M2compiler-V3/tools/v3-corpus/corpus.sh

#!/bin/sh
# Runs the V3 compiler (compiler/M2) over a corpus of standard Modula-2
# sources and reports how many compile cleanly.
#
# Each source is copied into a scratch tree (so its .LST listing never
# touches the corpus) and compiled alone, together with:
#   * its sibling DEFINITION (same basename, .def/.DEF) when present, and
#   * the DEFINITION of every module it imports, searched in the source
#     directory and in the -I-style library dirs listed in $V3_LIBS
#     (colon-separated), so cross-module imports resolve.
#
# A file with 0 errors is a pass.  Failures are split into CRASH (M2
# died), LIB (an import still unresolved: no .def found) and LANG (a
# real V3 gap).
#
# Usage: ./corpus.sh [corpus-dir ...]
cd "$(dirname "$0")"
ROOT="$(cd ../.. && pwd)"
M2="$ROOT/compiler/M2"
WORK=/tmp/opencode/v3corpus
KNOWN="SYSTEM libc SysIO TextIO Strings Math Conversions RealIO ProgramArgs IOChan Files Storage WholeIO CharClass SysClock"
[ -x "$M2" ] || { echo "compiler/M2 missing -- run compiler/build.sh"; exit 1; }
[ "$#" -gt 0 ] || set -- \
  "$HOME/Projets/Projets-Modula2/MyWork/gcc-git/gcc/testsuite/gm2/pim/pass" \
  "$HOME/Projets/Projets-Modula2/MyWork/gcc-git/gcc/testsuite/gm2/iso/run/pass"

known() { for k in $KNOWN; do [ "$1" = "$k" ] && return 0; done; return 1; }

# find a DEFINITION file for module $1 in the source dir or $V3_LIBS
finddef() {
  for d in "$scrdir" $(echo "$V3_LIBS" | tr ':' ' '); do
    [ -d "$d" ] || continue
    for cand in "$d/$1.def" "$d/$1.DEF" "$d/$(echo "$1" | tr 'A-Z' 'a-z').def"; do
      [ -f "$cand" ] && { echo "$cand"; return; }
    done
  done
}

# extract imported module names from a source
imports() {
  { sed -nE 's/^[[:space:]]*FROM[[:space:]]+([A-Za-z][A-Za-z0-9_]*).*/\1/p' "$1"
    sed -nE 's/^[[:space:]]*IMPORT[[:space:]]+(.*)/\1/p' "$1" | sed 's/;.*//' | tr ',' '\n'
  } | sed -E 's/[[:space:]]//g' | grep -E '^[A-Za-z][A-Za-z0-9_]*$'
}

# Transitively collect the DEFINITION of module $1 (and its own imports)
# into $w, appending each def (dependency order) to $deplist.  Sets
# $lib=1 when a needed definition cannot be found.  Uses $1 (per-call)
# rather than globals so recursion is safe.
adddef() {
  known "$1" && return
  case " $seen " in *" $1 "*) return;; esac
  if [ -z "$(finddef "$1")" ]; then lib=1; return; fi
  seen="$seen $1"
  for mm in $(imports "$(finddef "$1")"); do adddef "$mm"; done
  adf=$(finddef "$1")
  cp "$adf" "$w/$(basename "$adf")"
  deplist="$deplist $w/$(basename "$adf")"
}

rm -rf "$WORK"; mkdir -p "$WORK"; : > "$WORK/results.txt"
n=0
for scrdir in "$@"; do
  find "$scrdir" -maxdepth 1 \( -iname '*.mod' -o -iname '*.def' \) 2>/dev/null | sort |
  while read -r f; do
    n=$((n+1))
    w="$WORK/f$n"; mkdir -p "$w"; base=$(basename "$f")
    cp "$f" "$w/$base"
    lib=0; deplist=""; seen=""
    # the base file's imports, transitively (dependency order)
    for m in $(imports "$w/$base"); do adddef "$m"; done
    basedeps="$deplist"; deplist=""
    # sibling DEFINITION (same basename) and its own imports
    sibfile=""
    case "$base" in
      *.mod|*.MOD)
        sib="$(echo "$base" | sed -E 's/\.[^.]*$/.def/')"
        [ -f "$scrdir/$sib" ] || sib="$(echo "$base" | sed -E 's/\.[^.]*$/.DEF/')"
        if [ -f "$scrdir/$sib" ]; then
          cp "$scrdir/$sib" "$w/$sib"; sibfile="$w/$sib"
          for m in $(imports "$sibfile"); do adddef "$m"; done
        fi
        ;;
    esac
    files="$basedeps $deplist $sibfile $w/$base"
    "$M2" $files >/dev/null 2>&1
    rc=$?
    lst="$w/$(echo "$base" | sed 's/\.[^.]*$//').LST"
    if [ "$rc" -ge 128 ]; then echo "CRASH||$f" >> "$WORK/results.txt"; continue; fi
    if [ ! -f "$lst" ]; then echo "LANG|no listing|$f" >> "$WORK/results.txt"; continue; fi
    e=$(grep -oE '[0-9]+ errors?' "$lst" | head -1 | grep -oE '[0-9]+')
    [ -z "$e" ] && e=-1
    if [ "$e" = 0 ]; then echo "OK||$f" >> "$WORK/results.txt"; continue; fi
    m=$(grep -E '^\*\*\*\*\*' "$lst" | head -1 | sed -E 's/^\*\*\*\*\* *\^? *//; s/^\*\*\*\*\*//')
    if [ "$lib" = 1 ]; then echo "LIB|$m|$f" >> "$WORK/results.txt"
    else echo "LANG|$m|$f" >> "$WORK/results.txt"; fi
  done
done
total=$(wc -l < "$WORK/results.txt")
cnt() { grep -c "^$1" "$WORK/results.txt" 2>/dev/null || true; }
echo "total      : $total"
echo "compile-OK : $(cnt OK)"
echo "CRASH      : $(cnt CRASH)"
echo "LIB (unresolved import): $(cnt LIB)"
echo "LANG (V3 gap)          : $(cnt LANG)"
echo "=== LANG error kinds (top) ==="
grep '^LANG' "$WORK/results.txt" | cut -d'|' -f2 | sed -E 's/[0-9]+/N/g' | sort | uniq -c | sort -rn | head -15
echo "=== LANG files (first 40) ==="
grep '^LANG' "$WORK/results.txt" | head -40 | sed -E 's/^LANG\|([^|]*)\|/  [\1] /'