2017-05-13 22:23:12 +03:00
|
|
|
//- 💫 DOCS > API > ANNOTATION SPECS
|
|
|
|
|
|
|
|
include ../../_includes/_mixins
|
|
|
|
|
|
|
|
p
|
|
|
|
| spaCy comes with a small collection of utility functions located in
|
|
|
|
| #[+src(gh("spaCy", "spacy/util.py")) spacy/util.py].
|
|
|
|
|
|
|
|
+infobox("Important note")
|
|
|
|
| Because utility functions are mostly intended for
|
|
|
|
| #[strong internal use within spaCy], their behaviour may change with
|
|
|
|
| future releases. The functions documented on this page should be safe
|
|
|
|
| to use and we'll try to ensure backwards compatibility. However, we
|
|
|
|
| recommend having additional tests in place if your application depends on
|
|
|
|
| any of spaCy's utilities.
|
|
|
|
|
|
|
|
+h(2, "get_data_path") get_data_path
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Get path to the data directory where spaCy looks for models. Defaults to
|
|
|
|
| #[code spacy/data].
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code require_exists]
|
|
|
|
+cell bool
|
|
|
|
+cell Only return path if it exists, otherwise return #[code None].
|
|
|
|
|
|
|
|
+footrow
|
|
|
|
+cell return
|
|
|
|
+cell #[code Path] / #[code None]
|
|
|
|
+cell Data path or #[code None].
|
|
|
|
|
|
|
|
+h(2, "set_data_path") set_data_path
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Set custom path to the data directory where spaCy looks for models.
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
util.set_data_path('/custom/path')
|
|
|
|
util.get_data_path()
|
|
|
|
# PosixPath('/custom/path')
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code path]
|
|
|
|
+cell unicode or #[code Path]
|
|
|
|
+cell Path to new data directory.
|
|
|
|
|
2017-05-14 02:31:10 +03:00
|
|
|
+h(2, "get_lang_class") get_lang_class
|
2017-05-13 22:23:12 +03:00
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Import and load a #[code Language] class. Allows lazy-loading
|
|
|
|
| #[+a("/docs/usage/adding-languages") language data] and importing
|
|
|
|
| languages using the two-letter language code.
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
for lang_id in ['en', 'de']:
|
2017-05-14 02:31:10 +03:00
|
|
|
lang_class = util.get_lang_class(lang_id)
|
2017-05-13 22:23:12 +03:00
|
|
|
lang = lang_class()
|
|
|
|
tokenizer = lang.Defaults.create_tokenizer()
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code lang]
|
|
|
|
+cell unicode
|
|
|
|
+cell Two-letter language code, e.g. #[code 'en'].
|
|
|
|
|
|
|
|
+footrow
|
|
|
|
+cell return
|
|
|
|
+cell #[code Language]
|
|
|
|
+cell Language class.
|
|
|
|
|
|
|
|
+h(2, "resolve_model_path") resolve_model_path
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p Resolve a model name or string to a model path.
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
model_path = util.resolve_model_path('en')
|
|
|
|
model_path = util.resolve_model_path('/path/to/en')
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code name]
|
|
|
|
+cell unicode
|
|
|
|
+cell Package name, shortcut link or model path.
|
|
|
|
|
|
|
|
+footrow
|
|
|
|
+cell return
|
|
|
|
+cell #[code Path]
|
|
|
|
+cell Path to model data directory.
|
|
|
|
|
|
|
|
+h(2, "is_package") is_package
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Check if string maps to a package installed via pip. Mainly used to
|
|
|
|
| validate #[+a("/docs/usage/models") model packages].
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
util.is_package('en_core_web_sm') # True
|
|
|
|
util.is_package('xyz') # False
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code name]
|
|
|
|
+cell unicode
|
|
|
|
+cell Name of package.
|
|
|
|
|
|
|
|
+footrow
|
|
|
|
+cell return
|
|
|
|
+cell #[code bool]
|
|
|
|
+cell #[code True] if installed package, #[code False] if not.
|
|
|
|
|
|
|
|
+h(2, "get_model_package_path") get_model_package_path
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Get path to a #[+a("/docs/usage/models") model package] installed via pip.
|
|
|
|
| Currently imports the package to find it and parse its meta data.
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
util.get_model_package_path('en_core_web_sm')
|
|
|
|
# /usr/lib/python3.6/site-packages/en_core_web_sm/en_core_web_sm-1.2.0
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code package_name]
|
|
|
|
+cell unicode
|
|
|
|
+cell Name of installed package.
|
|
|
|
|
|
|
|
+footrow
|
|
|
|
+cell return
|
|
|
|
+cell #[code Path]
|
|
|
|
+cell Path to model data directory.
|
|
|
|
|
|
|
|
+h(2, "parse_package_meta") parse_package_meta
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Check if a #[code meta.json] exists in a model package and return its
|
|
|
|
| contents.
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
if util.is_package('en_core_web_sm'):
|
|
|
|
path = util.get_model_package_path('en_core_web_sm')
|
|
|
|
meta = util.parse_package_meta(path, require=True)
|
|
|
|
# {'name': 'core_web_sm', 'lang': 'en', ...}
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code package_path]
|
|
|
|
+cell #[code Path]
|
|
|
|
+cell Path to model package directory.
|
|
|
|
|
|
|
|
+row
|
|
|
|
+cell #[code require]
|
|
|
|
+cell #[code bool]
|
|
|
|
+cell If #[code True], raise error if no #[code meta.json] is found.
|
|
|
|
|
|
|
|
+footrow
|
|
|
|
+cell return
|
|
|
|
+cell dict / #[code None]
|
|
|
|
+cell Model meta data or #[code None].
|
|
|
|
|
|
|
|
+h(2, "update_exc") update_exc
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Update, validate and overwrite
|
|
|
|
| #[+a("/docs/usage/adding-languages#tokenizer-exceptions") tokenizer exceptions].
|
|
|
|
| Used to combine global exceptions with custom, language-specific
|
|
|
|
| exceptions. Will raise an error if key doesn't match #[code ORTH] values.
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
BASE = {"a.": [{ORTH: "a."}], ":)": [{ORTH: ":)"}]}
|
|
|
|
NEW = {"a.": [{ORTH: "a.", LEMMA: "all"}]}
|
|
|
|
exceptions = util.update_exc(BASE, NEW)
|
|
|
|
# {"a.": [{ORTH: "a.", LEMMA: "all"}], ":)": [{ORTH: ":)"}]}
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code base_exceptions]
|
|
|
|
+cell dict
|
|
|
|
+cell Base tokenizer exceptions.
|
|
|
|
|
|
|
|
+row
|
|
|
|
+cell #[code *addition_dicts]
|
|
|
|
+cell dicts
|
|
|
|
+cell Exception dictionaries to add to the base exceptions, in order.
|
|
|
|
|
|
|
|
+footrow
|
|
|
|
+cell return
|
|
|
|
+cell dict
|
|
|
|
+cell Combined tokenizer exceptions.
|
|
|
|
|
|
|
|
|
|
|
|
+h(2, "prints") prints
|
|
|
|
+tag function
|
|
|
|
|
|
|
|
p
|
|
|
|
| Print a formatted, text-wrapped message with optional title. If a text
|
|
|
|
| argument is a #[code Path], it's converted to a string. Should only
|
|
|
|
| be used for interactive components like the #[+a("/docs/usage/cli") CLI].
|
|
|
|
|
|
|
|
+aside-code("Example").
|
|
|
|
data_path = Path('/some/path')
|
|
|
|
if not path.exists():
|
|
|
|
util.prints("Can't find the path.", data_path,
|
|
|
|
title="Error", exits=True)
|
|
|
|
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
|
|
+row
|
|
|
|
+cell #[code *texts]
|
|
|
|
+cell unicode
|
|
|
|
+cell Texts to print. Each argument is rendered as paragraph.
|
|
|
|
|
|
|
|
+row
|
|
|
|
+cell #[code **kwargs]
|
|
|
|
+cell -
|
|
|
|
+cell
|
|
|
|
| #[code title] is rendered as coloured headline. #[code exits=True]
|
|
|
|
| performs system exit after printing.
|