QuotedString(quoteChar='(', endQuoteChar=')').setResultsName("subgroup") +
Suppress("]")
).setParseAction(lambda m: tokens.Context(
[None, 'Subjgrp:' + subjgrp_label(m.subgroup, [])], bool(m.certain)))
# Phrases like '“Nonimmigrant visa”' become 'p12345678'
_double_quote_label = QuotedString(
quoteChar=u'“', endQuoteChar=u'”'
).setParseAction(lambda m: "p{0}".format(hash_for_paragraph(m[0])))
# Phrases like "definition for the term “Nonimmigrant visa”" become a
# paragraph token with the appropriate paragraph label set
definition = (
Marker("definition") +
(Marker("of") | Marker("for")) +
Optional(Marker("the") + Marker("term")) +
_double_quote_label.copy().setResultsName("paragraph")
).setParseAction(lambda m: tokens.Paragraph.make(paragraphs=[m.paragraph]))
# grammar which captures all of these possibilities
token_patterns = QuickSearchable(
put_active | put_passive | post_active | post_passive |
delete_active | delete_passive | move_active | move_passive |
designate_active | reserve_active |
insert_in_order |
interp | marker_subpart | appendix |
comment_context_with_section | comment_context_without_section |
comment_context_under_with_section |
paragraph_heading_of | section_heading_of |
multiple_intro_text_of | intro_text_of |
appendix_section_heading_of |
QuotedString(quoteChar='(', endQuoteChar=')').setResultsName("subgroup") +
Suppress("]")
).setParseAction(lambda m: tokens.Context(
[None, 'Subjgrp:' + subjgrp_label(m.subgroup, [])], bool(m.certain)))
# Phrases like '“Nonimmigrant visa”' become 'p12345678'
_double_quote_label = QuotedString(
quoteChar=u'“', endQuoteChar=u'”'
).setParseAction(lambda m: "p{}".format(hash_for_paragraph(m[0])))
# Phrases like "definition for the term “Nonimmigrant visa”" become a
# paragraph token with the appropriate paragraph label set
definition = (
Marker("definition") +
(Marker("of") | Marker("for")) +
Optional(Marker("the") + Marker("term")) +
_double_quote_label.copy().setResultsName("paragraph")
).setParseAction(lambda m: tokens.Paragraph(paragraphs=[m.paragraph]))
# grammar which captures all of these possibilities
token_patterns = QuickSearchable(
put_active | put_passive | post_active | post_passive |
delete_active | delete_passive | move_active | move_passive |
designate_active | reserve_active |
insert_in_order |
interp | marker_subpart | appendix |
comment_context_with_section | comment_context_without_section |
comment_context_under_with_section |
paragraph_heading_of | section_heading_of |
multiple_intro_text_of | intro_text_of |
appendix_section_heading_of |
elif palavra in _PALAVRAS_PADRAO:
palavra = _PALAVRAS_PADRAO[palavra]
else:
palavra = tira_acentos(palavra)
return palavra
palavras_pt_BR = Word(alphanums + alphas8bit + '_=!')
palavras_pt_BR.setParseAction(_converte_ingles)
tripleQuote = QuotedString('"""', multiline=True, unquoteResults=False) | \
QuotedString("'''", multiline=True, unquoteResults=False)
unicodeTripleQuote = Combine(Literal('u') + tripleQuote.copy()).setName(
"unicode string triple quoted")
python_brasil = unicodeTripleQuote | tripleQuote | unicodeString | \
quotedString | pythonStyleComment | \
palavras_pt_BR
def python_pt_BR(texto, dicionario={}):
global PALAVRAS_BRASIL
PALAVRAS_BRASIL.update(dicionario)
if type(texto) != unicode:
texto = unicode(texto)
return python_brasil.transformString(texto)
