fix: pgsql digest fixtures (typecast spacing) + ParserSQL 1.0.3 bump (PG SET TIME ZONE + multi-value lists)#5805
Merged
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
📜 Recent review details🧰 Additional context used📓 Path-based instructions (2)**/*.{cpp,h,hpp}📄 CodeRabbit inference engine (CLAUDE.md)
Files:
test/tap/tests/**/*.cpp📄 CodeRabbit inference engine (CLAUDE.md)
Files:
🧠 Learnings (1)📚 Learning: 2026-01-20T09:34:19.124ZApplied to files:
🔇 Additional comments (2)
📝 WalkthroughWalkthroughParserSQL version 1.0.3 extends ChangesMulti-value SET parsing and test expansion
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related issues
Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
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 |
![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 updates the parsersql dependency to version 1.0.3 and enhances the query processor to support multi-value SET statements, which is necessary for PostgreSQL features like search_path. It also introduces new test suites for MySQL and PostgreSQL SET commands. Feedback was provided regarding the TestParsePgsql function in the test suite, suggesting the use of a lambda to reduce code duplication when joining strings and the adoption of the %zu format specifier for size_t to improve cross-platform compatibility.
Comment on lines
+162
to
+199
| void TestParsePgsql(const Test* tests, int ntests, const std::string& title) { | ||
| for (int i = 0; i < ntests; i++) { | ||
| std::map<std::string, std::vector<std::string>> data; | ||
| for (auto it = std::begin(tests[i].results); it != std::end(tests[i].results); ++it) { | ||
| data[it->var] = it->values; | ||
| } | ||
|
|
||
| std::map<std::string, std::vector<std::string>> result = parsersql_parse_set_pgsql(tests[i].query); | ||
|
|
||
| bool size_ok = (result.size() == data.size()); | ||
| ok(size_ok, "[%s %d] Sizes match: %lu, %lu", title.c_str(), i, result.size(), data.size()); | ||
| if (!size_ok) { | ||
| diag(" FAIL: sizes differ for query: %s", tests[i].query); | ||
| } | ||
|
|
||
| bool elem_ok = maps_match(result, data); | ||
| ok(elem_ok, "[%s %d] Elements match", title.c_str(), i); | ||
| if (!elem_ok) { | ||
| diag(" FAIL: elements differ for query: %s", tests[i].query); | ||
| for (auto& kv : result) { | ||
| std::string joined; | ||
| for (size_t j = 0; j < kv.second.size(); j++) { | ||
| if (j) joined += " | "; | ||
| joined += kv.second[j]; | ||
| } | ||
| diag(" result[%s] = [%s]", kv.first.c_str(), joined.c_str()); | ||
| } | ||
| for (auto& kv : data) { | ||
| std::string joined; | ||
| for (size_t j = 0; j < kv.second.size(); j++) { | ||
| if (j) joined += " | "; | ||
| joined += kv.second[j]; | ||
| } | ||
| diag(" expected[%s] = [%s]", kv.first.c_str(), joined.c_str()); | ||
| } | ||
| } | ||
| } | ||
| } |
There was a problem hiding this comment.
The TestParsePgsql function contains redundant logic for joining vector elements into a string for diagnostic output. Additionally, it uses %lu as a format specifier for size_t values, which can lead to portability issues or compiler warnings on certain architectures (e.g., 32-bit systems or Windows).
I suggest refactoring the join logic into a local lambda and using the %zu format specifier for size_t to improve maintainability and correctness.
void TestParsePgsql(const Test* tests, int ntests, const std::string& title) {
auto join_vals = [](const std::vector<std::string>& v) {
std::string s;
for (size_t j = 0; j < v.size(); j++) {
if (j) s += " | ";
s += v[j];
}
return s;
};
for (int i = 0; i < ntests; i++) {
std::map<std::string, std::vector<std::string>> data;
for (auto it = std::begin(tests[i].results); it != std::end(tests[i].results); ++it) {
data[it->var] = it->values;
}
std::map<std::string, std::vector<std::string>> result = parsersql_parse_set_pgsql(tests[i].query);
bool size_ok = (result.size() == data.size());
ok(size_ok, "[%s %d] Sizes match: %zu, %zu", title.c_str(), i, result.size(), data.size());
if (!size_ok) {
diag(" FAIL: sizes differ for query: %s", tests[i].query);
}
bool elem_ok = maps_match(result, data);
ok(elem_ok, "[%s %d] Elements match", title.c_str(), i);
if (!elem_ok) {
diag(" FAIL: elements differ for query: %s", tests[i].query);
for (auto& kv : result) {
diag(" result[%s] = [%s]", kv.first.c_str(), join_vals(kv.second).c_str());
}
for (auto& kv : data) {
diag(" expected[%s] = [%s]", kv.first.c_str(), join_vals(kv.second).c_str());
}
}
}
}![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 `@lib/Query_Processor_ParserSQL.cpp`:
- Around line 447-459: The downstream validator in lib/PgSQL_Session.cpp
currently rejects SET RHS vectors with size() > 2, causing valid PostgreSQL
multi-value SETs (e.g. SET search_path TO a,b,c) parsed in
Query_Processor_ParserSQL.cpp to fail; update the consumer/validator in
PgSQL_Session.cpp (the function that inspects the vector of values for
SET/VAR_TARGET handling, e.g., the SET parsing/validation routine) to allow
larger vectors for PostgreSQL-only multi-valued variables by: detect PG dialect
(or session type), identify the variable name (e.g., "search_path" or consult a
small whitelist of known multi-valued PG variables), and relax the size() > 2
rejection for those names (while keeping strict checks for single-valued
variables and non-PG modes), and update the error message accordingly.
🪄 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: CHILL
Plan: Pro
Run ID: 9db3ce64-cff5-4e0e-a46f-cf8522280aea
⛔ Files ignored due to path filters (2)
deps/parsersql/parsersql-1.0.2.tar.gzis excluded by!**/*.gzdeps/parsersql/parsersql-1.0.3.tar.gzis excluded by!**/*.gz
📒 Files selected for processing (3)
deps/parsersql/parsersqllib/Query_Processor_ParserSQL.cpptest/tap/tests/setparser_parsersql_test.cpp
📜 Review details
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{cpp,h,hpp}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{cpp,h,hpp}: Class names should use PascalCase with protocol prefixes (MySQL_, PgSQL_, ProxySQL_)
Member variables should use snake_case
Constants and macros should use UPPER_SNAKE_CASE
Use C++17 features; conditional compilation should use#ifdefPROXYSQL31,#ifdefPROXYSQL40,#ifdefPROXYSQLFFTO,#ifdefPROXYSQLTSDB,#ifdefPROXYSQLCLICKHOUSE (PROXYSQLGENAI no longer guards core code)
Use RAII for resource management and jemalloc for memory allocation
Use pthread mutexes for synchronization and std::atomic<> for counters
Files:
lib/Query_Processor_ParserSQL.cpptest/tap/tests/setparser_parsersql_test.cpp
test/tap/tests/**/*.cpp
📄 CodeRabbit inference engine (CLAUDE.md)
Test files should follow naming pattern test_*.cpp or *-t.cpp in test/tap/tests/
Files:
test/tap/tests/setparser_parsersql_test.cpp
🧠 Learnings (1)
📚 Learning: 2026-01-20T09:34:19.124Z
Learnt from: yuji-hatakeyama
Repo: sysown/proxysql PR: 5307
File: test/tap/tests/reg_test_5306-show_warnings_with_comment-t.cpp:39-48
Timestamp: 2026-01-20T09:34:19.124Z
Learning: In ProxySQL's TAP test suite, resource leaks (e.g., not calling mysql_close() on early return paths) are commonly tolerated because test processes are short-lived and OS frees resources on exit. This pattern applies to all C++ test files under test/tap/tests. When reviewing, recognize this as a project-wide test convention and focus on test correctness and isolation rather than insisting on fixing such leaks in these test files.
Applied to files:
test/tap/tests/setparser_parsersql_test.cpp
🪛 Cppcheck (2.20.0)
test/tap/tests/setparser_parsersql_test.cpp
[warning] 46-46: If memory allocation fails, then there is a possible null pointer dereference
(nullPointerOutOfMemory)
🔇 Additional comments (2)
deps/parsersql/parsersql (1)
1-1: LGTM!test/tap/tests/setparser_parsersql_test.cpp (1)
3-5: LGTM!Also applies to: 7-7, 13-15, 30-97, 161-199, 213-216, 228-231
…value list ParserSQL v1.0.2's PG SET parser had two bugs that were hidden in CI until PR #5760 fixed `test/infra/control/ensure-infras.bash` to actually dispatch `pre-proxysql.sql` hooks (previously only `.bash` hooks ran). With the harness fix in place, `set_parser_algorithm_3-g1` for the first time ran its tests under `pgsql-set_parser_algorithm=3`, surfacing: * `pgsql-set_parameter_validation_test-t` — `SET search_path TO "$user", public` parsed as `search_path = "$user"`, dropping every value after the first comma. * `pgsql-set_statement_test-t` — `SET TIME ZONE 'UTC'` parsed as `time = ZONE`, dropping the actual timezone value entirely. ## Upstream fix ParserSQL v1.0.3 (ProxySQL/ParserSQL PR #38) is the upstream parser fix: * PG `SET TIME ZONE <value>` is now recognised as the PG alias for `SET TimeZone = <value>`. The two-word keyword is detected via case-insensitive identifier lookahead since the tokenizer has no dedicated TK_TIME / TK_ZONE keyword. * PG `parse()` no longer shares MySQL's comma loop. In PG, the comma after the first value is value-list continuation — each subsequent expression is appended as another child of the same NODE_VAR_ASSIGNMENT node, alongside the first RHS. Full upstream test suite: 1223/1223 pass; 0 regressions. ## ProxySQL-side changes * `deps/parsersql/parsersql-1.0.3.tar.gz` — new tarball, replaces 1.0.2. * `deps/parsersql/parsersql` symlink retargeted to `parsersql-1.0.3`. * `lib/Query_Processor_ParserSQL.cpp::walk_set_stmt` — the PG multi-value fix means a single NODE_VAR_ASSIGNMENT can have multiple RHS siblings. The adapter now iterates `target->next_sibling` chain instead of reading a single sibling, so the `map<string, vector<string>>` for `SET search_path TO 'a', 'b', 'c'` carries `["a", "b", "c"]` rather than `["a"]`. Fully backward-compatible for MySQL (always one RHS). * `test/tap/tests/setparser_parsersql_test.cpp` — adds four permanent regression-test groups exercising the library + adapter end-to-end without a live backend: * `mysql_filtered_set` (7 cases) — verifies the filtered-SET variables parse cleanly so the downstream filter logic gets the input it expects. * `mysql_set_testing` (4 cases) — multi-variable comma-separated SET samples from `set_testing-240.csv`. * `pgsql_search_path` (8 cases) — single-value and multi-value shapes from `pgsql-set_parameter_validation_test-t`. * `pgsql_time_zone` (4 cases) — every `SET TIME ZONE ...` shape exercised by `pgsql-set_statement_test-t`. The 4 new assertions for the `INTERVAL '7' HOUR` case capture today's actual ParserSQL output (`timezone = [INTERVAL]`) — the expression parser does not yet consume the full interval modifier chain. The test reflects observable behaviour so it stays green; tightening to capture the full interval value is a future ExpressionParser improvement. ## Test plan - [x] Local rebuild of ProxySQL from the new 1.0.3 tarball: clean. - [x] `./setparser_parsersql_test`: 46 new assertions, all pass. - [x] No regressions in the 256 pre-existing assertions. The same 10 pre-existing failures (sql_mode 23-25, Set1_v2 0-1) — unrelated to this work, present before the upgrade. - [ ] CI on this branch: TAP groups `legacy-g2`, `mysql84-g2`, and `set_parser_algorithm_3-g1` are expected to flip green for the ParserSQL-related failures. Two non-ParserSQL bugs on the algorithm=3 ProxySQL session-dispatch path (`test_filtered_set_statements-t`, `set_testing-t`) remain to be investigated separately — the adapter now returns the correct maps, but downstream dispatch still misbehaves. ## Dependency Should not be merged before ProxySQL/ParserSQL PR #38 is merged and a v1.0.3 tag is cut. The vendored tarball in this commit was built from that PR's branch head; once the upstream tag exists the tarball SHA should be identical to a fresh `git archive --prefix=ParserSQL-1.0.3/ v1.0.3 | gzip` from the upstream tag.
renecannao
force-pushed
the
fix/parsersql-1.0.3-pg-set-fixes
branch
from
fa75a0d to
5a48004
Compare
There was a problem hiding this comment.
🧹 Nitpick comments (1)
test/tap/tests/setparser_parsersql_test.cpp (1)
162-199: ⚖️ Poor tradeoffConsider extracting the common test harness logic.
TestParsePgsqlandTestParse(lines 131-158) share nearly identical structure—only the parser function call and multi-value diagnostic formatting differ. You could reduce duplication by parameterizing the parser function and diagnostic strategy.However, given this is test code that works correctly and the duplication is localized, deferring this refactor is reasonable.
🤖 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 `@test/tap/tests/setparser_parsersql_test.cpp` around lines 162 - 199, TestParsePgsql duplicates most of TestParse (only differing in the parser call and how multi-value diagnostics are formatted); refactor by extracting a generic test harness (e.g., a function TestParseGeneric) that accepts a parser function pointer or std::function (to call parsersql_parse_set_pgsql or the other parser) and a small diagnostic formatter callback for printing multi-value results, then have TestParsePgsql and TestParse call TestParseGeneric with the appropriate parser and formatter to remove the duplicated loop, size/element checks, and diag printing logic while preserving current 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.
Nitpick comments:
In `@test/tap/tests/setparser_parsersql_test.cpp`:
- Around line 162-199: TestParsePgsql duplicates most of TestParse (only
differing in the parser call and how multi-value diagnostics are formatted);
refactor by extracting a generic test harness (e.g., a function
TestParseGeneric) that accepts a parser function pointer or std::function (to
call parsersql_parse_set_pgsql or the other parser) and a small diagnostic
formatter callback for printing multi-value results, then have TestParsePgsql
and TestParse call TestParseGeneric with the appropriate parser and formatter to
remove the duplicated loop, size/element checks, and diag printing logic while
preserving current behavior.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 7a3eb555-a371-48ab-9199-ed2a590c5b4e
⛔ Files ignored due to path filters (2)
deps/parsersql/parsersql-1.0.2.tar.gzis excluded by!**/*.gzdeps/parsersql/parsersql-1.0.3.tar.gzis excluded by!**/*.gz
📒 Files selected for processing (3)
deps/parsersql/parsersqllib/Query_Processor_ParserSQL.cpptest/tap/tests/setparser_parsersql_test.cpp
✅ Files skipped from review due to trivial changes (1)
- deps/parsersql/parsersql
📜 Review details
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{cpp,h,hpp}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{cpp,h,hpp}: Class names should use PascalCase with protocol prefixes (MySQL_, PgSQL_, ProxySQL_)
Member variables should use snake_case
Constants and macros should use UPPER_SNAKE_CASE
Use C++17 features; conditional compilation should use#ifdefPROXYSQL31,#ifdefPROXYSQL40,#ifdefPROXYSQLFFTO,#ifdefPROXYSQLTSDB,#ifdefPROXYSQLCLICKHOUSE (PROXYSQLGENAI no longer guards core code)
Use RAII for resource management and jemalloc for memory allocation
Use pthread mutexes for synchronization and std::atomic<> for counters
Files:
lib/Query_Processor_ParserSQL.cpptest/tap/tests/setparser_parsersql_test.cpp
test/tap/tests/**/*.cpp
📄 CodeRabbit inference engine (CLAUDE.md)
Test files should follow naming pattern test_*.cpp or *-t.cpp in test/tap/tests/
Files:
test/tap/tests/setparser_parsersql_test.cpp
🧠 Learnings (1)
📚 Learning: 2026-01-20T09:34:19.124Z
Learnt from: yuji-hatakeyama
Repo: sysown/proxysql PR: 5307
File: test/tap/tests/reg_test_5306-show_warnings_with_comment-t.cpp:39-48
Timestamp: 2026-01-20T09:34:19.124Z
Learning: In ProxySQL's TAP test suite, resource leaks (e.g., not calling mysql_close() on early return paths) are commonly tolerated because test processes are short-lived and OS frees resources on exit. This pattern applies to all C++ test files under test/tap/tests. When reviewing, recognize this as a project-wide test convention and focus on test correctness and isolation rather than insisting on fixing such leaks in these test files.
Applied to files:
test/tap/tests/setparser_parsersql_test.cpp
🪛 Cppcheck (2.20.0)
test/tap/tests/setparser_parsersql_test.cpp
[warning] 46-46: If memory allocation fails, then there is a possible null pointer dereference
(nullPointerOutOfMemory)
🔇 Additional comments (3)
lib/Query_Processor_ParserSQL.cpp (1)
447-459: LGTM!test/tap/tests/setparser_parsersql_test.cpp (2)
34-96: LGTM!
213-232: LGTM!
…ehavior PR #5755 (commit e6bef5c) fixed `process_pg_typecast()` in `lib/pgsql_tokenizer.cpp` so that the trailing space after a PG typecast is preserved unless the next non-space character is a modifier `(` or array bracket `[`. The commit message documented this as an intentional behaviour change: "The new lookahead-conditional skip preserves the trailing space unless the very next non-space character is a modifier `(` or array bracket `[`." Three test cases in `tokenizer_payloads/pgsql_regular_tokenizer_digests.hjson` hardcoded expected digests against the OLD (buggy) tokenizer output, where the space-eating bug glued the preceding literal to the following operator. With the fix in place those expectations mismatch, making `pgsql-query_digests_stages_test-t` fail deterministically in the legacy-g4 TAP group on v3.0 HEAD: * `::json -> 'key'` STAGE 1: actual `select ? -> ?` vs old expected `select ?-> ?` * `::jsonb @> ...` STAGE 1-4: actual `select ? @> ?` vs old expected `select ?@> ?` * `::money + ...` STAGE 1: actual `select ? + ?` vs old expected `select ?+ ?` For `->` and `+`, only STAGE 1 changes — STAGE 2-4's existing whitespace-collapse step still glues `?->` and `?+` for those operators, so `s2`/`s3`/`s4` expectations stay as-is. For `@>`, none of the stages collapse the space, so all four expectations move. The new actual digest output is the more correct one — it mirrors the existing MySQL tokenizer's behaviour for the same shape, where `'literal' + 'literal'` already produces `? + ?` at STAGE 1. This commit only updates the fixture; no tokenizer or test source changes. Verified locally against the existing test binary (built from v3.0 HEAD, includes the new tokenizer behaviour): ./pgsql-query_digests_stages_test-t → 734/734 ok, RC=0 The 9 previously-failing assertions (#381, #385, #389-#392, #592, #596, #600) all flip to ok with the updated fixture.
renecannao
changed the title
3 tasks
|
Follow-up to the cluster-2 ParserSQL 1.0.3 bump (this same PR),
addressing review feedback from coderabbit + gemini.
## 1. PgSQL_Session: accept multi-value SET vectors (coderabbit, Major)
The previous commit `5a48004af` taught the adapter to walk every RHS
sibling so PG multi-value lists (e.g. `SET search_path TO "$user",
public`) come through as a `std::vector<std::string>` of every value.
But `lib/PgSQL_Session.cpp:4516` still had `size() > 2` →
`unable_to_parse_set_statement()`, which would have caused 3+ value
PG SETs to lock the hostgroup instead of being processed. Worse,
the downstream value-consumer at the same site used only
`it->second.front()`, silently dropping every value past the first
for valid 2-value SETs too.
Fix:
* Drop the upper bound from the cardinality check (keep `< 1` so
empty value lists still fail loudly).
* Join every value in the vector into `value1` with the
comma-separated form PG itself uses for these parameters
(`a, b, c`). Single-value SETs hit the loop with `size()==1` and
take just `it->second.front()`, preserving the previous behaviour.
The validator / hash-compare / tracker / param_status code below the
join is unchanged — it now receives the full joined value instead of
the truncated first element.
## 2. setparser_parsersql_test: drop INTERVAL test that locked in
incomplete behaviour (subagent correctness review, Major)
`parsersql_pgsql_time_zone` previously asserted that
`SET TIME ZONE INTERVAL '7' HOUR` produces `timezone = "INTERVAL"`,
which is the *current* observable output of ParserSQL — the
expression parser does not yet consume the `'7' HOUR` modifier
chain. Encoding that as expected output would flip the test red
when ParserSQL is later improved to capture the full interval
expression, conflating an improvement with a regression.
Removed the case; left a comment in the fixture explaining the gap
so a future contributor adds the case back together with the
ExpressionParser fix.
## 3. Diag-output cleanup (gemini, cosmetic)
* `%lu` → `%zu` for `size_t` (portability — `size_t` is not always
`unsigned long` on 32-bit / Windows).
* Extract the per-vector " | "-separated diag-string builder into
a single `join_values_for_diag()` helper used by both
`TestParse` (now also dumps full vector on mismatch, where it
previously printed just `vals[0]`) and `TestParsePgsql`.
## Verification
* `./setparser_parsersql_test`: 260/270 ok; the 10 remaining
not-ok are unchanged pre-existing failures (`sql_mode 23-25`,
`Set1_v2 0-1`), nothing new from this commit.
* `pgsql_time_zone` group: 6 assertions (3 cases × 2) — confirms
the INTERVAL case is removed cleanly.
* `pgsql_search_path` group: 16 assertions still all pass — the
multi-value join in PgSQL_Session does not affect the parser-
side test (which goes through the adapter, not the session).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Combines two related PG SET / digest fixes (originally split as PR #5804 + #5805) into one PR to avoid running CI twice.
Commit 1 —
fix(test): update pgsql digest fixtures for typecast trailing-space behaviorUpdates 3 expected-digest cases in
tokenizer_payloads/pgsql_regular_tokenizer_digests.hjsonto match the corrected tokenizer behavior from PR #5755 (commite6bef5c58), which intentionally preserves the trailing space after a PG typecast unless the next non-space char is a modifier(or array bracket[.Fixes
pgsql-query_digests_stages_test-t(legacy-g4) — was failing deterministically with 9 not-ok assertions across::json ->,::jsonb @>, and::money +shapes.Commit 2 —
fix(deps): bump ParserSQL to v1.0.3 — PG SET TIME ZONE alias + multi-value listBumps ParserSQL from v1.0.2 to v1.0.3 (ProxySQL/ParserSQL#38, tag pushed). Tarball is byte-identical to https://github.com/ProxySQL/ParserSQL/archive/refs/tags/v1.0.3.tar.gz.
Fixes two PG SET parser bugs in
set_parser_algorithm_3-g1:pgsql-set_parameter_validation_test-t—SET search_path TO "$user", publicdropped every value after the first comma.pgsql-set_statement_test-t—SET TIME ZONE 'UTC'parsed astime = ZONE, dropping the actual timezone value.Includes:
lib/Query_Processor_ParserSQL.cpp— adapterwalk_set_stmtnow iterates all RHS siblings underNODE_VAR_ASSIGNMENTfor PG multi-value lists.test/tap/tests/setparser_parsersql_test.cpp— adds 46 newok()assertions across 4 groups (mysql_filtered_set,mysql_set_testing,pgsql_search_path,pgsql_time_zone) as permanent regression coverage.Test plan
pgsql-query_digests_stages_test-t(commit 1): 734/734 ok localsetparser_parsersql_test(commit 2): 46 new assertions pass; same 10 pre-existing failures (sql_mode 23-25,Set1_v2 0-1) — unrelated baseline.0989cc09554d7019fafb25c4208e10ad68b1938ecd1caae3b55ca6c7b54ec90ematches GitHub release archive.legacy-g4(commit 1) andlegacy-g2/mysql84-g2/legacy-g2-genai/set_parser_algorithm_3-g1(commit 2) expected to flip green for the ParserSQL-related failures.test_filtered_set_statements-t,set_testing-t) are out of scope here. The adapter now produces the correct parsed map for both (verified bymysql_filtered_set+mysql_set_testingassertions); downstream dispatch is a separate investigation.Supersedes
Closes #5804 (digest fixtures), combined here to save CI compute.
Summary by CodeRabbit
New Features
Tests
Chores