john/cell
1
0
Fork 0
Code Issues 31 Pull Requests Actions Packages Projects Releases 2 Wiki Activity

respsect array and object length requests

Browse Source
This commit is contained in:
John Alanbrook
2026-02-14 15:42:19 -06:00
parent 356c51bde3
commit e75596ce30
18 changed files with 54250 additions and 62692 deletions
Download Patch File Download Diff File Expand all files Collapse all files

500
boot/bootstrap.cm.mcode
View File

File diff suppressed because it is too large Load Diff

1064
boot/engine.cm.mcode
View File

File diff suppressed because it is too large Load Diff

560
boot/fold.cm.mcode
View File

File diff suppressed because it is too large Load Diff

10533
boot/mcode.cm.mcode
View File

File diff suppressed because it is too large Load Diff

5934
boot/parse.cm.mcode
View File

File diff suppressed because it is too large Load Diff

293
boot/qbe.cm.mcode
View File

File diff suppressed because it is too large Load Diff

922
boot/qbe_emit.cm.mcode
View File

File diff suppressed because it is too large Load Diff

310
boot/seed_bootstrap.cm.mcode
View File

File diff suppressed because it is too large Load Diff

62568
boot/streamline.cm.mcode
View File

File diff suppressed because it is too large Load Diff

32883
boot/tokenize.cm.mcode
View File

File diff suppressed because it is too large Load Diff

790
boot/verify_ir.cm.mcode
View File

File diff suppressed because it is too large Load Diff

28
docs/spec/mcode.md
View File

@@ -13,6 +13,34 @@ Source → Tokenize → Parse → Fold → Mcode → Streamline → Machine
Mcode is produced by `mcode.cm`, optimized by `streamline.cm`, then either serialized to 32-bit bytecode for the Mach VM (`mach.c`), or lowered to QBE/LLVM IL for native compilation (`qbe_emit.cm`). See [Compilation Pipeline](pipeline.md) for the full overview.
## Module Structure
An `.mcode` file is a JSON object representing a compiled module:
| Field | Type | Description |
|-------|------|-------------|
| `name` | string | Module name (typically the source filename) |
| `filename` | string | Source filename |
| `data` | object | Constant pool — string and number literals used by instructions |
| `main` | function | The top-level function (module body) |
| `functions` | array | Nested function definitions (referenced by `function dest, id`) |
### Function Record
Each function (both `main` and entries in `functions`) has:
| Field | Type | Description |
|-------|------|-------------|
| `name` | string | Function name (`"<anonymous>"` for lambdas) |
| `filename` | string | Source filename |
| `nr_args` | integer | Number of parameters |
| `nr_slots` | integer | Total register slots needed (args + locals + temporaries) |
| `nr_close_slots` | integer | Number of closure slots captured from parent scope |
| `disruption_pc` | integer | Instruction index of the disruption handler (0 if none) |
| `instructions` | array | Instruction arrays and label strings |
Slot 0 is reserved. Slots 1 through `nr_args` hold parameters. Remaining slots up to `nr_slots - 1` are locals and temporaries.
## Instruction Format
Each instruction is a JSON array. The first element is the instruction name (string), followed by operands. The last two elements are line and column numbers for source mapping:

4
mcode.cm
View File

@@ -1930,7 +1930,7 @@ var mcode = function(ast) {
_i = _i + 1
}
dest = alloc_slot()
add_instr(["array", dest, 0])
add_instr(["array", dest, count])
_i = 0
while (_i < count) {
emit_2("push", dest, elem_slots[_i])
@@ -1943,7 +1943,7 @@ var mcode = function(ast) {
if (kind == "record") {
list = expr.list
dest = alloc_slot()
push(s_instructions, ["record", dest, 0])
push(s_instructions, ["record", dest, length(list)])
_i = 0
while (_i < length(list)) {
pair = list[_i]

17
source/mach.c
View File

@@ -1196,7 +1196,7 @@ JSValue JS_CallRegisterVM(JSContext *ctx, JSCodeRegister *code,
}
case MACH_NEWARRAY: {
JSValue arr = JS_NewArray(ctx);
JSValue arr = JS_NewArrayCap(ctx, b);
frame = (JSFrameRegister *)JS_VALUE_GET_PTR(frame_ref.val);
if (JS_IsException(arr)) { goto disrupt; }
frame->slots[a] = arr;
@@ -1550,7 +1550,7 @@ JSValue JS_CallRegisterVM(JSContext *ctx, JSCodeRegister *code,
/* New record */
case MACH_NEWRECORD: {
JSValue obj = JS_NewObject(ctx);
JSValue obj = b > 0 ? JS_NewObjectCap(ctx, b) : JS_NewObject(ctx);
frame = (JSFrameRegister *)JS_VALUE_GET_PTR(frame_ref.val);
if (JS_IsException(obj)) goto disrupt;
frame->slots[a] = obj;
@@ -2008,11 +2008,9 @@ static int mcode_reg_items(cJSON *it, cJSON **out) {
/* record: [1]=dest, [2]=0(const) — no line/col suffix */
if (!strcmp(op, "record")) { ADD(1); return c; }
/* array: [1]=dest, [2]=count(const), [3..]=elements (no line/col suffix) */
/* array: [1]=dest, [2]=count(const) — elements added via separate push instrs */
if (!strcmp(op, "array")) {
ADD(1);
int cnt = (int)cJSON_GetArrayItem(it, 2)->valuedouble;
for (int j = 0; j < cnt; j++) ADD(3 + j);
return c;
}
@@ -2475,15 +2473,10 @@ static MachCode *mcode_lower_func(cJSON *fobj, const char *filename) {
}
/* Array/Object creation */
else if (strcmp(op, "array") == 0) {
int dest = A1, count = A2;
EM(MACH_ABC(MACH_NEWARRAY, dest, 0, 0));
for (int j = 0; j < count; j++) {
int elem = ml_int(it, 3 + j);
EM(MACH_ABC(MACH_PUSH, dest, elem, 0));
}
EM(MACH_ABC(MACH_NEWARRAY, A1, A2, 0));
}
else if (strcmp(op, "record") == 0) {
EM(MACH_ABC(MACH_NEWRECORD, A1, 0, 0));
EM(MACH_ABC(MACH_NEWRECORD, A1, A2, 0));
}
/* Push/Pop */
else if (strcmp(op, "push") == 0) {

2
source/quickjs.h
View File

@@ -514,9 +514,11 @@ JSValue JS_NewObjectProtoClass (JSContext *ctx, JSValue proto, JSClassID class_i
JSValue JS_NewObjectClass (JSContext *ctx, int class_id);
JSValue JS_NewObjectProto (JSContext *ctx, JSValue proto);
JSValue JS_NewObject (JSContext *ctx);
JSValue JS_NewObjectCap (JSContext *ctx, uint32_t n);
JSValue JS_NewArray (JSContext *ctx);
JSValue JS_NewArrayLen (JSContext *ctx, uint32_t len);
JSValue JS_NewArrayCap (JSContext *ctx, uint32_t cap);
JSValue JS_NewArrayFrom (JSContext *ctx, int count, JSValue *values);
int JS_ArrayPush (JSContext *ctx, JSValue *arr_ptr, JSValue val);
JSValue JS_ArrayPop (JSContext *ctx, JSValue obj);

58
source/runtime.c
View File

@@ -2136,8 +2136,24 @@ static JSValue js_sub_string_val (JSContext *ctx, JSValue src, int start, int en
return js_new_string8_len (ctx, buf, len);
}
/* Heap string — fast path for short ASCII substrings (avoids heap alloc) */
JSText *p = JS_VALUE_GET_STRING (src);
if (len <= MIST_ASCII_MAX_LEN) {
char buf[MIST_ASCII_MAX_LEN];
int all_ascii = 1;
for (int i = 0; i < len; i++) {
uint32_t c = string_get (p, start + i);
if (c >= 0x80) { all_ascii = 0; break; }
buf[i] = (char)c;
}
if (all_ascii) {
JSValue imm = MIST_TryNewImmediateASCII (buf, len);
if (!JS_IsNull (imm)) return imm;
}
}
/* Heap string — delegate to existing js_sub_string */
return js_sub_string (ctx, JS_VALUE_GET_STRING (src), start, end);
return js_sub_string (ctx, p, start, end);
}
/* Allocate a new pretext (mutable JSText) with initial capacity */
@@ -2646,11 +2662,51 @@ JSValue JS_NewArrayLen (JSContext *ctx, uint32_t len) {
JSValue JS_NewArray (JSContext *ctx) { return JS_NewArrayLen (ctx, 0); }
/* Create array with pre-allocated capacity but len=0 (for push-fill patterns) */
JSValue JS_NewArrayCap (JSContext *ctx, uint32_t cap) {
if (cap == 0) cap = JS_ARRAY_INITIAL_SIZE;
size_t values_size = sizeof (JSValue) * cap;
size_t total_size = sizeof (JSArray) + values_size;
JSArray *arr = js_malloc (ctx, total_size);
if (!arr) return JS_EXCEPTION;
arr->mist_hdr = objhdr_make (cap, OBJ_ARRAY, false, false, false, false);
arr->len = 0;
for (uint32_t i = 0; i < cap; i++)
arr->values[i] = JS_NULL;
return JS_MKPTR (arr);
}
JSValue JS_NewObject (JSContext *ctx) {
/* inline JS_NewObjectClass(ctx, JS_CLASS_OBJECT); */
return JS_NewObjectProtoClass (ctx, ctx->class_proto[JS_CLASS_OBJECT], JS_CLASS_OBJECT);
}
/* Create object with pre-allocated hash table for n properties */
JSValue JS_NewObjectCap (JSContext *ctx, uint32_t n) {
/* slot 0 is reserved, so need n+1 slots minimum.
Hash table needs ~2x entries for good load factor.
mask must be power-of-2 minus 1. */
uint32_t need = (n + 1) * 2;
uint32_t mask = JS_RECORD_INITIAL_MASK;
while (mask + 1 < need) mask = (mask << 1) | 1;
JSGCRef proto_ref;
JS_PushGCRef (ctx, &proto_ref);
proto_ref.val = ctx->class_proto[JS_CLASS_OBJECT];
JSRecord *rec = js_new_record_class (ctx, mask, JS_CLASS_OBJECT);
JSValue proto_val = proto_ref.val;
JS_PopGCRef (ctx, &proto_ref);
if (!rec) return JS_EXCEPTION;
if (JS_IsRecord (proto_val))
rec->proto = proto_val;
return JS_MKPTR (rec);
}
/* Note: at least 'length' arguments will be readable in 'argv' */
static JSValue JS_NewCFunction3 (JSContext *ctx, JSCFunction *func, const char *name, int length, JSCFunctionEnum cproto, int magic) {

159
streamline.cm
View File

@@ -123,45 +123,45 @@ var streamline = function(ir, log) {
var op = instr[0]
var src_type = null
if (op == "access") {
slot_types[text(instr[1])] = access_value_type(instr[2])
slot_types[instr[1]] = access_value_type(instr[2])
} else if (op == "int") {
slot_types[text(instr[1])] = T_INT
slot_types[instr[1]] = T_INT
} else if (op == "true" || op == "false") {
slot_types[text(instr[1])] = T_BOOL
slot_types[instr[1]] = T_BOOL
} else if (op == "null") {
slot_types[text(instr[1])] = T_NULL
slot_types[instr[1]] = T_NULL
} else if (op == "move") {
src_type = slot_types[text(instr[2])]
slot_types[text(instr[1])] = src_type != null ? src_type : T_UNKNOWN
src_type = slot_types[instr[2]]
slot_types[instr[1]] = src_type != null ? src_type : T_UNKNOWN
} else if (op == "concat") {
slot_types[text(instr[1])] = T_TEXT
slot_types[instr[1]] = T_TEXT
} else if (bool_result_ops[op] == true) {
slot_types[text(instr[1])] = T_BOOL
slot_types[instr[1]] = T_BOOL
} else if (op == "load_field" || op == "load_index" || op == "load_dynamic") {
slot_types[text(instr[1])] = T_UNKNOWN
slot_types[instr[1]] = T_UNKNOWN
} else if (op == "invoke" || op == "tail_invoke") {
slot_types[text(instr[2])] = T_UNKNOWN
slot_types[instr[2]] = T_UNKNOWN
} else if (op == "pop" || op == "get") {
slot_types[text(instr[1])] = T_UNKNOWN
slot_types[instr[1]] = T_UNKNOWN
} else if (op == "array") {
slot_types[text(instr[1])] = T_ARRAY
slot_types[instr[1]] = T_ARRAY
} else if (op == "record") {
slot_types[text(instr[1])] = T_RECORD
slot_types[instr[1]] = T_RECORD
} else if (op == "function") {
slot_types[text(instr[1])] = T_FUNCTION
slot_types[instr[1]] = T_FUNCTION
} else if (op == "length") {
slot_types[text(instr[1])] = T_INT
slot_types[instr[1]] = T_INT
} else if (op == "negate" || numeric_ops[op] == true) {
slot_types[text(instr[1])] = T_UNKNOWN
slot_types[instr[1]] = T_UNKNOWN
} else if (op == "bitnot" || op == "bitand" || op == "bitor" ||
op == "bitxor" || op == "shl" || op == "shr" || op == "ushr") {
slot_types[text(instr[1])] = T_INT
slot_types[instr[1]] = T_INT
}
return null
}
var slot_is = function(slot_types, slot, typ) {
var known = slot_types[text(slot)]
var known = slot_types[slot]
if (known == null) {
return false
}
@@ -175,24 +175,22 @@ var streamline = function(ir, log) {
}
var merge_backward = function(backward_types, slot, typ) {
var sk = null
var existing = null
if (!is_number(slot)) {
return null
}
sk = text(slot)
existing = backward_types[sk]
existing = backward_types[slot]
if (existing == null) {
backward_types[sk] = typ
backward_types[slot] = typ
} else if (existing != typ && existing != T_UNKNOWN) {
if ((existing == T_INT || existing == T_FLOAT) && typ == T_NUM) {
// Keep more specific
} else if (existing == T_NUM && (typ == T_INT || typ == T_FLOAT)) {
backward_types[sk] = typ
backward_types[slot] = typ
} else if ((existing == T_INT && typ == T_FLOAT) || (existing == T_FLOAT && typ == T_INT)) {
backward_types[sk] = T_NUM
backward_types[slot] = T_NUM
} else {
backward_types[sk] = T_UNKNOWN
backward_types[slot] = T_UNKNOWN
}
}
return null
@@ -201,8 +199,8 @@ var streamline = function(ir, log) {
var seed_params = function(slot_types, param_types, nr_args) {
var j = 1
while (j <= nr_args) {
if (param_types[text(j)] != null) {
slot_types[text(j)] = param_types[text(j)]
if (param_types[j] != null) {
slot_types[j] = param_types[j]
}
j = j + 1
}
@@ -210,10 +208,11 @@ var streamline = function(ir, log) {
}
var seed_writes = function(slot_types, write_types) {
var keys = array(write_types)
var k = 0
while (k < length(keys)) {
slot_types[keys[k]] = write_types[keys[k]]
while (k < length(write_types)) {
if (write_types[k] != null) {
slot_types[k] = write_types[k]
}
k = k + 1
}
return null
@@ -236,11 +235,11 @@ var streamline = function(ir, log) {
var bt = null
if (instructions == null || nr_args == 0) {
return {}
return array(func.nr_slots)
}
num_instr = length(instructions)
backward_types = {}
backward_types = array(func.nr_slots)
i = 0
while (i < num_instr) {
instr = instructions[i]
@@ -296,12 +295,12 @@ var streamline = function(ir, log) {
i = i + 1
}
param_types = {}
param_types = array(func.nr_slots)
j = 1
while (j <= nr_args) {
bt = backward_types[text(j)]
bt = backward_types[j]
if (bt != null && bt != T_UNKNOWN) {
param_types[text(j)] = bt
param_types[j] = bt
}
j = j + 1
}
@@ -319,22 +318,19 @@ var streamline = function(ir, log) {
var nr_args = func.nr_args != null ? func.nr_args : 0
var num_instr = 0
var write_types = null
var result = null
var keys = null
var i = 0
var k = 0
var instr = null
var op = null
var slot = 0
var typ = null
var wt = null
if (instructions == null) {
return {}
return array(func.nr_slots)
}
num_instr = length(instructions)
write_types = {}
write_types = array(func.nr_slots)
i = 0
while (i < num_instr) {
instr = instructions[i]
@@ -410,17 +406,14 @@ var streamline = function(ir, log) {
}
// Filter to only slots with known (non-unknown) types
result = {}
keys = array(write_types)
k = 0
while (k < length(keys)) {
wt = write_types[keys[k]]
if (wt != null && wt != T_UNKNOWN) {
result[keys[k]] = wt
while (k < length(write_types)) {
if (write_types[k] == T_UNKNOWN) {
write_types[k] = null
}
k = k + 1
}
return result
return write_types
}
// =========================================================
@@ -462,14 +455,14 @@ var streamline = function(ir, log) {
num_instr = length(instructions)
j = 1
while (j <= nr_args) {
if (param_types[text(j)] != null) {
if (param_types[j] != null) {
has_params = true
}
j = j + 1
}
has_writes = length(array(write_types)) > 0
has_writes = some(write_types, function(x) { return x != null })
slot_types = {}
slot_types = array(func.nr_slots)
if (has_params) {
seed_params(slot_types, param_types, nr_args)
}
@@ -482,7 +475,7 @@ var streamline = function(ir, log) {
instr = instructions[i]
if (is_text(instr)) {
slot_types = {}
slot_types = array(func.nr_slots)
if (has_params) {
seed_params(slot_types, param_types, nr_args)
}
@@ -525,14 +518,14 @@ var streamline = function(ir, log) {
at: i,
before: [instr, next],
after: [instructions[i], instructions[i + 1]],
why: {slot: src, known_type: slot_types[text(src)], checked_type: checked_type}
why: {slot: src, known_type: slot_types[src], checked_type: checked_type}
}
}
slot_types[text(dest)] = T_BOOL
slot_types[dest] = T_BOOL
i = i + 2
continue
}
src_known = slot_types[text(src)]
src_known = slot_types[src]
if (src_known != null && src_known != T_UNKNOWN && src_known != checked_type) {
if (checked_type == T_NUM && (src_known == T_INT || src_known == T_FLOAT)) {
nc = nc + 1
@@ -550,7 +543,7 @@ var streamline = function(ir, log) {
why: {slot: src, known_type: src_known, checked_type: checked_type}
}
}
slot_types[text(dest)] = T_BOOL
slot_types[dest] = T_BOOL
i = i + 2
continue
}
@@ -569,12 +562,12 @@ var streamline = function(ir, log) {
why: {slot: src, known_type: src_known, checked_type: checked_type}
}
}
slot_types[text(dest)] = T_UNKNOWN
slot_types[dest] = T_UNKNOWN
i = i + 2
continue
}
slot_types[text(dest)] = T_BOOL
slot_types[text(src)] = checked_type
slot_types[dest] = T_BOOL
slot_types[src] = checked_type
i = i + 2
continue
}
@@ -594,14 +587,14 @@ var streamline = function(ir, log) {
at: i,
before: [instr, next],
after: [instructions[i], instructions[i + 1]],
why: {slot: src, known_type: slot_types[text(src)], checked_type: checked_type}
why: {slot: src, known_type: slot_types[src], checked_type: checked_type}
}
}
slot_types[text(dest)] = T_BOOL
slot_types[dest] = T_BOOL
i = i + 2
continue
}
src_known = slot_types[text(src)]
src_known = slot_types[src]
if (src_known != null && src_known != T_UNKNOWN && src_known != checked_type) {
if (checked_type == T_NUM && (src_known == T_INT || src_known == T_FLOAT)) {
nc = nc + 1
@@ -619,7 +612,7 @@ var streamline = function(ir, log) {
why: {slot: src, known_type: src_known, checked_type: checked_type}
}
}
slot_types[text(dest)] = T_BOOL
slot_types[dest] = T_BOOL
i = i + 2
continue
}
@@ -638,17 +631,17 @@ var streamline = function(ir, log) {
why: {slot: src, known_type: src_known, checked_type: checked_type}
}
}
slot_types[text(dest)] = T_BOOL
slot_types[dest] = T_BOOL
i = i + 2
continue
}
slot_types[text(dest)] = T_BOOL
slot_types[dest] = T_BOOL
i = i + 2
continue
}
}
slot_types[text(dest)] = T_BOOL
slot_types[dest] = T_BOOL
i = i + 1
continue
}
@@ -664,7 +657,7 @@ var streamline = function(ir, log) {
pass: "eliminate_type_checks",
rule: "dynamic_to_field",
at: i, before: old_op, after: instr[0],
why: {slot: instr[3], known_type: slot_types[text(instr[3])]}
why: {slot: instr[3], known_type: slot_types[instr[3]]}
}
}
} else if (slot_is(slot_types, instr[3], T_INT)) {
@@ -675,11 +668,11 @@ var streamline = function(ir, log) {
pass: "eliminate_type_checks",
rule: "dynamic_to_index",
at: i, before: old_op, after: instr[0],
why: {slot: instr[3], known_type: slot_types[text(instr[3])]}
why: {slot: instr[3], known_type: slot_types[instr[3]]}
}
}
}
slot_types[text(instr[1])] = T_UNKNOWN
slot_types[instr[1]] = T_UNKNOWN
i = i + 1
continue
}
@@ -693,7 +686,7 @@ var streamline = function(ir, log) {
pass: "eliminate_type_checks",
rule: "dynamic_to_field",
at: i, before: old_op, after: instr[0],
why: {slot: instr[3], known_type: slot_types[text(instr[3])]}
why: {slot: instr[3], known_type: slot_types[instr[3]]}
}
}
} else if (slot_is(slot_types, instr[3], T_INT)) {
@@ -704,7 +697,7 @@ var streamline = function(ir, log) {
pass: "eliminate_type_checks",
rule: "dynamic_to_index",
at: i, before: old_op, after: instr[0],
why: {slot: instr[3], known_type: slot_types[text(instr[3])]}
why: {slot: instr[3], known_type: slot_types[instr[3]]}
}
}
}
@@ -745,14 +738,14 @@ var streamline = function(ir, log) {
}
num_instr = length(instructions)
slot_values = {}
slot_values = array(func.nr_slots)
i = 0
while (i < num_instr) {
instr = instructions[i]
if (is_text(instr)) {
slot_values = {}
slot_values = array(func.nr_slots)
i = i + 1
continue
}
@@ -766,19 +759,19 @@ var streamline = function(ir, log) {
// Track known constant values
if (op == "int") {
slot_values[text(instr[1])] = instr[2]
slot_values[instr[1]] = instr[2]
} else if (op == "access" && is_number(instr[2])) {
slot_values[text(instr[1])] = instr[2]
slot_values[instr[1]] = instr[2]
} else if (op == "true") {
slot_values[text(instr[1])] = true
slot_values[instr[1]] = true
} else if (op == "false") {
slot_values[text(instr[1])] = false
slot_values[instr[1]] = false
} else if (op == "move") {
sv = slot_values[text(instr[2])]
sv = slot_values[instr[2]]
if (sv != null) {
slot_values[text(instr[1])] = sv
slot_values[instr[1]] = sv
} else {
slot_values[text(instr[1])] = null
slot_values[instr[1]] = null
}
}
@@ -797,7 +790,7 @@ var streamline = function(ir, log) {
why: {op: op, slot: instr[2]}
}
}
slot_values[text(instr[1])] = true
slot_values[instr[1]] = true
i = i + 1
continue
}
@@ -814,7 +807,7 @@ var streamline = function(ir, log) {
why: {op: op, slot: instr[2]}
}
}
slot_values[text(instr[1])] = false
slot_values[instr[1]] = false
i = i + 1
continue
}
@@ -822,7 +815,7 @@ var streamline = function(ir, log) {
// Clear value tracking for dest-producing ops (not reads-only)
if (op == "invoke" || op == "tail_invoke") {
slot_values[text(instr[2])] = null
slot_values[instr[2]] = null
} else if (op != "int" && op != "access" && op != "true" &&
op != "false" && op != "move" && op != "null" &&
op != "jump" && op != "jump_true" && op != "jump_false" &&
@@ -830,7 +823,7 @@ var streamline = function(ir, log) {
op != "store_field" && op != "store_index" &&
op != "store_dynamic" && op != "push" && op != "setarg") {
if (is_number(instr[1])) {
slot_values[text(instr[1])] = null
slot_values[instr[1]] = null
}
}

317
tokenize.cm
View File

@@ -1,72 +1,11 @@
var tokenize = function(src, filename) {
var len = length(src)
var cp = array(array(src), codepoint)
var pos = 0
var row = 0
var col = 0
var tokens = []
// Codepoint constants
def CP_LF = 10
def CP_CR = 13
def CP_TAB = 9
def CP_SPACE = 32
def CP_BANG = 33
def CP_DQUOTE = 34
def CP_HASH = 35
def CP_DOLLAR = 36
def CP_PERCENT = 37
def CP_AMP = 38
def CP_SQUOTE = 39
def CP_LPAREN = 40
def CP_RPAREN = 41
def CP_STAR = 42
def CP_PLUS = 43
def CP_COMMA = 44
def CP_MINUS = 45
def CP_DOT = 46
def CP_SLASH = 47
def CP_0 = 48
def CP_1 = 49
def CP_7 = 55
def CP_9 = 57
def CP_COLON = 58
def CP_SEMI = 59
def CP_LT = 60
def CP_EQ = 61
def CP_GT = 62
def CP_QMARK = 63
def CP_AT = 64
def CP_A = 65
def CP_B = 66
def CP_E = 69
def CP_F = 70
def CP_O = 79
def CP_X = 88
def CP_Z = 90
def CP_LBRACKET = 91
def CP_BSLASH = 92
def CP_RBRACKET = 93
def CP_CARET = 94
def CP_UNDERSCORE = 95
def CP_BACKTICK = 96
def CP_a = 97
def CP_b = 98
def CP_e = 101
def CP_f = 102
def CP_n = 110
def CP_o = 111
def CP_r = 114
def CP_t = 116
def CP_u = 117
def CP_x = 120
def CP_z = 122
def CP_LBRACE = 123
def CP_PIPE = 124
def CP_RBRACE = 125
def CP_TILDE = 126
// Keywords lookup
var keywords = {
if: "if", in: "in", do: "do", go: "go",
@@ -79,20 +18,20 @@ var tokenize = function(src, filename) {
}
var pk = function() {
if (pos >= len) return -1
return cp[pos]
if (pos >= len) return null
return src[pos]
}
var pk_at = function(n) {
var idx = pos + n
if (idx >= len) return -1
return cp[idx]
if (idx >= len) return null
return src[idx]
}
var adv = function() {
var c = cp[pos]
var c = src[pos]
pos = pos + 1
if (c == CP_LF) {
if (c == "\n") {
row = row + 1
col = 0
} else {
@@ -102,17 +41,17 @@ var tokenize = function(src, filename) {
}
var is_digit = function(c) {
return c >= CP_0 && c <= CP_9
return c >= "0" && c <= "9"
}
var is_hex = function(c) {
return (c >= CP_0 && c <= CP_9) || (c >= CP_a && c <= CP_f) || (c >= CP_A && c <= CP_F)
return (c >= "0" && c <= "9") || (c >= "a" && c <= "f") || (c >= "A" && c <= "F")
}
var hex_val = function(c) {
if (c >= CP_0 && c <= CP_9) return c - CP_0
if (c >= CP_a && c <= CP_f) return c - CP_a + 10
if (c >= CP_A && c <= CP_F) return c - CP_A + 10
if (c >= "0" && c <= "9") return codepoint(c) - codepoint("0")
if (c >= "a" && c <= "f") return codepoint(c) - codepoint("a") + 10
if (c >= "A" && c <= "F") return codepoint(c) - codepoint("A") + 10
return 0
}
@@ -127,7 +66,7 @@ var tokenize = function(src, filename) {
}
var is_alpha = function(c) {
return (c >= CP_a && c <= CP_z) || (c >= CP_A && c <= CP_Z)
return (c >= "a" && c <= "z") || (c >= "A" && c <= "Z")
}
var is_alnum = function(c) {
@@ -135,41 +74,41 @@ var tokenize = function(src, filename) {
}
var is_ident_start = function(c) {
return is_alpha(c) || c == CP_UNDERSCORE || c == CP_DOLLAR
return is_alpha(c) || c == "_" || c == "$"
}
var is_ident_char = function(c) {
return is_alnum(c) || c == CP_UNDERSCORE || c == CP_DOLLAR || c == CP_QMARK || c == CP_BANG
return is_alnum(c) || c == "_" || c == "$" || c == "?" || c == "!"
}
var substr = function(start, end) {
return text(src, start, end)
}
var read_string = function(quote_cp) {
var read_string = function(quote) {
var start = pos
var start_row = row
var start_col = col
var parts = []
var run_start = 0
var esc = 0
var esc = null
adv() // skip opening quote
run_start = pos
while (pos < len && pk() != quote_cp) {
if (pk() == CP_BSLASH) {
while (pos < len && pk() != quote) {
if (pk() == "\\") {
if (pos > run_start) push(parts, text(src, run_start, pos))
adv()
esc = adv()
if (esc == CP_n) { push(parts, "\n") }
else if (esc == CP_t) { push(parts, "\t") }
else if (esc == CP_r) { push(parts, "\r") }
else if (esc == CP_BSLASH) { push(parts, "\\") }
else if (esc == CP_SQUOTE) { push(parts, "'") }
else if (esc == CP_DQUOTE) { push(parts, "\"") }
else if (esc == CP_0) { push(parts, character(0)) }
else if (esc == CP_BACKTICK) { push(parts, "`") }
else if (esc == CP_u) { push(parts, read_unicode_escape()) }
else { push(parts, character(esc)) }
if (esc == "n") { push(parts, "\n") }
else if (esc == "t") { push(parts, "\t") }
else if (esc == "r") { push(parts, "\r") }
else if (esc == "\\") { push(parts, "\\") }
else if (esc == "'") { push(parts, "'") }
else if (esc == "\"") { push(parts, "\"") }
else if (esc == "0") { push(parts, character(0)) }
else if (esc == "`") { push(parts, "`") }
else if (esc == "u") { push(parts, read_unicode_escape()) }
else { push(parts, esc) }
run_start = pos
} else {
adv()
@@ -192,33 +131,33 @@ var tokenize = function(src, filename) {
var parts = []
var run_start = 0
var depth = 0
var tc = 0
var q = 0
var tc = null
var q = null
var interp_start = 0
adv() // skip opening backtick
run_start = pos
while (pos < len && pk() != CP_BACKTICK) {
if (pk() == CP_BSLASH && pos + 1 < len) {
while (pos < len && pk() != "`") {
if (pk() == "\\" && pos + 1 < len) {
if (pos > run_start) push(parts, text(src, run_start, pos))
push(parts, text(src, pos, pos + 2))
adv(); adv()
run_start = pos
} else if (pk() == CP_DOLLAR && pos + 1 < len && pk_at(1) == CP_LBRACE) {
} else if (pk() == "$" && pos + 1 < len && pk_at(1) == "{") {
if (pos > run_start) push(parts, text(src, run_start, pos))
interp_start = pos
adv(); adv() // $ {
depth = 1
while (pos < len && depth > 0) {
tc = pk()
if (tc == CP_LBRACE) { depth = depth + 1; adv() }
else if (tc == CP_RBRACE) {
if (tc == "{") { depth = depth + 1; adv() }
else if (tc == "}") {
depth = depth - 1
adv()
}
else if (tc == CP_SQUOTE || tc == CP_DQUOTE || tc == CP_BACKTICK) {
else if (tc == "'" || tc == "\"" || tc == "`") {
q = adv()
while (pos < len && pk() != q) {
if (pk() == CP_BSLASH && pos + 1 < len) adv()
if (pk() == "\\" && pos + 1 < len) adv()
adv()
}
if (pos < len) adv()
@@ -245,24 +184,24 @@ var tokenize = function(src, filename) {
var start_row = row
var start_col = col
var raw = ""
if (pk() == CP_0 && (pk_at(1) == CP_x || pk_at(1) == CP_X)) {
if (pk() == "0" && (pk_at(1) == "x" || pk_at(1) == "X")) {
adv(); adv()
while (pos < len && (is_hex(pk()) || pk() == CP_UNDERSCORE)) adv()
} else if (pk() == CP_0 && (pk_at(1) == CP_b || pk_at(1) == CP_B)) {
while (pos < len && (is_hex(pk()) || pk() == "_")) adv()
} else if (pk() == "0" && (pk_at(1) == "b" || pk_at(1) == "B")) {
adv(); adv()
while (pos < len && (pk() == CP_0 || pk() == CP_1 || pk() == CP_UNDERSCORE)) adv()
} else if (pk() == CP_0 && (pk_at(1) == CP_o || pk_at(1) == CP_O)) {
while (pos < len && (pk() == "0" || pk() == "1" || pk() == "_")) adv()
} else if (pk() == "0" && (pk_at(1) == "o" || pk_at(1) == "O")) {
adv(); adv()
while (pos < len && pk() >= CP_0 && pk() <= CP_7) adv()
while (pos < len && pk() >= "0" && pk() <= "7") adv()
} else {
while (pos < len && (is_digit(pk()) || pk() == CP_UNDERSCORE)) adv()
if (pos < len && pk() == CP_DOT) {
while (pos < len && (is_digit(pk()) || pk() == "_")) adv()
if (pos < len && pk() == ".") {
adv()
while (pos < len && (is_digit(pk()) || pk() == CP_UNDERSCORE)) adv()
while (pos < len && (is_digit(pk()) || pk() == "_")) adv()
}
if (pos < len && (pk() == CP_e || pk() == CP_E)) {
if (pos < len && (pk() == "e" || pk() == "E")) {
adv()
if (pos < len && (pk() == CP_PLUS || pk() == CP_MINUS)) adv()
if (pos < len && (pk() == "+" || pk() == "-")) adv()
while (pos < len && is_digit(pk())) adv()
}
}
@@ -305,12 +244,12 @@ var tokenize = function(src, filename) {
var start_row = row
var start_col = col
var raw = ""
if (pk_at(1) == CP_SLASH) {
while (pos < len && pk() != CP_LF && pk() != CP_CR) adv()
if (pk_at(1) == "/") {
while (pos < len && pk() != "\n" && pk() != "\r") adv()
} else {
adv(); adv() // skip /*
while (pos < len) {
if (pk() == CP_STAR && pk_at(1) == CP_SLASH) {
if (pk() == "*" && pk_at(1) == "/") {
adv(); adv()
break
}
@@ -359,144 +298,144 @@ var tokenize = function(src, filename) {
var start_row = 0
var start_col = 0
var raw = ""
if (c == -1) return false
if (c == null) return false
if (c == CP_LF) {
if (c == "\n") {
start = pos; start_row = row; start_col = col
adv()
push(tokens, { kind: "newline", at: start, from_row: start_row, from_column: start_col, to_row: row, to_column: col, value: "\n" })
return true
}
if (c == CP_CR) {
if (c == "\r") {
start = pos; start_row = row; start_col = col
adv()
if (pos < len && pk() == CP_LF) adv()
if (pos < len && pk() == "\n") adv()
push(tokens, { kind: "newline", at: start, from_row: start_row, from_column: start_col, to_row: row, to_column: col, value: "\n" })
return true
}
if (c == CP_SPACE || c == CP_TAB) {
if (c == " " || c == "\t") {
start = pos; start_row = row; start_col = col
while (pos < len && (pk() == CP_SPACE || pk() == CP_TAB)) adv()
while (pos < len && (pk() == " " || pk() == "\t")) adv()
raw = substr(start, pos)
push(tokens, { kind: "space", at: start, from_row: start_row, from_column: start_col, to_row: row, to_column: col, value: raw })
return true
}
if (c == CP_SQUOTE || c == CP_DQUOTE) { read_string(c); return true }
if (c == CP_BACKTICK) { read_template(); return true }
if (c == "'" || c == "\"") { read_string(c); return true }
if (c == "`") { read_template(); return true }
if (is_digit(c)) { read_number(); return true }
if (c == CP_DOT && is_digit(pk_at(1))) { read_number(); return true }
if (c == "." && is_digit(pk_at(1))) { read_number(); return true }
if (is_ident_start(c)) { read_name(); return true }
if (c == CP_SLASH) {
if (pk_at(1) == CP_SLASH || pk_at(1) == CP_STAR) { read_comment(); return true }
if (pk_at(1) == CP_EQ) { emit_op("/=", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (c == "/") {
if (pk_at(1) == "/" || pk_at(1) == "*") { read_comment(); return true }
if (pk_at(1) == "=") { emit_op("/=", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("/", 1); return true
}
if (c == CP_STAR) {
if (pk_at(1) == CP_STAR) {
if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(2) == CP_EQ) { emit_op("**=", 3); return true }
if (c == "*") {
if (pk_at(1) == "*") {
if (pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(2) == "=") { emit_op("**=", 3); return true }
emit_op("**", 2); return true
}
if (pk_at(1) == CP_EQ) { emit_op("*=", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (pk_at(1) == "=") { emit_op("*=", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("*", 1); return true
}
if (c == CP_PERCENT) {
if (pk_at(1) == CP_EQ) { emit_op("%=", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (c == "%") {
if (pk_at(1) == "=") { emit_op("%=", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("%", 1); return true
}
if (c == CP_PLUS) {
if (pk_at(1) == CP_EQ) { emit_op("+=", 2); return true }
if (pk_at(1) == CP_PLUS) { emit_op("++", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (c == "+") {
if (pk_at(1) == "=") { emit_op("+=", 2); return true }
if (pk_at(1) == "+") { emit_op("++", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("+", 1); return true
}
if (c == CP_MINUS) {
if (pk_at(1) == CP_EQ) { emit_op("-=", 2); return true }
if (pk_at(1) == CP_MINUS) { emit_op("--", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (c == "-") {
if (pk_at(1) == "=") { emit_op("-=", 2); return true }
if (pk_at(1) == "-") { emit_op("--", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("-", 1); return true
}
if (c == CP_LT) {
if (pk_at(1) == CP_EQ && pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(1) == CP_EQ) { emit_op("<=", 2); return true }
if (pk_at(1) == CP_LT) {
if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(2) == CP_EQ) { emit_op("<<=", 3); return true }
if (c == "<") {
if (pk_at(1) == "=" && pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(1) == "=") { emit_op("<=", 2); return true }
if (pk_at(1) == "<") {
if (pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(2) == "=") { emit_op("<<=", 3); return true }
emit_op("<<", 2); return true
}
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("<", 1); return true
}
if (c == CP_GT) {
if (pk_at(1) == CP_EQ && pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(1) == CP_EQ) { emit_op(">=", 2); return true }
if (pk_at(1) == CP_GT) {
if (pk_at(2) == CP_GT) {
if (pk_at(3) == CP_BANG) { emit_ident(4); return true }
if (pk_at(3) == CP_EQ) { emit_op(">>>=", 4); return true }
if (c == ">") {
if (pk_at(1) == "=" && pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(1) == "=") { emit_op(">=", 2); return true }
if (pk_at(1) == ">") {
if (pk_at(2) == ">") {
if (pk_at(3) == "!") { emit_ident(4); return true }
if (pk_at(3) == "=") { emit_op(">>>=", 4); return true }
emit_op(">>>", 3); return true
}
if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(2) == CP_EQ) { emit_op(">>=", 3); return true }
if (pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(2) == "=") { emit_op(">>=", 3); return true }
emit_op(">>", 2); return true
}
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op(">", 1); return true
}
if (c == CP_EQ) {
if (pk_at(1) == CP_EQ) {
if (pk_at(2) == CP_EQ) { emit_op("===", 3); return true }
if (c == "=") {
if (pk_at(1) == "=") {
if (pk_at(2) == "=") { emit_op("===", 3); return true }
emit_op("==", 2); return true
}
if (pk_at(1) == CP_GT) { emit_op("=>", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (pk_at(1) == ">") { emit_op("=>", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("=", 1); return true
}
if (c == CP_BANG) {
if (pk_at(1) == CP_EQ) {
if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(2) == CP_EQ) { emit_op("!==", 3); return true }
if (c == "!") {
if (pk_at(1) == "=") {
if (pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(2) == "=") { emit_op("!==", 3); return true }
emit_op("!=", 2); return true
}
emit_op("!", 1); return true
}
if (c == CP_AMP) {
if (pk_at(1) == CP_AMP) {
if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(2) == CP_EQ) { emit_op("&&=", 3); return true }
if (c == "&") {
if (pk_at(1) == "&") {
if (pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(2) == "=") { emit_op("&&=", 3); return true }
emit_op("&&", 2); return true
}
if (pk_at(1) == CP_EQ) { emit_op("&=", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (pk_at(1) == "=") { emit_op("&=", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("&", 1); return true
}
if (c == CP_PIPE) {
if (pk_at(1) == CP_PIPE) {
if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (pk_at(2) == CP_EQ) { emit_op("||=", 3); return true }
if (c == "|") {
if (pk_at(1) == "|") {
if (pk_at(2) == "!") { emit_ident(3); return true }
if (pk_at(2) == "=") { emit_op("||=", 3); return true }
emit_op("||", 2); return true
}
if (pk_at(1) == CP_EQ) { emit_op("|=", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (pk_at(1) == "=") { emit_op("|=", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("|", 1); return true
}
if (c == CP_CARET) {
if (pk_at(1) == CP_EQ) { emit_op("^=", 2); return true }
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (c == "^") {
if (pk_at(1) == "=") { emit_op("^=", 2); return true }
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("^", 1); return true
}
if (c == CP_LBRACKET) {
if (pk_at(1) == CP_RBRACKET && pk_at(2) == CP_BANG) { emit_ident(3); return true }
if (c == "[") {
if (pk_at(1) == "]" && pk_at(2) == "!") { emit_ident(3); return true }
emit_op("[", 1); return true
}
if (c == CP_TILDE) {
if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
if (c == "~") {
if (pk_at(1) == "!") { emit_ident(2); return true }
emit_op("~", 1); return true
}
emit_op(character(c), 1)
emit_op(c, 1)
return true
}
@@ -508,7 +447,7 @@ var tokenize = function(src, filename) {
// EOF token
push(tokens, { kind: "eof", at: pos, from_row: row, from_column: col, to_row: row, to_column: col })
return {filename: filename, tokens: tokens, cp: cp}
return {filename: filename, tokens: tokens}
}
return tokenize