WIP: Add bcrlarch to cf-paired-loci phylo benchmarking framework

.gitignore

@@ -7,7 +7,9 @@
 /packages/ham/bench
 bunnyhutch_id_rsa
 /_tmp/
+/_temp/
 /_output/
+/_benchmark_output/
 /tmp.csv
 /tmp-cluster-annotations.csv
 /packages/ig-sw/src/ig_align/ig-sw
@@ -63,3 +65,4 @@ packages/RPANDA/lib/
 /build/
 /dist/
 /partis_bcr.egg-info/
+_ignore/

bin/partis

@@ -1641,7 +1641,7 @@ parent_args.append({'name' : '--get-selection-metrics', 'kwargs' : {'action' : '
 parent_args.append({'name' : '--min-selection-metric-cluster-size', 'kwargs' : {'type' : int, 'default' : treeutils.default_min_selection_metric_cluster_size, 'help' : 'When calculating selection metrics, ignore clusters smaller than this. See also --min-paired-cluster-size-to-read, which is similar but applies earlier, when reading clusters from files.'}})
 parent_args.append({'name' : '--min-paired-cluster-size-to-read', 'kwargs' : {'type' : int, 'default' : treeutils.default_min_selection_metric_cluster_size, 'help' : 'When reading paired annotations when getting selection metrics or plotting partitions, ignore clusters with either N h or l ids smaller than this. See also --min-selection-metric-cluster-size, which is similar but only skips selection metric calculation.'}})
 parent_args.append({'name' : '--treefname', 'kwargs' : {'help' : 'newick-formatted file with a tree corresponding to the sequences either in --infname (if making new output, i.e. action is annotate or partition) or --outfname (if reading existing output, i.e. action is get-selection-metrics). Used for instance if getting selection metrics using trees inferred by an external program (unrelated to --input-simulation-treefname).'}})
-parent_args.append({'name' : '--tree-inference-method', 'kwargs' : {'choices' : ['fasttree', 'iqtree', 'iqtree-1.6.beta3', 'iqtree-2.3.1', 'raxml', 'gctree', 'gctree-base', 'gctree-mut-mult', 'gctree-no-dag', 'linearham', 'igphyml', 'cpath'], 'help' : 'Method to use when inferring trees (default: fasttree)'}})
+parent_args.append({'name' : '--tree-inference-method', 'kwargs' : {'choices' : ['fasttree', 'iqtree', 'iqtree-1.6.beta3', 'iqtree-2.3.1', 'raxml', 'gctree', 'gctree-base', 'gctree-mut-mult', 'gctree-no-dag', 'linearham', 'igphyml', 'bcrlarch-pars', 'cpath'], 'help' : 'Method to use when inferring trees (default: fasttree)'}})
 parent_args.append({'name' : '--tree-inference-subdir', 'kwargs' : {'help' : 'Subdirectory of the (automatically-set) tree inference workdir to which to write tree inference output files. By default, these are written to a subdir of --outfname/--paired-outdir with the name of the inference method, but this argument allows multiple versions, as with --sub-plotdir.'}})
 parent_args.append({'name' : '--infer-trees-with-only-leaves', 'kwargs' : {'action' : 'store_true', 'help' : 'Discard internal nodes in true trees when inferring phylogenetic trees.'}})
 parent_args.append({'name' : '--infer-trees-with-collapsed-duplicate-seqs', 'kwargs' : {'action' : 'store_true', 'help' : 'collapse identical sequences when inferring trees (and then again when plotting them, since unfortunately it\'s really hard to pass the information between those two scripts). Yes, it sucks having both this and --collapse-duplicate-sequences (which acts during smith-waterman), but sometimes we can\'t use that, e.g. with queries to include or subset partitioning (at least without more work).'}})

bin/xvfb-run

@@ -1,194 +1,155 @@
 #!/bin/sh
-# ----------------------------------------------------------------------------------------
-# NOTE copied from ubuntu system location in order to remove the '2>&1' at the bottom, see https://bugs.launchpad.net/ubuntu/+source/xorg-server/+bug/1059947
-# ----------------------------------------------------------------------------------------
-
-# This script starts an instance of Xvfb, the "fake" X server, runs a command
-# with that server available, and kills the X server when done.  The return
-# value of the command becomes the return value of this script, except in cases
-# where this script encounters an error.
 #
-# If anyone is using this to build a Debian package, make sure the package
-# Build-Depends on xvfb and xauth.
-
-set -e
-
-PROGNAME=xvfb-run
-SERVERNUM=99
-AUTHFILE=
-ERRORFILE=/dev/null
-XVFBARGS="-screen 0 640x480x8"
-LISTENTCP="-nolisten tcp"
-XAUTHPROTO=.
-
-# Query the terminal to establish a default number of columns to use for
-# displaying messages to the user.  This is used only as a fallback in the event
-# the COLUMNS variable is not set.  ($COLUMNS can react to SIGWINCH while the
-# script is running, and this cannot, only being calculated once.)
-DEFCOLUMNS=$(stty size 2>/dev/null | awk '{print $2}') || true
-if ! expr "$DEFCOLUMNS" : "[[:digit:]]\+$" >/dev/null 2>&1; then
-    DEFCOLUMNS=80
-fi
+# Robust xvfb-run wrapper for headless / HPC environments
+#
+# Key features:
+#  - Clear error logging
+#  - No use of `tempfile`, `$$`, or explicit XXXXX templates
+#  - Falls back to running command directly if Xvfb is unavailable
+#  - Forces headless plotting backends when falling back
+#
 
-# Display a message, wrapping lines at the terminal width.
-message () {
-    echo "$PROGNAME: $*" | fmt -t -w ${COLUMNS:-$DEFCOLUMNS}
-}
+set -u
 
-# Display an error message.
-error () {
-    message "error: $*" >&2
-}
+PROGNAME="$(basename "$0")"
+
+SERVERNUM=""
+AUTO_SERVERNUM=""
+ERRORFILE=""
+XVFBARGS="-screen 0 1280x1024x24"
+XVFB_RUN_TMPDIR=""
+AUTHFILE=""
+XVFBPID=""
+
+XAUTHORITY_ORIG="${XAUTHORITY-}"
+DISPLAY_ORIG="${DISPLAY-}"
+
+usage() {
+    cat >&2 <<EOF
+Usage: ${PROGNAME} [OPTIONS] command [args...]
 
-# Display a usage message.
-usage () {
-    if [ -n "$*" ]; then
-        message "usage error: $*"
-    fi
-    cat <<EOF
-Usage: $PROGNAME [OPTION ...] COMMAND
-Run COMMAND (usually an X client) in a virtual X server environment.
 Options:
--a        --auto-servernum          try to get a free server number, starting at
-                                    --server-num
--e FILE   --error-file=FILE         file used to store xauth errors and Xvfb
-                                    output (default: $ERRORFILE)
--f FILE   --auth-file=FILE          file used to store auth cookie
-                                    (default: ./.Xauthority)
--h        --help                    display this usage message and exit
--n NUM    --server-num=NUM          server number to use (default: $SERVERNUM)
--l        --listen-tcp              enable TCP port listening in the X server
--p PROTO  --xauth-protocol=PROTO    X authority protocol name to use
-                                    (default: xauth command's default)
--s ARGS   --server-args=ARGS        arguments (other than server number and
-                                    "-nolisten tcp") to pass to the Xvfb server
-                                    (default: "$XVFBARGS")
+  -a            Automatically choose a free X server number (starting at 99)
+  -n NUM        Use X server number NUM
+  -e FILE       Append logs to FILE (default: stderr only)
+  -s ARGS       Extra arguments for Xvfb
+  -h            Show this help
+
+Behavior:
+  If Xvfb is not available on PATH, the command is run directly with
+  headless backends forced (MPLBACKEND=Agg, QT_QPA_PLATFORM=offscreen).
 EOF
 }
 
-# Find a free server number by looking at .X*-lock files in /tmp.
-find_free_servernum() {
-    # Sadly, the "local" keyword is not POSIX.  Leave the next line commented in
-    # the hope Debian Policy eventually changes to allow it in /bin/sh scripts
-    # anyway.
-    #local i
-
-    i=$SERVERNUM
-    while [ -f /tmp/.X$i-lock ]; do
-        i=$(($i + 1))
-    done
-    echo $i
+log() {
+    msg="[$PROGNAME] $*"
+    echo "$msg" >&2
+    if [ -n "$ERRORFILE" ]; then
+        echo "$msg" >>"$ERRORFILE" 2>/dev/null || true
+    fi
 }
 
-# Clean up files
-clean_up() {
-    if [ -e "$AUTHFILE" ]; then
-        XAUTHORITY=$AUTHFILE xauth remove ":$SERVERNUM" >>"$ERRORFILE" 2>&1
+die() {
+    log "ERROR: $*"
+    exit 1
+}
+
+cleanup() {
+    if [ -n "$XVFBPID" ] && kill -0 "$XVFBPID" 2>/dev/null; then
+        kill "$XVFBPID" 2>/dev/null || true
+        wait "$XVFBPID" 2>/dev/null || true
+    fi
+    if [ -n "$XVFB_RUN_TMPDIR" ] && [ -d "$XVFB_RUN_TMPDIR" ]; then
+        rm -rf "$XVFB_RUN_TMPDIR" 2>/dev/null || true
     fi
-    if [ -n "$XVFB_RUN_TMPDIR" ]; then
-        if ! rm -r "$XVFB_RUN_TMPDIR"; then
-            error "problem while cleaning up temporary directory"
-            exit 5
-        fi
+    if [ -n "$XAUTHORITY_ORIG" ]; then
+        export XAUTHORITY="$XAUTHORITY_ORIG"
+    else
+        unset XAUTHORITY 2>/dev/null || true
     fi
-    if [ -n "$XVFBPID" ]; then
-        kill "$XVFBPID" >>"$ERRORFILE" 2>&1
+    if [ -n "$DISPLAY_ORIG" ]; then
+        export DISPLAY="$DISPLAY_ORIG"
+    else
+        unset DISPLAY 2>/dev/null || true
     fi
 }
-
-# Parse the command line.
-ARGS=$(getopt --options +ae:f:hn:lp:s:w: \
-       --long auto-servernum,error-file:,auth-file:,help,server-num:,listen-tcp,xauth-protocol:,server-args:,wait: \
-       --name "$PROGNAME" -- "$@")
-GETOPT_STATUS=$?
-
-if [ $GETOPT_STATUS -ne 0 ]; then
-    error "internal error; getopt exited with status $GETOPT_STATUS"
-    exit 6
-fi
-
-eval set -- "$ARGS"
-
-while :; do
-    case "$1" in
-        -a|--auto-servernum) SERVERNUM=$(find_free_servernum); AUTONUM="yes" ;;
-        -e|--error-file) ERRORFILE="$2"; shift ;;
-        -f|--auth-file) AUTHFILE="$2"; shift ;;
-        -h|--help) SHOWHELP="yes" ;;
-        -n|--server-num) SERVERNUM="$2"; shift ;;
-        -l|--listen-tcp) LISTENTCP="" ;;
-        -p|--xauth-protocol) XAUTHPROTO="$2"; shift ;;
-        -s|--server-args) XVFBARGS="$2"; shift ;;
-        -w|--wait) shift ;;
-        --) shift; break ;;
-        *) error "internal error; getopt permitted \"$1\" unexpectedly"
-           exit 6
-           ;;
+trap cleanup EXIT HUP INT TERM
+
+# Parse options
+while getopts "an:e:s:h" opt; do
+    case "$opt" in
+        a) AUTO_SERVERNUM=1 ;;
+        n) SERVERNUM="$OPTARG" ;;
+        e) ERRORFILE="$OPTARG" ;;
+        s) XVFBARGS="$XVFBARGS $OPTARG" ;;
+        h) usage; exit 0 ;;
+        *) usage; exit 2 ;;
     esac
-    shift
 done
+shift $((OPTIND - 1))
 
-if [ "$SHOWHELP" ]; then
-    usage
-    exit 0
-fi
+[ "$#" -ge 1 ] || { usage; exit 2; }
 
-if [ -z "$*" ]; then
-    usage "need a command to run" >&2
-    exit 2
+# --- Fallback path: no Xvfb available ---
+if ! command -v Xvfb >/dev/null 2>&1; then
+    log "WARNING: Xvfb not found; running command without virtual display."
+    export MPLBACKEND="${MPLBACKEND-Agg}"
+    export QT_QPA_PLATFORM="${QT_QPA_PLATFORM-offscreen}"
+    exec "$@"
 fi
 
-if ! which xauth >/dev/null; then
-    error "xauth command not found"
-    exit 3
+# Required tools if we are using Xvfb
+command -v mktemp >/dev/null 2>&1 || die "Required command not found: mktemp"
+command -v xauth  >/dev/null 2>&1 || die "Required command not found: xauth"
+command -v mcookie >/dev/null 2>&1 || die "Required command not found: mcookie"
+
+# Choose server number
+if [ -z "$SERVERNUM" ]; then
+    SERVERNUM=99
+    if [ -n "$AUTO_SERVERNUM" ]; then
+        while [ -f "/tmp/.X${SERVERNUM}-lock" ]; do
+            SERVERNUM=$((SERVERNUM + 1))
+            [ "$SERVERNUM" -le 200 ] || die "Could not find free X server number"
+        done
+    fi
 fi
 
-# tidy up after ourselves
-trap clean_up EXIT
+# Temp dir and Xauthority
+XVFB_RUN_TMPDIR="$(mktemp -d)" || die "mktemp -d failed"
+AUTHFILE="$XVFB_RUN_TMPDIR/Xauthority"
+: >"$AUTHFILE" || die "Cannot create $AUTHFILE"
 
-# If the user did not specify an X authorization file to use, set up a temporary
-# directory to house one.
-if [ -z "$AUTHFILE" ]; then
-    XVFB_RUN_TMPDIR="$(mktemp -d -t $PROGNAME.XXXXXX)"
-    # Create empty file to avoid xauth warning
-    AUTHFILE=$(tempfile -n "$XVFB_RUN_TMPDIR/Xauthority")
+COOKIE="$(mcookie)" || die "mcookie failed"
+if ! XAUTHORITY="$AUTHFILE" xauth -q add ":$SERVERNUM" MIT-MAGIC-COOKIE-1 "$COOKIE" \
+    2>>"${ERRORFILE:-/dev/stderr}"; then
+    die "xauth failed"
 fi
 
-# Start Xvfb.
-MCOOKIE=$(mcookie)
-tries=10
-while [ $tries -gt 0 ]; do
-    tries=$(( $tries - 1 ))
-    XAUTHORITY=$AUTHFILE xauth source - << EOF >>"$ERRORFILE" 2>&1
-add :$SERVERNUM $XAUTHPROTO $MCOOKIE
-EOF
-    # handle SIGUSR1 so Xvfb knows to send a signal when it's ready to accept
-    # connections
-    trap : USR1
-    (trap '' USR1; exec Xvfb ":$SERVERNUM" $XVFBARGS $LISTENTCP -auth $AUTHFILE >>"$ERRORFILE" 2>&1) &
-    XVFBPID=$!
-
-    wait || :
-    if kill -0 $XVFBPID 2>/dev/null; then
+# Start Xvfb
+log "Starting Xvfb on :$SERVERNUM"
+(
+    exec Xvfb ":$SERVERNUM" -auth "$AUTHFILE" $XVFBARGS
+) >>"${ERRORFILE:-/dev/stderr}" 2>&1 &
+XVFBPID=$!
+
+# Wait for socket
+i=0
+while [ $i -lt 50 ]; do
+    if [ -S "/tmp/.X11-unix/X$SERVERNUM" ]; then
         break
-    elif [ -n "$AUTONUM" ]; then
-        # The display is in use so try another one (if '-a' was specified).
-        SERVERNUM=$((SERVERNUM + 1))
-        SERVERNUM=$(find_free_servernum)
-        continue
     fi
-    error "Xvfb failed to start" >&2
-    XVFBPID=
-    exit 1
+    if ! kill -0 "$XVFBPID" 2>/dev/null; then
+        die "Xvfb died during startup"
+    fi
+    i=$((i + 1))
+    sleep 0.05 2>/dev/null || sleep 1
 done
 
-# Start the command and save its exit status.
-set +e
-DISPLAY=:$SERVERNUM XAUTHORITY=$AUTHFILE "$@"
-RETVAL=$?
-set -e
+[ -S "/tmp/.X11-unix/X$SERVERNUM" ] || die "Xvfb did not start"
 
-# Return the executed command's exit status.
-exit $RETVAL
+# Run command
+export DISPLAY=":$SERVERNUM"
+export XAUTHORITY="$AUTHFILE"
 
-# vim:set ai et sts=4 sw=4 tw=80:
+log "Running: $*"
+exec "$@"