LLM-Assisted Dialect-Agnostic SQL Query Parsing

Junwen An. 2025. SPLASH Companion.

Read the paper · doi:10.1145/3758316.3763249

What this paper does with SQLancer

One citation, listing DBMS testing among the tasks that rely on query analysis, with SQLancer's work among the references. SQLFlex parses SQL across dialects. Grammar-based parsers, on which query analysis and rewriting tools depend, fail on dialect-specific syntax, while large language models understand SQL but do not reliably produce accurate syntax trees. SQLFlex tries a grammar-based parser first and, when that fails, uses an LLM to split the query into smaller parsable pieces. It parsed 96.37% of queries across eight dialects. Written by claude-opus-5 from the 1 place this paper refers to SQLancer. The quotations below are the paper's own words, stored verbatim when the text was extracted.

How it was classified

uses infrastructure — no

SQLancer is cited, not used; nothing in the mentions describes reusing its code.

extends technique — no

No technique is extended; the citation is background.

compares with — no

No empirical comparison against SQLancer is reported in the mentions.

describes as state of the art — no

The citation does not characterise SQLancer as the state of the art.

SQLancer publications it cites (1)

Bibliography entries that resolved to a SQLancer publication, or to a paper by one of the project's authors. A sentence citing one of these numbers is a reference to SQLancer even when it never writes the name.

#	Entry	Matched as
14	Manuel Rigger and Zhendong Su. 2020. Finding Bugs in Database Systems via Query Partitioning. Proc. ACM Program. Lang. 4, OOPSLA, Article 211 (2020). https://doi.org/10.1145/3428279	sqlancer publication · TLP

Every place it refers to SQLancer (1)

1 sentence, each stored verbatim from the extracted text with where it was found and how. “Citation marker” means the sentence names no tool at all and was reached through a reference number that resolved to a SQLancer publication.

Id	Sentence	Found by	Where
M1	Many tasks, such as SQL linting [ 17], test case reduction [ 10], DBMS testing [ 8,14], and SQL grading [ 2], rely on query analysis and rewriting.	citation marker background	1 Introduction page 1

This page is rendered from _data/papers/paper_doi_10_1145_3758316_3763249.json, extracted from supplied pdf. 3 pages, 19 references parsed.