Last active
July 14, 2016 17:13
-
-
Save oskarpearson/0c365dd5d25667bf7b1a9094bcded868 to your computer and use it in GitHub Desktop.
Some inconsistencies with detection of email addresses in postgres
This file contains 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
# select version(); | |
version | |
------------------------------------------------------------------------------------------------- | |
PostgreSQL 9.5.3 on x86_64-pc-linux-gnu, compiled by gcc (Ubuntu 4.8.2-19ubuntu1) 4.8.2, 64-bit | |
(1 row) | |
# SELECT email, to_tsvector('simple', email) FROM ( | |
VALUES ('foo@example.com'), ('foo+123@example.com'), | |
('123+foo@example.com'), ('123+123foo@example.com'), | |
('foo123@example.com'), ('foo_123@example.com'), | |
('foo__123@example.com') | |
) as t (email); | |
email | to_tsvector | |
------------------------+-------------------------------------- | |
foo@example.com | 'foo@example.com':1 | |
foo+123@example.com | '+123':2 'example.com':3 'foo':1 | |
123+foo@example.com | '123':1 'foo@example.com':2 | |
123+123foo@example.com | '+123':2 '123':1 'foo@example.com':3 | |
foo123@example.com | 'foo123@example.com':1 | |
foo_123@example.com | 'foo_123@example.com':1 | |
foo__123@example.com | '123':2 'example.com':3 'foo':1 | |
# select ts_debug('foo@example.com'); | |
ts_debug | |
--------------------------------------------------------------------------- | |
(email,"Email address",foo@example.com,{simple},simple,{foo@example.com}) | |
(1 row) | |
# select ts_debug('foo+123@example.com'); | |
ts_debug | |
--------------------------------------------------------------------- | |
(asciiword,"Word, all ASCII",foo,{english_stem},english_stem,{foo}) | |
(int,"Signed integer",+123,{simple},simple,{+123}) | |
(blank,"Space symbols",@,{},,) | |
(host,Host,example.com,{simple},simple,{example.com}) | |
(4 rows) | |
# select ts_debug('123+foo@example.com'); | |
ts_debug | |
--------------------------------------------------------------------------- | |
(uint,"Unsigned integer",123,{simple},simple,{123}) | |
(blank,"Space symbols",+,{},,) | |
(email,"Email address",foo@example.com,{simple},simple,{foo@example.com}) | |
(3 rows) | |
# select ts_debug('123+123foo@example.com'); | |
ts_debug | |
--------------------------------------------------------------------------- | |
(uint,"Unsigned integer",123,{simple},simple,{123}) | |
(int,"Signed integer",+123,{simple},simple,{+123}) | |
(email,"Email address",foo@example.com,{simple},simple,{foo@example.com}) | |
(3 rows) | |
# select ts_debug('foo123@example.com'); | |
ts_debug | |
--------------------------------------------------------------------------------- | |
(email,"Email address",foo123@example.com,{simple},simple,{foo123@example.com}) | |
(1 row) | |
# select ts_debug('foo_123@example.com'); | |
ts_debug | |
----------------------------------------------------------------------------------- | |
(email,"Email address",foo_123@example.com,{simple},simple,{foo_123@example.com}) | |
(1 row) | |
# select ts_debug('foo__123@example.com'); | |
ts_debug | |
--------------------------------------------------------------------- | |
(asciiword,"Word, all ASCII",foo,{english_stem},english_stem,{foo}) | |
(blank,"Space symbols",__,{},,) | |
(uint,"Unsigned integer",123,{simple},simple,{123}) | |
(blank,"Space symbols",@,{},,) | |
(host,Host,example.com,{simple},simple,{example.com}) | |
(5 rows) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment