Files
Martin Vogel 8669ba8f9e fix(extract): a missing final newline is not a partial parse
A file that does not end with a newline leaves the grammar's mandatory line
terminator MISSING. cbm_collect_error_regions counted that node, so the file was
reported parse_partial with the last line as its error range.

It is not a miss. The node is ZERO-WIDTH and sits at EOF: the parser consumed no
source for it, so by construction nothing was dropped - no construct can live in
a zero-byte span - and every real instruction above it parsed normally. Proven
by dumping the tree: the reporter's two-line Dockerfile yields
(source_file (from_instruction ...) (entrypoint_instruction ...) (MISSING "\n"))
with both instructions intact and the MISSING node spanning bytes 73-73.

It was never Dockerfile-specific. Stripping the trailing newline from the 156
linkable grammar fixtures flips 13 of them to has_error, and SIX produce regions:
dockerfile, tcl, fish, gomod, hyprlang - and makefile, which is a genuinely
different case (its ERROR has WIDTH; the recipe really is lost).

Worse, the ones that stayed silent did so for no principled reason. ini, fsharp,
beancount, requirements, gitignore, sshconfig and kconfig omit the same
terminator, but theirs is a HIDDEN node and hidden nodes are invisible to
ts_node_child(). Whether a user was told their file was partially parsed came
down to whether that grammar's author declared the terminator visible.

The cost was not cosmetic: a phantom parse_partial writes a "<project>::missed"
shadow row, and until #1609 that row made the project fail cross-repo validation
as BOTH source and target. A single absent byte could remove an entire
repository from cross-repo intelligence with no error shown anywhere.

The suppression is deliberately narrow - zero-width AND at EOF. A MISSING or
ERROR node with width still counts even at EOF, and anything before EOF is
untouched. Both callers pass the raw root, so one source_len is correct for
both; verified rather than assumed, since root is bound once and never
reassigned.

Reported by @vitaliy-shatskiy, who could not share the original file and instead
rebuilt the property from scratch with a byte-exact script - an editor would
have silently re-added the newline and hidden it. Their isolation matrix ruled
out BOM, CRLF vs LF, exec-form vs shell-form and file length before we looked at
it once.

Reproduce-first, revert-checked: the Dockerfile and cross-grammar tests fail on
the previous tree and pass with the fix; forcing the new predicate to return
false brings the identical REDs back. Two guards pin the boundary and hold in
both directions - a width-bearing failure at EOF (makefile) and a real
mid-file ERROR in a file that ALSO lacks its final newline (built from
C_IFDEF_SPLIT, the fixture this suite already proves is flagged).

parse_coverage 14, extraction 276, language 217, infrascan 3,
grammar_regression 1 - 511 passed, 0 failed.

Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
2026-08-15 16:09:04 +02:00
..