Cumulative season's silent-bug hunting (~62 fixes) across the FiveSql2 SQL engine, the Five compiler/runtime, and the hbrdd RDD layer. Saved as a single checkpoint before refactoring the parser to delegate xBase command translation to the preprocessor. Highlights: FiveSql2 engine (_FiveSql2/src/) - prefix-glob index attach -> explicit convention (<table>_pk.ntx, <table>_uq.ntx, <table>.cdx) — fixes silent multi-row INSERT row-drop - DROP/CREATE TABLE FErase chain extended (.cdx, .fsc, .fsv, .dbt, .fpt) - COUNT(DISTINCT col) parsed + aggregated via hSeen hash - UNION column-count mismatch returns SQL_ERR_GRAMMAR (was silent) - DISTINCT + ORDER BY hidden-col leak fixed (trim before DISTINCT) - Derived table FROM (SELECT...) + JOIN right-side derived - Self-FK CASCADE depth 2+ via SqlGetSingleColPK pre-collect - LAG/LEAD default arg uses SqlEvalRowExpr (handles -N const exprs) - DATE literal round-trip validation (Feb 29 non-leap rejected) - CREATE OR REPLACE VIEW; CREATE VIEW errors on already-exists - AlterTable type dispatcher comma-wrapped (1-char type "A" no longer matches CHARACTER) Compiler / runtime - gengo: HB_ -> FV_ prefix on emitted Go function names (Five identity) - gengo split: emit_block.go, emit_stmt.go, folding.go extracted - parser/stmtreg.go nudges - hbrt: debug TUI/CLI restructure (debugcmd, debugkey, termios_*), windows debug stubs collapsed - thread/vm/value/class/pcinterp tightening from panic traces RDD layer (hbrdd/) - dbf: null bitmap support (null.go + null_test.go), mmap split (mmap_posix.go / mmap_windows.go), byte-level numeric parse - ntx/cdx: windows mmap parity - workarea + mem RDD: cross-area state-bleed fixes RTL (hbrtl/) - errorlog rewrite with platform-specific FD (errorlog_fd_unix / errorlog_fd_other) - sqlscan, sqlhelpers, indexrtl, datetime extensions Gates green at checkpoint: - go test ./... : PASS - FiveSql2 SQL:1999 : 43/43 - Harbour compat : 56/56 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
323 lines
7.8 KiB
Go
323 lines
7.8 KiB
Go
// Copyright (c) 2026 Charles KWON OhJun (charleskwonohjun@gmail.com)
|
||
// All rights reserved.
|
||
|
||
// Five pcode interpreter — executes pcode bytecode on a Thread.
|
||
// Each opcode directly calls the corresponding Thread method,
|
||
// so pcode execution is semantically identical to gengo-compiled code.
|
||
|
||
package hbrt
|
||
|
||
import (
|
||
"encoding/binary"
|
||
"fmt"
|
||
"math"
|
||
)
|
||
|
||
// ExecPcode runs a pcode function on the given thread.
|
||
// Full variant — installs a defer/recover so panics from inside the
|
||
// pcode body (HbError, BreakValue, user Break) are re-panicked with
|
||
// proper frame unwinding. Used for general-purpose pcode evaluation.
|
||
func ExecPcode(t *Thread, fn *PcodeFunc, mod *PcodeModule) {
|
||
t.Frame(fn.Params, fn.Locals)
|
||
defer t.EndProc()
|
||
execPcodeBody(t, fn, mod)
|
||
}
|
||
|
||
// ExecPcodeFast is a hot-path variant for short, pure expressions
|
||
// (FiveSql2 WHERE predicates, inline lambdas) where the caller has
|
||
// already guaranteed that the body will not panic with HbError /
|
||
// BreakValue. Skips the defer+recover dance in EndProc, saving ~15ns
|
||
// per call × tens of thousands of rows in scan loops.
|
||
//
|
||
// Contract: caller is responsible for panic discipline. If the pcode
|
||
// body panics, the frame stack is still cleaned up (EndProcFast) but
|
||
// no diagnostic is logged and SEQUENCE/RECOVER will not see the panic.
|
||
func ExecPcodeFast(t *Thread, fn *PcodeFunc, mod *PcodeModule) {
|
||
t.Frame(fn.Params, fn.Locals)
|
||
execPcodeBody(t, fn, mod)
|
||
t.EndProcFast()
|
||
}
|
||
|
||
// execPcodeBody is the shared opcode dispatch loop.
|
||
func execPcodeBody(t *Thread, fn *PcodeFunc, mod *PcodeModule) {
|
||
code := fn.Code
|
||
pc := 0 // program counter
|
||
|
||
for pc < len(code) {
|
||
op := code[pc]
|
||
pc++
|
||
|
||
switch op {
|
||
case PcOpNop:
|
||
// do nothing
|
||
|
||
// --- Stack ---
|
||
case PcOpPushNil:
|
||
t.PushNil()
|
||
case PcOpPushTrue:
|
||
t.PushBool(true)
|
||
case PcOpPushFalse:
|
||
t.PushBool(false)
|
||
case PcOpPushInt:
|
||
v := int64(binary.LittleEndian.Uint64(code[pc:]))
|
||
pc += 8
|
||
t.PushLong(v)
|
||
case PcOpPushDouble:
|
||
bits := binary.LittleEndian.Uint64(code[pc:])
|
||
pc += 8
|
||
t.PushDouble(math.Float64frombits(bits), 0, 0)
|
||
case PcOpPushString:
|
||
slen := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
t.PushString(string(code[pc : pc+slen]))
|
||
pc += slen
|
||
case PcOpPushBool:
|
||
t.PushBool(code[pc] != 0)
|
||
pc++
|
||
case PcOpPushLocal:
|
||
idx := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
t.PushLocal(idx)
|
||
case PcOpPushMemvar:
|
||
slen := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
name := string(code[pc : pc+slen])
|
||
pc += slen
|
||
// Resolve through Memvars (PRIVATE shadows PUBLIC).
|
||
// Unknown names push NIL — matches Harbour behavior for
|
||
// undeclared memvars inside `&(expr)`.
|
||
if t.Memvars != nil {
|
||
if v, ok := t.Memvars.Get(name); ok {
|
||
t.push(v)
|
||
continue
|
||
}
|
||
}
|
||
t.PushNil()
|
||
case PcOpPopLocal:
|
||
idx := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
t.PopLocal(idx)
|
||
case PcOpPop:
|
||
t.Pop()
|
||
case PcOpDup:
|
||
t.Dup()
|
||
|
||
// --- Arithmetic ---
|
||
case PcOpPlus:
|
||
t.Plus()
|
||
case PcOpMinus:
|
||
t.Minus()
|
||
case PcOpMult:
|
||
t.Mult()
|
||
case PcOpDivide:
|
||
t.Divide()
|
||
case PcOpMod:
|
||
t.Modulus()
|
||
case PcOpPower:
|
||
t.Power()
|
||
case PcOpNegate:
|
||
t.Negate()
|
||
|
||
// --- Comparison ---
|
||
case PcOpEqual:
|
||
t.Equal()
|
||
case PcOpNotEqual:
|
||
t.NotEqual()
|
||
case PcOpLess:
|
||
t.Less()
|
||
case PcOpGreater:
|
||
t.Greater()
|
||
case PcOpLessEq:
|
||
t.LessEqual()
|
||
case PcOpGreaterEq:
|
||
t.GreaterEqual()
|
||
case PcOpInString:
|
||
t.InString()
|
||
|
||
// --- Logical ---
|
||
case PcOpAnd:
|
||
t.And()
|
||
case PcOpOr:
|
||
t.Or()
|
||
case PcOpNot:
|
||
t.Not()
|
||
|
||
// --- Flow control ---
|
||
case PcOpJump:
|
||
offset := int32(binary.LittleEndian.Uint32(code[pc:]))
|
||
pc += 4
|
||
pc += int(offset)
|
||
case PcOpJumpFalse:
|
||
offset := int32(binary.LittleEndian.Uint32(code[pc:]))
|
||
pc += 4
|
||
if !t.PopLogical() {
|
||
pc += int(offset)
|
||
}
|
||
case PcOpJumpTrue:
|
||
offset := int32(binary.LittleEndian.Uint32(code[pc:]))
|
||
pc += 4
|
||
if t.PopLogical() {
|
||
pc += int(offset)
|
||
}
|
||
case PcOpReturn:
|
||
return
|
||
case PcOpRetValue:
|
||
t.RetValue()
|
||
return
|
||
|
||
// --- Frame ---
|
||
case PcOpFrame:
|
||
// Already called at function entry; skip if re-encountered
|
||
pc += 4 // params + locals
|
||
case PcOpEndProc:
|
||
return
|
||
|
||
// --- Workarea field access (peephole for FieldGet(literal)) ---
|
||
case PcOpFieldGet:
|
||
fIdx := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
// Hot path — SqlScan plugs a direct field getter closure into
|
||
// t.FastFieldGetter before running the predicate, so we skip
|
||
// PushSymbol + Function dispatch + FieldGet RTL's own Frame.
|
||
if fg := t.FastFieldGetter; fg != nil {
|
||
t.PushValue(fg(fIdx))
|
||
} else {
|
||
// Generic fallback: resolve through RTL symbol table
|
||
t.PushSymbol(t.VM().FindSymbol("FIELDGET"))
|
||
t.PushNil()
|
||
t.PushLong(int64(fIdx))
|
||
t.Function(1)
|
||
}
|
||
|
||
// --- AllTrim(FieldGet(n)) fused peephole ---
|
||
case PcOpFieldTrim:
|
||
fIdx := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
// Fast path: use direct field getter, trim inline.
|
||
var v Value
|
||
if fg := t.FastFieldGetter; fg != nil {
|
||
v = fg(fIdx)
|
||
} else {
|
||
// Fallback: resolve via FIELDGET RTL
|
||
t.PushSymbol(t.VM().FindSymbol("FIELDGET"))
|
||
t.PushNil()
|
||
t.PushLong(int64(fIdx))
|
||
t.Function(1)
|
||
v = t.Pop2()
|
||
}
|
||
if v.IsString() {
|
||
s := v.AsString()
|
||
// ASCII-space trim — DBF CHAR fields pad with 0x20 only
|
||
lo, hi := 0, len(s)
|
||
for lo < hi && s[lo] == ' ' {
|
||
lo++
|
||
}
|
||
for hi > lo && s[hi-1] == ' ' {
|
||
hi--
|
||
}
|
||
if lo == 0 && hi == len(s) {
|
||
t.PushValue(v)
|
||
} else {
|
||
t.PushString(s[lo:hi])
|
||
}
|
||
} else {
|
||
t.PushValue(v)
|
||
}
|
||
|
||
// --- Function calls ---
|
||
case PcOpPushSymbol:
|
||
slen := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
name := string(code[pc : pc+slen])
|
||
pc += slen
|
||
sym := t.VM().FindSymbol(name)
|
||
t.PushSymbol(sym)
|
||
case PcOpPushNilArg:
|
||
t.PushNil()
|
||
case PcOpFunction:
|
||
nArgs := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
t.Function(nArgs)
|
||
case PcOpDo:
|
||
nArgs := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
t.Do(nArgs)
|
||
|
||
// --- Self / OOP ---
|
||
case PcOpPushSelf:
|
||
t.PushSelf()
|
||
case PcOpPushSelfField:
|
||
slen := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
name := string(code[pc : pc+slen])
|
||
pc += slen
|
||
t.PushSelfField(name)
|
||
case PcOpSetSelfField:
|
||
slen := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
name := string(code[pc : pc+slen])
|
||
pc += slen
|
||
t.SetSelfField(name)
|
||
case PcOpSend:
|
||
slen := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
name := string(code[pc : pc+slen])
|
||
pc += slen
|
||
nArgs := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
t.Send(name, nArgs)
|
||
|
||
// --- Array ---
|
||
case PcOpArrayGen:
|
||
count := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
t.ArrayGen(count)
|
||
case PcOpArrayPush:
|
||
t.ArrayPush()
|
||
case PcOpArrayPop:
|
||
t.ArrayPop()
|
||
|
||
// --- Block ---
|
||
case PcOpPushBlock:
|
||
codeLen := int(binary.LittleEndian.Uint32(code[pc:]))
|
||
pc += 4
|
||
blockCode := make([]byte, codeLen)
|
||
copy(blockCode, code[pc:pc+codeLen])
|
||
pc += codeLen
|
||
nDetached := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
|
||
// Create a Go function that interprets the block's pcode
|
||
blockFn := &PcodeFunc{Code: blockCode}
|
||
modCopy := mod
|
||
t.PushBlock(func(t2 *Thread) {
|
||
ExecPcode(t2, blockFn, modCopy)
|
||
}, nDetached)
|
||
|
||
// --- Local ops ---
|
||
case PcOpLocalAddInt:
|
||
idx := int(binary.LittleEndian.Uint16(code[pc:]))
|
||
pc += 2
|
||
val := int32(binary.LittleEndian.Uint32(code[pc:]))
|
||
pc += 4
|
||
t.LocalAddInt(idx, int64(val))
|
||
case PcOpInc:
|
||
t.Inc()
|
||
case PcOpDec:
|
||
t.Dec()
|
||
|
||
case PcOpPopLogical:
|
||
t.PopLogical()
|
||
|
||
case PcOpLine:
|
||
pc += 2 // skip line number (for debugging)
|
||
|
||
case PcOpHalt:
|
||
return
|
||
|
||
default:
|
||
panic(fmt.Sprintf("unknown pcode opcode: 0x%02X at pc=%d", op, pc-1))
|
||
}
|
||
}
|
||
}
|