stackalytics/dashboard/memory_storage.py
Ilya Shakhat b7f19335f6 Implementation of blueprint stackalytics-core
* Data updater is implemented
* Completed implementation of commit processor
* Logging is added into commit processor and runtime storage
* Commit processor is fixed
* Domain-company map is inverted
* Extracted get update count into separate function
* Fixed regex that matches diff statistics (lines inserted, lines deleted and files changed)
* Implemented caching of unknown users
* Replaced dictionaries by sets for pids and branches
* Vcs is responsible for module and branches fields of commit record
* Added release tags support
* Implemented statistics by company
* Added config for releases
* Implemented front-end for companies details
* Implemented front-end for modules details
* Fixed metric switch
* Implemented timeline rendering
* Release selector is fixed
* Chdir is needed after cloning a new repo
* Company details screen is implemented
* Fixed invalid emails processing by Launchpad
* Fixed parsing of 0 files changed case
* Module details screen implemented
* Commit message is cleared and links are inserted
* Engineer details screen is implemented
* Fixed mapping from company to email for subdomains of 3rd level
* Fixed wrong user structure for users not found by LP
* Also coverage for commit processor
* Fixed company matching algorithm
* The company was not matched when user email had more domains than company's one
* Add option to enforce sync with default data
* Default data is added. Old confs removed
* Add *.local into gitignore

Scripts cleanup

Moved from pylibmc to python-memcached

Library pylibmc depends on libmemcached and doesn't work on CentOS (version conflict bw lib requirement and memcached).

Change-Id: I0cc61c6d344ba24442ec954635010b518c0efa95
2013-07-10 23:05:47 +04:00

101 lines
3.4 KiB
Python

from stackalytics.processor import user_utils
MEMORY_STORAGE_CACHED = 0
class MemoryStorage(object):
def __init__(self, records):
pass
class CachedMemoryStorage(MemoryStorage):
def __init__(self, records):
super(CachedMemoryStorage, self).__init__(records)
self.records = {}
self.company_index = {}
self.date_index = {}
self.module_index = {}
self.launchpad_id_index = {}
self.release_index = {}
self.dates = []
for record in records:
self.records[record['record_id']] = record
self.index(record)
self.dates = sorted(self.date_index)
self.company_name_mapping = dict((c.lower(), c)
for c in self.company_index.keys())
def index(self, record):
self._add_to_index(self.company_index, record, 'company_name')
self._add_to_index(self.module_index, record, 'module')
self._add_to_index(self.launchpad_id_index, record, 'launchpad_id')
self._add_to_index(self.release_index, record, 'release')
self._add_to_index(self.date_index, record, 'date')
record['week'] = user_utils.timestamp_to_week(record['date'])
record['loc'] = record['lines_added'] + record['lines_deleted']
def _add_to_index(self, record_index, record, key):
record_key = record[key]
if record_key in record_index:
record_index[record_key].add(record['record_id'])
else:
record_index[record_key] = set([record['record_id']])
def _get_record_ids_from_index(self, items, index):
record_ids = set()
for item in items:
if item not in index:
raise Exception('Parameter %s not valid' % item)
record_ids |= index[item]
return record_ids
def get_record_ids_by_modules(self, modules):
return self._get_record_ids_from_index(modules, self.module_index)
def get_record_ids_by_companies(self, companies):
return self._get_record_ids_from_index(
map(self._get_company_name, companies),
self.company_index)
def get_record_ids_by_launchpad_ids(self, launchpad_ids):
return self._get_record_ids_from_index(launchpad_ids,
self.launchpad_id_index)
def get_record_ids_by_releases(self, releases):
return self._get_record_ids_from_index(releases, self.release_index)
def get_record_ids(self):
return set(self.records.keys())
def get_records(self, record_ids):
for i in record_ids:
yield self.records[i]
def _get_company_name(self, company_name):
normalized = company_name.lower()
if normalized not in self.company_name_mapping:
raise Exception('Unknown company name %s' % company_name)
return self.company_name_mapping[normalized]
def get_companies(self):
return self.company_index.keys()
def get_modules(self):
return self.module_index.keys()
def get_launchpad_ids(self):
return self.launchpad_id_index.keys()
class MemoryStorageFactory(object):
@staticmethod
def get_storage(memory_storage_type, records):
if memory_storage_type == MEMORY_STORAGE_CACHED:
return CachedMemoryStorage(records)
else:
raise Exception('Unknown memory storage type')