Skip to content
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

Jump to bottom

FIX: SimpleSQLGrammar quote parsing regression #5700

Merged
merged 9 commits into from
Mar 21, 2024
Merged

FIX: SimpleSQLGrammar quote parsing regression #5700

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
63514ce
Update grammar and associated tests
Mar 14, 2024
d8f0385
Grammar cleanup and commenting
Mar 15, 2024
0b2b2ba
Merge branch 'fix-quote-parsing-regression' of https://github.com/jas…
MalloD12 Mar 15, 2024
c40ac87
Add test output to help with future debugging
Mar 16, 2024
fd89a49
Merge branch 'master' into fix-quote-parsing-regression
jasonlyle88 Mar 18, 2024
ba175bf
Two more test scenarios added, plus a formatting change.
MalloD12 Mar 18, 2024
d0ecff2
Merge branch 'fix-quote-parsing-regression' of https://github.com/jas…
MalloD12 Mar 18, 2024
54500f4
Merge branch 'master' into jasonlyle88-fix-quote-parsing-regression
MalloD12 Mar 18, 2024
941ebcc
Merge branch 'master' into fix-quote-parsing-regression
rberezen Mar 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
40 changes: 21 additions & 19 deletions liquibase-standard/src/main/javacc/liquibase/util/grammar/SimpleSqlGrammar.jj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,36 +57,39 @@ TOKEN:
TOKEN : /* Numeric Constants */
{
< S_DOUBLE: ((<S_LONG>)? "." <S_LONG> ( ["e","E"] (["+", "-"])? <S_LONG>)?
|
<S_LONG> "." (["e","E"] (["+", "-"])? <S_LONG>)?
|
<S_LONG> ["e","E"] (["+", "-"])? <S_LONG>
)>
| < S_LONG: ( <DIGIT> )+ >
| < #DIGIT: ["0" - "9"] >
|
<S_LONG> "." (["e","E"] (["+", "-"])? <S_LONG>)?
|
<S_LONG> ["e","E"] (["+", "-"])? <S_LONG>
)>
| < S_LONG: ( <DIGIT> )+ >
| < #DIGIT: ["0" - "9"] >
}

TOKEN:
{
< COMPLEX_IDENTIFIER: (<S_IDENTIFIER> | <S_QUOTED_IDENTIFIER>) ((["\r","\n"," "])* "." (["\r","\n"," "])* (<S_IDENTIFIER> | <S_QUOTED_IDENTIFIER>))+ >
| < S_IDENTIFIER: ( <LETTER> | <UNICODE_LETTERS> )+ ( <DIGIT> | <LETTER> | <UNICODE_LETTERS> | <SPECIAL_CHARS> )* >
| < #LETTER: ["a"-"z", "A"-"Z", "_", "$"] >
| < #SPECIAL_CHARS: "$" | "_" | "#" | "@" >
| < S_IDENTIFIER: ( <LETTER> | <UNICODE_LETTERS> | <FIRST_CHAR_SPECIAL_CHARS> ) ( <LETTER> | <UNICODE_LETTERS> | <SPECIAL_CHARS> | <DIGIT> )* >
| < #LETTER: ["a"-"z", "A"-"Z"] >
| < #FIRST_CHAR_SPECIAL_CHARS: "$" | "_" >
| < #SPECIAL_CHARS: <FIRST_CHAR_SPECIAL_CHARS> | "#" | "@" >

| < #ESC_S_QUOTE_A: ( "''" ) > /* probably the closest to a universal standard */
| < #ESC_S_QUOTE_B: ( "\\'" ) > /* Valid in Postgres and MySQL (if NO_BACKSLASH_ESCAPES not enabled), NOT valid in Oracle or MSSQL */
| < #ESC_D_QUOTE_A: ( "\"\"" ) > /* probably the 2nd closest to a universal standard */
| < #ESC_D_QUOTE_B: ( "\\\"" ) > /* Valid in Postgres and MySQL (if NO_BACKSLASH_ESCAPES not enabled), NOT valid in Oracle or MSSQL */
| < #ESC_NON_QUOTE: "\\" ["n","t","b","r","f","\\","0"] >
| < #ESC_S_QUOTE: ( "''" ) > /* probably the closest to a universal standard */
| < #ESC_D_QUOTE: ( "\"\"" ) > /* probably the 2nd closest to a universal standard */
| < #ESC_ANY_CHAR: "\\" ~[] > // Matches any character following '\'
/* SQL-standard is that string literals are delimited only by single-quote, and double-quotes are only for identifiers... */
| < #S_QUOTED_STRING_HYBRID: ( "'" ( <ESC_S_QUOTE_A> | <ESC_S_QUOTE_B> | <ESC_D_QUOTE_B> | <ESC_NON_QUOTE> | ~["\\","'"] )* ("'" | "\\'")) >
/*
Negative match in hybrid string tokens looks for a single slash (i.e. "\\") so that slashes are matched
with the ESC_ANY_CHAR token rather than prematuraly ending a match
*/
| < #S_QUOTED_STRING_HYBRID: ( "'" ( <ESC_S_QUOTE> | <ESC_ANY_CHAR> | ~["\\","'"] )* ("'" | "\\'")) >
/* ... but many DBs tolerate double-quotes around string literals, including MySQL (unless you enable ANSI SQL mode), and MSSQL (if you disable SET QUOTED_IDENTIFIER) */
| < #D_QUOTED_STRING_HYBRID: ( "\"" ( <ESC_S_QUOTE_B> | <ESC_D_QUOTE_A> | <ESC_D_QUOTE_B> | <ESC_NON_QUOTE> | ~["\\","\""] )* ("\"" | "\\\"")) >
| < #D_QUOTED_STRING_HYBRID: ( "\"" ( <ESC_D_QUOTE> | <ESC_ANY_CHAR> | ~["\\","\""] )* ("\"" | "\\\"")) >
/* Finally... */
| < S_CHAR_LITERAL: (["U","E","N","R","B"]|"RB"|"_utf8")? (<S_QUOTED_STRING_HYBRID> | <D_QUOTED_STRING_HYBRID>) >

| < S_QUOTED_IDENTIFIER: "\"" (~["\n","\r","\""])+ "\"" | ("`" (~["\n","\r","`"])+ "`") | ( "[" ~["0"-"9","]"] (~["\n","\r","]"])* "]" ) >
| < EMPTY_QUOTE: "\"" "\"">
| < EMPTY_QUOTE: "\"" "\"">

/*
Built list from http://stackoverflow.com/a/37668315/45756
Expand Down Expand Up @@ -514,4 +517,3 @@ TOKEN: /* symbols */
"\u00A1"-"\uFF65" /* everything else */
] >
}

15 changes: 13 additions & 2 deletions liquibase-standard/src/test/groovy/liquibase/util/grammar/SimpleSqlGrammarTest.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,15 @@ class SimpleSqlGrammarTest extends Specification {
@Unroll
def test() {
when:
def tokenManager = new SimpleSqlGrammarTokenManager(new SimpleCharStream(new StringReader(input)));
def tokenManager = new SimpleSqlGrammarTokenManager(new SimpleCharStream(new StringReader(input)))
def grammar = new SimpleSqlGrammar(tokenManager)

def tokens = new ArrayList<String>()
Token token
System.out.println("----------------------------------------------------------------")
System.out.println("'" + input + "'")
while ((token = grammar.getNextToken()).kind != SimpleSqlGrammarConstants.EOF) {
System.out.println(" " + String.format('%1$-32s', SimpleSqlGrammarConstants.tokenImage[token.kind]) + ": '" + token.toString() + "'")
tokens.add(token.toString())
}

Expand All @@ -37,7 +40,7 @@ class SimpleSqlGrammarTest extends Specification {
"mysql escaped quotes '\\''" | ["mysql", " ", "escaped", " ", "quotes", " ", "'\\''"]
"invalid ' sql" | ["invalid", " ", "'", " ", "sql"]
"'invalid' ' sql" | ["'invalid'", " ", "'", " ", "sql"]
"utf8-〠＠chars works" | ["utf8", "-", "〠＠chars", " ", "works"]
"utf8-〠＠chars works" | ["utf8", "-", "〠＠chars", " ", "works"]
"single '\\' works" | ["single", " ", "'\\'", " ", "works"]
"double '\\\\' works" | ["double", " ", "'\\\\'", " ", "works"]
"unquoted \\\\ works" | ["unquoted", " ", "\\", "\\", " ", "works"]
Expand All @@ -52,5 +55,13 @@ class SimpleSqlGrammarTest extends Specification {
"This has a \\ and symbol ≤ (u2264)" | ["This", " ", "has", " ", "a", " ", "\\", " ", "and", " ", "symbol", " ", "≤", " ", "(", "u2264", ")"]
"This ≤ (u2264) is before the \\" | ["This", " ", "≤", " ", "(", "u2264", ")", " ", "is", " ", "before", " ", "the", " ", "\\"]
"This has an unicode char ÀÀÀÀÀÀ+++ãããioú≤₢" | ["This", " ", "has", " ", "an", " ", "unicode"," ", "char", " ", "ÀÀÀÀÀÀ", "+", "+", "+", "ãããioú", "≤", "₢"]
"select 'foo\\_bar' from sys.dual;" | ["select", " ", "'foo\\_bar'", " ", "from", " ", "sys.dual", ";"]
"select \"foo\\_bar\" from sys.dual;" | ["select", " ", "\"foo\\_bar\"", " ", "from", " ", "sys.dual", ";"]
"select 'foo\\sbar' from sys.dual;" | ["select", " ", "'foo\\sbar'", " ", "from", " ", "sys.dual", ";"]
"select \"foo\\sbar\" from sys.dual;" | ["select", " ", "\"foo\\sbar\"", " ", "from", " ", "sys.dual", ";"]
"select '' from sys.dual;" | ["select", " ", "''", " ", "from", " ", "sys.dual", ";"]
"select \"\" from sys.dual;" | ["select", " ", "\"\"", " ", "from", " ", "sys.dual", ";"]
"select q'~;\\~' from sys.dual;" | ["select", " ", "q", "'~;\\~'", " ", "from", " ", "sys.dual", ";"]
"select q'{\\\n;\n\\}' from sys.dual;" | ["select", " ", "q", "'{\\\n;\n\\}'", " ", "from", " ", "sys.dual", ";"]
}
}