision. +int position(word frame) { return icon.icon.position(frame); } +// return the number of statements and control-flow decisions executed. +int steps(word frame) { return icon.icon.steps(frame); } +// count retained local records, including shadowed records in active blocks. +int local_count(word frame) { return icon.icon.local_count(frame); } +// return the zero-based local record name, or 0 when index is out of range. +char* local_name(word frame, int index) { return icon.icon.local_name(frame, index); } +// execute scalar declarations and assignments, standalone ++/--, return, blocks, +// or braced if/else/while; direct program globals need bind_global first. +// unsupported syntax sets error status 5. +int step(word frame) { return icon.icon.step(frame); } +// execute at most budget steps and return the frame state; frame bindings are scalar int/word values. +int resume(word frame, int budget) { return icon.icon.resume(frame, budget); } +// release the frame and owned storage; consumes frame and returns 0. +int close(.d frame) { return icon.icon.close(d*frame); } diff --git a/src/lib/std.zc b/src/lib/std.zc index 375f403..f232422 100644 --- a/src/lib/std.zc +++ b/src/lib/std.zc @@ -1,35 +1,40 @@ +namespace std; +include rt, run; + // small helpers for strings, files, the clock and byte buffers. not part of the -// genome; include it with: include "src/lib/std.zc"; +// genome as declarations; its source is embedded. include it with: include std; // syscall numbers (SYS_OPEN and the rest) live in the runtime. -// a string here is a word string, one character per word and a 0 at the end, -// which is char*. the Bytes group takes packed byte strings (b"..."), whose -// type is a plain word. +// a character string has type char*, one character per word and a 0 at the end. +// the Bytes group takes packed byte strings (b"..."), whose +// type is bstr. // the helpers are grouped in structs, and each is a static function, so it is -// called as Group.name(args): Text.itoa(n, buf), Host.now(), Buf.get(b, 0). +// called as std.Group.name(args): std.Text.itoa(n, buf), std.Host.now(), +// std.Buf.get(b, 0). // the constructors arena(n) and bnew(n) and the argv helpers are plain // functions, because an owned result has to carry its .u tag. -// ---- the command line and the environment ---- +//: ---- the command line and the environment ---- + +//: argc and argv, envc and envp, as passed to main by c. a zc string is +//: one character per word, so an array of them is char*[?]. libinit() fills +//: these and the runtime calls it before main, if the program has one (an +//: image built by build_image, or a check-mode document, does not). -// argc and argv, envc and envp, the way c hands them to main. a zc string is -// one character per word, so an array of them is []char*. libinit() fills -// these and the runtime calls it before main, if the program has one (an -// image built by build_image, or a check-mode document, does not). int argc; -[]char* argv; +char*[?] argv; int envc; -[]char* envp; +char*[?] envp; // one entry of a vector syscall, as a fresh string, or 0 past the end. // op: the syscall that fetches an entry (SYS_ARG or SYS_ENV) // i: which entry // returns: the entry, owned by the caller; 0 when there is no entry i -unchecked char*.u argstr(int op, int i) { - int n = syscall(op, i, 0, 0); +char*.u argstr(int op, int i) { + int n = rt.syscall(op, i, 0, 0); char* s; if (n < 0) return 0; - s = new(n + 1); - syscall(op, i, s, n + 1); + s = rt.new(n + 1); + rt.syscall(op, i, s, n + 1); return s; } @@ -37,9 +42,9 @@ unchecked char*.u argstr(int op, int i) { // cntop: the syscall that counts the entries (SYS_ARGC or SYS_ENVC) // stop: the syscall that fetches one (SYS_ARG or SYS_ENV) // returns: a new array of the strings, owned by the caller -unchecked []char*.u argsvec(int cntop, int stop) { - int n = syscall(cntop, 0, 0, 0), i = 0; - []char* a = new([]char*, 0); +char*[?].u argsvec(int cntop, int stop) { + int n = rt.syscall(cntop, 0, 0, 0), i = 0; + char*[?] a = rt.new(char*[?], 0); while (i < n) { push(a, argstr(stop, i)); i++; } return a; } @@ -48,43 +53,44 @@ unchecked []char*.u argsvec(int cntop, int stop) { // it stays a plain function: the compiler looks it up by name. // returns: 0 int libinit() { - argv = argsvec(SYS_ARGC, SYS_ARG); - envp = argsvec(SYS_ENVC, SYS_ENV); + argv = argsvec(rt.SYS_ARGC, rt.SYS_ARG); + envp = argsvec(rt.SYS_ENVC, rt.SYS_ENV); argc = len(argv); envc = len(envp); return 0; } -// ---- capturing output ---- +//: ---- capturing output ---- // capture.start() redirects everything the program writes into a string and -// hands it back. writes go to the buffer instead of the terminal until end() +// returns it. writes go to the buffer instead of the terminal until end() // stops it, so the buffer is a string once end() has run: // let buf = capture.start(); // put_s("hello world!"); // nothing on the terminal -// buf.end(); +// capture.end(buf); // put_s(buf); // hello world // one capture at a time, and the buffer belongs to whoever holds it. + struct capture { - // starts a capture of the output. - // returns: the buffer, a word on purpose: the method end() is looked up on - // any receiver the compiler cannot type, and a typed one has none - static word start() { + // redirects program output into a collector-managed character buffer. + // returns the buffer; call end(buffer) before reading its terminator. + // returns: the buffer used for this capture + static char* start() { int cap = 256; - outmode = 2; outn = 0; outcap = cap; - outbuf = new(cap); - return outbuf; + rt.outmode = 2; rt.outn = 0; rt.outcap = cap; + rt.outbuf = rt.new(cap); + return rt.outbuf; } - - // stops the capture and terminates the buffer. - // returns: the string it collected (this is the buffer) - word end() { - outbuf[outn] = 0; - outmode = 0; outbuf = 0; outn = 0; outcap = 0; - return this; + // stops output capture, terminates the buffer, and returns the collected text. + // buffer: the buffer returned by start + // returns: the same buffer, now terminated + static char* end(char* buffer) { + rt.outbuf[rt.outn] = 0; + rt.outmode = 0; rt.outbuf = 0; rt.outn = 0; rt.outcap = 0; + return buffer; } } -// ---- word strings ---- +//: ---- character strings ---- struct Text { // the number written in decimal at the start of s. a leading '-' makes it @@ -106,7 +112,7 @@ struct Text { int b[24], i = 0, j = 0, neg = 0; if (!n) { dst[0] = '0'; dst[1] = 0; return 1; } if (n < 0) { neg = 1; n = 0 - n; } - if (n < 0) { copy_w(dst, "-9223372036854775808", 21); return 20; } + if (n < 0) { rt.copy_w(dst, "-9223372036854775808", 21); return 20; } while (n) { b[i] = '0' + n % 10; i++; n = n / 10; } if (neg) { dst[0] = '-'; j = 1; } while (i) { i--; dst[j] = b[i]; j++; } @@ -138,6 +144,19 @@ struct Text { return 1; } + // does s end with suffix? an empty suffix always matches. + // s: the string to test + // suffix: the ending to look for + // returns: 1 when it matches, 0 otherwise + static int ends(char* s, char* suffix) { + int n = 0, m = 0, i = 0; + while (s[n]) n++; + while (suffix[m]) m++; + if (m > n) return 0; + while (i < m) { if (s[n - m + i] != suffix[i]) return 0; i++; } + return 1; + } + // how many characters come before the 0. // s: the string // returns: the length, not counting the 0 @@ -227,23 +246,32 @@ struct Text { } } -// ---- numbers ---- +//: ---- numbers ---- + // plain integer helpers. none of them can fail: an out of range result wraps // the same way the arithmetic does. + struct Num { - // the absolute value of n. + // the absolute value of n, using wrapping word arithmetic. the minimum + // word remains negative because its positive value cannot fit in a word. + // n: the value + // returns: its absolute value, or the minimum word static int abs(int n) { if (n < 0) return 0 - n; return n; } // the smaller of a and b. + // a, b: the values to compare + // returns: the smaller value (a when they are equal) static int min(int a, int b) { if (a < b) return a; return b; } // the larger of a and b. + // a, b: the values to compare + // returns: the larger value (a when they are equal) static int max(int a, int b) { if (a > b) return a; return b; @@ -251,14 +279,17 @@ struct Num { // v, kept between lo and hi. // v: the value - // lo, hi: the bounds, lo first + // lo, hi: the bounds, lo first; lo must not exceed hi + // returns: v clamped to the bounds static int clamp(int v, int lo, int hi) { if (v < lo) return lo; if (v > hi) return hi; return v; } - // the greatest common divisor of two numbers, always 0 or more. + // the greatest common divisor of a and b, computed with word arithmetic. + // a, b: the values + // returns: their greatest common divisor static int gcd(int a, int b) { if (a < 0) a = 0 - a; if (b < 0) b = 0 - b; @@ -267,7 +298,10 @@ struct Num { return a; } - // b raised to the power e, for e of 0 or more. e below 0 gives 1. + // b raised to the power e. e below 0 gives 1; the result wraps as a word. + // b: the base + // e: the exponent + // returns: b to the power e, or 1 when e is negative static int pow(int b, int e) { int r = 1; while (e > 0) { r = r * b; e--; } @@ -275,6 +309,8 @@ struct Num { } // the whole square root of n, rounded down. n below 0 gives 0. + // n: the value + // returns: the greatest integer whose square is at most n, or 0 for n <= 0 static int isqrt(int n) { int lo = 0, hi = 3037000499, mid; if (n <= 0) return 0; @@ -285,7 +321,9 @@ struct Num { return lo; } - // -1, 0 or 1 by the sign of n. + // -1, 0 or 1 according to the sign of n. + // n: the value + // returns: -1 when n is negative, 0 when it is zero, and 1 when it is positive static int sign(int n) { if (n < 0) return 0 - 1; if (n > 0) return 1; @@ -293,9 +331,9 @@ struct Num { } } -// ---- the host ---- +//: ---- the host ---- -// the argument block for Host.raw: the number, then its six arguments. +//: the argument block for Host.raw: the number, then its six arguments. int rawblk[7]; struct Host { @@ -309,115 +347,160 @@ struct Host { // is wanted. // nr: the syscall number (x86-64 and arm64 numbers differ, so check the host) // a..f: the six arguments, unused ones 0 - // returns: the kernel's result, or -errno when the call fails + // returns: the kernel's result, -errno on failure, or -1 on unsupported hosts static int raw(int nr, int a, int b, int c, int d, int e, int f) { rawblk[0] = nr; rawblk[1] = a; rawblk[2] = b; rawblk[3] = c; rawblk[4] = d; rawblk[5] = e; rawblk[6] = f; - return syscall(SYS_RAW, rawblk, 0, 0); + return rt.syscall(rt.SYS_RAW, rawblk, 0, 0); } // the value of an environment variable. // name: the variable's name - // dst: where the value goes, a word string + // dst: where the value goes, a zero-terminated character string // n: how many words dst has // returns: the length of the value, -1 if the variable is not set - static int env(char* name, char* dst, int n) { return syscall(SYS_GETENV, name, dst, n); } + static int env(char* name, char* dst, int n) { return rt.syscall(rt.SYS_GETENV, name, dst, n); } // the clock. // returns: the time in seconds since 1970 - static int now() { return syscall(SYS_TIME, 0, 0, 0); } + static int now() { return rt.syscall(rt.SYS_TIME, 0, 0, 0); } // writes a string to a file, replacing what was there. // path: the file's name // s: the text to write // returns: how many bytes were written, -1 if the file could not be opened static int writefile(char* path, char* s) { - int fd = syscall(SYS_OPEN, path, 1, 0), n; + int fd = rt.syscall(rt.SYS_OPEN, path, 1, 0), n; if (fd < 0) return -1; - n = syscall(SYS_WRITE, fd, s, len_w(s)); - syscall(SYS_CLOSE, fd, 0, 0); + n = rt.syscall(rt.SYS_WRITE, fd, s, rt.len_w(s)); + rt.syscall(rt.SYS_CLOSE, fd, 0, 0); return n; } } -// ---- byte strings ---- -// the same helpers for packed byte strings. word strings above are unchanged. -// a byte string is a word whose first word is its length (see len_s). +//: ---- byte strings ---- + +// the same helpers for packed byte strings. character-string helpers above are unchanged. +// a packed byte string has type bstr; len_s reads its stored byte length. struct Bytes { - // like Text.atoi, for a byte string. + // reads a decimal number at the start of s; a leading '-' makes it + // negative, and the first non-digit ends the number. // s: the byte string - // returns: the number - static int atoi(word s) { return s_to_n(s); } + // returns: the number, or 0 when s starts with no digit + static int atoi(bstr s) { return rt.s_to_n(s); } // like Text.itoa, but the text is made fresh. // n: the number // returns: a new byte string - static word itoa(int n) { return n_to_s(n); } + static bstr itoa(int n) { return rt.n_to_s(n); } // like Text.starts, for byte strings. // s: the byte string to test // pfx: the beginning to look for // returns: 1 if s begins with pfx, 0 if not - static int starts(word s, word pfx) { + static int starts(bstr s, bstr pfx) { + int i = 0, n = rt.len_s(s), m = rt.len_s(pfx); + if (m > n) return 0; + while (i < m) { if (rt.at_s(s, i) != rt.at_s(pfx, i)) return 0; i++; } + return 1; + } + + // the number of bytes in a packed byte string. + // s: the byte string + // returns: its stored length + static int len(bstr s) { return rt.len_s(s); } + + // are two packed byte strings equal, byte for byte. + // a, b: the byte strings to compare + // returns: 1 if equal, 0 otherwise + static int eq(bstr a, bstr b) { int i = 0; - if (len_s(pfx) > len_s(s)) return 0; - while (i < len_s(pfx)) { if (at_s(s, i) != at_s(pfx, i)) return 0; i++; } + if (rt.len_s(a) != rt.len_s(b)) return 0; + while (i < rt.len_s(a)) { if (rt.at_s(a, i) != rt.at_s(b, i)) return 0; i++; } + return 1; + } + + // where pat first appears in s. + // s: the byte string to search + // pat: the byte string to find; an empty pat is found at 0 + // returns: its byte index, or -1 when absent + static int find(bstr s, bstr pat) { + int i = 0, j, n = rt.len_s(s), m = rt.len_s(pat); + if (!m) return 0; + while (i + m <= n) { + j = 0; + while (j < m && rt.at_s(s, i + j) == rt.at_s(pat, j)) j++; + if (j == m) return i; + i++; + } + return 0 - 1; + } + + // does s end with suffix? an empty suffix always matches. + // s: the byte string to test + // suffix: the ending to look for + // returns: 1 when it matches, 0 otherwise + static int ends(bstr s, bstr suffix) { + int n = rt.len_s(s), m = rt.len_s(suffix), i = 0; + if (m > n) return 0; + while (i < m) { if (rt.at_s(s, n - m + i) != rt.at_s(suffix, i)) return 0; i++; } return 1; } // like Host.env, for byte strings. // name: the variable's name, a byte string - // dst: where the value goes, a word buffer - // n: how many bytes dst can take + // dst: the packed byte string whose payload receives the value + // n: the maximum number of bytes to write // returns: the length of the value, -1 if the variable is not set - static int env(word name, word dst, int n) { return bgetenv(name, dst, n); } + static int env(bstr name, bstr dst, int n) { return rt.bgetenv(name, dst, n); } // like Host.writefile, for a byte string. // path: the file's name, a byte string // s: the bytes to write // returns: how many bytes were written, -1 if the file could not be opened - static int writefile(word path, word s) { - int fd = bopen(path, 1), n; + static int writefile(bstr path, bstr s) { + int fd = rt.bopen(path, 1), n; if (fd < 0) return -1; - n = bwrite(fd, s, len_s(s)); - syscall(SYS_CLOSE, fd, 0, 0); + n = rt.bwrite(fd, s, rt.len_s(s)); + rt.syscall(rt.SYS_CLOSE, fd, 0, 0); return n; } } -// ---- arenas ---- +//: ---- arenas ---- // a region that is freed all at once. -// n: its size in words +// n: its capacity in words; values below 1 allocate one word // returns: the arena, owned by the caller -int .u arena(int n) { return arena_new(n); } +int .u arena(int n) { return rt.arena_new(n); } struct Arena { - // takes n words from an arena. + // takes n zeroed words from an arena. // a: the arena // n: how many words - // returns: the address of the first, 0 if the arena is full - static int alloc(word a, int n) { return arena_alloc(a, n); } + // returns: the first word, or 0 when n words do not fit + static int alloc(word a, int n) { return rt.arena_alloc(a, n); } - // gives every block of an arena back at once. + // gives every block of an arena back at once. pointers returned by alloc + // before the reset are no longer valid. // a: the arena // returns: 0 - static int reset(word a) { return arena_reset(a); } + static int reset(word a) { return rt.arena_reset(a); } } -// ---- growable byte buffers ---- +//: ---- growable byte buffers ---- -// a byte buffer that knows its length and its capacity: two words, then the +// a byte buffer stores its length and capacity in two words, followed by the // bytes, packed. -// n: the capacity in bytes -// returns: the buffer, owned by the caller, empty +// n: the capacity in bytes; a negative value is treated as 0 +// returns: an empty buffer with that capacity, owned by the caller word .u bnew(int n) { int words; word p; if (n < 0) n = 0; words = (n + 7) >> 3; - p = new(2 + words); + p = rt.new(2 + words); p[0] = 0; p[1] = n; return u*p; @@ -438,9 +521,9 @@ struct Buf { // b: the buffer // i: the position // returns: the byte, 0 when i is outside the buffer - static int get(word b, int i) { if (i < 0 || i >= b[0]) return 0; return ld8(addr_b(b + 2) + i); } + static int get(word b, int i) { if (i < 0 || i >= b[0]) return 0; return rt.ld8(rt.addr_b(b + 2) + i); } - // sets one byte of a buffer. setting the byte just past the end makes the + // sets one byte of a buffer. setting the byte at the current length makes the // buffer one longer. // b: the buffer // i: the position, below the capacity @@ -448,8 +531,74 @@ struct Buf { // returns: the byte stored, 0 when i is outside the capacity static int set(word b, int i, int v) { if (i < 0 || i >= b[1]) return 0; - st8(addr_b(b + 2) + i, v & 255); + rt.st8(rt.addr_b(b + 2) + i, v & 255); if (i >= b[0]) b[0] = i + 1; return v & 255; } } + +//: array algorithms borrow their input and visit elements in index order. +//: map and filter return independent handles. reference elements are shared +//: with the collector, so freeing the input does not invalidate the result. + +// the first index equal to value, or -1 when no element matches. +int array_find<T>(fixed T[?].m source, T value) { + int length = len(source); + for (int i = 0; i < length; i++) if (source[i] == value) return i; + return -1; +} +// true when an element equals value. +int array_contains<T>(fixed T[?].m source, T value) { return array_find(source, value) >= 0; } +// the first index whose predicate is true, or -1 when none matches. +int array_find_if<T>(fixed T[?].m source, int(T).m predicate) { + int length = len(source); + for (int i = 0; i < length; i++) if (predicate(source[i])) return i; + return -1; +} +// true when any element satisfies predicate; false for an empty array. +int array_any<T>(fixed T[?].m source, int(T).m predicate) { return array_find_if(source, predicate) >= 0; } +// true when every element satisfies predicate, including an empty array. +int array_all<T>(fixed T[?].m source, int(T).m predicate) { + int length = len(source); + for (int i = 0; i < length; i++) if (!predicate(source[i])) return 0; + return 1; +} +// the number of elements satisfying predicate. +int array_count<T>(fixed T[?].m source, int(T).m predicate) { + int length = len(source); + int count = 0; + for (int i = 0; i < length; i++) if (predicate(source[i])) count++; + return count; +} +// apply transform once to each element and return the transformed array. +// the result element type follows the callback's return type. +U[?].u array_map<T,U>(fixed T[?].m source, U(T).m transform) { + int length = len(source); + U[?] result = rt.new(U[?]); + for (int i = 0; i < length; i++) push(result, run.share_value(transform(source[i]))); + return result; +} +// copy elements satisfying predicate into a new array, preserving order. +T[?].u array_filter<T>(fixed T[?].m source, int(T).m predicate) { + int length = len(source); + T[?] result = rt.new(T[?]); + for (int i = 0; i < length; i++) if (predicate(source[i])) push(result, run.share_value(source[i])); + return result; +} +// fold elements from left to right, starting with initial; an empty array +// returns initial without calling combine. +A array_reduce<T,A>(fixed T[?].m source, A initial, A(A,T).m combine) { + int length = len(source); + for (int i = 0; i < length; i++) initial = combine(initial, source[i]); + return initial; +} + +run.method("find", array_find); +run.method("contains", array_contains); +run.method("find_if", array_find_if); +run.method("any", array_any); +run.method("all", array_all); +run.method("count", array_count); +run.method("map", array_map); +run.method("filter", array_filter); +run.method("reduce", array_reduce); |
