diff options
Diffstat (limited to 'examples/live')
| -rw-r--r-- | examples/live/build.zig | 11 | ||||
| -rw-r--r-- | examples/live/grammar/grammar.js | 24 | ||||
| -rw-r--r-- | examples/live/grammar/src/parser.c | 918 | ||||
| -rw-r--r-- | examples/live/grammar/src/tree_sitter/alloc.h | 54 | ||||
| -rw-r--r-- | examples/live/grammar/src/tree_sitter/array.h | 330 | ||||
| -rw-r--r-- | examples/live/grammar/src/tree_sitter/parser.h | 286 | ||||
| -rw-r--r-- | examples/live/queries/highlights.scm | 6 | ||||
| -rw-r--r-- | examples/live/queries/indents.scm | 5 | ||||
| -rw-r--r-- | examples/live/src/Lang.zig | 5 | ||||
| -rw-r--r-- | examples/live/src/main.zig | 37 | ||||
| -rw-r--r-- | examples/live/test/grammar.zig | 54 |
11 files changed, 1724 insertions, 6 deletions
diff --git a/examples/live/build.zig b/examples/live/build.zig index ccfd32d..a07fe7d 100644 --- a/examples/live/build.zig +++ b/examples/live/build.zig @@ -40,7 +40,16 @@ pub fn build(b: *std.Build) void { .{ .name = "scope", .module = sb.modules.scope }, .{ .name = "pardes-editor", .module = pardes.module("pardes-editor") }, } }); - const steps = app.addSteps(.{ .scripts = &.{b.path("test/live.script")} }); + // The language's tree-sitter grammar: grammar/grammar.js and the + // parser.c generated from it, committed (the build never runs the + // generator); its colours and a new line's indent, queries/. + const grammar = b.addLibrary(.{ .name = "tree-sitter-live", .linkage = .static, .root_module = b.createModule(.{ .target = target, .optimize = .ReleaseFast, .link_libc = true, .pic = true }) }); + grammar.root_module.addCSourceFile(.{ .file = b.path("grammar/src/parser.c") }); + grammar.root_module.addIncludePath(b.path("grammar/src")); + app.module.linkLibrary(grammar); + app.module.addAnonymousImport("highlights.scm", .{ .root_source_file = b.path("queries/highlights.scm") }); + app.module.addAnonymousImport("indents.scm", .{ .root_source_file = b.path("queries/indents.scm") }); + const steps = app.addSteps(.{ .scripts = &.{b.path("test/live.script")}, .tests = &.{b.path("test/grammar.zig")} }); const lang_test = b.addTest(.{ .root_module = b.createModule(.{ .root_source_file = b.path("src/Lang.zig"), .target = target, .optimize = optimize }) }); steps.test_step.dependOn(&b.addRunArtifact(lang_test).step); diff --git a/examples/live/grammar/grammar.js b/examples/live/grammar/grammar.js new file mode 100644 index 0000000..31f50b1 --- /dev/null +++ b/examples/live/grammar/grammar.js @@ -0,0 +1,24 @@ +// The language as src/Lang.zig parses it, for tree-sitter: lines of +// `name = expression`, `+ -` below `* /` below unary `-`, calls, numbers, +// names, `#` comments. `tree-sitter generate` here writes src/parser.c, +// which is committed: the build compiles it and never runs the generator. +module.exports = grammar({ + name: 'live', + extras: $ => [/[ \t\r]/, $.comment], + word: $ => $.name, + rules: { + source_file: $ => seq(optional($.definition), repeat(seq('\n', optional($.definition)))), + definition: $ => seq(field('name', $.name), '=', field('value', $._expression)), + _expression: $ => choice($.binary, $.unary, $.call, $.parenthesized, $.number, $.name), + binary: $ => choice( + prec.left(1, seq(field('left', $._expression), field('operator', choice('+', '-')), field('right', $._expression))), + prec.left(2, seq(field('left', $._expression), field('operator', choice('*', '/')), field('right', $._expression))), + ), + unary: $ => prec(3, seq('-', field('operand', $._expression))), + call: $ => seq(field('function', $.name), '(', optional(seq($._expression, repeat(seq(',', $._expression)))), ')'), + parenthesized: $ => seq('(', $._expression, ')'), + number: $ => /(\d+(\.\d*)?|\.\d+)(e[+-]?\d+)?/, + name: $ => /[a-zA-Z_][a-zA-Z0-9_]*/, + comment: $ => /#[^\n]*/, + }, +}); diff --git a/examples/live/grammar/src/parser.c b/examples/live/grammar/src/parser.c new file mode 100644 index 0000000..e694827 --- /dev/null +++ b/examples/live/grammar/src/parser.c @@ -0,0 +1,918 @@ +/* Automatically @generated by tree-sitter */ + +#include "tree_sitter/parser.h" + +#if defined(__GNUC__) || defined(__clang__) +#pragma GCC diagnostic ignored "-Wmissing-field-initializers" +#endif + +#define LANGUAGE_VERSION 14 +#define STATE_COUNT 31 +#define LARGE_STATE_COUNT 2 +#define SYMBOL_COUNT 22 +#define ALIAS_COUNT 0 +#define TOKEN_COUNT 13 +#define EXTERNAL_TOKEN_COUNT 0 +#define FIELD_COUNT 7 +#define MAX_ALIAS_SEQUENCE_LENGTH 5 +#define MAX_RESERVED_WORD_SET_SIZE 0 +#define PRODUCTION_ID_COUNT 5 +#define SUPERTYPE_COUNT 0 + +enum ts_symbol_identifiers { + sym_name = 1, + anon_sym_LF = 2, + anon_sym_EQ = 3, + anon_sym_PLUS = 4, + anon_sym_DASH = 5, + anon_sym_STAR = 6, + anon_sym_SLASH = 7, + anon_sym_LPAREN = 8, + anon_sym_COMMA = 9, + anon_sym_RPAREN = 10, + sym_number = 11, + sym_comment = 12, + sym_source_file = 13, + sym_definition = 14, + sym__expression = 15, + sym_binary = 16, + sym_unary = 17, + sym_call = 18, + sym_parenthesized = 19, + aux_sym_source_file_repeat1 = 20, + aux_sym_call_repeat1 = 21, +}; + +static const char * const ts_symbol_names[] = { + [ts_builtin_sym_end] = "end", + [sym_name] = "name", + [anon_sym_LF] = "\n", + [anon_sym_EQ] = "=", + [anon_sym_PLUS] = "+", + [anon_sym_DASH] = "-", + [anon_sym_STAR] = "*", + [anon_sym_SLASH] = "/", + [anon_sym_LPAREN] = "(", + [anon_sym_COMMA] = ",", + [anon_sym_RPAREN] = ")", + [sym_number] = "number", + [sym_comment] = "comment", + [sym_source_file] = "source_file", + [sym_definition] = "definition", + [sym__expression] = "_expression", + [sym_binary] = "binary", + [sym_unary] = "unary", + [sym_call] = "call", + [sym_parenthesized] = "parenthesized", + [aux_sym_source_file_repeat1] = "source_file_repeat1", + [aux_sym_call_repeat1] = "call_repeat1", +}; + +static const TSSymbol ts_symbol_map[] = { + [ts_builtin_sym_end] = ts_builtin_sym_end, + [sym_name] = sym_name, + [anon_sym_LF] = anon_sym_LF, + [anon_sym_EQ] = anon_sym_EQ, + [anon_sym_PLUS] = anon_sym_PLUS, + [anon_sym_DASH] = anon_sym_DASH, + [anon_sym_STAR] = anon_sym_STAR, + [anon_sym_SLASH] = anon_sym_SLASH, + [anon_sym_LPAREN] = anon_sym_LPAREN, + [anon_sym_COMMA] = anon_sym_COMMA, + [anon_sym_RPAREN] = anon_sym_RPAREN, + [sym_number] = sym_number, + [sym_comment] = sym_comment, + [sym_source_file] = sym_source_file, + [sym_definition] = sym_definition, + [sym__expression] = sym__expression, + [sym_binary] = sym_binary, + [sym_unary] = sym_unary, + [sym_call] = sym_call, + [sym_parenthesized] = sym_parenthesized, + [aux_sym_source_file_repeat1] = aux_sym_source_file_repeat1, + [aux_sym_call_repeat1] = aux_sym_call_repeat1, +}; + +static const TSSymbolMetadata ts_symbol_metadata[] = { + [ts_builtin_sym_end] = { + .visible = false, + .named = true, + }, + [sym_name] = { + .visible = true, + .named = true, + }, + [anon_sym_LF] = { + .visible = true, + .named = false, + }, + [anon_sym_EQ] = { + .visible = true, + .named = false, + }, + [anon_sym_PLUS] = { + .visible = true, + .named = false, + }, + [anon_sym_DASH] = { + .visible = true, + .named = false, + }, + [anon_sym_STAR] = { + .visible = true, + .named = false, + }, + [anon_sym_SLASH] = { + .visible = true, + .named = false, + }, + [anon_sym_LPAREN] = { + .visible = true, + .named = false, + }, + [anon_sym_COMMA] = { + .visible = true, + .named = false, + }, + [anon_sym_RPAREN] = { + .visible = true, + .named = false, + }, + [sym_number] = { + .visible = true, + .named = true, + }, + [sym_comment] = { + .visible = true, + .named = true, + }, + [sym_source_file] = { + .visible = true, + .named = true, + }, + [sym_definition] = { + .visible = true, + .named = true, + }, + [sym__expression] = { + .visible = false, + .named = true, + }, + [sym_binary] = { + .visible = true, + .named = true, + }, + [sym_unary] = { + .visible = true, + .named = true, + }, + [sym_call] = { + .visible = true, + .named = true, + }, + [sym_parenthesized] = { + .visible = true, + .named = true, + }, + [aux_sym_source_file_repeat1] = { + .visible = false, + .named = false, + }, + [aux_sym_call_repeat1] = { + .visible = false, + .named = false, + }, +}; + +enum ts_field_identifiers { + field_function = 1, + field_left = 2, + field_name = 3, + field_operand = 4, + field_operator = 5, + field_right = 6, + field_value = 7, +}; + +static const char * const ts_field_names[] = { + [0] = NULL, + [field_function] = "function", + [field_left] = "left", + [field_name] = "name", + [field_operand] = "operand", + [field_operator] = "operator", + [field_right] = "right", + [field_value] = "value", +}; + +static const TSMapSlice ts_field_map_slices[PRODUCTION_ID_COUNT] = { + [1] = {.index = 0, .length = 2}, + [2] = {.index = 2, .length = 1}, + [3] = {.index = 3, .length = 1}, + [4] = {.index = 4, .length = 3}, +}; + +static const TSFieldMapEntry ts_field_map_entries[] = { + [0] = + {field_name, 0}, + {field_value, 2}, + [2] = + {field_operand, 1}, + [3] = + {field_function, 0}, + [4] = + {field_left, 0}, + {field_operator, 1}, + {field_right, 2}, +}; + +static const TSSymbol ts_alias_sequences[PRODUCTION_ID_COUNT][MAX_ALIAS_SEQUENCE_LENGTH] = { + [0] = {0}, +}; + +static const uint16_t ts_non_terminal_alias_map[] = { + 0, +}; + +static const TSStateId ts_primary_state_ids[STATE_COUNT] = { + [0] = 0, + [1] = 1, + [2] = 2, + [3] = 3, + [4] = 4, + [5] = 5, + [6] = 6, + [7] = 7, + [8] = 8, + [9] = 9, + [10] = 10, + [11] = 11, + [12] = 12, + [13] = 13, + [14] = 14, + [15] = 15, + [16] = 16, + [17] = 17, + [18] = 18, + [19] = 19, + [20] = 20, + [21] = 21, + [22] = 22, + [23] = 23, + [24] = 24, + [25] = 25, + [26] = 26, + [27] = 27, + [28] = 28, + [29] = 29, + [30] = 30, +}; + +static bool ts_lex(TSLexer *lexer, TSStateId state) { + START_LEXER(); + eof = lexer->eof(lexer); + switch (state) { + case 0: + if (eof) ADVANCE(4); + ADVANCE_MAP( + '\n', 5, + '#', 18, + '(', 11, + ')', 13, + '*', 9, + '+', 7, + ',', 12, + '-', 8, + '.', 2, + '/', 10, + '=', 6, + ); + if (lookahead == '\t' || + lookahead == '\r' || + lookahead == ' ') SKIP(0); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(14); + if (('A' <= lookahead && lookahead <= 'Z') || + lookahead == '_' || + ('a' <= lookahead && lookahead <= 'z')) ADVANCE(17); + END_STATE(); + case 1: + if (lookahead == '+' || + lookahead == '-') ADVANCE(3); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(16); + END_STATE(); + case 2: + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(15); + END_STATE(); + case 3: + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(16); + END_STATE(); + case 4: + ACCEPT_TOKEN(ts_builtin_sym_end); + END_STATE(); + case 5: + ACCEPT_TOKEN(anon_sym_LF); + END_STATE(); + case 6: + ACCEPT_TOKEN(anon_sym_EQ); + END_STATE(); + case 7: + ACCEPT_TOKEN(anon_sym_PLUS); + END_STATE(); + case 8: + ACCEPT_TOKEN(anon_sym_DASH); + END_STATE(); + case 9: + ACCEPT_TOKEN(anon_sym_STAR); + END_STATE(); + case 10: + ACCEPT_TOKEN(anon_sym_SLASH); + END_STATE(); + case 11: + ACCEPT_TOKEN(anon_sym_LPAREN); + END_STATE(); + case 12: + ACCEPT_TOKEN(anon_sym_COMMA); + END_STATE(); + case 13: + ACCEPT_TOKEN(anon_sym_RPAREN); + END_STATE(); + case 14: + ACCEPT_TOKEN(sym_number); + if (lookahead == '.') ADVANCE(15); + if (lookahead == 'e') ADVANCE(1); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(14); + END_STATE(); + case 15: + ACCEPT_TOKEN(sym_number); + if (lookahead == 'e') ADVANCE(1); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(15); + END_STATE(); + case 16: + ACCEPT_TOKEN(sym_number); + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(16); + END_STATE(); + case 17: + ACCEPT_TOKEN(sym_name); + if (('0' <= lookahead && lookahead <= '9') || + ('A' <= lookahead && lookahead <= 'Z') || + lookahead == '_' || + ('a' <= lookahead && lookahead <= 'z')) ADVANCE(17); + END_STATE(); + case 18: + ACCEPT_TOKEN(sym_comment); + if (lookahead != 0 && + lookahead != '\n') ADVANCE(18); + END_STATE(); + default: + return false; + } +} + +static bool ts_lex_keywords(TSLexer *lexer, TSStateId state) { + START_LEXER(); + eof = lexer->eof(lexer); + switch (state) { + case 0: + ACCEPT_TOKEN(ts_builtin_sym_end); + END_STATE(); + default: + return false; + } +} + +static const TSLexMode ts_lex_modes[STATE_COUNT] = { + [0] = {.lex_state = 0}, + [1] = {.lex_state = 0}, + [2] = {.lex_state = 0}, + [3] = {.lex_state = 0}, + [4] = {.lex_state = 0}, + [5] = {.lex_state = 0}, + [6] = {.lex_state = 0}, + [7] = {.lex_state = 0}, + [8] = {.lex_state = 0}, + [9] = {.lex_state = 0}, + [10] = {.lex_state = 0}, + [11] = {.lex_state = 0}, + [12] = {.lex_state = 0}, + [13] = {.lex_state = 0}, + [14] = {.lex_state = 0}, + [15] = {.lex_state = 0}, + [16] = {.lex_state = 0}, + [17] = {.lex_state = 0}, + [18] = {.lex_state = 0}, + [19] = {.lex_state = 0}, + [20] = {.lex_state = 0}, + [21] = {.lex_state = 0}, + [22] = {.lex_state = 0}, + [23] = {.lex_state = 0}, + [24] = {.lex_state = 0}, + [25] = {.lex_state = 0}, + [26] = {.lex_state = 0}, + [27] = {.lex_state = 0}, + [28] = {.lex_state = 0}, + [29] = {.lex_state = 0}, + [30] = {.lex_state = 0}, +}; + +static const uint16_t ts_parse_table[LARGE_STATE_COUNT][SYMBOL_COUNT] = { + [STATE(0)] = { + [ts_builtin_sym_end] = ACTIONS(1), + [sym_name] = ACTIONS(1), + [anon_sym_LF] = ACTIONS(1), + [anon_sym_EQ] = ACTIONS(1), + [anon_sym_PLUS] = ACTIONS(1), + [anon_sym_DASH] = ACTIONS(1), + [anon_sym_STAR] = ACTIONS(1), + [anon_sym_SLASH] = ACTIONS(1), + [anon_sym_LPAREN] = ACTIONS(1), + [anon_sym_COMMA] = ACTIONS(1), + [anon_sym_RPAREN] = ACTIONS(1), + [sym_number] = ACTIONS(1), + [sym_comment] = ACTIONS(3), + }, + [STATE(1)] = { + [sym_source_file] = STATE(30), + [sym_definition] = STATE(22), + [aux_sym_source_file_repeat1] = STATE(23), + [ts_builtin_sym_end] = ACTIONS(5), + [sym_name] = ACTIONS(7), + [anon_sym_LF] = ACTIONS(9), + [sym_comment] = ACTIONS(3), + }, +}; + +static const uint16_t ts_small_parse_table[] = { + [0] = 7, + ACTIONS(3), 1, + sym_comment, + ACTIONS(11), 1, + sym_name, + ACTIONS(13), 1, + anon_sym_DASH, + ACTIONS(15), 1, + anon_sym_LPAREN, + ACTIONS(17), 1, + anon_sym_RPAREN, + ACTIONS(19), 1, + sym_number, + STATE(17), 5, + sym__expression, + sym_binary, + sym_unary, + sym_call, + sym_parenthesized, + [26] = 6, + ACTIONS(3), 1, + sym_comment, + ACTIONS(11), 1, + sym_name, + ACTIONS(13), 1, + anon_sym_DASH, + ACTIONS(15), 1, + anon_sym_LPAREN, + ACTIONS(21), 1, + sym_number, + STATE(10), 5, + sym__expression, + sym_binary, + sym_unary, + sym_call, + sym_parenthesized, + [49] = 6, + ACTIONS(3), 1, + sym_comment, + ACTIONS(11), 1, + sym_name, + ACTIONS(13), 1, + anon_sym_DASH, + ACTIONS(15), 1, + anon_sym_LPAREN, + ACTIONS(23), 1, + sym_number, + STATE(18), 5, + sym__expression, + sym_binary, + sym_unary, + sym_call, + sym_parenthesized, + [72] = 6, + ACTIONS(3), 1, + sym_comment, + ACTIONS(11), 1, + sym_name, + ACTIONS(13), 1, + anon_sym_DASH, + ACTIONS(15), 1, + anon_sym_LPAREN, + ACTIONS(25), 1, + sym_number, + STATE(20), 5, + sym__expression, + sym_binary, + sym_unary, + sym_call, + sym_parenthesized, + [95] = 3, + ACTIONS(3), 1, + sym_comment, + ACTIONS(29), 1, + anon_sym_LPAREN, + ACTIONS(27), 8, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_STAR, + anon_sym_SLASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [112] = 6, + ACTIONS(3), 1, + sym_comment, + ACTIONS(11), 1, + sym_name, + ACTIONS(13), 1, + anon_sym_DASH, + ACTIONS(15), 1, + anon_sym_LPAREN, + ACTIONS(31), 1, + sym_number, + STATE(13), 5, + sym__expression, + sym_binary, + sym_unary, + sym_call, + sym_parenthesized, + [135] = 6, + ACTIONS(3), 1, + sym_comment, + ACTIONS(11), 1, + sym_name, + ACTIONS(13), 1, + anon_sym_DASH, + ACTIONS(15), 1, + anon_sym_LPAREN, + ACTIONS(33), 1, + sym_number, + STATE(19), 5, + sym__expression, + sym_binary, + sym_unary, + sym_call, + sym_parenthesized, + [158] = 6, + ACTIONS(3), 1, + sym_comment, + ACTIONS(11), 1, + sym_name, + ACTIONS(13), 1, + anon_sym_DASH, + ACTIONS(15), 1, + anon_sym_LPAREN, + ACTIONS(35), 1, + sym_number, + STATE(14), 5, + sym__expression, + sym_binary, + sym_unary, + sym_call, + sym_parenthesized, + [181] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(37), 8, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_STAR, + anon_sym_SLASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [195] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(39), 8, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_STAR, + anon_sym_SLASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [209] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(41), 8, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_STAR, + anon_sym_SLASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [223] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(43), 8, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_STAR, + anon_sym_SLASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [237] = 3, + ACTIONS(3), 1, + sym_comment, + ACTIONS(45), 2, + anon_sym_STAR, + anon_sym_SLASH, + ACTIONS(43), 6, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [253] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(47), 8, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_STAR, + anon_sym_SLASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [267] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(49), 8, + ts_builtin_sym_end, + anon_sym_LF, + anon_sym_PLUS, + anon_sym_DASH, + anon_sym_STAR, + anon_sym_SLASH, + anon_sym_COMMA, + anon_sym_RPAREN, + [281] = 6, + ACTIONS(3), 1, + sym_comment, + ACTIONS(53), 1, + anon_sym_COMMA, + ACTIONS(55), 1, + anon_sym_RPAREN, + STATE(26), 1, + aux_sym_call_repeat1, + ACTIONS(45), 2, + anon_sym_STAR, + anon_sym_SLASH, + ACTIONS(51), 2, + anon_sym_PLUS, + anon_sym_DASH, + [302] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(45), 2, + anon_sym_STAR, + anon_sym_SLASH, + ACTIONS(51), 2, + anon_sym_PLUS, + anon_sym_DASH, + ACTIONS(57), 2, + ts_builtin_sym_end, + anon_sym_LF, + [318] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(45), 2, + anon_sym_STAR, + anon_sym_SLASH, + ACTIONS(51), 2, + anon_sym_PLUS, + anon_sym_DASH, + ACTIONS(59), 2, + anon_sym_COMMA, + anon_sym_RPAREN, + [334] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(61), 1, + anon_sym_RPAREN, + ACTIONS(45), 2, + anon_sym_STAR, + anon_sym_SLASH, + ACTIONS(51), 2, + anon_sym_PLUS, + anon_sym_DASH, + [349] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(7), 1, + sym_name, + STATE(28), 1, + sym_definition, + ACTIONS(63), 2, + ts_builtin_sym_end, + anon_sym_LF, + [363] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(9), 1, + anon_sym_LF, + ACTIONS(65), 1, + ts_builtin_sym_end, + STATE(24), 1, + aux_sym_source_file_repeat1, + [376] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(9), 1, + anon_sym_LF, + ACTIONS(65), 1, + ts_builtin_sym_end, + STATE(25), 1, + aux_sym_source_file_repeat1, + [389] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(9), 1, + anon_sym_LF, + ACTIONS(67), 1, + ts_builtin_sym_end, + STATE(25), 1, + aux_sym_source_file_repeat1, + [402] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(69), 1, + ts_builtin_sym_end, + ACTIONS(71), 1, + anon_sym_LF, + STATE(25), 1, + aux_sym_source_file_repeat1, + [415] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(53), 1, + anon_sym_COMMA, + ACTIONS(74), 1, + anon_sym_RPAREN, + STATE(27), 1, + aux_sym_call_repeat1, + [428] = 4, + ACTIONS(3), 1, + sym_comment, + ACTIONS(59), 1, + anon_sym_RPAREN, + ACTIONS(76), 1, + anon_sym_COMMA, + STATE(27), 1, + aux_sym_call_repeat1, + [441] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(69), 2, + ts_builtin_sym_end, + anon_sym_LF, + [449] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(79), 1, + anon_sym_EQ, + [456] = 2, + ACTIONS(3), 1, + sym_comment, + ACTIONS(81), 1, + ts_builtin_sym_end, +}; + +static const uint32_t ts_small_parse_table_map[] = { + [SMALL_STATE(2)] = 0, + [SMALL_STATE(3)] = 26, + [SMALL_STATE(4)] = 49, + [SMALL_STATE(5)] = 72, + [SMALL_STATE(6)] = 95, + [SMALL_STATE(7)] = 112, + [SMALL_STATE(8)] = 135, + [SMALL_STATE(9)] = 158, + [SMALL_STATE(10)] = 181, + [SMALL_STATE(11)] = 195, + [SMALL_STATE(12)] = 209, + [SMALL_STATE(13)] = 223, + [SMALL_STATE(14)] = 237, + [SMALL_STATE(15)] = 253, + [SMALL_STATE(16)] = 267, + [SMALL_STATE(17)] = 281, + [SMALL_STATE(18)] = 302, + [SMALL_STATE(19)] = 318, + [SMALL_STATE(20)] = 334, + [SMALL_STATE(21)] = 349, + [SMALL_STATE(22)] = 363, + [SMALL_STATE(23)] = 376, + [SMALL_STATE(24)] = 389, + [SMALL_STATE(25)] = 402, + [SMALL_STATE(26)] = 415, + [SMALL_STATE(27)] = 428, + [SMALL_STATE(28)] = 441, + [SMALL_STATE(29)] = 449, + [SMALL_STATE(30)] = 456, +}; + +static const TSParseActionEntry ts_parse_actions[] = { + [0] = {.entry = {.count = 0, .reusable = false}}, + [1] = {.entry = {.count = 1, .reusable = false}}, RECOVER(), + [3] = {.entry = {.count = 1, .reusable = true}}, SHIFT_EXTRA(), + [5] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_source_file, 0, 0, 0), + [7] = {.entry = {.count = 1, .reusable = true}}, SHIFT(29), + [9] = {.entry = {.count = 1, .reusable = true}}, SHIFT(21), + [11] = {.entry = {.count = 1, .reusable = true}}, SHIFT(6), + [13] = {.entry = {.count = 1, .reusable = true}}, SHIFT(3), + [15] = {.entry = {.count = 1, .reusable = true}}, SHIFT(5), + [17] = {.entry = {.count = 1, .reusable = true}}, SHIFT(12), + [19] = {.entry = {.count = 1, .reusable = true}}, SHIFT(17), + [21] = {.entry = {.count = 1, .reusable = true}}, SHIFT(10), + [23] = {.entry = {.count = 1, .reusable = true}}, SHIFT(18), + [25] = {.entry = {.count = 1, .reusable = true}}, SHIFT(20), + [27] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym__expression, 1, 0, 0), + [29] = {.entry = {.count = 1, .reusable = true}}, SHIFT(2), + [31] = {.entry = {.count = 1, .reusable = true}}, SHIFT(13), + [33] = {.entry = {.count = 1, .reusable = true}}, SHIFT(19), + [35] = {.entry = {.count = 1, .reusable = true}}, SHIFT(14), + [37] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_unary, 2, 0, 2), + [39] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_parenthesized, 3, 0, 0), + [41] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_call, 3, 0, 3), + [43] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_binary, 3, 0, 4), + [45] = {.entry = {.count = 1, .reusable = true}}, SHIFT(7), + [47] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_call, 4, 0, 3), + [49] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_call, 5, 0, 3), + [51] = {.entry = {.count = 1, .reusable = true}}, SHIFT(9), + [53] = {.entry = {.count = 1, .reusable = true}}, SHIFT(8), + [55] = {.entry = {.count = 1, .reusable = true}}, SHIFT(15), + [57] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_definition, 3, 0, 1), + [59] = {.entry = {.count = 1, .reusable = true}}, REDUCE(aux_sym_call_repeat1, 2, 0, 0), + [61] = {.entry = {.count = 1, .reusable = true}}, SHIFT(11), + [63] = {.entry = {.count = 1, .reusable = true}}, REDUCE(aux_sym_source_file_repeat1, 1, 0, 0), + [65] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_source_file, 1, 0, 0), + [67] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_source_file, 2, 0, 0), + [69] = {.entry = {.count = 1, .reusable = true}}, REDUCE(aux_sym_source_file_repeat1, 2, 0, 0), + [71] = {.entry = {.count = 2, .reusable = true}}, REDUCE(aux_sym_source_file_repeat1, 2, 0, 0), SHIFT_REPEAT(21), + [74] = {.entry = {.count = 1, .reusable = true}}, SHIFT(16), + [76] = {.entry = {.count = 2, .reusable = true}}, REDUCE(aux_sym_call_repeat1, 2, 0, 0), SHIFT_REPEAT(8), + [79] = {.entry = {.count = 1, .reusable = true}}, SHIFT(4), + [81] = {.entry = {.count = 1, .reusable = true}}, ACCEPT_INPUT(), +}; + +#ifdef __cplusplus +extern "C" { +#endif +#ifdef TREE_SITTER_HIDE_SYMBOLS +#define TS_PUBLIC +#elif defined(_WIN32) +#define TS_PUBLIC __declspec(dllexport) +#else +#define TS_PUBLIC __attribute__((visibility("default"))) +#endif + +TS_PUBLIC const TSLanguage *tree_sitter_live(void) { + static const TSLanguage language = { + .abi_version = LANGUAGE_VERSION, + .symbol_count = SYMBOL_COUNT, + .alias_count = ALIAS_COUNT, + .token_count = TOKEN_COUNT, + .external_token_count = EXTERNAL_TOKEN_COUNT, + .state_count = STATE_COUNT, + .large_state_count = LARGE_STATE_COUNT, + .production_id_count = PRODUCTION_ID_COUNT, + .field_count = FIELD_COUNT, + .max_alias_sequence_length = MAX_ALIAS_SEQUENCE_LENGTH, + .parse_table = &ts_parse_table[0][0], + .small_parse_table = ts_small_parse_table, + .small_parse_table_map = ts_small_parse_table_map, + .parse_actions = ts_parse_actions, + .symbol_names = ts_symbol_names, + .field_names = ts_field_names, + .field_map_slices = ts_field_map_slices, + .field_map_entries = ts_field_map_entries, + .symbol_metadata = ts_symbol_metadata, + .public_symbol_map = ts_symbol_map, + .alias_map = ts_non_terminal_alias_map, + .alias_sequences = &ts_alias_sequences[0][0], + .lex_modes = (const void*)ts_lex_modes, + .lex_fn = ts_lex, + .keyword_lex_fn = ts_lex_keywords, + .keyword_capture_token = sym_name, + .primary_state_ids = ts_primary_state_ids, + }; + return &language; +} +#ifdef __cplusplus +} +#endif diff --git a/examples/live/grammar/src/tree_sitter/alloc.h b/examples/live/grammar/src/tree_sitter/alloc.h new file mode 100644 index 0000000..1abdd12 --- /dev/null +++ b/examples/live/grammar/src/tree_sitter/alloc.h @@ -0,0 +1,54 @@ +#ifndef TREE_SITTER_ALLOC_H_ +#define TREE_SITTER_ALLOC_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> + +// Allow clients to override allocation functions +#ifdef TREE_SITTER_REUSE_ALLOCATOR + +extern void *(*ts_current_malloc)(size_t size); +extern void *(*ts_current_calloc)(size_t count, size_t size); +extern void *(*ts_current_realloc)(void *ptr, size_t size); +extern void (*ts_current_free)(void *ptr); + +#ifndef ts_malloc +#define ts_malloc ts_current_malloc +#endif +#ifndef ts_calloc +#define ts_calloc ts_current_calloc +#endif +#ifndef ts_realloc +#define ts_realloc ts_current_realloc +#endif +#ifndef ts_free +#define ts_free ts_current_free +#endif + +#else + +#ifndef ts_malloc +#define ts_malloc malloc +#endif +#ifndef ts_calloc +#define ts_calloc calloc +#endif +#ifndef ts_realloc +#define ts_realloc realloc +#endif +#ifndef ts_free +#define ts_free free +#endif + +#endif + +#ifdef __cplusplus +} +#endif + +#endif // TREE_SITTER_ALLOC_H_ diff --git a/examples/live/grammar/src/tree_sitter/array.h b/examples/live/grammar/src/tree_sitter/array.h new file mode 100644 index 0000000..56fc8cd --- /dev/null +++ b/examples/live/grammar/src/tree_sitter/array.h @@ -0,0 +1,330 @@ +#ifndef TREE_SITTER_ARRAY_H_ +#define TREE_SITTER_ARRAY_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include "./alloc.h" + +#include <assert.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> + +#ifdef _MSC_VER +#pragma warning(push) +#pragma warning(disable : 4101) +#elif defined(__GNUC__) || defined(__clang__) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wunused-variable" +#endif + +#define Array(T) \ + struct { \ + T *contents; \ + uint32_t size; \ + uint32_t capacity; \ + } + +/// Initialize an array. +#define array_init(self) \ + ((self)->size = 0, (self)->capacity = 0, (self)->contents = NULL) + +/// Create an empty array. +#define array_new() \ + { NULL, 0, 0 } + +/// Get a pointer to the element at a given `index` in the array. +#define array_get(self, _index) \ + (assert((uint32_t)(_index) < (self)->size), &(self)->contents[_index]) + +/// Get a pointer to the first element in the array. +#define array_front(self) array_get(self, 0) + +/// Get a pointer to the last element in the array. +#define array_back(self) array_get(self, (self)->size - 1) + +/// Clear the array, setting its size to zero. Note that this does not free any +/// memory allocated for the array's contents. +#define array_clear(self) ((self)->size = 0) + +/// Reserve `new_capacity` elements of space in the array. If `new_capacity` is +/// less than the array's current capacity, this function has no effect. +#define array_reserve(self, new_capacity) \ + ((self)->contents = _array__reserve( \ + (void *)(self)->contents, &(self)->capacity, \ + array_elem_size(self), new_capacity) \ + ) + +/// Free any memory allocated for this array. Note that this does not free any +/// memory allocated for the array's contents. +#define array_delete(self) \ + do { \ + if ((self)->contents) ts_free((self)->contents); \ + (self)->contents = NULL; \ + (self)->size = 0; \ + (self)->capacity = 0; \ + } while (0) + +/// Push a new `element` onto the end of the array. +#define array_push(self, element) \ + do { \ + (self)->contents = _array__grow( \ + (void *)(self)->contents, (self)->size, &(self)->capacity, \ + 1, array_elem_size(self) \ + ); \ + (self)->contents[(self)->size++] = (element); \ + } while(0) + +/// Increase the array's size by `count` elements. +/// New elements are zero-initialized. +#define array_grow_by(self, count) \ + do { \ + if ((count) == 0) break; \ + (self)->contents = _array__grow( \ + (self)->contents, (self)->size, &(self)->capacity, \ + count, array_elem_size(self) \ + ); \ + memset((self)->contents + (self)->size, 0, (count) * array_elem_size(self)); \ + (self)->size += (count); \ + } while (0) + +/// Append all elements from one array to the end of another. +#define array_push_all(self, other) \ + array_extend((self), (other)->size, (other)->contents) + +/// Append `count` elements to the end of the array, reading their values from the +/// `contents` pointer. +#define array_extend(self, count, other_contents) \ + (self)->contents = _array__splice( \ + (void*)(self)->contents, &(self)->size, &(self)->capacity, \ + array_elem_size(self), (self)->size, 0, count, other_contents \ + ) + +/// Remove `old_count` elements from the array starting at the given `index`. At +/// the same index, insert `new_count` new elements, reading their values from the +/// `new_contents` pointer. +#define array_splice(self, _index, old_count, new_count, new_contents) \ + (self)->contents = _array__splice( \ + (void *)(self)->contents, &(self)->size, &(self)->capacity, \ + array_elem_size(self), _index, old_count, new_count, new_contents \ + ) + +/// Insert one `element` into the array at the given `index`. +#define array_insert(self, _index, element) \ + (self)->contents = _array__splice( \ + (void *)(self)->contents, &(self)->size, &(self)->capacity, \ + array_elem_size(self), _index, 0, 1, &(element) \ + ) + +/// Remove one element from the array at the given `index`. +#define array_erase(self, _index) \ + _array__erase((void *)(self)->contents, &(self)->size, array_elem_size(self), _index) + +/// Pop the last element off the array, returning the element by value. +#define array_pop(self) ((self)->contents[--(self)->size]) + +/// Assign the contents of one array to another, reallocating if necessary. +#define array_assign(self, other) \ + (self)->contents = _array__assign( \ + (void *)(self)->contents, &(self)->size, &(self)->capacity, \ + (const void *)(other)->contents, (other)->size, array_elem_size(self) \ + ) + +/// Swap one array with another +#define array_swap(self, other) \ + do { \ + void *_array_swap_tmp = (void *)(self)->contents; \ + (self)->contents = (other)->contents; \ + (other)->contents = _array_swap_tmp; \ + _array__swap(&(self)->size, &(self)->capacity, \ + &(other)->size, &(other)->capacity); \ + } while (0) + +/// Get the size of the array contents +#define array_elem_size(self) (sizeof *(self)->contents) + +/// Search a sorted array for a given `needle` value, using the given `compare` +/// callback to determine the order. +/// +/// If an existing element is found to be equal to `needle`, then the `index` +/// out-parameter is set to the existing value's index, and the `exists` +/// out-parameter is set to true. Otherwise, `index` is set to an index where +/// `needle` should be inserted in order to preserve the sorting, and `exists` +/// is set to false. +#define array_search_sorted_with(self, compare, needle, _index, _exists) \ + _array__search_sorted(self, 0, compare, , needle, _index, _exists) + +/// Search a sorted array for a given `needle` value, using integer comparisons +/// of a given struct field (specified with a leading dot) to determine the order. +/// +/// See also `array_search_sorted_with`. +#define array_search_sorted_by(self, field, needle, _index, _exists) \ + _array__search_sorted(self, 0, _compare_int, field, needle, _index, _exists) + +/// Insert a given `value` into a sorted array, using the given `compare` +/// callback to determine the order. +#define array_insert_sorted_with(self, compare, value) \ + do { \ + unsigned _index, _exists; \ + array_search_sorted_with(self, compare, &(value), &_index, &_exists); \ + if (!_exists) array_insert(self, _index, value); \ + } while (0) + +/// Insert a given `value` into a sorted array, using integer comparisons of +/// a given struct field (specified with a leading dot) to determine the order. +/// +/// See also `array_search_sorted_by`. +#define array_insert_sorted_by(self, field, value) \ + do { \ + unsigned _index, _exists; \ + array_search_sorted_by(self, field, (value) field, &_index, &_exists); \ + if (!_exists) array_insert(self, _index, value); \ + } while (0) + +// Private + +// Pointers to individual `Array` fields (rather than the entire `Array` itself) +// are passed to the various `_array__*` functions below to address strict aliasing +// violations that arises when the _entire_ `Array` struct is passed as `Array(void)*`. +// +// The `Array` type itself was not altered as a solution in order to avoid breakage +// with existing consumers (in particular, parsers with external scanners). + +/// This is not what you're looking for, see `array_erase`. +static inline void _array__erase(void* self_contents, uint32_t *size, + size_t element_size, uint32_t index) { + assert(index < *size); + char *contents = (char *)self_contents; + memmove(contents + index * element_size, contents + (index + 1) * element_size, + (*size - index - 1) * element_size); + (*size)--; +} + +/// This is not what you're looking for, see `array_reserve`. +static inline void *_array__reserve(void *contents, uint32_t *capacity, + size_t element_size, uint32_t new_capacity) { + void *new_contents = contents; + if (new_capacity > *capacity) { + if (contents) { + new_contents = ts_realloc(contents, new_capacity * element_size); + } else { + new_contents = ts_malloc(new_capacity * element_size); + } + *capacity = new_capacity; + } + return new_contents; +} + +/// This is not what you're looking for, see `array_assign`. +static inline void *_array__assign(void* self_contents, uint32_t *self_size, uint32_t *self_capacity, + const void *other_contents, uint32_t other_size, size_t element_size) { + void *new_contents = _array__reserve(self_contents, self_capacity, element_size, other_size); + *self_size = other_size; + memcpy(new_contents, other_contents, *self_size * element_size); + return new_contents; +} + +/// This is not what you're looking for, see `array_swap`. +static inline void _array__swap(uint32_t *self_size, uint32_t *self_capacity, + uint32_t *other_size, uint32_t *other_capacity) { + uint32_t tmp_size = *self_size; + uint32_t tmp_capacity = *self_capacity; + *self_size = *other_size; + *self_capacity = *other_capacity; + *other_size = tmp_size; + *other_capacity = tmp_capacity; +} + +/// This is not what you're looking for, see `array_push` or `array_grow_by`. +static inline void *_array__grow(void *contents, uint32_t size, uint32_t *capacity, + uint32_t count, size_t element_size) { + void *new_contents = contents; + uint32_t new_size = size + count; + if (new_size > *capacity) { + uint32_t new_capacity = *capacity * 2; + if (new_capacity < 8) new_capacity = 8; + if (new_capacity < new_size) new_capacity = new_size; + new_contents = _array__reserve(contents, capacity, element_size, new_capacity); + } + return new_contents; +} + +/// This is not what you're looking for, see `array_splice`. +static inline void *_array__splice(void *self_contents, uint32_t *size, uint32_t *capacity, + size_t element_size, + uint32_t index, uint32_t old_count, + uint32_t new_count, const void *elements) { + uint32_t new_size = *size + new_count - old_count; + uint32_t old_end = index + old_count; + uint32_t new_end = index + new_count; + assert(old_end <= *size); + + void *new_contents = _array__reserve(self_contents, capacity, element_size, new_size); + + char *contents = (char *)new_contents; + if (*size > old_end) { + memmove( + contents + new_end * element_size, + contents + old_end * element_size, + (*size - old_end) * element_size + ); + } + if (new_count > 0) { + if (elements) { + memcpy( + (contents + index * element_size), + elements, + new_count * element_size + ); + } else { + memset( + (contents + index * element_size), + 0, + new_count * element_size + ); + } + } + *size += new_count - old_count; + + return new_contents; +} + +/// A binary search routine, based on Rust's `std::slice::binary_search_by`. +/// This is not what you're looking for, see `array_search_sorted_with` or `array_search_sorted_by`. +#define _array__search_sorted(self, start, compare, suffix, needle, _index, _exists) \ + do { \ + *(_index) = start; \ + *(_exists) = false; \ + uint32_t size = (self)->size - *(_index); \ + if (size == 0) break; \ + int comparison; \ + while (size > 1) { \ + uint32_t half_size = size / 2; \ + uint32_t mid_index = *(_index) + half_size; \ + comparison = compare(&((self)->contents[mid_index] suffix), (needle)); \ + if (comparison <= 0) *(_index) = mid_index; \ + size -= half_size; \ + } \ + comparison = compare(&((self)->contents[*(_index)] suffix), (needle)); \ + if (comparison == 0) *(_exists) = true; \ + else if (comparison < 0) *(_index) += 1; \ + } while (0) + +/// Helper macro for the `_sorted_by` routines below. This takes the left (existing) +/// parameter by reference in order to work with the generic sorting function above. +#define _compare_int(a, b) ((int)*(a) - (int)(b)) + +#ifdef _MSC_VER +#pragma warning(pop) +#elif defined(__GNUC__) || defined(__clang__) +#pragma GCC diagnostic pop +#endif + +#ifdef __cplusplus +} +#endif + +#endif // TREE_SITTER_ARRAY_H_ diff --git a/examples/live/grammar/src/tree_sitter/parser.h b/examples/live/grammar/src/tree_sitter/parser.h new file mode 100644 index 0000000..858107d --- /dev/null +++ b/examples/live/grammar/src/tree_sitter/parser.h @@ -0,0 +1,286 @@ +#ifndef TREE_SITTER_PARSER_H_ +#define TREE_SITTER_PARSER_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stdbool.h> +#include <stdint.h> +#include <stdlib.h> + +#define ts_builtin_sym_error ((TSSymbol)-1) +#define ts_builtin_sym_end 0 +#define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024 + +#ifndef TREE_SITTER_API_H_ +typedef uint16_t TSStateId; +typedef uint16_t TSSymbol; +typedef uint16_t TSFieldId; +typedef struct TSLanguage TSLanguage; +typedef struct TSLanguageMetadata { + uint8_t major_version; + uint8_t minor_version; + uint8_t patch_version; +} TSLanguageMetadata; +#endif + +typedef struct { + TSFieldId field_id; + uint8_t child_index; + bool inherited; +} TSFieldMapEntry; + +// Used to index the field and supertype maps. +typedef struct { + uint16_t index; + uint16_t length; +} TSMapSlice; + +typedef struct { + bool visible; + bool named; + bool supertype; +} TSSymbolMetadata; + +typedef struct TSLexer TSLexer; + +struct TSLexer { + int32_t lookahead; + TSSymbol result_symbol; + void (*advance)(TSLexer *, bool); + void (*mark_end)(TSLexer *); + uint32_t (*get_column)(TSLexer *); + bool (*is_at_included_range_start)(const TSLexer *); + bool (*eof)(const TSLexer *); + void (*log)(const TSLexer *, const char *, ...); +}; + +typedef enum { + TSParseActionTypeShift, + TSParseActionTypeReduce, + TSParseActionTypeAccept, + TSParseActionTypeRecover, +} TSParseActionType; + +typedef union { + struct { + uint8_t type; + TSStateId state; + bool extra; + bool repetition; + } shift; + struct { + uint8_t type; + uint8_t child_count; + TSSymbol symbol; + int16_t dynamic_precedence; + uint16_t production_id; + } reduce; + uint8_t type; +} TSParseAction; + +typedef struct { + uint16_t lex_state; + uint16_t external_lex_state; +} TSLexMode; + +typedef struct { + uint16_t lex_state; + uint16_t external_lex_state; + uint16_t reserved_word_set_id; +} TSLexerMode; + +typedef union { + TSParseAction action; + struct { + uint8_t count; + bool reusable; + } entry; +} TSParseActionEntry; + +typedef struct { + int32_t start; + int32_t end; +} TSCharacterRange; + +struct TSLanguage { + uint32_t abi_version; + uint32_t symbol_count; + uint32_t alias_count; + uint32_t token_count; + uint32_t external_token_count; + uint32_t state_count; + uint32_t large_state_count; + uint32_t production_id_count; + uint32_t field_count; + uint16_t max_alias_sequence_length; + const uint16_t *parse_table; + const uint16_t *small_parse_table; + const uint32_t *small_parse_table_map; + const TSParseActionEntry *parse_actions; + const char * const *symbol_names; + const char * const *field_names; + const TSMapSlice *field_map_slices; + const TSFieldMapEntry *field_map_entries; + const TSSymbolMetadata *symbol_metadata; + const TSSymbol *public_symbol_map; + const uint16_t *alias_map; + const TSSymbol *alias_sequences; + const TSLexerMode *lex_modes; + bool (*lex_fn)(TSLexer *, TSStateId); + bool (*keyword_lex_fn)(TSLexer *, TSStateId); + TSSymbol keyword_capture_token; + struct { + const bool *states; + const TSSymbol *symbol_map; + void *(*create)(void); + void (*destroy)(void *); + bool (*scan)(void *, TSLexer *, const bool *symbol_whitelist); + unsigned (*serialize)(void *, char *); + void (*deserialize)(void *, const char *, unsigned); + } external_scanner; + const TSStateId *primary_state_ids; + const char *name; + const TSSymbol *reserved_words; + uint16_t max_reserved_word_set_size; + uint32_t supertype_count; + const TSSymbol *supertype_symbols; + const TSMapSlice *supertype_map_slices; + const TSSymbol *supertype_map_entries; + TSLanguageMetadata metadata; +}; + +static inline bool set_contains(const TSCharacterRange *ranges, uint32_t len, int32_t lookahead) { + uint32_t index = 0; + uint32_t size = len - index; + while (size > 1) { + uint32_t half_size = size / 2; + uint32_t mid_index = index + half_size; + const TSCharacterRange *range = &ranges[mid_index]; + if (lookahead >= range->start && lookahead <= range->end) { + return true; + } else if (lookahead > range->end) { + index = mid_index; + } + size -= half_size; + } + const TSCharacterRange *range = &ranges[index]; + return (lookahead >= range->start && lookahead <= range->end); +} + +/* + * Lexer Macros + */ + +#ifdef _MSC_VER +#define UNUSED __pragma(warning(suppress : 4101)) +#else +#define UNUSED __attribute__((unused)) +#endif + +#define START_LEXER() \ + bool result = false; \ + bool skip = false; \ + UNUSED \ + bool eof = false; \ + int32_t lookahead; \ + goto start; \ + next_state: \ + lexer->advance(lexer, skip); \ + start: \ + skip = false; \ + lookahead = lexer->lookahead; + +#define ADVANCE(state_value) \ + { \ + state = state_value; \ + goto next_state; \ + } + +#define ADVANCE_MAP(...) \ + { \ + static const uint16_t map[] = { __VA_ARGS__ }; \ + for (uint32_t i = 0; i < sizeof(map) / sizeof(map[0]); i += 2) { \ + if (map[i] == lookahead) { \ + state = map[i + 1]; \ + goto next_state; \ + } \ + } \ + } + +#define SKIP(state_value) \ + { \ + skip = true; \ + state = state_value; \ + goto next_state; \ + } + +#define ACCEPT_TOKEN(symbol_value) \ + result = true; \ + lexer->result_symbol = symbol_value; \ + lexer->mark_end(lexer); + +#define END_STATE() return result; + +/* + * Parse Table Macros + */ + +#define SMALL_STATE(id) ((id) - LARGE_STATE_COUNT) + +#define STATE(id) id + +#define ACTIONS(id) id + +#define SHIFT(state_value) \ + {{ \ + .shift = { \ + .type = TSParseActionTypeShift, \ + .state = (state_value) \ + } \ + }} + +#define SHIFT_REPEAT(state_value) \ + {{ \ + .shift = { \ + .type = TSParseActionTypeShift, \ + .state = (state_value), \ + .repetition = true \ + } \ + }} + +#define SHIFT_EXTRA() \ + {{ \ + .shift = { \ + .type = TSParseActionTypeShift, \ + .extra = true \ + } \ + }} + +#define REDUCE(symbol_name, children, precedence, prod_id) \ + {{ \ + .reduce = { \ + .type = TSParseActionTypeReduce, \ + .symbol = symbol_name, \ + .child_count = children, \ + .dynamic_precedence = precedence, \ + .production_id = prod_id \ + }, \ + }} + +#define RECOVER() \ + {{ \ + .type = TSParseActionTypeRecover \ + }} + +#define ACCEPT_INPUT() \ + {{ \ + .type = TSParseActionTypeAccept \ + }} + +#ifdef __cplusplus +} +#endif + +#endif // TREE_SITTER_PARSER_H_ diff --git a/examples/live/queries/highlights.scm b/examples/live/queries/highlights.scm new file mode 100644 index 0000000..f02ec48 --- /dev/null +++ b/examples/live/queries/highlights.scm @@ -0,0 +1,6 @@ +; The language's colours, in pardes's four classes (its themes' inks): +; the name a line defines, a builtin called, numbers, comments. +(definition name: (name) @keyword) +(call function: (name) @string) +(number) @number +(comment) @comment diff --git a/examples/live/queries/indents.scm b/examples/live/queries/indents.scm new file mode 100644 index 0000000..9ddd784 --- /dev/null +++ b/examples/live/queries/indents.scm @@ -0,0 +1,5 @@ +; A new line's indent (helix's indent queries): a level inside a call or +; parentheses left open, none else, so a line ending in `)` does not push +; the next one in. +[(call) (parenthesized)] @indent +")" @outdent diff --git a/examples/live/src/Lang.zig b/examples/live/src/Lang.zig index 484de54..cc6280f 100644 --- a/examples/live/src/Lang.zig +++ b/examples/live/src/Lang.zig @@ -519,8 +519,9 @@ fn expectOps(tape: Tape, want: []const Op) !void { try testing.expectEqualSlices(Op, want, ops(tape)[0..tape.len]); } -/// The survey's program (reports/demo1.md, §1 A). -const survey = +/// The survey's program (reports/demo1.md, §1 A); main.zig's test of the +/// grammar parses it too. +pub const survey = \\# the beat, shared by sound and picture \\bpm = 120 \\beat = t * bpm / 60 diff --git a/examples/live/src/main.zig b/examples/live/src/main.zig index ca4d0be..d6bc8d6 100644 --- a/examples/live/src/main.zig +++ b/examples/live/src/main.zig @@ -82,8 +82,24 @@ pub fn command(ss: *Session, c: *sk.Console, line: []const u8) !bool { /// call deterministic and bounded. A key at the most text took 29 KiB of it. var scratch: [128 * 1024]u8 = undefined; +/// The language's grammar (grammar/, its parser.c compiled in by build.zig), +/// handed to the editor at run time. +pub extern fn tree_sitter_live() *const pe.syntax.ts.Language; +pub fn language() pe.Language { + return .{ .name = "live", .ext = ".live", .ts = tree_sitter_live(), .highlights = @embedFile("highlights.scm"), .indents = @embedFile("indents.scm") }; +} + +/// The text's parse, for the editor's node walks (Alt-o, Alt-i, ...): +/// derived, so not in State, and kept between calls, as Alt-i goes back the +/// way Alt-o came only through its history; forgotten at a jump (`draw`). +/// A reload starts it again, with the code its grammar is in. +// ponytail: the tree a reload leaves behind is leaked (tree-sitter's +// malloc, a few KiB a reload). +var syn: pe.Syntax = .{}; + pub fn update(s: *State, in: *const sk.Input) void { const revision = s.ed.revision; + syn.lang = language(); // a chord's key_down may come with its letter as text too: not typed var chord = false; for (in.events) |e| { @@ -111,7 +127,7 @@ pub fn update(s: *State, in: *const sk.Input) void { var fba: std.heap.FixedBufferAllocator = .init(&scratch); // ponytail: a key the text has no room for is dropped, as part 1's // buffer dropped it; the editor leaves the value as it was. - _ = s.ed.key(fba.allocator(), null, k); + _ = s.ed.key(fba.allocator(), &syn, k); } if (s.ed.revision == revision) return; var text: [Editor.capacity.text]u8 = undefined; @@ -180,6 +196,7 @@ const picture_pipeline: gpu.Pipeline = .{ }; pub fn draw(s: *const State, ss: *Session, f: *sk.Frame) void { + if (f.in.jumped) syn.forget(); f.clear(0x000000); if (!f.host.gpu()) { f.text(16, 16, 2, "live needs a GPU: the host has none.", 0xff8080); @@ -276,8 +293,11 @@ const ink = 0xe8e8e8; const red = 0xff5a50; const selected: sk.Color = .{ .r = 0x3c, .g = 0x6e, .b = 0xc8, .a = 170 }; const also_selected: sk.Color = .{ .r = 0x3c, .g = 0x6e, .b = 0xc8, .a = 90 }; +/// pardes's own theme: its text's ink and a class's. +const theme = &pe.syntax.themes[0]; -/// The editor's text over the picture on a dark band: its lines, every +/// The editor's text over the picture on a dark band: its lines coloured +/// by the grammar in pardes's theme, every /// range (the primary stronger), a caret at each range's head that says /// the mode (a block in normal and select, a bar in insert), the mode's /// name in the corner; the problem as a red mark under its byte and its @@ -289,6 +309,8 @@ fn code(s: *const State, f: *sk.Frame) void { const text = s.ed.bytes(f.scratch) catch return; const ranges = f.scratch.create([pe.max_selections]pe.Selection) catch return; const got = s.ed.ranges(f.scratch, ranges) catch return; + // a class a byte, from the grammar's highlights (none if it fails) + const colors = pe.Syntax.colors(f.scratch, &s.ed, language(), 0, text.len) catch &.{}; const cell = f.host.textSizeIn(.code, scale, "M"); const problem = s.problem.len > 0; var lines: usize = 1; @@ -309,7 +331,16 @@ fn code(s: *const State, f: *sk.Frame) void { const to = @min(@max(r.anchor, r.head), end); if (from < to) f.fill(.{ .x = margin + @as(f32, @floatFromInt(from - start)) * cell[0], .y = y, .w = @as(f32, @floatFromInt(to - from)) * cell[0], .h = cell[1] }, if (i == got.primary) selected else also_selected); } - f.textIn(.code, margin, y, scale, line, ink); + // a run of bytes of one class at a time, in the theme's inks + var a: usize = 0; + while (a < line.len) { + const class = if (start + a < colors.len) colors[start + a] else .none; + var b = a + 1; + while (b < line.len and (if (start + b < colors.len) colors[start + b] else .none) == class) b += 1; + const c = pe.syntax.synInk(theme, class) orelse pe.syntax.ink(theme); + f.textIn(.code, margin + @as(f32, @floatFromInt(a)) * cell[0], y, scale, line[a..b], sk.Color{ .r = c[0], .g = c[1], .b = c[2] }); + a = b; + } for (ranges[0..got.n], 0..) |r, i| { // the head's character: the one before it in a range that // grows forward diff --git a/examples/live/test/grammar.zig b/examples/live/test/grammar.zig new file mode 100644 index 0000000..497c05d --- /dev/null +++ b/examples/live/test/grammar.zig @@ -0,0 +1,54 @@ +//! The language's grammar (grammar/grammar.js, its parser.c compiled into +//! the sketch) against src/Lang.zig, which compiles the text: they must +//! agree on what is well formed, or what is coloured and walked would not +//! be the program that plays. +const std = @import("std"); +const app = @import("app"); +const Lang = @import("Lang"); +const pe = @import("pardes-editor"); + +test "the grammar and Lang.zig agree: both take a program, both refuse a broken line; what only Lang.zig refuses is its meaning" { + const parser = pe.syntax.ts.Parser.create(); + defer parser.destroy(); + try parser.setLanguage(app.tree_sitter_live()); + const Case = struct { text: []const u8, grammar: bool, lang: bool }; + for ([_]Case{ + .{ .text = Lang.survey, .grammar = true, .lang = true }, + .{ .text = "out = sin(tau * 220 * t) * 0.3\ncolor = hsv(x, 0.5, y)", .grammar = true, .lang = true }, + .{ .text = "\n # nothing\n a = 1 + 2 * -t / 4 - (5 - -6) # trailing\n\nout = a + 1e-3\n", .grammar = true, .lang = true }, + // broken lines: both refuse + .{ .text = "out = sin(tau * 220 * t * 0.3", .grammar = false, .lang = false }, + .{ .text = "out = 1 +", .grammar = false, .lang = false }, + .{ .text = "= 1", .grammar = false, .lang = false }, + .{ .text = "out 1", .grammar = false, .lang = false }, + .{ .text = "out", .grammar = false, .lang = false }, + .{ .text = "out = * 2", .grammar = false, .lang = false }, + .{ .text = "out = 1 2", .grammar = false, .lang = false }, + .{ .text = "out = sin(1 2)", .grammar = false, .lang = false }, + .{ .text = "out = 1.2.3", .grammar = false, .lang = false }, + .{ .text = "out = 1 $ 2", .grammar = false, .lang = false }, + .{ .text = "out = (1 + 2))", .grammar = false, .lang = false }, + // well formed, but meaning nothing: only Lang.zig knows its names, + // builtins and arities, and the problem it shows is the one drawn + .{ .text = "out = kick\nkick = 1", .grammar = true, .lang = false }, + .{ .text = "a = 1\na = 2", .grammar = true, .lang = false }, + .{ .text = "sin = 1", .grammar = true, .lang = false }, + .{ .text = "out = sin", .grammar = true, .lang = false }, + .{ .text = "out = foo(2)", .grammar = true, .lang = false }, + .{ .text = "out = mix(1, 2)", .grammar = true, .lang = false }, + .{ .text = "out = rgb(1, 1, 1)", .grammar = true, .lang = false }, + .{ .text = "a = 1\nout = a(2)", .grammar = true, .lang = false }, + }) |case| { + const tree = parser.parseString(case.text, null) orelse return error.NoTree; + defer tree.destroy(); + const lang = Lang.compile(case.text) == .program; + std.testing.expectEqual(case.grammar, !tree.rootNode().hasError()) catch |e| { + std.debug.print("the grammar on {s}\n", .{case.text}); + return e; + }; + std.testing.expectEqual(case.lang, lang) catch |e| { + std.debug.print("Lang.zig on {s}\n", .{case.text}); + return e; + }; + } +} |
