2020-12-10 12:36:46 +00:00
from typing import Optional , Union , Any , Dict , List
2017-03-21 01:06:29 +00:00
import shutil
2017-03-20 21:50:13 +00:00
from pathlib import Path
2020-06-21 19:35:01 +00:00
from wasabi import Printer , get_raw_input
💫 Replace ujson, msgpack and dill/pickle/cloudpickle with srsly (#3003)
Remove hacks and wrappers, keep code in sync across our libraries and move spaCy a few steps closer to only depending on packages with binary wheels 🎉
See here: https://github.com/explosion/srsly
Serialization is hard, especially across Python versions and multiple platforms. After dealing with many subtle bugs over the years (encodings, locales, large files) our libraries like spaCy and Prodigy have steadily grown a number of utility functions to wrap the multiple serialization formats we need to support (especially json, msgpack and pickle). These wrapping functions ended up duplicated across our codebases, so we wanted to put them in one place.
At the same time, we noticed that having a lot of small dependencies was making maintainence harder, and making installation slower. To solve this, we've made srsly standalone, by including the component packages directly within it. This way we can provide all the serialization utilities we need in a single binary wheel.
srsly currently includes forks of the following packages:
ujson
msgpack
msgpack-numpy
cloudpickle
* WIP: replace json/ujson with srsly
* Replace ujson in examples
Use regular json instead of srsly to make code easier to read and follow
* Update requirements
* Fix imports
* Fix typos
* Replace msgpack with srsly
* Fix warning
2018-12-03 00:28:22 +00:00
import srsly
2020-06-21 19:35:01 +00:00
import sys
2017-03-20 21:50:13 +00:00
2020-07-10 15:57:40 +00:00
from . _util import app , Arg , Opt
2020-06-21 19:35:01 +00:00
from . . schemas import validate , ModelMetaSchema
2017-03-20 21:50:13 +00:00
from . . import util
2017-05-07 21:25:29 +00:00
from . . import about
2017-03-20 21:50:13 +00:00
2020-06-21 11:44:00 +00:00
@app.command ( " package " )
2020-06-21 19:35:01 +00:00
def package_cli (
2020-01-01 12:15:46 +00:00
# fmt: off
2020-09-03 11:13:03 +00:00
input_dir : Path = Arg ( . . . , help = " Directory with pipeline data " , exists = True , file_okay = False ) ,
2020-06-21 19:35:01 +00:00
output_dir : Path = Arg ( . . . , help = " Output parent directory " , exists = True , file_okay = False ) ,
2020-12-10 12:36:46 +00:00
code_paths : Optional [ str ] = Opt ( None , " --code " , " -c " , help = " Comma-separated paths to Python file with additional code (registered functions) to be included in the package " ) ,
2020-06-27 18:36:08 +00:00
meta_path : Optional [ Path ] = Opt ( None , " --meta-path " , " --meta " , " -m " , help = " Path to meta.json " , exists = True , dir_okay = False ) ,
2020-06-21 22:57:28 +00:00
create_meta : bool = Opt ( False , " --create-meta " , " -c " , " -C " , help = " Create meta.json, even if one exists " ) ,
2020-09-11 09:38:28 +00:00
name : Optional [ str ] = Opt ( None , " --name " , " -n " , help = " Package name to override meta " ) ,
2020-06-27 18:36:08 +00:00
version : Optional [ str ] = Opt ( None , " --version " , " -v " , help = " Package version to override meta " ) ,
2020-07-27 14:52:23 +00:00
no_sdist : bool = Opt ( False , " --no-sdist " , " -NS " , help = " Don ' t build .tar.gz sdist, can be set if you want to run this step manually " ) ,
2020-09-03 11:13:03 +00:00
force : bool = Opt ( False , " --force " , " -f " , " -F " , help = " Force overwriting existing data in output directory " ) ,
2020-01-01 12:15:46 +00:00
# fmt: on
) :
2017-05-27 18:01:46 +00:00
"""
2020-09-03 11:13:03 +00:00
Generate an installable Python package for a pipeline . Includes binary data ,
2020-07-12 11:53:49 +00:00
meta and required installation files . A new directory will be created in the
2020-09-03 11:13:03 +00:00
specified output directory , and the data will be copied over . If
2020-07-12 11:53:49 +00:00
- - create - meta is set and a meta . json already exists in the output directory ,
the existing values will be used as the defaults in the command - line prompt .
After packaging , " python setup.py sdist " is run in the package directory ,
which will create a . tar . gz archive that can be installed via " pip install " .
2020-09-04 10:58:50 +00:00
2020-12-10 12:36:46 +00:00
If additional code files are provided ( e . g . Python files containing custom
registered functions like pipeline components ) , they are copied into the
package and imported in the __init__ . py .
2020-09-04 10:58:50 +00:00
DOCS : https : / / nightly . spacy . io / api / cli #package
2017-05-22 10:28:58 +00:00
"""
2020-12-10 12:36:46 +00:00
code_paths = (
[ Path ( p . strip ( ) ) for p in code_paths . split ( " , " ) ]
if code_paths is not None
else [ ]
)
2020-06-21 19:35:01 +00:00
package (
input_dir ,
output_dir ,
meta_path = meta_path ,
2020-12-10 12:36:46 +00:00
code_paths = code_paths ,
2020-09-11 09:38:28 +00:00
name = name ,
2020-06-27 18:36:08 +00:00
version = version ,
2020-06-21 19:35:01 +00:00
create_meta = create_meta ,
2020-07-27 14:52:23 +00:00
create_sdist = not no_sdist ,
2020-06-21 19:35:01 +00:00
force = force ,
silent = False ,
)
def package (
input_dir : Path ,
output_dir : Path ,
meta_path : Optional [ Path ] = None ,
2020-12-10 12:36:46 +00:00
code_paths : List [ Path ] = [ ] ,
2020-09-11 09:38:28 +00:00
name : Optional [ str ] = None ,
2020-06-27 18:36:08 +00:00
version : Optional [ str ] = None ,
2020-06-21 19:35:01 +00:00
create_meta : bool = False ,
2020-07-27 14:52:23 +00:00
create_sdist : bool = True ,
2020-06-21 19:35:01 +00:00
force : bool = False ,
silent : bool = True ,
) - > None :
msg = Printer ( no_print = silent , pretty = not silent )
2017-05-07 21:25:29 +00:00
input_path = util . ensure_path ( input_dir )
output_path = util . ensure_path ( output_dir )
2017-08-12 19:44:15 +00:00
meta_path = util . ensure_path ( meta_path )
2017-05-07 21:25:29 +00:00
if not input_path or not input_path . exists ( ) :
2020-09-03 11:13:03 +00:00
msg . fail ( " Can ' t locate pipeline data " , input_path , exits = 1 )
2017-05-07 21:25:29 +00:00
if not output_path or not output_path . exists ( ) :
2018-12-08 10:49:43 +00:00
msg . fail ( " Output directory not found " , output_path , exits = 1 )
2020-12-10 12:36:46 +00:00
for code_path in code_paths :
if not code_path . exists ( ) :
msg . fail ( " Can ' t find code file " , code_path , exits = 1 )
# Import the code here so it's available when model is loaded (via
# get_meta helper). Also verifies that everything works
util . import_file ( code_path . stem , code_path )
if code_paths :
msg . good ( f " Including { len ( code_paths ) } Python module(s) with custom code " )
2017-05-07 21:25:29 +00:00
if meta_path and not meta_path . exists ( ) :
2020-09-03 11:13:03 +00:00
msg . fail ( " Can ' t find pipeline meta.json " , meta_path , exits = 1 )
2020-06-21 19:35:01 +00:00
meta_path = meta_path or input_dir / " meta.json "
if not meta_path . exists ( ) or not meta_path . is_file ( ) :
2020-09-03 11:13:03 +00:00
msg . fail ( " Can ' t load pipeline meta.json " , meta_path , exits = 1 )
2020-06-21 19:35:01 +00:00
meta = srsly . read_json ( meta_path )
2020-06-27 18:36:08 +00:00
meta = get_meta ( input_dir , meta )
2020-09-11 09:38:28 +00:00
if name is not None :
meta [ " name " ] = name
2020-06-27 18:36:08 +00:00
if version is not None :
meta [ " version " ] = version
2020-06-21 19:35:01 +00:00
if not create_meta : # only print if user doesn't want to overwrite
msg . good ( " Loaded meta.json from file " , meta_path )
else :
2020-06-27 18:36:08 +00:00
meta = generate_meta ( meta , msg )
2020-06-21 19:35:01 +00:00
errors = validate ( ModelMetaSchema , meta )
if errors :
2020-09-03 11:13:03 +00:00
msg . fail ( " Invalid pipeline meta.json " )
2020-08-25 15:13:33 +00:00
print ( " \n " . join ( errors ) )
sys . exit ( 1 )
2018-11-30 19:16:14 +00:00
model_name = meta [ " lang " ] + " _ " + meta [ " name " ]
model_name_v = model_name + " - " + meta [ " version " ]
2020-06-21 19:35:01 +00:00
main_path = output_dir / model_name_v
2017-03-20 21:50:13 +00:00
package_path = main_path / model_name
2017-03-21 01:06:53 +00:00
if package_path . exists ( ) :
if force :
2019-12-22 00:53:56 +00:00
shutil . rmtree ( str ( package_path ) )
2017-03-21 01:06:53 +00:00
else :
2018-11-30 19:16:14 +00:00
msg . fail (
2018-12-08 10:49:43 +00:00
" Package directory already exists " ,
" Please delete the directory and try again, or use the "
2019-12-22 00:53:56 +00:00
" `--force` flag to overwrite existing directories. " ,
2018-11-30 19:16:14 +00:00
exits = 1 ,
)
2017-03-21 01:06:53 +00:00
Path . mkdir ( package_path , parents = True )
2020-06-21 19:35:01 +00:00
shutil . copytree ( str ( input_dir ) , str ( package_path / model_name_v ) )
2020-11-30 12:43:58 +00:00
license_path = package_path / model_name_v / " LICENSE "
if license_path . exists ( ) :
shutil . move ( str ( license_path ) , str ( main_path ) )
2020-12-10 12:36:46 +00:00
imports = [ ]
for code_path in code_paths :
imports . append ( code_path . stem )
shutil . copy ( str ( code_path ) , str ( package_path ) )
2018-12-19 13:36:08 +00:00
create_file ( main_path / " meta.json " , srsly . json_dumps ( meta , indent = 2 ) )
2018-11-30 19:16:14 +00:00
create_file ( main_path / " setup.py " , TEMPLATE_SETUP )
create_file ( main_path / " MANIFEST.in " , TEMPLATE_MANIFEST )
2020-12-10 12:36:46 +00:00
init_py = TEMPLATE_INIT . format (
imports = " \n " . join ( f " from . import { m } " for m in imports )
)
create_file ( package_path / " __init__.py " , init_py )
2019-12-22 00:53:56 +00:00
msg . good ( f " Successfully created package ' { model_name_v } ' " , main_path )
2020-07-27 14:52:23 +00:00
if create_sdist :
with util . working_dir ( main_path ) :
2020-09-20 14:21:43 +00:00
util . run_command ( [ sys . executable , " setup.py " , " sdist " ] , capture = False )
2020-07-27 14:52:23 +00:00
zip_file = main_path / " dist " / f " { model_name_v } .tar.gz "
msg . good ( f " Successfully created zipped Python package " , zip_file )
2017-03-21 01:06:53 +00:00
2020-06-21 19:35:01 +00:00
def create_file ( file_path : Path , contents : str ) - > None :
2017-03-20 21:50:13 +00:00
file_path . touch ( )
2018-11-30 19:16:14 +00:00
file_path . open ( " w " , encoding = " utf-8 " ) . write ( contents )
2017-03-20 21:50:13 +00:00
2020-06-27 18:36:08 +00:00
def get_meta (
model_path : Union [ str , Path ] , existing_meta : Dict [ str , Any ]
2020-06-21 19:35:01 +00:00
) - > Dict [ str , Any ] :
2020-06-27 18:36:08 +00:00
meta = {
" lang " : " en " ,
2020-09-03 11:13:03 +00:00
" name " : " pipeline " ,
2020-06-27 18:36:08 +00:00
" version " : " 0.0.0 " ,
2020-08-25 15:13:33 +00:00
" description " : " " ,
" author " : " " ,
" email " : " " ,
" url " : " " ,
2020-06-27 18:36:08 +00:00
" license " : " MIT " ,
}
meta . update ( existing_meta )
2017-10-25 14:03:26 +00:00
nlp = util . load_model_from_path ( Path ( model_path ) )
2020-05-30 13:01:58 +00:00
meta [ " spacy_version " ] = util . get_model_version_range ( about . __version__ )
2018-11-30 19:16:14 +00:00
meta [ " vectors " ] = {
" width " : nlp . vocab . vectors_length ,
" vectors " : len ( nlp . vocab . vectors ) ,
" keys " : nlp . vocab . vectors . n_keys ,
2018-12-27 18:55:40 +00:00
" name " : nlp . vocab . vectors . name ,
2018-11-30 19:16:14 +00:00
}
2020-06-27 18:36:08 +00:00
if about . __title__ != " spacy " :
meta [ " parent_package " ] = about . __title__
return meta
def generate_meta ( existing_meta : Dict [ str , Any ] , msg : Printer ) - > Dict [ str , Any ] :
meta = existing_meta or { }
settings = [
2020-09-03 11:13:03 +00:00
( " lang " , " Pipeline language " , meta . get ( " lang " , " en " ) ) ,
( " name " , " Pipeline name " , meta . get ( " name " , " pipeline " ) ) ,
( " version " , " Package version " , meta . get ( " version " , " 0.0.0 " ) ) ,
( " description " , " Package description " , meta . get ( " description " , None ) ) ,
2020-06-27 18:36:08 +00:00
( " author " , " Author " , meta . get ( " author " , None ) ) ,
( " email " , " Author email " , meta . get ( " email " , None ) ) ,
( " url " , " Author website " , meta . get ( " url " , None ) ) ,
( " license " , " License " , meta . get ( " license " , " MIT " ) ) ,
]
2018-12-08 10:49:43 +00:00
msg . divider ( " Generating meta.json " )
msg . text (
2020-09-03 11:13:03 +00:00
" Enter the package settings for your pipeline. The following information "
" will be read from your pipeline data: pipeline, vectors. "
2018-12-08 10:49:43 +00:00
)
2017-03-20 21:50:13 +00:00
for setting , desc , default in settings :
2018-11-30 19:16:14 +00:00
response = get_raw_input ( desc , default )
meta [ setting ] = default if response == " " and default else response
2017-05-27 18:02:01 +00:00
return meta
2017-04-16 11:13:17 +00:00
2017-11-07 11:15:35 +00:00
TEMPLATE_SETUP = """
#!/usr/bin/env python
import io
import json
from os import path , walk
from shutil import copy
from setuptools import setup
def load_meta ( fp ) :
with io . open ( fp , encoding = ' utf8 ' ) as f :
return json . load ( f )
def list_files ( data_dir ) :
output = [ ]
for root , _ , filenames in walk ( data_dir ) :
for filename in filenames :
if not filename . startswith ( ' . ' ) :
output . append ( path . join ( root , filename ) )
output = [ path . relpath ( p , path . dirname ( data_dir ) ) for p in output ]
output . append ( ' meta.json ' )
return output
def list_requirements ( meta ) :
parent_package = meta . get ( ' parent_package ' , ' spacy ' )
2020-05-30 13:01:58 +00:00
requirements = [ parent_package + meta [ ' spacy_version ' ] ]
2017-11-07 11:15:35 +00:00
if ' setup_requires ' in meta :
requirements + = meta [ ' setup_requires ' ]
2019-07-27 11:34:57 +00:00
if ' requirements ' in meta :
requirements + = meta [ ' requirements ' ]
2017-11-07 11:15:35 +00:00
return requirements
def setup_package ( ) :
root = path . abspath ( path . dirname ( __file__ ) )
meta_path = path . join ( root , ' meta.json ' )
meta = load_meta ( meta_path )
model_name = str ( meta [ ' lang ' ] + ' _ ' + meta [ ' name ' ] )
model_dir = path . join ( model_name , model_name + ' - ' + meta [ ' version ' ] )
copy ( meta_path , path . join ( model_name ) )
copy ( meta_path , model_dir )
setup (
name = model_name ,
2020-06-27 18:36:08 +00:00
description = meta . get ( ' description ' ) ,
author = meta . get ( ' author ' ) ,
author_email = meta . get ( ' email ' ) ,
url = meta . get ( ' url ' ) ,
2017-11-07 11:15:35 +00:00
version = meta [ ' version ' ] ,
2020-06-27 18:36:08 +00:00
license = meta . get ( ' license ' ) ,
2017-11-07 11:15:35 +00:00
packages = [ model_name ] ,
package_data = { model_name : list_files ( model_dir ) } ,
install_requires = list_requirements ( meta ) ,
zip_safe = False ,
2020-05-22 13:42:46 +00:00
entry_points = { ' spacy_models ' : [ ' {m} = {m} ' . format ( m = model_name ) ] }
2017-11-07 11:15:35 +00:00
)
if __name__ == ' __main__ ' :
setup_package ( )
""" .strip()
TEMPLATE_MANIFEST = """
include meta . json
2020-11-30 12:43:58 +00:00
include LICENSE
2017-11-07 11:15:35 +00:00
""" .strip()
TEMPLATE_INIT = """
from pathlib import Path
from spacy . util import load_model_from_init_py , get_model_meta
2020-12-10 12:36:46 +00:00
{ imports }
2017-11-07 11:15:35 +00:00
__version__ = get_model_meta ( Path ( __file__ ) . parent ) [ ' version ' ]
def load ( * * overrides ) :
return load_model_from_init_py ( __file__ , * * overrides )
""" .strip()