File size: 3,823 Bytes
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 | import re
class BSATextCleaner:
@staticmethod
def clean(text: str) -> str:
# =====================================
# Normalize line endings
# =====================================
text = text.replace("\r\n", "\n")
text = text.replace("\r", "\n")
# =====================================
# Remove Gazette headers
# =====================================
text = re.sub(
r"(?im)^.*THE\s+GAZETTE\s+OF\s+INDIA\s+EXTRAORDINARY.*$\n?",
"",
text
)
# =====================================
# Remove PART headers
# =====================================
text = re.sub(
r"(?im)^\[?\s*PART\s+[IVXLC0-9A-Z\- ]+\]?\s*$",
"",
text
)
# =====================================
# Remove Gazette footnotes
# =====================================
text = re.sub(
r"(?im)^\d+\.\s+\d+(?:st|nd|rd|th)\s+day.*?$",
"",
text
)
# =====================================
# Remove notification notes
# =====================================
text = re.sub(
r"(?im)^\d+\.\s+vide\s+notification.*?$",
"",
text
)
# =====================================
# Remove page numbers
# =====================================
text = re.sub(
r"(?m)^\d+\s*$",
"",
text
)
# =====================================
# Remove standalone page references
#
# 46.
# 127.
# =====================================
text = re.sub(
r"(?m)^\d+\.\s*$",
"",
text
)
# =====================================
# Remove separator lines
# =====================================
text = re.sub(
r"(?m)^[_=\-]{5,}\s*$",
"",
text
)
# =====================================
# Remove OCR underline blocks
# =====================================
text = re.sub(
r"(?m)^[_ ]{20,}$",
"",
text
)
# =====================================
# Remove form-feed characters
# =====================================
text = text.replace(
"\f",
"\n"
)
# =====================================
# Fix broken words
#
# exam-
# ple
# ->
# example
# =====================================
text = re.sub(
r"([a-zA-Z])-\n([a-zA-Z])",
r"\1\2",
text
)
# =====================================
# Join OCR split words
#
# evi
# dence
#
# only when lowercase
# =====================================
text = re.sub(
r"([a-z])\n([a-z])",
r"\1 \2",
text
)
# =====================================
# Normalize spaces
# =====================================
text = re.sub(
r"[ \t]+",
" ",
text
)
# =====================================
# Remove trailing spaces
# =====================================
text = re.sub(
r"[ \t]+\n",
"\n",
text
)
# =====================================
# Collapse blank lines
# =====================================
text = re.sub(
r"\n{3,}",
"\n\n",
text
)
return text.strip() |