def make_multiple(head, tail=None, wrap_tail=False):
"""We have a recurring need to parse citations which have a string of
terms, e.g. section 11(a), (b)(4), and (5). This function is a shorthand
for setting these elements up"""
if tail is None:
tail = head
head = keep_pos(head).setResultsName("head")
# We need to address just the matching text separately from the
# conjunctive phrase
tail = keep_pos(tail).setResultsName("match")
tail = (atomic.conj_phrases + tail).setResultsName("tail",
listAllMatches=True)
if wrap_tail:
tail = Optional(Suppress('(')) + tail + Optional(Suppress(')'))
return QuickSearchable(head + OneOrMore(tail))
def make_multiple(head, tail=None, wrap_tail=False):
"""We have a recurring need to parse citations which have a string of
terms, e.g. section 11(a), (b)(4), and (5). This function is a shorthand
for setting these elements up"""
if tail is None:
tail = head
head = keep_pos(head).setResultsName("head")
# We need to address just the matching text separately from the
# conjunctive phrase
tail = keep_pos(tail).setResultsName("match")
tail = (atomic.conj_phrases + tail).setResultsName(
"tail", listAllMatches=True)
if wrap_tail:
tail = Optional(Suppress('(')) + tail + Optional(Suppress(')'))
return QuickSearchable(head + OneOrMore(tail))
# vim: set encoding=utf-8
from pyparsing import (
LineStart, Literal, OneOrMore, Optional, Regex, SkipTo, srange, Suppress,
Word, ZeroOrMore)
from regparser.grammar import atomic, unified
from regparser.grammar.utils import (
DocLiteral, keep_pos, Marker, QuickSearchable)
smart_quotes = QuickSearchable(
Suppress(DocLiteral(u'“', "left-smart-quote")) +
keep_pos(SkipTo(DocLiteral(
u'”', "right-smart-quote"))).setResultsName("term")
)
e_tag = (
Suppress(Regex(r"<E[^>]*>")) +
keep_pos(OneOrMore(Word(srange("[a-zA-Z-]")))).setResultsName("term") +
Suppress(Literal("</E>"))
)
xml_term_parser = QuickSearchable(
LineStart() +
Optional(Suppress(unified.any_depth_p)) +
e_tag.setResultsName("head") +
ZeroOrMore(
(atomic.conj_phrases + e_tag).setResultsName(
"tail", listAllMatches=True)) +
Suppress(ZeroOrMore(Regex(r",[a-zA-Z ]+,"))) +
Suppress(ZeroOrMore(
# vim: set encoding=utf-8
"""Some common combinations"""
from pyparsing import (FollowedBy, LineEnd, Literal, OneOrMore, Optional,
Suppress, SkipTo, ZeroOrMore)
from regparser.grammar import atomic
from regparser.grammar.utils import keep_pos, Marker, QuickSearchable
period_section = Suppress(".") + atomic.section
part_section = atomic.part + period_section
marker_part_section = (
keep_pos(atomic.section_marker).setResultsName("marker") + part_section)
depth6_p = atomic.em_roman_p | atomic.plaintext_level6_p
depth5_p = ((atomic.em_digit_p | atomic.plaintext_level5_p) +
Optional(depth6_p))
depth4_p = atomic.upper_p + Optional(depth5_p)
depth3_p = atomic.roman_p + Optional(depth4_p)
depth2_p = atomic.digit_p + Optional(depth3_p)
depth1_p = atomic.lower_p + ~FollowedBy(atomic.upper_p) + Optional(depth2_p)
any_depth_p = QuickSearchable(depth1_p | depth2_p | depth3_p | depth4_p
| depth5_p | depth6_p)
depth3_c = atomic.upper_c + Optional(atomic.em_digit_c)
depth2_c = atomic.roman_c + Optional(depth3_c)
depth1_c = atomic.digit_c + Optional(depth2_c)
any_a = atomic.upper_a | atomic.digit_a
section_comment = atomic.section + depth1_c
section_paragraph = QuickSearchable(atomic.section + depth1_p)
# vim: set encoding=utf-8
from pyparsing import (LineStart, Literal, OneOrMore, Optional, Regex, SkipTo,
srange, Suppress, Word, ZeroOrMore)
from regparser.grammar import atomic, unified
from regparser.grammar.utils import (DocLiteral, keep_pos, Marker,
QuickSearchable)
smart_quotes = QuickSearchable(
Suppress(DocLiteral(u'“', "left-smart-quote")) + keep_pos(
SkipTo(DocLiteral(u'”', "right-smart-quote"))).setResultsName("term"))
e_tag = (
Suppress(Regex(r"<E[^>]*>")) +
keep_pos(OneOrMore(Word(srange("[a-zA-Z-]")))).setResultsName("term") +
Suppress(Literal("</E>")))
xml_term_parser = QuickSearchable(
LineStart() + Optional(Suppress(unified.any_depth_p)) +
e_tag.setResultsName("head") +
ZeroOrMore((atomic.conj_phrases +
e_tag).setResultsName("tail", listAllMatches=True)) +
Suppress(ZeroOrMore(Regex(r",[a-zA-Z ]+,"))) +
Suppress(ZeroOrMore((Marker("this") | Marker("the")) + Marker("term"))) +
((Marker("mean") | Marker("means"))
| (Marker("refers") + ZeroOrMore(Marker("only")) + Marker("to")) | (
(Marker("has") | Marker("have")) + Marker("the") + Marker("same") +
Marker("meaning") + Marker("as"))))
key_term_parser = QuickSearchable(
LineStart() + Optional(Suppress(unified.any_depth_p)) +
# vim: set encoding=utf-8
"""Some common combinations"""
from pyparsing import (
FollowedBy, LineEnd, Literal, OneOrMore, Optional, Suppress, SkipTo,
ZeroOrMore)
from regparser.grammar import atomic
from regparser.grammar.utils import keep_pos, Marker, QuickSearchable
period_section = Suppress(".") + atomic.section
part_section = atomic.part + period_section
marker_part_section = (
keep_pos(atomic.section_marker).setResultsName("marker") +
part_section)
depth6_p = atomic.em_roman_p | atomic.plaintext_level6_p
depth5_p = (
(atomic.em_digit_p | atomic.plaintext_level5_p) +
Optional(depth6_p))
depth4_p = atomic.upper_p + Optional(depth5_p)
depth3_p = atomic.roman_p + Optional(depth4_p)
depth2_p = atomic.digit_p + Optional(depth3_p)
depth1_p = atomic.lower_p + ~FollowedBy(atomic.upper_p) + Optional(depth2_p)
any_depth_p = QuickSearchable(
depth1_p | depth2_p | depth3_p | depth4_p | depth5_p | depth6_p)
depth3_c = atomic.upper_c + Optional(atomic.em_digit_c)
depth2_c = atomic.roman_c + Optional(depth3_c)
depth1_c = atomic.digit_c + Optional(depth2_c)
any_a = atomic.upper_a | atomic.digit_a
