#!/usr/bin/env bash
# definitions.sh — catch duplicate top-level definitions, and name the files.
#
# El has no namespacing. `import` is textual inlining, so two modules defining
# the same name emit two C functions into one translation unit. cc catches it,
# but reports the generated helpers (__el_body_f, __env_f, __thunk_f) before the
# user's own function, so the first three errors name symbols nobody wrote.
#
# Naming the FILES needed provenance threaded end to end: tokens had no line
# numbers at all, so no diagnostic in El could name a place. Now a token is
# (kind, value, line), FnDef carries its line, and resolve_imports publishes
# which line range of the combined source came from which file.
#
# LIMIT: a nested import returns one string, so a definition inside a
# transitively imported file is attributed to the direct import.
set -uo pipefail
REL="${1:?usage: definitions.sh <relations-file>}"
[ -f "$REL" ] || exit 0

# line in the COMBINED source -> "file:line-within-that-file". Reporting the
# combined line against a filename would point at a line that file does not
# have, which is worse than reporting no line at all.
locate() {
    awk -v L="$1" '$2=="spans" && $3<=L && $4>=L {printf "%s:%d", $1, L-$3+1; found=1; exit}
                   END{ if(!found) printf "" }' "$REL"
}

V=0
while read -r name; do
    lines=$(grep -E "^$name calls defines_at:" "$REL" | sed 's/.*defines_at://' | sort -un)
    n=$(echo "$lines" | wc -l | tr -d ' ')
    [ "$n" -gt 1 ] || continue
    printf "duplicate definition: '%s' is defined %s times — El has no namespacing, so imported modules share one global scope\n" "$name" "$n"
    for l in $lines; do
        loc=$(locate "$l")
        [ -n "$loc" ] && printf "    %s\n" "$loc" || printf "    combined line %s\n" "$l"
    done
    V=$((V+1))
done < <(grep ' calls defines_at:' "$REL" | awk '{print $1}' | sort -u)

[ "$V" -eq 0 ] && echo "definitions: clean"
exit "$V"