Repeated map values can take less room as a count and a value—but only if the output buffer is big enough.
Use it in a project
INPUT_COUNT selects 0–8 bytes B0–B7. Encode consecutive equal values as positive count/value byte pairs in R0–R15, up to CAPACITY 0–16. Preflight all runs before writing. Invalid bounds return VALID=0, ERROR=1; insufficient output returns VALID=1, ERROR=2. Both failures leave output bytes unchanged and WRITTEN=0. Success returns ERROR=0 and the even byte count; unused output bytes are preserved.
Include component.inc once (MOS callers include the shared 6502 implementation through it). Reserve the public fields in this exact order: WRITTEN, ERROR, VALID, INPUT_COUNT, CAPACITY, B0, B1, B2, B3, B4, B5, B6, B7, R0, R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, R12, R13, R14, R15. They occupy 29 contiguous bytes. Also reserve the private workspace: T0, T1, T2, T3, T4, EXPR_SAVE (6 bytes). Array names in the explanation refer to the numbered consecutive bindings, such as C0, C1 and so on.
Call bounded_rle_encoder_init once at the intended reset boundary. It clears inputs as well as outputs and workspace. Set your starting state and configuration afterwards, then call bounded_rle_encoder_step whenever the described event occurs. The helper reads no device, waits for no frame and installs no interrupt handler.
| Ownership | Fields |
|---|---|
| Retain between calls | R0–R15 as the owned destination |
| Supply before service | INPUT_COUNT, CAPACITY and B0–B7 |
| Read after service | WRITTEN, ERROR and VALID |
A first pass counts runs and proves that every pair will fit. A second pass writes the pairs. That extra scan gives the caller an all-or-nothing output contract.
Reusable initialisation and service
; SPDX-License-Identifier: MIT
; Encode a Small Run-length Block. See README.md for the byte interface and ownership.
; init clears the public fields and private workspace; set inputs afterwards.
bounded_rle_encoder_init:
ld a,0
ld (WRITTEN),a
ld (ERROR),a
ld (VALID),a
ld (INPUT_COUNT),a
ld (CAPACITY),a
ld (B0),a
ld (B1),a
ld (B2),a
ld (B3),a
ld (B4),a
ld (B5),a
ld (B6),a
ld (B7),a
ld (R0),a
ld (R1),a
ld (R2),a
ld (R3),a
ld (R4),a
ld (R5),a
ld (R6),a
ld (R7),a
ld (R8),a
ld (R9),a
ld (R10),a
ld (R11),a
ld (R12),a
ld (R13),a
ld (R14),a
ld (R15),a
ld (T0),a
ld (T1),a
ld (T2),a
ld (T3),a
ld (T4),a
ld (EXPR_SAVE),a
ret
bounded_rle_encoder_step:
; WRITTEN = 0
ld a,0
ld (WRITTEN),a
; ERROR = 1
ld a,1
ld (ERROR),a
; VALID = 0
ld a,0
ld (VALID),a
; if INPUT_COUNT > 8:
ld a,(INPUT_COUNT)
cp 8
jp z,bounded_rle_encoder_L2
jp nc,bounded_rle_encoder_L1
jp bounded_rle_encoder_L2
bounded_rle_encoder_L1:
; return
ret
jp bounded_rle_encoder_L3
bounded_rle_encoder_L2:
bounded_rle_encoder_L3:
; if CAPACITY > 16:
ld a,(CAPACITY)
cp 16
jp z,bounded_rle_encoder_L5
jp nc,bounded_rle_encoder_L4
jp bounded_rle_encoder_L5
bounded_rle_encoder_L4:
; return
ret
jp bounded_rle_encoder_L6
bounded_rle_encoder_L5:
bounded_rle_encoder_L6:
; VALID = 1
ld a,1
ld (VALID),a
; ERROR = 0
ld a,0
ld (ERROR),a
; if INPUT_COUNT == 0:
ld a,(INPUT_COUNT)
cp 0
jp z,bounded_rle_encoder_L7
jp bounded_rle_encoder_L8
bounded_rle_encoder_L7:
; return
ret
jp bounded_rle_encoder_L9
bounded_rle_encoder_L8:
bounded_rle_encoder_L9:
; T0 = 1
ld a,1
ld (T0),a
; T1 = B[0]
ld a,0
ld e,a
ld d,0
ld hl,B0
add hl,de
ld a,(hl)
ld (T1),a
; T2 = 1
ld a,1
ld (T2),a
; while T0 < INPUT_COUNT:
bounded_rle_encoder_L10:
ld a,(T0)
ld b,a
ld a,(INPUT_COUNT)
ld c,a
ld a,b
cp c
jp c,bounded_rle_encoder_L11
jp bounded_rle_encoder_L12
bounded_rle_encoder_L11:
; T3 = B[T0]
ld a,(T0)
ld e,a
ld d,0
ld hl,B0
add hl,de
ld a,(hl)
ld (T3),a
; if T3 != T1:
ld a,(T3)
ld b,a
ld a,(T1)
ld c,a
ld a,b
cp c
jp nz,bounded_rle_encoder_L13
jp bounded_rle_encoder_L14
bounded_rle_encoder_L13:
; T2 = T2 + 1
ld a,(T2)
add a,1
ld (T2),a
; T1 = T3
ld a,(T3)
ld (T1),a
jp bounded_rle_encoder_L15
bounded_rle_encoder_L14:
bounded_rle_encoder_L15:
; T0 = T0 + 1
ld a,(T0)
add a,1
ld (T0),a
jp bounded_rle_encoder_L10
bounded_rle_encoder_L12:
; T2 = T2 << 1
ld a,(T2)
sla a
ld (T2),a
; if T2 > CAPACITY:
ld a,(T2)
ld b,a
ld a,(CAPACITY)
ld c,a
ld a,b
cp c
jp z,bounded_rle_encoder_L17
jp nc,bounded_rle_encoder_L16
jp bounded_rle_encoder_L17
bounded_rle_encoder_L16:
; ERROR = 2
ld a,2
ld (ERROR),a
; return
ret
jp bounded_rle_encoder_L18
bounded_rle_encoder_L17:
bounded_rle_encoder_L18:
; T0 = 0
ld a,0
ld (T0),a
; T1 = 0
ld a,0
ld (T1),a
; while T0 < INPUT_COUNT:
bounded_rle_encoder_L19:
ld a,(T0)
ld b,a
ld a,(INPUT_COUNT)
ld c,a
ld a,b
cp c
jp c,bounded_rle_encoder_L20
jp bounded_rle_encoder_L21
bounded_rle_encoder_L20:
; T2 = B[T0]
ld a,(T0)
ld e,a
ld d,0
ld hl,B0
add hl,de
ld a,(hl)
ld (T2),a
; T3 = 1
ld a,1
ld (T3),a
; T0 = T0 + 1
ld a,(T0)
add a,1
ld (T0),a
; while T0 < INPUT_COUNT:
bounded_rle_encoder_L22:
ld a,(T0)
ld b,a
ld a,(INPUT_COUNT)
ld c,a
ld a,b
cp c
jp c,bounded_rle_encoder_L23
jp bounded_rle_encoder_L24
bounded_rle_encoder_L23:
; T4 = B[T0]
ld a,(T0)
ld e,a
ld d,0
ld hl,B0
add hl,de
ld a,(hl)
ld (T4),a
; if T4 != T2:
ld a,(T4)
ld b,a
ld a,(T2)
ld c,a
ld a,b
cp c
jp nz,bounded_rle_encoder_L25
jp bounded_rle_encoder_L26
bounded_rle_encoder_L25:
; break
jp bounded_rle_encoder_L24
jp bounded_rle_encoder_L27
bounded_rle_encoder_L26:
bounded_rle_encoder_L27:
; T3 = T3 + 1
ld a,(T3)
add a,1
ld (T3),a
; T0 = T0 + 1
ld a,(T0)
add a,1
ld (T0),a
jp bounded_rle_encoder_L22
bounded_rle_encoder_L24:
; R[T1] = T3
ld a,(T3)
ld c,a
ld a,(T1)
ld e,a
ld d,0
ld hl,R0
add hl,de
ld (hl),c
; T1 = T1 + 1
ld a,(T1)
add a,1
ld (T1),a
; R[T1] = T2
ld a,(T2)
ld c,a
ld a,(T1)
ld e,a
ld d,0
ld hl,R0
add hl,de
ld (hl),c
; T1 = T1 + 1
ld a,(T1)
add a,1
ld (T1),a
jp bounded_rle_encoder_L19
bounded_rle_encoder_L21:
; WRITTEN = T1
ld a,(T1)
ld (WRITTEN),a
ret
component_end:Machine contract
AF/BC/DE/HL may change; IX/IY are preserved. A direct CALL needs two return-address stack bytes. The helper makes no nested calls and adds no other stack use. Its named scratch is private workspace, not a pointer, a ROM variable or shared zero-page space that the game may borrow concurrently. The samples use fixed symbol bindings. Scope or rename every label and binding, including the component_end measurement marker, and allocate a separate block for each independent instance. Different helpers can also use common field names, so combining them needs separate namespaces or explicitly renamed bindings. Give each block one mutation owner.
The 48K diagnostic boots through ROM tape loading and USR, disables interrupts and owns the screen. The helper performs no port or screen writes.
Adapt the caller
demo.asm supplies the bindings and include order. exercise.inc first runs table cases, then a separate client retaining state between calls. A game can call the public step entry directly and remove the diagnostic packet and display. Do not copy the diagnostic’s hardware takeover into an existing game loop.
Build with make ASM198X=/path/to/asm198x. The Makefile produces normal, custom, deliberately wrong and repaired programs. Tools must already be installed; the sample downloads nothing.
Bindings and include order
org $8000
CUSTOM equ 0
BROKEN equ 0
COYOTE_STEPS equ 4
BUFFER_STEPS equ 4
TEXT_CAP equ 8
PROPERTY_COUNT equ 16
STREAM_BYTES equ 13
CRC_POLY equ 7
include "caller.inc"
include "exercise.inc"
component_start:
include "component.inc"
include "data.inc"
include "cases.inc"
include "../../physics/rectangle-overlap/display.inc"
code_end:
STATE:
WRITTEN: defb 0
ERROR: defb 0
VALID: defb 0
INPUT_COUNT: defb 0
CAPACITY: defb 0
B0: defb 0
B1: defb 0
B2: defb 0
B3: defb 0
B4: defb 0
B5: defb 0
B6: defb 0
B7: defb 0
R0: defb 0
R1: defb 0
R2: defb 0
R3: defb 0
R4: defb 0
R5: defb 0
R6: defb 0
R7: defb 0
R8: defb 0
R9: defb 0
R10: defb 0
R11: defb 0
R12: defb 0
R13: defb 0
R14: defb 0
R15: defb 0
T0: defb 0
T1: defb 0
T2: defb 0
T3: defb 0
T4: defb 0
EXPR_SAVE: defb 0
input_ptr: defw 0
output_ptr: defw 0
cases_left: defb 0
ready: defb 0
preview: defs 8,0
OUTPUT: defs 1300,0
end startA client retaining state between calls
preview_rules:
if CUSTOM
; INPUT_COUNT = 8
ld a,8
ld (INPUT_COUNT),a
; CAPACITY = 16
ld a,16
ld (CAPACITY),a
; B0 = 0
ld a,0
ld (B0),a
; B1 = 1
ld a,1
ld (B1),a
; B2 = 2
ld a,2
ld (B2),a
; B3 = 3
ld a,3
ld (B3),a
; B4 = 4
ld a,4
ld (B4),a
; B5 = 5
ld a,5
ld (B5),a
; B6 = 6
ld a,6
ld (B6),a
; B7 = 7
ld a,7
ld (B7),a
if BROKEN
; CAPACITY = 0
ld a,0
ld (CAPACITY),a
endif
call checked_step
call emit_state
ret
else
; INPUT_COUNT = 6
ld a,6
ld (INPUT_COUNT),a
; CAPACITY = 16
ld a,16
ld (CAPACITY),a
; B0 = 65
ld a,65
ld (B0),a
; B1 = 65
ld a,65
ld (B1),a
; B2 = 65
ld a,65
ld (B2),a
; B3 = 66
ld a,66
ld (B3),a
; B4 = 66
ld a,66
ld (B4),a
; B5 = 67
ld a,67
ld (B5),a
if BROKEN
; CAPACITY = 0
ld a,0
ld (CAPACITY),a
endif
call checked_step
call emit_state
endif
retCustomise it
Encode eight distinct values, the worst expansion for this small block. The maintained custom caller changes its inputs or client sequence rather than hiding a different implementation behind the same label. Compare every state of the two clients, not only their final display.
Custom client selection
org $8000
CUSTOM equ 1
BROKEN equ 0
COYOTE_STEPS equ 2
BUFFER_STEPS equ 2
TEXT_CAP equ 4
PROPERTY_COUNT equ 16
STREAM_BYTES equ 13
CRC_POLY equ 49
include "caller.inc"
include "exercise.inc"
component_start:
include "component.inc"
include "data.inc"
include "cases.inc"
include "../../physics/rectangle-overlap/display.inc"
code_end:
STATE:
WRITTEN: defb 0
ERROR: defb 0
VALID: defb 0
INPUT_COUNT: defb 0
CAPACITY: defb 0
B0: defb 0
B1: defb 0
B2: defb 0
B3: defb 0
B4: defb 0
B5: defb 0
B6: defb 0
B7: defb 0
R0: defb 0
R1: defb 0
R2: defb 0
R3: defb 0
R4: defb 0
R5: defb 0
R6: defb 0
R7: defb 0
R8: defb 0
R9: defb 0
R10: defb 0
R11: defb 0
R12: defb 0
R13: defb 0
R14: defb 0
R15: defb 0
T0: defb 0
T1: defb 0
T2: defb 0
T3: defb 0
T4: defb 0
EXPR_SAVE: defb 0
input_ptr: defw 0
output_ptr: defw 0
cases_left: defb 0
ready: defb 0
preview: defs 8,0
OUTPUT: defs 1300,0
end startThe custom diagnostic row is 10 00 01 08 10 00 01 02. The full client trace in the source explains how it gets there.
Mistake and repair
The wrong caller passes no output capacity for a nonempty block. The encoder rejects the whole request and preserves its output buffer. Pass the actual reserved capacity, rather than a count that has not yet been filled.
The BROKEN branch lives in the sequential client, not the reusable helper. wrong.asm selects it; repaired.asm restores the normal call sequence. The repaired executable matches the normal program (for Spectrum, compare loaded CODE rather than the tape filename).
Select the deliberately wrong client
org $8000
CUSTOM equ 0
BROKEN equ 1
COYOTE_STEPS equ 4
BUFFER_STEPS equ 4
TEXT_CAP equ 8
PROPERTY_COUNT equ 16
STREAM_BYTES equ 13
CRC_POLY equ 7
include "caller.inc"
include "exercise.inc"
component_start:
include "component.inc"
include "data.inc"
include "cases.inc"
include "../../physics/rectangle-overlap/display.inc"
code_end:
STATE:
WRITTEN: defb 0
ERROR: defb 0
VALID: defb 0
INPUT_COUNT: defb 0
CAPACITY: defb 0
B0: defb 0
B1: defb 0
B2: defb 0
B3: defb 0
B4: defb 0
B5: defb 0
B6: defb 0
B7: defb 0
R0: defb 0
R1: defb 0
R2: defb 0
R3: defb 0
R4: defb 0
R5: defb 0
R6: defb 0
R7: defb 0
R8: defb 0
R9: defb 0
R10: defb 0
R11: defb 0
R12: defb 0
R13: defb 0
R14: defb 0
R15: defb 0
T0: defb 0
T1: defb 0
T2: defb 0
T3: defb 0
T4: defb 0
EXPR_SAVE: defb 0
input_ptr: defw 0
output_ptr: defw 0
cases_left: defb 0
ready: defb 0
preview: defs 8,0
OUTPUT: defs 1300,0
end start
Cost and alternatives
The measured helper extent is 497 code bytes; public state is 29 bytes and private scratch is 6 bytes. There are no immutable helper tables. Caller data, the test cases, return-address stack, alignment and display buffers cost additional space. These are assembled sizes, not cycle measurements.
Two bounded scans over at most eight bytes, plus sixteen destination writes in the worst case. A streaming encoder can avoid preflight but must report partial output and support continuation explicitly.
RLE can expand data: eight distinct bytes need sixteen encoded bytes. This uses the existing count/value idea, not a new project-wide asset container. A decoder must still validate its own lengths and output bounds.
Execution evidence
Four variants run on 48K PAL ROM tape load and USR, using Asm198x 0.0.72, Emu198x 0.44.2. Each executes 34 boundary/varied/error table cases, dirty initialisation and the separate retained-state client. An independent mathematical/container model checks every public byte after every call. This is bounded example coverage, not exhaustive correctness for every possible state.
The records retain loaded immutable code, completion, register sentinels, full packets, source/tool/firmware hashes and captures. The public gate validates these retained observations and rejects altered evidence; it does not run restricted firmware. No firmware is distributed. The eight displayed bytes are the first eight public fields, zero-padded when shorter; the packet includes every field.
Where it fits
Bounded RLE decoding: Encoding and decoding share count/value semantics but need different buffer and failure contracts.