chore(grammar): vendor Mojo tree-sitter parser

Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>

THIRD_PARTY.md

@@ -26,7 +26,7 @@ The core runtime headers in `internal/cbm/vendored/common/tree_sitter/`
 
 ## Tree-sitter Grammars
 
-160 pre-generated parsers are vendored in `internal/cbm/vendored/grammars/<lang>/`
+159 pre-generated parsers are vendored in `internal/cbm/vendored/grammars/<lang>/`
 (generated `parser.c` plus `scanner.c` where applicable, compiled statically).
 Each grammar is the work of its upstream authors and each grammar directory
 contains the upstream `LICENSE` file.

internal/cbm/grammar_mojo.c

@@ -0,0 +1,4 @@
+// Vendored tree-sitter grammar: mojo
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/mojo/parser.c"
+#include "vendored/grammars/mojo/scanner.c"

internal/cbm/vendored/grammars/MANIFEST.md

@@ -9,11 +9,12 @@ The grammars were originally vendored as bare `parser.c`+`scanner.c` with **no r
 
 ## Summary
 
-- Grammars: **158** — vendored-from-upstream: **141**, first-party/self-maintained: **12**, registry-disagreement: **5** (nim removed 2026-06-12; objectscript_udl + objectscript_routine added 2026-06-24 — see note below)
+- Grammars: **159** — vendored-from-upstream: **142**, first-party/self-maintained: **12**, registry-disagreement: **5** (nim removed 2026-06-12; objectscript_udl + objectscript_routine added 2026-06-24; mojo added 2026-07-01 — see notes below)
 - ABI distribution: **7×** ABI-13 **85×** ABI-14 **64×** ABI-15 (runtime ceiling is ABI 15; never vendor ABI 16 without a runtime upgrade)
 - Vendored copies missing LICENSE: **0** — all upstream LICENSE files restored 2026-06-11 (first-party grammars carry the project MIT license; `move` uses the Helix-listed upstream tzakian/tree-sitter-move MIT text, `zsh` uses georgeharker/tree-sitter-zsh MIT)
 - `verdict`: VERIFIED-BOTH = our source matches *both* registries; VERIFIED-NVIM/HELIX = matches one; registry-disagreement = registries name a different repo (listed separately); `vendor-maintained` = the language vendor's own grammar, not in nvim/Helix.
 - **objectscript_udl / objectscript_routine** (added 2026-06-24): vendored from [intersystems/tree-sitter-objectscript](https://github.com/intersystems/tree-sitter-objectscript) @ `a7ffcdf` — MIT, the InterSystems-official grammars (a niche vendor language, hence `vendor-maintained`, not in nvim-treesitter/Helix). **Re-vendor note:** each `scanner.c`'s upstream `#include "../../common/scanner.h"` is repointed to a per-directory `objectscript_common.h` (a verbatim copy of upstream `common/scanner.h`), because this repo's shared `vendored/common/scanner.h` belongs to the cfml/fsharp grammars and differs. The generated `parser.c`/`scanner.c` are otherwise byte-for-byte upstream — on re-vendor, re-apply only that single include rename.
+- **mojo** (added 2026-07-01): vendored from [lsh/tree-sitter-mojo](https://github.com/lsh/tree-sitter-mojo) @ `33193a99afe6` — MIT, ABI 15. Helix tracks `lsh/tree-sitter-mojo` as its Mojo grammar source, but the Helix-pinned commit (`3d7c53b8038f`) no longer resolves in the upstream repository after a force-push, so this vendor uses current upstream `main` rather than the stale registry SHA. Security review covered only the vendored C surface (`parser.c`, `scanner.c`, `tree_sitter/*.h`) plus upstream license/provenance metadata; no package manager hooks, workflow files, prompt/agent instruction files, or generated lockfiles were vendored.
 
 > ⚠️ **Pinned commit = the revision nvim-treesitter/Helix vendor** (battle-tested, canonical source), not bleeding-edge HEAD. When re-vendoring, update the pinned commit here.
 
@@ -143,6 +144,7 @@ Re-vendoring from upstream must re-apply these.
 | matlab | 15 | acristoffers/tree-sitter-matlab | `c2390a59016f` | VERIFIED-BOTH | ✅ |
 | mermaid | 14 | monaqa/tree-sitter-mermaid | `90ae195b3193` | VERIFIED-BOTH | ✅ |
 | meson | 15 | tree-sitter-grammars/tree-sitter-meson | `c84f3540624b` | VERIFIED-BOTH | ✅ |
+| mojo | 15 | lsh/tree-sitter-mojo | `33193a99afe6` | VERIFIED-HELIX-SOURCE | ✅ |
 | nasm | 14 | naclsn/tree-sitter-nasm | `d1b3638d017f` | VERIFIED-BOTH | ✅ |
 | nickel | 15 | nickel-lang/tree-sitter-nickel | `b5b6cc3bc7b9` | VERIFIED-BOTH | ✅ |
 | nix | 13 | nix-community/tree-sitter-nix | `eabf96807ea4` | VERIFIED-BOTH | ✅ |

internal/cbm/vendored/grammars/mojo/LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Max Brunsfeld
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

internal/cbm/vendored/grammars/mojo/scanner.c

@@ -0,0 +1,498 @@
+#include "tree_sitter/array.h"
+#include "tree_sitter/parser.h"
+
+#include <assert.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+
+enum TokenType {
+    NEWLINE,
+    INDENT,
+    DEDENT,
+    STRING_START,
+    STRING_CONTENT,
+    ESCAPE_INTERPOLATION,
+    STRING_END,
+    COMMENT,
+    CLOSE_PAREN,
+    CLOSE_BRACKET,
+    CLOSE_BRACE,
+    EXCEPT,
+    // MLIR backtick-fragment interior tokens. Emitted only inside ``…`` MLIR
+    // fragments (where comment/string lexing is suppressed) so the interior is
+    // tokenized into highlightable pieces.
+    MLIR_BACKTICK,
+    MLIR_IDENT,
+    MLIR_NUMBER,
+    MLIR_PUNCTUATION,
+};
+
+typedef enum {
+    SingleQuote = 1 << 0,
+    DoubleQuote = 1 << 1,
+    BackQuote = 1 << 2,
+    Raw = 1 << 3,
+    Format = 1 << 4,
+    Triple = 1 << 5,
+    Bytes = 1 << 6,
+} Flags;
+
+typedef struct {
+    char flags;
+} Delimiter;
+
+static inline Delimiter new_delimiter() { return (Delimiter){0}; }
+
+static inline bool is_format(Delimiter *delimiter) { return delimiter->flags & Format; }
+
+static inline bool is_raw(Delimiter *delimiter) { return delimiter->flags & Raw; }
+
+static inline bool is_triple(Delimiter *delimiter) { return delimiter->flags & Triple; }
+
+static inline bool is_bytes(Delimiter *delimiter) { return delimiter->flags & Bytes; }
+
+static inline int32_t end_character(Delimiter *delimiter) {
+    if (delimiter->flags & SingleQuote) {
+        return '\'';
+    }
+    if (delimiter->flags & DoubleQuote) {
+        return '"';
+    }
+    if (delimiter->flags & BackQuote) {
+        return '`';
+    }
+    return 0;
+}
+
+static inline void set_format(Delimiter *delimiter) { delimiter->flags |= Format; }
+
+static inline void set_raw(Delimiter *delimiter) { delimiter->flags |= Raw; }
+
+static inline void set_triple(Delimiter *delimiter) { delimiter->flags |= Triple; }
+
+static inline void set_bytes(Delimiter *delimiter) { delimiter->flags |= Bytes; }
+
+static inline void set_end_character(Delimiter *delimiter, int32_t character) {
+    switch (character) {
+        case '\'':
+            delimiter->flags |= SingleQuote;
+            break;
+        case '"':
+            delimiter->flags |= DoubleQuote;
+            break;
+        case '`':
+            delimiter->flags |= BackQuote;
+            break;
+        default:
+            assert(false);
+    }
+}
+
+typedef struct {
+    Array(uint16_t) indents;
+    Array(Delimiter) delimiters;
+    bool inside_interpolated_string;
+} Scanner;
+
+static inline void advance(TSLexer *lexer) { lexer->advance(lexer, false); }
+
+static inline void skip(TSLexer *lexer) { lexer->advance(lexer, true); }
+
+bool tree_sitter_mojo_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
+    Scanner *scanner = (Scanner *)payload;
+
+    bool error_recovery_mode = valid_symbols[STRING_CONTENT] && valid_symbols[INDENT];
+    bool within_brackets = valid_symbols[CLOSE_BRACE] || valid_symbols[CLOSE_PAREN] || valid_symbols[CLOSE_BRACKET];
+
+    // MLIR backtick-fragment tokenization. Inside ``__mlir_op.`...` `` and the
+    // like, the interior is lexed into typed/number/punctuation pieces so it can
+    // be highlighted as MLIR. Comment and string lexing are suppressed here by
+    // handling the characters directly and returning before that logic runs.
+    bool mlir_interior = valid_symbols[MLIR_IDENT] || valid_symbols[MLIR_NUMBER] ||
+                         valid_symbols[MLIR_PUNCTUATION];
+    if (!error_recovery_mode && (mlir_interior || valid_symbols[MLIR_BACKTICK])) {
+        if (mlir_interior) {
+            // Skip insignificant whitespace between fragment pieces.
+            while (lexer->lookahead == ' ' || lexer->lookahead == '\t') {
+                skip(lexer);
+            }
+        }
+        int32_t c = lexer->lookahead;
+        if (c == '`' && valid_symbols[MLIR_BACKTICK]) {
+            advance(lexer);
+            lexer->mark_end(lexer);
+            lexer->result_symbol = MLIR_BACKTICK;
+            return true;
+        }
+        if (mlir_interior) {
+            if (c == '_' || (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z')) {
+                while (true) {
+                    int32_t d = lexer->lookahead;
+                    if (d == '_' || (d >= 'A' && d <= 'Z') || (d >= 'a' && d <= 'z') ||
+                        (d >= '0' && d <= '9')) {
+                        advance(lexer);
+                    } else {
+                        break;
+                    }
+                }
+                lexer->mark_end(lexer);
+                lexer->result_symbol = MLIR_IDENT;
+                return true;
+            }
+            if (c >= '0' && c <= '9') {
+                while (lexer->lookahead >= '0' && lexer->lookahead <= '9') {
+                    advance(lexer);
+                }
+                lexer->mark_end(lexer);
+                lexer->result_symbol = MLIR_NUMBER;
+                return true;
+            }
+            if (c != 0 && c != '`' && c != '\n' && c != '\r') {
+                // A single punctuation/other character.
+                advance(lexer);
+                lexer->mark_end(lexer);
+                lexer->result_symbol = MLIR_PUNCTUATION;
+                return true;
+            }
+        }
+        return false;
+    }
+
+    bool advanced_once = false;
+    if (valid_symbols[ESCAPE_INTERPOLATION] && scanner->delimiters.size > 0 &&
+        (lexer->lookahead == '{' || lexer->lookahead == '}') && !error_recovery_mode) {
+        Delimiter *delimiter = array_back(&scanner->delimiters);
+        if (is_format(delimiter)) {
+            lexer->mark_end(lexer);
+            bool is_left_brace = lexer->lookahead == '{';
+            advance(lexer);
+            advanced_once = true;
+            if ((lexer->lookahead == '{' && is_left_brace) || (lexer->lookahead == '}' && !is_left_brace)) {
+                advance(lexer);
+                lexer->mark_end(lexer);
+                lexer->result_symbol = ESCAPE_INTERPOLATION;
+                return true;
+            }
+            return false;
+        }
+    }
+
+    if (valid_symbols[STRING_CONTENT] && scanner->delimiters.size > 0 && !error_recovery_mode) {
+        Delimiter *delimiter = array_back(&scanner->delimiters);
+        int32_t end_char = end_character(delimiter);
+        bool has_content = advanced_once;
+        while (lexer->lookahead) {
+            if ((advanced_once || lexer->lookahead == '{' || lexer->lookahead == '}') && is_format(delimiter)) {
+                lexer->mark_end(lexer);
+                lexer->result_symbol = STRING_CONTENT;
+                return has_content;
+            }
+            if (lexer->lookahead == '\\') {
+                if (is_raw(delimiter)) {
+                    // Step over the backslash.
+                    advance(lexer);
+                    // Step over any escaped quotes.
+                    if (lexer->lookahead == end_character(delimiter) || lexer->lookahead == '\\') {
+                        advance(lexer);
+                    }
+                    // Step over newlines
+                    if (lexer->lookahead == '\r') {
+                        advance(lexer);
+                        if (lexer->lookahead == '\n') {
+                            advance(lexer);
+                        }
+                    } else if (lexer->lookahead == '\n') {
+                        advance(lexer);
+                    }
+                    continue;
+                }
+                if (is_bytes(delimiter)) {
+                    lexer->mark_end(lexer);
+                    advance(lexer);
+                    if (lexer->lookahead == 'N' || lexer->lookahead == 'u' || lexer->lookahead == 'U') {
+                        // In bytes string, \N{...}, \uXXXX and \UXXXXXXXX are
+                        // not escape sequences
+                        // https://docs.mojo.org/3/reference/lexical_analysis.html#string-and-bytes-literals
+                        advance(lexer);
+                    } else {
+                        lexer->result_symbol = STRING_CONTENT;
+                        return has_content;
+                    }
+                } else {
+                    lexer->mark_end(lexer);
+                    lexer->result_symbol = STRING_CONTENT;
+                    return has_content;
+                }
+            } else if (lexer->lookahead == end_char) {
+                if (is_triple(delimiter)) {
+                    lexer->mark_end(lexer);
+                    advance(lexer);
+                    if (lexer->lookahead == end_char) {
+                        advance(lexer);
+                        if (lexer->lookahead == end_char) {
+                            if (has_content) {
+                                lexer->result_symbol = STRING_CONTENT;
+                            } else {
+                                advance(lexer);
+                                lexer->mark_end(lexer);
+                                array_pop(&scanner->delimiters);
+                                lexer->result_symbol = STRING_END;
+                                scanner->inside_interpolated_string = false;
+                            }
+                            return true;
+                        }
+                        lexer->mark_end(lexer);
+                        lexer->result_symbol = STRING_CONTENT;
+                        return true;
+                    }
+                    lexer->mark_end(lexer);
+                    lexer->result_symbol = STRING_CONTENT;
+                    return true;
+                }
+                if (has_content) {
+                    lexer->result_symbol = STRING_CONTENT;
+                } else {
+                    advance(lexer);
+                    array_pop(&scanner->delimiters);
+                    lexer->result_symbol = STRING_END;
+                    scanner->inside_interpolated_string = false;
+                }
+                lexer->mark_end(lexer);
+                return true;
+
+            } else if (lexer->lookahead == '\n' && has_content && !is_triple(delimiter)) {
+                return false;
+            }
+            advance(lexer);
+            has_content = true;
+        }
+    }
+
+    lexer->mark_end(lexer);
+
+    bool found_end_of_line = false;
+    uint16_t indent_length = 0;
+    int32_t first_comment_indent_length = -1;
+    for (;;) {
+        if (lexer->lookahead == '\n') {
+            found_end_of_line = true;
+            indent_length = 0;
+            skip(lexer);
+        } else if (lexer->lookahead == ' ') {
+            indent_length++;
+            skip(lexer);
+        } else if (lexer->lookahead == '\r' || lexer->lookahead == '\f') {
+            indent_length = 0;
+            skip(lexer);
+        } else if (lexer->lookahead == '\t') {
+            indent_length += 8;
+            skip(lexer);
+        } else if (lexer->lookahead == '#' && (valid_symbols[INDENT] || valid_symbols[DEDENT] ||
+                                               valid_symbols[NEWLINE] || valid_symbols[EXCEPT])) {
+            // If we haven't found an EOL yet,
+            // then this is a comment after an expression:
+            //   foo = bar # comment
+            // Just return, since we don't want to generate an indent/dedent
+            // token.
+            if (!found_end_of_line) {
+                return false;
+            }
+            if (first_comment_indent_length == -1) {
+                first_comment_indent_length = (int32_t)indent_length;
+            }
+            while (lexer->lookahead && lexer->lookahead != '\n') {
+                skip(lexer);
+            }
+            skip(lexer);
+            indent_length = 0;
+        } else if (lexer->lookahead == '\\') {
+            skip(lexer);
+            if (lexer->lookahead == '\r') {
+                skip(lexer);
+            }
+            if (lexer->lookahead == '\n' || lexer->eof(lexer)) {
+                skip(lexer);
+            } else {
+                return false;
+            }
+        } else if (lexer->eof(lexer)) {
+            indent_length = 0;
+            found_end_of_line = true;
+            break;
+        } else {
+            break;
+        }
+    }
+
+    if (found_end_of_line) {
+        if (scanner->indents.size > 0) {
+            uint16_t current_indent_length = *array_back(&scanner->indents);
+
+            if (valid_symbols[INDENT] && indent_length > current_indent_length) {
+                array_push(&scanner->indents, indent_length);
+                lexer->result_symbol = INDENT;
+                return true;
+            }
+
+            bool next_tok_is_string_start =
+                lexer->lookahead == '\"' || lexer->lookahead == '\'' || lexer->lookahead == '`';
+
+            if ((valid_symbols[DEDENT] ||
+                 (!valid_symbols[NEWLINE] && !(valid_symbols[STRING_START] && next_tok_is_string_start) &&
+                  !within_brackets)) &&
+                indent_length < current_indent_length && !scanner->inside_interpolated_string &&
+
+                // Wait to create a dedent token until we've consumed any
+                // comments
+                // whose indentation matches the current block.
+                first_comment_indent_length < (int32_t)current_indent_length) {
+                array_pop(&scanner->indents);
+                lexer->result_symbol = DEDENT;
+                return true;
+            }
+        }
+
+        if (valid_symbols[NEWLINE] && !error_recovery_mode) {
+            lexer->result_symbol = NEWLINE;
+            return true;
+        }
+    }
+
+    if (first_comment_indent_length == -1 && valid_symbols[STRING_START]) {
+        Delimiter delimiter = new_delimiter();
+
+        bool has_flags = false;
+        while (lexer->lookahead) {
+            if (lexer->lookahead == 'f' || lexer->lookahead == 'F' || lexer->lookahead == 't' ||
+                lexer->lookahead == 'T') {
+                set_format(&delimiter);
+            } else if (lexer->lookahead == 'r' || lexer->lookahead == 'R') {
+                set_raw(&delimiter);
+            } else if (lexer->lookahead == 'b' || lexer->lookahead == 'B') {
+                set_bytes(&delimiter);
+            } else if (lexer->lookahead != 'u' && lexer->lookahead != 'U') {
+                break;
+            }
+            has_flags = true;
+            advance(lexer);
+        }
+
+        if (lexer->lookahead == '`') {
+            set_end_character(&delimiter, '`');
+            advance(lexer);
+            lexer->mark_end(lexer);
+        } else if (lexer->lookahead == '\'') {
+            set_end_character(&delimiter, '\'');
+            advance(lexer);
+            lexer->mark_end(lexer);
+            if (lexer->lookahead == '\'') {
+                advance(lexer);
+                if (lexer->lookahead == '\'') {
+                    advance(lexer);
+                    lexer->mark_end(lexer);
+                    set_triple(&delimiter);
+                }
+            }
+        } else if (lexer->lookahead == '"') {
+            set_end_character(&delimiter, '"');
+            advance(lexer);
+            lexer->mark_end(lexer);
+            if (lexer->lookahead == '"') {
+                advance(lexer);
+                if (lexer->lookahead == '"') {
+                    advance(lexer);
+                    lexer->mark_end(lexer);
+                    set_triple(&delimiter);
+                }
+            }
+        }
+
+        if (end_character(&delimiter)) {
+            array_push(&scanner->delimiters, delimiter);
+            lexer->result_symbol = STRING_START;
+            scanner->inside_interpolated_string = is_format(&delimiter);
+            return true;
+        }
+        if (has_flags) {
+            return false;
+        }
+    }
+
+    return false;
+}
+
+unsigned tree_sitter_mojo_external_scanner_serialize(void *payload, char *buffer) {
+    Scanner *scanner = (Scanner *)payload;
+
+    size_t size = 0;
+
+    buffer[size++] = (char)scanner->inside_interpolated_string;
+
+    size_t delimiter_count = scanner->delimiters.size;
+    if (delimiter_count > UINT8_MAX) {
+        delimiter_count = UINT8_MAX;
+    }
+    buffer[size++] = (char)delimiter_count;
+
+    if (delimiter_count > 0) {
+        memcpy(&buffer[size], scanner->delimiters.contents, delimiter_count);
+    }
+    size += delimiter_count;
+
+    uint32_t iter = 1;
+    for (; iter < scanner->indents.size && size < TREE_SITTER_SERIALIZATION_BUFFER_SIZE; ++iter) {
+        uint16_t indent_value = *array_get(&scanner->indents, iter);
+        buffer[size++] = (char)(indent_value & 0xFF);
+        buffer[size++] = (char)((indent_value >> 8) & 0xFF);
+    }
+
+    return size;
+}
+
+void tree_sitter_mojo_external_scanner_deserialize(void *payload, const char *buffer, unsigned length) {
+    Scanner *scanner = (Scanner *)payload;
+
+    array_delete(&scanner->delimiters);
+    array_delete(&scanner->indents);
+    array_push(&scanner->indents, 0);
+
+    if (length > 0) {
+        size_t size = 0;
+
+        scanner->inside_interpolated_string = (bool)buffer[size++];
+
+        size_t delimiter_count = (uint8_t)buffer[size++];
+        if (delimiter_count > 0) {
+            array_reserve(&scanner->delimiters, delimiter_count);
+            scanner->delimiters.size = delimiter_count;
+            memcpy(scanner->delimiters.contents, &buffer[size], delimiter_count);
+            size += delimiter_count;
+        }
+
+        for (; size + 1 < length; size += 2) {
+            uint16_t indent_value = (unsigned char)buffer[size] | ((unsigned char)buffer[size + 1] << 8);
+            array_push(&scanner->indents, indent_value);
+        }
+    }
+}
+
+void *tree_sitter_mojo_external_scanner_create() {
+#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 201112L)
+    _Static_assert(sizeof(Delimiter) == sizeof(char), "");
+#else
+    assert(sizeof(Delimiter) == sizeof(char));
+#endif
+    Scanner *scanner = calloc(1, sizeof(Scanner));
+    array_init(&scanner->indents);
+    array_init(&scanner->delimiters);
+    tree_sitter_mojo_external_scanner_deserialize(scanner, NULL, 0);
+    return scanner;
+}
+
+void tree_sitter_mojo_external_scanner_destroy(void *payload) {
+    Scanner *scanner = (Scanner *)payload;
+    array_delete(&scanner->indents);
+    array_delete(&scanner->delimiters);
+    free(scanner);
+}

internal/cbm/vendored/grammars/mojo/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_

internal/cbm/vendored/grammars/mojo/tree_sitter/array.h

@@ -0,0 +1,291 @@
+#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) \
+  _array__reserve((Array *)(self), 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) _array__delete((Array *)(self))
+
+/// Push a new `element` onto the end of the array.
+#define array_push(self, element)                            \
+  (_array__grow((Array *)(self), 1, array_elem_size(self)), \
+   (self)->contents[(self)->size++] = (element))
+
+/// Increase the array's size by `count` elements.
+/// New elements are zero-initialized.
+#define array_grow_by(self, count) \
+  do { \
+    if ((count) == 0) break; \
+    _array__grow((Array *)(self), 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, contents)                    \
+  _array__splice(                                               \
+    (Array *)(self), array_elem_size(self), (self)->size, \
+    0, count,  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)  \
+  _array__splice(                                                       \
+    (Array *)(self), 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) \
+  _array__splice((Array *)(self), 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((Array *)(self), 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) \
+  _array__assign((Array *)(self), (const Array *)(other), array_elem_size(self))
+
+/// Swap one array with another
+#define array_swap(self, other) \
+  _array__swap((Array *)(self), (Array *)(other))
+
+/// 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
+
+typedef Array(void) Array;
+
+/// This is not what you're looking for, see `array_delete`.
+static inline void _array__delete(Array *self) {
+  if (self->contents) {
+    ts_free(self->contents);
+    self->contents = NULL;
+    self->size = 0;
+    self->capacity = 0;
+  }
+}
+
+/// This is not what you're looking for, see `array_erase`.
+static inline void _array__erase(Array *self, size_t element_size,
+                                uint32_t index) {
+  assert(index < self->size);
+  char *contents = (char *)self->contents;
+  memmove(contents + index * element_size, contents + (index + 1) * element_size,
+          (self->size - index - 1) * element_size);
+  self->size--;
+}
+
+/// This is not what you're looking for, see `array_reserve`.
+static inline void _array__reserve(Array *self, size_t element_size, uint32_t new_capacity) {
+  if (new_capacity > self->capacity) {
+    if (self->contents) {
+      self->contents = ts_realloc(self->contents, new_capacity * element_size);
+    } else {
+      self->contents = ts_malloc(new_capacity * element_size);
+    }
+    self->capacity = new_capacity;
+  }
+}
+
+/// This is not what you're looking for, see `array_assign`.
+static inline void _array__assign(Array *self, const Array *other, size_t element_size) {
+  _array__reserve(self, element_size, other->size);
+  self->size = other->size;
+  memcpy(self->contents, other->contents, self->size * element_size);
+}
+
+/// This is not what you're looking for, see `array_swap`.
+static inline void _array__swap(Array *self, Array *other) {
+  Array swap = *other;
+  *other = *self;
+  *self = swap;
+}
+
+/// This is not what you're looking for, see `array_push` or `array_grow_by`.
+static inline void _array__grow(Array *self, uint32_t count, size_t element_size) {
+  uint32_t new_size = self->size + count;
+  if (new_size > self->capacity) {
+    uint32_t new_capacity = self->capacity * 2;
+    if (new_capacity < 8) new_capacity = 8;
+    if (new_capacity < new_size) new_capacity = new_size;
+    _array__reserve(self, element_size, new_capacity);
+  }
+}
+
+/// This is not what you're looking for, see `array_splice`.
+static inline void _array__splice(Array *self, size_t element_size,
+                                 uint32_t index, uint32_t old_count,
+                                 uint32_t new_count, const void *elements) {
+  uint32_t new_size = self->size + new_count - old_count;
+  uint32_t old_end = index + old_count;
+  uint32_t new_end = index + new_count;
+  assert(old_end <= self->size);
+
+  _array__reserve(self, element_size, new_size);
+
+  char *contents = (char *)self->contents;
+  if (self->size > old_end) {
+    memmove(
+      contents + new_end * element_size,
+      contents + old_end * element_size,
+      (self->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
+      );
+    }
+  }
+  self->size += new_count - old_count;
+}
+
+/// 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_

internal/cbm/vendored/grammars/mojo/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_