|
| 1 | +# -*- coding: utf-8 -*- |
| 2 | +# Copyright (C) 2021 Rocky Bernstein <[email protected]> |
| 3 | +# This program is free software: you can redistribute it and/or modify |
| 4 | +# it under the terms of the GNU General Public License as published by |
| 5 | +# the Free Software Foundation, either version 3 of the License, or |
| 6 | +# (at your option) any later version. |
| 7 | +# |
| 8 | +# This program is distributed in the hope that it will be useful, |
| 9 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 | +# GNU General Public License for more details. |
| 12 | +# |
| 13 | +# You should have received a copy of the GNU General Public License |
| 14 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. |
| 15 | + |
| 16 | +from enum import Enum |
| 17 | +import os.path as osp |
| 18 | +import re |
| 19 | + |
| 20 | +from typing import Iterable, NamedTuple |
| 21 | + |
| 22 | +from mathics.core.expression import strip_context |
| 23 | +from mathics_scanner import named_characters |
| 24 | +from mathics_pygments.lexer import Regex |
| 25 | +from prompt_toolkit.completion import CompleteEvent, Completion, WordCompleter |
| 26 | +from prompt_toolkit.document import Document |
| 27 | + |
| 28 | +SYMBOLS = fr"[`]?({Regex.IDENTIFIER}|{Regex.NAMED_CHARACTER})(`({Regex.IDENTIFIER}|{Regex.NAMED_CHARACTER}))+[`]?" |
| 29 | + |
| 30 | +if False: # FIXME reinstate this |
| 31 | + NAMED_CHARACTER_START = fr"\\\[{Regex.IDENTIFIER}" |
| 32 | + FIND_MATHICS_WORD_RE = re.compile( |
| 33 | + fr"({NAMED_CHARACTER_START})|(?:.*[\[\(])?({SYMBOLS}$)" |
| 34 | + ) |
| 35 | +FIND_MATHICS_WORD_RE = re.compile(r"((?:\[)?[^\s]+)") |
| 36 | + |
| 37 | + |
| 38 | +class TokenKind(Enum): |
| 39 | + Null = "Null" |
| 40 | + NamedCharacter = "NamedCharacter" |
| 41 | + Symbol = "Symbol" |
| 42 | + ASCII_Operator = "ASCII_Operator" |
| 43 | + EscapeSequence = "EscapeSequence" # Not working yet |
| 44 | + |
| 45 | + |
| 46 | +# TODO: "kind" could be an enumeration: of "Null", "Symbol", "NamedCharacter" |
| 47 | +WordToken = NamedTuple("WordToken", [("text", str), ("kind", TokenKind)]) |
| 48 | + |
| 49 | + |
| 50 | +def get_datadir(): |
| 51 | + datadir = osp.normcase(osp.join(osp.dirname(osp.abspath(__file__)), "data")) |
| 52 | + return osp.realpath(datadir) |
| 53 | + |
| 54 | + |
| 55 | +class MathicsCompleter(WordCompleter): |
| 56 | + def __init__(self, definitions): |
| 57 | + self.definitions = definitions |
| 58 | + self.completer = WordCompleter([]) |
| 59 | + self.named_characters = [name + "]" for name in named_characters.keys()] |
| 60 | + |
| 61 | + # From WordCompleter, adjusted with default values |
| 62 | + self.ignore_case = True |
| 63 | + self.display_dict = {} |
| 64 | + self.meta_dict = {} |
| 65 | + self.WORD = False |
| 66 | + self.sentence = False |
| 67 | + self.match_middle = False |
| 68 | + self.pattern = None |
| 69 | + |
| 70 | + try: |
| 71 | + import ujson |
| 72 | + except ImportError: |
| 73 | + import json as ujson |
| 74 | + # Load tables from disk |
| 75 | + with open(osp.join(get_datadir(), "mma-tables.json"), "r") as f: |
| 76 | + _data = ujson.load(f) |
| 77 | + |
| 78 | + # @ is not really an operator |
| 79 | + self.ascii_operators = frozenset(_data["ascii-operators"]) |
| 80 | + from mathics_scanner.characters import aliased_characters |
| 81 | + |
| 82 | + self.escape_sequences = aliased_characters.keys() |
| 83 | + |
| 84 | + def _is_space_before_cursor(self, document, text_before_cursor: bool) -> bool: |
| 85 | + """Space before or no text before cursor.""" |
| 86 | + return text_before_cursor == "" or text_before_cursor[-1:].isspace() |
| 87 | + |
| 88 | + def get_completions( |
| 89 | + self, document: Document, complete_event: CompleteEvent |
| 90 | + ) -> Iterable[Completion]: |
| 91 | + # Get word/text before cursor. |
| 92 | + word_before_cursor, kind = self.get_word_before_cursor_with_kind(document) |
| 93 | + if kind == TokenKind.Symbol: |
| 94 | + words = self.get_word_names() |
| 95 | + elif kind == TokenKind.NamedCharacter: |
| 96 | + words = self.named_characters |
| 97 | + elif kind == TokenKind.ASCII_Operator: |
| 98 | + words = self.ascii_operators |
| 99 | + elif kind == TokenKind.EscapeSequence: |
| 100 | + words = self.escape_sequences |
| 101 | + else: |
| 102 | + words = [] |
| 103 | + |
| 104 | + def word_matches(word: str) -> bool: |
| 105 | + """ True when the word before the cursor matches. """ |
| 106 | + |
| 107 | + if self.match_middle: |
| 108 | + return word_before_cursor in word |
| 109 | + else: |
| 110 | + return word.startswith(word_before_cursor) |
| 111 | + |
| 112 | + for a in words: |
| 113 | + if word_matches(a): |
| 114 | + display = self.display_dict.get(a, a) |
| 115 | + display_meta = self.meta_dict.get(a, "") |
| 116 | + yield Completion( |
| 117 | + a, |
| 118 | + -len(word_before_cursor), |
| 119 | + display=display, |
| 120 | + display_meta=display_meta, |
| 121 | + ) |
| 122 | + |
| 123 | + def get_word_before_cursor_with_kind(self, document: Document) -> WordToken: |
| 124 | + """ |
| 125 | + Get the word before the cursor and clasify it into one of the kinds |
| 126 | + of tokens: NamedCharacter, AsciiOperator, Symbol, etc. |
| 127 | +
|
| 128 | +
|
| 129 | + If we have whitespace before the cursor this returns an empty string. |
| 130 | + """ |
| 131 | + |
| 132 | + text_before_cursor = document.text_before_cursor |
| 133 | + |
| 134 | + if self._is_space_before_cursor( |
| 135 | + document=document, text_before_cursor=text_before_cursor |
| 136 | + ): |
| 137 | + return WordToken("", TokenKind.Null) |
| 138 | + |
| 139 | + start = ( |
| 140 | + document.find_start_of_previous_word( |
| 141 | + WORD=False, pattern=FIND_MATHICS_WORD_RE |
| 142 | + ) |
| 143 | + or 0 |
| 144 | + ) |
| 145 | + |
| 146 | + word_before_cursor = text_before_cursor[len(text_before_cursor) + start :] |
| 147 | + if word_before_cursor.startswith(r"\["): |
| 148 | + return WordToken(word_before_cursor[2:], TokenKind.NamedCharacter) |
| 149 | + if word_before_cursor.startswith(r"["): |
| 150 | + word_before_cursor = word_before_cursor[1:] |
| 151 | + |
| 152 | + if word_before_cursor.isnumeric(): |
| 153 | + return WordToken(word_before_cursor, TokenKind.Null) |
| 154 | + elif word_before_cursor in self.ascii_operators: |
| 155 | + return WordToken(word_before_cursor, TokenKind.ASCII_Operator) |
| 156 | + elif word_before_cursor.startswith("\1xb"): |
| 157 | + return WordToken(word_before_cursor, TokenKind.EscapeSequence) |
| 158 | + |
| 159 | + return word_before_cursor, TokenKind.Symbol |
| 160 | + |
| 161 | + def get_word_names(self: str): |
| 162 | + names = self.definitions.get_names() |
| 163 | + short_names = [strip_context(m) for m in names] |
| 164 | + return list(names) + short_names |
0 commit comments