# Phase 3 all-assembly baseline orchestration.
# All original and generated ROM-derived inputs/outputs remain ignored.

SHELL := /usr/bin/bash

EXE := extracted/SCUS_946.40;1
MANIFEST := extracted/MANIFEST.tsv
SPLAT := tools/splat/.venv/bin/splat
AS := tools/mipsel-none-elf-binutils/prefix/usr/bin/mipsel-none-elf-as
LD := tools/mipsel-none-elf-binutils/prefix/usr/bin/mipsel-none-elf-ld
OBJCOPY := tools/mipsel-none-elf-binutils/prefix/usr/bin/mipsel-none-elf-objcopy

ASM_ROOT := asm
SPLAT_CONFIG := $(ASM_ROOT)/scus_946_40.yaml
SPLAT_OUTPUT := $(ASM_ROOT)/generated
LINKER_SCRIPT := $(ASM_ROOT)/scus_946_40.ld
BUILD := build
ELF := $(BUILD)/scus_946_40.elf
REBUILT := $(BUILD)/scus_946_40.rebuilt
INPUT_REPORT := .run/p3-exe-info.tsv

# Phase 5 ordered code build: C regions listed in the tracked registry are
# compiled with the identified toolchain and linked in address order between
# data fallbacks taken from the original executable. An empty registry
# reproduces the all-payload data baseline exactly.
REGIONS := config/regions.tsv
SYMBOLS := config/symbols.tsv
INVENTORY := config/function_inventory.tsv
EXTENTS := config/function_extents.tsv
DUPES := config/duplicate_bodies.tsv
NEGATIVES := config/near_match_negatives.tsv
WORKLIST := config/match_worklist.tsv
MATCH := tools/sf3_match
EXTENTS_TOOL := tools/sf3_extents
DUPES_TOOL := tools/sf3_dupes
TRIAGE_TOOL := tools/sf3_triage
NEGPOOL_TOOL := tools/sf3_negpool

# Rows deliberately excluded from dispatch, kept in ONE place: a previous phase excluded each for a
# recorded reason (false extent start, shared tail, unmatchable $gp-thunk half, fragment), and the
# reason is in the comment block above `worklist`. Both `worklist` and `negpool` are given this
# list, because the Phase 12 pools were first built by a one-off script that did not know about it
# and **8 of these 12 rows were delivered straight back to the workers as fresh work**.
NAMED_EXCLUSIONS := 0x8005DEF8 0x800F3160 0x80108034 0x8010804C 0x80012A10 0x80012AE0 \
                    0x80012CFC 0x80012B20 0x8008A198 0x8010080C 0x800C3490 0x8001DC20

# Worker staging for the classified-negatives pools. Empty in a clean checkout, which is correct:
# the pools then contain only the rows the tracked index names.
NEGPOOL_DIR := .run/p12
NEGPOOL_CLASSIFIED := $(wildcard .run/p12/w-*/negatives.tsv)
CODE_OUT := build/code
EXPECTED_SHA1 := e173426c157384ebf1b6caf8c6fea18a85a14af9

.PHONY: all validate split assemble link binary code gate extents extents-verify dupes worklist negpool test check clean

all: binary

validate:
	@test -f "$(EXE)"
	@test -f "$(MANIFEST)"
	@mkdir -p .run
	@./tools/sf3_extract psx-exe-info "$(EXE)" "$(MANIFEST)" > "$(INPUT_REPORT)"

split: validate
	@test -f "$(SPLAT)"
	@test -f "$(SPLAT_CONFIG)"
	@cd "$(ASM_ROOT)" && ../"$(SPLAT)" split "$$(basename "$(SPLAT_CONFIG)")" --disassemble-all

assemble: split
	@test -d "$(SPLAT_OUTPUT)" && test ! -L "$(SPLAT_OUTPUT)"
	@test -f "$(AS)"
	@test ! -L "$(BUILD)"
	@mkdir -p "$(BUILD)"
	@while IFS= read -r source; do \
		rel="$${source#$(ASM_ROOT)/}"; \
		object="$(BUILD)/$${rel}.o"; \
		mkdir -p "$$(dirname "$$object")"; \
		"$(AS)" -march=r3000 -G0 -I "$(ASM_ROOT)/include" -o "$$object" "$$source"; \
	done < <(find "$(SPLAT_OUTPUT)" -type f -name '*.s' -print | sort)

link: assemble
	@test -f "$(LINKER_SCRIPT)"
	@test -f "$(LD)"
	@rm -f "$(ELF)"
	@"$(LD)" -T "$(LINKER_SCRIPT)" -o "$(ELF)"

binary: link
	@test -f "$(OBJCOPY)"
	@rm -f "$(REBUILT)"
	@"$(OBJCOPY)" -O binary "$(ELF)" "$(REBUILT)"

# Ordered code build and full-binary gate (Phase 5). `code` builds only;
# `gate` builds and then requires the whole executable to be byte-identical.
code: validate
	@test -f "$(MATCH)"
	@test -f "$(REGIONS)"
	@test -f "$(SYMBOLS)"
	@rm -rf "$(CODE_OUT)"
	@"$(MATCH)" build --exe "$(EXE)" --regions "$(REGIONS)" --symbols "$(SYMBOLS)" --out "$(CODE_OUT)"

gate: validate
	@test -f "$(MATCH)"
	@test -f "$(REGIONS)"
	@test -f "$(SYMBOLS)"
	@rm -rf "$(CODE_OUT)"
	@"$(MATCH)" gate --exe "$(EXE)" --regions "$(REGIONS)" --symbols "$(SYMBOLS)" --out "$(CODE_OUT)" \
		--expect-sha1 "$(EXPECTED_SHA1)"

# Function extents (Phase 7). `extents` regenerates the tracked table from the
# inventory; `extents-verify` re-derives it and requires every registered region
# to agree, so a region can never silently disagree with the derived extent.
extents: validate
	@test -f "$(EXTENTS_TOOL)"
	@test -f "$(INVENTORY)"
	@"$(EXTENTS_TOOL)" scan --exe "$(EXE)" --inventory "$(INVENTORY)" --out "$(EXTENTS)" --force

extents-verify: validate
	@test -f "$(EXTENTS_TOOL)"
	@test -f "$(INVENTORY)"
	@test -f "$(EXTENTS)"
	@"$(EXTENTS_TOOL)" verify --exe "$(EXE)" --inventory "$(INVENTORY)" \
		--extents "$(EXTENTS)" --regions "$(REGIONS)"

# Duplicate-body census (Phase 7): groups byte-identical bodies so a shared body
# is matched once and registered once per address.
dupes: validate
	@test -f "$(DUPES_TOOL)"
	@test -f "$(EXTENTS)"
	@"$(DUPES_TOOL)" census --exe "$(EXE)" --extents "$(EXTENTS)" --out "$(DUPES)" --force

# Ranked match worklist (Phase 7). The --exclude addresses are recorded
# near-misses or known-bad rows deferred by developer direction; naming them here
# keeps the exclusion visible instead of burying it in the tool.
# 0x8010080C was added in Phase 10 as a FALSE EXTENT START (worker C): its first
# instruction is `beq s0,zero` with s0 never written in range, and the walk split
# one real 252-byte function (0x801007E0..0x801008DC) at a spurious `jal`-target
# boundary. It is now caught earlier by sf3_triage's general `restores_unsaved`
# rule (worker A's independent scan re-derived the same row from a different
# signal), so this row is retained only as the provenance record for that defect.
#
# 0x800C3490 was added in Phase 12 as a FRAGMENT, not a function (cookbook 114,
# found by worker A and re-confirmed by the coordinator against the registry). It
# starts mid-expression, its body is a SHARED TAIL (`addiu sp,sp,48; jr ra`) that
# also appears at 0x800C3470-0x800C348C, and it cannot be matched standalone. The
# extents table still grades it `exact` with `term=jr_ra`, because the boundary walk
# sees a well-formed terminal -- so the tool cannot catch this one. Excluded rather
# than left in the dispatch files, where it costs every fresh-band worker a reading
# budget before it is recognised again. Worker A identified it for the second time in
# Phase 12 and skipped it rather than spending that budget.
#
# 0x8001DC20 was added in Phase 12 as the SECOND instance of the same class, and it
# gives the class a CHECKABLE predicate instead of a vibe. Its first instruction is
# `lw t0,0(t5)` (0x8DA80000) and **$13 is written ZERO times in the whole 72-byte
# extent** -- t5 is read but never established, so the extent is the tail of a larger
# function. Worker D found it and refused to spend GTE spellings on it; the
# coordinator re-derived the same conclusion from the bytes before excluding it, so
# this row is a two-worker confirmation like 0x800C3490 is.
# The general predicate -- "a caller-saved temporary ($8-$15) is READ before any
# instruction in the extent WRITES it" -- holds for BOTH rows (`0x800C3490` also
# writes $13 zero times) and is sound, because $8-$15 are never incoming o32
# arguments and no compiler emits a read of an uninitialised temporary. It is NOT
# yet implemented as an automatic triage rule; until it is, fragments are caught by
# a worker reading the row. See the Phase 12 ledger for that open item.
worklist: validate
	@test -f "$(TRIAGE_TOOL)"
	@test -f "$(EXTENTS)"
	@test -f "$(DUPES)"
	@"$(TRIAGE_TOOL)" plan --exe "$(EXE)" --extents "$(EXTENTS)" --inventory "$(INVENTORY)" \
		--census "$(DUPES)" --regions "$(REGIONS)" --negatives "$(NEGATIVES)" \
		$(foreach a,$(NAMED_EXCLUSIONS),--exclude $(a)) --out "$(WORKLIST)" --force

# Classified-negatives worker pools. Regenerating these is cheap and idempotent; handing a worker a
# pool that a row was ALREADY removed from is not, so this target owns both filters:
#   * $(NAMED_EXCLUSIONS)                 -- rows dispatch must never offer (same list as `worklist`)
#   * the workers' own classification     -- a row already read this phase, kept at prio 1 only if
#                                            it NAMES a mechanism, dropped otherwise.
# See the tools/sf3_negpool docstring for why both rules exist and what they cost when absent.
negpool: validate
	@test -f "$(NEGPOOL_TOOL)"
	@test -f "$(EXTENTS)"
	@excl=""; for a in $(NAMED_EXCLUSIONS); do excl="$$excl --exclude $$a"; done; \
	 cls=""; for f in $(NEGPOOL_CLASSIFIED); do cls="$$cls --classified $$f"; done; \
	 "$(NEGPOOL_TOOL)" --negatives "$(NEGATIVES)" --regions "$(REGIONS)" --extents "$(EXTENTS)" \
		--exe "$(EXE)" --out-dir "$(NEGPOOL_DIR)" --prefix negatives --workers 4 \
		$$excl $$cls

# Verification gates. `test` is synthetic-only and needs no game input;
# `check` adds the extents check and the full-binary byte gate (which do).
test:
	@PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s tools/tests

check: test extents-verify gate

clean:
	@if test -e "$(BUILD)"; then \
		test -d "$(BUILD)" && test ! -L "$(BUILD)"; \
		rm -rf "$(BUILD)"; \
	fi
