diff options
| author | Peter Eisentraut | 2021-03-28 06:16:15 +0000 |
|---|---|---|
| committer | Peter Eisentraut | 2021-03-29 09:56:53 +0000 |
| commit | f37fec837ce8bf7af408ba66d32099e5a0182402 (patch) | |
| tree | cfbdeae1f431dab8803c9d2cac91e4d71a5e1cad /src/test | |
| parent | ebedd0c78fc51c293abe56e99a18c67af14da0c9 (diff) | |
Add unistr function
This allows decoding a string with Unicode escape sequences. It is
similar to Unicode escape strings, but offers some more flexibility.
Author: Pavel Stehule <pavel.stehule@gmail.com>
Reviewed-by: Asif Rehman <asifr.rehman@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/CAFj8pRA5GnKT+gDVwbVRH2ep451H_myBt+NTz8RkYUARE9+qOQ@mail.gmail.com
Diffstat (limited to 'src/test')
| -rw-r--r-- | src/test/regress/expected/strings.out | 36 | ||||
| -rw-r--r-- | src/test/regress/sql/strings.sql | 13 |
2 files changed, 49 insertions, 0 deletions
diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out index afd84249c82..91aa8198045 100644 --- a/src/test/regress/expected/strings.out +++ b/src/test/regress/expected/strings.out @@ -2234,3 +2234,39 @@ SELECT bit_count('\x1234567890'::bytea); 15 (1 row) +SELECT unistr('\0064at\+0000610'); + unistr +-------- + data0 +(1 row) + +SELECT unistr('d\u0061t\U000000610'); + unistr +-------- + data0 +(1 row) + +SELECT unistr('a\\b'); + unistr +-------- + a\b +(1 row) + +-- errors: +SELECT unistr('wrong: \db99'); +ERROR: invalid Unicode surrogate pair +SELECT unistr('wrong: \db99\0061'); +ERROR: invalid Unicode surrogate pair +SELECT unistr('wrong: \+00db99\+000061'); +ERROR: invalid Unicode surrogate pair +SELECT unistr('wrong: \+2FFFFF'); +ERROR: invalid Unicode code point: 2FFFFF +SELECT unistr('wrong: \udb99\u0061'); +ERROR: invalid Unicode surrogate pair +SELECT unistr('wrong: \U0000db99\U00000061'); +ERROR: invalid Unicode surrogate pair +SELECT unistr('wrong: \U002FFFFF'); +ERROR: invalid Unicode code point: 2FFFFF +SELECT unistr('wrong: \xyz'); +ERROR: invalid Unicode escape +HINT: Unicode escapes must be \XXXX, \+XXXXXX, \uXXXX, or \UXXXXXXXX. diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql index 9aa1825f921..2c502534c2b 100644 --- a/src/test/regress/sql/strings.sql +++ b/src/test/regress/sql/strings.sql @@ -746,3 +746,16 @@ SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 8) SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 5 for 3),'escape'); SELECT bit_count('\x1234567890'::bytea); + +SELECT unistr('\0064at\+0000610'); +SELECT unistr('d\u0061t\U000000610'); +SELECT unistr('a\\b'); +-- errors: +SELECT unistr('wrong: \db99'); +SELECT unistr('wrong: \db99\0061'); +SELECT unistr('wrong: \+00db99\+000061'); +SELECT unistr('wrong: \+2FFFFF'); +SELECT unistr('wrong: \udb99\u0061'); +SELECT unistr('wrong: \U0000db99\U00000061'); +SELECT unistr('wrong: \U002FFFFF'); +SELECT unistr('wrong: \xyz'); |