ackandClaude Fable 5.1
715d939727
- CRLF line endings are read as newlines on every system (the reader used to delete the pair, collapsing a Notepad++ file into one line on Linux and macOS); a leading UTF-8 byte-order mark is ignored; a UTF-16 or Windows-1252 source is refused with the encoding, the place and the remedy named. .gitattributes pins LF in every clone. - Windows source install: the repository path must hold no space (GNU Make), accented letters are fine (every linker input is relative now); python.org's Python is selected ahead of an MSYS2 one that poppler pulls in; TeX Live goes to its Windows default C:\texlive\2026. - The Python binding needs an ASCII installation path on Windows, and its suite says so there. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
193 lines
6.8 KiB
Bash
Executable File
193 lines
6.8 KiB
Bash
Executable File
#!/bin/bash
|
|
#
|
|
# filename_test.sh — Regression tests for filenames containing spaces.
|
|
#
|
|
# Filenames may contain spaces. The rules (see CLAUDE.md "Output directory
|
|
# policy" and the filename-list functions in mac/file.cpp):
|
|
# - argv boundaries are authoritative: a shell-quoted "my file.kt" is one
|
|
# filename (Argv stores the original argv vector; nothing re-splits it).
|
|
# - A filename LIST is separated by a standalone "/" token (whitespace on
|
|
# both sides) — never a legal input filename, since "/" alone is the
|
|
# root directory.
|
|
# - Rescue: without a separator, whitespace-split names that do not exist
|
|
# are greedily rejoined with their neighbors into names that do; the
|
|
# regrouping is announced on stderr.
|
|
# - A leading "~/" expands to $HOME (shells do not expand a quoted tilde).
|
|
#
|
|
# Engine tier: uses --klammersets none; no SKS.
|
|
#
|
|
# Usage: ./filename_test.sh
|
|
# Exit code: 0 if all tests pass, 1 otherwise.
|
|
|
|
PASS=0
|
|
FAIL=0
|
|
KTEXT=ktext
|
|
K=${KLAMMERTEXT_HOME:?KLAMMERTEXT_HOME must be set}
|
|
|
|
red=$'\033[31m'
|
|
green=$'\033[32m'
|
|
bold=$'\033[1m'
|
|
reset=$'\033[0m'
|
|
|
|
# Scratch input files
|
|
DIR=$(mktemp -d)
|
|
trap 'rm -rf "$DIR"' EXIT
|
|
mkdir "$DIR/my dir"
|
|
printf 'ALPHA\n' > "$DIR/my file.kt"
|
|
printf 'BETA\n' > "$DIR/b.kt"
|
|
printf 'GAMMA\n' > "$DIR/my dir/c.kt"
|
|
printf '\357\273\277DELTA\n' > "$DIR/bom.kt" # a UTF-8 byte-order mark, then the text
|
|
printf 'EPSILON\r\nZETA\r\n' > "$DIR/crlf.kt" # Windows line endings
|
|
printf '\377\376h\000i\000\n\000' > "$DIR/utf16.kt" # UTF-16LE with its byte-order mark
|
|
printf 'ETA\nTHETA M\374ller\n' > "$DIR/cp1252.kt" # Windows-1252: an umlaut that is not UTF-8
|
|
cd "$DIR" || exit 1
|
|
|
|
# check TEST_NAME EXPECTED_STDOUT EXPECTED_STDERR_SUBSTRING KTEXT_ARGS...
|
|
# EXPECTED_STDERR_SUBSTRING may be "" (no stderr requirement).
|
|
check() {
|
|
local test_name="$1" expected="$2" err_needle="$3"
|
|
shift 3
|
|
local output status errfile=$DIR/.stderr
|
|
output=$("$KTEXT" "$@" 2>"$errfile")
|
|
status=$?
|
|
output=$(printf '%s' "$output" | sed -e 's/[ \t]*$//' | grep -v '^$')
|
|
if [ $status -ne 0 ]; then
|
|
echo "${red}FAIL${reset} $test_name — ktext exited $status"
|
|
echo " stderr: $(head -3 "$errfile")"
|
|
FAIL=$((FAIL + 1))
|
|
return
|
|
fi
|
|
if [ "$output" != "$expected" ]; then
|
|
echo "${red}FAIL${reset} $test_name"
|
|
echo " expected: [$expected]"
|
|
echo " got: [$output]"
|
|
FAIL=$((FAIL + 1))
|
|
return
|
|
fi
|
|
if [ -n "$err_needle" ] && ! grep -qF "$err_needle" "$errfile"; then
|
|
echo "${red}FAIL${reset} $test_name — expected stderr to contain [$err_needle]"
|
|
echo " stderr: $(head -3 "$errfile")"
|
|
FAIL=$((FAIL + 1))
|
|
return
|
|
fi
|
|
echo "${green}PASS${reset} $test_name"
|
|
PASS=$((PASS + 1))
|
|
}
|
|
|
|
# check_error TEST_NAME EXPECTED_SUBSTRING KTEXT_ARGS...
|
|
# Expects a nonzero exit whose combined output contains EXPECTED_SUBSTRING.
|
|
check_error() {
|
|
local test_name="$1" needle="$2"
|
|
shift 2
|
|
local output status
|
|
output=$("$KTEXT" "$@" 2>&1)
|
|
status=$?
|
|
if [ $status -eq 0 ]; then
|
|
echo "${red}FAIL${reset} $test_name — expected an error, got exit 0"
|
|
FAIL=$((FAIL + 1))
|
|
return
|
|
fi
|
|
if echo "$output" | grep -qF "$needle"; then
|
|
echo "${green}PASS${reset} $test_name"
|
|
PASS=$((PASS + 1))
|
|
else
|
|
echo "${red}FAIL${reset} $test_name — expected output to contain [$needle]"
|
|
echo " output: $(echo "$output" | head -3)"
|
|
FAIL=$((FAIL + 1))
|
|
fi
|
|
}
|
|
|
|
echo "${bold}Filename-with-spaces tests${reset}"
|
|
echo "======================="
|
|
|
|
check "1. quoted filename with a space is one file" \
|
|
"ALPHA" "" \
|
|
"my file.kt" -d --klammersets none
|
|
|
|
# The regrouping is a DERIVED value -- the command completed a name the input
|
|
# left ambiguous -- so since 2026-08-15 it is reported at "-v 1" and the
|
|
# default run is silent. Silence is safe because a rescue only succeeds when
|
|
# the joined name names an existing file: a mistyped name fails instead of
|
|
# resolving to something else.
|
|
check "2. unquoted spaces are rescued into an existing file" \
|
|
"ALPHA" "" \
|
|
my file.kt -d --klammersets none
|
|
|
|
check "2a. ... silently at the default verbosity" \
|
|
"ALPHA" "" \
|
|
my file.kt -d --klammersets none
|
|
|
|
check "2b. ... and reported at -v 1" \
|
|
"ALPHA" "interpreting \"my file.kt\" as one filename" \
|
|
my file.kt -d --klammersets none -v 1
|
|
|
|
case "$(uname -s)" in
|
|
MINGW*|MSYS*)
|
|
# The MSYS shell rewrites a bare "/" argument into the MSYS root
|
|
# (C:/msys64/) before a native program sees it; a Windows user in
|
|
# PowerShell or cmd is not affected, so the feature is not what fails.
|
|
echo "SKIP 3. standalone / separates a filename list (the MSYS shell rewrites a bare /)";;
|
|
*)
|
|
check "3. standalone / separates a filename list" \
|
|
"ALPHA
|
|
BETA" "" \
|
|
my file.kt / b.kt -d --klammersets none
|
|
;;
|
|
esac
|
|
|
|
check "4. space in a directory component" \
|
|
"GAMMA" "" \
|
|
"my dir/c.kt" -d --klammersets none
|
|
|
|
check "5. quoted name that exists is never split (b.kt also exists)" \
|
|
"ALPHA" "" \
|
|
"my file.kt" -d --klammersets none
|
|
|
|
HOME="$DIR" check "6. quoted ~/ expands to \$HOME inside ktext" \
|
|
"BETA" "" \
|
|
"~/b.kt" -d --klammersets none
|
|
|
|
check "7. @read argument keeps its internal space" \
|
|
"ALPHA" "" \
|
|
-s '@read my file.kt @' -d --klammersets none
|
|
|
|
check_error "8. unrescuable name is reported as written" \
|
|
"no such.kt" \
|
|
"no such.kt" -d --klammersets none
|
|
|
|
# A leading UTF-8 byte-order mark is ignored (2026-09-26): Windows tools write
|
|
# one, and it was reported as "Word not parsed" at 1:1 with an invisible word.
|
|
check "9. a leading UTF-8 BOM in the input file is ignored" \
|
|
"DELTA" "" \
|
|
bom.kt -d --klammersets none
|
|
|
|
check "10. a leading UTF-8 BOM in a @read file is ignored" \
|
|
"DELTA" "" \
|
|
-s '@read bom.kt @' -d --klammersets none
|
|
|
|
# Windows line endings are newlines (2026-09-26): the reader DELETED the pair,
|
|
# so on Linux and macOS a CRLF file collapsed into one line.
|
|
check "11. CRLF line endings are read as newlines" \
|
|
$'EPSILON\nZETA' "" \
|
|
crlf.kt -d --klammersets none
|
|
|
|
# What a Windows editor can also save (2026-09-26): a UTF-16 file and an
|
|
# ANSI (Windows-1252) file are named as such, with the remedy, instead of
|
|
# "Word not parsed" or a failure inside the embedded Python.
|
|
check_error "12. a UTF-16 file is named as such" \
|
|
"UTF-16" \
|
|
utf16.kt -d --klammersets none
|
|
|
|
check_error "13. a Windows-1252 file is located at its first non-UTF-8 byte" \
|
|
"line 2, character 8" \
|
|
cp1252.kt -d --klammersets none
|
|
|
|
check_error "14. ... through @read as well" \
|
|
"not UTF-8" \
|
|
-s '@read cp1252.kt @' -d --klammersets none
|
|
|
|
echo
|
|
echo "======================="
|
|
echo "Results: ${green}$PASS passed${reset}, ${red}$FAIL failed${reset}"
|
|
[ $FAIL -eq 0 ]
|