Spaces:
Running
Running
File size: 69,546 Bytes
3b58069 4eaf9a0 b6d0007 e2fd471 4eaf9a0 3b58069 606dcc8 3b58069 4eaf9a0 3b58069 ccf23f2 21790a4 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 cb87c06 4eaf9a0 cb87c06 3b58069 cb87c06 3b58069 cb87c06 3b58069 cb87c06 3b58069 cb87c06 3b58069 4eaf9a0 3b58069 cb87c06 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 cb87c06 4eaf9a0 3b58069 cb87c06 3b58069 cb87c06 3b58069 4eaf9a0 cb87c06 3b58069 4eaf9a0 cb87c06 3b58069 cb87c06 4eaf9a0 3b58069 cb87c06 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 ddbe479 3b58069 4eaf9a0 94ee684 4eaf9a0 fff2f80 4eaf9a0 d300238 4eaf9a0 d300238 4eaf9a0 d300238 4eaf9a0 d300238 4eaf9a0 d300238 4eaf9a0 d300238 4eaf9a0 3b58069 08077ef ddbe479 08077ef ddbe479 4db2f42 f35e60a ddbe479 ccf23f2 f35e60a fff2f80 f35e60a ddbe479 ccf23f2 ddbe479 ccf23f2 ddbe479 ccf23f2 f35e60a ccf23f2 ddbe479 ccf23f2 f35e60a ccf23f2 f35e60a ccf23f2 ddbe479 ccf23f2 4db2f42 ccf23f2 ddbe479 f35e60a ccf23f2 f35e60a ddbe479 ccf23f2 ddbe479 21790a4 08077ef 21790a4 08077ef 21790a4 3b58069 4eaf9a0 d300238 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 d300238 3b58069 d300238 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 4eaf9a0 3b58069 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 |
import logging
import os
import subprocess
try:
result = subprocess.run(['bash', 'install.sh'], check=True)
except subprocess.CalledProcessError as e:
print(f"The install script failed with return code {e.returncode}")
logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)
import gradio as gr
import torah
import bible
import quran
import hindu
import tripitaka
from utils import number_to_ordinal_word, custom_normalize, date_to_words, translate_date_to_words
from gematria import calculate_gematria, strip_diacritics
import pandas as pd
from deep_translator import GoogleTranslator
from gradio_calendar import Calendar
from datetime import datetime, timedelta
import math
import json
import re
import sqlite3
from collections import defaultdict
from typing import List, Tuple
# import rich # Removed rich
# from fuzzywuzzy import fuzz # Removed fuzzywuzzy
import calendar
import translation_utils
import hashlib
import copy
from collections import Counter
translation_utils.create_translation_table()
# Create a translator instance *once* globally
translator = GoogleTranslator(source='auto', target='auto')
LANGUAGES_SUPPORTED = translator.get_supported_languages(as_dict=True)
LANGUAGE_CODE_MAP = LANGUAGES_SUPPORTED # Use deep_translator's mapping directly
# --- Constants ---
DATABASE_FILE = 'gematria.db'
MAX_PHRASE_LENGTH_LIMIT = 20
ELS_CACHE_DB = "els_cache.db"
DATABASE_TIMEOUT = 60
# --- ELS Cache Functions ---
def create_els_cache_table():
if not os.path.exists(ELS_CACHE_DB):
with sqlite3.connect(ELS_CACHE_DB) as conn:
conn.execute('''
CREATE TABLE IF NOT EXISTS els_cache (
query_hash TEXT PRIMARY KEY,
function_name TEXT,
args TEXT,
kwargs TEXT,
results TEXT
)
''')
# --- Database Initialization ---
def initialize_database():
global conn
conn = sqlite3.connect(DATABASE_FILE)
cursor = conn.cursor()
cursor.execute('''
CREATE TABLE IF NOT EXISTS results (
gematria_sum INTEGER,
words TEXT,
translation TEXT,
book TEXT,
chapter INTEGER,
verse INTEGER,
phrase_length INTEGER,
word_position TEXT,
PRIMARY KEY (gematria_sum, words, book, chapter, verse, word_position)
)
''')
cursor.execute('''
CREATE INDEX IF NOT EXISTS idx_results_gematria
ON results (gematria_sum)
''')
cursor.execute('''
CREATE TABLE IF NOT EXISTS processed_books (
book TEXT PRIMARY KEY,
max_phrase_length INTEGER
)
''')
conn.commit()
# --- Initialize Database ---
initialize_database()
# --- ELS Cache Functions ---
def create_els_cache_table():
with sqlite3.connect(ELS_CACHE_DB) as conn:
try:
conn.execute('''
CREATE TABLE IF NOT EXISTS els_cache (
query_hash TEXT PRIMARY KEY,
function_name TEXT,
args TEXT,
kwargs TEXT,
results TEXT
)
''')
except sqlite3.OperationalError as e:
logger.error(f"Error creating table: {e}")
def get_query_hash(func, args, kwargs):
key = (func.__name__, args, kwargs)
return hashlib.sha256(json.dumps(key).encode()).hexdigest()
def cached_process_json_files(func, *args, **kwargs):
# Create a dictionary to store the parameters
params = {
"function": f"{func.__module__}.{func.__name__}"
}
# Add the positional arguments with their names
arg_names = func.__code__.co_varnames[:func.__code__.co_argcount]
for name, value in zip(arg_names, args):
params[name] = value
# Add the keyword arguments
for name, value in kwargs.items():
params[name] = value
# Convert the parameters to a JSON string
params_json = json.dumps(params)
# Use the parameters JSON string to generate the query hash
query_hash = get_query_hash(func, params_json, "")
# Ensure the table exists before any operations
create_els_cache_table()
try:
with sqlite3.connect(ELS_CACHE_DB, timeout=DATABASE_TIMEOUT) as conn:
cursor = conn.cursor()
cursor.execute(
"SELECT results FROM els_cache WHERE query_hash = ?", (query_hash,))
result = cursor.fetchone()
if result:
logger.info(f"Cache hit for query: {query_hash}")
return json.loads(result[0])
except sqlite3.Error as e:
logger.error(f"Database error checking cache: {e}")
logger.info(f"Cache miss for query: {query_hash}")
results = func(*args, **kwargs)
try:
with sqlite3.connect(ELS_CACHE_DB, timeout=DATABASE_TIMEOUT) as conn:
cursor = conn.cursor()
cursor.execute(
"INSERT INTO els_cache (query_hash, function_name, args, kwargs, results) VALUES (?, ?, ?, ?, ?)",
(query_hash, params["function"], params_json, json.dumps({}), json.dumps(results)))
conn.commit()
except sqlite3.Error as e:
logger.error(f"Database error caching results: {e}")
return results
# --- Helper Functions (from Network app.py) ---
def flatten_text(text: List) -> str:
if isinstance(text, list):
return " ".join(flatten_text(item) if isinstance(item, list) else item for item in text)
return text
def search_gematria_in_db(gematria_sum: int, max_words: int) -> List[Tuple[str, str, int, int, int, str]]:
global conn
with sqlite3.connect(DATABASE_FILE) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT words, book, chapter, verse, phrase_length, word_position
FROM results
WHERE gematria_sum = ? AND phrase_length <= ?
''', (gematria_sum, max_words))
results = cursor.fetchall()
return results
def get_most_frequent_phrase(results):
phrase_counts = defaultdict(int)
for words, book, chapter, verse, phrase_length, word_position in results:
phrase_counts[words] += 1
most_frequent_phrase = max(phrase_counts, key=phrase_counts.get) if phrase_counts else None
return most_frequent_phrase
# --- Functions from BOS app.py ---
def create_language_dropdown(label, default_value='English', show_label=True):
return gr.Dropdown(
choices=list(LANGUAGE_CODE_MAP.keys()),
label=label,
value=default_value,
show_label=show_label
)
def calculate_gematria_sum(text, date_words):
if text or date_words:
combined_input = f"{text} {date_words}"
logger.info(f"searching for input: {combined_input}")
numbers = re.findall(r'\d+', combined_input)
text_without_numbers = re.sub(r'\d+', '', combined_input)
number_sum = sum(int(number) for number in numbers)
text_gematria = calculate_gematria(strip_diacritics(text_without_numbers))
total_sum = text_gematria + number_sum
return total_sum
else:
return None
def perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk,
include_torah, include_bible, include_quran, include_hindu, include_tripitaka):
if step == 0 or rounds_combination == "0,0":
return None
results = {}
length = 0
selected_language_long = tlang
tlang = LANGUAGES_SUPPORTED.get(selected_language_long)
if tlang is None:
tlang = "en"
logger.warning(
f"Unsupported language selected: {selected_language_long}. Defaulting to English (en).")
if include_torah:
logger.debug(
f"Arguments for Torah: {(1, 39, step, rounds_combination, length, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)}")
results["Torah"] = cached_process_json_files(torah.process_json_files, 1, 39, step, rounds_combination, length,
tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)
else:
results["Torah"] = []
if include_bible:
results["Bible"] = cached_process_json_files(bible.process_json_files, 40, 66, step, rounds_combination,
length,
tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)
else:
results["Bible"] = []
if include_quran:
results["Quran"] = cached_process_json_files(quran.process_json_files, 1, 114, step, rounds_combination,
length,
tlang, strip_spaces, strip_in_braces, strip_diacritics_chk)
else:
results["Quran"] = []
if include_hindu:
results["Rig Veda"] = cached_process_json_files(
hindu.process_json_files, 1, 10, step, rounds_combination, length, tlang, False, strip_in_braces,
strip_diacritics_chk)
else:
results["Rig Veda"] = []
if include_tripitaka:
results["Tripitaka"] = cached_process_json_files(
tripitaka.process_json_files, 1, 52, step, rounds_combination, length, tlang, strip_spaces,
strip_in_braces, strip_diacritics_chk)
else:
results["Tripitaka"] = []
return results
def add_24h_projection(results_dict):
for book_name, results in results_dict.items():
num_results = len(results)
if num_results > 0:
time_interval = timedelta(minutes=24 * 60 / num_results)
current_time = datetime.min.time()
for i in range(num_results):
next_time = (datetime.combine(datetime.min, current_time) + time_interval).time()
time_range_str = f"{current_time.strftime('%H:%M')}-{next_time.strftime('%H:%M')}"
results[i]['24h Projection'] = time_range_str
current_time = next_time
return results_dict
def add_monthly_projection(results_dict, selected_date):
if selected_date is None:
return results_dict
for book_name, results in results_dict.items():
num_results = len(results)
if num_results > 0:
days_in_month = calendar.monthrange(selected_date.year, selected_date.month)[1]
total_seconds = (days_in_month - 1) * 24 * 3600
seconds_interval = total_seconds / num_results
start_datetime = datetime(selected_date.year, selected_date.month, 1)
current_datetime = start_datetime
for i in range(num_results):
next_datetime = current_datetime + timedelta(seconds=seconds_interval)
current_date = current_datetime.date()
next_date = next_datetime.date()
date_range_str = f"{current_date.strftime('%h %d')} - {next_date.strftime('%h %d')}"
results[i]['Monthly Projection'] = date_range_str
current_datetime = next_datetime
current_date = next_datetime.date()
return results_dict
def add_yearly_projection(results_dict, selected_date):
if selected_date is None:
return results_dict
for book_name, results in results_dict.items():
num_results = len(results)
if num_results > 0:
days_in_year = 366 if calendar.isleap(selected_date.year) else 365
total_seconds = (days_in_year - 1) * 24 * 3600
seconds_interval = total_seconds / num_results
start_datetime = datetime(selected_date.year, 1, 1)
current_datetime = start_datetime
for i in range(num_results):
next_datetime = current_datetime + timedelta(seconds=seconds_interval)
current_date = current_datetime.date()
next_date = next_datetime.date()
date_range_str = f"{current_date.strftime('%b %d')} - {next_date.strftime('%b %d')}"
results[i]['Yearly Projection'] = date_range_str
current_datetime = next_datetime
return results_dict
def sort_results(results):
def parse_time(time_str):
try:
hours, minutes = map(int, time_str.split(':'))
return hours * 60 + minutes
except ValueError:
return 24 * 60
return sorted(results, key=lambda x: (
parse_time(x.get('24h Projection', '23:59').split('-')[0]),
parse_time(x.get('24h Projection', '23:59').split('-')[1])
))
def extract_rounds_combinations():
"""Extracts unique rounds combinations from the database."""
combinations = set()
try:
with sqlite3.connect(ELS_CACHE_DB) as conn:
cursor = conn.cursor()
cursor.execute("SELECT args FROM els_cache")
all_args = cursor.fetchall()
for args_tuple in all_args:
args_str = args_tuple[0]
try:
args_json = json.loads(args_str)
if 'rounds' in args_json:
combinations.add(args_json['rounds'])
except json.JSONDecodeError:
logger.error(f"Could not decode JSON for args: {args_str}")
except sqlite3.Error as e:
logger.error(f"Database error: {e}")
logger.info(f"Found unique rounds combinations: {combinations}")
return ["All"] + sorted(list(combinations))
def update_rounds_dropdown():
new_choices = extract_rounds_combinations()
return new_choices
def perform_gematria_calculation_for_date_range(start_date, end_date):
logger.debug(f"Calculating date gematria for range: {start_date} - {end_date}")
results = {}
delta = timedelta(days=1)
current_date = start_date
while current_date <= end_date:
date_string = current_date.strftime("%Y-%m-%d")
date_words = date_to_words(date_string)
date_gematria = calculate_gematria_sum(date_words, "") # Angepasst, um der Funktion calculate_gematria_sum zu entsprechen
results[date_string] = {
"date_words": date_words,
"date_gematria": date_gematria,
}
current_date += delta
logger.debug(f"Finished calculating date gematria.")
return results
def find_matching_dates(date_gematrias, names, search_journal_sum):
logger.debug(f"Searching for matches with journal sum: {search_journal_sum}")
matching_dates = {}
for name in names:
name_gematria = calculate_gematria_sum(name, "") # Angepasst, um der Funktion calculate_gematria_sum zu entsprechen
target_date_gematria = search_journal_sum - name_gematria if name_gematria is not None else None
logger.debug(f"Name: {name}, Gematria: {name_gematria}, Target Date Gematria: {target_date_gematria}")
if target_date_gematria is not None:
for date_str, date_data in date_gematrias.items():
if date_data["date_gematria"] == target_date_gematria:
if name not in matching_dates:
matching_dates[name] = []
matching_dates[name].append(date_str)
logger.debug(f"Matches for {name}: {matching_dates.get(name, [])}")
return matching_dates
def find_shared_journal_sums(date_gematrias, names):
"""Finds shared journal sums and formats output with names and dates together."""
logger.debug("Calculating shared journal sums...")
shared_sums = {}
name_gematrias = {name: calculate_gematria_sum(name, "") for name in names}
for date_str, date_data in date_gematrias.items():
date_gematria = date_data["date_gematria"]
for name, name_gematria in name_gematrias.items():
journal_sum = date_gematria + name_gematria
journal_sum_str = str(journal_sum) # Konvertiere den Schlüssel (journal_sum) in einen String
if journal_sum_str not in shared_sums:
shared_sums[journal_sum_str] = {}
if name not in shared_sums[journal_sum_str]:
shared_sums[journal_sum_str][name] = []
shared_sums[journal_sum_str][name].append(date_str)
# Filter out sums not shared by at least two names and format output
result = {}
for journal_sum_str, data in shared_sums.items():
if len(data) >= 2:
result[journal_sum_str] = {}
for name, dates in data.items():
result[journal_sum_str][name] = dates
logger.debug(f"Shared Journal Sums: {result}")
return result
def calculate_and_find_dates(start_date, end_date, names_input, search_journal_sum, find_shared=False):
names = [n.strip() for n in names_input.split("\n") if n.strip()]
date_gematrias = perform_gematria_calculation_for_date_range(start_date, end_date)
if find_shared:
shared_sums = find_shared_journal_sums(date_gematrias, names)
return None, shared_sums
else:
matching_dates = find_matching_dates(date_gematrias, names, int(search_journal_sum))
return matching_dates, None
# --- Main Gradio App ---
with gr.Blocks() as app:
with gr.Tab("ELS Search"):
with gr.Column():
with gr.Row():
tlang = create_language_dropdown("Target Language for Result Translation", default_value='english')
selected_date = Calendar(type="datetime", label="Date to investigate (optional)",
info="Pick a date from the calendar")
use_day = gr.Checkbox(label="Use Day", info="Check to include day in search", value=True)
use_month = gr.Checkbox(label="Use Month", info="Check to include month in search", value=True)
use_year = gr.Checkbox(label="Use Year", info="Check to include year in search", value=True)
date_language_input = create_language_dropdown(
"Language of the person/topic (optional) (Date Word Language)", default_value='english')
with gr.Row():
gematria_text = gr.Textbox(label="Name and/or Topic (required)",
value="Albert Einstein Mileva Marity-Einstein")
date_words_output = gr.Textbox(label="Date in Words Translated (optional)")
gematria_result = gr.Number(label="Journal Sum")
# with gr.Row():
with gr.Row():
step = gr.Number(label="Jump Width (Steps) for ELS")
float_step = gr.Number(visible=False, value=1)
half_step_btn = gr.Button("Steps / 2")
double_step_btn = gr.Button("Steps * 2")
with gr.Column():
round_x = gr.Number(label="Round (1)", value=1)
round_y = gr.Number(label="Round (2)", value=-1)
rounds_combination = gr.Textbox(label="Combined Rounds", value="1,-0.5,0.5,-1")
with gr.Row():
include_torah_chk = gr.Checkbox(label="Include Torah", value=True)
include_bible_chk = gr.Checkbox(label="Include Bible", value=True)
include_quran_chk = gr.Checkbox(label="Include Quran", value=True)
include_hindu_chk = gr.Checkbox(label="Include Rigveda", value=False)
include_tripitaka_chk = gr.Checkbox(label="Include Tripitaka", value=False)
strip_spaces = gr.Checkbox(label="Strip Spaces from Books", value=True)
strip_in_braces = gr.Checkbox(label="Strip Text in Braces from Books", value=True)
strip_diacritics_chk = gr.Checkbox(label="Strip Diacritics from Books", value=True)
translate_btn = gr.Button("Search with ELS")
# --- Output Components ---
markdown_output = gr.Dataframe(label="ELS Results")
most_frequent_phrase_output = gr.Textbox(label="Most Frequent Phrase in Network Search")
json_output = gr.JSON(label="JSON Output")
with gr.Tab("Cache Database Search"):
with gr.Column():
with gr.Row():
main_book_filter = gr.Dropdown(label="Filter by Main Book",
choices=["All", "Torah", "Bible", "Quran", "Rig Veda", "Tripitaka"],
value="Torah")
# Keine choices hier, nur das Label und den Initialwert
rounds_filter = gr.Dropdown(label="Filter by Rounds", allow_custom_value=True, value="1,-1")
with gr.Row():
search_type = gr.Radio(label="Search by",
choices=["Text in result_text", "Gematria Sum in results"],
value="Text in result_text")
with gr.Row():
search_mode = gr.Radio(label="Search Mode",
choices=["Exact Search", "Contains Word"],
value="Contains Word")
with gr.Row():
search_term = gr.Textbox(label="Search Term", visible=True)
gematria_sum_search = gr.Number(label="Gematria Sum", visible=False)
with gr.Row():
search_db_btn = gr.Button("Search Cache Database")
with gr.Row():
cache_search_results = gr.JSON(label="Cache Search Results")
def update_search_components(search_type):
if search_type == "Text in result_text":
return gr.Textbox.update(visible=True), gr.Number.update(visible=False)
else:
return gr.Textbox.update(visible=False), gr.Number.update(visible=True)
def search_cache_database(search_type, search_term, gematria_sum_search, main_book_filter, rounds_filter, search_mode):
"""Searches the cache database based on the selected filters and search term."""
results = []
search_term = strip_diacritics(search_term)
if main_book_filter == "All" and rounds_filter == "All" and not search_term and not gematria_sum_search:
return results
try:
with sqlite3.connect(ELS_CACHE_DB) as conn:
cursor = conn.cursor()
if search_type == "Text in result_text":
# Optimization: If only main_book_filter is selected, don't perform a full search
if main_book_filter != "All" and rounds_filter == "All" and not search_term:
return results
cursor.execute("SELECT * FROM els_cache")
all_results = cursor.fetchall()
columns = [desc[0] for desc in cursor.description]
for row in all_results:
row_dict = dict(zip(columns, row))
args_dict = json.loads(row_dict['args'])
function_name = row_dict['function_name']
# Function name filtering
include_result = False
if main_book_filter == "All":
include_result = True
elif main_book_filter == "Torah" and function_name == "torah.process_json_files":
include_result = True
elif main_book_filter == "Bible" and function_name == "bible.process_json_files":
include_result = True
elif main_book_filter == "Quran" and function_name == "quran.process_json_files":
include_result = True
elif main_book_filter == "Rig Veda" and function_name == "hindu.process_json_files":
include_result = True
elif main_book_filter == "Tripitaka" and function_name == "tripitaka.process_json_files":
include_result = True
if not include_result:
continue
# Rounds filtering
if rounds_filter != "All" and args_dict.get('rounds') != rounds_filter:
continue
try:
results_json = json.loads(row_dict['results'])
for result_entry in results_json:
if 'result_text' in result_entry:
if search_mode == "Exact Search" and search_term == result_entry['result_text']:
entry = {
'function_name': function_name,
'step': args_dict.get('step'),
'rounds': args_dict.get('rounds'),
'result': result_entry
}
results.append(entry)
elif search_mode == "Contains Word" and search_term in result_entry['result_text']:
entry = {
'function_name': function_name,
'step': args_dict.get('step'),
'rounds': args_dict.get('rounds'),
'result': result_entry
}
results.append(entry)
except (json.JSONDecodeError, TypeError) as e:
logger.error(f"Error processing row: {e}")
continue
elif search_type == "Gematria Sum in results":
# Optimization: If only main_book_filter is selected, don't perform a full search
if main_book_filter != "All" and rounds_filter == "All" and not gematria_sum_search:
return results
if not isinstance(gematria_sum_search, (int, float)):
return results
cursor.execute("SELECT * FROM els_cache")
all_results = cursor.fetchall()
columns = [desc[0] for desc in cursor.description]
for row in all_results:
row_dict = dict(zip(columns, row))
args_dict = json.loads(row_dict['args'])
function_name = row_dict['function_name']
# Function name filtering
include_result = False
if main_book_filter == "All":
include_result = True
elif main_book_filter == "Torah" and function_name == "torah.process_json_files":
include_result = True
elif main_book_filter == "Bible" and function_name == "bible.process_json_files":
include_result = True
elif main_book_filter == "Quran" and function_name == "quran.process_json_files":
include_result = True
elif main_book_filter == "Rig Veda" and function_name == "hindu.process_json_files":
include_result = True
elif main_book_filter == "Tripitaka" and function_name == "tripitaka.process_json_files":
include_result = True
if not include_result:
continue
# Rounds filtering
if rounds_filter != "All" and args_dict.get('rounds') != rounds_filter:
continue
try:
results_json = json.loads(row_dict['results'])
for result_entry in results_json:
if 'result_sum' in result_entry and result_entry[
'result_sum'] == gematria_sum_search:
entry = {
'function_name': function_name,
'step': args_dict.get('step'),
'rounds': args_dict.get('rounds'),
'result': result_entry
}
results.append(entry)
except (json.JSONDecodeError, TypeError) as e:
logger.error(f"Error processing row: {e}")
continue
# Sort results by gematria sum
results.sort(
key=lambda x: x['result']['result_sum'] if 'result' in x and 'result_sum' in x['result'] else 0)
return results
except sqlite3.Error as e:
logger.error(f"Database error: {e}")
return []
def update_search_components(search_type):
"""Updates the visibility of the search term and gematria sum input fields."""
if search_type == "Text in result_text":
return {"visible": True, "__type__": "update"}, {"visible": False, "__type__": "update"}
else:
return {"visible": False, "__type__": "update"}, {"visible": True, "__type__": "update"}
with gr.Tab("Date Range Synchronicity + Journal-sum Search"):
with gr.Row():
start_date_jr = Calendar(type="datetime", label="Start Date")
end_date_jr = Calendar(type="datetime", label="End Date")
with gr.Row():
names_input_jr = gr.Textbox(label="Names (one per line)", lines=5)
search_sum_jr = gr.Number(label="Search Journal Sum", precision=0)
with gr.Row():
calculate_btn_jr = gr.Button("Search Journal Sum")
shared_sums_btn_jr = gr.Button("Find Shared Journal Sums")
matching_dates_output_jr = gr.JSON(label="Matching Dates")
shared_sums_output_jr = gr.JSON(label="Shared Journal Sums")
calculate_btn_jr.click(
lambda start_date, end_date, names_input, search_sum: calculate_and_find_dates(
start_date, end_date, names_input, search_sum, find_shared=False),
inputs=[start_date_jr, end_date_jr, names_input_jr, search_sum_jr],
outputs=[matching_dates_output_jr, shared_sums_output_jr]
)
shared_sums_btn_jr.click(
lambda start_date, end_date, names_input: calculate_and_find_dates(
start_date, end_date, names_input, 0, find_shared=True),
inputs=[start_date_jr, end_date_jr, names_input_jr],
outputs=[matching_dates_output_jr, shared_sums_output_jr]
)
with gr.Tab("Date Range ELS Journal Search"):
with gr.Row():
start_date_els = Calendar(type="datetime", label="Start Date")
end_date_els = Calendar(type="datetime", label="End Date")
with gr.Row():
names_input_els = gr.Textbox(label="Names (one per line)", lines=5)
with gr.Row():
search_type_els = gr.Radio(
label="Search by",
choices=["Text in result_text", "Gematria Sum in results"],
value="Text in result_text"
)
with gr.Row():
search_mode_els = gr.Radio(
label="Search Mode",
choices=["Exact Search", "Contains Word"],
value="Contains Word"
)
with gr.Row():
search_term_els = gr.Textbox(label="Search Term", visible=True)
gematria_sum_search_els = gr.Number(label="Gematria Sum", visible=False)
with gr.Row():
include_torah_chk_els = gr.Checkbox(label="Include Torah", value=True)
include_bible_chk_els = gr.Checkbox(label="Include Bible", value=True)
include_quran_chk_els = gr.Checkbox(label="Include Quran", value=True)
include_hindu_chk_els = gr.Checkbox(label="Include Rigveda", value=False)
include_tripitaka_chk_els = gr.Checkbox(label="Include Tripitaka", value=False)
with gr.Row():
translate_results_chk_els = gr.Checkbox(label="Translate Results to English", value=False)
with gr.Row():
sub_oscillation_search_chk_els = gr.Checkbox(label="Search in Sub-Oscillations", value=False) # Neue Checkbox
sub_oscillation_level_els = gr.Number(label="Sub-Oscillation Level (0 = off)", precision=0, value=1)
with gr.Row():
perform_search_btn_els = gr.Button("Perform Search")
filtered_results_output_els = gr.JSON(label="Filtered Results")
# Funktionen zur Aktualisierung der Sichtbarkeit der Sucheingabefelder
def update_search_components_els(search_type):
if search_type == "Text in result_text":
return gr.Textbox(visible=True), gr.Number(visible=False)
else:
return gr.Textbox(visible=False), gr.Number(visible=True)
search_type_els.change(
fn=update_search_components_els,
inputs=[search_type_els],
outputs=[search_term_els, gematria_sum_search_els]
)
def perform_els_search_for_gematria_sum(
gematria_sum,
include_torah,
include_bible,
include_quran,
include_hindu,
include_tripitaka
):
"""
Calls your actual ELS search function, returning a dict like:
{
"Torah": [ { "result_sum": ..., "result_text": ..., "source_language": ...}, ...],
"Bible": [...],
...
}
"""
return perform_els_search(
step=gematria_sum,
rounds_combination="1,-0.5,0.5,-1",
tlang="english",
strip_spaces=True,
strip_in_braces=True,
strip_diacritics_chk=True,
include_torah=include_torah,
include_bible=include_bible,
include_quran=include_quran,
include_hindu=include_hindu,
include_tripitaka=include_tripitaka
)
def perform_sub_oscillation_search(
base_results_list,
initial_gematria_sum,
level,
include_torah,
include_bible,
include_quran,
include_hindu,
include_tripitaka
):
"""
Recursively populates 'subresults' for each base entry, up to the specified level.
base_results_list: A list of dicts, each shaped like:
{
"book": "Torah",
"result": {
"result_sum": ...,
"result_text": ...
},
"subresults": []
}
initial_gematria_sum: The base sum from day+name (or from prior recursion).
level: how many sub-levels we still want to descend.
include_XXX: booleans for controlling which texts to include.
"""
if level <= 0:
return base_results_list
for base_entry in base_results_list:
parent_sum = base_entry["result"]["result_sum"]
combined_sum = initial_gematria_sum + parent_sum
# Next-level search
sub_search_results = perform_els_search_for_gematria_sum(
gematria_sum=combined_sum,
include_torah=include_torah,
include_bible=include_bible,
include_quran=include_quran,
include_hindu=include_hindu,
include_tripitaka=include_tripitaka
)
# Build child entries
child_entries = []
for book_name, res_list in sub_search_results.items():
for one_res in res_list:
child_entries.append({
"book": book_name,
"result": one_res,
"subresults": []
})
# Attach to subresults
base_entry["subresults"].extend(child_entries)
# Recurse deeper
perform_sub_oscillation_search(
base_entry["subresults"],
initial_gematria_sum,
level - 1,
include_torah,
include_bible,
include_quran,
include_hindu,
include_tripitaka
)
return base_results_list
def matches_criteria(item, search_type, search_term, gematria_sum_search, search_mode):
"""
Checks if a single item (a dict with 'result_text', 'result_sum', etc.)
matches the user’s chosen filter criteria.
item shape example:
{
"book": "Torah",
"result": {
"result_text": "foo bar",
"result_sum": 1234,
...
},
"subresults": [ ... ]
}
"""
result_text = item["result"].get("result_text", "")
result_sum = item["result"].get("result_sum", None)
if search_type == "Text in result_text":
if search_mode == "Exact Search":
return (result_text == search_term)
else: # "Contains Word"
return (search_term in result_text)
else:
# search_type == "Gematria Sum in results"
return (result_sum == gematria_sum_search)
def prune_tree_by_search_criteria(results_list, search_type, search_term, gematria_sum_search, search_mode):
"""
Recursively filters a list of items so that:
- An item is included if it directly matches the search criteria,
OR if any of its child subresults match (in which case we keep
the item *and* the matching children).
- This preserves parent chain for matching subresults.
returns a new, pruned list of items with the same nested structure,
but only containing the branches that match or lead to a match.
"""
pruned_list = []
for item in results_list:
# Recurse into subresults first
pruned_sub = prune_tree_by_search_criteria(
item["subresults"],
search_type,
search_term,
gematria_sum_search,
search_mode
)
does_item_match = matches_criteria(item, search_type, search_term, gematria_sum_search, search_mode)
# If the item itself matches OR any child matches
if does_item_match or len(pruned_sub) > 0:
# Make a copy of the item so we don't destroy the original
new_item = copy.deepcopy(item)
# Overwrite subresults with the pruned version
new_item["subresults"] = pruned_sub
pruned_list.append(new_item)
return pruned_list
def translate_subresults_recursive(subresults_list):
"""
Recursively translates the 'result_text' of each item in subresults_list.
We only visit items that remain in the filtered results.
"""
for sub_item in subresults_list:
text = sub_item["result"].get("result_text", "")
source_lang = sub_item["result"].get("source_language", "auto")
if text:
translated_text = translation_utils.get_translation(text, "en", source_lang)[0]
sub_item["result"]["translated_text"] = translated_text
# Recurse into deeper subresults
if sub_item["subresults"]:
translate_subresults_recursive(sub_item["subresults"])
def perform_date_range_els_search(
start_date,
end_date,
names_input,
search_type,
search_term,
gematria_sum_search,
search_mode,
include_torah,
include_bible,
include_quran,
include_hindu,
include_tripitaka,
translate_results,
sub_oscillation_search,
sub_oscillation_level
):
"""
- Builds a fully nested sub-oscillation structure if requested.
- Then prunes it so only matching items remain (plus parents).
- Finally, optionally translates the pruned items if requested.
- Returns the filtered (and optionally translated) structure.
"""
# 1) Compute gematria sums for all dates in the chosen range
names = [n.strip() for n in names_input.split("\n") if n.strip()]
date_gematrias = perform_gematria_calculation_for_date_range(start_date, end_date)
all_filtered_results = []
# 2) Loop over each date
for date_str, date_data in date_gematrias.items():
for name in names:
# base sum: day gematria + name gematria
name_gem = calculate_gematria_sum(name, "")
initial_gem = date_data["date_gematria"] + name_gem
date_words = date_data["date_words"]
search_path_basic = f"{name} {date_words}"
# 3) Do the base ELS search (this is the top-level results)
base_results = perform_els_search_for_gematria_sum(
gematria_sum=initial_gem,
include_torah=include_torah,
include_bible=include_bible,
include_quran=include_quran,
include_hindu=include_hindu,
include_tripitaka=include_tripitaka
)
# 4) Convert "base_results" into a uniform nested format
# shaped like { "0": {"book":..., "results": [ {...}, ... ]}, ... }
formatted_base_results = {}
idx_counter = 0
for book_name, book_res_list in base_results.items():
if book_res_list:
formatted_base_results[str(idx_counter)] = {
"book": book_name,
"results": []
}
for res in book_res_list:
formatted_base_results[str(idx_counter)]["results"].append({
"book": book_name,
"result": res,
"subresults": []
})
idx_counter += 1
# 5) Flatten out for sub-osc recursion
base_results_list = []
for val in formatted_base_results.values():
base_results_list.extend(val["results"])
# 6) If sub-oscillation is requested, build deeper levels
if sub_oscillation_search and sub_oscillation_level > 0 and base_results_list:
perform_sub_oscillation_search(
base_results_list,
initial_gem,
sub_oscillation_level,
include_torah,
include_bible,
include_quran,
include_hindu,
include_tripitaka
)
# 7) Now we prune (filter) the results according to the user’s search criteria
# For each "book" block, we filter the "results" array
pruned_base_results = {}
for key, block in formatted_base_results.items():
original_list = block["results"] # each is {book, result, subresults}
filtered_list = prune_tree_by_search_criteria(
original_list,
search_type,
search_term,
gematria_sum_search,
search_mode
)
# Keep only if we got something back
if filtered_list:
pruned_base_results[key] = {
"book": block["book"],
"results": filtered_list
}
# If there’s nothing left after filtering, skip adding
if not pruned_base_results:
continue
# 8) Build the final item for this date+name, with pruned results
final_item = {
"date": date_str,
"name": name,
"search_path_basic": search_path_basic,
"basic_gematria": initial_gem,
"basic_results": pruned_base_results
}
# 9) If translation is requested, only translate the pruned results
if translate_results:
# Recursively translate only the items in pruned_base_results
for block_key, block_val in final_item["basic_results"].items():
for entry in block_val["results"]:
txt = entry["result"].get("result_text", "")
src_lang = entry["result"].get("source_language", "auto")
if txt:
trans = translation_utils.get_translation(txt, "en", src_lang)[0]
entry["result"]["translated_text"] = trans
# And go deeper into subresults
if entry["subresults"]:
translate_subresults_recursive(entry["subresults"])
# 10) Add this final, fully filtered (and possibly translated) item
all_filtered_results.append(final_item)
# Return the fully processed set of results
return all_filtered_results
def remove_duplicates(dict_list):
"""
If you need to remove duplicates at any stage, you can call this,
but it's optional if your data doesn't require deduping.
"""
seen = set()
unique_list = []
for item in dict_list:
item_id = repr(item)
if item_id not in seen:
seen.add(item_id)
unique_list.append(item)
return unique_list
perform_search_btn_els.click(
perform_date_range_els_search,
inputs=[
start_date_els,
end_date_els,
names_input_els,
search_type_els,
search_term_els,
gematria_sum_search_els,
search_mode_els,
include_torah_chk_els,
include_bible_chk_els,
include_quran_chk_els,
include_hindu_chk_els,
include_tripitaka_chk_els,
translate_results_chk_els,
sub_oscillation_search_chk_els,
sub_oscillation_level_els
],
outputs=[filtered_results_output_els]
)
with gr.Tab("ELS Journal Gematria-sum Synchronicity search"):
with gr.Row():
start_date_comp = Calendar(type="datetime", label="Start Date")
end_date_comp = Calendar(type="datetime", label="End Date")
with gr.Row():
names_input_comp = gr.Textbox(label="Names (one per line)", lines=5)
with gr.Row():
sub_oscillation_level_comp = gr.Number(label="Sub-Oscillation Level", precision=0, value=0)
with gr.Row():
include_torah_chk_comp = gr.Checkbox(label="Include Torah", value=True)
include_bible_chk_comp = gr.Checkbox(label="Include Bible", value=True)
include_quran_chk_comp = gr.Checkbox(label="Include Quran", value=True)
include_hindu_chk_comp = gr.Checkbox(label="Include Rigveda", value=False)
include_tripitaka_chk_comp = gr.Checkbox(label="Include Tripitaka", value=False)
with gr.Row():
translate_results_chk_comp = gr.Checkbox(label="Translate Results to English", value=False)
with gr.Row():
common_gematria_results = gr.JSON(label="Common Gematria Results")
with gr.Row():
perform_search_btn_comp = gr.Button("Perform Search")
def perform_comprehensive_els_search(
start_date,
end_date,
names_input,
sub_oscillation_level,
include_torah,
include_bible,
include_quran,
include_hindu,
include_tripitaka,
translate_results
):
names = [n.strip() for n in names_input.split("\n") if n.strip()]
date_gematrias = perform_gematria_calculation_for_date_range(start_date, end_date)
all_results_by_date = {}
for date_str, date_data in date_gematrias.items():
all_results_by_date[date_str] = {}
for name in names:
name_gem = calculate_gematria_sum(name, "")
initial_gem = date_data["date_gematria"] + name_gem
base_results_list = []
base_results = perform_els_search_for_gematria_sum(
gematria_sum=initial_gem,
include_torah=include_torah,
include_bible=include_bible,
include_quran=include_quran,
include_hindu=include_hindu,
include_tripitaka=include_tripitaka
)
for book_name, res_list in base_results.items():
for one_res in res_list:
if not isinstance(one_res, dict) or "result_sum" not in one_res:
print(f"Warning: Invalid result format for {name} on {date_str}: {one_res}")
continue
base_results_list.append({
"book": book_name,
"result": one_res,
"subresults": []
})
if sub_oscillation_level > 0 and base_results_list:
perform_sub_oscillation_search(
base_results_list,
initial_gem,
sub_oscillation_level,
include_torah,
include_bible,
include_quran,
include_hindu,
include_tripitaka
)
all_results_by_date[date_str][name] = base_results_list
common_results = {}
for date_str, name_results in all_results_by_date.items():
common_results[date_str] = {}
sums_by_name = {}
all_sums_count = Counter()
for name, results in name_results.items():
sums_by_name[name] = set()
count_sums_recursive(results, all_sums_count)
extract_sums_recursive(results, sums_by_name[name])
ordered_common_sums = [item for item, count in all_sums_count.most_common() if all(item in sums_by_name[n] for n in sums_by_name)]
for common_sum in ordered_common_sums:
common_results[date_str][str(common_sum)] = {}
for name, results in name_results.items():
matching_items = []
for item in results:
if find_results_by_sum([item], common_sum):
item_copy = copy.deepcopy(item)
if translate_results:
translate_recursive(item_copy)
item_copy["subresults"] = find_results_by_sum(item.get("subresults", []), common_sum)
if translate_results:
for sub_item in item_copy["subresults"]:
translate_recursive(sub_item)
matching_items.append(item_copy)
if matching_items:
common_results[date_str][str(common_sum)][name] = matching_items
return common_results
def find_results_by_sum(results, target_sum):
matches = []
if isinstance(results, list):
for item in results:
matches.extend(find_results_by_sum(item, target_sum))
elif isinstance(results, dict):
if "result" in results and isinstance(results["result"], dict) and "result_sum" in results["result"]:
try:
result_sum = int(results["result"]["result_sum"])
if result_sum == target_sum:
matches.append(results)
except (TypeError, ValueError) as e:
print(f"Error comparing result_sum: {e}, Data: {results}")
if "subresults" in results:
matches.extend(find_results_by_sum(results["subresults"], target_sum))
return matches
def extract_sums_recursive(data, sums_set):
if isinstance(data, list):
for item in data:
extract_sums_recursive(item, sums_set)
elif isinstance(data, dict):
if "result" in data and isinstance(data["result"], dict) and "result_sum" in data["result"]:
try:
result_sum = int(data["result"]["result_sum"])
sums_set.add(result_sum)
except (TypeError, ValueError) as e:
print(f"Error extracting result_sum: {e}, Data: {data}")
if "subresults" in data:
extract_sums_recursive(data["subresults"], sums_set)
def count_sums_recursive(data, sums_counter):
if isinstance(data, list):
for item in data:
count_sums_recursive(item, sums_counter)
elif isinstance(data, dict):
if "result" in data and isinstance(data["result"], dict) and "result_sum" in data["result"]:
try:
result_sum = int(data["result"]["result_sum"])
sums_counter[result_sum] += 1
except (TypeError, ValueError) as e:
print(f"Error counting result_sum: {e}, Data: {data}")
if "subresults" in data:
count_sums_recursive(data["subresults"], sums_counter)
def translate_recursive(item):
if "result" in item and isinstance(item["result"], dict) and "result_text" in item["result"]:
text = item["result"].get("result_text", "")
source_lang = item["result"].get("source_language", "auto")
if text:
translated_text = translation_utils.get_translation(text, "en", source_lang)[0]
item["result"]["translated_text"] = translated_text
if "subresults" in item and isinstance(item["subresults"], list):
for sub in item["subresults"]:
translate_recursive(sub)
perform_search_btn_comp.click(
perform_comprehensive_els_search,
inputs=[
start_date_comp,
end_date_comp,
names_input_comp,
sub_oscillation_level_comp,
include_torah_chk_comp,
include_bible_chk_comp,
include_quran_chk_comp,
include_hindu_chk_comp,
include_tripitaka_chk_comp,
translate_results_chk_comp
],
outputs=[common_gematria_results]
)
# --- Event Handlers ---
search_type.change(
fn=update_search_components,
inputs=[search_type],
outputs=[search_term, gematria_sum_search]
)
search_db_btn.click(
fn=search_cache_database,
inputs=[search_type, search_term, gematria_sum_search, main_book_filter, rounds_filter, search_mode],
outputs=cache_search_results
)
def update_rounds_choices():
return gr.update(choices=extract_rounds_combinations()) # gr.update, nicht gr.Dropdown.update
app.load(fn=update_rounds_choices, inputs=None, outputs=rounds_filter)
main_book_filter.change(
fn=update_rounds_choices,
inputs=None, # No input needed here
outputs=rounds_filter
)
# rest of the handlers
def update_date_words(selected_date, date_language_input, use_day, use_month, use_year):
if selected_date is None:
return ""
if not use_year and not use_month and not use_day:
return translate_date_to_words(selected_date, date_language_input)
year = selected_date.year if use_year else None
month = selected_date.month if use_month else None
day = selected_date.day if use_day else None
if year is not None and month is not None and day is not None:
date_obj = selected_date
elif year is not None and month is not None:
date_obj = str(f"{year}-{month}")
elif year is not None:
date_obj = str(f"{year}")
else: # Return empty string if no date components are selected
return ""
date_in_words = date_to_words(date_obj)
translator = GoogleTranslator(source='auto', target=date_language_input)
translated_date_words = translator.translate(date_in_words)
return custom_normalize(translated_date_words)
def update_journal_sum(gematria_text, date_words_output):
sum_value = calculate_gematria_sum(gematria_text, date_words_output)
return sum_value, sum_value, sum_value
def update_rounds_combination(round_x, round_y):
return f"{int(round_x)},{int(round_y)}"
def update_step_half(float_step):
new_step = math.ceil(float_step / 2)
return new_step, float_step / 2
def update_step_double(float_step):
new_step = math.ceil(float_step * 2)
return new_step, float_step * 2
def find_closest_phrase(target_phrase, phrases):
best_match = None
best_score = 0
logging.debug(f"Target phrase for similarity search: {target_phrase}")
for phrase, _, _, _, _, _ in phrases:
word_length_diff = abs(len(target_phrase.split()) - len(phrase.split()))
similarity_score = fuzz.ratio(target_phrase, phrase)
combined_score = similarity_score - word_length_diff
logging.debug(f"Comparing with phrase: {phrase}")
logging.debug(
f"Word Length Difference: {word_length_diff}, Similarity Score: {similarity_score}, Combined Score: {combined_score}")
if combined_score > best_score:
best_score = combined_score
best_match = phrase
logging.debug(f"Closest phrase found: {best_match} with score: {best_score}")
return best_match
def perform_search(step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk,
include_torah, include_bible, include_quran, include_hindu, include_tripitaka, gematria_text,
date_words_output, selected_date):
els_results = perform_els_search(step, rounds_combination, tlang, strip_spaces, strip_in_braces,
strip_diacritics_chk, include_torah, include_bible, include_quran,
include_hindu,
include_tripitaka)
most_frequent_phrases = {}
combined_and_sorted_results = []
for book_name, book_results in els_results.items():
if book_results:
most_frequent_phrases[book_name] = ""
for result in book_results:
try:
gematria_sum = calculate_gematria(result['result_text'])
max_words = len(result['result_text'].split())
matching_phrases = search_gematria_in_db(gematria_sum, max_words)
max_words_limit = 20
while not matching_phrases and max_words < max_words_limit:
max_words += 1
matching_phrases = search_gematria_in_db(gematria_sum, max_words)
if matching_phrases:
most_frequent_phrase = get_most_frequent_phrase(matching_phrases)
most_frequent_phrases[book_name] = most_frequent_phrase
else:
# closest_phrase = find_closest_phrase(result['result_text'],
# search_gematria_in_db(gematria_sum, max_words_limit)) # Removed fuzzywuzzy
most_frequent_phrases[
book_name] = "" # closest_phrase or ""
result['Most Frequent Phrase'] = most_frequent_phrases[book_name]
if 'book' in result:
if isinstance(result['book'], int):
result['book'] = f"{book_name} {result['book']}."
combined_and_sorted_results.append(result)
except KeyError as e:
print(f"DEBUG: KeyError - Key '{e.args[0]}' not found in result. Skipping this result.")
continue
selected_language_long = tlang
tlang_short = LANGUAGES_SUPPORTED.get(selected_language_long)
if tlang_short is None:
tlang_short = "en"
logger.warning(f"Unsupported language selected: {selected_language_long}. Defaulting to English (en).")
phrases_to_translate = []
phrases_source_langs = []
results_to_translate = []
results_source_langs = []
for result in combined_and_sorted_results:
phrases_to_translate.append(result.get('Most Frequent Phrase', ''))
phrases_source_langs.append("he")
results_to_translate.append(result.get('result_text', ''))
results_source_langs.append(result.get("source_language", "auto"))
translated_phrases = translation_utils.batch_translate(phrases_to_translate, tlang_short,
phrases_source_langs)
translated_result_texts = translation_utils.batch_translate(results_to_translate, tlang_short,
results_source_langs)
for i, result in enumerate(combined_and_sorted_results):
result['translated_text'] = translated_result_texts.get(results_to_translate[i], None)
result['Translated Most Frequent Phrase'] = translated_phrases.get(phrases_to_translate[i], None)
updated_els_results = add_24h_projection(els_results)
updated_els_results = add_monthly_projection(updated_els_results, selected_date)
updated_els_results = add_yearly_projection(updated_els_results, selected_date)
combined_and_sorted_results = []
for book_results in updated_els_results.values():
combined_and_sorted_results.extend(book_results)
combined_and_sorted_results = sort_results(combined_and_sorted_results)
df = pd.DataFrame(combined_and_sorted_results)
df.index = range(1, len(df) + 1)
df.reset_index(inplace=True)
df.rename(columns={'index': 'Result Number'}, inplace=True)
for i, result in enumerate(combined_and_sorted_results):
result['Result Number'] = i + 1
search_config = {
"step": step,
"rounds_combination": rounds_combination,
"target_language": tlang,
"strip_spaces": strip_spaces,
"strip_in_braces": strip_in_braces,
"strip_diacritics": strip_diacritics_chk,
"include_torah": include_torah,
"include_bible": include_bible,
"include_quran": include_quran,
"include_hindu": include_hindu,
"include_tripitaka": include_tripitaka,
"gematria_text": gematria_text,
"date_words": date_words_output
}
output_data = {
"search_configuration": search_config,
"results": combined_and_sorted_results
}
json_data = output_data
combined_most_frequent = "\n".join(
f"{book}: {phrase}" for book, phrase in most_frequent_phrases.items())
return df, combined_most_frequent, json_data
# --- Event Triggers ---
round_x.change(update_rounds_combination, inputs=[round_x, round_y], outputs=rounds_combination)
round_y.change(update_rounds_combination, inputs=[round_x, round_y], outputs=rounds_combination)
selected_date.change(update_date_words, inputs=[selected_date, date_language_input, use_day, use_month, use_year],
outputs=[date_words_output])
date_language_input.change(update_date_words,
inputs=[selected_date, date_language_input, use_day, use_month, use_year],
outputs=[date_words_output])
gematria_text.change(update_journal_sum, inputs=[gematria_text, date_words_output],
outputs=[gematria_result, step, float_step])
date_words_output.change(update_journal_sum, inputs=[gematria_text, date_words_output],
outputs=[gematria_result, step, float_step])
half_step_btn.click(update_step_half, inputs=[float_step], outputs=[step, float_step])
double_step_btn.click(update_step_double, inputs=[float_step], outputs=[step, float_step])
translate_btn.click(
perform_search,
inputs=[step, rounds_combination, tlang, strip_spaces, strip_in_braces, strip_diacritics_chk, include_torah_chk,
include_bible_chk, include_quran_chk, include_hindu_chk, include_tripitaka_chk, gematria_text,
date_words_output, selected_date],
outputs=[markdown_output, most_frequent_phrase_output, json_output]
)
app.load(
update_date_words,
inputs=[selected_date, date_language_input, use_day, use_month, use_year],
outputs=[date_words_output]
)
use_day.change(
update_date_words,
inputs=[selected_date, date_language_input, use_day, use_month, use_year],
outputs=[date_words_output]
)
use_month.change(
update_date_words,
inputs=[selected_date, date_language_input, use_day, use_month, use_year],
outputs=[date_words_output]
)
use_year.change(
update_date_words,
inputs=[selected_date, date_language_input, use_day, use_month, use_year],
outputs=[date_words_output]
)
def checkbox_behavior(use_day_value, use_month_value):
if use_day_value:
return True, True
return use_month_value, True
use_day.change(checkbox_behavior, inputs=[use_day, use_month], outputs=[use_month, use_year])
use_month.change(checkbox_behavior, inputs=[use_day, use_month], outputs=[use_month, use_year])
if __name__ == "__main__":
app.launch(share=False)
|