#!/usr/bin/env bash
# scripts/quality/coverage.sh
#
# Measure line/branch test coverage of code/include/ via gcov + lcov.
#
# Builds the test suite with `--coverage` (gcc) or `-fprofile-instr-generate
# -fcoverage-mapping` (clang), runs ctest, and emits:
#   * build-coverage/coverage.info        — lcov tracefile
#   * build-coverage/lcov-html/index.html — browseable HTML report
#   * stdout: per-file summary + grand total
#
# Local + CI.  Threshold gate: 80 % line / 70 % branch / 90 % function.
# Set SKIP_COVERAGE_GATE=1 to measure without failing (ramp-up mode).
# CI: invoked from cpp-tests.yml test-cgal job (after the full suite runs).
#
# Usage:
#   bash scripts/quality/coverage.sh              # gcc default
#   CXX=g++-13 bash scripts/quality/coverage.sh   # specific compiler
#
# Prerequisites: gcov + lcov (apt install lcov / brew install lcov)
#
# Exit codes:
#   0  coverage report generated and all thresholds met
#   1  tests failed (no usable trace)
#   2  prerequisite missing (lcov / compiler not found)
#   3  coverage.info is empty after lcov run (version mismatch)
#   4  coverage below threshold

set -euo pipefail
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
cd "$ROOT"

BUILD_DIR="build-coverage"

command -v lcov >/dev/null 2>&1 || {
    echo "FAIL: lcov not found in PATH.  Install via:" >&2
    echo "        macOS:  brew install lcov" >&2
    echo "        Linux:  sudo apt install lcov" >&2
    exit 2
}

# On macOS we prefer brew-installed LLVM clang++ because Apple Clang's
# GCov-compatible `--coverage` runtime is known to deadlock during
# static-initializer profiling on arm64 with template-heavy code
# (Eigen + CGAL); the LLVM build does not.  Override with `CXX=...`.
DEFAULT_CXX="g++"
if [ -z "${CXX:-}" ] && [ "$(uname -s)" = "Darwin" ] \
       && [ -x /opt/homebrew/opt/llvm/bin/clang++ ]; then
    DEFAULT_CXX="/opt/homebrew/opt/llvm/bin/clang++"
fi
CXX_BIN="${CXX:-$DEFAULT_CXX}"
command -v "$CXX_BIN" >/dev/null 2>&1 || { echo "FAIL: $CXX_BIN not found" >&2; exit 2; }

echo "========================================"
echo "  Coverage build  (gcov + lcov)"
echo "  CXX:    $CXX_BIN ($($CXX_BIN --version | head -1))"
echo "  build:  $BUILD_DIR"
echo "========================================"
echo

cmake -S code -B "$BUILD_DIR" \
    -DCMAKE_CXX_COMPILER="$CXX_BIN" \
    -DCMAKE_CXX_FLAGS="--coverage -O0 -g" \
    -DCMAKE_EXE_LINKER_FLAGS="--coverage" \
    -DCMAKE_BUILD_TYPE=Debug \
    -DCMAKE_GTEST_DISCOVER_TESTS_DISCOVERY_MODE=PRE_TEST \
    -Wno-dev

nice -n 19 cmake --build "$BUILD_DIR" --target conformallab_tests \
    -j"$(nproc 2>/dev/null || sysctl -n hw.logicalcpu 2>/dev/null || echo 2)"

# Run the non-CGAL test suite.  (CGAL tests under coverage instrumentation
# blow up to ~6 GB RAM during compilation; out-of-scope for this gate.)
cd "$BUILD_DIR"
if ! ctest -E "^cgal\." --output-on-failure; then
    cd "$ROOT"
    echo "FAIL: coverage build's test run did not complete cleanly." >&2
    exit 1
fi
cd "$ROOT"

# ── Capture trace ────────────────────────────────────────────────────────────
# lcov ≥ 2.0 became strict about "inconsistent" / "unsupported" / "negative"
# diagnostics from gcov data; the GTest sources reliably trigger
# "inconsistent" because of their preprocessor gymnastics, and brew clang's
# gcov shim is older than the function-end-line tracking lcov wants.
# These are noise we cannot fix in our source tree — suppress them.
LCOV_TOLERANT=(
    --ignore-errors inconsistent
    --ignore-errors unsupported
    --ignore-errors negative
    --ignore-errors empty
    --ignore-errors mismatch
    --rc lcov_branch_coverage=1
)

# C2 fix: capture and extract must succeed (or we have no valid trace).
# The --ignore-errors flags above suppress the gcov-version noise; any
# remaining error is real (e.g. no .gcda files, compiler mismatch) and
# should be visible as a non-zero exit.
lcov --capture --directory "$BUILD_DIR" \
     --output-file "$BUILD_DIR/coverage.raw.info" \
     --no-external \
     "${LCOV_TOLERANT[@]}" \
     >/dev/null 2>&1

# Restrict to code/include/  (our public API surface; ignore deps/tests).
lcov --extract "$BUILD_DIR/coverage.raw.info" \
     "*/code/include/*" \
     --output-file "$BUILD_DIR/coverage.info" \
     "${LCOV_TOLERANT[@]}" \
     >/dev/null 2>&1

# ── HTML report (best-effort; failure here does not fail the script) ──────────
genhtml --branch-coverage --legend \
        --output-directory "$BUILD_DIR/lcov-html" \
        "${LCOV_TOLERANT[@]}" \
        "$BUILD_DIR/coverage.info" >/dev/null 2>&1 || true

# ── Summary to stdout ────────────────────────────────────────────────────────
echo
echo "── Coverage summary (code/include/) ─────────────────────────"
if [ ! -s "$BUILD_DIR/coverage.info" ]; then
    echo "    FAIL: coverage.info is empty — likely an lcov/gcov version" >&2
    echo "          mismatch.  Tests passed; raw .gcda files are in $BUILD_DIR." >&2
    echo "          Inspect with:  find $BUILD_DIR -name '*.gcda' | head" >&2
    exit 3
fi

lcov --summary "$BUILD_DIR/coverage.info" "${LCOV_TOLERANT[@]}" 2>/dev/null \
    | grep -E "lines\.\.\.\.|functions|branches" \
    | sed 's/^/    /'
echo
echo "HTML report:  $BUILD_DIR/lcov-html/index.html"
echo "              open $BUILD_DIR/lcov-html/index.html"
echo

# ── Coverage threshold gate (C3) ─────────────────────────────────────────────
# Agreed thresholds (2026-05-31): 80 % line / 70 % branch / 90 % function.
# Set SKIP_COVERAGE_GATE=1 to print without failing (useful during ramp-up).
THRESHOLD_LINE=80
THRESHOLD_BRANCH=70
THRESHOLD_FUNC=90

if [ "${SKIP_COVERAGE_GATE:-0}" = "1" ]; then
    echo "NOTE: SKIP_COVERAGE_GATE=1 — thresholds not enforced."
    exit 0
fi

SUMMARY=$(lcov --summary "$BUILD_DIR/coverage.info" "${LCOV_TOLERANT[@]}" 2>/dev/null)

extract_pct() {
    echo "$SUMMARY" | grep -i "$1" | grep -oE '[0-9]+\.[0-9]+' | head -1
}

LINE_PCT=$(extract_pct "lines")
BRANCH_PCT=$(extract_pct "branches")
FUNC_PCT=$(extract_pct "functions")

FAIL=0
check_threshold() {
    local label="$1" actual="$2" threshold="$3"
    if [ -z "$actual" ]; then
        echo "    WARN: could not parse $label coverage — skipping gate" >&2
        return
    fi
    # Use awk for float comparison (bash cannot do floats)
    if awk "BEGIN { exit ($actual >= $threshold) ? 0 : 1 }"; then
        printf "    ✓ %-10s %s%% >= %s%%\n" "$label" "$actual" "$threshold"
    else
        printf "    ✗ %-10s %s%% < %s%%  (threshold: %s%%)\n" \
            "$label" "$actual" "$threshold" "$threshold" >&2
        FAIL=1
    fi
}

echo "── Coverage gate ─────────────────────────────────────────────"
check_threshold "lines"     "$LINE_PCT"   "$THRESHOLD_LINE"
check_threshold "branches"  "$BRANCH_PCT" "$THRESHOLD_BRANCH"
check_threshold "functions" "$FUNC_PCT"   "$THRESHOLD_FUNC"
echo

if [ "$FAIL" -eq 1 ]; then
    echo "FAIL: coverage below threshold — see above." >&2
    echo "      To suppress (ramp-up): SKIP_COVERAGE_GATE=1 bash $0" >&2
    exit 4
fi
echo "PASS: all coverage thresholds met."