mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-21 23:21:59 +00:00
Fix unbundled build
This commit is contained in:
alesapin
parent
f0fc12d0dd
commit
aa86fac4e7
@ -23,6 +23,7 @@ RUN apt-get update \
|
||||
libboost-regex-dev \
|
||||
libboost-context-dev \
|
||||
libboost-coroutine-dev \
|
||||
libboost-graph-dev \
|
||||
zlib1g-dev \
|
||||
liblz4-dev \
|
||||
libdouble-conversion-dev \
|
||||
|
||||
@ -96,7 +96,7 @@ public:
|
||||
|
||||
if (synset)
|
||||
{
|
||||
for (const auto &token : *synset)
|
||||
for (const auto & token : *synset)
|
||||
out_data.insert(Field(token.data(), token.size()));
|
||||
|
||||
current_offset += synset->size();
|
||||
|
||||
@ -41,8 +41,7 @@ Lemmatizers::Lemmatizers(const Poco::Util::AbstractConfiguration & config)
|
||||
Poco::Util::AbstractConfiguration::Keys keys;
|
||||
|
||||
if (!config.has(prefix))
|
||||
throw Exception("You should specify list of lemmatizers in " + prefix,
|
||||
ErrorCodes::INVALID_CONFIG_PARAMETER);
|
||||
throw Exception(ErrorCodes::INVALID_CONFIG_PARAMETER, "No lemmatizers specified in server config on prefix '{}'", prefix);
|
||||
|
||||
config.keys(prefix, keys);
|
||||
|
||||
|
||||
@ -86,8 +86,8 @@ SynonymsExtensions::SynonymsExtensions(const Poco::Util::AbstractConfiguration &
|
||||
Poco::Util::AbstractConfiguration::Keys keys;
|
||||
|
||||
if (!config.has(prefix))
|
||||
throw Exception("You should specify list of synonyms extensions in " + prefix,
|
||||
ErrorCodes::INVALID_CONFIG_PARAMETER);
|
||||
throw Exception(ErrorCodes::INVALID_CONFIG_PARAMETER,
|
||||
"No synonims extensions specified in server config on prefix '{}'", prefix);
|
||||
|
||||
config.keys(prefix, keys);
|
||||
|
||||
@ -108,8 +108,7 @@ SynonymsExtensions::SynonymsExtensions(const Poco::Util::AbstractConfiguration &
|
||||
if (ext_type.empty())
|
||||
throw Exception("Extension type in config is not specified here: " + prefix + "." + key + ".type",
|
||||
ErrorCodes::INVALID_CONFIG_PARAMETER);
|
||||
if (ext_type != "plain" &&
|
||||
ext_type != "wordnet")
|
||||
if (ext_type != "plain" && ext_type != "wordnet")
|
||||
throw Exception("Unknown extension type in config: " + prefix + "." + key + ".type, must be 'plain' or 'wordnet'",
|
||||
ErrorCodes::INVALID_CONFIG_PARAMETER);
|
||||
|
||||
|
||||
@ -1,48 +0,0 @@
|
||||
<?xml version="1.0"?>
|
||||
<yandex>
|
||||
<logger>
|
||||
<level>trace</level>
|
||||
<log>/var/log/clickhouse-server/clickhouse-server.log</log>
|
||||
<errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
|
||||
<size>1000M</size>
|
||||
<count>10</count>
|
||||
</logger>
|
||||
|
||||
<tcp_port>9000</tcp_port>
|
||||
<listen_host>127.0.0.1</listen_host>
|
||||
|
||||
<openSSL>
|
||||
<client>
|
||||
<cacheSessions>true</cacheSessions>
|
||||
<verificationMode>none</verificationMode>
|
||||
<invalidCertificateHandler>
|
||||
<name>AcceptCertificateHandler</name>
|
||||
</invalidCertificateHandler>
|
||||
</client>
|
||||
</openSSL>
|
||||
|
||||
<max_concurrent_queries>500</max_concurrent_queries>
|
||||
<mark_cache_size>5368709120</mark_cache_size>
|
||||
<path>./clickhouse/</path>
|
||||
<users_config>users.xml</users_config>
|
||||
|
||||
<synonyms_extensions>
|
||||
<extension>
|
||||
<name>en</name>
|
||||
<type>plain</type>
|
||||
<path>/etc/clickhouse-server/dictionaries/ext-en.txt</path>
|
||||
</extension>
|
||||
<extension>
|
||||
<name>ru</name>
|
||||
<type>plain</type>
|
||||
<path>/etc/clickhouse-server/dictionaries/ext-ru.txt</path>
|
||||
</extension>
|
||||
</synonyms_extensions>
|
||||
|
||||
<lemmatizers>
|
||||
<lemmatizer>
|
||||
<lang>en</lang>
|
||||
<path>/etc/clickhouse-server/dictionaries/lem-en.bin</path>
|
||||
</lemmatizer>
|
||||
</lemmatizers>
|
||||
</yandex>
|
||||
22
tests/integration/test_nlp/configs/dicts_config.xml
Normal file
22
tests/integration/test_nlp/configs/dicts_config.xml
Normal file
@ -0,0 +1,22 @@
|
||||
<?xml version="1.0"?>
|
||||
<yandex>
|
||||
<synonyms_extensions>
|
||||
<extension>
|
||||
<name>en</name>
|
||||
<type>plain</type>
|
||||
<path>/etc/clickhouse-server/dictionaries/ext-en.txt</path>
|
||||
</extension>
|
||||
<extension>
|
||||
<name>ru</name>
|
||||
<type>plain</type>
|
||||
<path>/etc/clickhouse-server/dictionaries/ext-ru.txt</path>
|
||||
</extension>
|
||||
</synonyms_extensions>
|
||||
|
||||
<lemmatizers>
|
||||
<lemmatizer>
|
||||
<lang>en</lang>
|
||||
<path>/etc/clickhouse-server/dictionaries/lem-en.bin</path>
|
||||
</lemmatizer>
|
||||
</lemmatizers>
|
||||
</yandex>
|
||||
@ -1,119 +0,0 @@
|
||||
<?xml version="1.0"?>
|
||||
<yandex>
|
||||
<!-- Profiles of settings. -->
|
||||
<profiles>
|
||||
<!-- Default settings. -->
|
||||
<default>
|
||||
<!-- Maximum memory usage for processing single query, in bytes. -->
|
||||
<max_memory_usage>10000000000</max_memory_usage>
|
||||
|
||||
<!-- How to choose between replicas during distributed query processing.
|
||||
random - choose random replica from set of replicas with minimum number of errors
|
||||
nearest_hostname - from set of replicas with minimum number of errors, choose replica
|
||||
with minimum number of different symbols between replica's hostname and local hostname
|
||||
(Hamming distance).
|
||||
in_order - first live replica is chosen in specified order.
|
||||
first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
|
||||
-->
|
||||
<load_balancing>random</load_balancing>
|
||||
</default>
|
||||
|
||||
<!-- Profile that allows only read queries. -->
|
||||
<readonly>
|
||||
<readonly>1</readonly>
|
||||
</readonly>
|
||||
</profiles>
|
||||
|
||||
<!-- Users and ACL. -->
|
||||
<users>
|
||||
<!-- If user name was not specified, 'default' user is used. -->
|
||||
<default>
|
||||
<!-- Password could be specified in plaintext or in SHA256 (in hex format).
|
||||
|
||||
If you want to specify password in plaintext (not recommended), place it in 'password' element.
|
||||
Example: <password>qwerty</password>.
|
||||
Password could be empty.
|
||||
|
||||
If you want to specify SHA256, place it in 'password_sha256_hex' element.
|
||||
Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
|
||||
Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
|
||||
|
||||
If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
|
||||
Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>
|
||||
|
||||
If you want to specify a previously defined LDAP server (see 'ldap_servers' in the main config) for authentication,
|
||||
place its name in 'server' element inside 'ldap' element.
|
||||
Example: <ldap><server>my_ldap_server</server></ldap>
|
||||
|
||||
If you want to authenticate the user via Kerberos (assuming Kerberos is enabled, see 'kerberos' in the main config),
|
||||
place 'kerberos' element instead of 'password' (and similar) elements.
|
||||
The name part of the canonical principal name of the initiator must match the user name for authentication to succeed.
|
||||
You can also place 'realm' element inside 'kerberos' element to further restrict authentication to only those requests
|
||||
whose initiator's realm matches it.
|
||||
Example: <kerberos />
|
||||
Example: <kerberos><realm>EXAMPLE.COM</realm></kerberos>
|
||||
|
||||
How to generate decent password:
|
||||
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
|
||||
In first line will be password and in second - corresponding SHA256.
|
||||
|
||||
How to generate double SHA1:
|
||||
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha1sum | tr -d '-' | xxd -r -p | sha1sum | tr -d '-'
|
||||
In first line will be password and in second - corresponding double SHA1.
|
||||
-->
|
||||
<password></password>
|
||||
|
||||
<!-- List of networks with open access.
|
||||
|
||||
To open access from everywhere, specify:
|
||||
<ip>::/0</ip>
|
||||
|
||||
To open access only from localhost, specify:
|
||||
<ip>::1</ip>
|
||||
<ip>127.0.0.1</ip>
|
||||
|
||||
Each element of list has one of the following forms:
|
||||
<ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
|
||||
2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
|
||||
<host> Hostname. Example: server01.yandex.ru.
|
||||
To check access, DNS query is performed, and all received addresses compared to peer address.
|
||||
<host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.yandex\.ru$
|
||||
To check access, DNS PTR query is performed for peer address and then regexp is applied.
|
||||
Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
|
||||
Strongly recommended that regexp is ends with $
|
||||
All results of DNS requests are cached till server restart.
|
||||
-->
|
||||
<networks>
|
||||
<ip>::/0</ip>
|
||||
</networks>
|
||||
|
||||
<!-- Settings profile for user. -->
|
||||
<profile>default</profile>
|
||||
|
||||
<!-- Quota for user. -->
|
||||
<quota>default</quota>
|
||||
|
||||
<!-- User can create other users and grant rights to them. -->
|
||||
<!-- <access_management>1</access_management> -->
|
||||
</default>
|
||||
</users>
|
||||
|
||||
<!-- Quotas. -->
|
||||
<quotas>
|
||||
<!-- Name of quota. -->
|
||||
<default>
|
||||
<!-- Limits for time interval. You could specify many intervals with different limits. -->
|
||||
<interval>
|
||||
<!-- Length of interval. -->
|
||||
<duration>3600</duration>
|
||||
|
||||
<!-- No limits. Just calculate resource usage for time interval. -->
|
||||
<queries>0</queries>
|
||||
<errors>0</errors>
|
||||
<result_rows>0</result_rows>
|
||||
<read_rows>0</read_rows>
|
||||
<execution_time>0</execution_time>
|
||||
</interval>
|
||||
</default>
|
||||
</quotas>
|
||||
</yandex>
|
||||
@ -10,7 +10,7 @@ from helpers.cluster import ClickHouseCluster
|
||||
|
||||
|
||||
cluster = ClickHouseCluster(__file__)
|
||||
instance = cluster.add_instance('instance', base_config_dir='configs/')
|
||||
instance = cluster.add_instance('instance', main_configs=['configs/dicts_config.xml'])
|
||||
|
||||
def copy_file_to_container(local_path, dist_path, container_id):
|
||||
os.system("docker cp {local} {cont_id}:{dist}".format(local=local_path, cont_id=container_id, dist=dist_path))
|
||||
|
||||
Loading…
Reference in New Issue
Block a user