# -*- coding: utf-8 -*-
# :-
# SPDX-FileCopyrightText: © 2026 Franz Glasner
# SPDX-License-Identifier: MIT
# :-
r"""A pseudocode lexer along the lines of CTAN's algpseudocode or
algpseudocodex.

"""

__all__ = ["AlgPseudocodeLexer",
           "AlgPseudocodeLexer_DE", "AlgPseudocodeLexer_FR"]


import re

import pygments.util
from pygments.lexer import include, bygroups
from pygments.token import (Comment, Keyword, Name, Text, Whitespace)

#
# Relative imports do not work with pygments.lexers.load_lexer_from_file()
# in all of our supported Python releases.
#
from pygments_lexer_pseudocode2.bases import LexBase


class AlgPseudocodeLexer(LexBase):

    """A pseudocode lexer along the lines of CTAN's algpseudocode or
    algpseudocodex.

    Some ideas (e.g. strings) are borrowed from Pygment's Python lexer.

    """

    name = "AlgPseudocode"
    aliases = ["algpseudocode", "algpseudo"]
    filenames = ["*.algpseudo", "*.algpseudocode"]
    mimetypes = []
    flags = re.MULTILINE

    LANG = "en"
    TRANSLATIONS = {
        "PROG": "PROGRAM",
        "PROGRAM": "PROGRAM",
        "ALGO": "ALGORITHM",
        "ALGORITHM": "ALGORITHM",
        "PROC": "PROCEDURE",
        "PROCEDURE": "PROCEDURE",
        "FUNC": "FUNCTION",
        "FUNCTION": "FUNCTION",
        "FN": "FUNCTION",
        "CLASS": "CLASS",
        "IS": "IS",
    }
    END_TRANSLATIONS = {
        "PROG": "END OF PROGRAM",
        "PROGRAM": "END OF PROGRAM",
        "ALGO": "END OF ALGORITHM",
        "ALGORITHM": "END OF ALGORITHM",
        "PROC": "END OF PROCEDURE",
        "PROCEDURE": "END OF PROCEDURE",
        "FUNC": "END OF FUNCTION",
        "FUNCTION": "END OF FUNCTION",
        "FN": "END OF FUNCTION",
        "CLASS": "END OF CLASS",
    }
    DEFAULT_END_PREFIX = "END OF "
    SYMBOL_REMARK = "▷"            # U+25B7: Unicode 1.0 (Geometric Shapes)
    # SYMBOL_REMARK = "▻"          # U+25BB: Unicode 1.0 (Geometric Shapes)
    SYMBOL_BLOCK = "◆"             # U+25C6: Unicode 1.0 (Geometric Shapes)
    # SYMBOL_BLOCK = "┃"           # U+2503: Unicode 1.0 (Bow Drawing)
    # SYMBOL_BLOCK = "●"           # U+25CF: Unicode 1.0 (Geometric Shapes)
    SYMBOL_TEXTSTATEMENT = "■"     # U+25A0: Unicode 1.0 (Geometric Shapes)
    SYMBOLS = {
        "REMARK": SYMBOL_REMARK,
        "Remark": SYMBOL_REMARK,
        "remark": SYMBOL_REMARK,
        "REM": SYMBOL_REMARK,
        "Rem": SYMBOL_REMARK,
        "rem": SYMBOL_REMARK,
        "R": SYMBOL_REMARK,
        "r": SYMBOL_REMARK,
        "BLOCK": SYMBOL_BLOCK,
        "Block": SYMBOL_BLOCK,
        "block": SYMBOL_BLOCK,
        "TEXTSTATEMENT": SYMBOL_TEXTSTATEMENT,
        "TextStatement": SYMBOL_TEXTSTATEMENT,
        "textstatement":  SYMBOL_TEXTSTATEMENT,
        "TSTATEMENT": SYMBOL_TEXTSTATEMENT,
        "TStatement": SYMBOL_TEXTSTATEMENT,
        "tstatement":  SYMBOL_TEXTSTATEMENT,
        "TSTATE": SYMBOL_TEXTSTATEMENT,
        "TState": SYMBOL_TEXTSTATEMENT,
        "tstate": SYMBOL_TEXTSTATEMENT,
        "TEXT": SYMBOL_TEXTSTATEMENT,
        "Text": SYMBOL_TEXTSTATEMENT,
        "text": SYMBOL_TEXTSTATEMENT,
    }

    def op_translate(toktype):

        def _op_translate(lexer, match, ctx=None):
            kw = match.group().upper()
            yield match.start(), toktype, lexer.TRANSLATIONS.get(kw, kw)

        return _op_translate

    def op_opt_end_translate(toktype):

        def _op_end_translate(lexer, match, ctx=None):
            if not lexer.no_end:
                kw = match.group().upper()
                yield (match.start(),
                       toktype,
                       lexer.END_TRANSLATIONS.get(
                           kw,
                           lexer.DEFAULT_END_PREFIX + kw))

        return _op_end_translate

    def op_opt_ignore(toktype):

        def _op_opt_ignore(lexer, match, ctx=None):
            if not lexer.no_end:
                yield match.start(), toktype, match.group()

        return _op_opt_ignore

    def op_symbol(toktype):

        def _op_symbol(lexer, match, ctx=None):
            kw = match.group()
            yield match.start(), toktype, lexer.SYMBOLS.get(kw, kw)

        return _op_symbol

    tokens = {
        "root": [
            (r"\n", Whitespace),
            (r"/\*", Comment.Multiline, "multiline-nested-comment"),
            (r"//.*$", Comment.Single),
            (r"(?:\\)(REMARK|Remark|remark|REM|Rem|rem|R|r)\b(.*)$",
             bygroups(op_symbol(Comment.Single), Comment.Single)),
            (r"(?:\\)(BLOCK|Block|block)\b(.*)$",
             bygroups(op_symbol(Text), Text)),
            (r"\\\n", Text),
            (r"(?i)\\("
             r"(?:prog(?:ram)?)"
             r"|(?:algo(?:rithm)?)"
             r"|(?:proc(?:edure)?)"
             r"|(?:func(?:tion)?|(?:fn))"
             r"|(?:class)"
             r")(\s*)(\{)",
             bygroups(op_translate(Keyword), Whitespace, LexBase.op_ignore),
             "entity-name"),
            # ENDxxx keywords with optional entity name
            #   with name
            (r"(?i)\\end(?:_|-)?("
             r"(?:prog(?:ram)?)"
             r"|(?:algo(?:rithm)?)"
             r"|(?:proc(?:edure)?)"
             r"|(?:func(?:tion)?)"
             r"|(?:class)"
             r")(\s*)(\{)",
             bygroups(op_opt_end_translate(Keyword),
                      op_opt_ignore(Whitespace),
                      LexBase.op_ignore),
             "entity-name-end"),
            #   without name
            (r"(?i)\\end(?:_|-)?("
             r"(?:prog(?:ram)?)"
             r"|(?:algo(?:rithm)?)"
             r"|(?:proc(?:edure)?)"
             r"|(?:func(?:tion)?)"
             r"|(?:class)"
             r")\b",
             bygroups(op_opt_end_translate(Keyword))),
            # Keywords
            (r"(?i)\\("
             r"(?:is)"
             r")\b",
             bygroups(op_translate(Keyword))),
            include("expr"),
            (r"\s+", Text),
        ],
        "entity-name": [      # may be multiline
            (r"[^\\}]+", Name.Entity),
            (r"\\\}", Name.Entity),
            (r"\\", Name.Entity),
            (r"\}", LexBase.op_ignore, "#pop"),
        ],
        "entity-name-end": [  # may be multiline -- suppressed if no_end
            (r"[^\\}]+", op_opt_ignore(Name.Entity)),
            (r"\\\}", op_opt_ignore(Name.Entity)),
            (r"\\", op_opt_ignore(Name.Entity)),
            (r"\}", LexBase.op_ignore, "#pop"),
        ],
        "expr": [
            include("py-strings"),
            include("py-numbers"),
            include("py-name"),
        ]
    }

    def __init__(self, **options):
        val = pygments.util.get_bool_opt(options, "no_end", default=False)
        self.no_end = val
        LexBase.__init__(self, **options)


class AlgPseudocodeLexer_DE(AlgPseudocodeLexer):

    name = "AlgPseudocodeDE"
    aliases = ["algpseudocode-de", "algpseudo-de"]
    filenames = ["*.algpseudo-de", "*.algpseudocode-de"]

    LANG = "de"
    TRANSLATIONS = AlgPseudocodeLexer.TRANSLATIONS.copy()
    TRANSLATIONS.update({
        "PROG": "PROGRAMM",
        "PROGRAM": "PROGRAMM",
        "ALGO": "ALGORITHMUS",
        "ALGORITHM": "ALGORITHMUS",
        "PROC": "PROZEDUR",
        "PROCEDURE": "PROZEDUR",
        "FUNC": "FUNKTION",
        "FUNCTION": "FUNKTION",
        "FN": "FUNKTION",
        "CLASS": "KLASSE",
        "IS": "IST",
    })
    END_TRANSLATIONS = AlgPseudocodeLexer.END_TRANSLATIONS.copy()
    END_TRANSLATIONS.update({
        "PROG": "ENDE DES PROGRAMMS",
        "PROGRAM": "ENDE VON PROGRAMMS",
        "ALGO": "ENDE DES ALGORITHMUS",
        "ALGORITHM": "ENDE DES ALGORITHMUS",
        "PROC": "ENDE DER PROZEDUR",
        "PROCEDURE": "ENDE DER PROZEDUR",
        "FUNC": "ENDE DER FUNKTION",
        "FUNCTION": "ENDE DER FUNKTION",
        "FN": "ENDE DER FUNKTION",
        "CLASS": "ENDE DER KLASSE",
    })
    DEFAULT_END_PREFIX = "ENDE VON "


class AlgPseudocodeLexer_FR(AlgPseudocodeLexer):

    name = "AlgPseudocodeFR"
    aliases = ["algpseudocode-fr", "algpseudo-fr"]
    filenames = ["*.algpseudo-fr", "*.algpseudocode-fr"]

    LANG = "de"
    TRANSLATIONS = AlgPseudocodeLexer.TRANSLATIONS.copy()
    TRANSLATIONS.update({
        "PROG": "PROGRAMME",
        "PROGRAM": "PROGRAMME",
        "ALGO": "ALGORITHME",
        "ALGORITHM": "ALGORITHME",
        "PROC": "PROCÉDURE",
        "PROCEDURE": "PROCÉDURE",
        "FUNC": "FONCTION",
        "FUNCTION": "FOUNCTION",
        "FN": "FONCTION",
        "CLASS": "CLASSE",
        "IS": "EST",
    })
    END_TRANSLATIONS = AlgPseudocodeLexer.END_TRANSLATIONS.copy()
    END_TRANSLATIONS.update({
        "PROG": "FIN DE PROGRAMME",
        "PROGRAM": "FIN DE PROGRAMME",
        "ALGO": "FIN D'ALGORITHME",
        "ALGORITHM": "FIN D'ALGORITHME",
        "PROC": "FIN DE PROCÉDURE",
        "PROCEDURE": "FIN DE PROCÉDURE",
        "FUNC": "FIN DE FONCTION",
        "FUNCTION": "FIN DE FOUNCTION",
        "FN": "FIN DE FONCTION",
        "CLASS": "FIN DE CLASSE",
    })
    DEFAULT_END_PREFIX = "FIN DE "