AnachronautandClaude Opus 5
373454ec00
A fixture built by makedisks.sh was handed to each test where it lay. Twenty four tests name disks/cosmos.img and several of them write to one, so a test could hand the next one a disk with its leavings on. romBoot is what found it. Its recorded output described a directory that selfBoot had made earlier in the same run, so it passed in a full run and failed on its own - which is the worst way round for a test to be wrong, because the form nobody runs is the one telling the truth. Its recording now says "made" like selfBoot's, which is what running the same input on the same disk should always have said. Fixed as a class rather than as an instance: run.sh copies a fixture before attaching it, the same way it already removed a scratch image. Then every one of the 138 run and rom tests was run on its own to see whether anything else was leaning on what ran before it. Nothing was, before or after. Also, cosmosEditKeys.in was written by Python's write_text, which encodes as UTF-8, so every key byte was 0xC2 and then the key. The test passed anyway, because the shell ignores a byte it has no use for - a fixture working for a reason it was not built on, which is exactly the thing that stops working without anybody touching it. Written as bytes now; the recording is unchanged, which is the proof the stray bytes were being ignored. docs.sh is what caught that, and it turns out to draw the line in the right place by construction: a deliberately binary fixture does not decode as UTF-8 and is skipped, while one that is accidentally UTF-8 decodes and is reported. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01E2JrLzFvuFX9fgi1LDRjrW
347 lines
14 KiB
Bash
Executable File
347 lines
14 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# run.sh
|
|
# Test runner for the SplitBit Emulator and Assembler.
|
|
# Written by Anachronaut
|
|
#
|
|
# Assembles and runs every program listed in Tests/manifest and compares the
|
|
# output against the recorded results in Tests/expected.
|
|
#
|
|
# ./Tests/run.sh Run the suite.
|
|
# ./Tests/run.sh --bless Record current output as the expected results.
|
|
# ./Tests/run.sh <name>... Run only the named tests.
|
|
#
|
|
# Programs are built inside Tests/build so that running the suite never touches
|
|
# the binaries in Programs/.
|
|
|
|
set -u
|
|
|
|
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
|
TESTS="$ROOT/Tests"
|
|
BUILD="$TESTS/build"
|
|
EXPECTED="$TESTS/expected"
|
|
INPUT="$TESTS/input"
|
|
MANIFEST="$TESTS/manifest"
|
|
|
|
ASSEMBLER="$ROOT/Assembler"
|
|
|
|
# ---- Which machine runs the programs ----
|
|
#
|
|
# SplitBit unless something says otherwise. Tests/voyager.sh sets these to run the whole
|
|
# manifest through the OTHER front end and hold it to the same recorded results, which is
|
|
# the strongest thing that can be said about the two of them: not that they look alike, but
|
|
# that one satisfies every recording the other does. Doing it this way rather than by
|
|
# copying this file means the two can never be tested differently by accident.
|
|
EMULATOR="${SPLITBIT_EMULATOR:-$ROOT/SplitBit}"
|
|
read -r -a EMULATOR_EXTRA <<< "${SPLITBIT_EMULATOR_ARGS:-}"
|
|
|
|
RUN_TIMEOUT=10
|
|
|
|
BLESS=0
|
|
ONLY=()
|
|
|
|
for arg in "$@"; do
|
|
case "$arg" in
|
|
--bless) BLESS=1 ;;
|
|
-h|--help)
|
|
sed -n '3,14p' "${BASH_SOURCE[0]}" | sed 's/^# \{0,1\}//'
|
|
exit 0
|
|
;;
|
|
-*) echo "run.sh: unknown option $arg" >&2; exit 2 ;;
|
|
*) ONLY+=("$arg") ;;
|
|
esac
|
|
done
|
|
|
|
for tool in "$ASSEMBLER" "$EMULATOR"; do
|
|
if [ ! -x "$tool" ]; then
|
|
echo "run.sh: $tool is missing. Run 'make' first." >&2
|
|
exit 2
|
|
fi
|
|
done
|
|
|
|
PROGRAMS="$ROOT/Programs"
|
|
|
|
rm -rf "$BUILD"
|
|
mkdir -p "$BUILD" "$EXPECTED"
|
|
|
|
# Disk images the tests read from are built here, with the host tool, before anything
|
|
# runs. The build directory is thrown away above, so they are always freshly made.
|
|
if [ -x "$TESTS/makedisks.sh" ]; then
|
|
"$TESTS/makedisks.sh" "$BUILD" || { echo "Couldn't build the test disks."; exit 1; }
|
|
fi
|
|
|
|
PASS=0
|
|
FAIL=0
|
|
BLESSED=0
|
|
FAILED_NAMES=()
|
|
|
|
wanted() {
|
|
[ ${#ONLY[@]} -eq 0 ] && return 0
|
|
local n
|
|
for n in "${ONLY[@]}"; do [ "$n" = "$1" ] && return 0; done
|
|
return 1
|
|
}
|
|
|
|
report() {
|
|
# report <status> <name> <detail>
|
|
printf ' [%-4s] %-20s %s\n' "$1" "$2" "$3"
|
|
}
|
|
|
|
trim() {
|
|
local v="$1"
|
|
v="${v#"${v%%[![:space:]]*}"}"
|
|
v="${v%"${v##*[![:space:]]}"}"
|
|
printf '%s' "$v"
|
|
}
|
|
|
|
# Takes the cycle count out of the emulator's last line, in place.
|
|
#
|
|
# HOW MANY CYCLES A PROGRAM TOOK IS NOT WHAT ANY OF THESE TESTS ARE ABOUT, and having it in
|
|
# every recorded result made every one of them fragile in the same way: two instructions
|
|
# added to CosmOS moved the count in six unrelated files at once, so a real difference
|
|
# would have arrived in a crowd of meaningless ones and had to be picked out by hand.
|
|
#
|
|
# WHETHER a program stopped on its own or ran into its limit is kept, because that is
|
|
# behaviour and several tests exist to check it. Only the number goes.
|
|
#
|
|
# Anything that genuinely wants to measure cycles should say so out loud in a test of its
|
|
# own rather than every test carrying the measurement and nothing asserting anything about
|
|
# it.
|
|
settle() {
|
|
# NOT ANCHORED TO THE START OF A LINE. A program whose last output has no newline on it
|
|
# leaves the cursor mid line, and the halt message is printed there - so the count this
|
|
# exists to remove was sitting inside a line rather than at the head of one, and
|
|
# survived. replCalculator is the one that does that, and it was the only test to churn
|
|
# when the machine started charging for memory instead of counting instructions.
|
|
sed -i -E 's/Execution halted after [0-9]+ cycles, [0-9]+ of them waiting\./Execution halted./;
|
|
s/Execution halted after [0-9]+ cycles\./Execution halted./;
|
|
s/Execution stopped after [0-9]+ cycles\. \(cycle limit reached\)/Execution stopped. (cycle limit reached)/' "$1"
|
|
}
|
|
|
|
check() {
|
|
# check <name> <actual-file>
|
|
local name="$1" actual="$2" golden="$EXPECTED/$1.out"
|
|
if [ "$BLESS" -eq 1 ]; then
|
|
cp "$actual" "$golden"
|
|
BLESSED=$((BLESSED + 1))
|
|
report "rec" "$name" "$(wc -c < "$golden" | tr -d ' ') bytes recorded"
|
|
return 0
|
|
fi
|
|
if [ ! -f "$golden" ]; then
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "no recorded output; run with --bless"
|
|
return 1
|
|
fi
|
|
if cmp -s "$actual" "$golden"; then
|
|
PASS=$((PASS + 1))
|
|
report "ok" "$name" ""
|
|
return 0
|
|
fi
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "output differs"
|
|
diff -u "$golden" "$actual" 2>/dev/null | head -20 | sed 's/^/ /'
|
|
return 1
|
|
}
|
|
|
|
assemble() {
|
|
# assemble <name> <source>; echoes the built binary path on success.
|
|
# Everything builds from Programs/ with Libraries/ and CosmOS/ on the include path,
|
|
# and the binary goes to Tests/build, so the source tree is never written to.
|
|
# CosmOS is there because it owns the filesystem library and the service names, which
|
|
# test programs outside it include.
|
|
local name="$1" src="$2"
|
|
local bin="$BUILD/$name.bin"
|
|
( cd "$PROGRAMS" && "$ASSEMBLER" -I Libraries -I CosmOS/Source -o "$bin" "$src" ) \
|
|
>"$BUILD/.assemble.log" 2>&1
|
|
# WRITTEN TO A FILE RATHER THAN A VARIABLE, because this function is called inside a
|
|
# command substitution below and that runs it in a subshell, where anything it set
|
|
# would be thrown away. A file is the one channel that survives either call site.
|
|
echo $? > "$BUILD/.assemble.status"
|
|
if [ "$(cat "$BUILD/.assemble.status")" -eq 0 ]; then
|
|
echo "$bin"
|
|
return 0
|
|
fi
|
|
return 1
|
|
}
|
|
|
|
# Takes the colour out of a diagnostic, in place. The assembler paints its errors whether
|
|
# or not anything is a terminal, so a recorded refusal would otherwise carry escape
|
|
# sequences - and a recorded result full of them is unreadable in a diff, which is the one
|
|
# moment it has to be read.
|
|
uncolour() {
|
|
sed -i -E 's/\x1b\[[0-9;]*m//g' "$1"
|
|
}
|
|
|
|
while IFS='|' read -r name src mode stdin limit disk keys; do
|
|
name="$(trim "$name")"
|
|
[ -z "$name" ] && continue
|
|
case "$name" in \#*) continue ;; esac
|
|
src="$(trim "$src")"
|
|
mode="$(trim "$mode")"; stdin="$(trim "$stdin")"
|
|
limit="$(trim "$limit")"; disk="$(trim "$disk")"
|
|
keys="$(trim "${keys:-}")"
|
|
[ -z "$disk" ] && disk="-"
|
|
[ -z "$keys" ] && keys="-"
|
|
|
|
wanted "$name" || continue
|
|
|
|
if [ "$mode" = "xfail" ]; then
|
|
if assemble "$name" "$src" >/dev/null; then
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "expected assembly to fail, but it succeeded"
|
|
continue
|
|
fi
|
|
# WHAT IT SAID, not merely that it said something. Checking only that the assembler
|
|
# exited non zero passed for the intended error, for an unrelated error, for a
|
|
# changed message, and for the assembler falling over on its way to the point - all
|
|
# four look identical from outside. So the diagnostic is recorded and compared like
|
|
# any other output, which is what the Test Manual has always claimed happened here.
|
|
OUT="$BUILD/.out"
|
|
cp "$BUILD/.assemble.log" "$OUT"
|
|
uncolour "$OUT"
|
|
# The same last line every other recorded result carries, and for the same reason:
|
|
# which non zero status a refusal exits with is part of what it does.
|
|
printf '[exit %d]\n' "$(cat "$BUILD/.assemble.status")" >> "$OUT"
|
|
check "$name" "$OUT"
|
|
continue
|
|
fi
|
|
|
|
if ! BIN="$(assemble "$name" "$src")"; then
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "assembly failed"
|
|
head -3 "$BUILD/.assemble.log" | tr -d '\033' | sed 's/\[[0-9;]*m//g' | sed 's/^/ /'
|
|
continue
|
|
fi
|
|
|
|
if [ "$mode" = "assemble" ]; then
|
|
PASS=$((PASS + 1))
|
|
report "ok" "$name" "assembles"
|
|
continue
|
|
fi
|
|
|
|
if [ "$stdin" != "-" ] && [ ! -f "$INPUT/$stdin" ]; then
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "missing input fixture $stdin"
|
|
continue
|
|
fi
|
|
IN=/dev/null
|
|
[ "$stdin" != "-" ] && IN="$INPUT/$stdin"
|
|
|
|
OUT="$BUILD/.out"
|
|
case "$mode" in
|
|
run|rom)
|
|
# --fast because there is nothing to learn from waiting out the emulated
|
|
# clock, and --cycles for programs that never halt on their own, which
|
|
# bounds them by cycle count rather than by wall clock.
|
|
EMUARGS=(--fast "${EMULATOR_EXTRA[@]}")
|
|
# ---- A file standing in for a keyboard ----
|
|
#
|
|
# Not the same as standard input, and that is the whole point of it. Input from a
|
|
# file reaches a console that believes a terminal is doing the line editing; a
|
|
# keyboard reaches one that knows it has to do the editing itself, which is what
|
|
# happens behind a window. The second had no test at all until it broke twice.
|
|
if [ "$keys" != "-" ]; then
|
|
if [ ! -f "$INPUT/$keys" ]; then
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "missing keyboard fixture $keys"
|
|
continue
|
|
fi
|
|
EMUARGS+=(--keyboard "$INPUT/$keys")
|
|
fi
|
|
[ "$limit" != "-" ] && EMUARGS+=(--cycles "$limit")
|
|
# A disk starts fresh for every test, so a test cannot pass because of what a
|
|
# previous one left lying on it. How that is arranged differs between a scratch
|
|
# image and a built fixture, and both are below.
|
|
# ---- More than one, separated by a plus ----
|
|
#
|
|
# The machine has four drives, so a test may name up to four images and they
|
|
# become drives 0 upwards in the order written. Each keeps its own :ro and @N,
|
|
# because those are properties of a disk rather than of the machine.
|
|
for onedisk in ${disk//+/ }; do
|
|
# ---- A drive made of memory ----
|
|
#
|
|
# "ram:2048" asks for one of that many blocks instead of naming an image. It has
|
|
# no file behind it, so there is nothing to remove between runs and nothing to
|
|
# go stale: it is zeroes every time by construction.
|
|
case "$onedisk" in
|
|
ram:*) EMUARGS+=(--ram-disk "${onedisk#ram:}"); onedisk="-" ;;
|
|
esac
|
|
if [ "$onedisk" != "-" ]; then
|
|
# A trailing :ro attaches the image write protected, so that a test can
|
|
# check the device bars writes rather than the filesystem asking nicely.
|
|
DISKFILE="${onedisk%:ro}"
|
|
# And a trailing @N gives the disk a latency, so that a test can check the
|
|
# filesystem waits for it. Every other test runs with the answer there
|
|
# before the next instruction, which is the one condition under which not
|
|
# waiting looks like working.
|
|
DISKWAIT=""
|
|
case "$DISKFILE" in
|
|
*@*) DISKWAIT="${DISKFILE##*@}"; DISKFILE="${DISKFILE%@*}" ;;
|
|
esac
|
|
# ---- A fresh disk for every test, whichever kind it is ----
|
|
#
|
|
# A bare name is scratch: it is removed, and the emulator makes a blank image
|
|
# in its place.
|
|
#
|
|
# A name with a directory in it is one of the images makedisks.sh built, and
|
|
# it is COPIED rather than used where it lies. Twenty four tests name
|
|
# disks/cosmos.img and several of them write to it, so a test used to be able
|
|
# to hand the next one a disk with its leavings on. That is not hypothetical:
|
|
# romBoot's recorded output described a directory that selfBoot had made, so
|
|
# it passed in a full run and failed on its own, which is the worst way round
|
|
# for a test to be wrong.
|
|
case "$DISKFILE" in
|
|
*/*)
|
|
mkdir -p "$BUILD/.fixture"
|
|
cp "$BUILD/$DISKFILE" "$BUILD/.fixture/${DISKFILE##*/}"
|
|
DISKFILE=".fixture/${DISKFILE##*/}"
|
|
;;
|
|
*) rm -f "$BUILD/$DISKFILE" ;;
|
|
esac
|
|
EMUARGS+=(--disk "$BUILD/$DISKFILE")
|
|
[ -n "$DISKWAIT" ] && EMUARGS+=(--disk-cycles "$DISKWAIT")
|
|
case "$onedisk" in *:ro) EMUARGS+=(--write-protect) ;; esac
|
|
fi
|
|
done
|
|
# A rom test names no image. The emulator then shadows its built in stage
|
|
# one into Program Memory and reads the disk for everything else, which is
|
|
# what a machine with no debugger attached does.
|
|
if [ "$mode" = "rom" ]; then
|
|
timeout "$RUN_TIMEOUT" "$EMULATOR" "${EMUARGS[@]}" <"$IN" >"$OUT" 2>&1
|
|
else
|
|
timeout "$RUN_TIMEOUT" "$EMULATOR" "${EMUARGS[@]}" "$BIN" <"$IN" >"$OUT" 2>&1
|
|
fi
|
|
STATUS=$?
|
|
if [ "$STATUS" -eq 124 ]; then
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "did not finish within ${RUN_TIMEOUT}s"
|
|
continue
|
|
fi
|
|
# What a program exits with is part of what it does, so it is recorded
|
|
# with the output rather than thrown away. A program that faults is
|
|
# supposed to exit non zero, and that should be just as pinned down as
|
|
# what it printed.
|
|
printf '[exit %d]\n' "$STATUS" >> "$OUT"
|
|
settle "$OUT"
|
|
check "$name" "$OUT"
|
|
;;
|
|
*)
|
|
FAIL=$((FAIL + 1)); FAILED_NAMES+=("$name")
|
|
report "FAIL" "$name" "unknown mode '$mode' in manifest"
|
|
;;
|
|
esac
|
|
done < "$MANIFEST"
|
|
|
|
echo
|
|
if [ "$BLESS" -eq 1 ]; then
|
|
echo "Recorded $BLESSED expected results into Tests/expected."
|
|
exit 0
|
|
fi
|
|
WHICH=""
|
|
[ "$EMULATOR" = "$ROOT/SplitBit" ] || WHICH=" under $(basename "$EMULATOR")"
|
|
if [ "$FAIL" -eq 0 ]; then
|
|
echo "All $PASS tests passed$WHICH."
|
|
exit 0
|
|
fi
|
|
echo "$PASS passed, $FAIL failed$WHICH: ${FAILED_NAMES[*]}"
|
|
exit 1
|