#!/usr/bin/env bash # Index compatibility test between two obikmer binaries that differ only by # their ptr_hash version (A = baseline, B = candidate). # # Usage: compat_ptrhash.sh VOL_A VOL_B OUT # VOL_A / VOL_B docker volumes holding a musl release build (CARGO_TARGET_DIR) # OUT host directory receiving report.txt # # What it checks (everything compared by md5 of dump/query output): # T0 on-disk bytes of an index built by A vs by B (informational) # T1 A-built single-genome indexes read by A and by B # T2 merges: A merging A-built sources (reference), B merging A-built # sources, B merging B-built sources; each result dumped by A and by B # T3 queries (hits and misses) on indexes read by A and by B # T4 incremental merge into an existing A-built merged index, by A and B set -u VOL_A="$1"; VOL_B="$2"; OUT="$3" HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" REPO="$(cd "$HERE/../.." && pwd)" mkdir -p "$OUT" docker run --rm --platform linux/amd64 \ -v "$VOL_A:/va:ro" -v "$VOL_B:/vb:ro" \ -v "$REPO/benchmark/run/genomes:/genomes_ro:ro" -v "$OUT:/out" \ obikmer-debug:linux-amd64 bash -c ' set -u R=x86_64-unknown-linux-musl/release/obikmer mkdir -p /tmp/bin && cp /va/$R /tmp/bin/A && cp /vb/$R /tmp/bin/B A=/tmp/bin/A; B=/tmp/bin/B W=/tmp/w; rm -rf $W; mkdir -p $W/ia $W/ib exec > >(tee /out/report.txt) 2>&1 echo "A sha: $(sha256sum $A | cut -c1-16) B sha: $(sha256sum $B | cut -c1-16)" mapfile -t G < <(ls -S /genomes_ro/*.fna.gz | sed -n 8,12p) echo "genomes: ${#G[@]}"; printf " %s\n" "${G[@]##*/}" mkdir -p $W/fa; n=0; for gz in "${G[@]}"; do n=$((n+1)); g=$W/fa/L$n.fasta; zcat "$gz" > "$g" $A index -k 21 -m 9 --theta 0 -p 256 --label L$n -o $W/ia/L$n.idx "$g" 2>$W/ia/L$n.err >/dev/null || { echo "A index failed L$n"; tail -2 $W/ia/L$n.err; } $B index -k 21 -m 9 --theta 0 -p 256 --label L$n -o $W/ib/L$n.idx "$g" 2>$W/ib/L$n.err >/dev/null || { echo "B index failed L$n"; tail -2 $W/ib/L$n.err; } done echo; echo "== T0 on-disk bytes, index built by A vs by B" nd=$(diff -rq $W/ia $W/ib | wc -l); nt=$(find $W/ia -type f | wc -l) echo "files differing: $nd / $nt" diff -rq $W/ia $W/ib | sed "s#$W/##g" | awk "{print \$2}" | sed -E "s#/partitions/.*/#/…/#" | sort | uniq -c | sort -rn | head -8 h() { md5sum | cut -c1-12; } echo; echo "== T1 A-built single-genome indexes: dump by A vs by B" for i in 1 2 3 4 5; do a=$($A dump $W/ia/L$i.idx 2>/dev/null | h); b=$($B dump $W/ia/L$i.idx 2>/dev/null | h) echo "L$i A:$a B:$b $([ "$a" = "$b" ] && echo OK || echo DIFF)" done cp_src() { rm -rf $2; mkdir -p $2; for i in $1; do cp -r $3/L$i.idx $2/; done; } echo; echo "== T2 merges of 4 genomes (presence)" cp_src "1 2 3 4" $W/s_aa $W/ia; cp_src "1 2 3 4" $W/s_ba $W/ia; cp_src "1 2 3 4" $W/s_bb $W/ib $A merge --output $W/M_AA --force --force-presence $W/s_aa/L*.idx 2>$W/m_aa.err; echo "M_AA rc=$?" $B merge --output $W/M_BA --force --force-presence $W/s_ba/L*.idx 2>$W/m_ba.err; echo "M_BA rc=$? (B merging A-built sources)" $B merge --output $W/M_BB --force --force-presence $W/s_bb/L*.idx 2>$W/m_bb.err; echo "M_BB rc=$? (B merging B-built sources)" for X in M_AA M_BA M_BB; do for T in A B; do eval "BIN=\$$T"; $BIN dump $W/$X 2>/dev/null > $W/d_${X}_$T.csv echo "dump $X by $T: $(wc -l < $W/d_${X}_$T.csv) lines raw:$(h < $W/d_${X}_$T.csv) sorted:$(LC_ALL=C sort -S 2G $W/d_${X}_$T.csv | h)" done; done echo; echo "== T3 queries" head -c 60000 $W/fa/L1.fasta > $W/q.fa python3 - <> $W/q.fa import random random.seed(1) print(">rand") print("".join(random.choice("ACGT") for _ in range(5000))) PY for X in ia/L1.idx M_AA M_BA M_BB; do for T in A B; do eval "BIN=\$$T"; echo "query $X by $T: $($BIN query $W/$X $W/q.fa 2>/dev/null | h)" done; done echo; echo "== T4 incremental merge (existing A-built merged index + a 5th genome)" for T in A B; do eval "BIN=\$$T"; rm -rf $W/inc_$T $W/dst_$T; cp -r $W/M_AA $W/dst_$T; cp -r $W/ia/L5.idx $W/l5_$T.idx $BIN merge --output $W/inc_$T --force --force-presence $W/dst_$T $W/l5_$T.idx 2>$W/inc_$T.err; echo "inc by $T rc=$?" $BIN dump $W/inc_$T 2>/dev/null | h done echo; echo done '