Merge branch 'develop' into funcs

# Conflicts:
#	src/infi/clickhouse_orm/query.py
#	tests/test_decimal_fields.py
#	tests/test_querysets.py
This commit is contained in:
Itai Shirav 2019-07-13 11:51:10 +03:00
commit 342f06e7b0
38 changed files with 1926 additions and 324 deletions

1073
.noseids Normal file

File diff suppressed because it is too large Load Diff

View File

@ -1,11 +1,31 @@
Change Log
==========
Unreleased
----------
v1.2.0
------
- Add support for per-field compression codecs (rbelio, Chocorean)
- Add support for low cardinality fields (rbelio)
v1.1.0
------
- Add PREWHERE support to querysets (M1hacka)
- Add WITH TOTALS support to querysets (M1hacka)
- Extend date field range (trthhrtz)
- Fix parsing of server errors in ClickHouse v19.3.3+
- Fix pagination when asking for the last page on a query that matches no records
- Use HTTP Basic Authentication instead of passing the credentials in the URL
- Support default/alias/materialized for nullable fields
- Add UUIDField (kpotehin)
- Add `log_statements` parameter to database initializer
- Fix test_merge which fails on ClickHouse v19.8.3
- Fix querysets using the SystemPart model
v1.0.4
------
- Added `timeout` parameter to database initializer (SUHAR1K)
- Added `verify_ssl_cert` parameter to database initializer
- Added `final()` method to querysets (M1hacka)
- Fixed a migrations problem - cannot add a new materialized field after a regular field
v1.0.3
------

View File

@ -49,7 +49,7 @@ eggs = ${project:name}
ipython<6
nose
coverage
enum34
enum-compat
infi.unittest
infi.traceback
memory_profiler

View File

@ -10,7 +10,7 @@ infi.clickhouse_orm.database
Database instances connect to a specific ClickHouse database for running queries,
inserting data and other operations.
#### Database(db_name, db_url="http://localhost:8123/", username=None, password=None, readonly=False, autocreate=True, timeout=60, verify_ssl_cert=True)
#### Database(db_name, db_url="http://localhost:8123/", username=None, password=None, readonly=False, autocreate=True, timeout=60, verify_ssl_cert=True, log_statements=False)
Initializes a database instance. Unless it's readonly, the database will be
@ -24,6 +24,7 @@ created on the ClickHouse server if it does not already exist.
- `autocreate`: automatically create the database if it does not exist (unless in readonly mode).
- `timeout`: the connection timeout in seconds.
- `verify_ssl_cert`: whether to verify the server's certificate when connecting via HTTPS.
- `log_statements`: when True, all database statements are logged.
#### add_setting(name, value)
@ -510,7 +511,7 @@ infi.clickhouse_orm.fields
Extends Field
#### ArrayField(inner_field, default=None, alias=None, materialized=None, readonly=None)
#### ArrayField(inner_field, default=None, alias=None, materialized=None, readonly=None, codec=None)
### BaseEnumField
@ -520,7 +521,7 @@ Extends Field
Abstract base class for all enum-type fields.
#### BaseEnumField(enum_cls, default=None, alias=None, materialized=None, readonly=None)
#### BaseEnumField(enum_cls, default=None, alias=None, materialized=None, readonly=None, codec=None)
### BaseFloatField
@ -530,7 +531,7 @@ Extends Field
Abstract base class for all float-type fields.
#### BaseFloatField(default=None, alias=None, materialized=None, readonly=None)
#### BaseFloatField(default=None, alias=None, materialized=None, readonly=None, codec=None)
### BaseIntField
@ -540,21 +541,21 @@ Extends Field
Abstract base class for all integer-type fields.
#### BaseIntField(default=None, alias=None, materialized=None, readonly=None)
#### BaseIntField(default=None, alias=None, materialized=None, readonly=None, codec=None)
### DateField
Extends Field
#### DateField(default=None, alias=None, materialized=None, readonly=None)
#### DateField(default=None, alias=None, materialized=None, readonly=None, codec=None)
### DateTimeField
Extends Field
#### DateTimeField(default=None, alias=None, materialized=None, readonly=None)
#### DateTimeField(default=None, alias=None, materialized=None, readonly=None, codec=None)
### Decimal128Field
@ -592,14 +593,14 @@ Base class for all decimal fields. Can also be used directly.
Extends BaseEnumField
#### Enum16Field(enum_cls, default=None, alias=None, materialized=None, readonly=None)
#### Enum16Field(enum_cls, default=None, alias=None, materialized=None, readonly=None, codec=None)
### Enum8Field
Extends BaseEnumField
#### Enum8Field(enum_cls, default=None, alias=None, materialized=None, readonly=None)
#### Enum8Field(enum_cls, default=None, alias=None, materialized=None, readonly=None, codec=None)
### Field
@ -607,7 +608,7 @@ Extends BaseEnumField
Abstract base class for all field types.
#### Field(default=None, alias=None, materialized=None, readonly=None)
#### Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### FixedStringField
@ -621,84 +622,98 @@ Extends StringField
Extends BaseFloatField
#### Float32Field(default=None, alias=None, materialized=None, readonly=None)
#### Float32Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### Float64Field
Extends BaseFloatField
#### Float64Field(default=None, alias=None, materialized=None, readonly=None)
#### Float64Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### Int16Field
Extends BaseIntField
#### Int16Field(default=None, alias=None, materialized=None, readonly=None)
#### Int16Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### Int32Field
Extends BaseIntField
#### Int32Field(default=None, alias=None, materialized=None, readonly=None)
#### Int32Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### Int64Field
Extends BaseIntField
#### Int64Field(default=None, alias=None, materialized=None, readonly=None)
#### Int64Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### Int8Field
Extends BaseIntField
#### Int8Field(default=None, alias=None, materialized=None, readonly=None)
#### Int8Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### LowCardinalityField
Extends Field
#### LowCardinalityField(inner_field, default=None, alias=None, materialized=None, readonly=None, codec=None)
### NullableField
Extends Field
#### NullableField(inner_field, default=None, alias=None, materialized=None, extra_null_values=None)
#### NullableField(inner_field, default=None, alias=None, materialized=None, extra_null_values=None, codec=None)
### StringField
Extends Field
#### StringField(default=None, alias=None, materialized=None, readonly=None)
#### StringField(default=None, alias=None, materialized=None, readonly=None, codec=None)
### UInt16Field
Extends BaseIntField
#### UInt16Field(default=None, alias=None, materialized=None, readonly=None)
#### UInt16Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### UInt32Field
Extends BaseIntField
#### UInt32Field(default=None, alias=None, materialized=None, readonly=None)
#### UInt32Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### UInt64Field
Extends BaseIntField
#### UInt64Field(default=None, alias=None, materialized=None, readonly=None)
#### UInt64Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### UInt8Field
Extends BaseIntField
#### UInt8Field(default=None, alias=None, materialized=None, readonly=None)
#### UInt8Field(default=None, alias=None, materialized=None, readonly=None, codec=None)
### UUIDField
Extends Field
#### UUIDField(default=None, alias=None, materialized=None, readonly=None, codec=None)
infi.clickhouse_orm.engines
@ -835,10 +850,10 @@ is equivalent to:
Returns the whole query as a SQL string.
#### conditions_as_sql()
#### conditions_as_sql(prewhere=False)
Returns the contents of the query's `WHERE` clause as a string.
Returns the contents of the query's `WHERE` or `PREWHERE` clause as a string.
#### count()
@ -854,17 +869,18 @@ Adds a DISTINCT clause to the query, meaning that any duplicate rows
in the results will be omitted.
#### exclude(**filter_fields)
#### exclude(*q, **kwargs)
Returns a copy of this queryset that excludes all rows matching the conditions.
Pass `prewhere=True` to apply the conditions as PREWHERE instead of WHERE.
#### filter(*q, **filter_fields)
#### filter(*q, **kwargs)
Returns a copy of this queryset that includes only rows matching the conditions.
Add q object to query if it specified.
Pass `prewhere=True` to apply the conditions as PREWHERE instead of WHERE.
#### final()
@ -908,6 +924,12 @@ The result is a namedtuple containing `objects` (list), `number_of_objects`,
`pages_total`, `number` (of the current page), and `page_size`.
#### select_fields_as_sql()
Returns the selected fields or expressions as a SQL string.
### AggregateQuerySet
Extends QuerySet
@ -943,10 +965,10 @@ This method is not supported on `AggregateQuerySet`.
Returns the whole query as a SQL string.
#### conditions_as_sql()
#### conditions_as_sql(prewhere=False)
Returns the contents of the query's `WHERE` clause as a string.
Returns the contents of the query's `WHERE` or `PREWHERE` clause as a string.
#### count()
@ -962,17 +984,18 @@ Adds a DISTINCT clause to the query, meaning that any duplicate rows
in the results will be omitted.
#### exclude(**filter_fields)
#### exclude(*q, **kwargs)
Returns a copy of this queryset that excludes all rows matching the conditions.
Pass `prewhere=True` to apply the conditions as PREWHERE instead of WHERE.
#### filter(*q, **filter_fields)
#### filter(*q, **kwargs)
Returns a copy of this queryset that includes only rows matching the conditions.
Add q object to query if it specified.
Pass `prewhere=True` to apply the conditions as PREWHERE instead of WHERE.
#### final()
@ -1022,3 +1045,17 @@ The result is a namedtuple containing `objects` (list), `number_of_objects`,
`pages_total`, `number` (of the current page), and `page_size`.
#### select_fields_as_sql()
Returns the selected fields or expressions as a SQL string.
#### with_totals()
Adds WITH TOTALS modifier ot GROUP BY, making query return extra row
with aggregate function calculated across all the rows. More information:
https://clickhouse.yandex/docs/en/query_language/select/#with-totals-modifier

View File

@ -9,7 +9,7 @@ Currently the following field types are supported:
| ------------------ | ---------- | ------------------- | -----------------------------------------------------
| StringField | String | unicode | Encoded as UTF-8 when written to ClickHouse
| FixedStringField | String | unicode | Encoded as UTF-8 when written to ClickHouse
| DateField | Date | datetime.date | Range 1970-01-01 to 2038-01-19
| DateField | Date | datetime.date | Range 1970-01-01 to 2105-12-31
| DateTimeField | DateTime | datetime.datetime | Minimal value is 1970-01-01 00:00:00; Always in UTC
| Int8Field | Int8 | int | Range -128 to 127
| Int16Field | Int16 | int | Range -32768 to 32767
@ -25,6 +25,7 @@ Currently the following field types are supported:
| Decimal32Field | Decimal32 | Decimal | Ditto
| Decimal64Field | Decimal64 | Decimal | Ditto
| Decimal128Field | Decimal128 | Decimal | Ditto
| UUIDField | UUID | Decimal |
| Enum8Field | Enum8 | Enum | See below
| Enum16Field | Enum16 | Enum | See below
| ArrayField | Array | list | See below
@ -120,8 +121,7 @@ db.select('SELECT * FROM $db.event', model_class=Event)
Working with nullable fields
----------------------------
From [some time](https://github.com/yandex/ClickHouse/pull/70) ClickHouse provides a NULL value support.
Also see some information [here](https://github.com/yandex/ClickHouse/blob/master/dbms/tests/queries/0_stateless/00395_nullable.sql).
[ClickHouse provides a NULL value support](https://clickhouse.yandex/docs/en/data_types/nullable).
Wrapping another field in a `NullableField` makes it possible to assign `None` to that field. For example:
@ -147,6 +147,79 @@ to `None`.
NOTE: `ArrayField` of `NullableField` is not supported. Also `EnumField` cannot be nullable.
NOTE: Using `Nullable` almost always negatively affects performance, keep this in mind when designing your databases.
Working with field compression codecs
-------------------------------------
Besides default data compression, defined in server settings, per-field specification is also available.
Supported compression algorithms:
| Codec | Argument | Comment
| -------------------- | -------------------------------------------| ----------------------------------------------------
| NONE | None | No compression.
| LZ4 | None | LZ4 compression.
| LZ4HC(`level`) | Possible `level` range: [3, 12]. | Default value: 9. Greater values stands for better compression and higher CPU usage. Recommended value range: [4,9].
| ZSTD(`level`) | Possible `level`range: [1, 22]. | Default value: 1. Greater values stands for better compression and higher CPU usage. Levels >= 20, should be used with caution, as they require more memory.
| Delta(`delta_bytes`) | Possible `delta_bytes` range: 1, 2, 4 , 8. | Default value for `delta_bytes` is `sizeof(type)` if it is equal to 1, 2,4 or 8 and equals to 1 otherwise.
Codecs can be combined in a pipeline. Default table codec is not included into pipeline (if it should be applied to a field, you have to specify it explicitly in pipeline).
Recommended usage for codecs:
- Usually, values for particular metric, stored in path does not differ significantly from point to point. Using delta-encoding allows to reduce disk space usage significantly.
- DateTime works great with pipeline of Delta, ZSTD and the column size can be compressed to 2-3% of its original size (given a smooth datetime data)
- Numeric types usually enjoy best compression rates with ZSTD
- String types enjoy good compression rates with LZ4HC
Usage:
```python
class Stats(models.Model):
id = fields.UInt64Field(codec='ZSTD(10)')
timestamp = fields.DateTimeField(codec='Delta,ZSTD')
timestamp_date = fields.DateField(codec='Delta(4),ZSTD(22)')
metadata_id = fields.Int64Field(codec='LZ4')
status = fields.StringField(codec='LZ4HC(10)')
calculation = fields.NullableField(fields.Float32Field(), codec='ZSTD')
alerts = fields.ArrayField(fields.FixedStringField(length=15), codec='Delta(2),LZ4HC')
engine = MergeTree('timestamp_date', ('id', 'timestamp'))
```
Note: This feature is supported on ClickHouse version 19.1.16 and above. Codec arguments will be ignored by the ORM for older versions of ClickHouse.
Working with LowCardinality fields
----------------------------------
Starting with version 19.0 ClickHouse offers a new type of field to improve the performance of queries
and compaction of columns for low entropy data.
[More specifically](https://github.com/yandex/ClickHouse/issues/4074) LowCardinality data type builds dictionaries automatically. It can use multiple different dictionaries if necessarily.
If the number of distinct values is pretty large, the dictionaries become local, several different dictionaries will be used for different ranges of data. For example, if you have too many distinct values in total, but only less than about a million values each day - then the queries by day will be processed efficiently, and queries for larger ranges will be processed rather efficiently.
LowCardinality works independently of (generic) fields compression.
LowCardinality fields are subsequently compressed as usual.
The compression ratios of LowCardinality fields for text data may be significantly better than without LowCardinality.
LowCardinality will give performance boost, in the form of processing speed, if the number of distinct values is less than a few millions. This is because data is processed in dictionary encoded form.
You can find further information about LowCardinality in [this presentation](https://github.com/yandex/clickhouse-presentations/blob/master/meetup19/string_optimization.pdf).
Usage example:
```python
class LowCardinalityModel(models.Model):
date = fields.DateField()
int32 = fields.LowCardinalityField(fields.Int32Field())
float32 = fields.LowCardinalityField(fields.Float32Field())
string = fields.LowCardinalityField(fields.StringField())
nullable = fields.LowCardinalityField(fields.NullableField(fields.StringField()))
array = fields.ArrayField(fields.LowCardinalityField(fields.UInt64Field()))
engine = MergeTree('date', ('date',))
```
Note: `LowCardinality` field with an inner array field is not supported. Use an `ArrayField` with a `LowCardinality` inner field as seen in the example.
Creating custom field types
---------------------------
Sometimes it is convenient to use data types that are supported in Python, but have no corresponding column type in ClickHouse. In these cases it is possible to define a custom field class that knows how to convert the Pythonic object to a suitable representation in the database, and vice versa.
@ -183,46 +256,6 @@ class BooleanField(Field):
return '1' if value else '0'
```
Here's another example - a field for storing UUIDs in the database as 16-byte strings. We'll use Python's built-in `UUID` class to handle the conversion from strings, ints and tuples into UUID instances. So in our Python code we'll have the convenience of working with UUID objects, but they will be stored in the database as efficiently as possible:
```python
from infi.clickhouse_orm.fields import Field
from infi.clickhouse_orm.utils import escape
from uuid import UUID
import six
class UUIDField(Field):
# The ClickHouse column type to use
db_type = 'FixedString(16)'
# The default value if empty
class_default = UUID(int=0)
def to_python(self, value, timezone_in_use):
# Convert valid values to UUID instance
if isinstance(value, UUID):
return value
elif isinstance(value, six.string_types):
return UUID(bytes=value.encode('latin1')) if len(value) == 16 else UUID(value)
elif isinstance(value, six.integer_types):
return UUID(int=value)
elif isinstance(value, tuple):
return UUID(fields=value)
else:
raise ValueError('Invalid value for UUIDField: %r' % value)
def to_db_string(self, value, quote=True):
# The value was already converted by to_python, so it's a UUID instance
val = value.bytes
if six.PY3:
val = str(val, 'latin1')
return escape(val, quote)
```
Note that the latin-1 encoding is used as an identity encoding for converting between raw bytes and strings. This is required in Python 3, where `str` and `bytes` are different types.
---
[<< Querysets](querysets.md) | [Table of Contents](toc.md) | [Table Engines >>](table_engines.md)

View File

@ -89,7 +89,7 @@ When values are assigned to model fields, they are immediately converted to thei
>>> suzy.birthday = 0.5
ValueError: Invalid value for DateField - 0.5
>>> suzy.birthday = '1922-05-31'
ValueError: DateField out of range - 1922-05-31 is not between 1970-01-01 and 2038-01-19
ValueError: DateField out of range - 1922-05-31 is not between 1970-01-01 and 2105-12-31
Inserting to the Database
-------------------------

View File

@ -32,6 +32,14 @@ For filters with compound conditions you can use `Q` objects inside `filter` wit
>>> qs.conditions_as_sql()
u"((first_name = 'Ciaran' AND last_name = 'Carver') OR height <= 1.8) AND (NOT (first_name = 'David'))"
By default conditions from `filter` and `exclude` methods are add to `WHERE` clause.
For better aggregation performance you can add them to `PREWHERE` section using `prewhere=True` parameter
>>> qs = Person.objects_in(database)
>>> qs = qs.filter(first_name__startswith='V', prewhere=True)
>>> qs.conditions_as_sql(prewhere=True)
u"first_name LIKE 'V%'"
There are different operators that can be used, by passing `<fieldname>__<operator>=<value>` (two underscores separate the field name from the operator). In case no operator is given, `eq` is used by default. Below are all the supported operators.
| Operator | Equivalent SQL | Comments |
@ -202,6 +210,19 @@ This queryset is translated to:
After calling `aggregate` you can still use most of the regular queryset methods, such as `count`, `order_by` and `paginate`. It is not possible, however, to call `only` or `aggregate`. It is also not possible to filter the queryset on calculated fields, only on fields that exist in the model.
If you limit aggregation results, it might be useful to get total aggregation values for all rows.
To achieve this, you can use `with_totals` method. It will return extra row (last) with
values aggregated for all rows suitable for filters.
qs = Person.objects_in(database).aggregate('first_name', num='count()').with_totals().order_by('-count')[:3]
>>> print qs.count()
4
>>> for row in qs:
>>> print("'{}': {}".format(row.first_name, row.count))
'Cassandra': 2
'Alexandra': 2
'': 100
---
[<< Models and Databases](models_and_databases.md) | [Table of Contents](toc.md) | [Field Types >>](field_types.md)

View File

@ -482,9 +482,9 @@ infi.clickhouse_orm.query
#### QuerySet(model_cls, database)
#### conditions_as_sql()
#### conditions_as_sql(prewhere=True)
Return the contents of the queryset's WHERE clause.
Return the contents of the queryset's WHERE or `PREWHERE` clause.
#### count()

View File

@ -36,6 +36,8 @@
* [Working with array fields](field_types.md#working-with-array-fields)
* [Working with materialized and alias fields](field_types.md#working-with-materialized-and-alias-fields)
* [Working with nullable fields](field_types.md#working-with-nullable-fields)
* [Working with field compression codecs](field_types.md#working-with-field-compression-codecs)
* [Working with LowCardinality fields](field_types.md#working-with-lowcardinality-fields)
* [Creating custom field types](field_types.md#creating-custom-field-types)
* [Table Engines](table_engines.md#table-engines)
@ -86,12 +88,14 @@
* [Int32Field](class_reference.md#int32field)
* [Int64Field](class_reference.md#int64field)
* [Int8Field](class_reference.md#int8field)
* [LowCardinalityField](class_reference.md#lowcardinalityfield)
* [NullableField](class_reference.md#nullablefield)
* [StringField](class_reference.md#stringfield)
* [UInt16Field](class_reference.md#uint16field)
* [UInt32Field](class_reference.md#uint32field)
* [UInt64Field](class_reference.md#uint64field)
* [UInt8Field](class_reference.md#uint8field)
* [UUIDField](class_reference.md#uuidfield)
* [infi.clickhouse_orm.engines](class_reference.md#infi.clickhouse_orm.engines)
* [Engine](class_reference.md#engine)
* [TinyLog](class_reference.md#tinylog)

View File

@ -40,11 +40,19 @@ class ServerError(DatabaseException):
self.message = message
super(ServerError, self).__init__(message)
ERROR_PATTERN = re.compile(r'''
Code:\ (?P<code>\d+),
\ e\.displayText\(\)\ =\ (?P<type1>[^ \n]+):\ (?P<msg>.+?),
\ e.what\(\)\ =\ (?P<type2>[^ \n]+)
''', re.VERBOSE | re.DOTALL)
ERROR_PATTERNS = (
# ClickHouse prior to v19.3.3
re.compile(r'''
Code:\ (?P<code>\d+),
\ e\.displayText\(\)\ =\ (?P<type1>[^ \n]+):\ (?P<msg>.+?),
\ e.what\(\)\ =\ (?P<type2>[^ \n]+)
''', re.VERBOSE | re.DOTALL),
# ClickHouse v19.3.3+
re.compile(r'''
Code:\ (?P<code>\d+),
\ e\.displayText\(\)\ =\ (?P<type1>[^ \n]+):\ (?P<msg>.+)
''', re.VERBOSE | re.DOTALL),
)
@classmethod
def get_error_code_msg(cls, full_error_message):
@ -54,10 +62,11 @@ class ServerError(DatabaseException):
See the list of error codes here:
https://github.com/yandex/ClickHouse/blob/master/dbms/src/Common/ErrorCodes.cpp
"""
match = cls.ERROR_PATTERN.match(full_error_message)
if match:
# assert match.group('type1') == match.group('type2')
return int(match.group('code')), match.group('msg')
for pattern in cls.ERROR_PATTERNS:
match = pattern.match(full_error_message)
if match:
# assert match.group('type1') == match.group('type2')
return int(match.group('code')), match.group('msg').strip()
return 0, full_error_message
@ -74,7 +83,7 @@ class Database(object):
def __init__(self, db_name, db_url='http://localhost:8123/',
username=None, password=None, readonly=False, autocreate=True,
timeout=60, verify_ssl_cert=True):
timeout=60, verify_ssl_cert=True, log_statements=False):
'''
Initializes a database instance. Unless it's readonly, the database will be
created on the ClickHouse server if it does not already exist.
@ -87,15 +96,17 @@ class Database(object):
- `autocreate`: automatically create the database if it does not exist (unless in readonly mode).
- `timeout`: the connection timeout in seconds.
- `verify_ssl_cert`: whether to verify the server's certificate when connecting via HTTPS.
- `log_statements`: when True, all database statements are logged.
'''
self.db_name = db_name
self.db_url = db_url
self.username = username
self.password = password
self.readonly = False
self.timeout = timeout
self.request_session = requests.Session()
self.request_session.verify = verify_ssl_cert
if username:
self.request_session.auth = (username, password or '')
self.log_statements = log_statements
self.settings = {}
self.db_exists = False # this is required before running _is_existing_database
self.db_exists = self._is_existing_database()
@ -109,6 +120,10 @@ class Database(object):
self.server_version = self._get_server_version()
# Versions 1.1.53981 and below don't have timezone function
self.server_timezone = self._get_server_timezone() if self.server_version > (1, 1, 53981) else pytz.utc
# Versions 19.1.16 and above support codec compression
self.has_codec_support = self.server_version >= (19, 1, 16)
# Version 19.0 and above support LowCardinality
self.has_low_cardinality_support = self.server_version >= (19, 0)
def create_database(self):
'''
@ -276,7 +291,7 @@ class Database(object):
count = self.count(model_class, conditions)
pages_total = int(ceil(count / float(page_size)))
if page_num == -1:
page_num = pages_total
page_num = max(pages_total, 1)
elif page_num < 1:
raise ValueError('Invalid page number: %d' % page_num)
offset = (page_num - 1) * page_size
@ -287,7 +302,7 @@ class Database(object):
query += ' LIMIT %d, %d' % (offset, page_size)
query = self._substitute(query, model_class)
return Page(
objects=list(self.select(query, model_class, settings)),
objects=list(self.select(query, model_class, settings)) if count else [],
number_of_objects=count,
pages_total=pages_total,
number=page_num,
@ -325,6 +340,8 @@ class Database(object):
def _send(self, data, settings=None, stream=False):
if isinstance(data, string_types):
data = data.encode('utf-8')
if self.log_statements:
logger.info(data)
params = self._build_params(settings)
r = self.request_session.post(self.db_url, params=params, data=data, stream=stream, timeout=self.timeout)
if r.status_code != 200:
@ -336,10 +353,6 @@ class Database(object):
params.update(self.settings)
if self.db_exists:
params['database'] = self.db_name
if self.username:
params['user'] = self.username
if self.password:
params['password'] = self.password
# Send the readonly flag, unless the connection is already readonly (to prevent db error)
if self.readonly and not self.connection_readonly:
params['readonly'] = '1'
@ -352,7 +365,10 @@ class Database(object):
if '$' in query:
mapping = dict(db="`%s`" % self.db_name)
if model_class:
mapping['table'] = "`%s`.`%s`" % (self.db_name, model_class.table_name())
if model_class.is_system_model():
mapping['table'] = model_class.table_name()
else:
mapping['table'] = "`%s`.`%s`" % (self.db_name, model_class.table_name())
query = Template(query).safe_substitute(mapping)
return query

View File

@ -40,7 +40,7 @@ class MergeTree(Engine):
assert date_col is None or isinstance(date_col, six.string_types), 'date_col must be string if present'
assert partition_key is None or type(partition_key) in (list, tuple),\
'partition_key must be tuple or list if present'
assert (replica_table_path is None) == (replica_name == None), \
assert (replica_table_path is None) == (replica_name is None), \
'both replica_table_path and replica_name must be specified'
# These values conflict with each other (old and new syntax of table engines.

View File

@ -1,15 +1,16 @@
from __future__ import unicode_literals
from six import string_types, text_type, binary_type
from six import string_types, text_type, binary_type, integer_types
import datetime
import iso8601
import pytz
import time
from calendar import timegm
from decimal import Decimal, localcontext
from uuid import UUID
from logging import getLogger
from .utils import escape, parse_array, comma_join
from .funcs import F, FunctionOperatorsMixin
logger = getLogger('clickhouse_orm')
class Field(FunctionOperatorsMixin):
'''
@ -21,14 +22,16 @@ class Field(FunctionOperatorsMixin):
class_default = 0 # should be overridden by concrete subclasses
db_type = None # should be overridden by concrete subclasses
def __init__(self, default=None, alias=None, materialized=None, readonly=None):
def __init__(self, default=None, alias=None, materialized=None, readonly=None, codec=None):
assert (None, None) in {(default, alias), (alias, materialized), (default, materialized)}, \
"Only one of default, alias and materialized parameters can be given"
assert alias is None or isinstance(alias, string_types) and alias != "",\
"Alias field must be string field name, if given"
assert materialized is None or isinstance(materialized, string_types) and alias != "",\
"Alias field must be a string, if given"
assert materialized is None or isinstance(materialized, string_types) and materialized != "",\
"Materialized field must be string, if given"
assert readonly is None or type(readonly) is bool, "readonly parameter must be bool if given"
assert codec is None or isinstance(codec, string_types) and codec != "", \
"Codec field must be string, if given"
self.creation_counter = Field.creation_counter
Field.creation_counter += 1
@ -36,6 +39,7 @@ class Field(FunctionOperatorsMixin):
self.alias = alias
self.materialized = materialized
self.readonly = bool(self.alias or self.materialized or readonly)
self.codec = codec
def to_python(self, value, timezone_in_use):
'''
@ -66,22 +70,30 @@ class Field(FunctionOperatorsMixin):
'''
return escape(value, quote)
def get_sql(self, with_default_expression=True):
def get_sql(self, with_default_expression=True, db=None):
'''
Returns an SQL expression describing the field (e.g. for CREATE TABLE).
:param with_default_expression: If True, adds default value to sql.
It doesn't affect fields with alias and materialized values.
:param db: Database, used for checking supported features.
'''
sql = self.db_type
if with_default_expression:
if self.alias:
return '%s ALIAS %s' % (self.db_type, self.alias)
elif self.materialized:
return '%s MATERIALIZED %s' % (self.db_type, self.materialized)
else:
default = self.to_db_string(self.default)
return '%s DEFAULT %s' % (self.db_type, default)
else:
return self.db_type
sql += self._extra_params(db)
return sql
def _extra_params(self, db):
sql = ''
if self.alias:
sql += ' ALIAS %s' % self.alias
elif self.materialized:
sql += ' MATERIALIZED %s' % self.materialized
elif self.default:
default = self.to_db_string(self.default)
sql += ' DEFAULT %s' % default
if self.codec and db and db.has_codec_support:
sql += ' CODEC(%s)' % self.codec
return sql
def isinstance(self, types):
"""
@ -154,7 +166,7 @@ class FixedStringField(StringField):
class DateField(Field):
min_value = datetime.date(1970, 1, 1)
max_value = datetime.date(2038, 1, 19)
max_value = datetime.date(2105, 12, 31)
class_default = min_value
db_type = 'Date'
@ -383,11 +395,11 @@ class BaseEnumField(Field):
Abstract base class for all enum-type fields.
'''
def __init__(self, enum_cls, default=None, alias=None, materialized=None, readonly=None):
def __init__(self, enum_cls, default=None, alias=None, materialized=None, readonly=None, codec=None):
self.enum_cls = enum_cls
if default is None:
default = list(enum_cls)[0]
super(BaseEnumField, self).__init__(default, alias, materialized, readonly)
super(BaseEnumField, self).__init__(default, alias, materialized, readonly, codec)
def to_python(self, value, timezone_in_use):
if isinstance(value, self.enum_cls):
@ -406,12 +418,14 @@ class BaseEnumField(Field):
def to_db_string(self, value, quote=True):
return escape(value.name, quote)
def get_sql(self, with_default_expression=True):
def get_sql(self, with_default_expression=True, db=None):
values = ['%s = %d' % (escape(item.name), item.value) for item in self.enum_cls]
sql = '%s(%s)' % (self.db_type, ' ,'.join(values))
if with_default_expression:
default = self.to_db_string(self.default)
sql = '%s DEFAULT %s' % (sql, default)
if self.codec and db and db.has_codec_support:
sql+= ' CODEC(%s)' % self.codec
return sql
@classmethod
@ -421,10 +435,7 @@ class BaseEnumField(Field):
this method returns a matching enum field.
'''
import re
try:
Enum # exists in Python 3.4+
except NameError:
from enum import Enum # use the enum34 library instead
from enum import Enum
members = {}
for match in re.finditer("'(\w+)' = (\d+)", db_type):
members[match.group(1)] = int(match.group(2))
@ -447,11 +458,11 @@ class ArrayField(Field):
class_default = []
def __init__(self, inner_field, default=None, alias=None, materialized=None, readonly=None):
def __init__(self, inner_field, default=None, alias=None, materialized=None, readonly=None, codec=None):
assert isinstance(inner_field, Field), "The first argument of ArrayField must be a Field instance"
assert not isinstance(inner_field, ArrayField), "Multidimensional array fields are not supported by the ORM"
self.inner_field = inner_field
super(ArrayField, self).__init__(default, alias, materialized, readonly)
super(ArrayField, self).__init__(default, alias, materialized, readonly, codec)
def to_python(self, value, timezone_in_use):
if isinstance(value, text_type):
@ -470,9 +481,34 @@ class ArrayField(Field):
array = [self.inner_field.to_db_string(v, quote=True) for v in value]
return '[' + comma_join(array) + ']'
def get_sql(self, with_default_expression=True):
from .utils import escape
return 'Array(%s)' % self.inner_field.get_sql(with_default_expression=False)
def get_sql(self, with_default_expression=True, db=None):
sql = 'Array(%s)' % self.inner_field.get_sql(with_default_expression=False, db=db)
if with_default_expression and self.codec and db and db.has_codec_support:
sql+= ' CODEC(%s)' % self.codec
return sql
class UUIDField(Field):
class_default = UUID(int=0)
db_type = 'UUID'
def to_python(self, value, timezone_in_use):
if isinstance(value, UUID):
return value
elif isinstance(value, binary_type):
return UUID(bytes=value)
elif isinstance(value, string_types):
return UUID(value)
elif isinstance(value, integer_types):
return UUID(int=value)
elif isinstance(value, tuple):
return UUID(fields=value)
else:
raise ValueError('Invalid value for UUIDField: %r' % value)
def to_db_string(self, value, quote=True):
return escape(str(value), quote)
class NullableField(Field):
@ -480,12 +516,12 @@ class NullableField(Field):
class_default = None
def __init__(self, inner_field, default=None, alias=None, materialized=None,
extra_null_values=None):
extra_null_values=None, codec=None):
self.inner_field = inner_field
self._null_values = [None]
if extra_null_values:
self._null_values.extend(extra_null_values)
super(NullableField, self).__init__(default, alias, materialized, readonly=None)
super(NullableField, self).__init__(default, alias, materialized, readonly=None, codec=codec)
def to_python(self, value, timezone_in_use):
if value == '\\N' or value in self._null_values:
@ -500,5 +536,38 @@ class NullableField(Field):
return '\\N'
return self.inner_field.to_db_string(value, quote=quote)
def get_sql(self, with_default_expression=True):
return 'Nullable(%s)' % self.inner_field.get_sql(with_default_expression=False)
def get_sql(self, with_default_expression=True, db=None):
sql = 'Nullable(%s)' % self.inner_field.get_sql(with_default_expression=False, db=db)
if with_default_expression:
sql += self._extra_params(db)
return sql
class LowCardinalityField(Field):
def __init__(self, inner_field, default=None, alias=None, materialized=None, readonly=None, codec=None):
assert isinstance(inner_field, Field), "The first argument of LowCardinalityField must be a Field instance. Not: {}".format(inner_field)
assert not isinstance(inner_field, LowCardinalityField), "LowCardinality inner fields are not supported by the ORM"
assert not isinstance(inner_field, ArrayField), "Array field inside LowCardinality are not supported by the ORM. Use Array(LowCardinality) instead"
self.inner_field = inner_field
self.class_default = self.inner_field.class_default
super(LowCardinalityField, self).__init__(default, alias, materialized, readonly, codec)
def to_python(self, value, timezone_in_use):
return self.inner_field.to_python(value, timezone_in_use)
def validate(self, value):
self.inner_field.validate(value)
def to_db_string(self, value, quote=True):
return self.inner_field.to_db_string(value, quote=quote)
def get_sql(self, with_default_expression=True, db=None):
if db and db.has_low_cardinality_support:
sql = 'LowCardinality(%s)' % self.inner_field.get_sql(with_default_expression=False)
else:
sql = self.inner_field.get_sql(with_default_expression=False)
logger.warning('LowCardinalityField not supported on clickhouse-server version < 19.0 using {} as fallback'.format(self.inner_field.__class__.__name__))
if with_default_expression:
sql += self._extra_params(db)
return sql

View File

@ -75,13 +75,16 @@ class AlterTable(Operation):
# Identify fields that were added to the model
prev_name = None
for name, field in iteritems(self.model_class.fields()):
is_regular_field = not (field.materialized or field.alias)
if name not in table_fields:
logger.info(' Add column %s', name)
assert prev_name, 'Cannot add a column to the beginning of the table'
cmd = 'ADD COLUMN %s %s AFTER %s' % (name, field.get_sql(), prev_name)
cmd = 'ADD COLUMN %s %s' % (name, field.get_sql(db=database))
if is_regular_field:
cmd += ' AFTER %s' % prev_name
self._alter_table(database, cmd)
if not field.materialized and not field.alias:
if is_regular_field:
# ALIAS and MATERIALIZED fields are not stored in the database, and raise DatabaseError
# (no AFTER column). So we will skip them
prev_name = name
@ -90,7 +93,7 @@ class AlterTable(Operation):
# The order of class attributes can be changed any time, so we can't count on it
# Secondly, MATERIALIZED and ALIAS fields are always at the end of the DESC, so we can't expect them to save
# attribute position. Watch https://github.com/Infinidat/infi.clickhouse_orm/issues/47
model_fields = {name: field.get_sql(with_default_expression=False)
model_fields = {name: field.get_sql(with_default_expression=False, db=database)
for name, field in iteritems(self.model_class.fields())}
for field_name, field_sql in self._get_table_fields(database):
# All fields must have been created and dropped by this moment

View File

@ -197,7 +197,7 @@ class Model(with_metaclass(ModelBase)):
parts = ['CREATE TABLE IF NOT EXISTS `%s`.`%s` (' % (db.db_name, cls.table_name())]
cols = []
for name, field in iteritems(cls.fields()):
cols.append(' %s %s' % (name, field.get_sql()))
cols.append(' %s %s' % (name, field.get_sql(db=db)))
parts.append(',\n'.join(cols))
parts.append(')')
parts.append('ENGINE = ' + cls.engine.create_table_sql(db))
@ -318,9 +318,16 @@ class MergeModel(Model):
@classmethod
def create_table_sql(cls, db):
assert isinstance(cls.engine, Merge), "engine must be engines.Merge instance"
return super(MergeModel, cls).create_table_sql(db)
assert isinstance(cls.engine, Merge), "engine must be an instance of engines.Merge"
parts = ['CREATE TABLE IF NOT EXISTS `%s`.`%s` (' % (db.db_name, cls.table_name())]
cols = []
for name, field in iteritems(cls.fields()):
if name != '_table':
cols.append(' %s %s' % (name, field.get_sql(db=db)))
parts.append(',\n'.join(cols))
parts.append(')')
parts.append('ENGINE = ' + cls.engine.create_table_sql(db))
return '\n'.join(parts)
# TODO: base class for models that require specific engine
@ -331,7 +338,7 @@ class DistributedModel(Model):
"""
def set_database(self, db):
assert isinstance(self.engine, Distributed), "engine must be engines.Distributed instance"
assert isinstance(self.engine, Distributed), "engine must be an instance of engines.Distributed"
res = super(DistributedModel, self).set_database(db)
return res

View File

@ -2,7 +2,7 @@ from __future__ import unicode_literals
import six
import pytz
from copy import copy
from copy import copy, deepcopy
from math import ceil
from .engines import CollapsingMergeTree
from datetime import date, datetime
@ -185,25 +185,45 @@ class FieldCond(Cond):
def to_sql(self, model_cls):
return self._operator.to_sql(model_cls, self._field_name, self._value)
def __deepcopy__(self, memodict={}):
res = copy(self)
res._value = deepcopy(self._value)
return res
class Q(object):
AND_MODE = ' AND '
OR_MODE = ' OR '
AND_MODE = 'AND'
OR_MODE = 'OR'
def __init__(self, *filter_funcs, **filter_fields):
self._conds = list(filter_funcs) + [self._build_cond(k, v) for k, v in six.iteritems(filter_fields)]
self._l_child = None
self._r_child = None
self._children = []
self._negate = False
self._mode = self.AND_MODE
@property
def is_empty(self):
"""
Checks if there are any conditions in Q object
:return: Boolean
"""
return not bool(self._conds or self._children)
@classmethod
def _construct_from(cls, l_child, r_child, mode):
q = Q()
q._l_child = l_child
q._r_child = r_child
q._mode = mode # AND/OR
if mode == l_child._mode:
q = deepcopy(l_child)
q._children.append(deepcopy(r_child))
elif mode == r_child._mode:
q = deepcopy(r_child)
q._children.append(deepcopy(l_child))
else:
# Different modes
q = Q()
q._children = [l_child, r_child]
q._mode = mode # AND/OR
return q
def _build_cond(self, key, value):
@ -214,16 +234,27 @@ class Q(object):
return FieldCond(field_name, operator, value)
def to_sql(self, model_cls):
condition_sql = []
if self._conds:
sql = self._mode.join(cond.to_sql(model_cls) for cond in self._conds)
condition_sql.extend([cond.to_sql(model_cls) for cond in self._conds])
if self._children:
condition_sql.extend([child.to_sql(model_cls) for child in self._children if child])
if not condition_sql:
# Empty Q() object returns everything
sql = '1'
elif len(condition_sql) == 1:
# Skip not needed brackets over single condition
sql = condition_sql[0]
else:
if self._l_child and self._r_child:
sql = '({} {} {})'.format(
self._l_child.to_sql(model_cls), self._mode, self._r_child.to_sql(model_cls))
else:
return '1'
# Each condition must be enclosed in brackets, or order of operations may be wrong
sql = '(%s)' % ') {} ('.format(self._mode).join(condition_sql)
if self._negate:
sql = 'NOT (%s)' % sql
return sql
def __or__(self, other):
@ -237,6 +268,20 @@ class Q(object):
q._negate = True
return q
def __bool__(self):
return not self.is_empty
def __deepcopy__(self, memodict={}):
q = Q()
q._conds = [deepcopy(cond) for cond in self._conds]
q._negate = self._negate
q._mode = self._mode
if self._children:
q._children = [deepcopy(child) for child in self._children]
return q
@six.python_2_unicode_compatible
class QuerySet(object):
@ -254,7 +299,10 @@ class QuerySet(object):
self._model_cls = model_cls
self._database = database
self._order_by = []
self._q = []
self._where_q = Q()
self._prewhere_q = Q()
self._grouping_fields = []
self._grouping_with_totals = False
self._fields = model_cls.fields().keys()
self._extra = {}
self._limits = None
@ -297,22 +345,49 @@ class QuerySet(object):
qs._limits = (start, stop - start)
return qs
def as_sql(self):
def select_fields_as_sql(self):
"""
Returns the whole query as a SQL string.
Returns the selected fields or expressions as a SQL string.
"""
distinct = 'DISTINCT ' if self._distinct else ''
fields = '*'
if self._fields:
fields = comma_join('`%s`' % field for field in self._fields)
for name, func in self._extra.items():
fields += ', %s AS %s' % (func.to_sql(), name)
ordering = '\nORDER BY ' + self.order_by_as_sql() if self._order_by else ''
limit = '\nLIMIT %d, %d' % self._limits if self._limits else ''
return fields
def as_sql(self):
"""
Returns the whole query as a SQL string.
"""
distinct = 'DISTINCT ' if self._distinct else ''
final = ' FINAL' if self._final else ''
params = (distinct, fields, self._model_cls.table_name(), final,
self.conditions_as_sql(), ordering, limit)
return u'SELECT %s%s\nFROM `%s`%s\nWHERE %s%s%s' % params
table_name = self._model_cls.table_name()
if not self._model_cls.is_system_model():
table_name = '`%s`' % table_name
params = (distinct, self.select_fields_as_sql(), table_name, final)
sql = u'SELECT %s%s\nFROM %s%s' % params
if self._prewhere_q and not self._prewhere_q.is_empty:
sql += '\nPREWHERE ' + self.conditions_as_sql(prewhere=True)
if self._where_q and not self._where_q.is_empty:
sql += '\nWHERE ' + self.conditions_as_sql(prewhere=False)
if self._grouping_fields:
sql += '\nGROUP BY %s' % comma_join('`%s`' % field for field in self._grouping_fields)
if self._grouping_with_totals:
sql += ' WITH TOTALS'
if self._order_by:
sql += '\nORDER BY ' + self.order_by_as_sql()
if self._limits:
sql += '\nLIMIT %d, %d' % self._limits
return sql
def order_by_as_sql(self):
"""
@ -323,14 +398,12 @@ class QuerySet(object):
for field in self._order_by
])
def conditions_as_sql(self):
def conditions_as_sql(self, prewhere=False):
"""
Returns the contents of the query's `WHERE` clause as a string.
Returns the contents of the query's `WHERE` or `PREWHERE` clause as a string.
"""
if self._q:
return u' AND '.join([q.to_sql(self._model_cls) for q in self._q])
else:
return u'1'
q_object = self._prewhere_q if prewhere else self._where_q
return q_object.to_sql(self._model_cls)
def count(self):
"""
@ -341,8 +414,10 @@ class QuerySet(object):
sql = u'SELECT count() FROM (%s)' % self.as_sql()
raw = self._database.raw(sql)
return int(raw) if raw else 0
# Simple case
return self._database.count(self._model_cls, self.conditions_as_sql())
conditions = (self._where_q & self._prewhere_q).to_sql(self._model_cls)
return self._database.count(self._model_cls, conditions)
def order_by(self, *field_names):
"""
@ -367,32 +442,50 @@ class QuerySet(object):
qs._extra = kwargs
return qs
def filter(self, *q, **filter_fields):
"""
Returns a copy of this queryset that includes only rows matching the conditions.
Add q object to query if it specified.
"""
from infi.clickhouse_orm.funcs import F
def _filter_or_exclude(self, *q, **kwargs):
from .funcs import F
inverse = kwargs.pop('_inverse', False)
prewhere = kwargs.pop('prewhere', False)
qs = copy(self)
qs._q = list(self._q)
condition = Q()
for arg in q:
if isinstance(arg, Q):
qs._q.append(arg)
condition &= arg
elif isinstance(arg, F):
qs._q.append(Q(arg))
condition &= Q(arg)
else:
raise TypeError('Invalid argument "%r" to queryset filter' % arg)
if filter_fields:
qs._q += [Q(**filter_fields)]
if kwargs:
condition &= Q(**kwargs)
if inverse:
condition = ~condition
condition = copy(self._prewhere_q if prewhere else self._where_q) & condition
if prewhere:
qs._prewhere_q = condition
else:
qs._where_q = condition
return qs
def exclude(self, **filter_fields):
def filter(self, *q, **kwargs):
"""
Returns a copy of this queryset that includes only rows matching the conditions.
Pass `prewhere=True` to apply the conditions as PREWHERE instead of WHERE.
"""
return self._filter_or_exclude(*q, **kwargs)
def exclude(self, *q, **kwargs):
"""
Returns a copy of this queryset that excludes all rows matching the conditions.
Pass `prewhere=True` to apply the conditions as PREWHERE instead of WHERE.
"""
qs = copy(self)
qs._q = list(self._q) + [~Q(**filter_fields)]
return qs
return self._filter_or_exclude(*q, _inverse=True, **kwargs)
def paginate(self, page_num=1, page_size=100):
"""
@ -486,7 +579,8 @@ class AggregateQuerySet(QuerySet):
self._grouping_fields = grouping_fields
self._calculated_fields = calculated_fields
self._order_by = list(base_qs._order_by)
self._q = list(base_qs._q)
self._where_q = base_qs._where_q
self._prewhere_q = base_qs._prewhere_q
self._limits = base_qs._limits
self._distinct = base_qs._distinct
@ -515,26 +609,11 @@ class AggregateQuerySet(QuerySet):
"""
raise NotImplementedError('Cannot re-aggregate an AggregateQuerySet')
def as_sql(self):
def select_fields_as_sql(self):
"""
Returns the whole query as a SQL string.
Returns the selected fields or expressions as a SQL string.
"""
distinct = 'DISTINCT ' if self._distinct else ''
grouping = comma_join('`%s`' % field for field in self._grouping_fields)
fields = comma_join(list(self._fields) + ['%s AS %s' % (v, k) for k, v in self._calculated_fields.items()])
params = dict(
distinct=distinct,
grouping=grouping or "''",
fields=fields,
table=self._model_cls.table_name(),
conds=self.conditions_as_sql()
)
sql = u'SELECT %(distinct)s%(fields)s\nFROM `%(table)s`\nWHERE %(conds)s\nGROUP BY %(grouping)s' % params
if self._order_by:
sql += '\nORDER BY ' + self.order_by_as_sql()
if self._limits:
sql += '\nLIMIT %d, %d' % self._limits
return sql
return comma_join(list(self._fields) + ['%s AS %s' % (v, k) for k, v in self._calculated_fields.items()])
def __iter__(self):
return self._database.select(self.as_sql()) # using an ad-hoc model
@ -547,4 +626,12 @@ class AggregateQuerySet(QuerySet):
raw = self._database.raw(sql)
return int(raw) if raw else 0
def with_totals(self):
"""
Adds WITH TOTALS modifier ot GROUP BY, making query return extra row
with aggregate function calculated across all the rows. More information:
https://clickhouse.yandex/docs/en/query_language/select/#with-totals-modifier
"""
qs = copy(self)
qs._grouping_with_totals = True
return qs

View File

@ -19,8 +19,8 @@ class SystemPart(Model):
"""
OPERATIONS = frozenset({'DETACH', 'DROP', 'ATTACH', 'FREEZE', 'FETCH'})
readonly = True
system = True
_readonly = True
_system = True
database = StringField() # Name of the database where the table that this part belongs to is located.
table = StringField() # Name of the table that this part belongs to.

View File

@ -14,7 +14,7 @@ logging.getLogger("requests").setLevel(logging.WARNING)
class TestCaseWithData(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(Person)
def tearDown(self):

View File

@ -0,0 +1,7 @@
from infi.clickhouse_orm import migrations
from ..test_migrations import *
operations = [
migrations.AlterTable(Model4_compressed),
migrations.AlterTable(Model2LowCardinality)
]

View File

@ -11,7 +11,7 @@ from infi.clickhouse_orm.engines import *
class MaterializedFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(ModelWithAliasFields)
def tearDown(self):

View File

@ -11,7 +11,7 @@ from infi.clickhouse_orm.engines import *
class ArrayFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(ModelWithArrays)
def tearDown(self):

View File

@ -0,0 +1,123 @@
from __future__ import unicode_literals
import unittest
import datetime
import pytz
from infi.clickhouse_orm.database import Database
from infi.clickhouse_orm.models import Model
from infi.clickhouse_orm.fields import *
from infi.clickhouse_orm.engines import *
from infi.clickhouse_orm.utils import parse_tsv
class CompressedFieldsTestCase(unittest.TestCase):
def setUp(self):
self.database = Database('test-db', log_statements=True)
self.database.create_table(CompressedModel)
def tearDown(self):
self.database.drop_database()
def test_defaults(self):
# Check that all fields have their explicit or implicit defaults
instance = CompressedModel()
self.database.insert([instance])
self.assertEqual(instance.date_field, datetime.date(1970, 1, 1))
self.assertEqual(instance.datetime_field, datetime.datetime(1970, 1, 1, tzinfo=pytz.utc))
self.assertEqual(instance.string_field, 'dozo')
self.assertEqual(instance.int64_field, 42)
self.assertEqual(instance.float_field, 0)
self.assertEqual(instance.nullable_field, None)
self.assertEqual(instance.array_field, [])
def test_assignment(self):
# Check that all fields are assigned during construction
kwargs = dict(
uint64_field=217,
date_field=datetime.date(1973, 12, 6),
datetime_field=datetime.datetime(2000, 5, 24, 10, 22, tzinfo=pytz.utc),
string_field='aloha',
int64_field=-50,
float_field=3.14,
nullable_field=-2.718281,
array_field=['123456789123456','','a']
)
instance = CompressedModel(**kwargs)
self.database.insert([instance])
for name, value in kwargs.items():
self.assertEqual(kwargs[name], getattr(instance, name))
def test_string_conversion(self):
# Check field conversion from string during construction
instance = CompressedModel(date_field='1973-12-06', int64_field='100', float_field='7', nullable_field=None, array_field='[a,b,c]')
self.assertEqual(instance.date_field, datetime.date(1973, 12, 6))
self.assertEqual(instance.int64_field, 100)
self.assertEqual(instance.float_field, 7)
self.assertEqual(instance.nullable_field, None)
self.assertEqual(instance.array_field, ['a', 'b', 'c'])
# Check field conversion from string during assignment
instance.int64_field = '99'
self.assertEqual(instance.int64_field, 99)
def test_to_dict(self):
instance = CompressedModel(date_field='1973-12-06', int64_field='100', float_field='7', array_field='[a,b,c]')
self.assertDictEqual(instance.to_dict(), {
"date_field": datetime.date(1973, 12, 6),
"int64_field": 100,
"float_field": 7.0,
"datetime_field": datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=pytz.utc),
"alias_field": 0.0,
'string_field': 'dozo',
'nullable_field': None,
'uint64_field': 0,
'array_field': ['a','b','c']
})
self.assertDictEqual(instance.to_dict(include_readonly=False), {
"date_field": datetime.date(1973, 12, 6),
"int64_field": 100,
"float_field": 7.0,
"datetime_field": datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=pytz.utc),
'string_field': 'dozo',
'nullable_field': None,
'uint64_field': 0,
'array_field': ['a', 'b', 'c']
})
self.assertDictEqual(
instance.to_dict(include_readonly=False, field_names=('int64_field', 'alias_field', 'datetime_field')), {
"int64_field": 100,
"datetime_field": datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=pytz.utc)
})
# This test will fail on clickhouse version < 19.1.16, use skip test
def test_confirm_compression_codec(self):
instance = CompressedModel(date_field='1973-12-06', int64_field='100', float_field='7', array_field='[a,b,c]')
self.database.insert([instance])
r = self.database.raw("select name, compression_codec from system.columns where table = '{}' and database='{}' FORMAT TabSeparatedWithNamesAndTypes".format(instance.table_name(), self.database.db_name))
lines = r.splitlines()
field_names = parse_tsv(lines[0])
field_types = parse_tsv(lines[1])
data = [tuple(parse_tsv(line)) for line in lines[2:]]
self.assertListEqual(data, [('uint64_field', 'CODEC(ZSTD(10))'),
('datetime_field', 'CODEC(Delta(4), ZSTD(1))'),
('date_field', 'CODEC(Delta(4), ZSTD(22))'),
('int64_field', 'CODEC(LZ4)'),
('string_field', 'CODEC(LZ4HC(10))'),
('nullable_field', 'CODEC(ZSTD(1))'),
('array_field', 'CODEC(Delta(2), LZ4HC(0))'),
('float_field', 'CODEC(NONE)'),
('alias_field', 'CODEC(ZSTD(4))')])
class CompressedModel(Model):
uint64_field = UInt64Field(codec='ZSTD(10)')
datetime_field = DateTimeField(codec='Delta,ZSTD')
date_field = DateField(codec='Delta(4),ZSTD(22)')
int64_field = Int64Field(default=42, codec='LZ4')
string_field = StringField(default='dozo', codec='LZ4HC(10)')
nullable_field = NullableField(Float32Field(), codec='ZSTD')
array_field = ArrayField(FixedStringField(length=15), codec='Delta(2),LZ4HC')
float_field = Float32Field(codec='NONE')
alias_field = Float32Field(alias='float_field', codec='ZSTD(4)')
engine = MergeTree('datetime_field', ('uint64_field', 'datetime_field'))

View File

@ -1,18 +1,15 @@
from __future__ import unicode_literals
import unittest
import six
from uuid import UUID
from infi.clickhouse_orm.database import Database
from infi.clickhouse_orm.fields import Field, Int16Field
from infi.clickhouse_orm.models import Model
from infi.clickhouse_orm.engines import Memory
from infi.clickhouse_orm.utils import escape
class CustomFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
def tearDown(self):
self.database.drop_database()
@ -35,37 +32,6 @@ class CustomFieldsTest(unittest.TestCase):
with self.assertRaises(ValueError):
TestModel(i=1, f=value)
def test_uuid_field(self):
# Create a model
class TestModel(Model):
i = Int16Field()
f = UUIDField()
engine = Memory()
self.database.create_table(TestModel)
# Check valid values (all values are the same UUID)
values = [
'{12345678-1234-5678-1234-567812345678}',
'12345678123456781234567812345678',
'urn:uuid:12345678-1234-5678-1234-567812345678',
'\x12\x34\x56\x78'*4,
(0x12345678, 0x1234, 0x5678, 0x12, 0x34, 0x567812345678),
0x12345678123456781234567812345678,
]
for index, value in enumerate(values):
rec = TestModel(i=index, f=value)
self.database.insert([rec])
for rec in TestModel.objects_in(self.database):
self.assertEqual(rec.f, UUID(values[0]))
# Check that ClickHouse encoding functions are supported
for rec in self.database.select("SELECT i, UUIDNumToString(f) AS f FROM testmodel", TestModel):
self.assertEqual(rec.f, UUID(values[0]))
for rec in self.database.select("SELECT 1 as i, UUIDStringToNum('12345678-1234-5678-1234-567812345678') AS f", TestModel):
self.assertEqual(rec.f, UUID(values[0]))
# Check invalid values
for value in [None, 'zzz', -1, '123']:
with self.assertRaises(ValueError):
TestModel(i=1, f=value)
class BooleanField(Field):
@ -88,32 +54,3 @@ class BooleanField(Field):
# The value was already converted by to_python, so it's a bool
return '1' if value else '0'
class UUIDField(Field):
# The ClickHouse column type to use
db_type = 'FixedString(16)'
# The default value if empty
class_default = UUID(int=0)
def to_python(self, value, timezone_in_use):
# Convert valid values to UUID instance
if isinstance(value, UUID):
return value
elif isinstance(value, six.string_types):
return UUID(bytes=value.encode('latin1')) if len(value) == 16 else UUID(value)
elif isinstance(value, six.integer_types):
return UUID(int=value)
elif isinstance(value, tuple):
return UUID(fields=value)
else:
raise ValueError('Invalid value for UUIDField: %r' % value)
def to_db_string(self, value, quote=True):
# The value was already converted by to_python, so it's a UUID instance
val = value.bytes
if six.PY3:
val = str(val, 'latin1')
return escape(val, quote)

View File

@ -112,6 +112,14 @@ class DatabaseTestCase(TestCaseWithData):
self.assertEqual([obj.to_tsv() for obj in page_a.objects],
[obj.to_tsv() for obj in page_b.objects])
def test_pagination_empty_page(self):
for page_num in (-1, 1, 2):
page = self.database.paginate(Person, 'first_name, last_name', page_num, 10, conditions="first_name = 'Ziggy'")
self.assertEqual(page.number_of_objects, 0)
self.assertEqual(page.objects, [])
self.assertEqual(page.pages_total, 0)
self.assertEqual(page.number, max(page_num, 1))
def test_pagination_invalid_page(self):
self._insert_and_check(self._sample_data(), len(data))
for page_num in (0, -2, -100):
@ -142,7 +150,7 @@ class DatabaseTestCase(TestCaseWithData):
exc = cm.exception
self.assertEqual(exc.code, 193)
self.assertEqual(exc.message, 'Wrong password for user default')
self.assertTrue(exc.message.startswith('Wrong password for user default'))
def test_nonexisting_db(self):
db = Database('db_not_here', autocreate=False)
@ -150,7 +158,7 @@ class DatabaseTestCase(TestCaseWithData):
db.create_table(Person)
exc = cm.exception
self.assertEqual(exc.code, 81)
self.assertEqual(exc.message, "Database db_not_here doesn't exist")
self.assertTrue(exc.message.startswith("Database db_not_here doesn't exist"))
# Create and delete the db twice, to ensure db_exists gets updated
for i in range(2):
# Now create the database - should succeed

View File

@ -10,7 +10,7 @@ from infi.clickhouse_orm.engines import *
class DateFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(ModelWithDate)
def tearDown(self):

View File

@ -12,7 +12,7 @@ from infi.clickhouse_orm.engines import *
class DecimalFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
try:
self.database.create_table(DecimalModel)
except ServerError as e:

View File

@ -14,7 +14,7 @@ logging.getLogger("requests").setLevel(logging.WARNING)
class _EnginesHelperTestCase(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
def tearDown(self):
self.database.drop_database()
@ -115,8 +115,8 @@ class EnginesTestCase(_EnginesHelperTestCase):
TestModel2(date='2017-01-02', event_id=2, event_group=2, event_count=2, event_version=2)
])
# event_uversion is materialized field. So * won't select it and it will be zero
res = self.database.select('SELECT *, event_uversion FROM $table ORDER BY event_id', model_class=TestMergeModel)
res = [row for row in res]
res = self.database.select('SELECT *, _table, event_uversion FROM $table ORDER BY event_id', model_class=TestMergeModel)
res = list(res)
self.assertEqual(2, len(res))
self.assertDictEqual({
'_table': 'testmodel1',
@ -161,9 +161,9 @@ class EnginesTestCase(_EnginesHelperTestCase):
self.assertEqual(2, len(parts))
self.assertEqual('testcollapsemodel', parts[0].table)
self.assertEqual('(201701, 13)', parts[0].partition)
self.assertEqual('(201701, 13)'.replace(' ', ''), parts[0].partition.replace(' ', ''))
self.assertEqual('testmodel', parts[1].table)
self.assertEqual('(201701, 13)', parts[1].partition)
self.assertEqual('(201701, 13)'.replace(' ', ''), parts[1].partition.replace(' ', ''))
class SampleModel(Model):
@ -209,7 +209,7 @@ class DistributedTestCase(_EnginesHelperTestCase):
exc = cm.exception
self.assertEqual(exc.code, 170)
self.assertEqual(exc.message, "Requested cluster 'cluster_name' not found")
self.assertTrue(exc.message.startswith("Requested cluster 'cluster_name' not found"))
def test_verbose_engine_two_superclasses(self):
class TestModel2(SampleModel):

View File

@ -6,16 +6,13 @@ from infi.clickhouse_orm.models import Model
from infi.clickhouse_orm.fields import *
from infi.clickhouse_orm.engines import *
try:
Enum # exists in Python 3.4+
except NameError:
from enum import Enum # use the enum34 library instead
from enum import Enum
class EnumFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(ModelWithEnum)
self.database.create_table(ModelWithEnumArray)

View File

@ -11,7 +11,7 @@ from infi.clickhouse_orm.engines import *
class FixedStringFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(FixedStringModel)
def tearDown(self):

View File

@ -24,7 +24,7 @@ class FuncsTestCase(TestCaseWithData):
sql = 'SELECT %s AS value' % func.to_sql()
logger.info(sql)
result = list(self.database.select(sql))
logger.info('\t==> %s', result[0].value)
logger.info('\t==> %s', result[0].value if result else '<empty>')
if expected_value is not None:
self.assertEqual(result[0].value, expected_value)
@ -255,7 +255,7 @@ class FuncsTestCase(TestCaseWithData):
try:
self._test_func(F.base64Decode(F.base64Encode('Hello')), 'Hello')
self._test_func(F.tryBase64Decode(F.base64Encode('Hello')), 'Hello')
self._test_func(F.tryBase64Decode('zzz'), '')
self._test_func(F.tryBase64Decode('zzz'), None)
except ServerError as e:
# ClickHouse version that doesn't support these functions
raise unittest.SkipTest(e.message)

View File

@ -9,7 +9,7 @@ from infi.clickhouse_orm import database, engines, fields, models
class JoinTest(unittest.TestCase):
def setUp(self):
self.database = database.Database('test-db')
self.database = database.Database('test-db', log_statements=True)
self.database.create_table(Foo)
self.database.create_table(Bar)
self.database.insert([Foo(id=i) for i in range(3)])

View File

@ -11,7 +11,7 @@ from infi.clickhouse_orm.engines import *
class MaterializedFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(ModelWithMaterializedFields)
def tearDown(self):

View File

@ -7,14 +7,11 @@ from infi.clickhouse_orm.fields import *
from infi.clickhouse_orm.engines import *
from infi.clickhouse_orm.migrations import MigrationHistory
from enum import Enum
# Add tests to path so that migrations will be importable
import sys, os
sys.path.append(os.path.dirname(__file__))
try:
Enum # exists in Python 3.4+
except NameError:
from enum import Enum # use the enum34 library instead
import logging
logging.basicConfig(level=logging.DEBUG, format='%(message)s')
@ -24,7 +21,7 @@ logging.getLogger("requests").setLevel(logging.WARNING)
class MigrationsTestCase(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.drop_table(MigrationHistory)
def tearDown(self):
@ -93,10 +90,21 @@ class MigrationsTestCase(unittest.TestCase):
self.database.migrate('tests.sample_migrations', 14)
self.assertTrue(self.tableExists(MaterializedModel1))
self.assertEqual(self.getTableFields(MaterializedModel1),
[('date_time', "DateTime"), ('int_field', 'Int8'), ('date', 'Date')])
[('date_time', 'DateTime'), ('int_field', 'Int8'), ('date', 'Date'), ('int_field_plus_one', 'Int8')])
self.assertTrue(self.tableExists(AliasModel1))
self.assertEqual(self.getTableFields(AliasModel1),
[('date', 'Date'), ('int_field', 'Int8'), ('date_alias', "Date")])
[('date', 'Date'), ('int_field', 'Int8'), ('date_alias', 'Date'), ('int_field_plus_one', 'Int8')])
self.database.migrate('tests.sample_migrations', 15)
self.assertTrue(self.tableExists(Model4_compressed))
if self.database.has_low_cardinality_support:
self.assertEqual(self.getTableFields(Model2LowCardinality),
[('date', 'Date'), ('f1', 'LowCardinality(Int32)'), ('f3', 'LowCardinality(Float32)'),
('f2', 'LowCardinality(String)'), ('f4', 'LowCardinality(Nullable(String))'), ('f5', 'Array(LowCardinality(UInt64))')])
else:
logging.warning('No support for low cardinality')
self.assertEqual(self.getTableFields(Model2),
[('date', 'Date'), ('f1', 'Int32'), ('f3', 'Float32'), ('f2', 'String'), ('f4', 'Nullable(String)'),
('f5', 'Array(UInt64)')])
# Several different models with the same table name, to simulate a table that changes over time
@ -183,6 +191,7 @@ class MaterializedModel1(Model):
date_time = DateTimeField()
date = DateField(materialized='toDate(date_time)')
int_field = Int8Field()
int_field_plus_one = Int8Field(materialized='int_field + 1')
engine = MergeTree('date', ('date',))
@ -206,6 +215,7 @@ class AliasModel1(Model):
date = DateField()
date_alias = DateField(alias='date')
int_field = Int8Field()
int_field_plus_one = Int8Field(alias='int_field + 1')
engine = MergeTree('date', ('date',))
@ -256,3 +266,31 @@ class Model4Buffer_changed(BufferModel, Model4_changed):
@classmethod
def table_name(cls):
return 'model4buffer'
class Model4_compressed(Model):
date = DateField()
f3 = DateTimeField(codec='Delta,ZSTD(10)')
f2 = StringField(codec='LZ4HC')
engine = MergeTree('date', ('date',))
@classmethod
def table_name(cls):
return 'model4'
class Model2LowCardinality(Model):
date = DateField()
f1 = LowCardinalityField(Int32Field())
f3 = LowCardinalityField(Float32Field())
f2 = LowCardinalityField(StringField())
f4 = LowCardinalityField(NullableField(StringField()))
f5 = ArrayField(LowCardinalityField(UInt64Field()))
engine = MergeTree('date', ('date',))
@classmethod
def table_name(cls):
return 'mig'

View File

@ -6,6 +6,7 @@ from infi.clickhouse_orm.database import Database
from infi.clickhouse_orm.models import Model
from infi.clickhouse_orm.fields import *
from infi.clickhouse_orm.engines import *
from infi.clickhouse_orm.utils import comma_join
from datetime import date, datetime
@ -13,7 +14,7 @@ from datetime import date, datetime
class NullableFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(ModelWithNullable)
def tearDown(self):
@ -95,14 +96,19 @@ class NullableFieldsTest(unittest.TestCase):
ModelWithNullable(date_field='2016-08-30', null_str='', null_int=42, null_date=dt),
ModelWithNullable(date_field='2016-08-30', null_str='nothing', null_int=None, null_date=None),
ModelWithNullable(date_field='2016-08-31', null_str=None, null_int=42, null_date=dt),
ModelWithNullable(date_field='2016-08-31', null_str=None, null_int=None, null_date=None)
ModelWithNullable(date_field='2016-08-31', null_str=None, null_int=None, null_date=None, null_default=None)
])
def _assert_sample_data(self, results):
for r in results:
print(r.to_dict())
dt = date(1970, 1, 1)
self.assertEqual(len(results), 4)
self.assertIsNone(results[0].null_str)
self.assertEqual(results[0].null_int, 42)
self.assertEqual(results[0].null_default, 7)
self.assertEqual(results[0].null_alias, 21)
self.assertEqual(results[0].null_materialized, 420)
self.assertEqual(results[0].null_date, dt)
self.assertIsNone(results[1].null_date)
self.assertEqual(results[1].null_str, 'nothing')
@ -110,19 +116,27 @@ class NullableFieldsTest(unittest.TestCase):
self.assertIsNone(results[2].null_str)
self.assertEqual(results[2].null_date, dt)
self.assertEqual(results[2].null_int, 42)
self.assertEqual(results[2].null_default, 7)
self.assertEqual(results[2].null_alias, 21)
self.assertEqual(results[0].null_materialized, 420)
self.assertIsNone(results[3].null_int)
self.assertIsNone(results[3].null_default)
self.assertIsNone(results[3].null_alias)
self.assertIsNone(results[3].null_materialized)
self.assertIsNone(results[3].null_str)
self.assertIsNone(results[3].null_date)
def test_insert_and_select(self):
self._insert_sample_data()
query = 'SELECT * from $table ORDER BY date_field'
fields = comma_join(ModelWithNullable.fields().keys())
query = 'SELECT %s from $table ORDER BY date_field' % fields
results = list(self.database.select(query, ModelWithNullable))
self._assert_sample_data(results)
def test_ad_hoc_model(self):
self._insert_sample_data()
query = 'SELECT * from $db.modelwithnullable ORDER BY date_field'
fields = comma_join(ModelWithNullable.fields().keys())
query = 'SELECT %s from $db.modelwithnullable ORDER BY date_field' % fields
results = list(self.database.select(query))
self._assert_sample_data(results)
@ -133,5 +147,8 @@ class ModelWithNullable(Model):
null_str = NullableField(StringField(), extra_null_values={''})
null_int = NullableField(Int32Field())
null_date = NullableField(DateField())
null_default = NullableField(Int32Field(), default=7)
null_alias = NullableField(Int32Field(), alias='null_int/2')
null_materialized = NullableField(Int32Field(), alias='null_int*10')
engine = MergeTree('date_field', ('date_field',))

View File

@ -3,17 +3,15 @@ from __future__ import unicode_literals, print_function
import unittest
from infi.clickhouse_orm.database import Database
from infi.clickhouse_orm.query import Q, F
from infi.clickhouse_orm.query import Q
from infi.clickhouse_orm.funcs import F
from .base_test_with_data import *
from datetime import date, datetime
from enum import Enum
from logging import getLogger
logger = getLogger('tests')
try:
Enum # exists in Python 3.4+
except NameError:
from enum import Enum # use the enum34 library instead
class QuerySetTestCase(TestCaseWithData):
@ -31,6 +29,13 @@ class QuerySetTestCase(TestCaseWithData):
self.assertEqual(count, expected_count)
self.assertEqual(qs.count(), expected_count)
def test_prewhere(self):
# We can't distinguish prewhere and where results, it affects performance only.
# So let's control prewhere acts like where does
qs = Person.objects_in(self.database)
self.assertTrue(qs.filter(first_name='Connor', prewhere=True))
self.assertFalse(qs.filter(first_name='Willy', prewhere=True))
def test_no_filtering(self):
qs = Person.objects_in(self.database)
self._test_qs(qs, len(data))
@ -222,7 +227,7 @@ class QuerySetTestCase(TestCaseWithData):
qs = Person.objects_in(self.database).order_by('first_name', 'last_name')
# Try different page sizes
for page_size in (1, 2, 7, 10, 30, 100, 150):
# Iterate over pages and collect all intances
# Iterate over pages and collect all instances
page_num = 1
instances = set()
while True:
@ -296,7 +301,7 @@ class QuerySetTestCase(TestCaseWithData):
qs = Person.objects_in(self.database)
qs = qs.filter(Q(first_name='a'), F('greater', Person.height, 1.7), last_name='b')
self.assertEqual(qs.conditions_as_sql(),
"first_name = 'a' AND greater(`height`, 1.7) AND last_name = 'b'")
"(first_name = 'a') AND (greater(`height`, 1.7)) AND (last_name = 'b')")
def test_invalid_filter(self):
qs = Person.objects_in(self.database)
@ -417,6 +422,17 @@ class AggregateTestCase(TestCaseWithData):
print(qs.as_sql())
self.assertEqual(qs.count(), 1)
def test_aggregate_with_totals(self):
qs = Person.objects_in(self.database).aggregate('first_name', count='count()').\
with_totals().order_by('-count')[:5]
print(qs.as_sql())
result = list(qs)
self.assertEqual(len(result), 6)
for row in result[:-1]:
self.assertEqual(2, row.count)
self.assertEqual(100, result[-1].count)
def test_double_underscore_field(self):
class Mdl(Model):
the__number = Int32Field()
@ -463,9 +479,9 @@ class FuncsTestCase(TestCaseWithData):
# Numeric args
self.assertEqual(F('func', 1, 1.1, Decimal('3.3')).to_sql(), "func(1, 1.1, 3.3)")
# Date args
self.assertEqual(F('func', date(2018, 12, 31)).to_sql(), "func('2018-12-31')")
self.assertEqual(F('func', date(2018, 12, 31)).to_sql(), "func(toDate('2018-12-31'))")
# Datetime args
self.assertEqual(F('func', datetime(2018, 12, 31)).to_sql(), "func('1546214400')")
self.assertEqual(F('func', datetime(2018, 12, 31)).to_sql(), "func(toDateTime('1546214400'))")
# Boolean args
self.assertEqual(F('func', True, False).to_sql(), "func(1, 0)")
# Null args

View File

@ -36,9 +36,9 @@ class ReadonlyTestCase(TestCaseWithData):
def _check_db_readonly_err(self, exc, drop_table=None):
self.assertEqual(exc.code, 164)
if drop_table:
self.assertEqual(exc.message, 'Cannot drop table in readonly mode')
self.assertTrue(exc.message.startswith('Cannot drop table in readonly mode'))
else:
self.assertEqual(exc.message, 'Cannot insert into table in readonly mode')
self.assertTrue(exc.message.startswith('Cannot insert into table in readonly mode'))
def test_readonly_db_with_default_user(self):
self._test_readonly_db('default')

View File

@ -0,0 +1,32 @@
from __future__ import unicode_literals
import unittest
from infi.clickhouse_orm.database import ServerError
class ServerErrorTest(unittest.TestCase):
def test_old_format(self):
code, msg = ServerError.get_error_code_msg("Code: 81, e.displayText() = DB::Exception: Database db_not_here doesn't exist, e.what() = DB::Exception (from [::1]:33458)")
self.assertEqual(code, 81)
self.assertEqual(msg, "Database db_not_here doesn't exist")
code, msg = ServerError.get_error_code_msg("Code: 161, e.displayText() = DB::Exception: Limit for number of columns to read exceeded. Requested: 11, maximum: 1, e.what() = DB::Exception\n")
self.assertEqual(code, 161)
self.assertEqual(msg, "Limit for number of columns to read exceeded. Requested: 11, maximum: 1")
def test_new_format(self):
code, msg = ServerError.get_error_code_msg("Code: 164, e.displayText() = DB::Exception: Cannot drop table in readonly mode")
self.assertEqual(code, 164)
self.assertEqual(msg, "Cannot drop table in readonly mode")
code, msg = ServerError.get_error_code_msg("Code: 48, e.displayText() = DB::Exception: Method write is not supported by storage Merge")
self.assertEqual(code, 48)
self.assertEqual(msg, "Method write is not supported by storage Merge")
code, msg = ServerError.get_error_code_msg("Code: 60, e.displayText() = DB::Exception: Table default.zuzu doesn't exist.\n")
self.assertEqual(code, 60)
self.assertEqual(msg, "Table default.zuzu doesn't exist.")

View File

@ -13,8 +13,9 @@ from infi.clickhouse_orm.system_models import SystemPart
class SystemTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
def tearDown(self):
self.database.drop_database()
@ -38,7 +39,7 @@ class SystemPartTest(unittest.TestCase):
BACKUP_DIRS = ['/var/lib/clickhouse/shadow', '/opt/clickhouse/shadow/']
def setUp(self):
self.database = Database('test-db')
self.database = Database('test-db', log_statements=True)
self.database.create_table(TestTable)
self.database.create_table(CustomPartitionedTable)
self.database.insert([TestTable(date_field=date.today())])
@ -54,6 +55,12 @@ class SystemPartTest(unittest.TestCase):
return dirnames
raise unittest.SkipTest('Cannot find backups dir')
def test_is_read_only(self):
self.assertTrue(SystemPart.is_read_only())
def test_is_system_model(self):
self.assertTrue(SystemPart.is_system_model())
def test_get_all(self):
parts = SystemPart.get(self.database)
self.assertEqual(len(list(parts)), 2)
@ -62,7 +69,8 @@ class SystemPartTest(unittest.TestCase):
parts = list(SystemPart.get_active(self.database))
self.assertEqual(len(parts), 2)
parts[0].detach()
self.assertEqual(len(list(SystemPart.get_active(self.database))), 1)
parts = list(SystemPart.get_active(self.database))
self.assertEqual(len(parts), 1)
def test_get_conditions(self):
parts = list(SystemPart.get(self.database, conditions="table='testtable'"))
@ -101,6 +109,10 @@ class SystemPartTest(unittest.TestCase):
# TODO Not tested, as I have no replication set
pass
def test_query(self):
SystemPart.objects_in(self.database).count()
list(SystemPart.objects_in(self.database).filter(table='testtable'))
class TestTable(Model):
date_field = DateField()

45
tests/test_uuid_fields.py Normal file
View File

@ -0,0 +1,45 @@
from __future__ import unicode_literals
import unittest
from uuid import UUID
from infi.clickhouse_orm.database import Database
from infi.clickhouse_orm.fields import Int16Field, UUIDField
from infi.clickhouse_orm.models import Model
from infi.clickhouse_orm.engines import Memory
class UUIDFieldsTest(unittest.TestCase):
def setUp(self):
self.database = Database('test-db', log_statements=True)
def tearDown(self):
self.database.drop_database()
def test_uuid_field(self):
# Create a model
class TestModel(Model):
i = Int16Field()
f = UUIDField()
engine = Memory()
self.database.create_table(TestModel)
# Check valid values (all values are the same UUID)
values = [
'12345678-1234-5678-1234-567812345678',
'{12345678-1234-5678-1234-567812345678}',
'12345678123456781234567812345678',
'urn:uuid:12345678-1234-5678-1234-567812345678',
b'\x12\x34\x56\x78'*4,
(0x12345678, 0x1234, 0x5678, 0x12, 0x34, 0x567812345678),
0x12345678123456781234567812345678,
UUID(int=0x12345678123456781234567812345678),
]
for index, value in enumerate(values):
rec = TestModel(i=index, f=value)
self.database.insert([rec])
for rec in TestModel.objects_in(self.database):
self.assertEqual(rec.f, UUID(values[0]))
# Check invalid values
for value in [None, 'zzz', -1, '123']:
with self.assertRaises(ValueError):
TestModel(i=1, f=value)