Spaces:
Running
Running
| import enum | |
| import subprocess | |
| import spacy | |
| import pyinflect | |
| from typing import List, Union, Tuple | |
| # BES auxiliary “be” Let it **be**. | |
| # HVS forms of “have” I**’ve** seen the Queen | |
| # MD verb, modal auxiliary VerbType=mod This **could** work. | |
| # VB verb, base form VerbForm=inf I want to **go**. | |
| # VBD verb, past tense VerbForm=fin Tense=past This **was** a sentence. | |
| # VBG verb, gerund or present participle VerbForm=part Tense=pres Aspect=prog I am **going**. | |
| # VBN verb, past participle VerbForm=part Tense=past Aspect=perf The treasure was **lost**. | |
| # VBP verb, non-3rd person singular present VerbForm=fin Tense=pres I **want** to go. | |
| # VBZ verb, 3rd person singular present VerbForm=fin Tense=pres Number=sing Person=3 He **wants** to go. | |
| class Tense(enum.Enum): | |
| simple_present = { | |
| 'aux':[None,'VBZ'], | |
| 'main':['VBZ','VBP', 'VB'], | |
| 'tobe':{'NN':'is{}','NNS':'are{}'} | |
| } | |
| simple_past = { | |
| 'aux':[None, 'VBD'], | |
| 'main':['VBD', 'VB'], | |
| 'tobe':{'NN':'was{}','NNS':'were{}'} | |
| } | |
| future_simple = { | |
| 'aux':['MD'], | |
| 'main':['VB'], | |
| 'tobe':{'NN':'will{} be','NNS':'will{} be'} | |
| } | |
| present_cont = { | |
| 'aux':['VBP','VBZ'], | |
| 'main':['VBG'], | |
| 'tobe':{'NN':'is{} being','NNS':'are{} being'} | |
| } | |
| past_cont = { | |
| 'aux':['VBD'], | |
| 'main':['VBG'], | |
| 'tobe':{'NN':'was{} being','NNS':'were{} being'} | |
| } | |
| present_perfect = { | |
| 'aux':['VBP','VBZ'], | |
| 'main':['VBN'], | |
| 'tobe':{'NN':'has{} been','NNS':'have{} been'} | |
| } | |
| class Parser: | |
| def __init__( | |
| self | |
| ) -> None: | |
| self.parser = None | |
| self.__init_parser(model="en_core_web_sm") | |
| def __init_parser( | |
| self, | |
| model: str | |
| ) -> None: | |
| self.parser = None | |
| try: | |
| self.parser = spacy.load(model) | |
| except: | |
| print(f"* Downloading {model} model...") | |
| _ = subprocess.Popen( | |
| f"python -m spacy download {model}", | |
| stdout=subprocess.PIPE, | |
| shell=True).communicate() | |
| self.parser = spacy.load(model) | |
| def verb2participle( | |
| self, | |
| verb: str | |
| ) -> str: | |
| tk = self.parser(verb)[0] | |
| return tk._.inflect('VBN') | |
| def subj2obj( | |
| self, | |
| pronoun: str | |
| ) -> str: | |
| """ | |
| Convert Subject pronouns to Object pronouns. | |
| """ | |
| mapping = {"i":"me","you":"you","we":"us","they":"them","he":"him","she":"her", "it":"it"} | |
| return mapping.get(pronoun.lower(), None) | |
| def get_gramatical_number( | |
| self, | |
| dobj_data: List[List[Tuple[str,str,str]]] | |
| ) -> Union[str, None]: | |
| result = [tag for _,dep,tag in dobj_data if dep == 'dobj'] | |
| if len(result) == 0: | |
| result = None | |
| else: | |
| result = result[0].replace('NNP', 'NN') | |
| return result | |
| def get_verbal_tense( | |
| self, | |
| verb_data: List[List[Tuple[str,str,str,int]]] | |
| ) -> Union[str, None]: | |
| aux, neg, root = verb_data | |
| root = root[0][2] if len(root) > 0 else None | |
| aux = aux[0][2] if len(aux) > 0 else None | |
| tense_name = None | |
| for tense in Tense: | |
| if aux in tense.value['aux'] and root in tense.value['main']: | |
| tense_name = tense.name | |
| break | |
| return tense_name |