Support dynamic lexer token emission - #96
Conversation
WalkthroughSummary Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Copy/Paste DetectionFound 18 duplication(s) across 3 changed Rust file(s) (threshold: 100 tokens). Show duplicationsFound a 38 line (198 tokens) duplication in the following files:
atn,
|lexer, action| {
if !generated_action(lexer, action)
&& !dispatch_lexer_action_hook(&hooks, lexer, action)
&& unknown_policy == UnknownSemanticPolicy::Error
&& let (Ok(rule), Ok(index)) = (
usize::try_from(action.rule_index()),
usize::try_from(action.action_index()),
)
{
lexer.record_semantic_error(true, rule, index);
}
},
|lexer, predicate| {
generated_predicate(lexer, predicate)
.or_else(|| dispatch_lexer_predicate_hook(&hooks, lexer, predicate))
.unwrap_or_else(|| match unknown_policy {
UnknownSemanticPolicy::AssumeTrue => true,
UnknownSemanticPolicy::AssumeFalse => false,
UnknownSemanticPolicy::Error => {
lexer.record_semantic_error(
false,
predicate.rule_index(),
predicate.pred_index(),
);
false
}
})
},
accept_adjuster,
);
let token = token?;
hooks.borrow_mut().lexer_token_emitted(
sink.view(token)
.expect("lexer hook token should be present in its sink"),
);
Ok(token)
}Found a 27 line (145 tokens) duplication in the following files:
fn generated_match_token_recovers_missing_token_from_context_follow() {
let atn = generated_match_recovery_atn();
let data = RecognizerData::new(
"Mini.g4",
Vocabulary::new(
[None, Some("'X'"), Some("'Y'")],
[None, Some("X"), Some("Y")],
[None::<&str>, None, None],
),
);
let mut parser = BaseParser::new(
CommonTokenStream::new(Source {
tokens: vec![TestToken::eof("parser-test", 3, 1, 3)],
index: 0,
}),
data,
);
parser.rule_context_stack = vec![
RuleContextFrame {
rule_index: 0,
invoking_state: 0,
},
RuleContextFrame {
rule_index: 1,
invoking_state: 1,
},
];Found a 24 line (135 tokens) duplication in the following files:
pub fn next_token_with_hooks<I, A, P, E>(
lexer: &mut BaseLexer<I>,
sink: &mut TokenSink<'_>,
atn: &LexerAtn,
mut custom_action: A,
mut semantic_predicate: P,
mut accept_adjuster: E,
) -> Result<TokenId, TokenStoreError>
where
I: CharStream,
A: FnMut(&mut BaseLexer<I>, LexerCustomAction),
P: FnMut(&BaseLexer<I>, LexerPredicate) -> bool,
E: FnMut(&mut BaseLexer<I>, i32, usize),
{
next_token_with_hooks_impl(
lexer,
sink,
atn,
&mut custom_action,
&mut semantic_predicate,
&mut accept_adjuster,
LexerMatchStrategy {
compiled: None,
use_cache: false,Found a 22 line (130 tokens) duplication in the following files:
let Some(state) = atn.state(config.state) else {
continue;
};
for transition in &state.transitions {
if !transition.matches(symbol, MIN_CHAR_VALUE, MAX_CHAR_VALUE) {
continue;
}
let mut advanced = config.clone();
set_config_state(atn, &mut advanced, transition.target());
if symbol == EOF {
advanced.consumed_eof = true;
} else {
advanced.position += 1;
}
next.push(advanced);
}
}
let closure = epsilon_closure(atn, next, &mut |predicate| {
semantic_predicate(lexer, predicate)
});
let target_has_semantic_context = closure.has_semantic_context;Found a 27 line (127 tokens) duplication in the following files:
let mut atn = ParserAtnBuilder::new(2);
assert_eq!(
atn.add_state(AtnStateKind::RuleStart, Some(0))
.expect("state")
.index(),
0
);
assert_eq!(
atn.add_state(AtnStateKind::BlockStart, Some(0))
.expect("state")
.index(),
1
);
assert_eq!(
atn.add_state(AtnStateKind::Basic, Some(0))
.expect("state")
.index(),
2
);
assert_eq!(
atn.add_state(AtnStateKind::Basic, Some(0))
.expect("state")
.index(),
3
);
assert_eq!(
atn.add_state(AtnStateKind::BlockEnd, Some(0))Found a 22 line (125 tokens) duplication in the following files:
atn.add_state(AtnStateKind::BlockEnd, Some(0))
.expect("state")
.index(),
4
);
assert_eq!(
atn.add_state(AtnStateKind::RuleStop, Some(0))
.expect("state")
.index(),
5
);
atn.set_rule_to_start_state(vec![0])
.expect("rule start states");
atn.set_rule_to_stop_state(vec![5])
.expect("rule stop states");
atn.add_decision_state(1).expect("decision state");
atn.add_transition(0, ParserTransitionSpec::Epsilon { target: 1 })
.expect("transition");
atn.add_transition(
1,
ParserTransitionSpec::Atom {
target: 2,Found a 29 line (121 tokens) duplication in the following files:
let boundary = left_recursive_boundary(atn, state, target);
outcomes.extend(
self.recognize_state_fast(
atn,
FastRecognizeRequest {
state_number: target,
stop_state,
index,
rule_start_index,
decision_start_index: next_decision_start_index,
precedence,
depth: depth + 1,
recovery_symbols: Rc::clone(&epsilon_recovery_symbols),
recovery_state: epsilon_recovery_state,
},
visiting,
memo,
expected,
)
.into_iter()
.map(|mut outcome| {
if let Some(rule_index) = boundary {
let boundary = self.arena_boundary_node(rule_index);
self.arena_prepend(&mut outcome.nodes, boundary);
}
outcome
}),
);
}Found a 33 line (115 tokens) duplication in the following files:
outcomes.extend(
self.recognize_state(
atn,
RecognizeRequest {
state_number: *target,
stop_state,
index,
rule_start_index,
decision_start_index: next_decision_start_index,
init_action_rules,
predicates,
semantics,
rule_args,
member_actions,
return_actions,
local_int_arg,
member_values: member_values.clone(),
return_values: return_values.clone(),
rule_alt_number: next_alt_number,
track_alt_numbers,
consumed_eof,
precedence,
depth: depth + 1,
recovery_symbols: epsilon_recovery_symbols.clone(),
recovery_state: epsilon_recovery_state,
},
visiting,
memo,
expected,
)
.into_iter()
.map(|mut outcome| {
prepend_decision(&mut outcome, decision);Found a 15 line (113 tokens) duplication in the following files:
fn generated_match_token_counts_single_token_deletion_recovery() {
let atn = generated_match_recovery_atn();
let data = RecognizerData::new(
"Mini.g4",
Vocabulary::new(
[None, Some("'X'"), Some("'Y'"), Some("'Z'")],
[None, Some("X"), Some("Y"), Some("Z")],
[None::<&str>, None, None, None],
),
);
let mut parser = BaseParser::new(
CommonTokenStream::new(Source {
tokens: vec![
TestToken::new(3).with_text("z"),
TestToken::new(2).with_text("y"),Found a 22 line (112 tokens) duplication in the following files:
fn predicate_after_token_atn() -> Atn {
let mut atn = ParserAtnBuilder::new(2);
assert_eq!(
atn.add_state(AtnStateKind::RuleStart, Some(0))
.expect("state")
.index(),
0
);
assert_eq!(
atn.add_state(AtnStateKind::Basic, Some(0))
.expect("state")
.index(),
1
);
assert_eq!(
atn.add_state(AtnStateKind::Basic, Some(0))
.expect("state")
.index(),
2
);
assert_eq!(
atn.add_state(AtnStateKind::Basic, Some(0))Found a 22 line (111 tokens) duplication in the following files:
fn left_recursive_loop_with_caller_follow_atn(caller_symbol: i32) -> Atn {
let mut atn = ParserAtnBuilder::new(2);
assert_eq!(
atn.add_state(AtnStateKind::RuleStart, Some(0))
.expect("state")
.index(),
0
);
assert_eq!(
atn.add_state(AtnStateKind::Basic, Some(0))
.expect("state")
.index(),
1
);
assert_eq!(
atn.add_state(AtnStateKind::Basic, Some(0))
.expect("state")
.index(),
2
);
assert_eq!(
atn.add_state(AtnStateKind::RuleStart, Some(1))Found a 14 line (110 tokens) duplication in the following files:
fn parser_matches_token_and_reports_mismatch() {
let source = Source {
tokens: vec![
TestToken::new(1).with_text("x"),
TestToken::eof("parser-test", 1, 1, 1),
],
index: 0,
};
let data = RecognizerData::new(
"Mini.g4",
Vocabulary::new([None, Some("'x'")], [None, Some("X")], [None::<&str>, None]),
);
let mut parser = BaseParser::new(CommonTokenStream::new(source), data);
let matched = parser.match_token(1).expect("token 1 should match");Found a 13 line (109 tokens) duplication in the following files:
fn parser_matches_token_and_reports_mismatch() {
let source = Source {
tokens: vec![
TestToken::new(1).with_text("x"),
TestToken::eof("parser-test", 1, 1, 1),
],
index: 0,
};
let data = RecognizerData::new(
"Mini.g4",
Vocabulary::new([None, Some("'x'")], [None, Some("X")], [None::<&str>, None]),
);
let mut parser = BaseParser::new(CommonTokenStream::new(source), data);Found a 22 line (108 tokens) duplication in the following files:
) -> Option<RecognizeOutcome> {
let (error_index, message) = self.expected_error_message(rule_index, start_index, expected);
let diagnostic = diagnostic_for_token(self.token_at(error_index), message);
let mut next_index = error_index;
loop {
let symbol = self.token_type_at(next_index);
if sync_symbols.contains(&symbol) {
if next_index == error_index {
return None;
}
break;
}
if symbol == TOKEN_EOF {
break;
}
let after = self.consume_index(next_index, symbol);
if after == next_index {
break;
}
next_index = after;
}
let mut nodes = NodeSeqId::EMPTY;Found a 15 line (108 tokens) duplication in the following files:
fn outcome_ties_keep_later_non_recursive_alternative() {
let arena = RecognitionArena::default();
let first = RecognizeOutcome {
index: 1,
consumed_eof: false,
alt_number: 0,
member_values: BTreeMap::new(),
return_values: BTreeMap::new(),
diagnostics: DiagnosticSeqId::EMPTY,
decisions: Vec::new(),
actions: vec![ParserAction::new(1, 0, 0, None)],
nodes: NodeSeqId::EMPTY,
};
let second = RecognizeOutcome {
actions: vec![ParserAction::new(2, 0, 0, None)],Found a 16 line (106 tokens) duplication in the following files:
atn: &LexerAtn,
hooks: &mut H,
mut generated_action: A,
mut generated_predicate: P,
unknown_policy: UnknownSemanticPolicy,
accept_adjuster: E,
) -> Result<TokenId, TokenStoreError>
where
I: CharStream,
H: SemanticHooks,
A: FnMut(&mut BaseLexer<I>, LexerCustomAction) -> bool,
P: FnMut(&BaseLexer<I>, LexerPredicate) -> Option<bool>,
E: FnMut(&mut BaseLexer<I>, i32, usize),
{
let hooks = RefCell::new(hooks);
let token = next_token_with_hooks(Found a 16 line (105 tokens) duplication in the following files:
let start_state = atn.rule_to_start_state().get(rule_index).ok_or_else(|| {
AntlrError::Unsupported(format!("rule {rule_index} has no start state"))
})?;
let stop_state = atn
.rule_to_stop_state()
.get(rule_index)
.filter(|state| *state != usize::MAX)
.ok_or_else(|| {
AntlrError::Unsupported(format!("rule {rule_index} has no stop state"))
})?;
let start_index = self.current_visible_index();
self.clear_prediction_diagnostics();
self.reset_per_parse_caches();
self.reset_recognition_arena();
let caller_follow_state = self.pending_invoking_follow_state(atn);Found a 13 line (100 tokens) duplication in the following files:
let mut expected = BTreeSet::new();
for index in (1..self.rule_context_stack.len()).rev() {
let invoking_state = self.rule_context_stack[index].invoking_state;
let Ok(state_number) = usize::try_from(invoking_state) else {
continue;
};
let Some(Transition::Rule { follow_state, .. }) = atn
.state(state_number)
.and_then(|state| state.transitions().first())
.map(ParserTransition::data)
else {
continue;
}; |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request enhances the lexer and semantic context (LexerSemCtx) to support advanced token manipulation on the committed action path. Specifically, it allows custom lexer actions to override the pending token type and channel, consume characters, reset the accept position, advance the token start, and queue additional prefix tokens, enabling a single lexer match to emit multiple tokens. It also replaces the temporary LexerActionResult with direct mutations on BaseLexer and adds corresponding unit tests. There are no review comments to address, so I have no feedback to provide.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
tinovyatkin
changed the title
|
@codex review |
|
Codex Review: Didn't find any major issues. Keep them coming! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/atn/lexer.rs`:
- Around line 687-695: Recompute the EOF state after accept_adjuster and any
cursor-repositioning actions, using the final lexer input position rather than
the earlier hit_eof value. Update the emit path around emit_position and
emit_or_enqueue_with_stop so rewinding from EOF allows the remaining suffix to
be processed, and add a regression test covering a rewind at EOF.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 53e0ddeb-6e56-42f7-9f72-ec01a8210ab7
📒 Files selected for processing (4)
README.mdsrc/atn/lexer.rssrc/lexer.rssrc/parser.rs
|
@codex review |
|
Codex Review: Didn't find any major issues. Bravo. Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/atn/lexer.rs (1)
1663-1663: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueSimplify the lookahead condition.
A direct boolean comparison is more idiomatic and readable here than a
matches!macro with a pattern guard.♻️ Proposed refactor
- while matches!(ctx.la(1), value if value == ' ' as i32 || value == '\t' as i32) { + while ctx.la(1) == ' ' as i32 || ctx.la(1) == '\t' as i32 {🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/atn/lexer.rs` at line 1663, In the lexer loop around ctx.la(1), replace the matches! pattern-guard condition with a direct boolean comparison that checks whether the lookahead is a space or tab, preserving the existing whitespace behavior.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@src/atn/lexer.rs`:
- Line 1663: In the lexer loop around ctx.la(1), replace the matches!
pattern-guard condition with a direct boolean comparison that checks whether the
lookahead is a space or tab, preserving the existing whitespace behavior.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: bbab4035-bdbc-4bb8-b81c-1c9dcd7e2dbb
📒 Files selected for processing (1)
src/atn/lexer.rs
|
@coderabbitai Regarding the outside-diff suggestion on |
|
Tip For best results, initiate chat on the files or code changes.
🐇💭 |
1 participant
Summary
BaseLexerso portable lexer commands and custom actions mutate the same emission stateLexerSemCtxnext_tokencall still appends exactly one tokendetermineFunctionbehavior,.identifiersplitting, and EOF rewinds through the compiled lexer DFA, and document the expanded hook surfaceRoot cause and impact
Lexer action results were previously held in a private local value after ATN acceptance. Custom action hooks could change mode state but could not change the emitted token type or channel, and the runtime had no queue for multiple tokens from one match. That made standard ANTLR patterns used by MySQL-class lexers impossible to implement faithfully.
The shared pending-emission state and FIFO bring custom actions onto the same path as
type,channel,skip, andmorecommands, making dynamic function/identifier classification, whitespace-channel changes, and dot-prefix splitting expressible without grammar-specific runtime behavior. EOF state is refreshed after cursor-moving actions so rewound suffixes remain available to the next token call.Fixes #94.
Validation
cargo test --locked --all-features(344 passed)cargo clippy --locked --all-targets --all-features -- -D warningsgit diff --checkBenchmark
Compared the issue implementation at
8a4846a399againstorigin/mainat12712d34eon the same machine with generated Rust parsers only:compare.py --max-regression 1.15 --runtime rust-antlrpassed all 17 fixtures. Aggregate average time changed from 609.112 ms to 605.211 ms (-0.64%). The largest average increase was +2.79% on the 0.174 ms Trino Q21 fixture; larger fixtures remained within approximately +/-1.7%.After the EOF-rewind review fix, the final head at
adc3f4075was compared against8a4846a399with the same 10-iteration setup. All 17 fixtures passed again; aggregate average time changed from 601.911 ms to 594.604 ms (-1.21%), with the largest increase +2.97% on the 0.170 ms Trino Q21 fixture. No regression was observed.