Assertion failure for specific markdown file

[dozed]

The markdown parser fails for the following input: https://gist.github.com/dozed/411fa82c314772f4c57349aa9d88c86d

Reproduce:

const Parser = require('tree-sitter');
const Markdown = require('./build/Release/tree_sitter_markdown_binding');
const parser = new Parser();
parser.setLanguage(Markdown);
const text = fs.readFileSync('Test.md', 'utf8')
const tree = parser.parse(text);
tree

Results in:

terminate called after throwing an instance of 'int'
[1]    268688 IOT instruction (core dumped)  node

It seems to fail in: https://github.com/ikatyang/tree-sitter-markdown/blob/master/src/scanner.cc#L56

The relevant stacktrace in Emacs:

emacs: src/scanner.cc:56: unsigned int {anonymous}::Scanner::serialize(unsigned char*): Assertion `i <= 1024' failed.

Thread 1 "emacs" received signal SIGABRT, Aborted.
__pthread_kill_implementation (no_tid=0, signo=6, threadid=<optimized out>) at ./nptl/pthread_kill.c:44
44	./nptl/pthread_kill.c: No such file or directory.
(gdb) bt
#0  __pthread_kill_implementation (no_tid=0, signo=6, threadid=<optimized out>) at ./nptl/pthread_kill.c:44
#1  __pthread_kill_internal (signo=6, threadid=<optimized out>) at ./nptl/pthread_kill.c:78
#2  __GI___pthread_kill (threadid=<optimized out>, signo=signo@entry=6) at ./nptl/pthread_kill.c:89
#3  0x00007fffee23c406 in __GI_raise (sig=sig@entry=6) at ../sysdeps/posix/raise.c:26
#4  0x00007fffee22287c in __GI_abort () at ./stdlib/abort.c:79
#5  0x00007fffee22279b in __assert_fail_base
    (fmt=0x7fffee3b9f68 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=assertion@entry=0x7fffe40d66d9 "i <= 1024", file=file@entry=0x7fffe40d66ca "src/scanner.cc", line=line@entry=56, function=function@entry=0x7fffe40d3f20 "unsigned int {anonymous}::Scanner::serialize(unsigned char*)") at ./assert/assert.c:92
#6  0x00007fffee233b86 in __assert_fail
    (assertion=assertion@entry=0x7fffe40d66d9 "i <= 1024", file=file@entry=0x7fffe40d66ca "src/scanner.cc", line=line@entry=56, function=function@entry=0x7fffe40d3f20 "unsigned int {anonymous}::Scanner::serialize(unsigned char*)")
    at ./assert/assert.c:101
#7  0x00007fffe407fa49 in (anonymous namespace)::Scanner::serialize (buffer=0x55555be60f65 "\002", this=0x55555bcc10c0) at src/scanner.cc:56
#8  tree_sitter_markdown_external_scanner_serialize(void*, char*) (payload=0x55555bcc10c0, buffer=0x55555be60f65 "\002") at src/scanner.cc:301
#9  0x00007fffdeb4e340 in ts_parser_parse () at /home/user/.emacs.d/elpa/tsc-20220212.1632/tsc-dyn.so
#10 0x00007fffdeb2d0d1 in tsc_dyn::parser::__emr_O_parse_chunks::h8c1adc3341858b2b () at /home/user/.emacs.d/elpa/tsc-20220212.1632/tsc-dyn.so
#11 0x00007fffdeb28a6a in std::panicking::try::h5d5045dd90c5b416 () at /home/user/.emacs.d/elpa/tsc-20220212.1632/tsc-dyn.so
#12 0x00007fffdeb2d526 in tsc_dyn::parser::__emrs_E_parse_chunks::extern_lambda::hd67f0f0313299272 () at /home/user/.emacs.d/elpa/tsc-20220212.1632/tsc-dyn.so
#13 0x00005555558b6797 in funcall_module (function=..., nargs=3, arglist=0x7fffe87ff228) at emacs-module.c:1183
#14 0x000055555585df8e in funcall_lambda (fun=..., nargs=3, arg_vector=0x7fffe87ff228) at eval.c:3162
#15 0x000055555585d0b4 in funcall_general (fun=..., numargs=3, args=0x7fffe87ff228) at eval.c:2945
#16 0x00005555558c64fb in exec_byte_code (fun=..., args_template=0, nargs=0, args=0x7fffe87ff180) at bytecode.c:811
#17 0x000055555585da49 in fetch_and_exec_byte_code (fun=..., args_template=771, nargs=3, args=0x7fffffffc808) at eval.c:3081
#18 0x000055555585df53 in funcall_lambda (fun=..., nargs=3, arg_vector=0x7fffffffc808) at eval.c:3153
#19 0x000055555585d0b4 in funcall_general (fun=..., numargs=3, args=0x7fffffffc808) at eval.c:2945
#20 0x000055555585d3cc in Ffuncall (nargs=4, args=0x7fffffffc800) at eval.c:2995
#21 0x000055555585c58c in funcall_nil (nargs=4, args=0x7fffffffc800) at eval.c:2677
#22 0x000055555585cb1a in run_hook_with_args (nargs=4, args=0x7fffffffc800, funcall=0x55555585c565 <funcall_nil>) at eval.c:2854
#23 0x000055555585c61d in Frun_hook_with_args (nargs=4, args=0x7fffffffc800) at eval.c:2719
#24 0x00005555557b958d in signal_after_change (charpos=648, lendel=0, lenins=1) at insdel.c:2283
#25 0x00005555557b3507 in insert_and_inherit (string=0x7fffffffc953 "``", nbytes=1) at insdel.c:696
#26 0x00005555557dd4de in internal_self_insert (c=96, n=1) at cmds.c:472
#27 0x00005555557dc911 in Fself_insert_command (n=..., c=...) at cmds.c:294
#28 0x000055555585d674 in funcall_subr (subr=0x555556033c20 <Sself_insert_command>, numargs=1, args=0x7fffe87ff100) at eval.c:3036
#29 0x00005555558c64d8 in exec_byte_code (fun=..., args_template=257, nargs=1, args=0x7fffffffd218) at bytecode.c:809
#30 0x000055555585da49 in fetch_and_exec_byte_code (fun=..., args_template=257, nargs=1, args=0x7fffffffd210) at eval.c:3081
#31 0x000055555585df53 in funcall_lambda (fun=..., nargs=1, arg_vector=0x7fffffffd210) at eval.c:3153
#32 0x000055555585d0b4 in funcall_general (fun=..., numargs=1, args=0x7fffffffd210) at eval.c:2945
#33 0x000055555585d3cc in Ffuncall (nargs=2, args=0x7fffffffd208) at eval.c:2995
#34 0x000055555584ef5c in Ffuncall_interactively (nargs=2, args=0x7fffffffd208) at callint.c:250
#35 0x000055555585d8b1 in funcall_subr (subr=0x55555603a220 <Sfuncall_interactively>, numargs=2, args=0x7fffffffd208) at eval.c:3059
#36 0x000055555585d068 in funcall_general (fun=..., numargs=2, args=0x7fffffffd208) at eval.c:2941
#37 0x000055555585d3cc in Ffuncall (nargs=3, args=0x7fffffffd200) at eval.c:2995
#38 0x00005555558518ab in Fcall_interactively (function=..., record_flag=..., keys=...) at callint.c:787
#39 0x000055555585d6aa in funcall_subr (subr=0x55555603a280 <Scall_interactively>, numargs=3, args=0x7fffe87ff070) at eval.c:3038
#40 0x00005555558c64d8 in exec_byte_code (fun=..., args_template=1025, nargs=1, args=0x7fffffffdb20) at bytecode.c:809
#41 0x000055555585da49 in fetch_and_exec_byte_code (fun=..., args_template=1025, nargs=1, args=0x7fffffffdb18) at eval.c:3081
#42 0x000055555585df53 in funcall_lambda (fun=..., nargs=1, arg_vector=0x7fffffffdb18) at eval.c:3153
#43 0x000055555585d0b4 in funcall_general (fun=..., numargs=1, args=0x7fffffffdb18) at eval.c:2945
#44 0x000055555585d3cc in Ffuncall (nargs=2, args=0x7fffffffdb10) at eval.c:2995
#45 0x000055555575dadb in call1 (fn=..., arg1=...) at /home/user/Code/tools/emacs-29/src/lisp.h:3247
#46 0x00005555557615f1 in command_loop_1 () at keyboard.c:1503
#47 0x00005555558583fe in internal_condition_case (bfun=0x555555760d45 <command_loop_1>, handlers=..., hfun=0x5555557600ce <cmd_error>) at eval.c:1474
#48 0x00005555557608da in command_loop_2 (handlers=...) at keyboard.c:1133
#49 0x00005555558574b5 in internal_catch (tag=..., func=0x5555557608ac <command_loop_2>, arg=...) at eval.c:1197
#50 0x0000555555760868 in command_loop () at keyboard.c:1111
#51 0x000055555575fb50 in recursive_edit_1 () at keyboard.c:720
#52 0x000055555575fd84 in Frecursive_edit () at keyboard.c:803
#53 0x000055555575b047 in main (argc=1, argv=0x7fffffffe048) at emacs.c:2529