#!/usr/bin/env bash
# Checks the assembler that runs on SplitBit against the one that runs on the host.
#
# THE ONLY HONEST TEST OF AN ASSEMBLER IS THE BYTES IT PRODUCES. "It ran" and "the sizes
# look right" both pass for a binary with a label one byte out, which is a program that
# jumps into the middle of an instruction. So this assembles the same source both ways and
# compares the two files byte for byte, the same discipline SplitDisk and sbfs.asm work
# under: two implementations of one written specification, each one checking the other.
#
# Then it runs what the machine built, because a file that matches and does not work would
# mean both assemblers were wrong together.
#
# It checks a boot image and four loadable programs. The loadable ones are the harder case:
# they include another file, they are based somewhere other than zero, and every service
# they call is a name declared in that included file. The last of them also brings a vector,
# which is the only thing here that asks anything of its loader.
#
# Written by Anachronaut

set -u
ROOT="$(cd "$(dirname "$0")/.." && pwd)"
WORK="$ROOT/Tests/build/native"
ASM="$ROOT/Assembler"
TOOL="$ROOT/SplitDisk"
EMU="$ROOT/SplitBit"

PASS=0
FAIL=0
FAILED_NAMES=()

check() {
    local name="$1"
    shift
    if "$@"; then
        printf '  [ok  ] %-22s %s\n' "$name" "${REPORT:-}"
        PASS=$((PASS + 1))
    else
        printf '  [FAIL] %-22s %s\n' "$name" "${REPORT:-}"
        FAIL=$((FAIL + 1))
        FAILED_NAMES+=("$name")
    fi
    REPORT=""
}

for tool in "$ASM" "$TOOL" "$EMU"; do
    [ -x "$tool" ] || { echo "$(basename "$tool") is not built."; exit 1; }
done

rm -rf "$WORK"
mkdir -p "$WORK"

# The system it runs under, and the assembler itself, both built by the host assembler.
# Bootstrapping has to start somewhere, and this is the last place it does.
"$ASM" -I "$ROOT/Programs/Libraries" -I "$ROOT/Programs/CosmOS/Source" \
    -o "$WORK/cosmos.bin" "$ROOT/Programs/CosmOS/Source/cosmos.asm" >/dev/null || exit 1
"$ASM" -I "$ROOT/Programs/CosmOS/Source" -I "$ROOT/Programs/CosmOS/Assembler" \
    -o "$WORK/Asm.sbx" "$ROOT/Programs/CosmOS/Assembler/Asm.asm" >/dev/null || exit 1

"$TOOL" format "$WORK/native.img" 2048 4 >/dev/null
"$TOOL" put "$WORK/native.img" "$ROOT/Programs/Examples/hello.asm" hello.asm >/dev/null
"$TOOL" put "$WORK/native.img" "$WORK/Asm.sbx" Asm.sbx >/dev/null

# The applications, and the file of service names they all include. These are the reason
# the second milestone exists: an assembler that cannot follow an #Include cannot build
# anything that asks the system for anything.
#
# Keys is the last of them and the hardest: it brings a vector of its own, so it needs a
# Vector Segment in the output and the version two header that says so. Nothing else here
# asks anything of its loader beyond code and data.
APPS="Say greet Files Keys"
"$TOOL" put "$WORK/native.img" "$ROOT/Programs/CosmOS/Source/services.asm" services.asm >/dev/null
"$TOOL" put "$WORK/native.img" "$ROOT/Programs/CosmOS/Source/console.asm" console.asm >/dev/null
for app in $APPS; do
    [ -f "$ROOT/Programs/CosmOS/Apps/$app.asm" ] || continue
    "$TOOL" put "$WORK/native.img" "$ROOT/Programs/CosmOS/Apps/$app.asm" "$app.asm" >/dev/null
done

# ---- A file that ends in the middle of a comment ----
#
# Generated rather than committed, because what makes it work is the ABSENCE of a newline on
# the last line and no editor can be trusted to leave that alone.
#
# An included file running out inside a comment is the case the reader has to pop the include
# stack for, and it is the one shape no source in this repository happens to have: every file
# here ends on a line of code with a newline after it. Nothing exercised that path, so an
# error in it could not be caught - and comment skipping is exactly where such an error would
# live, since a comment is the only thing that reads past the end of a line without looking.
#
# usestail.asm names a label AFTER the include, which is what goes missing if the file that
# did the including is not put back: the include never returns, the rest of the program is
# never read, and the label is never defined.
printf '; nothing but a comment, and no newline after it' > "$WORK/tail.asm"
printf '#Include tail.asm\n#Program\n  #Base 0x5000\nstart:\n  SETD.0 Later\n  HALT\n#Data\n  #Base 0x3000\nLater:\n  0x00\n' > "$WORK/usestail.asm"
"$TOOL" put "$WORK/native.img" "$WORK/tail.asm" tail.asm >/dev/null
"$TOOL" put "$WORK/native.img" "$WORK/usestail.asm" usestail.asm >/dev/null

{
    echo "load Asm.sbx"
    echo "run hello.asm"
    echo "run usestail.asm"
    for app in $APPS; do
        [ -f "$ROOT/Programs/CosmOS/Apps/$app.asm" ] || continue
        echo "run $app.asm"
    done
    echo "exit"
} | "$EMU" --fast --cycles 600000000 -D "$WORK/native.img" "$WORK/cosmos.bin" \
    > "$WORK/session.txt" 2>&1

# ---- It got as far as writing something ----
check "it wrote a file" grep -q "wrote hello.bin" "$WORK/session.txt"

# ---- And a file that ends inside a comment did not swallow the one that included it ----
#
# The label is defined after the #Include, so it exists only if the reader came back.
check "an include that ends in a comment comes back" \
    grep -q "wrote usestail.sbx" "$WORK/session.txt"

# ---- And the file is the one the host assembler makes ----
"$ASM" -o "$WORK/reference.bin" "$ROOT/Programs/Examples/hello.asm" >/dev/null
"$TOOL" get "$WORK/native.img" hello.bin "$WORK/native.bin" >/dev/null 2>&1
if [ -f "$WORK/native.bin" ]; then
    REPORT="$(wc -c < "$WORK/native.bin" | tr -d ' ') bytes"
fi
check "byte for byte" cmp -s "$WORK/native.bin" "$WORK/reference.bin"

# ---- And what it built actually runs ----
"$EMU" --fast --cycles 100000 "$WORK/native.bin" > "$WORK/ran.txt" 2>&1
check "and it runs" grep -q "^Hello, World!$" "$WORK/ran.txt"

# ---- The report it printed says what it did ----
REPORT="$(grep -o 'program [0-9]*, data [0-9]*, labels [0-9]*' "$WORK/session.txt" | head -1 || true)"
check "it counted right" grep -q "program 17, data 14, labels 2" "$WORK/session.txt"

# ---- And the applications, which need an include, a base and the service names ----
#
# A loadable program is the harder case and the one that matters: #Include splices another
# file in, #Base moves every label to where the program will really live, and every SWI in
# them names a vector declared in a file the source never mentions by number.
for app in $APPS; do
    "$ASM" -I "$ROOT/Programs/Libraries" -I "$ROOT/Programs/CosmOS/Source" \
        -o "$WORK/ref-$app.sbx" "$ROOT/Programs/CosmOS/Apps/$app.asm" >/dev/null
    rm -f "$WORK/got-$app.sbx"
    "$TOOL" get "$WORK/native.img" "$app.sbx" "$WORK/got-$app.sbx" >/dev/null 2>&1
    if [ -f "$WORK/got-$app.sbx" ]; then
        REPORT="$(wc -c < "$WORK/got-$app.sbx" | tr -d ' ') bytes"
    fi
    check "$app byte for byte" cmp -s "$WORK/got-$app.sbx" "$WORK/ref-$app.sbx"
done

# ---- Self hosting ----
#
# The two things that make this more than a demonstration: the machine assembling the
# operating system it is running on, and the assembler assembling itself. Both have to come
# out byte for byte identical to what the host tool builds from the same source.
#
# THE FIXED POINT IS THE THIRD CHECK AND THE ONE THAT MATTERS MOST. A binary that matches
# could still have been built by an assembler that is wrong in some way the source happens
# not to exercise; a binary that BUILDS ITSELF AGAIN and comes out the same has been through
# its own machinery. The host is no longer necessary after this point - it is a convenience.

# ---- Read out of cosmos.asm rather than listed here ----
#
# Everything the system includes has to be on the disk it is going to be assembled on. This
# was a hand written list and went stale the moment script.asm was added: the self build
# stopped, saying it could not find a file nobody had thought to put there. That is the
# fourth time a list beside a thing has drifted from the thing, so it is now the thing that
# is asked.
SOURCES="cosmos $(sed -n 's/^#Include \(.*\)\.asm$/\1/p' "$ROOT/Programs/CosmOS/Source/cosmos.asm" | tr '\n' ' ')"
PARTS="Asm numbers source token classify labels vectors table"

"$TOOL" format "$WORK/self.img" 4096 8 >/dev/null
for f in $SOURCES; do
    "$TOOL" put "$WORK/self.img" "$ROOT/Programs/CosmOS/Source/$f.asm" "$f.asm" >/dev/null
done
for f in $PARTS; do
    "$TOOL" put "$WORK/self.img" "$ROOT/Programs/CosmOS/Assembler/$f.asm" "$f.asm" >/dev/null
done
"$TOOL" put "$WORK/self.img" "$WORK/Asm.sbx" Asm.sbx >/dev/null

printf 'load Asm.sbx\nrun cosmos.asm\nrun Asm.asm\nexit\n' \
    | "$EMU" --fast --cycles 4000000000 -D "$WORK/self.img" "$WORK/cosmos.bin" \
    > "$WORK/self.txt" 2>&1

rm -f "$WORK/built-cosmos.bin" "$WORK/built-Asm.sbx"
"$TOOL" get "$WORK/self.img" cosmos.bin "$WORK/built-cosmos.bin" >/dev/null 2>&1
"$TOOL" get "$WORK/self.img" Asm.sbx "$WORK/built-Asm.sbx" >/dev/null 2>&1

REPORT="$(grep -o 'program 7036, data 2448, labels [0-9]*' "$WORK/self.txt" || true)"
check "CosmOS builds CosmOS" cmp -s "$WORK/built-cosmos.bin" "$WORK/cosmos.bin"
REPORT="$(grep -o 'program 7533, data [0-9]*, labels [0-9]*' "$WORK/self.txt" || true)"
check "and builds itself" cmp -s "$WORK/built-Asm.sbx" "$WORK/Asm.sbx"

# ---- And the second generation is the first ----
#
# Boot the CosmOS that CosmOS built, and have that assemble CosmOS again.
if [ -s "$WORK/built-cosmos.bin" ]; then
    "$TOOL" delete "$WORK/self.img" cosmos.bin >/dev/null 2>&1
    printf 'load Asm.sbx\nrun cosmos.asm\nexit\n' \
        | "$EMU" --fast --cycles 4000000000 -D "$WORK/self.img" "$WORK/built-cosmos.bin" \
        > "$WORK/second.txt" 2>&1
    rm -f "$WORK/second-cosmos.bin"
    "$TOOL" get "$WORK/self.img" cosmos.bin "$WORK/second-cosmos.bin" >/dev/null 2>&1
fi
REPORT="a fixed point"
check "second generation" cmp -s "$WORK/second-cosmos.bin" "$WORK/built-cosmos.bin"

echo
if [ "$FAIL" -eq 0 ]; then
    echo "All $PASS native assembler checks passed."
else
    echo "$PASS passed, $FAIL failed: ${FAILED_NAMES[*]}"
    echo
    echo "The session was:"
    sed 's/^/    /' "$WORK/session.txt"
    if [ -f "$WORK/self.txt" ]; then
        echo
        echo "And the self hosting run:"
        sed 's/^/    /' "$WORK/self.txt"
    fi
    exit 1
fi