def setup_de_parser():
def preproc_func(text):
return re.sub('e$', '[e]?', text)
ptrs = ParserInitParams()
ptrs.key_word_preproc_func = preproc_func
ptrs.court_pattern_checker = re.compile('gericht')
ptrs.split_ptrs = LineSplitParams()
ptrs.split_ptrs.line_breaks = {'\n', '.', ';', ','
}.union(set(DeLanguageTokens.conjunctions))
ptrs.split_ptrs.abbreviations = DeLanguageTokens.abbreviations
ptrs.split_ptrs.abbr_ignore_case = True
ptrs.column_names = {
'type': 'Court Type (de-DE)',
'name': 'Court Name (de-DE)',
'jurisdiction': 'Jurisdiction',
'alias': 'Alias (de-DE)'
}
path = os.path.join(os.path.dirname(__file__),
"../../config/de/de_courts.csv")
ptrs.dataframe_paths = [path]
parser = UniversalCourtsParser(ptrs)
return parser
def setup_es_parser():
ptrs = ParserInitParams()
ptrs.dataframe_paths = [os.path.join(lexnlp_base_path, 'lexnlp/config/es/es_courts.csv')]
ptrs.split_ptrs = LineSplitParams()
ptrs.split_ptrs.line_breaks = {'\n', '.', ';', ','}.union(set(EsLanguageTokens.conjunctions))
ptrs.split_ptrs.abbreviations = EsLanguageTokens.abbreviations
ptrs.split_ptrs.abbr_ignore_case = True
ptrs.court_pattern_checker = re.compile('tribunal', re.IGNORECASE)
return UniversalCourtsParser(ptrs)
def setup_en_parser():
ptrs = ParserInitParams()
ptrs.dataframe_paths = [os.path.join(os.path.dirname(__file__), "../../config/en/us_state_courts.csv"),
os.path.join(os.path.dirname(__file__), "../../config/en/us_courts.csv"),
os.path.join(os.path.dirname(__file__), "../../config/en/ca_courts.csv"),
os.path.join(os.path.dirname(__file__), "../../config/en/au_courts.csv")]
ptrs.split_ptrs = LineSplitParams()
ptrs.split_ptrs.line_breaks = {'\n', '.', ';', ','}.union(set(EnLanguageTokens.conjunctions))
ptrs.split_ptrs.abbreviations = EnLanguageTokens.abbreviations
ptrs.split_ptrs.abbr_ignore_case = True
ptrs.court_pattern_checker = re.compile('court', re.IGNORECASE)
return UniversalCourtsParser(ptrs)
def make_en_parser(self):
url = "https://raw.githubusercontent.com/LexPredict/lexpredict-legal-dictionary/1.0.2/en/legal/us_courts.csv"
ptrs = ParserInitParams()
ptrs.court_pattern_checker = re.compile('court', re.IGNORECASE)
ptrs.dataframe_paths = [url]
ptrs.split_ptrs = LineSplitParams()
ptrs.split_ptrs.line_breaks = {'\n', '.', ';', ','}.union(set(EnLanguageTokens.conjunctions))
ptrs.split_ptrs.abbreviations = EnLanguageTokens.abbreviations
ptrs.split_ptrs.abbr_ignore_case = True
parser = UniversalCourtsParser(ptrs)
return parser
def setup_en_parser():
ptrs = ParserInitParams()
file_path = os.path.join(lexnlp_base_path, 'lexnlp/config/en')
ptrs.dataframe_paths = ['us_state_courts.csv',
'us_courts.csv',
'ca_courts.csv',
'au_courts.csv']
ptrs.dataframe_paths = [os.path.join(file_path, p)
for p in ptrs.dataframe_paths]
ptrs.split_ptrs = LineSplitParams()
ptrs.split_ptrs.line_breaks = {'\n', '.', ';', ','}.union(set(EnLanguageTokens.conjunctions))
ptrs.split_ptrs.abbreviations = EnLanguageTokens.abbreviations
ptrs.split_ptrs.abbr_ignore_case = True
ptrs.court_pattern_checker = re.compile('court', re.IGNORECASE)
return UniversalCourtsParser(ptrs)