explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Clarify error when words are of wrong type (#9541)

Browse Source 
* Clarify error when words are of wrong type

See #9437

* Update docs

* Use try/except

* Apply suggestions from code review

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
This commit is contained in:
Paul O'Leary McCann 2021-10-29 10:08:40 +00:00 committed by GitHub
parent 2fd8d616e7
commit 006df1ae1f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 12 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
spacy/errors.py
View File

@ -877,6 +877,7 @@ class Errors:
"filename. Specify an epoch to resume from.")
E1021 = ("`pos` value \"{pp}\" is not a valid Universal Dependencies tag. "
"Non-UD tags should use the `tag` property.")
E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
# Deprecated model shortcuts, only used in errors and warnings

16
spacy/tokens/doc.pyx
View File

@ -194,11 +194,12 @@ cdef class Doc:
vocab (Vocab): A vocabulary object, which must match any models you
want to use (e.g. tokenizer, parser, entity recognizer).
words (Optional[List[str]]): A list of unicode strings to add to the document
as words. If `None`, defaults to empty list.
spaces (Optional[List[bool]]): A list of boolean values, of the same length as
words. True means that the word is followed by a space, False means
it is not. If `None`, defaults to `[True]*len(words)`
words (Optional[List[Union[str, int]]]): A list of unicode strings or
hash values to add to the document as words. If `None`, defaults to
empty list.
spaces (Optional[List[bool]]): A list of boolean values, of the same
length as `words`. `True` means that the word is followed by a space,
`False` means it is not. If `None`, defaults to `[True]*len(words)`
user_data (dict or None): Optional extra data to attach to the Doc.
tags (Optional[List[str]]): A list of unicode strings, of the same
length as words, to assign as token.tag. Defaults to None.
@ -266,7 +267,10 @@ cdef class Doc:
elif isinstance(word, bytes):
raise ValueError(Errors.E028.format(value=word))
else:
lexeme = self.vocab.get_by_orth(self.mem, word)
try:
lexeme = self.vocab.get_by_orth(self.mem, word)
except TypeError:
raise TypeError(Errors.E1022.format(wtype=type(word)))
self.push_back(lexeme, has_space)
if heads is not None:

2
website/docs/api/doc.md
View File

@ -34,7 +34,7 @@ Construct a `Doc` object. The most common way to get a `Doc` object is via the
| Name | Description |
| ---------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `vocab` | A storage container for lexical types. ~~Vocab~~ |
| `words` | A list of strings to add to the container. ~~Optional[List[str]]~~ |
| `words` | A list of strings or integer hash values to add to the document as words. ~~Optional[List[Union[str,int]]]~~ |
| `spaces` | A list of boolean values indicating whether each word has a subsequent space. Must have the same length as `words`, if specified. Defaults to a sequence of `True`. ~~Optional[List[bool]]~~ |
| _keyword-only_ | |
| `user\_data` | Optional extra data to attach to the Doc. ~~Dict~~ |