#!/usr/bin/env bash
# garden.sh — the gardening loop.
#
# Reports doc sprawl and files that violate the "Discourse is the system of
# record for documentation; gitea .md files are stubs" policy. Run via
# `make garden`. Findings are WARNINGS (advisory); fix them at a natural break.
#
# What it checks:
#   1. Markdown sprawl: count of .md files per directory (top-10 by count).
#   2. Oversized .md files (default >300 lines) that don't cite a Discourse URL
#      — candidates to migrate to Discourse, leaving a stub.
#   3. .md files with no Discourse link at all (informational; exempt: the
#      operational files in EXEMPT_FILES).
set -euo pipefail

HERE="$(cd "$(dirname "$0")" && pwd)"
# shellcheck disable=SC1091
source "$HERE/lib/common.sh"
REPO_ROOT="$(repo_root)"
cd "$REPO_ROOT"

SIZE_LIMIT="${GARDEN_MD_LINE_LIMIT:-300}"
# Operational files that legitimately live next to code, not in Discourse.
EXEMPT_FILES="${GARDEN_EXEMPT:-AGENTS.md STATUS.md WORKING.md questions-v.*.md PATTERNS.md BASELINE-PROMPT.md README.md}"

log_step "Gardening report for $REPO_ROOT"

# --- 1. sprawl by directory -------------------------------------------------
log_info "Markdown file count by directory (top 10):"
find . -path ./.git -prune -o -name '*.md' -print 2>/dev/null \
    | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -10 | sed 's/^/    /'

# --- 2. oversized .md without a Discourse link ------------------------------
log_info "Oversized .md (>${SIZE_LIMIT} lines) lacking a Discourse URL — migrate candidates:"
OVERSIZED=0
while IFS= read -r -d '' f; do
    # skip exempt files (glob match against basename and relative path)
    exempt=false
    base=$(basename "$f")
    rel=${f#./}
    for pat in $EXEMPT_FILES; do
        # shellcheck disable=SC2254  # glob match is intentional
        case "$base" in $pat) exempt=true; break ;; esac
        # shellcheck disable=SC2254
        case "$rel" in $pat) exempt=true; break ;; esac
    done
    [ "$exempt" = true ] && continue
    lines=$(wc -l < "$f" 2>/dev/null || echo 0)
    if [ "$lines" -gt "$SIZE_LIMIT" ]; then
        if ! grep -qiE 'community\.turnsys\.com|discourse' "$f" 2>/dev/null; then
            printf '    %-60s %s lines\n' "$f" "$lines"
            OVERSIZED=$((OVERSIZED + 1))
        fi
    fi
done < <(find . -path ./.git -prune -o -name '*.md' -print0 2>/dev/null)
[ "$OVERSIZED" -eq 0 ] && echo "    (none)"

# --- 3. summary -------------------------------------------------------------
log_step "Gardening summary"
echo "    Oversized non-Discourse .md files: $OVERSIZED"
if [ "$OVERSIZED" -eq 0 ]; then
    log_ok "no migration candidates"
else
    log_warn "$OVERSIZED file(s) to migrate to Discourse"
fi