Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[#128] Update for iRODS 4.3.1 (main) #131

Merged
merged 10 commits into from
Feb 22, 2024
Merged

[#128] Update for iRODS 4.3.1 (main) #131

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
aaa8f33
[#128] Replace use of elasticlient and cpr with boost.beast.
korydraughn Feb 21, 2024
5683dc6
[#108,#138] Remove references to non-existent postinst scripts.
korydraughn Feb 21, 2024
f85ecb3
[#133] Remove document type rule engine plugin.
korydraughn Feb 21, 2024
6526402
[#137] Do not redefine preprocessor macros.
korydraughn Feb 21, 2024
32bf0ad
[#135] Return error if loading of config fails.
korydraughn Feb 21, 2024
373fe29
[#134] Make plugin API functions private to shared libraries.
korydraughn Feb 21, 2024
71da046
[#136] Do not use names reserved for the compiler.
korydraughn Feb 21, 2024
353aff4
[#44] Formatting, clean-up, and other small tweaks.
korydraughn Feb 21, 2024
08b6693
[#44] Do not print log message unless the HTTP request actually fails.
korydraughn Feb 21, 2024
d68d532
[#139] Add support for Rocky Linux to build and test python scripts.
korydraughn Feb 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,6 @@ set(CPACK_ARCHIVE_COMPONENT_INSTALL ON)

include(${CMAKE_SOURCE_DIR}/indexing.cmake)
include(${CMAKE_SOURCE_DIR}/elasticsearch.cmake)
include(${CMAKE_SOURCE_DIR}/document_type.cmake)

list(APPEND CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION "${CPACK_PACKAGING_INSTALL_PREFIX}${CMAKE_INSTALL_LIBDIR}/irods")
list(APPEND CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION "${CPACK_PACKAGING_INSTALL_PREFIX}${IRODS_PLUGINS_DIRECTORY}")
Expand All @@ -111,7 +110,4 @@ list(APPEND CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION "${CPACK_PACKAGING_INS
list(APPEND CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION "${CPACK_PACKAGING_INSTALL_PREFIX}${IRODS_HOME_DIRECTORY}/scripts/irods")
list(APPEND CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION "${CPACK_PACKAGING_INSTALL_PREFIX}${IRODS_HOME_DIRECTORY}/scripts/irods/test")

set(CPACK_DEBIAN_PACKAGE_CONTROL_EXTRA "${CMAKE_SOURCE_DIR}/packaging/postinst;")
set(CPACK_RPM_POST_INSTALL_SCRIPT_FILE "${CMAKE_SOURCE_DIR}/packaging/postinst")

include(CPack)
47 changes: 17 additions & 30 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,31 +27,24 @@ By default, should no resource be tagged it is assumed that all resources are av
There are currently three rule engine plugins to configure for the indexing capability which should be added to the `"rule_engines"` section of `/etc/irods/server_config.json`:

```
"rule_engines": [
{
"instance_name": "irods_rule_engine_plugin-indexing-instance",
"plugin_name": "irods_rule_engine_plugin-indexing",
"plugin_specific_configuration": {
}
},
{
"instance_name": "irods_rule_engine_plugin-elasticsearch-instance",
"plugin_name": "irods_rule_engine_plugin-elasticsearch",
"plugin_specific_configuration": {
"hosts" : ["http://localhost:9200/"],
"bulk_count" : 100,
"read_size" : 4194304
}
},
{
"instance_name": "irods_rule_engine_plugin-document_type-instance",
"plugin_name": "irods_rule_engine_plugin-document_type",
"plugin_specific_configuration": {
}
},
]
"rule_engines": [
{
"instance_name": "irods_rule_engine_plugin-indexing-instance",
"plugin_name": "irods_rule_engine_plugin-indexing",
"plugin_specific_configuration": {}
},
{
"instance_name": "irods_rule_engine_plugin-elasticsearch-instance",
"plugin_name": "irods_rule_engine_plugin-elasticsearch",
"plugin_specific_configuration": {
"hosts": ["http://localhost:9200/"],
"bulk_count": 100,
"read_size": 4194304
}
}
]
```
The first is the main indexing rule engine plugin, the second is the plugin responsible for implementing the policy for the indexing technology, and the third is responsible for implementing the document type introspection. Currently the default imply returns `text` as the document type. This policy can be overridden to call out to services like Tika for a better introspection of the data.
The first is the main indexing rule engine plugin and the second is the plugin responsible for implementing the policy for the indexing technology.

Within each plugin configuration stanza, the "plugin_specific_configuration" object may contain a number of key-value pairs. The following pairs are currently applicable for the purpose of setting the indexing capability's operating parameters:

Expand Down Expand Up @@ -79,12 +72,6 @@ irods_policy_indexing_metadata_index_<technology>
irods_policy_indexing_metadata_purge_<technology>
```

### Document Type Policy

```
irods_policy_indexing_document_type_<technology>
```

### Plugin Testing

Caveats:
Expand Down
163 changes: 88 additions & 75 deletions configuration.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,90 +1,103 @@

#include "configuration.hpp"

#include "plugin_specific_configuration.hpp"
#include <fmt/format.h>

#include <irods/rodsLog.h>
#include <irods/irods_log.hpp>

namespace irods {
namespace indexing {
configuration::configuration(
const std::string& _instance_name ) :
instance_name_{_instance_name} {
try {
auto cfg = get_plugin_specific_configuration(_instance_name);
auto capture_parameter = [&](const std::string& _param, std::string& _attr) {
if (const auto iter = cfg.find(_param); iter != cfg.end()) {
_attr = iter->get<std::string>();
}
}; // capture_parameter
#include <fmt/format.h>

namespace irods::indexing
{
configuration::configuration(const std::string& _instance_name)
: instance_name{_instance_name}
{
try {
auto cfg = get_plugin_specific_configuration(_instance_name);
auto capture_parameter = [&](const std::string& _param, std::string& _attr) {
if (const auto iter = cfg.find(_param); iter != cfg.end()) {
_attr = iter->get<std::string>();
}
}; // capture_parameter

// integer-or-string parameters
// integer-or-string parameters

using configuration_parameters::load;
using configuration_parameters::load;

job_limit = load<int>(cfg, "job_limit_per_collection_indexing_operation", 1000);
minimum_delay_time = load<int>(cfg, "minimum_delay_time", 1);
maximum_delay_time = load<int>(cfg, "maximum_delay_time", 30);
job_limit = load<int>(cfg, "job_limit_per_collection_indexing_operation", 1000);
minimum_delay_time = load<int>(cfg, "minimum_delay_time", 1);
maximum_delay_time = load<int>(cfg, "maximum_delay_time", 30);

// string parameters
// string parameters

capture_parameter("index", index);
capture_parameter("url_template", urlTemplate);
capture_parameter("delay_parameters", delay_parameters);
capture_parameter("collection_test_flag", collection_test_flag);
} catch ( const exception& _e ) {
THROW( KEY_NOT_FOUND, fmt::format("[{}:{}] - [{}] [error_code=[{}], instance_name=[{}]",
__func__, __LINE__, _e.client_display_what(), _e.code(), _instance_name));
} catch ( const nlohmann::json::exception& _e ) {
irods::log( LOG_ERROR,
fmt::format("[{}:{}] in [file={}] - json exception occurred [error={}], [instance_name={}]",
__func__,__LINE__,__FILE__, _e.what(), _instance_name));
THROW( SYS_LIBRARY_ERROR, _e.what() );
} catch ( const std::exception& _e ) {
THROW( SYS_INTERNAL_ERR,
fmt::format("[{}:{}] in [file={}] - general exception occurred [error={}], [instance_name={}]",
__func__,__LINE__,__FILE__, _e.what(), _instance_name));
} catch ( ... ) {
THROW( SYS_UNKNOWN_ERROR,
fmt::format( "[{}:{}] in [file={}], [instance_name={}]",__func__,__LINE__,__FILE__,_instance_name));
}
capture_parameter("index", index);
capture_parameter("delay_parameters", delay_parameters);
capture_parameter("collection_test_flag", collection_test_flag);
}
catch (const exception& _e) {
THROW(KEY_NOT_FOUND,
fmt::format("[{}:{}] - [{}] [error_code=[{}], instance_name=[{}]",
__func__,
__LINE__,
_e.client_display_what(),
_e.code(),
_instance_name));
}
catch (const nlohmann::json::exception& _e) {
THROW(SYS_LIBRARY_ERROR,
fmt::format("[{}:{}] in [file={}] - json exception occurred [error={}], [instance_name={}]",
__func__,
__LINE__,
__FILE__,
_e.what(),
_instance_name));
}
catch (const std::exception& _e) {
THROW(SYS_INTERNAL_ERR,
fmt::format("[{}:{}] in [file={}] - general exception occurred [error={}], [instance_name={}]",
__func__,
__LINE__,
__FILE__,
_e.what(),
_instance_name));
}
catch (...) {
THROW(
SYS_UNKNOWN_ERROR,
fmt::format("[{}:{}] in [file={}], [instance_name={}]", __func__, __LINE__, __FILE__, _instance_name));
}
} // ctor configuration

} // ctor configuration
namespace policy
{
std::string compose_policy_name(const std::string& _prefix, const std::string& _technology)
{
return fmt::format("{}_{}", _prefix, _technology);
}
} // namespace policy

namespace policy {
std::string compose_policy_name(
const std::string& _prefix,
const std::string& _technology) {
return _prefix+"_"+_technology;
}
}
std::string operation_and_index_types_to_policy_name(const std::string& _operation_type,
const std::string& _index_type)
{
if (operation_type::index == _operation_type) {
if (index_type::full_text == _index_type) {
return policy::object::index;
}

std::string operation_and_index_types_to_policy_name(
const std::string& _operation_type,
const std::string& _index_type) {
if(operation_type::index == _operation_type) {
if(index_type::full_text == _index_type) {
return policy::object::index;
}
else if(index_type::metadata == _index_type) {
return policy::metadata::index;
}
}
else if(operation_type::purge == _operation_type) {
if(index_type::full_text == _index_type) {
return policy::object::purge;
}
else if(index_type::metadata == _index_type) {
return policy::metadata::purge;
}
} // else
if (index_type::metadata == _index_type) {
return policy::metadata::index;
}
}
else if (operation_type::purge == _operation_type) {
if (index_type::full_text == _index_type) {
return policy::object::purge;
}

THROW(
SYS_INVALID_INPUT_PARAM,
boost::format("operation [%s], index [%s]")
% _operation_type
% _index_type);
} // operation_and_index_types_to_policy_name
} // namespace indexing
} // namepsace irods
if (index_type::metadata == _index_type) {
return policy::metadata::purge;
}
}

THROW(SYS_INVALID_INPUT_PARAM, fmt::format("operation [{}], index [{}]", _operation_type, _index_type));
} // operation_and_index_types_to_policy_name
} // namespace irods::indexing
Loading
Loading