Skip to content

parser: better unicode escape errors #1128

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kodiakhq merged 1 commit into from
May 10, 2026
Merged

parser: better unicode escape errors #1128

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
246 changes: 141 additions & 105 deletions crates/squawk_syntax/src/snapshots/squawk_syntax__test__unicode_escape_ident_validation.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
source: crates/squawk_syntax/src/test.rs
input_file: crates/squawk_syntax/test_data/validation/unicode_escape_ident.sql
---
SOURCE_FILE@0..425
SOURCE_FILE@0..489
COMMENT@0..5 "-- ok"
WHITESPACE@5..6 "\n"
SELECT@6..32
Expand Down Expand Up @@ -103,142 +103,178 @@ SOURCE_FILE@0..425
STRING@223..226 "'!'"
SEMICOLON@226..227 ";"
WHITESPACE@227..228 "\n"
SELECT@228..241
SELECT_CLAUSE@228..241
SELECT@228..262
SELECT_CLAUSE@228..262
SELECT_KW@228..234 "select"
WHITESPACE@234..235 " "
TARGET_LIST@235..241
TARGET@235..241
NAME_REF@235..241
IDENT@235..241 "U&\" \\\""
SEMICOLON@241..242 ";"
WHITESPACE@242..243 "\n"
SELECT@243..270
SELECT_CLAUSE@243..270
SELECT_KW@243..249 "select"
WHITESPACE@249..250 " "
TARGET_LIST@250..270
TARGET@250..270
NAME_REF@250..270
IDENT@250..259 "U&\"error\""
WHITESPACE@259..260 " "
UESCAPE_KW@260..267 "UESCAPE"
WHITESPACE@267..268 " "
STRING@268..270 "''"
SEMICOLON@270..271 ";"
WHITESPACE@271..272 "\n"
SELECT@272..300
SELECT_CLAUSE@272..300
SELECT_KW@272..278 "select"
WHITESPACE@278..279 " "
TARGET_LIST@279..300
TARGET@279..300
NAME_REF@279..300
IDENT@279..288 "U&\"error\""
WHITESPACE@288..289 " "
UESCAPE_KW@289..296 "UESCAPE"
WHITESPACE@296..297 " "
STRING@297..300 "' '"
SEMICOLON@300..301 ";"
WHITESPACE@301..302 "\n"
SELECT@302..330
SELECT_CLAUSE@302..330
SELECT_KW@302..308 "select"
WHITESPACE@308..309 " "
TARGET_LIST@309..330
TARGET@309..330
NAME_REF@309..330
IDENT@309..318 "U&\"error\""
WHITESPACE@318..319 " "
UESCAPE_KW@319..326 "UESCAPE"
WHITESPACE@326..327 " "
STRING@327..330 "'+'"
SEMICOLON@330..331 ";"
WHITESPACE@331..332 "\n"
SELECT@332..360
SELECT_CLAUSE@332..360
SELECT_KW@332..338 "select"
WHITESPACE@338..339 " "
TARGET_LIST@339..360
TARGET@339..360
NAME_REF@339..360
IDENT@339..348 "U&\"error\""
WHITESPACE@348..349 " "
UESCAPE_KW@349..356 "UESCAPE"
WHITESPACE@356..357 " "
STRING@357..360 "'A'"
SEMICOLON@360..361 ";"
WHITESPACE@361..362 "\n"
SELECT@362..391
SELECT_CLAUSE@362..391
SELECT_KW@362..368 "select"
WHITESPACE@368..369 " "
TARGET_LIST@369..391
TARGET@369..391
NAME_REF@369..391
IDENT@369..378 "U&\"error\""
WHITESPACE@378..379 " "
UESCAPE_KW@379..386 "UESCAPE"
WHITESPACE@386..387 " "
STRING@387..391 "'é'"
SEMICOLON@391..392 ";"
WHITESPACE@392..393 "\n"
SELECT@393..423
SELECT_CLAUSE@393..423
SELECT_KW@393..399 "select"
WHITESPACE@399..400 " "
TARGET_LIST@400..423
TARGET@400..423
NAME_REF@400..423
IDENT@400..409 "U&\"error\""
WHITESPACE@409..410 " "
UESCAPE_KW@410..417 "UESCAPE"
WHITESPACE@417..418 " "
STRING@418..423 "'foo'"
SEMICOLON@423..424 ";"
WHITESPACE@424..425 "\n"
TARGET_LIST@235..262
TARGET@235..262
NAME_REF@235..262
IDENT@235..262 "U&\"many: \\061 \\+0061 ..."
SEMICOLON@262..263 ";"
WHITESPACE@263..264 "\n"
SELECT@264..290
SELECT_CLAUSE@264..290
SELECT_KW@264..270 "select"
WHITESPACE@270..271 " "
TARGET_LIST@271..290
TARGET@271..290
NAME_REF@271..290
IDENT@271..290 "U&\"\\D800\\D801\\DC00\""
SEMICOLON@290..291 ";"
WHITESPACE@291..292 "\n"
SELECT@292..305
SELECT_CLAUSE@292..305
SELECT_KW@292..298 "select"
WHITESPACE@298..299 " "
TARGET_LIST@299..305
TARGET@299..305
NAME_REF@299..305
IDENT@299..305 "U&\" \\\""
SEMICOLON@305..306 ";"
WHITESPACE@306..307 "\n"
SELECT@307..334
SELECT_CLAUSE@307..334
SELECT_KW@307..313 "select"
WHITESPACE@313..314 " "
TARGET_LIST@314..334
TARGET@314..334
NAME_REF@314..334
IDENT@314..323 "U&\"error\""
WHITESPACE@323..324 " "
UESCAPE_KW@324..331 "UESCAPE"
WHITESPACE@331..332 " "
STRING@332..334 "''"
SEMICOLON@334..335 ";"
WHITESPACE@335..336 "\n"
SELECT@336..364
SELECT_CLAUSE@336..364
SELECT_KW@336..342 "select"
WHITESPACE@342..343 " "
TARGET_LIST@343..364
TARGET@343..364
NAME_REF@343..364
IDENT@343..352 "U&\"error\""
WHITESPACE@352..353 " "
UESCAPE_KW@353..360 "UESCAPE"
WHITESPACE@360..361 " "
STRING@361..364 "' '"
SEMICOLON@364..365 ";"
WHITESPACE@365..366 "\n"
SELECT@366..394
SELECT_CLAUSE@366..394
SELECT_KW@366..372 "select"
WHITESPACE@372..373 " "
TARGET_LIST@373..394
TARGET@373..394
NAME_REF@373..394
IDENT@373..382 "U&\"error\""
WHITESPACE@382..383 " "
UESCAPE_KW@383..390 "UESCAPE"
WHITESPACE@390..391 " "
STRING@391..394 "'+'"
SEMICOLON@394..395 ";"
WHITESPACE@395..396 "\n"
SELECT@396..424
SELECT_CLAUSE@396..424
SELECT_KW@396..402 "select"
WHITESPACE@402..403 " "
TARGET_LIST@403..424
TARGET@403..424
NAME_REF@403..424
IDENT@403..412 "U&\"error\""
WHITESPACE@412..413 " "
UESCAPE_KW@413..420 "UESCAPE"
WHITESPACE@420..421 " "
STRING@421..424 "'A'"
SEMICOLON@424..425 ";"
WHITESPACE@425..426 "\n"
SELECT@426..455
SELECT_CLAUSE@426..455
SELECT_KW@426..432 "select"
WHITESPACE@432..433 " "
TARGET_LIST@433..455
TARGET@433..455
NAME_REF@433..455
IDENT@433..442 "U&\"error\""
WHITESPACE@442..443 " "
UESCAPE_KW@443..450 "UESCAPE"
WHITESPACE@450..451 " "
STRING@451..455 "'é'"
SEMICOLON@455..456 ";"
WHITESPACE@456..457 "\n"
SELECT@457..487
SELECT_CLAUSE@457..487
SELECT_KW@457..463 "select"
WHITESPACE@463..464 " "
TARGET_LIST@464..487
TARGET@464..487
NAME_REF@464..487
IDENT@464..473 "U&\"error\""
WHITESPACE@473..474 " "
UESCAPE_KW@474..481 "UESCAPE"
WHITESPACE@481..482 " "
STRING@482..487 "'foo'"
SEMICOLON@487..488 ";"
WHITESPACE@488..489 "\n"

error[syntax-error]: Unicode escape requires 4 hex digits: \XXXX
╭▸
8 │ select U&"\006";
╰╴ ━━━━━━━━
╰╴ ━━━━
error[syntax-error]: Unicode escape requires 6 hex digits: \+XXXXXX
╭▸
9 │ select U&"\+0061";
╰╴ ━━━━━━━━━━
╰╴ ━━━━━━
error[syntax-error]: Unicode escape requires 4 hex digits: \XXXX
╭▸
10 │ select U&"wrong: \06" UESCAPE '\';
╰╴ ━━━━━━━━━━━━━━
╰╴ ━━━
error[syntax-error]: Unicode escape requires 4 hex digits: !XXXX
╭▸
11 │ select U&"wrong: !061" UESCAPE '!';
╰╴ ━━━━━━━━━━━━━━━
╰╴ ━━━━
error[syntax-error]: Unicode escape requires 4 hex digits: \XXXX
╭▸
12 │ select U&"many: \061 \+0061 \zzzz";
╰╴ ━━━━
error[syntax-error]: Unicode escape requires 6 hex digits: \+XXXXXX
╭▸
12 │ select U&"many: \061 \+0061 \zzzz";
╰╴ ━━━━━━
error[syntax-error]: Invalid Unicode escape sequence
╭▸
12 │ select U&"many: \061 \+0061 \zzzz";
╰╴ ━━
error[syntax-error]: Invalid Unicode surrogate pair
╭▸
13 │ select U&"\D800\D801\DC00";
╰╴ ━━━━━━━━━━
error[syntax-error]: Invalid Unicode escape sequence
╭▸
12 │ select U&" \";
╰╴ ━━━━━━
14 │ select U&" \";
╰╴ ━
error[syntax-error]: Invalid unicode escape character
╭▸
13 │ select U&"error" UESCAPE '';
15 │ select U&"error" UESCAPE '';
╰╴ ━━
error[syntax-error]: Invalid unicode escape character
╭▸
14 │ select U&"error" UESCAPE ' ';
16 │ select U&"error" UESCAPE ' ';
╰╴ ━━━
error[syntax-error]: Invalid unicode escape character
╭▸
15 │ select U&"error" UESCAPE '+';
17 │ select U&"error" UESCAPE '+';
╰╴ ━━━
error[syntax-error]: Invalid unicode escape character
╭▸
16 │ select U&"error" UESCAPE 'A';
18 │ select U&"error" UESCAPE 'A';
╰╴ ━━━
error[syntax-error]: Invalid unicode escape character
╭▸
17 │ select U&"error" UESCAPE 'é';
19 │ select U&"error" UESCAPE 'é';
╰╴ ━━━
error[syntax-error]: Invalid unicode escape character
╭▸
18 │ select U&"error" UESCAPE 'foo';
20 │ select U&"error" UESCAPE 'foo';
╰╴ ━━━━━
Loading
Loading