fn identify_keywords()

in cli/src/generate/build_tables/mod.rs [201:305]
89 lines of code
11 McCabe index (conditional complexity)

fn identify_keywords(
    lexical_grammar: &LexicalGrammar,
    parse_table: &ParseTable,
    word_token: Option<Symbol>,
    token_conflict_map: &TokenConflictMap,
    coincident_token_index: &CoincidentTokenIndex,
) -> TokenSet {
    if word_token.is_none() {
        return TokenSet::new();
    }

    let word_token = word_token.unwrap();
    let mut cursor = NfaCursor::new(&lexical_grammar.nfa, Vec::new());

    // First find all of the candidate keyword tokens: tokens that start with
    // letters or underscore and can match the same string as a word token.
    let keyword_candidates: TokenSet = lexical_grammar
        .variables
        .iter()
        .enumerate()
        .filter_map(|(i, variable)| {
            cursor.reset(vec![variable.start_state]);
            if all_chars_are_alphabetical(&cursor)
                && token_conflict_map.does_match_same_string(i, word_token.index)
            {
                info!(
                    "Keywords - add candidate {}",
                    lexical_grammar.variables[i].name
                );
                Some(Symbol::terminal(i))
            } else {
                None
            }
        })
        .collect();

    // Exclude keyword candidates that shadow another keyword candidate.
    let keywords: TokenSet = keyword_candidates
        .iter()
        .filter(|token| {
            for other_token in keyword_candidates.iter() {
                if other_token != *token
                    && token_conflict_map.does_match_same_string(other_token.index, token.index)
                {
                    info!(
                        "Keywords - exclude {} because it matches the same string as {}",
                        lexical_grammar.variables[token.index].name,
                        lexical_grammar.variables[other_token.index].name
                    );
                    return false;
                }
            }
            true
        })
        .collect();

    // Exclude keyword candidates for which substituting the keyword capture
    // token would introduce new lexical conflicts with other tokens.
    let keywords = keywords
        .iter()
        .filter(|token| {
            for other_index in 0..lexical_grammar.variables.len() {
                if keyword_candidates.contains(&Symbol::terminal(other_index)) {
                    continue;
                }

                // If the word token was already valid in every state containing
                // this keyword candidate, then substituting the word token won't
                // introduce any new lexical conflicts.
                if coincident_token_index
                    .states_with(*token, Symbol::terminal(other_index))
                    .iter()
                    .all(|state_id| {
                        parse_table.states[*state_id]
                            .terminal_entries
                            .contains_key(&word_token)
                    })
                {
                    continue;
                }

                if !token_conflict_map.has_same_conflict_status(
                    token.index,
                    word_token.index,
                    other_index,
                ) {
                    info!(
                        "Keywords - exclude {} because of conflict with {}",
                        lexical_grammar.variables[token.index].name,
                        lexical_grammar.variables[other_index].name
                    );
                    return false;
                }
            }

            info!(
                "Keywords - include {}",
                lexical_grammar.variables[token.index].name,
            );
            true
        })
        .collect();

    keywords
}