kit

run_file_escape.sh (2745B)

---

 #!/usr/bin/env bash
 # test/pp/run_file_escape.sh — regression for __FILE__ string-literal escaping.
 #
 # __FILE__ expands to a string literal of the source path. On POSIX paths use
 # '/', so wrapping the raw name in quotes happens to be a valid string literal;
 # on Windows the path holds backslashes (C:\Users\...), and emitting them raw
 # turns '\U'/'\u'/'\x' into bogus escape sequences — '\Users' was diagnosed as a
 # "malformed UCN" and other components (e.g. '\r') silently corrupted the value.
 # The preprocessor must escape '\' and '"' when building the __FILE__ literal.
 #
 # This reproduces the OS-path case faithfully (a backslash IS a legal filename
 # byte on POSIX): we create files whose *names* contain backslashes/quotes and
 # compile them, rather than a #line override (whose escapes are already in the
 # token spelling, so it cannot reproduce the raw-path bug). A #line case is
 # included too, to guard the symmetric destringize-then-re-escape path.
 #
 # Host-target only: each input is a self-contained TU (no includes), so no
 # sysroot is needed and the test runs anywhere build/kit exists.
 
 set -u
 
 ROOT=${KIT_TEST_ROOT:-$(cd "$(dirname "$0")/../.." && pwd)}
 KIT=${KIT:-"$ROOT/build/kit"}
 export KIT
 
 KIT_KIT_DIR="$ROOT/test/lib"
 . "$ROOT/test/lib/kit_sh_kit.sh"
 kit_require_kit pp-file-escape
 
 kit_report_init
 work=$(mktemp -d "${TMPDIR:-/tmp}/kit-pp-fesc.XXXXXX")
 trap 'rm -rf "$work"' EXIT
 cd "$work" || exit 2
 
 # emit_has NAME SRCFILE NEEDLE : `kit cc -E SRCFILE` must succeed and its output
 # must contain NEEDLE (the correctly-escaped spelling).
 emit_has() {
     name=$1; src=$2; needle=$3
     if "$KIT" cc -E "$src" -o "$name.pp" >"$work/$name.out" 2>"$work/$name.err"; then
         contains "$name" "$name.pp" "$needle"
     else
         not_ok "$name" "$work/$name.err"
     fi
 }
 
 # --- raw OS path: '\U' was the hard "malformed UCN" error -------------------
 printf 'const char *f = __FILE__;\n' > 'seg\Uone.c'
 emit_has emit_escape_U 'seg\Uone.c' 'seg\\Uone.c'
 run_ok compile_backslash_U "$KIT" cc -c 'seg\Uone.c' -o "$work/u.o"
 
 # --- raw OS path: '\r' silently injected a carriage return (no error) -------
 printf 'const char *f = __FILE__;\n' > 'seg\rtwo.c'
 emit_has emit_escape_r 'seg\rtwo.c' 'seg\\rtwo.c'
 
 # --- embedded double-quote in the name must escape too ----------------------
 printf 'const char *f = __FILE__;\n' > 'q"three.c'
 emit_has emit_escape_quote 'q"three.c' 'q\"three.c'
 
 # --- #line override: destringize-then-re-escape must stay correct -----------
 printf '#line 7 "a\\\\Users\\\\z.c"\nconst char *f = __FILE__;\n' > 'lineov.c'
 emit_has emit_line_override 'lineov.c' '"a\\Users\\z.c"'
 run_ok compile_line_override "$KIT" cc -c 'lineov.c' -o "$work/l.o"
 
 kit_summary pp-file-escape
 kit_exit