Summary: Move all the plugins python code into the main folder with the core code. Register file importing functions in the same main.py entrypoint as the data engine. Remove options relating to different entrypoints and code directories. The only remaining plugin-specific option in NSandbox is the import directory/mount, i.e. where files to be parsed are placed. Test Plan: this Reviewers: paulfitz Reviewed By: paulfitz Subscribers: dsagal Differential Revision: https://phab.getgrist.com/D2965pull/71/head
Alex Hall
3 years ago
parent
5b92a43849
commit
4d526da58f
@ -1 +0,0 @@
|
||||
__path__ = __import__('pkgutil').extend_path(__path__, __name__)
|
||||
@ -1,184 +0,0 @@
|
||||
from __future__ import absolute_import
|
||||
|
||||
import functools
|
||||
from collections import namedtuple
|
||||
from threading import RLock
|
||||
|
||||
_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"])
|
||||
|
||||
|
||||
@functools.wraps(functools.update_wrapper)
|
||||
def update_wrapper(wrapper,
|
||||
wrapped,
|
||||
assigned = functools.WRAPPER_ASSIGNMENTS,
|
||||
updated = functools.WRAPPER_UPDATES):
|
||||
"""
|
||||
Patch two bugs in functools.update_wrapper.
|
||||
"""
|
||||
# workaround for http://bugs.python.org/issue3445
|
||||
assigned = tuple(attr for attr in assigned if hasattr(wrapped, attr))
|
||||
wrapper = functools.update_wrapper(wrapper, wrapped, assigned, updated)
|
||||
# workaround for https://bugs.python.org/issue17482
|
||||
wrapper.__wrapped__ = wrapped
|
||||
return wrapper
|
||||
|
||||
|
||||
class _HashedSeq(list):
|
||||
__slots__ = 'hashvalue'
|
||||
|
||||
def __init__(self, tup, hash=hash):
|
||||
self[:] = tup
|
||||
self.hashvalue = hash(tup)
|
||||
|
||||
def __hash__(self):
|
||||
return self.hashvalue
|
||||
|
||||
|
||||
def _make_key(args, kwds, typed,
|
||||
kwd_mark=(object(),),
|
||||
fasttypes=set([int, str, frozenset, type(None)]),
|
||||
sorted=sorted, tuple=tuple, type=type, len=len):
|
||||
'Make a cache key from optionally typed positional and keyword arguments'
|
||||
key = args
|
||||
if kwds:
|
||||
sorted_items = sorted(kwds.items())
|
||||
key += kwd_mark
|
||||
for item in sorted_items:
|
||||
key += item
|
||||
if typed:
|
||||
key += tuple(type(v) for v in args)
|
||||
if kwds:
|
||||
key += tuple(type(v) for k, v in sorted_items)
|
||||
elif len(key) == 1 and type(key[0]) in fasttypes:
|
||||
return key[0]
|
||||
return _HashedSeq(key)
|
||||
|
||||
|
||||
def lru_cache(maxsize=100, typed=False):
|
||||
"""Least-recently-used cache decorator.
|
||||
|
||||
If *maxsize* is set to None, the LRU features are disabled and the cache
|
||||
can grow without bound.
|
||||
|
||||
If *typed* is True, arguments of different types will be cached separately.
|
||||
For example, f(3.0) and f(3) will be treated as distinct calls with
|
||||
distinct results.
|
||||
|
||||
Arguments to the cached function must be hashable.
|
||||
|
||||
View the cache statistics named tuple (hits, misses, maxsize, currsize) with
|
||||
f.cache_info(). Clear the cache and statistics with f.cache_clear().
|
||||
Access the underlying function with f.__wrapped__.
|
||||
|
||||
See: http://en.wikipedia.org/wiki/Cache_algorithms#Least_Recently_Used
|
||||
|
||||
"""
|
||||
|
||||
# Users should only access the lru_cache through its public API:
|
||||
# cache_info, cache_clear, and f.__wrapped__
|
||||
# The internals of the lru_cache are encapsulated for thread safety and
|
||||
# to allow the implementation to change (including a possible C version).
|
||||
|
||||
def decorating_function(user_function):
|
||||
|
||||
cache = dict()
|
||||
stats = [0, 0] # make statistics updateable non-locally
|
||||
HITS, MISSES = 0, 1 # names for the stats fields
|
||||
make_key = _make_key
|
||||
cache_get = cache.get # bound method to lookup key or return None
|
||||
_len = len # localize the global len() function
|
||||
lock = RLock() # because linkedlist updates aren't threadsafe
|
||||
root = [] # root of the circular doubly linked list
|
||||
root[:] = [root, root, None, None] # initialize by pointing to self
|
||||
nonlocal_root = [root] # make updateable non-locally
|
||||
PREV, NEXT, KEY, RESULT = 0, 1, 2, 3 # names for the link fields
|
||||
|
||||
if maxsize == 0:
|
||||
|
||||
def wrapper(*args, **kwds):
|
||||
# no caching, just do a statistics update after a successful call
|
||||
result = user_function(*args, **kwds)
|
||||
stats[MISSES] += 1
|
||||
return result
|
||||
|
||||
elif maxsize is None:
|
||||
|
||||
def wrapper(*args, **kwds):
|
||||
# simple caching without ordering or size limit
|
||||
key = make_key(args, kwds, typed)
|
||||
result = cache_get(key, root) # root used here as a unique not-found sentinel
|
||||
if result is not root:
|
||||
stats[HITS] += 1
|
||||
return result
|
||||
result = user_function(*args, **kwds)
|
||||
cache[key] = result
|
||||
stats[MISSES] += 1
|
||||
return result
|
||||
|
||||
else:
|
||||
|
||||
def wrapper(*args, **kwds):
|
||||
# size limited caching that tracks accesses by recency
|
||||
key = make_key(args, kwds, typed) if kwds or typed else args
|
||||
with lock:
|
||||
link = cache_get(key)
|
||||
if link is not None:
|
||||
# record recent use of the key by moving it to the front of the list
|
||||
root, = nonlocal_root
|
||||
link_prev, link_next, key, result = link
|
||||
link_prev[NEXT] = link_next
|
||||
link_next[PREV] = link_prev
|
||||
last = root[PREV]
|
||||
last[NEXT] = root[PREV] = link
|
||||
link[PREV] = last
|
||||
link[NEXT] = root
|
||||
stats[HITS] += 1
|
||||
return result
|
||||
result = user_function(*args, **kwds)
|
||||
with lock:
|
||||
root, = nonlocal_root
|
||||
if key in cache:
|
||||
# getting here means that this same key was added to the
|
||||
# cache while the lock was released. since the link
|
||||
# update is already done, we need only return the
|
||||
# computed result and update the count of misses.
|
||||
pass
|
||||
elif _len(cache) >= maxsize:
|
||||
# use the old root to store the new key and result
|
||||
oldroot = root
|
||||
oldroot[KEY] = key
|
||||
oldroot[RESULT] = result
|
||||
# empty the oldest link and make it the new root
|
||||
root = nonlocal_root[0] = oldroot[NEXT]
|
||||
oldkey = root[KEY]
|
||||
root[KEY] = root[RESULT] = None
|
||||
# now update the cache dictionary for the new links
|
||||
del cache[oldkey]
|
||||
cache[key] = oldroot
|
||||
else:
|
||||
# put result in a new link at the front of the list
|
||||
last = root[PREV]
|
||||
link = [last, root, key, result]
|
||||
last[NEXT] = root[PREV] = cache[key] = link
|
||||
stats[MISSES] += 1
|
||||
return result
|
||||
|
||||
def cache_info():
|
||||
"""Report cache statistics"""
|
||||
with lock:
|
||||
return _CacheInfo(stats[HITS], stats[MISSES], maxsize, len(cache))
|
||||
|
||||
def cache_clear():
|
||||
"""Clear the cache and cache statistics"""
|
||||
with lock:
|
||||
cache.clear()
|
||||
root = nonlocal_root[0]
|
||||
root[:] = [root, root, None, None]
|
||||
stats[:] = [0, 0]
|
||||
|
||||
wrapper.__wrapped__ = user_function
|
||||
wrapper.cache_info = cache_info
|
||||
wrapper.cache_clear = cache_clear
|
||||
return update_wrapper(wrapper, user_function)
|
||||
|
||||
return decorating_function
|
||||
@ -1,25 +0,0 @@
|
||||
import logging
|
||||
import sandbox
|
||||
|
||||
import import_csv
|
||||
import import_xls
|
||||
import import_json
|
||||
|
||||
def main():
|
||||
s = logging.StreamHandler()
|
||||
s.setFormatter(logging.Formatter(fmt='%(asctime)s.%(msecs)03d %(message)s',
|
||||
datefmt='%Y-%m-%d %H:%M:%S'))
|
||||
rootLogger = logging.getLogger()
|
||||
rootLogger.addHandler(s)
|
||||
rootLogger.setLevel(logging.INFO)
|
||||
|
||||
# Todo: Grist should expose a register method accepting arguments as
|
||||
# follow: register('csv_parser', 'canParse', can_parse)
|
||||
sandbox.register("csv_parser.parseFile", import_csv.parse_file_source)
|
||||
sandbox.register("xls_parser.parseFile", import_xls.import_file)
|
||||
sandbox.register("json_parser.parseFile", import_json.parse_file)
|
||||
|
||||
sandbox.run()
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@ -1,60 +0,0 @@
|
||||
"""This module loads a file_importer that implements the Grist import
|
||||
API, and calls its selected method passing argument received from
|
||||
PluginManager.sandboxImporter(). It returns an object formatted so
|
||||
that it can be used by Grist.
|
||||
|
||||
"""
|
||||
import sys
|
||||
import argparse
|
||||
import logging
|
||||
import imp
|
||||
import json
|
||||
import marshal
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
# Include /thirdparty into module search paths, in particular for messytables.
|
||||
# pylint: disable=wrong-import-position
|
||||
sys.path.append('/thirdparty')
|
||||
|
||||
def marshal_data(export_list):
|
||||
return marshal.dumps(export_list, 2)
|
||||
|
||||
def main():
|
||||
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('-d', '--debug', action='store_true',
|
||||
help="Print debug instead of producing normal binary output")
|
||||
parser.add_argument('-t', '--table',
|
||||
help="Suggested table name to use with CSV imports")
|
||||
parser.add_argument('-n', '--plugin-name', required=True,
|
||||
help="Name of a python module implementing the import API.")
|
||||
parser.add_argument('-p', '--plugin-path',
|
||||
help="Location of the module.")
|
||||
parser.add_argument('--action-options',
|
||||
help="Options to pass to the action. See API documentation.")
|
||||
parser.add_argument('action', help='Action to call',
|
||||
choices=['can_parse', 'parse_file'])
|
||||
parser.add_argument('input', help='File to convert')
|
||||
args = parser.parse_args()
|
||||
|
||||
s = logging.StreamHandler()
|
||||
s.setFormatter(logging.Formatter(fmt='%(asctime)s.%(msecs)03d %(message)s',
|
||||
datefmt='%Y-%m-%d %H:%M:%S'))
|
||||
rootLogger = logging.getLogger()
|
||||
rootLogger.addHandler(s)
|
||||
rootLogger.setLevel(logging.DEBUG if args.debug else logging.INFO)
|
||||
import_plugin = imp.load_compiled(
|
||||
args.plugin_name,
|
||||
args.plugin_path)
|
||||
options = {}
|
||||
if args.action_options:
|
||||
options = json.loads(args.action_options)
|
||||
parsed_data = getattr(import_plugin, args.action)(args.input, **options)
|
||||
marshalled_data = marshal_data(parsed_data)
|
||||
log.info("Marshalled data has %d bytes", len(marshalled_data))
|
||||
if not args.debug:
|
||||
sys.stdout.write(marshalled_data)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@ -0,0 +1,18 @@
|
||||
def register_import_parsers(sandbox):
|
||||
def parse_csv(file_source, options):
|
||||
from imports.import_csv import parse_file_source
|
||||
return parse_file_source(file_source, options)
|
||||
|
||||
sandbox.register("csv_parser.parseFile", parse_csv)
|
||||
|
||||
def parse_excel(file_source, parse_options):
|
||||
from imports.import_xls import import_file
|
||||
return import_file(file_source, parse_options)
|
||||
|
||||
sandbox.register("xls_parser.parseFile", parse_excel)
|
||||
|
||||
def parse_json(file_source, parse_options):
|
||||
from imports.import_json import parse_file
|
||||
return parse_file(file_source, parse_options)
|
||||
|
||||
sandbox.register("json_parser.parseFile", parse_json)
|
||||
@ -1,5 +1,5 @@
|
||||
import unittest
|
||||
from dateguess import guess, guess_bulk
|
||||
from imports.dateguess import guess, guess_bulk
|
||||
|
||||
|
||||
class TestGuesser(unittest.TestCase):
|
||||
@ -1,5 +1,5 @@
|
||||
from unittest import TestCase
|
||||
import import_json
|
||||
from imports import import_json
|
||||
|
||||
class TestImportJSON(TestCase):
|
||||
|
||||
Loading…
Reference in new issue