thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-19 16:20:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor improvements for Lemmatizers

Browse Source
This commit is contained in:
Nikolay Degterinsky 2024-09-04 19:36:16 +02:00 committed by GitHub
parent d948de53c6
commit c10455ca03
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
src/Interpreters/Lemmatizers.cpp
View File

@ -33,25 +33,16 @@ public:
}
};
/// Duplicate of code from StringUtils.h. Copied here for less dependencies.
static bool startsWith(const std::string & s, const char * prefix)
{
return s.size() >= strlen(prefix) && 0 == memcmp(s.data(), prefix, strlen(prefix));
}
Lemmatizers::Lemmatizers(const Poco::Util::AbstractConfiguration & config)
{
String prefix = "lemmatizers";
const String prefix = "lemmatizers";
Poco::Util::AbstractConfiguration::Keys keys;
if (!config.has(prefix))
throw Exception(ErrorCodes::INVALID_CONFIG_PARAMETER, "No lemmatizers specified in server config on prefix '{}'", prefix);
config.keys(prefix, keys);
for (const auto & key : keys)
{
if (startsWith(key, "lemmatizer"))
if (key.starts_with("lemmatizer"))
{
const auto & lemm_name = config.getString(prefix + "." + key + ".lang", "");
const auto & lemm_path = config.getString(prefix + "." + key + ".path", "");
@ -81,13 +72,13 @@ Lemmatizers::LemmPtr Lemmatizers::getLemmatizer(const String & name)
if (paths.find(name) != paths.end())
{
if (!std::filesystem::exists(paths[name]))
throw Exception(ErrorCodes::INVALID_CONFIG_PARAMETER, "Incorrect path to lemmatizer: {}", paths[name]);
throw Exception(ErrorCodes::INVALID_CONFIG_PARAMETER, "Path to lemmatizer does not exist: {}", paths[name]);
lemmatizers[name] = std::make_shared<Lemmatizer>(paths[name]);
return lemmatizers[name];
}
throw Exception(ErrorCodes::INVALID_CONFIG_PARAMETER, "Lemmatizer named: '{}' is not found", name);
throw Exception(ErrorCodes::INVALID_CONFIG_PARAMETER, "Lemmatizer with the name '{}' was not found in the configuration", name);
}
}