Spaces:
Build error
Build error
File size: 23,650 Bytes
48e7216 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 |
import datetime
import re
from pydantic import (
BaseModel,
computed_field,
Field,
ValidationInfo,
model_validator,
ConfigDict
)
import pandas as pd
class UKPayslipSchema(BaseModel):
model_config = ConfigDict(arbitrary_types_allowed=True)
pay_period_start_date: datetime.date | None = Field(
default=None,
description="Pay period's start date in YYYY-MM-DD format",
examples=["2025-02-01"],
)
pay_period_end_date: datetime.date | None = Field(
default=None,
description="Pay period's end date in YYYY-MM-DD format",
examples=["2025-02-28"],
)
pay_period_days: int | None = Field(
default=None,
description="pay_period_end_date - pay_period_start_date in days",
examples=[28],
)
pay_date: datetime.date | None = Field(None)
full_name: str | None = Field(
default=None,
description="Applicant's full name. Must consist of at least 2 words, have length gte 2 & lte 61",
examples=["Jodie Pippa"],
)
employer_name: str | None = Field(
default=None,
description="Employer name extracted",
examples=["ABC Ltd"],
)
is_basic_pay_net_pay_other_salary_components_present: bool = Field(
default=False,
description="Boolean indicating whether Basic Pay, Net Pay, other requisite salary components/line items are present in the payslip",
examples=[True, False],
)
is_tax_deducation_present: bool = Field(
default=False,
description="Boolean flag indicating whether Tax Deduction line item is present in the payslip",
examples=[True, False],
)
is_ni_deduction_present: bool = Field(
default=False,
description="Boolean flag indicating whether NI/National Insurance deduction line item is present in the payslip",
examples=[True, False],
)
complete_employee_address: str | None = Field(
default=None,
description="Employee's complete address as a string",
examples=["123 Maple Street, London, UK, SW1A 1AA"],
)
# employee_number: int | None = Field(
# default=None,
# description="Employee number",
# examples=[3558, 1234],
# )
pay_dates_err_msgs: str | None = None
full_name_err_msgs: str | None = None
employer_name_err_msgs: str | None = None
payslip_line_item_presence_err_msgs: str | None = None
complete_employee_address_err_msgs: str | None = None
validation_policy_status_df: pd.DataFrame = pd.DataFrame(
columns=["Policy", "Value", "Status", "Message"])
# employee_number_err_msgs: str | None = None
# is_red_flagged: bool = False
@model_validator(mode="after")
def validate_full_name(self, info: ValidationInfo):
"""Match applicant's full name against provided name (case-insensitive)"""
try:
err_msgs = []
expected = (
info.context.get("application_summary_full_name")
if info.context
else None
)
if not self.full_name:
err_msgs.append("Applicant's full name not present")
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", self.full_name, False, "Applicant's full name is not present"]
else:
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", self.full_name, True, "Applicant's full name is present"]
full_name_val_len = len(self.full_name) if self.full_name else 0
if not (2 <= full_name_val_len <= 61):
err_msgs.append(
"Full name must have a length of at least 2 & at most 61"
)
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", full_name_val_len, False, "Full name has a length of at least 2 & at most 61"]
else:
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", full_name_val_len, True, "Full name has a length of at least 2 & at most 61"]
if not self.full_name or len(self.full_name.strip().split(" ")) < 2:
err_msgs.append(
"Full name must consist of at least 2 words (first name + last name)"
)
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", self.full_name , False, "Full name does not consist of at least 2 words (first name + last name)"]
else:
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", len(self.full_name.strip().split(" ")), True, "Full name consists of at least 2 words (first name + last name)"]
if (
not expected
or not self.full_name
or self.full_name.lower() != expected.lower()
):
err_msgs.append("Name mismatch with provided value")
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", f"{self.full_name}, {expected}", False, "Name does not match with provided value"]
else:
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", f"{self.full_name}, {expected}", True, "Name matches with provided value"]
self.full_name_err_msgs = ", ".join(err_msgs) if err_msgs else None
return self
except Exception as e:
# logger.exception(e, exc_info=True)
# return None
raise
@model_validator(mode="after")
def validate_employer_name(self, info: ValidationInfo):
"""Match employer against provided employer name (case-insensitive)"""
try:
err_msgs = []
expected = (
info.context.get("application_summary_employer_name")
if info.context
else None
)
employer_name_val = self.employer_name
if not employer_name_val:
err_msgs.append("Employer name not present")
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", employer_name_val, False, "Employer name is not present"]
else:
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", employer_name_val, True, "Employer name is present"]
is_employer_name_match = (
expected
and employer_name_val
and employer_name_val.lower() == expected.lower()
)
if not is_employer_name_match:
err_msgs.append("Employer name mismatch with provided value")
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", f"{employer_name_val}, {expected}", False, "Employer name does not match with provided value"]
else:
self.validation_policy_status_df.loc[len(
self.validation_policy_status_df)] = ["Employer & Customer Names", f"{employer_name_val}, {expected}", True, "Employer name matches with provided value"]
# # Allowed: letters, numbers, spaces, and common name punctuation
# pattern = r"^[A-Za-z0-9&\-,.()'/@ ]{2,100}$"
# if not re.match(pattern, employer_name_val):
# err_msgs.append("Employer name contains invalid characters")
if not re.search(r"[A-Za-z]", employer_name_val):
err_msgs.append(
"Employer name must contain at least one letter")
if employer_name_val.strip() == "":
err_msgs.append("Employer name cannot be only whitespace")
self.employer_name_err_msgs = ", ".join(
err_msgs) if err_msgs else None
return self
except Exception as e:
# logger.exception(e, exc_info=True)
# return None
raise
@model_validator(mode="after")
def validate_payslip_dates(self):
try:
err_msgs = []
today = datetime.date.today()
threshold_date = today - datetime.timedelta(days=35)
if not self.pay_period_start_date or not self.pay_period_end_date:
err_msgs.append(
"Undated Payslips"
)
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Undated Payslips",
f"{self.pay_period_start_date}, {self.pay_period_end_date}",
False,
"Undated payslip",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Undated Payslips",
f"{self.pay_period_start_date}, {self.pay_period_end_date}",
True,
"Dated payslip",
]
# self.is_red_flagged = True
if self.pay_date:
if not (threshold_date <= self.pay_date <= today):
err_msgs.append(
"Pay date must be within the last 35 days & not in the future"
)
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Date Requirement",
self.pay_date,
False,
"Pay date is not within the last 35 days & not in the future",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Date Requirement",
self.pay_date,
True,
"Pay date is within the last 35 days & not in the future",
]
# elif self.pay_period_end_date:
else:
if not (threshold_date <= self.pay_period_end_date <= today):
err_msgs.append(
"Pay period's end date must be within the last 35 days & not in the future"
)
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Period End Date (DD/MM/YYYY, if no pay date)",
self.pay_date,
False,
"Pay date is not within the last 35 days &/or in the future",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Period End Date (DD/MM/YYYY, if no pay date)",
self.pay_date,
True,
"Pay date is within the last 35 days & not in the future",
]
prev_month_end = datetime.date.today().replace(day=1) - \
datetime.timedelta(days=1)
prev_month_start = prev_month_end.replace(day=1)
if not (
prev_month_start <= self.pay_period_start_date
and self.pay_period_start_date < self.pay_period_end_date <= today
):
err_msgs.append(
"Payslip date(s) must not be older than those of the last calendar month"
)
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Period Month (MM/YYYY, if no pay date) basis pay period duration",
self.pay_date,
False,
"Payslip date(s) is older than those of the last calendar month",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Period Month (MM/YYYY, if no pay date) basis pay period duration",
self.pay_date,
True,
"Payslip date(s) is not older than those of the last calendar month",
]
if self.pay_period_start_date and self.pay_period_end_date:
if self.pay_period_start_date >= self.pay_period_end_date:
err_msgs.append(
"Pay period's start date must be before the end date")
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Period Start & End Dates",
f"{self.pay_period_start_date}, {self.pay_period_end_date}",
False,
"Pay period's start date is not before the end date",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Period Start & End Dates",
f"{self.pay_period_start_date}, {self.pay_period_end_date}",
True,
"Pay period's start date is before the end date",
]
if (self.pay_period_end_date - self.pay_period_start_date).days < 28:
err_msgs.append(
"Pay period's start date & end date must have a gap of at least 28 days"
)
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Submission Requirement (Monthly Pay)",
(self.pay_period_end_date - self.pay_period_start_date).days,
False,
"Pay period's start date & end date donot have a gap of at least 28 days",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Submission Requirement (Monthly Pay)",
(self.pay_period_end_date - self.pay_period_start_date).days,
True,
"Pay period's start date & end date have a gap of at least 28 days",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Pay Period Start & End Dates",
f"{self.pay_period_start_date}, {self.pay_period_end_date}",
False,
"Pay period's start date is not before the end date",
]
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Submission Requirement (Monthly Pay)",
f"{self.pay_period_start_date}, {self.pay_period_end_date}",
False,
"Pay period's start date & end date donot have a gap of at least 28 days",
]
self.pay_dates_err_msgs = ", ".join(err_msgs) if err_msgs else None
return self
except Exception as e:
# logger.exception(e, exc_info=True)
# return None
raise
@model_validator(mode="after")
def validate_payslip_components_checks(self):
try:
err_msgs = []
if not self.is_basic_pay_net_pay_other_salary_components_present:
err_msgs.append(
"Basic salary, Net Salary and/or other requisite salary components not present"
)
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Requisite salary line items",
self.is_basic_pay_net_pay_other_salary_components_present,
False,
"Basic salary, Net Salary and/or other requisite salary components not present",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Requisite salary line items",
self.is_basic_pay_net_pay_other_salary_components_present,
True,
"Basic salary, Net Salary and/or other requisite salary components are present",
]
if not self.is_tax_deducation_present:
err_msgs.append("Tax Deduction line item must be present")
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Tax & NI Contributions",
self.is_tax_deducation_present,
False,
"Tax Deduction line item is not present",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Tax & NI Contributions",
self.is_tax_deducation_present,
True,
"Tax Deduction line item is present",
]
if not self.is_ni_deduction_present:
err_msgs.append("NI/National Insurance line item must be present")
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Tax & NI Contributions",
self.is_ni_deduction_present,
False,
"NI/National Insurance line item is not present",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Tax & NI Contributions",
self.is_ni_deduction_present,
True,
"NI/National Insurance line item is present",
]
self.payslip_line_item_presence_err_msgs = (
", ".join(err_msgs) if err_msgs else None
)
return self
except Exception as e:
# logger.exception(e, exc_info=True)
# return None
raise
@model_validator(mode="after")
def validate_complete_address(self, info: ValidationInfo):
try:
err_msgs = []
expected = (
info.context.get("application_summary_complete_address")
if info.context
else None
)
val = self.complete_employee_address
if not val:
err_msgs.append("Applicant's address not present")
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Applicant Address",
val,
False,
"Applicant's address not present",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Applicant Address",
val,
True,
"Applicant's address is present",
]
length = len(val) if val else 0
if not (10 <= length <= 300):
err_msgs.append(
"Applicant's complete address must have a length of at least 10 & at most 300"
)
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Applicant Address",
length,
False,
"Applicant's complete address does not have a length of at least 10 & at most 300",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Applicant Address",
length,
True,
"Applicant's complete address has a length of at least 10 & at most 300",
]
if not expected or not val or val.lower() != expected.lower():
err_msgs.append("Complete address mismatch with provided value")
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Applicant Address",
f"{val}, {expected}",
False,
"Complete address mismatch with provided value",
]
else:
self.validation_policy_status_df.loc[
len(self.validation_policy_status_df)
] = [
"Applicant Address",
f"{val}, {expected}",
True,
"Complete address matches with provided value",
]
self.complete_employee_address_err_msgs = (
", ".join(err_msgs) if err_msgs else None
)
return self
except Exception as e:
# logger.exception(e, exc_info=True)
# return None
raise
# @model_validator(mode="after")
# def validate_employee_number(self):
# try:
# if self.employee_number and self.employee_number <= 25:
# self.complete_employee_address_err_msgs = "Employee number low"
# return self
# except Exception as e:
# raise
@computed_field
@property
def is_red_flagged(self) -> bool:
if any([
self.pay_dates_err_msgs,
self.full_name_err_msgs,
self.employer_name_err_msgs,
self.payslip_line_item_presence_err_msgs,
self.complete_employee_address_err_msgs,
# self.employee_number_err_msgs,
]):
return True
return False
|