cic cache build

apps/cic-cache/cic_cache/__init__.py

@@ -0,0 +1 @@
+from .cache import BloomCache

apps/cic-cache/cic_cache/api.py

@@ -0,0 +1,73 @@
+"""API for cic-cache celery tasks
+
+.. moduleauthor:: Louis Holbrook <dev@holbrook.no>
+
+"""
+# standard imports
+import logging
+
+# third-party imports 
+import celery
+
+
+app = celery.current_app
+
+logg = logging.getLogger(__name__)
+
+
+class Api:
+    """Creates task chains to perform well-known CIC operations.
+
+    Each method that sends tasks returns details about the root task. The root task uuid can be provided in the callback, to enable to caller to correlate the result with individual calls. It can also be used to independently poll the completion of a task chain.
+
+    :param callback_param: Static value to pass to callback
+    :type callback_param: str
+    :param callback_task: Callback task that executes callback_param call. (Must be included by the celery worker)
+    :type callback_task: string
+    :param queue: Name of worker queue to submit tasks to
+    :type queue: str
+    """
+    def __init__(self, queue='cic-cache', callback_param=None, callback_task='cic_cache.callbacks.noop.noop', callback_queue=None):
+        self.callback_param = callback_param
+        self.callback_task = callback_task
+        self.queue = queue
+        logg.info('api using queue {}'.format(self.queue))
+        self.callback_success = None
+        self.callback_error = None
+        if callback_queue == None:
+            callback_queue=self.queue
+
+        if callback_param != None:
+            self.callback_success = celery.signature(
+                    callback_task,
+                    [
+                        callback_param,
+                        0,
+                        ],
+                    queue=callback_queue,
+                    )
+            self.callback_error = celery.signature(
+                    callback_task,
+                    [
+                        callback_param,
+                        1,
+                        ],
+                    queue=callback_queue,
+                    )       
+
+    def list(self, offset, limit, address=None):
+        s = celery.signature(
+        'cic_cache.tasks.tx.tx_filter',
+        [
+            0,
+            100,
+            address,
+            ],
+            queue=None
+        )
+        if self.callback_param != None:
+            s.link(self.callback_success).on_error(self.callback_error)
+
+        t = s.apply_async()
+
+        return t

apps/cic-cache/cic_cache/cache.py

@@ -0,0 +1,89 @@
+# standard imports
+import logging
+
+# third-party imports
+import moolb
+
+# local imports
+from cic_cache.db import list_transactions_mined
+from cic_cache.db import list_transactions_account_mined
+
+logg = logging.getLogger()
+
+
+class BloomCache:
+
+    def __init__(self, session):
+        self.session = session
+
+
+    @staticmethod
+    def __get_filter_size(n):
+        n = 8192 * 8
+        logg.warning('filter size hardcoded to {}'.format(n))
+        return n
+
+
+    def load_transactions(self, offset, limit):
+        """Retrieves a list of transactions from cache and creates a bloom filter pointing to blocks and transactions.
+
+        Block and transaction numbers are serialized as 32-bit big-endian numbers. The input to the second bloom filter is the concatenation of the serialized block number and transaction index.
+
+        For example, if the block number is 13 and the transaction index is 42, the input are:
+
+        block filter:       0x0d000000
+        block+tx filter:    0x0d0000002a0000000
+
+        :param offset: Offset in data set to return transactions from
+        :type offset: int
+        :param limit: Max number of transactions to retrieve
+        :type limit: int
+        :return: Lowest block, bloom filter for blocks, bloom filter for blocks|tx
+        :rtype: tuple
+        """
+        rows = list_transactions_mined(self.session, offset, limit) 
+
+        f_block = moolb.Bloom(BloomCache.__get_filter_size(limit), 3)
+        f_blocktx = moolb.Bloom(BloomCache.__get_filter_size(limit), 3)
+        highest_block = -1
+        lowest_block = -1
+        for r in rows:
+            if highest_block == -1:
+                highest_block = r[0]
+            lowest_block = r[0]
+            block = r[0].to_bytes(4, byteorder='big')
+            tx = r[1].to_bytes(4, byteorder='big')
+            f_block.add(block)
+            f_blocktx.add(block + tx)
+            logg.debug('added block {} tx {} lo {} hi {}'.format(r[0], r[1], lowest_block, highest_block))
+        return (lowest_block, highest_block, f_block.to_bytes(), f_blocktx.to_bytes(),)
+
+
+    def load_transactions_account(self, address, offset, limit):
+        """Same as load_transactions(...), but only retrieves transactions where the specified account address is sender or recipient.
+
+        :param address: Address to retrieve transactions for.
+        :type address: str, 0x-hex
+        :param offset: Offset in data set to return transactions from
+        :type offset: int
+        :param limit: Max number of transactions to retrieve
+        :type limit: int
+        :return: Lowest block, bloom filter for blocks, bloom filter for blocks|tx
+        :rtype: tuple
+        """
+        rows = list_transactions_account_mined(self.session, address, offset, limit) 
+
+        f_block = moolb.Bloom(BloomCache.__get_filter_size(limit), 3)
+        f_blocktx = moolb.Bloom(BloomCache.__get_filter_size(limit), 3)
+        highest_block = -1;
+        lowest_block = -1;
+        for r in rows:
+            if highest_block == -1:
+                highest_block = r[0]
+            lowest_block = r[0]
+            block = r[0].to_bytes(4, byteorder='big')
+            tx = r[1].to_bytes(4, byteorder='big')
+            f_block.add(block)
+            f_blocktx.add(block + tx)
+            logg.debug('added block {} tx {} lo {} hi {}'.format(r[0], r[1], lowest_block, highest_block))
+        return (lowest_block, highest_block, f_block.to_bytes(), f_blocktx.to_bytes(),)

apps/cic-cache/cic_cache/db/__init__.py

@@ -0,0 +1,35 @@
+# standard imports
+import logging
+
+# local imports
+from .list import list_transactions_mined
+from .list import list_transactions_account_mined
+from .list import add_transaction
+
+logg = logging.getLogger()
+
+
+def dsn_from_config(config):
+    scheme = config.get('DATABASE_ENGINE')
+    if config.get('DATABASE_DRIVER') != None:
+        scheme += '+{}'.format(config.get('DATABASE_DRIVER'))
+
+    dsn = ''
+    if config.get('DATABASE_ENGINE') == 'sqlite':
+        dsn = '{}:///{}'.format(
+                scheme,
+                config.get('DATABASE_NAME'),    
+            )
+
+    else:
+        dsn = '{}://{}:{}@{}:{}/{}'.format(
+                scheme,
+                config.get('DATABASE_USER'),
+                config.get('DATABASE_PASSWORD'),
+                config.get('DATABASE_HOST'),
+                config.get('DATABASE_PORT'),
+                config.get('DATABASE_NAME'),    
+            )
+    logg.debug('parsed dsn from config: {}'.format(dsn))
+    return dsn
+

apps/cic-cache/cic_cache/db/list.py

@@ -0,0 +1,79 @@
+# standard imports
+import logging
+import datetime
+
+# third-party imports
+from cic_cache.db.models.base import SessionBase
+
+logg = logging.getLogger()
+
+
+def list_transactions_mined(
+        session,
+        offset,
+        limit,
+        ):
+    """Executes db query to return all confirmed transactions according to the specified offset and limit.
+
+    :param offset: Offset in data set to return transactions from
+    :type offset: int
+    :param limit: Max number of transactions to retrieve
+    :type limit: int
+    :result: Result set
+    :rtype: SQLAlchemy.ResultProxy
+    """
+    s = "SELECT block_number, tx_index FROM tx ORDER BY block_number DESC, tx_index DESC LIMIT {} OFFSET {}".format(limit, offset)
+    r = session.execute(s)
+    return r
+
+
+def list_transactions_account_mined(
+        session,
+        address,
+        offset,
+        limit,
+        ):
+    """Same as list_transactions_mined(...), but only retrieves transaction where the specified account address is sender or recipient.
+
+    :param address: Address to retrieve transactions for.
+    :type address: str, 0x-hex
+    :param offset: Offset in data set to return transactions from
+    :type offset: int
+    :param limit: Max number of transactions to retrieve
+    :type limit: int
+    :result: Result set
+    :rtype: SQLAlchemy.ResultProxy
+    """
+    s = "SELECT block_number, tx_index FROM tx WHERE sender = '{}' OR recipient = '{}' ORDER BY block_number DESC, tx_index DESC LIMIT {} OFFSET {}".format(address, address, limit, offset)
+    r = session.execute(s)
+    return r
+
+
+def add_transaction(
+        session, tx_hash,
+        block_number,
+        tx_index,
+        sender,
+        receiver,
+        source_token,
+        destination_token,
+        from_value,
+        to_value,
+        success,
+        timestamp,
+        ):
+    date_block = datetime.datetime.fromtimestamp(timestamp)
+    s = "INSERT INTO tx (tx_hash, block_number, tx_index, sender, recipient, source_token, destination_token, from_value, to_value, success, date_block) VALUES ('{}', {}, {}, '{}', '{}', '{}', '{}', {}, {}, {}, '{}')".format(
+            tx_hash,
+            block_number,
+            tx_index,
+            sender,
+            receiver,
+            source_token,
+            destination_token,
+            from_value,
+            to_value,
+            success,
+            date_block,
+            )
+    session.execute(s)

apps/cic-cache/cic_cache/db/migrations/default/README

@@ -0,0 +1 @@
+Generic single-database configuration.

apps/cic-cache/cic_cache/db/migrations/default/alembic.ini

@@ -0,0 +1,86 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = .
+
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# timezone to use when rendering the date
+# within the migration file as well as the filename.
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; this defaults
+# to ./versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path
+# version_locations = %(here)s/bar %(here)s/bat ./versions
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+#sqlalchemy.url = driver://user:pass@localhost/dbname
+sqlalchemy.url = postgresql+psycopg2://postgres@localhost:5432/cic-cache
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks=black
+# black.type=console_scripts
+# black.entrypoint=black
+# black.options=-l 79
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

apps/cic-cache/cic_cache/db/migrations/default/env.py

@@ -0,0 +1,77 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = None
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline():
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

apps/cic-cache/cic_cache/db/migrations/default/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

apps/cic-cache/cic_cache/db/migrations/default/versions/63b629f14a85_.py

@@ -0,0 +1,52 @@
+"""Base tables
+
+Revision ID: 63b629f14a85
+Revises: 
+Create Date: 2020-12-04 08:16:00.412189
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '63b629f14a85'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.create_table(
+            'tx',
+            sa.Column('id', sa.Integer, primary_key=True),
+            sa.Column('date_registered', sa.DateTime, nullable=False, server_default=sa.func.current_timestamp()),
+            sa.Column('block_number', sa.Integer, nullable=False),
+            sa.Column('tx_index', sa.Integer, nullable=False),
+            sa.Column('tx_hash', sa.String(66), nullable=False),
+            sa.Column('sender', sa.String(42), nullable=False),
+            sa.Column('recipient', sa.String(42), nullable=False),
+            sa.Column('source_token', sa.String(42), nullable=False),
+            sa.Column('destination_token', sa.String(42), nullable=False),
+            sa.Column('success', sa.Boolean, nullable=False),
+            sa.Column('from_value', sa.BIGINT(), nullable=False),
+            sa.Column('to_value', sa.BIGINT(), nullable=False),
+            sa.Column('date_block', sa.DateTime, nullable=False),
+            )
+    op.create_table(
+            'tx_sync',
+            sa.Column('id', sa.Integer, primary_key=True),
+            sa.Column('tx', sa.String(66), nullable=False),
+            )
+
+    op.execute("INSERT INTO tx_sync (tx) VALUES('0x0000000000000000000000000000000000000000000000000000000000000000');")
+
+    op.create_index('sender_token_idx', 'tx', ['sender', 'source_token'])
+    op.create_index('recipient_token_idx', 'tx', ['recipient', 'destination_token'])
+            
+
+def downgrade():
+    op.drop_index('recipient_token_idx')
+    op.drop_index('sender_token_idx')
+    op.drop_table('tx_sync')
+    op.drop_table('tx')

apps/cic-cache/cic_cache/db/models/base.py

@@ -0,0 +1,102 @@
+# stanard imports
+import logging
+
+# third-party imports
+from sqlalchemy import Column, Integer
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+
+logg = logging.getLogger()
+
+Model = declarative_base(name='Model')
+
+
+class SessionBase(Model):
+    """The base object for all SQLAlchemy enabled models. All other models must extend this.
+    """
+    __abstract__ = True
+ 
+    id = Column(Integer, primary_key=True)
+
+    engine = None
+    """Database connection engine of the running aplication"""
+    sessionmaker = None
+    """Factory object responsible for creating sessions from the  connection pool"""
+    transactional = True
+    """Whether the database backend supports query transactions. Should be explicitly set by initialization code"""
+    poolable = True
+    """Whether the database backend supports connection pools. Should be explicitly set by initialization code"""
+    procedural = True
+    """Whether the database backend supports stored procedures"""
+    localsessions = {}
+    """Contains dictionary of sessions initiated by db model components"""
+
+
+    @staticmethod
+    def create_session():
+        """Creates a new database session.
+        """
+        return SessionBase.sessionmaker()
+
+
+    @staticmethod
+    def _set_engine(engine):
+        """Sets the database engine static property
+        """
+        SessionBase.engine = engine
+        SessionBase.sessionmaker = sessionmaker(bind=SessionBase.engine)
+
+
+    @staticmethod
+    def connect(dsn, debug=False):
+        """Create new database connection engine and connect to database backend.
+
+        :param dsn: DSN string defining connection.
+        :type dsn: str
+        """
+        e = None
+        if SessionBase.poolable:
+            e = create_engine(
+                    dsn,
+                    max_overflow=50,
+                    pool_pre_ping=True,
+                    pool_size=20,
+                    pool_recycle=10,
+                    echo=debug,
+                )
+        else:
+            e = create_engine(
+                    dsn,
+                    echo=debug,
+                    )
+
+        SessionBase._set_engine(e)
+
+
+    @staticmethod
+    def disconnect():
+        """Disconnect from database and free resources.
+        """
+        SessionBase.engine.dispose()
+        SessionBase.engine = None
+
+
+    @staticmethod
+    def bind_session(session=None):
+        localsession = session
+        if localsession == None:
+            localsession = SessionBase.create_session()
+            localsession_key = str(id(localsession))
+            logg.debug('creating new session {}'.format(localsession_key))
+            SessionBase.localsessions[localsession_key] = localsession
+        return localsession
+
+
+    @staticmethod
+    def release_session(session=None):
+        session_key = str(id(session))
+        if SessionBase.localsessions.get(session_key) != None:
+            logg.debug('destroying session {}'.format(session_key))
+            session.commit()
+            session.close()

apps/cic-cache/cic_cache/runnable/server.py

@@ -0,0 +1,141 @@
+# standard imports
+import os
+import re
+import logging
+import argparse
+import json
+import base64
+
+# third-party imports
+import confini
+
+# local imports
+from cic_cache import BloomCache
+from cic_cache.db import dsn_from_config
+from cic_cache.db.models.base import SessionBase
+
+logging.basicConfig(level=logging.WARNING)
+logg = logging.getLogger()
+
+rootdir = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
+dbdir = os.path.join(rootdir, 'cic_cache', 'db')
+migrationsdir = os.path.join(dbdir, 'migrations')
+
+config_dir = os.path.join('/usr/local/etc/cic-cache')
+
+argparser = argparse.ArgumentParser()
+argparser.add_argument('-c', type=str, default=config_dir, help='config file')
+argparser.add_argument('--env-prefix', default=os.environ.get('CONFINI_ENV_PREFIX'), dest='env_prefix', type=str, help='environment prefix for variables to overwrite configuration')
+argparser.add_argument('-v', action='store_true', help='be verbose')
+argparser.add_argument('-vv', action='store_true', help='be more verbose')
+args = argparser.parse_args()
+
+if args.vv:
+    logging.getLogger().setLevel(logging.DEBUG)
+elif args.v:
+    logging.getLogger().setLevel(logging.INFO)
+
+config = confini.Config(args.c, args.env_prefix)
+config.process()
+config.censor('PASSWORD', 'DATABASE')
+config.censor('PASSWORD', 'SSL')
+logg.debug('config:\n{}'.format(config))
+
+dsn = dsn_from_config(config)
+SessionBase.connect(dsn, config.true('DATABASE_DEBUG'))
+
+re_transactions_all_bloom = r'/tx/(\d+)?/?(\d+)/?'
+re_transactions_account_bloom = r'/tx/user/((0x)?[a-fA-F0-9]+)/?(\d+)?/?(\d+)/?'
+
+DEFAULT_LIMIT = 100
+
+
+def process_transactions_account_bloom(session, env):
+    r = re.match(re_transactions_account_bloom, env.get('PATH_INFO'))
+    if not r:
+        return None
+
+    address = r[1]
+    if r[2] == None:
+        address = '0x' + address
+    offset = DEFAULT_LIMIT
+    if r.lastindex > 2:
+        offset = r[3]
+    limit = 0
+    if r.lastindex > 3:
+        limit = r[4]
+
+    c = BloomCache(session)
+    (lowest_block, highest_block, bloom_filter_block, bloom_filter_tx) = c.load_transactions_account(address, offset, limit)
+
+    o = {
+        'alg': 'sha256',
+        'low': lowest_block,
+        'high': highest_block,
+        'block_filter': base64.b64encode(bloom_filter_block).decode('utf-8'),
+        'blocktx_filter': base64.b64encode(bloom_filter_tx).decode('utf-8'),
+        'filter_rounds': 3,
+            }
+
+    j = json.dumps(o)
+
+    return ('application/json', j.encode('utf-8'),)
+
+
+def process_transactions_all_bloom(session, env):
+    r = re.match(re_transactions_all_bloom, env.get('PATH_INFO'))
+    if not r:
+        return None
+
+    offset = DEFAULT_LIMIT
+    if r.lastindex > 0:
+        offset = r[1]
+    limit = 0
+    if r.lastindex > 1:
+        limit = r[2]
+
+    c = BloomCache(session)
+    (lowest_block, highest_block, bloom_filter_block, bloom_filter_tx) = c.load_transactions(offset, limit)
+
+    o = {
+        'alg': 'sha256',
+        'low': lowest_block,
+        'high': highest_block,
+        'block_filter': base64.b64encode(bloom_filter_block).decode('utf-8'),
+        'blocktx_filter': base64.b64encode(bloom_filter_tx).decode('utf-8'),
+        'filter_rounds': 3,
+            }
+
+    j = json.dumps(o)
+
+    return ('application/json', j.encode('utf-8'),)
+
+
+# uwsgi application
+def application(env, start_response):
+
+    headers = []
+    content = b''
+
+    session = SessionBase.create_session()
+    for handler in [
+            process_transactions_all_bloom,
+            process_transactions_account_bloom,
+            ]:
+        r = handler(session, env)
+        if r != None:
+            (mime_type, content) = r
+            break
+    session.close()
+
+    headers.append(('Content-Length', str(len(content))),)
+    headers.append(('Access-Control-Allow-Origin', '*',));
+
+    if len(content) == 0:
+        headers.append(('Content-Type', 'text/plain, charset=UTF-8',))
+        start_response('404 Looked everywhere, sorry', headers)
+    else:
+        headers.append(('Content-Type', mime_type,))
+        start_response('200 OK', headers)
+
+    return [content]

apps/cic-cache/cic_cache/runnable/tasker.py

@@ -0,0 +1,98 @@
+# standard imports
+import logging
+import os
+import sys
+import argparse
+
+# third-party imports
+import celery
+import confini
+
+# local imports
+from cic_cache.db import dsn_from_config
+from cic_cache.db.models.base import SessionBase
+from cic_cache.tasks.tx import *
+
+logging.basicConfig(level=logging.WARNING)
+logg = logging.getLogger()
+
+config_dir = os.path.join('/usr/local/etc/cic-cache')
+
+
+argparser = argparse.ArgumentParser()
+argparser.add_argument('-c', type=str, default=config_dir, help='config file')
+argparser.add_argument('-q', type=str, default='cic-cache', help='queue name for worker tasks')
+argparser.add_argument('--env-prefix', default=os.environ.get('CONFINI_ENV_PREFIX'), dest='env_prefix', type=str, help='environment prefix for variables to overwrite configuration')
+argparser.add_argument('-v', action='store_true', help='be verbose')
+argparser.add_argument('-vv', action='store_true', help='be more verbose')
+
+args = argparser.parse_args()
+
+if args.vv:
+    logging.getLogger().setLevel(logging.DEBUG)
+elif args.v:
+    logging.getLogger().setLevel(logging.INFO)
+
+config = confini.Config(args.c, args.env_prefix)
+config.process()
+
+# connect to database
+dsn = dsn_from_config(config)
+SessionBase.connect(dsn)
+
+# verify database connection with minimal sanity query
+#session = SessionBase.create_session()
+#session.execute('select version_num from alembic_version')
+#session.close()
+
+# set up celery
+current_app = celery.Celery(__name__)
+
+broker = config.get('CELERY_BROKER_URL')
+if broker[:4] == 'file':
+    bq = tempfile.mkdtemp()
+    bp = tempfile.mkdtemp()
+    current_app.conf.update({
+            'broker_url': broker,
+            'broker_transport_options': {
+                'data_folder_in': bq,
+                'data_folder_out': bq,
+                'data_folder_processed': bp,
+            },
+            },
+            )
+    logg.warning('celery broker dirs queue i/o {} processed {}, will NOT be deleted on shutdown'.format(bq, bp))
+else:
+    current_app.conf.update({
+        'broker_url': broker,
+        })
+
+result = config.get('CELERY_RESULT_URL')
+if result[:4] == 'file':
+    rq = tempfile.mkdtemp()
+    current_app.conf.update({
+        'result_backend': 'file://{}'.format(rq),
+        })
+    logg.warning('celery backend store dir {} created, will NOT be deleted on shutdown'.format(rq))
+else:
+    current_app.conf.update({
+        'result_backend': result,
+        })
+
+
+def main():
+    argv = ['worker']
+    if args.vv:
+        argv.append('--loglevel=DEBUG')
+    elif args.v:
+        argv.append('--loglevel=INFO')
+    argv.append('-Q')
+    argv.append(args.q)
+    argv.append('-n')
+    argv.append(args.q)
+
+    current_app.worker_main(argv)
+
+
+if __name__ == '__main__':
+    main()

apps/cic-cache/cic_cache/runnable/tracker.py

@@ -0,0 +1,339 @@
+# standard imports
+import sys
+import os
+import argparse
+import logging
+import time
+import enum
+import re
+
+# third-party imports
+import confini
+from cic_registry import CICRegistry
+from cic_registry.chain import (
+        ChainRegistry,
+        ChainSpec,
+        )
+#from cic_registry.bancor import BancorRegistryClient
+from cic_registry.token import Token
+from cic_registry.error import (
+        UnknownContractError,
+        UnknownDeclarationError,
+        )
+from cic_registry.declaration import to_token_declaration
+from web3.exceptions import BlockNotFound, TransactionNotFound
+from websockets.exceptions import ConnectionClosedError
+from requests.exceptions import ConnectionError
+import web3
+from web3 import HTTPProvider, WebsocketProvider
+
+# local imports
+from cic_cache import db
+from cic_cache.db.models.base import SessionBase
+
+logging.basicConfig(level=logging.WARNING)
+logg = logging.getLogger()
+logging.getLogger('websockets.protocol').setLevel(logging.CRITICAL)
+logging.getLogger('urllib3').setLevel(logging.CRITICAL)
+logging.getLogger('web3.RequestManager').setLevel(logging.CRITICAL)
+logging.getLogger('web3.providers.WebsocketProvider').setLevel(logging.CRITICAL)
+logging.getLogger('web3.providers.HTTPProvider').setLevel(logging.CRITICAL)
+
+log_topics = {
+    'transfer': '0xddf252ad1be2c89b69c2b068fc378daa952ba7f163c4a11628f55a4df523b3ef',
+    'convert': '0x7154b38b5dd31bb3122436a96d4e09aba5b323ae1fd580025fab55074334c095',
+    'accountregistry_add': '0a3b0a4f4c6e53dce3dbcad5614cb2ba3a0fa7326d03c5d64b4fa2d565492737',
+    }
+
+config_dir = os.path.join('/usr/local/etc/cic-cache')
+
+argparser = argparse.ArgumentParser(description='daemon that monitors transactions in new blocks')
+argparser.add_argument('-c', type=str, default=config_dir, help='config root to use')
+argparser.add_argument('-i', '--chain-spec', type=str, dest='i', help='chain spec')
+argparser.add_argument('--trust-address', default=[], type=str, dest='trust_address', action='append', help='Set address as trust')
+argparser.add_argument('--env-prefix', default=os.environ.get('CONFINI_ENV_PREFIX'), dest='env_prefix', type=str, help='environment prefix for variables to overwrite configuration')
+argparser.add_argument('--abi-dir', dest='abi_dir', type=str, help='Directory containing bytecode and abi')
+argparser.add_argument('-v', help='be verbose', action='store_true')
+argparser.add_argument('-vv', help='be more verbose', action='store_true')
+args = argparser.parse_args(sys.argv[1:])
+
+config_dir = os.path.join(args.c)
+os.makedirs(config_dir, 0o777, True)
+
+
+if args.v == True:
+    logging.getLogger().setLevel(logging.INFO)
+elif args.vv == True:
+    logging.getLogger().setLevel(logging.DEBUG)
+
+config = confini.Config(config_dir, args.env_prefix)
+config.process()
+args_override = {
+        'ETH_ABI_DIR': getattr(args, 'abi_dir'),
+        'CIC_TRUST_ADDRESS': ",".join(getattr(args, 'trust_address', [])),
+        }
+config.dict_override(args_override, 'cli flag')
+config.censor('PASSWORD', 'DATABASE')
+config.censor('PASSWORD', 'SSL')
+logg.debug('config loaded from {}:\n{}'.format(config_dir, config))
+
+# connect to database
+dsn = db.dsn_from_config(config)
+SessionBase.connect(dsn)
+
+
+re_websocket = re.compile('^wss?://')
+re_http = re.compile('^https?://')
+blockchain_provider = config.get('ETH_PROVIDER')
+if re.match(re_websocket, blockchain_provider) != None:
+    blockchain_provider = WebsocketProvider(blockchain_provider)
+elif re.match(re_http, blockchain_provider) != None:
+    blockchain_provider = HTTPProvider(blockchain_provider)
+else:
+    raise ValueError('unknown provider url {}'.format(blockchain_provider))
+
+def web3_constructor():
+    w3 = web3.Web3(blockchain_provider)
+    return (blockchain_provider, w3)
+
+
+class RunStateEnum(enum.IntEnum):
+    INIT = 0
+    RUN = 1
+    TERMINATE = 9
+
+
+def rubberstamp(src):
+    return True
+
+
+class Tracker:
+
+    def __init__(self, chain_spec, trusts=[]):
+        self.block_height = 0
+        self.tx_height = 0
+        self.state = RunStateEnum.INIT
+        self.declarator_cache = {}
+        self.convert_enabled = False
+        self.trusts = trusts
+        self.chain_spec = chain_spec
+        self.declarator = CICRegistry.get_contract(chain_spec, 'AddressDeclarator', 'Declarator')
+
+
+    def __process_tx(self, w3, session, t, r, l, b):
+        token_value = int(l.data, 16)
+        token_sender = l.topics[1][-20:].hex()
+        token_recipient = l.topics[2][-20:].hex()
+
+        #ts = ContractRegistry.get_address(t.address)
+        ts = CICRegistry.get_address(self.chain_spec, t.address())
+        logg.info('add token transfer {} value {} from {} to {}'.format(
+            ts.symbol(),
+            token_value,
+            token_sender,
+            token_recipient,
+            )
+            )
+
+        db.add_transaction(
+                session,
+                r.transactionHash.hex(),
+                r.blockNumber,
+                r.transactionIndex,
+                w3.toChecksumAddress(token_sender),
+                w3.toChecksumAddress(token_recipient),
+                t.address(),
+                t.address(),
+                token_value,
+                token_value,
+                r.status == 1,
+                b.timestamp,
+                )
+        session.flush()
+
+
+    # TODO: simplify/ split up and/or comment, function is too long
+    def __process_convert(self, w3, session, t, r, l, b):
+        logg.warning('conversions are deactivated')
+        return
+#        token_source = l.topics[2][-20:].hex()
+#        token_source = w3.toChecksumAddress(token_source)
+#        token_destination = l.topics[3][-20:].hex()
+#        token_destination = w3.toChecksumAddress(token_destination)
+#        data_noox = l.data[2:]
+#        d = data_noox[:64]
+#        token_from_value = int(d, 16)
+#        d = data_noox[64:128]
+#        token_to_value = int(d, 16)
+#        token_trader = '0x' + data_noox[192-40:]
+#
+#        #ts = ContractRegistry.get_address(token_source)
+#        ts = CICRegistry.get_address(CICRegistry.bancor_chain_spec, t.address())
+#        #if ts == None:
+#        #    ts = ContractRegistry.reserves[token_source]
+#        td = ContractRegistry.get_address(token_destination)
+#        #if td == None:
+#        #    td = ContractRegistry.reserves[token_source]
+#        logg.info('add token convert {} -> {} value {} -> {} trader {}'.format(
+#            ts.symbol(),
+#            td.symbol(),
+#            token_from_value,
+#            token_to_value,
+#            token_trader,
+#            )
+#            )
+#
+#        db.add_transaction(
+#                session,
+#                r.transactionHash.hex(),
+#                r.blockNumber,
+#                r.transactionIndex,
+#                w3.toChecksumAddress(token_trader),
+#                w3.toChecksumAddress(token_trader),
+#                token_source,
+#                token_destination,
+#                r.status == 1,
+#                b.timestamp,
+#                )
+#        session.flush()
+
+
+    def check_token(self, address):
+            t = None
+            try:
+                t = CICRegistry.get_address(CICRegistry.default_chain_spec, address)
+                return t
+            except UnknownContractError:
+                logg.debug('contract {} not in registry'.format(address))
+
+            # If nothing was returned, we look up the token in the declarator
+            for trust in self.trusts:
+                logg.debug('look up declaration for contract {} with trust {}'.format(address, trust))
+                fn = self.declarator.function('declaration')
+                # TODO: cache trust in LRUcache
+                declaration_array = fn(trust, address).call()
+                try:
+                    declaration = to_token_declaration(trust, address, declaration_array, [rubberstamp])
+                    logg.debug('found declaration for token {} from trust address {}'.format(address, trust))
+                except UnknownDeclarationError:
+                    continue
+               
+                try:
+                    c = w3.eth.contract(abi=CICRegistry.abi('ERC20'), address=address)
+                    t = CICRegistry.add_token(self.chain_spec, c)
+                    break
+                except ValueError:
+                    logg.error('declaration for {} validates as token, but location is not ERC20 compatible'.format(address))
+
+            return t
+
+
+    # TODO use input data instead of logs
+    def process(self, w3, session, block):
+        #self.refresh_registry(w3)
+        tx_count = w3.eth.getBlockTransactionCount(block.hash)
+        b = w3.eth.getBlock(block.hash)
+        for i in range(self.tx_height, tx_count):
+            tx = w3.eth.getTransactionByBlock(block.hash, i)
+            if tx.to == None:
+                logg.debug('block {} tx {} is contract creation tx, skipping'.format(block.number, i))
+                continue
+            if len(w3.eth.getCode(tx.to)) == 0:
+                logg.debug('block {} tx {} not a contract tx, skipping'.format(block.number, i))
+                continue
+
+            t = self.check_token(tx.to)
+            if t != None and isinstance(t, Token):
+                r = w3.eth.getTransactionReceipt(tx.hash)
+                for l in r.logs:
+                    logg.debug('block {} tx {} {} token log {} {}'.format(block.number, i, tx.hash.hex(), l.logIndex, l.topics[0].hex()))
+                    if l.topics[0].hex() == log_topics['transfer']:
+                        self.__process_tx(w3, session, t, r, l, b)
+
+            # TODO: cache contracts in LRUcache
+            elif self.convert_enabled and tx.to == CICRegistry.get_contract(CICRegistry.default_chain_spec, 'Converter').address:
+                r = w3.eth.getTransactionReceipt(tx.hash)
+                for l in r.logs:
+                    logg.info('block {} tx {} {} bancornetwork log {} {}'.format(block.number, i, tx.hash.hex(), l.logIndex, l.topics[0].hex()))
+                    if l.topics[0].hex() == log_topics['convert']:
+                        self.__process_convert(w3, session, t, r, l, b)
+            
+            session.execute("UPDATE tx_sync SET tx = '{}'".format(tx.hash.hex()))
+            session.commit()
+            self.tx_height += 1
+
+
+    def __get_next_retry(self, backoff=False):
+        return 1
+
+
+    def loop(self):
+        logg.info('starting at block {} tx index {}'.format(self.block_height, self.tx_height))
+        self.state = RunStateEnum.RUN
+        while self.state == RunStateEnum.RUN:
+            (provider, w3) = web3_constructor()
+            session = SessionBase.create_session()
+            try:
+                block = w3.eth.getBlock(self.block_height)
+                self.process(w3, session, block)
+                self.block_height += 1
+                self.tx_height = 0
+            except BlockNotFound as e:
+                logg.debug('no block {} yet, zZzZ...'.format(self.block_height))
+                time.sleep(self.__get_next_retry())
+            except ConnectionClosedError as e:
+                logg.info('connection gone, retrying')
+                time.sleep(self.__get_next_retry(True))
+            except OSError as e:
+                logg.error('cannot connect {}'.format(e))
+                time.sleep(self.__get_next_retry(True))
+            except Exception as e:
+                session.close()
+                raise(e)
+            session.close()
+
+
+    def load(self, w3):
+        session = SessionBase.create_session()
+        r = session.execute('SELECT tx FROM tx_sync').first()
+        if r != None:
+            if r[0] == '0x{0:0{1}X}'.format(0, 64):
+                logg.debug('last tx was zero-address, starting from scratch')
+                return
+            t = w3.eth.getTransaction(r[0])
+            
+            self.block_height = t.blockNumber
+            self.tx_height = t.transactionIndex+1
+            c = w3.eth.getBlockTransactionCount(t.blockHash.hex())
+            logg.debug('last tx processed {} index {} (max index {})'.format(t.blockNumber, t.transactionIndex, c-1))
+            if c == self.tx_height:
+                self.block_height += 1
+                self.tx_height = 0
+        session.close()
+
+(provider, w3) = web3_constructor()
+trust = config.get('CIC_TRUST_ADDRESS', []).split(",")
+chain_spec = args.i
+
+try:
+    w3.eth.chainId
+except Exception as e:
+    logg.exception(e)
+    sys.stderr.write('cannot connect to evm node\n')
+    sys.exit(1)
+
+def main():
+    chain_spec = ChainSpec.from_chain_str(config.get('CIC_CHAIN_SPEC'))
+
+    CICRegistry.init(w3, config.get('CIC_REGISTRY_ADDRESS'), chain_spec)
+    CICRegistry.add_path(config.get('ETH_ABI_DIR'))
+    chain_registry = ChainRegistry(chain_spec)
+    CICRegistry.add_chain_registry(chain_registry)
+
+    t = Tracker(chain_spec, trust) 
+    t.load(w3)
+    t.loop()
+    
+
+if __name__ == '__main__':
+    main()

apps/cic-cache/cic_cache/tasks/tx.py

@@ -0,0 +1,38 @@
+# third-party imports
+import celery
+
+# local imports
+from cic_cache.cache import BloomCache
+from cic_cache.db.models.base import SessionBase
+
+celery_app = celery.current_app
+
+
+@celery_app.task(bind=True)
+def tx_filter(self, offset, limit, address=None, encoding='hex'):
+    queue = self.request.delivery_info.get('routing_key')
+
+    session = SessionBase.create_session()
+
+    c = BloomCache(session)
+    b = None
+    if address == None:
+        (lowest_block, highest_block, bloom_filter_block, bloom_filter_tx) = c.load_transactions(offset, limit)
+    else:
+        (lowest_block, highest_block, bloom_filter_block, bloom_filter_tx) = c.load_transactions_account(address, offset, limit)
+
+    session.close()
+
+    o = {
+        'alg': 'sha256',
+        'low': lowest_block,
+        'high': highest_block,
+        'block_filter': bloom_filter_block.hex(), 
+        'blocktx_filter': bloom_filter_tx.hex(),
+        'filter_rounds': 3,
+            }
+
+    return o
+
+
+

apps/cic-cache/cic_cache/version.py

@@ -0,0 +1,18 @@
+import os
+import semver
+
+version = (
+        0,
+        2,
+        0,
+        'alpha.1',
+        )
+
+version_object = semver.VersionInfo(
+        major=version[0],
+        minor=version[1],
+        patch=version[2],
+        prerelease=version[3],
+        )
+
+version_string = str(version_object)