add copyright headers and check script

.gitignore

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: LGPL-3.0-or-later
+# See Notices.txt for copyright information
 /.venv
 /.vscode
 *.egg-info

README.md

@@ -1,3 +1,7 @@
+<!--
+SPDX-License-Identifier: LGPL-3.0-or-later
+See Notices.txt for copyright information
+-->
 parser for the OPF PowerISA 3.1C pdf to attempt to extract all instructions' pseudo-code including subscripts/superscripts and other formatting
 
 Usage:

parse_powerisa_pdf/parse_powerisa_pdf.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: LGPL-3.0-or-later
+# See Notices.txt for copyright information
 from __future__ import annotations
 from collections import defaultdict
 from collections.abc import Generator, Iterable, Iterator, Callable

parse_powerisa_pdf/quad_tree.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: LGPL-3.0-or-later
+# See Notices.txt for copyright information
 from __future__ import annotations
 from typing import Callable, Generic, Iterable, Iterator, TypeVar
 from math import frexp, isfinite, isnan, ldexp

parse_powerisa_pdf/set_by_id.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: LGPL-3.0-or-later
+# See Notices.txt for copyright information
 from collections import abc
 from typing import Callable, Generic, Iterable, Iterator, Protocol, TypeAlias, TypeVar, overload
 

pyproject.toml

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: LGPL-3.0-or-later
+# See Notices.txt for copyright information
 [build-system]
 requires = ["setuptools >= 61.0"]
 build-backend = "setuptools.build_meta"

scripts/check-copyright.sh

@@ -0,0 +1,63 @@
+#!/bin/bash
+# SPDX-License-Identifier: LGPL-3.0-or-later
+# See Notices.txt for copyright information
+set -e
+
+function fail()
+{
+    local error="$1"
+    echo "error: $error" >&2
+    exit 1
+}
+
+function fail_file()
+{
+    local file="$1" line="$2" error="$3"
+    fail "$file:$((line + 1)): $error"
+}
+
+function check_file()
+{
+    local file="$1" regexes=("${@:2}")
+    local lines
+    mapfile -t lines < "$file"
+    if (("${#lines[@]}" == 0)); then
+        return # empty file, no copyright needed
+    fi
+    local line
+    for line in "${!regexes[@]}"; do
+        eval '[[ "${lines[i]}" =~ '"${regexes[i]}"' ]]' ||
+            fail_file "$file" "$line" "doesn't match regex: ${regexes[i]}"
+    done
+}
+
+POUND_HEADER=('^"# SPDX-License-Identifier: LGPL-3.0-or-later"$' '^"# See Notices.txt for copyright information"$')
+MD_HEADER=('^"<!--"$' '^"SPDX-License-Identifier: LGPL-3.0-or-later"$' '^"See Notices.txt for copyright information"$')
+
+function main()
+{
+    local IFS=$'\n'
+    [[ -z "$(git status --porcelain)" ]] || fail "git repo is dirty"
+    local file
+    for file in $(git ls-tree --name-only --full-tree -r HEAD); do
+        case "/$file" in
+        */LICENSE.md|*/Notices.txt)
+            # copyright file
+            ;;
+        /.forgejo/workflows/*.yml|*/.gitignore|*.toml|*.py)
+            check_file "$file" "${POUND_HEADER[@]}"
+            ;;
+        *.md)
+            check_file "$file" "${MD_HEADER[@]}"
+            ;;
+        *.sh)
+            check_file "$file" '^'\''#!'\' "${POUND_HEADER[@]}"
+            ;;
+        *)
+            fail_file "$file" 0 "unimplemented file kind -- you need to add it to $0"
+            ;;
+        esac
+    done
+}
+
+main