Spaces:
Sleeping
Sleeping
File size: 12,289 Bytes
ef15c6c | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 | """
μνκΈ°λ‘λΆ μΉμ
ν
νλ¦Ώ μ μ v2.0
ν¨ν΄ κ°μ§κ° μλ 'κ³ μ νμ΄ν λ§€μΉ' λ°©μ
- νμ΄ν λ³νμ λͺ
μμ μΌλ‘ μ μ
- λ¬Έμ λ²μ (ꡬλ²μ 8μΉμ
/ μ λ²μ 9μΉμ
) μλ κ°μ§
- λμ
μ νμ©(λ²νΈ μμ) μ§μ
"""
from dataclasses import dataclass, field
from typing import Optional
from enum import Enum
class DocVersion(Enum):
"""λ¬Έμ λ²μ """
V1_8_SECTIONS = "v1" # ꡬλ²μ (8μΉμ
, ~2024)
V2_9_SECTIONS = "v2" # μ λ²μ (9μΉμ
, 2024~ νκ΅νλ ₯ μΆκ°)
COLLEGE_ADMISSION = "ca" # λμ
μ νμ© (λ²νΈ μμ)
@dataclass
class SectionDef:
"""μΉμ
μ μ"""
id: str # κ³ μ ID
titles: list[str] # λ§€μΉν νμ΄ν λͺ©λ‘ (곡백 무μ λ§€μΉ)
order_v1: Optional[int] = None # ꡬλ²μ μμμ μμ (λ²νΈ)
order_v2: Optional[int] = None # μ λ²μ μμμ μμ (λ²νΈ)
required: bool = True # νμ μΉμ
μ¬λΆ
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# μΉμ
νμ΄ν μ μ
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
SECTIONS = [
SectionDef(
id="μΈμ νμ ",
titles=["μΈμ Β·νμ μ¬ν", "μΈμ νμ μ¬ν", "μΈμ νμ μ¬ν", "μΈμ μ¬ν"],
order_v1=1, order_v2=1,
),
SectionDef(
id="μΆκ²°",
titles=["μΆκ²°μν©", "μΆ κ²° μ ν©"],
order_v1=2, order_v2=2,
),
SectionDef(
id="μμ",
titles=["μμκ²½λ ₯", "μ μ κ²½ λ ₯"],
order_v1=3, order_v2=3,
),
SectionDef(
id="μ격μ¦",
titles=["μκ²©μ¦ λ° μΈμ¦ μ·¨λμν©", "μ격μ¦", "μκ²©μ¦ λ° μΈμ¦"],
order_v1=4, order_v2=4,
required=False,
),
SectionDef(
id="νκ΅νλ ₯",
titles=["νκ΅νλ ₯ μ‘°μΉμν© κ΄λ¦¬", "νκ΅νλ ₯ μ‘°μΉμν©"],
order_v1=None, order_v2=5, # μ λ²μ μλ§ μ‘΄μ¬
required=False,
),
SectionDef(
id="창체",
titles=["μ°½μμ 체ννλμν©", "μ°½μμ 체ννλμν©", "μ°½μμ 체ννλ"],
order_v1=5, order_v2=6,
),
SectionDef(
id="κ΅κ³Ό",
titles=["κ΅κ³Όνμ΅λ°λ¬μν©", "κ΅κ³Όνμ΅ λ°λ¬μν©", "κ΅κ³Ό νμ΅ λ°λ¬ μν©"],
order_v1=6, order_v2=7,
),
SectionDef(
id="λ
μ",
titles=["λ
μνλμν©", "λ
μ νλ μν©", "λ
μνλ"],
order_v1=7, order_v2=8,
),
SectionDef(
id="νλ",
titles=["νλνΉμ± λ° μ’
ν©μ견", "νλνΉμ±λ°μ’
ν©μ견", "νλ νΉμ± λ° μ’
ν© μ견"],
order_v1=8, order_v2=9,
),
]
# λΉ λ₯Έ μ‘°νμ© λμ
λ리
SECTION_BY_ID = {s.id: s for s in SECTIONS}
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# μ°½μμ 체ννλ λ΄λΆ ꡬ쑰
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
@dataclass
class CreativeActivityArea:
"""창체 μμ μ μ"""
id: str
titles: list[str]
has_hours: bool = True # μκ° νλ μμ
has_details: bool = True # νΉκΈ°μ¬ν μμ
extra_fields: list[str] = field(default_factory=list) # μΆκ° νλ
CREATIVE_ACTIVITY_AREAS = [
CreativeActivityArea(
id="μμ¨",
titles=["μμ¨νλ", "μμ¨ νλ"],
),
CreativeActivityArea(
id="λμ리",
titles=["λμ리νλ", "λμ리 νλ"],
extra_fields=["club_name"], # (λμ리λͺ
)(μκ°) νμ
),
CreativeActivityArea(
id="μ§λ‘",
titles=["μ§λ‘νλ", "μ§λ‘ νλ"],
extra_fields=["desired_field"], # ν¬λ§λΆμΌ λ³λ ν
),
CreativeActivityArea(
id="λ΄μ¬",
titles=["λ΄μ¬νλ", "λ΄μ¬ νλ", "λ΄μ¬νλμ€μ "],
has_details=False, # ν
μ΄λΈ νμ
extra_fields=["date", "location", "activity", "cumulative_hours"],
),
]
CREATIVE_AREA_BY_ID = {a.id: a for a in CREATIVE_ACTIVITY_AREAS}
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# κ΅κ³Όνμ΅λ°λ¬μν© λ΄λΆ ꡬ쑰
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
@dataclass
class AcademicCategory:
"""κ΅κ³Ό μΉ΄ν
κ³ λ¦¬ μ μ"""
id: str
titles: list[str] # λ§€μΉν λ§μ»€ λͺ©λ‘ (μΌλ°μ λΉ λͺ©λ‘ = κΈ°λ³Έκ°)
marker: Optional[str] # λ¬Έμ λ΄ μ€μ λ§μ»€ (μΌλ°μ None)
columns: list[str] # ν
μ΄λΈ μ»¬λΌ κ΅¬μ‘°
has_rank: bool = True # μμ°¨λ±κΈ μμ
has_distribution: bool = False # μ±μ·¨λλ³ λΆν¬ μμ
has_score: bool = True # μμ μ/νκ· /νμ€νΈμ°¨ μμ
# μΉ΄ν
κ³ λ¦¬λ³ ν
μ΄λΈ μ»¬λΌ μ μ
# - μΌλ°: νκΈ°|κ΅κ³Ό|κ³Όλͺ©|λ¨μμ|μμ μ/νκ· (νμ€νΈμ°¨)|μ±μ·¨λ(μκ°μ)|μμ°¨λ±κΈ
# - μ§λ‘μ ν: νκΈ°|κ΅κ³Ό|κ³Όλͺ©|λ¨μμ|μμ μ/νκ· (νμ€νΈμ°¨)|μ±μ·¨λ(μκ°μ)|μ±μ·¨λλ³λΆν¬
# - 체μ‘μμ : νκΈ°|κ΅κ³Ό|κ³Όλͺ©|λ¨μμ|μ±μ·¨λ
ACADEMIC_CATEGORIES = [
AcademicCategory(
id="μΌλ°",
titles=[], # κΈ°λ³Έκ° - λͺ
μμ λ§μ»€ μμ
marker=None,
columns=["νκΈ°", "κ΅κ³Ό", "κ³Όλͺ©", "λ¨μμ", "μμ μ/νκ· (νμ€νΈμ°¨)", "μ±μ·¨λ(μκ°μ)", "μμ°¨λ±κΈ"],
has_rank=True,
has_distribution=False,
has_score=True,
),
AcademicCategory(
id="μ§λ‘μ ν",
titles=["<μ§λ‘ μ ν κ³Όλͺ©>", "μ§λ‘ μ ν κ³Όλͺ©", "μ§λ‘μ ν", "μ§λ‘ μ ν"],
marker="<μ§λ‘ μ ν κ³Όλͺ©>",
columns=["νκΈ°", "κ΅κ³Ό", "κ³Όλͺ©", "λ¨μμ", "μμ μ/νκ· (νμ€νΈμ°¨)", "μ±μ·¨λ(μκ°μ)", "μ±μ·¨λλ³λΆν¬"],
has_rank=False,
has_distribution=True,
has_score=True,
),
AcademicCategory(
id="체μ‘μμ ",
titles=["<체μ‘γμμ >", "<체μ‘Β·μμ >", "체μ‘Β·μμ ", "체μ‘γμμ ", "체μ‘μμ ", "체μ‘Β·μμ (κ΅μ)"],
marker="<체μ‘γμμ >",
columns=["νκΈ°", "κ΅κ³Ό", "κ³Όλͺ©", "λ¨μμ", "μ±μ·¨λ"],
has_rank=False,
has_distribution=False,
has_score=False, # μμ μ/νκ· μμ
),
]
ACADEMIC_CATEGORY_BY_ID = {c.id: c for c in ACADEMIC_CATEGORIES}
@dataclass
class SubjectRemarkPattern:
"""μΈλΆλ₯λ ₯νΉκΈ°μ¬ν ν¨ν΄"""
# κ³Όλͺ© μΈνΉ: "κ³Όλͺ©λͺ
: λ΄μ©" λλ "(νκΈ°)κ³Όλͺ©λͺ
: λ΄μ©"
subject_prefix_pattern: str = r"^(?:\(([12])νκΈ°\))?([κ°-ν£A-Za-zβ
-β
’\sΒ·]+)\s*[:οΌ]"
# κ°μΈ μΈνΉ: κ³Όλͺ©λͺ
μμ΄ μμ (λ§μ§λ§μ μμΉ)
personal_remark_min_length: int = 50 # μ΅μ 50μ μ΄μ
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# μΆκ²°μν© ν
μ΄λΈ ꡬ쑰
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ATTENDANCE_COLUMNS = {
"primary": ["νλ
", "μμ
μΌμ"],
"absence": {
"header": "κ²°μμΌμ",
"sub": ["μ§λ³", "λ―ΈμΈμ ", "κΈ°ν"],
},
"late": {
"header": "μ§κ°",
"sub": ["μ§λ³", "λ―ΈμΈμ ", "κΈ°ν"],
},
"early_leave": {
"header": "μ‘°ν΄",
"sub": ["μ§λ³", "λ―ΈμΈμ ", "κΈ°ν"],
},
"class_absence": {
"header": "κ²°κ³Ό", # κ²°κ³Ό = μμ
κ²°μ
"sub": ["μ§λ³", "λ―ΈμΈμ ", "κΈ°ν"],
},
"notes": "νΉκΈ°μ¬ν",
}
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# μμκ²½λ ₯ ν
μ΄λΈ ꡬ쑰
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
AWARDS_COLUMNS = [
"νλ
",
"νκΈ°", # (νκΈ°) λλ λ³λ 컬λΌ
"μμλͺ
",
"λ±κΈ", # λ±κΈ(μ)
"μμμ°μμΌ",
"μμ¬κΈ°κ΄",
"μ°Έκ°λμ", # (μ°Έκ°μΈμ)
]
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# λ
μνλμν© κ΅¬μ‘°
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
@dataclass
class ReadingFormat:
"""λ
μνλ νμ"""
# νλ
λ³λ‘ ꡬλΆ
grade_based: bool = True
# κ³Όλͺ©λ³ κ΅¬λΆ (μλ κ²½μ°)
subject_based: bool = False
# λμ νμ: "μ λͺ©(μ μ)" λλ "μ λͺ©"
book_pattern: str = r"([^(]+)(?:\(([^)]+)\))?"
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# ν¬νΌ ν¨μ
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
def normalize_text(text: str) -> str:
"""곡백 λ° νΉμλ¬Έμ μ κ·ν (λ§€μΉμ©)"""
import re
# 곡백 μ κ±°
text = re.sub(r'\s+', '', text)
# νΉμ μ (Β·, γ) ν΅μΌ
text = text.replace('γ', 'Β·')
return text
def match_title(text: str, titles: list[str]) -> bool:
"""νμ΄ν λ§€μΉ (곡백 무μ)"""
normalized = normalize_text(text)
for title in titles:
if normalize_text(title) in normalized:
return True
return False
def detect_doc_version(full_text: str) -> DocVersion:
"""λ¬Έμ λ²μ κ°μ§"""
import re
# λ²νΈ μμ΄ μΉμ
μμνλ©΄ λμ
μ νμ©
if re.search(r'^μΈμ [Β·\s]*νμ ', full_text, re.MULTILINE):
if not re.search(r'^\d+\.\s*μΈμ ', full_text, re.MULTILINE):
return DocVersion.COLLEGE_ADMISSION
# νκ΅νλ ₯ μΉμ
μμΌλ©΄ μ λ²μ
if match_title(full_text, SECTION_BY_ID["νκ΅νλ ₯"].titles):
return DocVersion.V2_9_SECTIONS
return DocVersion.V1_8_SECTIONS
def get_section_order(section_id: str, version: DocVersion) -> Optional[int]:
"""λ²μ μ λ°λ₯Έ μΉμ
μμ λ°ν"""
section = SECTION_BY_ID.get(section_id)
if not section:
return None
if version == DocVersion.V2_9_SECTIONS:
return section.order_v2
else:
return section.order_v1
|