File size: 2,746 Bytes
660dde6 dbabef2 660dde6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | from __future__ import annotations
import re
from typing import List
from db.parsers.bsa.legal_models import Part
class PartParser:
"""
Supports:
PART I
PRELIMINARY
PART II
RELEVANCY OF FACTS
PART III
FACTS WHICH NEED NOT BE PROVED
"""
# ==========================================
# PART HEADER
# ==========================================
PART_RE = re.compile(
r"(?im)^PART\s+([IVXLCDM0-9A-Z]+)\s*$"
)
# ==========================================
# EXTRACT PARTS
# ==========================================
def extract_parts(
self,
text: str
) -> List[Part]:
matches = list(
self.PART_RE.finditer(
text
)
)
if not matches:
return []
parts = []
for i, match in enumerate(
matches
):
start = match.start()
end = (
matches[i + 1].start()
if i + 1 < len(matches)
else len(text)
)
block = (
text[start:end]
.strip()
)
lines = [
line.strip()
for line in block.splitlines()
if line.strip()
]
part_no = (
match.group(1)
)
title = ""
if len(lines) >= 2:
title = lines[1]
parts.append(
Part(
document="bsa",
part_no=part_no,
title=title,
text=block
)
)
return parts
# ==========================================
# VALIDATION
# ==========================================
def validate_parts(
self,
parts: List[Part]
) -> List[str]:
errors = []
seen = set()
for part in parts:
if part.part_no in seen:
errors.append(
f"Duplicate Part "
f"{part.part_no}"
)
seen.add(
part.part_no
)
if not part.title:
errors.append(
f"Part {part.part_no} "
f"missing title"
)
return errors
if __name__ == "__main__":
sample = """
PART I
PRELIMINARY
1. Short title.
PART II
RELEVANCY OF FACTS
2. Evidence may be given.
"""
parser = PartParser()
parts = parser.extract_parts(
sample
)
for part in parts:
print(
part.part_no,
part.title
) |