Spaces:
Sleeping
Sleeping
File size: 22,419 Bytes
6ea020b | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 | """
LIS V1 β V2 Migration / Seeding Script (FIXED)
=================================================
Seeds in order:
1. Parameters
2. Departments
3. SampleTypes
4. Devices (V1 "Methods")
5. ReportNotes (V1 "Notes") β "None" inserted first as id=1
6. Tests
7. Ranges (V1 "TestRange")
Key fix applied
βββββββββββββββ
β’ PRAGMA foreign_keys is turned OFF for the duration of the migration.
This prevents SQLite from silently dropping (INSERT OR IGNORE) rows
whose created_by=1 FK cannot be resolved until a User row exists,
which previously left earlier tables empty and caused the
"FOREIGN KEY constraint failed" error on the TestDefinition insert.
Data integrity is guaranteed by the oldβnew ID maps built in code.
β’ Ranges that reference ParameterIds absent from parmeters.xlsx are
inserted with parameter_id = NULL (orphaned V1 records).
β’ Row-level error reporting: any single-row failure is printed with the
offending row data rather than aborting the whole batch.
"""
import os
import sqlite3
import pandas as pd
from datetime import datetime
# βββββββββββββββββββββββββββββββββββββββββββββ
# CONFIG β resolved dynamically relative to project root
# βββββββββββββββββββββββββββββββββββββββββββββ
project_root = os.path.dirname(os.path.abspath(__file__))
DB_PATH = os.path.join(project_root, "lab_database.db")
EXCEL_DIR = os.path.join(project_root, "excel_files")
NOW = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
CREATED_BY = 1
# ββ helpers ββββββββββββββββββββββββββββββββββ
def xls(filename: str) -> pd.DataFrame:
path = os.path.join(EXCEL_DIR, filename)
df = pd.read_excel(path)
df.columns = df.columns.str.strip()
return df
def clean(val):
if val is None:
return None
s = str(val).strip()
return None if s.lower() in ("", "nan", "none", "null") else s
def gender_map(v) -> str:
return {1: "male", 2: "female", 3: "both"}.get(int(v), "both")
def age_unit_map(v) -> str:
return {1: "year", 2: "month", 3: "day"}.get(int(v), "year")
def range_type_map(v) -> str:
return {1: "number", 2: "text"}.get(int(v), "number")
def opt_float(val):
try:
f = float(val)
return None if pd.isna(f) else f
except (TypeError, ValueError):
return None
def safe_executemany(cur, sql: str, rows: list, label: str) -> int:
"""
Insert rows one-by-one so a single bad row is reported and skipped
instead of aborting the whole batch. Returns the number inserted.
"""
inserted = 0
for row in rows:
try:
cur.execute(sql, row)
inserted += 1
except sqlite3.IntegrityError as exc:
print(f" β οΈ Skipped {label} row (IntegrityError: {exc}): {row[:4]}")
except Exception as exc:
print(f" β οΈ Skipped {label} row (Error: {exc}): {row[:4]}")
return inserted
# ββ main βββββββββββββββββββββββββββββββββββββ
def main():
conn = sqlite3.connect(DB_PATH)
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# CRITICAL FIX: disable FK enforcement for the migration.
# All FK integrity is enforced by the oldβnew ID maps in this script.
# Re-enabled at the very end after all data is committed.
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
conn.execute("PRAGMA foreign_keys = OFF;")
cur = conn.cursor()
# ββββββββββββββββββββββββββββββββββββββββββ
# 1. PARAMETERS
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 1. Seeding Parameters ββ")
df = xls("parmeters.xlsx")
df = df.dropna(subset=["ParameterName"])
df = df[df["ParameterName"].astype(str).str.strip() != ""]
param_old_to_new: dict[int, int] = {}
new_id = 1
rows = []
for _, r in df.iterrows():
old_id = int(r["ParameterId"])
param_old_to_new[old_id] = new_id
rows.append((
new_id,
str(r["ParameterName"]).strip(),
str(r["ShortName"]).strip() if clean(r["ShortName"]) else str(r["ParameterName"]).strip(),
1 if int(r["IsHeader"]) == 1 else 0,
CREATED_BY, NOW,
None, None,
None, None,
))
new_id += 1
sql = """
INSERT OR IGNORE INTO parameter
(id, parameter_name, parameter_short_name, is_header,
created_by, created_at, edited_by, edited_at, deleted_by, deleted_at)
VALUES (?,?,?,?,?,?,?,?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "parameter")
conn.commit()
print(f" β
{inserted} / {len(rows)} parameters inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# 2. DEPARTMENTS
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 2. Seeding Departments ββ")
df = xls("Departments.xlsx")
df = df.dropna(subset=["DepartmentName"])
dept_old_to_new: dict[int, int] = {}
new_id = 1
rows = []
for _, r in df.iterrows():
old_id = int(r["DepartmentId"])
dept_old_to_new[old_id] = new_id
rows.append((
new_id,
str(r["DepartmentName"]).strip(),
clean(r["DepartmentNote"]),
1,
CREATED_BY, NOW,
None, None,
None, None,
None, None,
None, None,
))
new_id += 1
sql = """
INSERT OR IGNORE INTO department
(id, department_name, department_note, is_active,
created_by, created_at, edited_by, edited_at,
deleted_by, deleted_at, activated_by, activated_at,
deactivated_by, deactivated_at)
VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "department")
conn.commit()
print(f" β
{inserted} / {len(rows)} departments inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# 3. SAMPLE TYPES
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 3. Seeding Sample Types ββ")
df = xls("SampleType.xlsx")
df = df.dropna(subset=["SampleTypeName"])
sample_old_to_new: dict[int, int] = {}
new_id = 1
rows = []
for _, r in df.iterrows():
old_id = int(r["SampleTypeId"])
sample_old_to_new[old_id] = new_id
rows.append((
new_id,
str(r["SampleTypeName"]).strip(),
clean(r["SampleTypeNote"]),
1,
CREATED_BY, NOW,
None, None,
None, None,
None, None,
None, None,
))
new_id += 1
sql = """
INSERT OR IGNORE INTO sampletype
(id, sample_name, sample_note, is_active,
created_by, created_at, edited_by, edited_at,
deleted_by, deleted_at, activated_by, activated_at,
deactivated_by, deactivated_at)
VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "sampletype")
conn.commit()
print(f" β
{inserted} / {len(rows)} sample types inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# 4. DEVICES (V1 "Methods")
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 4. Seeding Devices (from V1 Methods) ββ")
df = xls("Devices.xlsx")
df = df.dropna(subset=["MethodName"])
device_old_to_new: dict[int, int] = {}
new_id = 1
rows = []
for _, r in df.iterrows():
old_id = int(r["MethodId"])
device_old_to_new[old_id] = new_id
rows.append((
new_id,
str(r["MethodName"]).strip(),
"N/A",
NOW,
"N/A",
"N/A",
clean(r["MethodNote"]),
1,
CREATED_BY, NOW,
None, None,
None, None,
None, None,
None, None,
))
new_id += 1
sql = """
INSERT OR IGNORE INTO device
(id, device_name, serial_number, install_date,
installer_name, installer_phone, note, is_active,
created_by, created_at, edited_by, edited_at,
deleted_by, deleted_at, activated_by, activated_at,
deactivated_by, deactivated_at)
VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "device")
conn.commit()
print(f" β
{inserted} / {len(rows)} devices inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# 5. REPORT NOTES (V1 "Note")
# "None" is forced to be id=1
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 5. Seeding Report Notes ββ")
df = xls("ReportNote.xlsx")
df = df.dropna(subset=["NoteName"])
mask_none = df["NoteName"].astype(str).str.strip().str.lower() == "none"
df_ordered = pd.concat(
[df[mask_none], df[~mask_none].sort_values("NoteId")],
ignore_index=True,
)
note_old_to_new: dict[int, int] = {}
new_id = 1
rows = []
for _, r in df_ordered.iterrows():
old_id = int(r["NoteId"])
note_old_to_new[old_id] = new_id
rows.append((
new_id,
str(r["NoteName"]).strip(),
clean(r["TheNote"]) or "",
1,
CREATED_BY, NOW,
None, None,
None, None,
))
new_id += 1
sql = """
INSERT OR IGNORE INTO reportnote
(id, note_name, note_content, is_active,
created_by, created_at, edited_by, edited_at,
deleted_by, deleted_at)
VALUES (?,?,?,?,?,?,?,?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "reportnote")
conn.commit()
print(f" β
{inserted} / {len(rows)} report notes inserted (id=1 β 'None').")
# ββββββββββββββββββββββββββββββββββββββββββ
# 6. TESTS
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 6. Seeding Tests ββ")
df = xls("Tests.xlsx")
df = df.dropna(subset=["TestName"])
test_old_to_new: dict[int, int] = {}
new_id = 1
rows = []
for _, r in df.iterrows():
old_id = int(r["TestId"])
old_dept_id = int(r["DepartmentId"])
old_sample_id = int(r["SampleTypeId"])
old_note_id = int(r["NoteId"]) if clean(r["NoteId"]) else None
new_dept_id = dept_old_to_new.get(old_dept_id)
new_sample_id = sample_old_to_new.get(old_sample_id)
new_note_id = note_old_to_new.get(old_note_id) if old_note_id else None
if new_dept_id is None:
print(f" β οΈ TestId={old_id} skipped: DepartmentId={old_dept_id} not found in map.")
continue
if new_sample_id is None:
print(f" β οΈ TestId={old_id} skipped: SampleTypeId={old_sample_id} not found in map.")
continue
test_old_to_new[old_id] = new_id
rows.append((
new_id,
str(r["TestName"]).strip(),
str(r["ShortTestName"]).strip() if clean(r["ShortTestName"]) else str(r["TestName"]).strip(),
new_dept_id,
new_sample_id,
new_note_id,
float(r["Price"]) if clean(r["Price"]) else 0.0,
clean(r["TestNotes"]),
clean(r["TestConditions"]),
1,
CREATED_BY, NOW,
None, None,
None, None,
))
new_id += 1
sql = """
INSERT OR IGNORE INTO testdefinition
(id, test_name, test_short_name, department_id, sample_type_id,
report_note_id, price, test_note, test_condition, is_available,
created_by, created_at, edited_by, edited_at, deleted_by, deleted_at)
VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "testdefinition")
conn.commit()
print(f" β
{inserted} / {len(rows)} tests inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# 7. TEST-PARAMETER LINKS (from Ranges)
# Source: unique (TestId, ParameterId) pairs in Ranges.xlsx
# where ParameterId != 0 and ParameterId exists in parmeters.xlsx
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 7. Seeding Test-Parameter links ββ")
df_ranges = xls("Ranges.xlsx")
seen_tp = set() # (new_test_id, new_param_id) dedup
rows = []
new_id = 1
tp_skip_test = 0
tp_skip_param = 0
for _, r in df_ranges.iterrows():
old_test_id = int(r["TestId"])
old_param_id = int(r["ParameterId"])
if old_param_id == 0:
continue # test-level range, no parameter link
new_test_id = test_old_to_new.get(old_test_id)
if new_test_id is None:
tp_skip_test += 1
continue
new_param_id = param_old_to_new.get(old_param_id)
if new_param_id is None:
tp_skip_param += 1 # orphaned V1 parameter β skip
continue
pair = (new_test_id, new_param_id)
if pair in seen_tp:
continue # already added this link
seen_tp.add(pair)
rows.append((new_id, new_test_id, new_param_id))
new_id += 1
sql = """
INSERT OR IGNORE INTO testparameter (id, test_id, parameter_id)
VALUES (?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "testparameter")
conn.commit()
if tp_skip_test:
print(f" βΉοΈ {tp_skip_test} rows skipped (TestId not in test map).")
if tp_skip_param:
print(f" βΉοΈ {tp_skip_param} rows skipped (ParameterId orphaned in V1).")
print(f" β
{inserted} / {len(rows)} test-parameter links inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# 8. TEST-DEVICE LINKS (from Ranges)
# Source: unique (TestId, MethodId) pairs in Ranges.xlsx
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 8. Seeding Test-Device links ββ")
seen_td = set() # (new_test_id, new_device_id) dedup
rows = []
new_id = 1
td_skip_test = 0
td_skip_device = 0
for _, r in df_ranges.iterrows():
old_test_id = int(r["TestId"])
old_device_id = int(r["MethodId"])
new_test_id = test_old_to_new.get(old_test_id)
if new_test_id is None:
td_skip_test += 1
continue
new_device_id = device_old_to_new.get(old_device_id)
if new_device_id is None:
td_skip_device += 1
continue
pair = (new_test_id, new_device_id)
if pair in seen_td:
continue
seen_td.add(pair)
rows.append((new_id, new_test_id, new_device_id))
new_id += 1
sql = """
INSERT OR IGNORE INTO testdevice (id, test_id, device_id)
VALUES (?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "testdevice")
conn.commit()
if td_skip_test:
print(f" βΉοΈ {td_skip_test} rows skipped (TestId not in test map).")
if td_skip_device:
print(f" βΉοΈ {td_skip_device} rows skipped (MethodId not in device map).")
print(f" β
{inserted} / {len(rows)} test-device links inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# 9. RANGES (V1 "TestRange")
# ββββββββββββββββββββββββββββββββββββββββββ
print("\nββ 9. Seeding Ranges ββ")
df = df_ranges # already loaded above β no need to re-read from disk
new_id = 1
rows = []
skipped = 0
orphaned_params = 0
for _, r in df.iterrows():
old_test_id = int(r["TestId"])
new_test_id = test_old_to_new.get(old_test_id)
if new_test_id is None:
skipped += 1
continue
old_param_id = int(r["ParameterId"])
if old_param_id == 0:
new_param_id = None
else:
new_param_id = param_old_to_new.get(old_param_id)
if new_param_id is None:
# ParameterId exists in Ranges but not in parmeters.xlsx
# (orphaned V1 record) β insert with parameter_id = NULL
orphaned_params += 1
new_param_id = None
old_device_id = int(r["MethodId"])
new_device_id = device_old_to_new.get(old_device_id)
rtype = range_type_map(r["RangeTypeId"])
rows.append((
new_id,
new_test_id,
new_param_id,
new_device_id,
clean(r["UnitName"]) or "",
gender_map(r["Gender"]),
int(r["AgeFrom"]),
int(r["AgeTo"]),
age_unit_map(r["AgeFromTypeId"]),
1 if int(r["Fasting"]) == 1 else 0,
rtype,
opt_float(r["NormalFrom"]),
opt_float(r["NormalTo"]),
None, None, # vlow
None, None, # low
None, None, # midlow
None, None, # midhigh
None, None, # high
None, None, # vhigh
None, None, # panic
clean(r["TextRange"]) if rtype == "text" else None,
1,
CREATED_BY, NOW,
None, None,
None, None,
))
new_id += 1
sql = """
INSERT OR IGNORE INTO testrange
(id, test_id, parameter_id, device_id,
unit, gender_type, age_from, age_to, age_unit,
fasting_required, range_type,
normal_from, normal_to,
vlow_from, vlow_to, low_from, low_to,
midlow_from, midlow_to, midhigh_from, midhigh_to,
high_from, high_to, vhigh_from, vhigh_to,
panic_less_than, panic_more_than,
text_range,
is_active, created_by, created_at,
edited_by, edited_at, deleted_by, deleted_at)
VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)
"""
inserted = safe_executemany(cur, sql, rows, "testrange")
conn.commit()
if skipped:
print(f" βΉοΈ {skipped} ranges skipped (TestId had no matching test in V1 export).")
if orphaned_params:
print(f" βΉοΈ {orphaned_params} ranges had orphaned ParameterIds β inserted with parameter_id=NULL.")
print(f" β
{inserted} / {len(rows)} ranges inserted.")
# ββββββββββββββββββββββββββββββββββββββββββ
# Re-enable FK enforcement now that all data is in place
# ββββββββββββββββββββββββββββββββββββββββββ
conn.execute("PRAGMA foreign_keys = ON;")
conn.close()
print("\nπ Migration complete β all tables seeded successfully.")
print("\nββ Summary ββββββββββββββββββββββββββββββ")
print(f" Parameters : {len(param_old_to_new)}")
print(f" Departments : {len(dept_old_to_new)}")
print(f" Sample Types : {len(sample_old_to_new)}")
print(f" Devices : {len(device_old_to_new)}")
print(f" Report Notes : {len(note_old_to_new)} (id=1 is 'None')")
print(f" Tests : {len(test_old_to_new)}")
print(f" Test-Param links : {len(seen_tp)}")
print(f" Test-Device links : {len(seen_td)}")
print(f" Ranges : {new_id - 1} (inserted: {inserted})")
if __name__ == "__main__":
try:
main()
except Exception as exc:
import traceback
print(f"\nπ₯ Migration failed: {exc}")
traceback.print_exc() |