fivedev/five
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

perf(FiveSql2): hybrid fast path — 11x speedup on string WHERE scans

Browse Source 
Implements hybrid execution model: keep AST tree-walk for SQL:2013+
features (Window, Recursive CTE, JOIN, aggregates) while compiling
simple SELECT hot paths to Go + pcode. See docs/FiveSql2-Hybrid-Plan.md
for the full architecture rationale (why not SQLite-style VDBE).

Hot path (single table, no joins/groups/aggregates):
  - TryBuildFieldPositions: resolves SELECT column list to FieldPos
    array once per query (bails to PRG loop on any complex expr).
  - TryCompileWhere + SqlExprToPrg: walks WHERE AST, emits equivalent
    PRG source, runs it through PcCompile to get a PcodeFunc.
  - SqlScan RTL: Go-native scan loop — GoTop/EOF/Skip/GetValue
    direct, ExecPcode per row for WHERE, result array pre-alloc.

WHERE compiler scope:
  - ND_LIT numeric/logical/string (string literals AllTrim'd to match
    SqlCmpEq CHAR-padding semantics; rejects embedded quotes/newlines)
  - ND_COL: CHAR fields auto-wrapped with AllTrim(FieldGet(n)) based
    on dbStruct() lookup cached once per query in aCompileStruct
  - ND_BIN: = <> != < <= > >= AND OR + - * /
  - ND_UNI: NOT -
  - Anything else (ND_FN, ND_CASE, ND_SUB, ND_PAR, LIKE, IN, IS NULL,
    BETWEEN, dates) returns NIL → falls back to PRG tree-walk.

Bench (50k rows, ~/tmp ext4):
                        Before      After     Speedup
  Numeric WHERE         ~150ms     11.7ms     ~13x
  String WHERE          119.3ms    10.5ms     11.4x
  No WHERE               -         14.6ms      -
  Raw RDD baseline        6.8ms     6.8ms      1.0x

Remaining gap to raw RDD (~1.5x) is structural: Value boxing, result
array construction, per-row ExecPcode frame overhead. Would need a
Value-pool or SoA refactor to close further.

Side fixes bundled:
  - TSqlIndex:FindExclusive short-circuited. Originally called
    dbInfo(DBI_FULLPATH)/DBI_SHARED which are unresolved symbols in
    Five (dbInfo is a stub, DBI_* never defined). Panic'd with
    "local variable index out of range: 0" whenever a standalone PRG
    had a workarea Used before calling five_SQL. 43-test masked the
    bug because it only reached FindExclusive with no open workareas.
    Restore the scan once dbInfo lands in hbrtl.
  - cmd/five/main.go: FIVE_KEEP_BUILD=1 env var keeps the temp Go
    project around for debugging gengo output.

Validation:
  - FiveSql2 43/43
  - Harbour compat 51/51
  - go test ./... ALL PASS

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
CharlesKWON
2026-04-14 09:15:08 +09:00
parent 6b26f1b642
commit 8aaed994f4
6 changed files with 552 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

200
_FiveSql2/src/TSqlExecutor.prg
View File

@@ -32,6 +32,7 @@ CLASS TSqlExecutor
DATA nDepth INIT 0
DATA aOpened INIT {}
DATA aTables INIT {}
DATA aCompileStruct
CLASSDATA hSubCache INIT { => } SHARED
@@ -62,6 +63,9 @@ CLASS TSqlExecutor
METHOD ApplyWindowFunctions( aRows, aFN, aCols )
METHOD RunMerge()
METHOD RunTruncate()
METHOD TryBuildFieldPositions( aExprs )
METHOD TryCompileWhere( xWhere )
METHOD SqlExprToPrg( xNode )
ENDCLASS
@@ -970,6 +974,7 @@ METHOD RunSelect() CLASS TSqlExecutor
LOCAL xArgExpr, cBare, lFound, aLeafCols, k
LOCAL hJoinHash
LOCAL lIndexUsed, aTmp
LOCAL aFP, pcW, aGoRows
aCols := ::hQuery[ "columns" ]
::aTables := ::hQuery[ "tables" ]
@@ -1190,6 +1195,31 @@ METHOD RunSelect() CLASS TSqlExecutor
hJoinHash := { => }
/* === GO NATIVE FAST PATH ===
* Single-table, no joins, no aggregates, all SELECT exprs
* simple field refs, WHERE is NIL or compilable to pcode.
* Hands the scan loop off to Go's SqlScan (~15x faster
* than the PRG per-row tree walk).
*/
aFP := NIL
pcW := NIL
aGoRows := NIL
IF Len( aJoins ) == 0 .AND. Len( aGroupBy ) == 0 .AND. ;
! ::oAgg:HasAgg( aCols )
aFP := ::TryBuildFieldPositions( aResultExprs )
IF aFP != NIL
pcW := ::TryCompileWhere( xWhere )
IF xWhere == NIL .OR. pcW != NIL
aGoRows := SqlScan( aFP, pcW )
FOR i := 1 TO Len( aGoRows )
AAdd( aRows, aGoRows[ i ] )
NEXT
ENDIF
ENDIF
ENDIF
/* Fallback: PRG interpreter loop */
IF aGoRows == NIL
WHILE ! Eof()
IF Len( aJoins ) > 0
::JoinRecurse( aJoins, 1, xWhere, aResultExprs, @aRows, hJoinHash )
@@ -1206,6 +1236,7 @@ METHOD RunSelect() CLASS TSqlExecutor
ENDIF
ENDIF
ENDIF
ENDIF
/* GROUP BY */
IF Len( aGroupBy ) > 0 .OR. ::oAgg:HasAgg( aCols )
@@ -2731,3 +2762,172 @@ STATIC FUNCTION RecCteJoin( hRecQuery, aFN, aPrevRows, cCteName )
dbSelectArea( nSaveWA )
RETURN aResult
/* --------------------------------------------------------------
* Go fast-path helpers
* Return non-NIL only when the query can be handed off to Go's
* SqlScan RTL. Any complexity (expressions, functions, joins,
* parameters in WHERE) → return NIL so the PRG loop takes over.
* -------------------------------------------------------------- */
METHOD TryBuildFieldPositions( aExprs ) CLASS TSqlExecutor
LOCAL aPositions := {}, i, xE, cRef, nDot, cField, nFPos
FOR i := 1 TO Len( aExprs )
xE := aExprs[ i ][ 1 ]
IF xE == NIL .OR. xE[ 1 ] != ND_COL .OR. xE[ 2 ] == "*"
RETURN NIL
ENDIF
cRef := xE[ 2 ]
nDot := At( ".", cRef )
IF nDot > 0
cField := Upper( SubStr( cRef, nDot + 1 ) )
ELSE
cField := Upper( cRef )
ENDIF
nFPos := FieldPos( cField )
IF nFPos == 0
RETURN NIL
ENDIF
AAdd( aPositions, nFPos )
NEXT
RETURN aPositions
METHOD TryCompileWhere( xWhere ) CLASS TSqlExecutor
/* Phase 1+2: compile numeric/logical/string WHERE to pcode.
* Semantic guard: SqlExprToPrg returns NIL for anything that would
* drift from SqlCmpEq/SqlCoerceForCmp semantics. CHAR columns are
* auto-wrapped with AllTrim() to match Harbour SqlCmpEq behavior.
* NULL/function/subquery/parameter → NIL (fallback).
*/
LOCAL cPrg, xResult
IF xWhere == NIL
RETURN NIL
ENDIF
/* Cache struct once for field-type lookups during expr walk */
::aCompileStruct := dbStruct()
cPrg := ::SqlExprToPrg( xWhere )
::aCompileStruct := NIL
IF cPrg == NIL
RETURN NIL
ENDIF
xResult := PcCompile( cPrg )
RETURN xResult
METHOD SqlExprToPrg( xNode ) CLASS TSqlExecutor
LOCAL cOp, cL, cR
LOCAL cRef, nDot, cField, nFPos, cFType, cLit
IF xNode == NIL
RETURN NIL
ENDIF
DO CASE
CASE xNode[ 1 ] == ND_LIT
IF ValType( xNode[ 2 ] ) == "N"
RETURN AllTrim( Str( xNode[ 2 ] ) )
ENDIF
IF ValType( xNode[ 2 ] ) == "L"
IF xNode[ 2 ]
RETURN ".T."
ENDIF
RETURN ".F."
ENDIF
IF ValType( xNode[ 2 ] ) == "C"
cLit := xNode[ 2 ]
/* Reject strings with embedded quotes — escaping would be ambiguous */
IF "'" $ cLit .OR. '"' $ cLit .OR. Chr(10) $ cLit .OR. Chr(13) $ cLit
RETURN NIL
ENDIF
/* Match SqlCmpEq: compare trimmed values */
RETURN "'" + AllTrim( cLit ) + "'"
ENDIF
/* Dates/datetimes deferred */
RETURN NIL
CASE xNode[ 1 ] == ND_COL
cRef := xNode[ 2 ]
IF cRef == "*"
RETURN NIL
ENDIF
nDot := At( ".", cRef )
IF nDot > 0
cField := Upper( SubStr( cRef, nDot + 1 ) )
ELSE
cField := Upper( cRef )
ENDIF
nFPos := FieldPos( cField )
IF nFPos == 0
RETURN NIL
ENDIF
/* Look up field type from cached struct to decide AllTrim wrap */
cFType := ""
IF ::aCompileStruct != NIL .AND. nFPos <= Len( ::aCompileStruct )
cFType := ::aCompileStruct[ nFPos ][ 2 ]
ENDIF
IF cFType == "C"
RETURN "AllTrim(FieldGet(" + AllTrim( Str( nFPos ) ) + "))"
ENDIF
RETURN "FieldGet(" + AllTrim( Str( nFPos ) ) + ")"
CASE xNode[ 1 ] == ND_UNI
cOp := xNode[ 2 ]
cL := ::SqlExprToPrg( xNode[ 3 ] )
IF cL == NIL
RETURN NIL
ENDIF
IF cOp == "NOT"
RETURN "!(" + cL + ")"
ENDIF
IF cOp == "-"
RETURN "-(" + cL + ")"
ENDIF
RETURN NIL
CASE xNode[ 1 ] == ND_BIN
cOp := xNode[ 2 ]
cL := ::SqlExprToPrg( xNode[ 3 ] )
IF cL == NIL
RETURN NIL
ENDIF
cR := ::SqlExprToPrg( xNode[ 4 ] )
IF cR == NIL
RETURN NIL
ENDIF
DO CASE
CASE cOp == "=" .OR. cOp == "=="
RETURN "(" + cL + ")==(" + cR + ")"
CASE cOp == "<>" .OR. cOp == "!="
RETURN "(" + cL + ")!=(" + cR + ")"
CASE cOp == "<"
RETURN "(" + cL + ")<(" + cR + ")"
CASE cOp == "<="
RETURN "(" + cL + ")<=(" + cR + ")"
CASE cOp == ">"
RETURN "(" + cL + ")>(" + cR + ")"
CASE cOp == ">="
RETURN "(" + cL + ")>=(" + cR + ")"
CASE cOp == "AND"
RETURN "(" + cL + ").AND.(" + cR + ")"
CASE cOp == "OR"
RETURN "(" + cL + ").OR.(" + cR + ")"
CASE cOp == "+"
RETURN "(" + cL + ")+(" + cR + ")"
CASE cOp == "-"
RETURN "(" + cL + ")-(" + cR + ")"
CASE cOp == "*"
RETURN "(" + cL + ")*(" + cR + ")"
CASE cOp == "/"
RETURN "(" + cL + ")/(" + cR + ")"
ENDCASE
RETURN NIL
ENDCASE
RETURN NIL

38
_FiveSql2/src/TSqlIndex.prg
View File

@@ -132,27 +132,23 @@ RETURN nWA
METHOD FindExclusive( cTableLow ) CLASS TSqlIndex
LOCAL nSaved, nArea, cDbfName, lShared
nSaved := Select()
FOR nArea := 1 TO 250
IF ( nArea )->( Used() )
dbSelectArea( nArea )
IF ! Empty( Alias() )
cDbfName := Lower( AllTrim( dbInfo( DBI_FULLPATH ) ) )
IF cTableLow + ".dbf" $ cDbfName .OR. cTableLow $ cDbfName
lShared := dbInfo( DBI_SHARED )
IF ! lShared
dbSelectArea( nSaved )
RETURN nArea
ENDIF
ENDIF
ENDIF
ENDIF
NEXT
dbSelectArea( nSaved )
/* Pre-flight exclusive-lock detection.
* Originally used dbInfo(DBI_FULLPATH)/DBI_SHARED to scan open
* workareas for an exclusive hold on the target DBF. In Five,
* `dbInfo()` is stubbed (returns NIL) and the DBI_* symbols are
* unresolved at compile time → runtime panic the moment any
* workarea is Used() when this runs (standalone PRGs routinely
* dbUseArea before calling five_SQL, so they tripped this).
*
* The check cannot function correctly on Five regardless, so
* we short-circuit to 0 (= no conflict). Matches behavior of
* the 43-test harness which only reaches here with no Used
* workareas, so the net behavior is preserved.
*
* Future: when dbInfo(DBI_FULLPATH) lands in hbrtl, restore
* the scan. Until then use `Alias()` + filename matching if
* exclusive-lock preflight becomes necessary.
*/
RETURN 0

20
cmd/five/main.go
View File

@@ -128,7 +128,11 @@ func runPRG(prgFile string) {
if err != nil {
fatal("failed to create temp dir: " + err.Error())
}
if os.Getenv("FIVE_KEEP_BUILD") == "" {
defer os.RemoveAll(tmpDir)
} else {
fmt.Fprintln(os.Stderr, "[FIVE_KEEP_BUILD] keeping:", tmpDir)
}
writeGoProject(tmpDir, prgFile, goCode)
@@ -159,7 +163,11 @@ func buildPRG(prgFile, output string) {
if err != nil {
fatal("failed to create temp dir: " + err.Error())
}
if os.Getenv("FIVE_KEEP_BUILD") == "" {
defer os.RemoveAll(tmpDir)
} else {
fmt.Fprintln(os.Stderr, "[FIVE_KEEP_BUILD] keeping:", tmpDir)
}
writeGoProject(tmpDir, prgFile, goCode)
@@ -198,7 +206,11 @@ func buildMultiPRG(prgFiles []string, output string) {
if err != nil {
fatal("failed to create temp dir: " + err.Error())
}
if os.Getenv("FIVE_KEEP_BUILD") == "" {
defer os.RemoveAll(tmpDir)
} else {
fmt.Fprintln(os.Stderr, "[FIVE_KEEP_BUILD] keeping:", tmpDir)
}
// Phase 1: Parse all files and collect cross-file function names
type parsedFile struct {
@@ -549,7 +561,11 @@ func buildFRB(prgFile, outputFile string) {
if err != nil {
fatal("cannot create temp dir: " + err.Error())
}
if os.Getenv("FIVE_KEEP_BUILD") == "" {
defer os.RemoveAll(tmpDir)
} else {
fmt.Fprintln(os.Stderr, "[FIVE_KEEP_BUILD] keeping:", tmpDir)
}
// Write go.mod — point to Five's module root
fiveRoot := mustAbs(".")
@@ -659,7 +675,11 @@ func debugPRG(prgFile string) {
if err != nil {
fatal("cannot create temp dir: " + err.Error())
}
if os.Getenv("FIVE_KEEP_BUILD") == "" {
defer os.RemoveAll(tmpDir)
} else {
fmt.Fprintln(os.Stderr, "[FIVE_KEEP_BUILD] keeping:", tmpDir)
}
fiveRoot := findProjectRoot()
goMod := fmt.Sprintf("module five-generated\n\ngo 1.21.13\n\nrequire five v0.0.0\n\nreplace five => %s\n", fiveRoot)

175
docs/FiveSql2-Hybrid-Plan.md Normal file
View File

@@ -0,0 +1,175 @@
# FiveSql2 하이브리드 실행 모델 — 구현 계획
**Date:** 2026-04-14
**Decision Owner:** Charles KWON
**Status:** 확정 (user: "좋아요 그게 답입니다")
---
## 1. 아키텍처 결정
### 1.1 설계 원칙
FiveSql2는 **AST tree-walk 평가기**와 **pcode/Go 핫패스**를 공존시킨다.
SQLite 방식(AST 폐기 + 전량 VDBE 컴파일)은 **채택하지 않는다**.
### 1.2 왜 하이브리드인가
| 관점 | AST 유지 (FiveSql2) | VDBE 전량 (SQLite) |
|------|---------------------|-------------------|
| 신규 SQL 표준 추가 | evaluator에 CASE 추가 | 코드젠 + opcode 신설 |
| Window/RECURSIVE CTE | tree-walk로 자연 표현 | 서브프로그램·임시 커서 필요 |
| 단순 SELECT 성능 | 느림 (트리 워크) | 빠름 (op dispatch) |
| 구현 복잡도 | 낮음 | 매우 높음 |
FiveSql2는 SQL:1999 → SQL:2013 → 향후 표준 확장이 최우선이므로
**AST 기반 확장성**을 희생하지 않는다. 성능은 **핫패스 선별 하강**으로 해결.
### 1.3 역할 분담
```
┌─────────────────────────────────────────────────────┐
│ Parser (PRG) → AST (영속) │
│ │ │
│ ▼ │
│ TSqlExecutor.RunSelect (PRG) │
│ ├─ Window / CTE / Recursive → tree-walk evaluator │
│ ├─ GROUP BY / Aggregate → tree-walk evaluator │
│ ├─ JOIN → tree-walk evaluator │
│ │ │
│ └─ ★ Hot path (simple scan) │
│ ├─ TryBuildFieldPositions(aExprs) │
│ ├─ TryCompileWhere(xWhere) → PcCompile │
│ └─ SqlScan(fields, pcWhere) ── Go RTL ──┐ │
└─────────────────────────────────────────────────┼────┘
▼
┌────────────────────────┐
│ hbrtl/sqlscan.go │
│ area.GoTop/EOF/Skip │
│ ExecPcode per row │
│ GetValue(idx) direct │
└────────────────────────┘
```
---
## 2. 현재 상태 (2026-04-14)
### 완료
- [x] `compiler/genpc/genpc.go` — `CompileExpr` 공개 API
- [x] `hbrtl/pcexpr.go` — `PcCompile` / `PcEval` RTL
- [x] `hbrtl/sqlscan.go` — Go 네이티브 스캔 루프
- [x] `hbrdd/dbf/dbf.go` — `FieldPosCache` O(1)
- [x] `_FiveSql2/src/TSqlExecutor.prg` — `TryBuildFieldPositions` / `TryCompileWhere` 메서드
- [x] Fast path 통합 (WHERE 없음 + 단순 projection 한정)
- [x] 회귀: 43/43 · 51/51 · Go tests ALL PASS
### 미완성
- [ ] `TryCompileWhere`가 항상 NIL 반환 — WHERE 있는 쿼리는 느린 경로
- [ ] `BindColumns/ResolveCache` 4-test 회귀 미해결
- [ ] 소형 PRG `TSqlIndex:FindExclusive` 패닉 (격리 벤치 차단)
---
## 3. 단계별 작업 계획
### Phase 1 — WHERE 컴파일러 (우선순위 최상)
**목표:** `TryCompileWhere`가 단순 WHERE를 pcode로 변환해 `SqlScan`에 넘김.
**범위:**
- ND_COL → `FieldGet(n)` (CHAR 비교 시 `AllTrim()` 자동 래핑)
- ND_LIT → 숫자/문자열 literal
- ND_BIN — `=`, `<>`, `!=`, `<`, `<=`, `>`, `>=`, `AND`, `OR`
- 그 외 (ND_FN, ND_CASE, ND_SUB, LIKE, IN, IS NULL, BETWEEN, ND_PAR) → NIL 반환 (fallback)
**의미 보존 원칙:**
- `SqlCmpEq`의 CHAR trim 규칙을 PRG 변환 시점에 반영 (비교 양변이 ND_COL이고 CHAR면 `AllTrim()` 래핑)
- NULL 비교는 첫 버전에서 미지원 — ND_NIL 포함 시 NIL 반환
- 타입 강제는 Five의 기본 연산자 오버로딩에 위임
**파일:**
- `_FiveSql2/src/TSqlExecutor.prg` — `METHOD SqlExprToPrg(xNode)` 신설
- `TryCompileWhere`에서 호출
**검증:** 43/43 유지 + simple WHERE 벤치 (50k rows, `salary > 50000`) pcode 경로 확인.
---
### Phase 2 — Projection 확장
**목표:** `TryBuildFieldPositions`를 넘어 단순 식 projection 지원.
**범위:**
- `SELECT a + b, c * 2 FROM t` — ND_BIN 산술식도 pcode로
- 설계 변경: `SqlScan`이 필드 인덱스 배열 대신 **pcode 배열**(projection 표현식) 수신
- `aSelectExprs []*PcodeFunc` 형태로 RTL 확장
**파일:**
- `hbrtl/sqlscan.go` — 시그니처 변경: `SqlScan(aProjs, pcWhere)`
- `_FiveSql2/src/TSqlExecutor.prg` — projection 빌더
**Risk:** SQL 함수(UPPER/ALLTRIM/SUBSTR)는 PRG 런타임에 존재. pcode ExecPcode가 이들 함수를 호출 가능한지 확인 필요.
---
### Phase 3 — BindColumns 회귀 해결
**목표:** 이전 세션의 `ResolveCache` PushLocal(0) 버그 근본 원인 파악.
**증상:** 4 tests panic at `class.go:278` Send. "Unresolved variable → PushLocal(0)".
**조사 항목:**
- CLASS 내부에서 Resolve를 캐시할 때 `self` 참조가 깨지는 경우
- `pendingParams` 순서와의 상호작용
- gengo가 캐시 변수를 local index 0으로 emit하는지
**파일:** `hbrt/class.go`, `compiler/gengo/gen_class.go` (조사 우선, 수정은 증거 기반)
---
### Phase 4 — 소형 PRG FindExclusive 패닉
**목표:** 격리 벤치가 가능하도록 class-system edge case 수정.
**증상:** 소형 PRG에서 `TSqlIndex:FindExclusive` "local variable index out of range: 0"
**영향:** 벤치 격리 차단. 43-test 통합 실행에서는 발생 안 함 → **Phase 1 종료 후** 진행.
---
### Phase 5 — 벤치 + 커밋
**목표:** 실측 데이터로 고속화 배수 확정 후 커밋.
**벤치 케이스:**
- 50k × 3 컬럼 DBF
- SELECT * (fast path)
- SELECT a, b WHERE ... (fast path after Phase 1)
- JOIN / GROUP BY / Window (fallback, 변화 없음 확인)
**커밋 규칙:** Phase 별 개별 커밋. CLAUDE.md의 3-테스트 게이트 매번 통과.
---
## 4. 비목표 (Non-goals)
- SQLite식 전량 VDBE 컴파일 — 거부
- AST 구조 변경 — SQL:2013 이상 확장 경로 보존
- 옵티마이저 전면 재작성 — 기존 `oIndex:TryIndexScan`, plan cache는 유지
- 동시성/트랜잭션 모델 변경 — 이번 범위 밖
---
## 5. 검증 게이트 (불변)
모든 Phase 종료 시 CLAUDE.md 규칙대로 3개 통과:
```bash
go test ./... # Go 유닛
./five build _FiveSql2/test/test_sql1999.prg _FiveSql2/src/*.prg -o /tmp/test_sql && \
cd ~/tmp && rm -f *.dbf __cte_*.dbf 2>/dev/null; /tmp/test_sql # 43/43
./five build tests/compat_harbour.prg -o /tmp/test_compat && /tmp/test_compat # 51/51
```
하나라도 실패 → 해당 Phase 롤백.

2
hbrtl/register.go
View File

@@ -610,6 +610,8 @@ func RegisterRTL(vm *hbrt.VM) {
// Expression bytecode compilation (FiveSql2 hot-path optimization)
hbrt.Sym("PCCOMPILE", hbrt.FsPublic, PcCompile),
hbrt.Sym("PCEVAL", hbrt.FsPublic, PcEval),
// Go-native SQL scan loop (bypasses PRG interpreter for hot path)
hbrt.Sym("SQLSCAN", hbrt.FsPublic, SqlScan),
// Goroutine / Concurrency
hbrt.Sym("GO", hbrt.FsPublic, GoFunc),

122
hbrtl/sqlscan.go Normal file
View File

@@ -0,0 +1,122 @@
// Copyright (c) 2026 Charles KWON OhJun (charleskwonohjun@gmail.com)
// All rights reserved.
// Go-native SQL scan loop for FiveSql2 hot path.
//
// Motivation: FiveSql2 is a PRG-based SQL interpreter. For simple
// "SELECT cols FROM table WHERE cond" queries, the per-row cost is
// dominated by PRG interpreter overhead (AST tree walk, field name
// lookup, workarea switching). Moving just the inner scan loop to Go
// bypasses all that overhead and gets us ~15x speedup for the common
// case while keeping the rest of FiveSql2 untouched.
//
// The SQL engine remains responsible for:
// - Parsing SQL and building AST
// - Resolving field names to positions (column binding)
// - Compiling WHERE expression to pcode (via PcCompile)
// - GROUP BY, ORDER BY, aggregates (not per-row)
//
// This helper only handles the hot loop:
// - Full table scan (workarea already positioned)
// - Per-row WHERE evaluation via ExecPcode
// - Column extraction via cached field positions
// - Result array construction
package hbrtl
import (
"five/hbrdd"
"five/hbrt"
)
// SqlScan(aFieldPositions, pcWhere) → aRows
//
// Scans the current workarea top-to-bottom, evaluates pcWhere per row
// (nil = no filter), collects selected column values into rows.
//
// aFieldPositions: array of 1-based field positions to extract per row.
// Resolve once before calling (FieldPos cache is O(1)
// but still has PRG → Go call overhead).
// pcWhere: pcode function pointer from PcCompile, or NIL.
//
// Returns:
// Array of rows, each row = Array of field values.
//
// Notes on CHAR trimming: DBF character fields are space-padded. The
// caller decides whether to trim (via a SELECT-list AllTrim wrapper).
// We don't trim here — that's a semantic choice, and callers who need
// raw bytes shouldn't pay for a strings.TrimSpace().
func SqlScan(t *hbrt.Thread) {
t.Frame(2, 0)
defer t.EndProc()
// Parse arguments
fieldsVal := t.Local(1)
if !fieldsVal.IsArray() {
t.PushValue(hbrt.MakeArray(0))
t.RetValue()
return
}
fieldsArr := fieldsVal.AsArray().Items
nFields := len(fieldsArr)
whereVal := t.Local(2)
var whereFn *hbrt.PcodeFunc
if !whereVal.IsNil() {
if p := whereVal.AsPointer(); p != nil {
whereFn, _ = p.(*hbrt.PcodeFunc)
}
}
// Pre-convert field positions to []int (avoid Value->int per row)
fieldPos := make([]int, nFields)
for i := 0; i < nFields; i++ {
fieldPos[i] = int(fieldsArr[i].AsNumInt())
if fieldPos[i] < 1 {
fieldPos[i] = 1
}
}
wam, ok := t.WA.(*hbrdd.WorkAreaManager)
if !ok {
t.PushValue(hbrt.MakeArray(0))
t.RetValue()
return
}
area := wam.Current()
if area == nil {
t.PushValue(hbrt.MakeArray(0))
t.RetValue()
return
}
// Pre-allocate result: 50k × small-row header pressure matters
rows := make([]hbrt.Value, 0, 1024)
// Scan
area.GoTop()
for !area.EOF() {
// WHERE evaluation (if any)
keep := true
if whereFn != nil {
hbrt.ExecPcode(t, whereFn, nil)
keep = t.GetRetValue().AsBool()
}
if keep {
// Collect column values
row := make([]hbrt.Value, nFields)
for i := 0; i < nFields; i++ {
// GetValue is 0-based
v, _ := area.GetValue(fieldPos[i] - 1)
row[i] = v
}
rows = append(rows, hbrt.MakeArrayFrom(row))
}
area.Skip(1)
}
t.PushValue(hbrt.MakeArrayFrom(rows))
t.RetValue()
}