class RegtextParagraphProcessor(paragraph_processor.ParagraphProcessor):
MATCHERS = [paragraph_processor.StarsMatcher(),
paragraph_processor.TableMatcher(),
paragraph_processor.FencedMatcher(),
flatsubtree_processor.FlatsubtreeMatcher(
tags=['EXTRACT'], node_type=Node.EXTRACT),
import_category.ImportCategoryMatcher(),
flatsubtree_processor.FlatsubtreeMatcher(tags=['EXAMPLE']),
paragraph_processor.HeaderMatcher(),
paragraph_processor.GraphicsMatcher(),
ParagraphMatcher(),
note_processor.NoteMatcher(),
paragraph_processor.IgnoreTagMatcher(
'SECTNO', 'SUBJECT', 'CITA', 'SECAUTH', 'APPRO',
'PRTPAGE', 'EAR', 'RESERVED')]
def additional_constraints(self):
return [
optional_rules.depth_type_inverses,
optional_rules.limit_sequence_gap(3),
optional_rules.stars_occupy_space,
] + self.relaxed_constraints()
def relaxed_constraints(self):
return [optional_rules.star_new_level,
optional_rules.limit_paragraph_types(
mtypes.lower, mtypes.upper,
mtypes.ints, mtypes.roman,
mtypes.em_ints, mtypes.em_roman,
mtypes.stars, mtypes.markerless)]
class FlatParagraphProcessor(paragraph_processor.ParagraphProcessor):
"""Paragraph Processor which does not try to derive paragraph markers"""
MATCHERS = [paragraph_processor.StarsMatcher(),
paragraph_processor.TableMatcher(),
simple_hierarchy_processor.SimpleHierarchyMatcher(
['NOTE', 'NOTES'], Node.NOTE),
paragraph_processor.HeaderMatcher(),
paragraph_processor.SimpleTagMatcher('P', 'FP'),
us_code.USCodeMatcher(),
paragraph_processor.GraphicsMatcher(),
paragraph_processor.IgnoreTagMatcher('PRTPAGE')]