mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
adc9745718
* Restructure tag maps for MorphAnalysis changes
Prepare tag maps for upcoming MorphAnalysis changes that allow
arbritrary features.
* Use default tag map rather than duplicating for ca / uk / vi
* Import tag map into defaults for ga
* Modify tag maps so all morphological fields and features are strings
* Move features from `"Other"` to the top level
* Rewrite tuples as strings separated by `","`
* Rewrite morph symbols for fr lemmatizer as strings
* Export MorphAnalysis under spacy.tokens
* Modify morphology to support arbitrary features
Modify `Morphology` and `MorphAnalysis` so that arbitrary features are
supported.
* Modify `MorphAnalysisC` so that it can support arbitrary features and
multiple values per field. `MorphAnalysisC` is redesigned to contain:
* key: hash of UD FEATS string of morphological features
* array of `MorphFeatureC` structs that each contain a hash of `Field`
and `Field=Value` for a given morphological feature, which makes it
possible to:
* find features by field
* represent multiple values for a given field
* `get_field()` is renamed to `get_by_field()` and is no longer `nogil`.
Instead a new helper function `get_n_by_field()` is `nogil` and returns
`n` features by field.
* `MorphAnalysis.get()` returns all possible values for a field as a
list of individual features such as `["Tense=Pres", "Tense=Past"]`.
* `MorphAnalysis`'s `str()` and `repr()` are the UD FEATS string.
* `Morphology.feats_to_dict()` converts a UD FEATS string to a dict
where:
* Each field has one entry in the dict
* Multiple values remain separated by a separator in the value string
* `Token.morph_` returns the UD FEATS string and you can set
`Token.morph_` with a UD FEATS string or with a tag map dict.
* Modify get_by_field to use np.ndarray
Modify `get_by_field()` to use np.ndarray. Remove `max_results` from
`get_n_by_field()` and always iterate over all the fields.
* Rewrite without MorphFeatureC
* Add shortcut for existing feats strings as keys
Add shortcut for existing feats strings as keys in `Morphology.add()`.
* Check for '_' as empty analysis when adding morphs
* Extend helper converters in Morphology
Add and extend helper converters that convert and normalize between:
* UD FEATS strings (`"Case=dat,gen|Number=sing"`)
* per-field dict of feats (`{"Case": "dat,gen", "Number": "sing"}`)
* list of individual features (`["Case=dat", "Case=gen",
"Number=sing"]`)
All converters sort fields and values where applicable.
286 lines
7.3 KiB
Python
286 lines
7.3 KiB
Python
from ...symbols import LEMMA, PRON_LEMMA
|
|
|
|
|
|
# Used the table of pronouns at https://sv.wiktionary.org/wiki/deras
|
|
MORPH_RULES = {
|
|
"PRP": {
|
|
"jag": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Case": "Nom",
|
|
},
|
|
"mig": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Case": "Acc",
|
|
},
|
|
"mej": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Case": "Acc",
|
|
},
|
|
"du": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing",
|
|
"Case": "Nom",
|
|
},
|
|
"han": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Masc",
|
|
"Case": "Nom",
|
|
},
|
|
"honom": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Masc",
|
|
"Case": "Acc",
|
|
},
|
|
"hon": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Fem",
|
|
"Case": "Nom",
|
|
},
|
|
"henne": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Fem",
|
|
"Case": "Acc",
|
|
},
|
|
"det": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Sing",
|
|
"Gender": "Neut",
|
|
},
|
|
"vi": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Case": "Nom",
|
|
},
|
|
"oss": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Case": "Acc",
|
|
},
|
|
"ni": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Case": "Nom",
|
|
},
|
|
"er": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Plur"},
|
|
"de": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Case": "Nom",
|
|
},
|
|
"dom": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Case": "Nom,Acc",
|
|
},
|
|
"dem": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Case": "Acc",
|
|
},
|
|
"min": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"mitt": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"mina": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"din": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"ditt": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"dina": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"hans": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing,Plur",
|
|
"Gender": "Masc",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"hennes": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing,Plur",
|
|
"Gender": "Fem",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"dess": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Sing,Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"vår": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"våran": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"vårt": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"vårat": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"våra": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "One",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"eran": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"ert": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"erat": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"era": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Two",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
"deras": {
|
|
LEMMA: PRON_LEMMA,
|
|
"PronType": "Prs",
|
|
"Person": "Three",
|
|
"Number": "Plur",
|
|
"Poss": "Yes",
|
|
"Reflex": "Yes",
|
|
},
|
|
},
|
|
"VBZ": {
|
|
"är": {
|
|
"VerbForm": "Fin",
|
|
"Person": "One,Two,Three",
|
|
"Tense": "Pres",
|
|
"Mood": "Ind",
|
|
}
|
|
},
|
|
"VBP": {"är": {"VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"}},
|
|
"VBD": {
|
|
"var": {"VerbForm": "Fin", "Tense": "Past", "Number": "Sing"},
|
|
"vart": {"VerbForm": "Fin", "Tense": "Past", "Number": "Plur"},
|
|
},
|
|
}
|