Spaces:
Paused
Paused
File size: 71,244 Bytes
2d765ca | 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 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 | """
processor_utils.py
==================
Contains the static skill taxonomy (copied from the scraper service) and
re-exports the utility functions and constants used by cv_chunker.py
and job_matcher.py.
All other modules import from here:
from services.processor_utils import (
DEFAULT_SKILL_ALIASES, DEFAULT_CATEGORY_SKILLS, SOFT_SKILL_KEYS,
SENIORITY_ORDER, _TECH_LOC_BLACKLIST,
_normalize, _has_alias, _extract_skills, _infer_category,
_detect_seniority, _extract_years, compute_years_from_experience,
refine_seniority_with_years, _extract_cv_title,
)
"""
from __future__ import annotations
import logging
import re
from datetime import datetime as _dt
from typing import Any, Dict, List, Optional, Set, Tuple
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Configuration
# ---------------------------------------------------------------------------
DEFAULT_SKILL_ALIASES: Dict[str, List[str]] = {
"3d design": [
"3d design",
"blender",
"cinema 4d",
"3d modeling",
"3d rendering",
"maya",
],
"3pl": [
"3pl",
"third party logistics",
"outsourced logistics",
"logistics provider",
],
"acca": ["acca", "chartered accountant", "cpa", "cima", "icpak", "aca"],
"account management": [
"account management",
"key account management",
"client management",
"portfolio management",
],
"accounting": ["accounting", "accountancy", "bookkeeping", "accounts"],
"accounts payable": ["accounts payable", "vendor payments", "creditors", "ap"],
"accounts receivable": [
"accounts receivable",
"invoicing",
"debtors",
"collections",
"ar",
],
"active directory": [
"active directory",
"ldap",
"azure ad",
"microsoft entra",
"entra id",
"domain services",
],
"actuarial": ["actuarial", "actuary", "actuarial science", "actuarial analysis"],
"adaptability": ["adaptability", "adaptable", "flexible", "versatile"],
"adobe after effects": ["after effects", "adobe after effects", "motion graphics"],
"adobe illustrator": ["illustrator", "adobe illustrator", "vector graphics"],
"adobe photoshop": ["photoshop", "adobe photoshop"],
"adobe premiere": ["adobe premiere", "premiere pro", "video editing"],
"adobe xd": ["adobe xd", "xd"],
"affiliate marketing": [
"affiliate marketing",
"performance marketing",
"influencer marketing",
"partnership marketing",
],
"agile": [
"agile",
"agile methodology",
"agile development",
"agile framework",
"scrum",
"scrum master",
"safe",
"scaled agile",
],
"aml": [
"aml",
"anti-money laundering",
"anti money laundering",
"financial crime",
"fraud detection",
],
"android": ["android", "android studio", "android sdk", "android development"],
"angular": ["angular", "angularjs", "angular.js", "angular 2+"],
"ansible": ["ansible", "ansible playbook", "configuration management"],
"apache airflow": ["apache airflow", "airflow", "workflow orchestration", "dag"],
"apache hadoop": ["apache hadoop", "hadoop", "hdfs", "hive", "hbase"],
"apache spark": ["apache spark", "pyspark", "spark streaming", "spark sql"],
"arbitration": [
"arbitration",
"mediation",
"dispute resolution",
"adr",
"alternative dispute resolution",
],
"assessment": [
"assessment",
"grading",
"marking",
"examination",
"evaluation",
"formative assessment",
],
"attention to detail": [
"attention to detail",
"accuracy",
"meticulous",
"detail oriented",
"detail-oriented",
],
"auditing": [
"auditing",
"internal audit",
"external audit",
"audit",
"statutory audit",
"audit trail",
],
"autocad": ["autocad", "auto cad", "cad", "computer aided design", "drafting"],
"aws": [
"aws",
"amazon web services",
"ec2",
"s3",
"lambda",
"ecs",
"eks",
"rds",
"cloudformation",
"cdk",
],
"azure": [
"azure",
"microsoft azure",
"azure devops",
"azure functions",
"azure pipelines",
"arm templates",
"bicep",
],
"backup recovery": [
"backup",
"backup and recovery",
"backup strategy",
"data backup",
"veeam",
"commvault",
],
"bash": [
"bash",
"shell scripting",
"bash scripting",
"shell script",
"unix scripting",
],
"bloomberg": ["bloomberg", "bloomberg terminal", "bloomberg api"],
"brand design": ["brand design", "branding", "visual identity", "brand guidelines"],
"brand management": ["brand management", "brand strategy"],
"budgeting": [
"budgeting",
"budget management",
"budget planning",
"forecasting",
"variance analysis",
"capex",
"opex",
],
"business analysis": [
"business analysis",
"business analyst",
"requirements gathering",
"process improvement",
"business case",
],
"business process": [
"business process",
"bpm",
"business process management",
"process mapping",
"process documentation",
"sop",
],
"c": ["c language", "c programming", "embedded c"],
"c#": ["c#", "csharp", "c sharp"],
"c++": ["c++", "cpp", "c plus plus"],
"call centre": [
"call centre",
"call center",
"contact centre",
"contact center",
"inbound calls",
"outbound calls",
],
"canva": ["canva"],
"cash flow": ["cash flow", "cash management", "treasury", "liquidity management"],
"cassandra": ["cassandra", "apache cassandra"],
"cfa": ["cfa", "chartered financial analyst"],
"change management": [
"change management",
"organisational change",
"change leadership",
"transformation",
],
"chef": ["chef", "chef infra"],
"ci/cd": [
"ci/cd",
"ci cd",
"github actions",
"jenkins",
"gitlab ci",
"bitbucket pipelines",
"circle ci",
"travis ci",
"argocd",
"tekton",
],
"cisco": ["cisco", "ccna", "ccnp", "ccie", "cisco ios", "cisco networking"],
"civil 3d": ["civil 3d", "autocad civil 3d", "road design", "drainage design"],
"civil engineering": [
"civil engineering",
"structural engineering",
"geotechnical",
"quantity surveying",
"qs",
],
"classroom management": [
"classroom management",
"student management",
"behaviour management",
"student discipline",
],
"clickhouse": ["clickhouse"],
"clinical skills": [
"clinical skills",
"clinical assessment",
"clinical procedures",
"clinical competencies",
],
"clinical trials": [
"clinical trials",
"good clinical practice",
"gcp",
"clinical research",
"research protocol",
],
"cloud security": ["cloud security", "aws security", "azure security", "cspm"],
"cloudwatch": ["cloudwatch", "aws cloudwatch"],
"communication": [
"communication",
"interpersonal",
"verbal communication",
"written communication",
"correspondence",
],
"compensation": [
"compensation",
"benefits",
"compensation and benefits",
"remuneration",
"total rewards",
"salary benchmarking",
],
"computer vision": [
"computer vision",
"image recognition",
"object detection",
"opencv",
"image processing",
],
"conflict resolution": [
"conflict resolution",
"dispute management",
"mediation skills",
"grievance resolution",
],
"confluence": ["confluence", "atlassian confluence"],
"content writing": [
"content writing",
"copywriting",
"content creation",
"blog writing",
"content strategy",
"editorial",
],
"context api": ["context api", "react context"],
"contract drafting": [
"contract drafting",
"contract review",
"drafting agreements",
"legal drafting",
"contract management",
],
"conveyancing": [
"conveyancing",
"property law",
"land transactions",
"title search",
],
"core banking": [
"core banking",
"banking system",
"flexcube",
"temenos",
"finacle",
"murex",
"t24",
],
"corporate law": [
"corporate law",
"company law",
"corporate governance",
"company secretarial",
],
"credit analysis": [
"credit analysis",
"credit risk",
"loan appraisal",
"credit scoring",
"underwriting",
],
"crm": [
"crm",
"salesforce",
"hubspot",
"zoho crm",
"customer relationship management",
"pipedrive",
"dynamics crm",
],
"cro": [
"cro",
"conversion rate optimization",
"conversion optimisation",
"a/b testing",
"landing page optimization",
],
"css": ["css", "css3", "sass", "scss", "less", "stylesheets"],
"cucumber": [
"cucumber",
"gherkin",
"bdd",
"behavior driven development",
"behaviour driven development",
],
"culture": [
"culture",
"employee engagement",
"employer branding",
"employee experience",
],
"curriculum development": [
"curriculum development",
"curriculum design",
"lesson planning",
"scheme of work",
"curriculum mapping",
],
"customer satisfaction": [
"customer satisfaction",
"csat",
"net promoter score",
"nps",
"customer feedback",
],
"customer service": [
"customer service",
"client service",
"customer support",
"client relations",
"client care",
],
"customer success": [
"customer success",
"customer retention",
"account growth",
"upselling",
"cross-selling",
],
"customs": [
"customs",
"customs clearance",
"import export",
"trade compliance",
"incoterms",
],
"cypress": ["cypress", "cypress.io"],
"dart": ["dart"],
"data analysis": [
"data analysis",
"analytics",
"data analytics",
"business intelligence",
],
"data entry": [
"data entry",
"typing",
"data input",
"data capture",
"data processing",
],
"data governance": [
"data governance",
"data quality",
"data catalog",
"metadata management",
"data stewardship",
],
"data modeling": [
"data modeling",
"data modelling",
"star schema",
"dimensional modeling",
"entity relationship",
],
"data pipeline": [
"data pipeline",
"etl",
"elt",
"data integration",
"data ingestion",
"data warehouse",
"data lake",
"data lakehouse",
],
"data science": ["data science", "data scientist"],
"data visualization": [
"data visualization",
"data visualisation",
"data viz",
"dashboarding",
],
"databricks": ["databricks", "lakehouse"],
"datadog": ["datadog", "data dog"],
"dbt": ["dbt", "data build tool", "analytics engineering"],
"decision making": [
"decision making",
"decision-making",
"strategic thinking",
"judgement",
],
"dei": [
"diversity equity inclusion",
"dei",
"diversity and inclusion",
"equal opportunity",
"inclusive workplace",
],
"demand planning": [
"demand planning",
"demand forecasting",
"s&op",
"sales and operations planning",
],
"derivatives": [
"derivatives",
"futures",
"options",
"swaps",
"structured products",
],
"devsecops": [
"devsecops",
"security as code",
"shift left security",
"sast",
"dast",
],
"digital marketing": [
"digital marketing",
"online marketing",
"marketing campaigns",
"marketing strategy",
"performance marketing",
],
"distance learning": [
"distance learning",
"online teaching",
"remote teaching",
"blended learning",
"hybrid learning",
],
"django": ["django", "django rest framework", "drf"],
"docker": [
"docker",
"docker compose",
"dockerfile",
"containerization",
"containerisation",
],
"dotnet": [
".net",
".net core",
"dotnet",
"asp.net",
"asp.net core",
"net core",
".net framework",
".net maui",
"blazor",
"wpf",
"xamarin",
],
"due diligence": [
"due diligence",
"legal due diligence",
"commercial due diligence",
],
"dynamodb": ["dynamodb", "dynamo db", "amazon dynamodb"],
"dynatrace": ["dynatrace"],
"e-learning": [
"e-learning",
"elearning",
"lms",
"moodle",
"instructional design",
"online course development",
],
"ehr systems": [
"ehr",
"emr",
"electronic health record",
"epic",
"cerner",
"meditech",
"allscripts",
"hospital information system",
],
"elasticsearch": ["elasticsearch", "elastic search", "opensearch", "elk"],
"electrical engineering": [
"electrical engineering",
"power systems",
"plc",
"scada",
"instrumentation",
"hv",
"lv",
],
"elixir": ["elixir", "phoenix framework", "phoenix"],
"elk stack": ["elk stack", "logstash", "kibana", "elastic stack", "fluentd"],
"email marketing": [
"email marketing",
"mailchimp",
"email campaigns",
"newsletter",
"klaviyo",
"sendgrid",
],
"emotional intelligence": [
"emotional intelligence",
"eq",
"empathy",
"self-awareness",
],
"employee relations": [
"employee relations",
"labour relations",
"labor relations",
"grievance handling",
"disciplinary",
],
"employment law": [
"employment law",
"labour law",
"labor law",
"employment tribunal",
],
"entity framework": ["entity framework", "ef core", "entity framework core"],
"erp": [
"erp",
"enterprise resource planning",
"sap erp",
"oracle erp",
"dynamics 365",
"netsuite",
"odoo",
],
"event management": [
"event management",
"events coordination",
"venue management",
"conference management",
],
"excel analytics": [
"pivot tables",
"advanced excel",
"excel analytics",
"vlookup",
"xlookup",
],
"f#": ["f#", "fsharp", "f sharp"],
"facebook ads": [
"facebook ads",
"meta ads",
"social media advertising",
"paid social",
],
"fastapi": ["fastapi", "fast api"],
"figma": ["figma"],
"filing": [
"filing",
"document management",
"records management",
"file management",
"document control",
"record keeping",
],
"financial analysis": [
"financial analysis",
"financial modelling",
"financial modeling",
"financial reporting",
"financial planning",
"fp&a",
],
"financial compliance": [
"financial compliance",
"financial regulation",
"regulatory reporting",
"cbk",
"sec compliance",
],
"firestore": [
"firestore",
"firebase",
"cloud firestore",
"firebase realtime database",
],
"first aid": [
"first aid",
"cpr",
"bls",
"basic life support",
"acls",
"emergency response",
"resuscitation",
],
"flask": ["flask", "flask api"],
"flutter": ["flutter"],
"food safety": [
"food safety",
"haccp",
"food hygiene",
"food handling",
"food service",
],
"gaap": ["gaap", "generally accepted accounting principles", "us gaap", "uk gaap"],
"gcp": [
"gcp",
"google cloud",
"google cloud platform",
"cloud run",
"gke",
"bigquery",
"cloud functions",
],
"gdpr": ["gdpr", "data protection regulation", "ccpa", "data privacy law"],
"generative ai": [
"generative ai",
"gen ai",
"llm",
"large language model",
"gpt",
"langchain",
"hugging face",
"transformers",
"openai",
],
"git": [
"git",
"github",
"gitlab",
"bitbucket",
"version control",
"source control",
],
"go": ["golang", "go lang", "go programming"],
"google ads": [
"google ads",
"google adwords",
"ppc",
"pay per click",
"sem",
"paid search",
],
"google analytics": [
"google analytics",
"ga4",
"web analytics",
"google tag manager",
"gtm",
],
"google workspace": [
"google workspace",
"google docs",
"google drive",
"gsuite",
"g suite",
],
"grafana": ["grafana", "grafana dashboard"],
"graphic design": ["graphic design", "graphics", "visual design", "print design"],
"graphql": ["graphql", "graph ql", "apollo", "apollo server", "apollo client"],
"groovy": ["groovy"],
"grpc": ["grpc", "protocol buffers", "protobuf"],
"haskell": ["haskell"],
"health and safety": [
"health and safety",
"hse",
"ohse",
"occupational health",
"workplace safety",
"risk assessment",
],
"help desk": [
"help desk",
"helpdesk",
"it support",
"technical support",
"service desk",
"l1 support",
"l2 support",
],
"hibernate": ["hibernate", "jpa", "java persistence api", "orm"],
"high availability": [
"high availability",
"ha cluster",
"failover",
"load balancing",
"disaster recovery",
"rto",
"rpo",
"bcp",
"business continuity",
"fault tolerance",
],
"hl7": [
"hl7",
"hl7 fhir",
"fhir",
"healthcare interoperability",
"health data exchange",
],
"hospitality management": [
"hospitality management",
"hotel management",
"f&b",
"food and beverage",
"front office",
],
"housekeeping": [
"housekeeping",
"rooms division",
"facilities management",
"janitorial",
],
"hr compliance": [
"hr compliance",
"employment law",
"labour law",
"labor law",
"hr policy",
"hr regulation",
"employment relations",
],
"hris": [
"hris",
"hr information system",
"workday",
"bamboohr",
"zoho hr",
"oracle hcm",
"successfactors",
"peoplesoft",
],
"html": ["html", "html5", "semantic html"],
"hyper-v": ["hyper-v", "hyperv", "hyper v"],
"icd coding": [
"icd",
"icd-10",
"icd-11",
"medical coding",
"cpt coding",
"clinical coding",
],
"ifrs": ["ifrs", "international financial reporting standards"],
"infection control": [
"infection control",
"infection prevention",
"ips",
"sterilization",
"ppe",
],
"influxdb": ["influxdb", "influx db", "time series database", "timescaledb"],
"intellectual property": [
"intellectual property",
"ip law",
"trademark",
"patent",
"copyright",
"ip rights",
"ip management",
],
"inventory management": [
"inventory management",
"stock control",
"stock management",
"stock checking",
"inventory tracking",
],
"invision": ["invision", "invision studio"],
"ionic": ["ionic", "capacitor", "cordova", "hybrid app"],
"ios": ["ios", "xcode", "ios development", "iphone development"],
"iso 27001": ["iso 27001", "iso27001", "information security management", "isms"],
"itil": ["itil", "it service management", "itsm", "itil v4", "service lifecycle"],
"jasmine": ["jasmine"],
"java": ["java"],
"javascript": ["javascript", "js", "es6", "es2015", "ecmascript", "vanilla js"],
"jest": ["jest", "jest.js"],
"jetpack compose": ["jetpack compose", "android compose", "compose multiplatform"],
"jira": ["jira", "atlassian jira"],
"jmeter": ["jmeter", "apache jmeter", "load testing", "performance testing"],
"job analysis": [
"job analysis",
"job evaluation",
"job grading",
"job description",
],
"junit": ["junit", "junit5", "junit 4", "junit jupiter"],
"jwt": ["jwt", "json web token", "json web tokens"],
"kafka": ["kafka", "apache kafka", "kafka streams", "confluent", "event streaming"],
"kanban": ["kanban", "kanban board"],
"kotlin": ["kotlin", "kotlin multiplatform"],
"kubernetes": ["kubernetes", "k8s", "helm", "openshift", "container orchestration"],
"kyc": [
"kyc",
"know your customer",
"customer due diligence",
"cdd",
"customer onboarding compliance",
],
"laboratory": [
"laboratory",
"lab technician",
"medical laboratory",
"specimen processing",
"pathology",
],
"laravel": ["laravel"],
"lead generation": [
"lead generation",
"prospecting",
"cold calling",
"cold outreach",
"demand generation",
],
"leadership": [
"leadership",
"team leadership",
"people management",
"people leader",
],
"lean": [
"lean",
"lean manufacturing",
"lean six sigma",
"continuous improvement",
"kaizen",
"5s",
"value stream mapping",
],
"legal compliance": [
"legal compliance",
"regulatory affairs",
"compliance management",
"regulatory framework",
],
"legal research": [
"legal research",
"case research",
"statute interpretation",
"case law",
],
"legal tech": [
"legal tech",
"legaltech",
"contract automation",
"clm",
"e-discovery",
],
"legal writing": [
"legal writing",
"pleadings",
"legal opinions",
"memoranda",
"legal briefs",
],
"linux": [
"linux",
"ubuntu",
"centos",
"rhel",
"red hat",
"debian",
"fedora",
"unix",
"linux administration",
],
"litigation": [
"litigation",
"court proceedings",
"legal proceedings",
"advocacy",
"trial",
],
"live chat": ["live chat", "chat support", "intercom", "drift", "livechat"],
"lms": [
"learning management system",
"blackboard",
"canvas lms",
"google classroom",
"schoology",
"d2l",
"brightspace",
],
"logistics": [
"logistics",
"fleet management",
"transportation management",
"freight",
"delivery",
"last mile delivery",
],
"looker": ["looker", "looker studio", "google data studio"],
"lua": ["lua"],
"machine learning": [
"machine learning",
"ml",
"deep learning",
"neural networks",
"artificial intelligence",
"ai",
],
"mariadb": ["mariadb", "maria db"],
"marketing automation": [
"marketing automation",
"hubspot marketing",
"marketo",
"pardot",
"salesforce marketing cloud",
],
"mechanical engineering": [
"mechanical engineering",
"hvac",
"fluid mechanics",
"thermodynamics",
"piping",
],
"medical records": [
"medical records",
"electronic health records",
"medical documentation",
"health records",
],
"mental health": [
"mental health",
"psychiatry",
"psychology",
"counselling",
"counseling",
"psychotherapy",
"cbt",
],
"mentoring": [
"mentoring",
"mentorship",
"coaching",
"academic guidance",
"career coaching",
],
"mergers acquisitions": [
"mergers and acquisitions",
"m&a",
"corporate restructuring",
"merger",
"acquisition",
"takeover",
],
"message broker": [
"message broker",
"activemq",
"apache activemq",
"nats",
"zeromq",
"pub/sub",
"pubsub",
"azure service bus",
"aws sqs",
"google pub/sub",
],
"microservices": [
"microservices",
"micro-services",
"microservice architecture",
"service-oriented",
"soa",
"event-driven",
],
"microsoft excel": [
"microsoft excel",
"ms excel",
"excel",
"spreadsheets",
"google sheets",
],
"microsoft office": [
"microsoft office",
"ms office",
"office suite",
"office 365",
"microsoft 365",
],
"microsoft outlook": ["microsoft outlook", "ms outlook", "outlook"],
"microsoft powerpoint": [
"microsoft powerpoint",
"ms powerpoint",
"powerpoint",
"power point",
"google slides",
"presentations",
],
"microsoft word": ["microsoft word", "ms word", "word processor"],
"midwifery": [
"midwifery",
"obstetrics",
"maternity",
"antenatal",
"postnatal",
"labour ward",
],
"minute taking": ["minute taking", "meeting minutes", "notetaking", "secretarial"],
"miro": ["miro", "miroboard", "whiteboarding", "collaborative design"],
"mobx": ["mobx"],
"mocha": ["mocha", "mocha.js"],
"mongodb": ["mongodb", "mongo"],
"mqtt": ["mqtt", "hivemq", "mosquitto", "emqx", "iot messaging"],
"ms project": [
"ms project",
"microsoft project",
"project planning software",
"primavera",
],
"mysql": ["mysql"],
"negotiation": [
"negotiation",
"contract negotiation",
"deal closing",
"deal making",
],
"neo4j": ["neo4j", "graph database", "graph db"],
"nestjs": ["nestjs", "nest.js", "nestjs framework"],
"networking": [
"networking",
"network administration",
"network engineering",
"tcp/ip",
"dns",
"dhcp",
"vpn",
"lan",
"wan",
"sd-wan",
"sdwan",
"firewall",
"routing",
"switching",
"vlan",
"mpls",
],
"new relic": ["new relic", "newrelic"],
"next.js": ["next.js", "nextjs", "next js"],
"ngrx": ["ngrx", "ngxs"],
"nist": ["nist", "nist framework", "nist cybersecurity"],
"nlp": [
"nlp",
"natural language processing",
"text mining",
"sentiment analysis",
"text analytics",
],
"node.js": ["node", "node.js", "nodejs", "express", "express.js"],
"nunit": ["nunit"],
"nursing": [
"nursing",
"registered nurse",
"rn",
"clinical nursing",
"enrolled nurse",
"bscn",
],
"nutrition": [
"nutrition",
"dietetics",
"dietitian",
"nutritionist",
"food science",
],
"oauth": ["oauth", "oauth2", "oauth 2.0", "openid connect", "oidc", "pkce"],
"onboarding": [
"staff onboarding",
"new hire orientation",
"employee induction",
"new employee onboarding",
],
"openapi": [
"openapi",
"swagger",
"openapi spec",
"swagger ui",
"api spec",
"api documentation",
],
"opentelemetry": [
"opentelemetry",
"open telemetry",
"distributed tracing",
"jaeger",
"zipkin",
"observability",
],
"oracle db": ["oracle database", "oracle db", "oracle sql", "pl/sql"],
"owasp": ["owasp", "owasp top 10", "web application security", "appsec"],
"partnership": [
"partnership",
"channel sales",
"partnership management",
"alliances",
"channel management",
"reseller",
],
"patient care": [
"patient care",
"patient management",
"bedside manner",
"patient assessment",
"patient monitoring",
],
"payroll": [
"payroll",
"payroll processing",
"payroll management",
"payroll administration",
],
"pci dss": ["pci dss", "pci", "payment card industry"],
"penetration testing": [
"penetration testing",
"pen testing",
"pentesting",
"ethical hacking",
"red team",
"blue team",
"purple team",
],
"performance management": [
"performance management",
"performance review",
"appraisal",
"kpi management",
"okr",
],
"perl": ["perl"],
"pharmacy": [
"pharmacy",
"dispensing",
"pharmaceutical",
"pharmacology",
"medication management",
],
"photography": ["photography", "photo editing", "lightroom", "photo retouching"],
"php": ["php"],
"physiotherapy": [
"physiotherapy",
"physical therapy",
"rehabilitation",
"musculoskeletal",
],
"pinia": ["pinia"],
"postgresql": ["postgresql", "postgres", "supabase"],
"postman": ["postman", "api testing"],
"power bi": ["power bi", "powerbi", "power bi desktop", "dax"],
"powershell": ["powershell", "power shell", "ps script", "windows scripting"],
"pr": [
"pr",
"public relations",
"media relations",
"press release",
"communications",
],
"primavera": [
"primavera",
"oracle primavera",
"p6",
"primavera p6",
"project scheduling",
],
"prisma": ["prisma", "prisma orm"],
"problem solving": [
"problem solving",
"problem-solving",
"critical thinking",
"analytical thinking",
"troubleshooting",
],
"procurement": [
"procurement",
"purchasing",
"vendor management",
"sourcing",
"tendering",
"rfq",
"rfp",
],
"program management": [
"program management",
"programme management",
"portfolio management",
"pmo",
"project portfolio",
],
"project management": [
"project management",
"pmp",
"prince2",
"agile project management",
"project planning",
"waterfall",
"project delivery",
],
"prometheus": ["prometheus", "prometheus monitoring", "alertmanager"],
"property management": [
"property management",
"pms",
"property management system",
"opera pms",
"real estate management",
],
"prototyping": [
"prototyping",
"rapid prototyping",
"interactive prototype",
"high-fidelity prototype",
],
"public speaking": [
"public speaking",
"presentation skills",
"presenting",
"facilitation",
"keynote",
],
"puppet": ["puppet", "puppet enterprise"],
"pytest": ["pytest", "py.test"],
"python": ["python"],
"pytorch": ["pytorch", "torch"],
"qlik": ["qlik", "qlikview", "qliksense"],
"quality control": [
"quality control",
"qc",
"quality assurance",
"qa",
"iso",
"quality management",
"iso 9001",
"total quality management",
],
"quickbooks": ["quickbooks", "quick books"],
"r": ["r programming", "r language", "rstudio"],
"rabbitmq": ["rabbitmq", "rabbit mq", "amqp", "message queue"],
"radiology": [
"radiology",
"imaging",
"mri",
"ct scan",
"x-ray",
"radiography",
"ultrasound",
],
"rails": ["rails", "ruby on rails", "ror"],
"react": ["react", "react.js", "reactjs", "react hooks", "react native"],
"real estate": [
"real estate",
"property valuation",
"mortgage",
"property development",
"estate agency",
"letting",
],
"reconciliation": [
"reconciliation",
"bank reconciliation",
"account reconciliation",
],
"recruitment": [
"recruitment",
"recruiting",
"talent acquisition",
"hiring",
"staffing",
"talent sourcing",
"headhunting",
],
"redis": ["redis", "redis cache", "redis cluster"],
"redux": ["redux", "redux toolkit", "react redux", "rtk query"],
"reporting": [
"reporting",
"report writing",
"report generation",
"management reporting",
"progress reports",
],
"research": [
"research",
"academic research",
"literature review",
"research methodology",
"data collection",
],
"rest api": [
"rest api",
"restful api",
"restful apis",
"restful",
"api development",
"api design",
"web services",
"api integration",
],
"retail": [
"retail",
"retail sales",
"merchandising",
"point of sale",
"pos",
"fmcg",
],
"revenue management": [
"revenue management",
"yield management",
"revenue optimization",
"pricing strategy",
],
"revenue operations": [
"revenue operations",
"revops",
"sales operations",
"go-to-market",
"gtm",
],
"revit": [
"revit",
"bim",
"building information modeling",
"autodesk revit",
"building information modelling",
],
"risk management": [
"risk management",
"risk assessment",
"enterprise risk management",
"erm",
"risk framework",
"risk mitigation",
],
"robot framework": ["robot framework", "robotframework"],
"ruby": ["ruby"],
"rust": ["rust", "rust lang", "systems programming"],
"sage": ["sage", "sage accounting", "sage 50", "sage 200", "sage intacct"],
"sales": [
"sales",
"selling",
"business development",
"b2b sales",
"b2c sales",
"direct sales",
"inside sales",
"field sales",
],
"saml": [
"saml",
"saml 2.0",
"sso",
"single sign-on",
"single sign on",
"federated identity",
],
"sap": ["sap", "sap finance", "sap s/4hana", "sap fico", "sap hana"],
"scala": ["scala"],
"scheduling": [
"scheduling",
"calendar management",
"appointment setting",
"diary management",
"timetabling",
],
"scikit-learn": ["scikit-learn", "sklearn", "scikit learn"],
"selenium": ["selenium", "selenium webdriver", "selenium grid"],
"seo": [
"seo",
"search engine optimization",
"search engine optimisation",
"on-page seo",
"off-page seo",
"technical seo",
],
"sequelize": ["sequelize"],
"siem": [
"siem",
"security information and event management",
"soc analyst",
"security operations center",
"soc",
],
"six sigma": ["six sigma", "6 sigma", "dmaic", "black belt", "green belt"],
"sketch": ["sketch", "sketch app"],
"sla management": [
"sla",
"sla management",
"service level agreement",
"service level",
"response time",
],
"snowflake": ["snowflake", "snowflake data warehouse"],
"soap": ["soap", "soap api", "soap web service", "wsdl", "web service"],
"soc 2": ["soc 2", "soc2", "aicpa soc"],
"social media": [
"social media",
"social media management",
"instagram",
"facebook marketing",
"tiktok",
"linkedin marketing",
"twitter",
],
"solidworks": ["solidworks", "solid works", "parametric design"],
"special education": [
"special education",
"special needs",
"sen",
"inclusive education",
"learning disabilities",
],
"splunk": ["splunk", "splunk siem"],
"spring boot": [
"spring boot",
"spring",
"spring framework",
"spring mvc",
"spring security",
"spring cloud",
],
"sql": ["sql", "pl/sql", "t-sql", "structured query language"],
"sqlalchemy": ["sqlalchemy", "sql alchemy"],
"sqlite": ["sqlite"],
"sre": [
"sre",
"site reliability engineering",
"site reliability",
"reliability engineering",
],
"ssl tls": [
"ssl",
"tls",
"ssl/tls",
"certificates",
"pki",
"public key infrastructure",
],
"stakeholder management": [
"stakeholder management",
"stakeholder engagement",
"stakeholder communication",
"stakeholder relations",
],
"statistics": ["statistics", "statistical analysis", "spss", "stata", "minitab"],
"stem": ["stem", "science technology engineering mathematics", "stem education"],
"storage": [
"storage",
"nas",
"san",
"object storage",
"block storage",
"aws s3",
"azure blob",
"gcs",
],
"streaming": [
"real-time streaming",
"stream processing",
"event-driven architecture",
"cdc",
"change data capture",
],
"student counseling": [
"student counseling",
"student counselling",
"academic advising",
"student welfare",
"pastoral care",
],
"succession planning": [
"succession planning",
"talent pipeline",
"leadership development",
],
"supply chain": [
"supply chain",
"supply chain management",
"scm",
"end-to-end supply chain",
],
"surgical": [
"surgical",
"theatre",
"perioperative",
"scrub nurse",
"surgical technician",
],
"surveying": [
"surveying",
"land surveying",
"total station",
"gps surveying",
"topographic",
],
"svelte": ["svelte", "sveltekit"],
"swift": ["swift", "swiftui", "swift ui"],
"symfony": ["symfony"],
"tableau": ["tableau", "tableau desktop"],
"tailwind css": ["tailwind", "tailwind css"],
"talent management": [
"talent management",
"talent strategy",
"high potential",
"talent review",
],
"taxation": [
"taxation",
"tax",
"tax compliance",
"tax preparation",
"tax returns",
"vat",
"corporation tax",
"withholding tax",
],
"tdd": [
"tdd",
"test driven development",
"test-driven development",
"unit testing",
"integration testing",
"end-to-end testing",
],
"teaching": [
"teaching",
"instruction",
"lecturing",
"tutoring",
"classroom teaching",
"pedagogy",
],
"teamwork": [
"teamwork",
"team work",
"team player",
"collaboration",
"cross-functional",
],
"technical writing": [
"technical writing",
"technical documentation",
"user manuals",
"sop writing",
"standard operating procedures",
],
"telemedicine": [
"telemedicine",
"telehealth",
"remote patient monitoring",
"virtual clinic",
],
"tensorflow": ["tensorflow", "tf", "keras"],
"terraform": [
"terraform",
"infrastructure as code",
"iac",
"hashicorp terraform",
"pulumi",
],
"testng": ["testng", "test ng"],
"threat intelligence": [
"threat intelligence",
"threat hunting",
"cyber threat",
"ioc",
"indicators of compromise",
],
"ticketing systems": [
"ticketing",
"zendesk",
"freshdesk",
"jira service desk",
"servicenow",
"remedy",
"ivanti",
],
"time management": [
"time management",
"prioritization",
"prioritisation",
"multitasking",
"deadline management",
],
"trade finance": [
"trade finance",
"letter of credit",
"documentary credit",
"trade operations",
],
"training and development": [
"learning and development",
"l&d",
"employee training",
"talent development",
"workforce training",
"capability building",
],
"typeorm": ["typeorm", "type orm"],
"typescript": ["typescript", "ts"],
"ui design": ["ui design", "user interface design", "interface design"],
"ux design": [
"ux design",
"user experience design",
"ux research",
"usability",
"ux writing",
],
"vagrant": ["vagrant"],
"video editing": [
"video editing",
"video production",
"final cut pro",
"davinci resolve",
],
"virtual assistant": [
"virtual assistant",
"executive assistant",
"pa",
"personal assistant",
"administrative assistant",
],
"virtualization": [
"virtualization",
"virtualisation",
"virtual machine",
"vm management",
"kvm",
"proxmox",
],
"vmware": ["vmware", "vsphere", "vcenter", "esxi", "vsan", "vmware workstation"],
"vue": ["vue", "vue.js", "vuejs", "vue 3", "nuxt", "nuxt.js"],
"vuex": ["vuex"],
"vulnerability management": [
"vulnerability management",
"vulnerability assessment",
"vulnerability scanning",
"nessus",
"qualys",
],
"warehouse": [
"warehouse",
"stockroom",
"store room",
"stores",
"warehouse operations",
],
"warehouse management": [
"warehouse management system",
"wms",
"inventory system",
"warehouse operations",
],
"wealth management": [
"wealth management",
"asset management",
"portfolio management",
"investment management",
"fund management",
],
"windows server": [
"windows server",
"iis",
"windows administration",
"active directory",
],
"wireframing": ["wireframe", "wireframing", "low-fidelity"],
"workforce planning": [
"workforce planning",
"headcount planning",
"org design",
"organisational design",
],
"xero": ["xero"],
"xunit": ["xunit", "x unit"],
"zero trust": ["zero trust", "zero trust network", "ztna"],
"zustand": ["zustand"],
}
DEFAULT_CATEGORY_SKILLS: Dict[str, Set[str]] = {
"Admin & Office": {
"data entry",
"erp",
"customer service",
"scheduling",
"communication",
"microsoft powerpoint",
"warehouse",
"time management",
"inventory management",
"reporting",
"virtual assistant",
"microsoft office",
"google workspace",
"minute taking",
"attention to detail",
"teamwork",
"filing",
"adaptability",
"microsoft excel",
"microsoft word",
},
"Construction & Engineering": {
"electrical engineering",
"mechanical engineering",
"health and safety",
"surveying",
"primavera",
"civil 3d",
"autocad",
"revit",
"civil engineering",
"ms project",
"solidworks",
},
"Customer Support": {
"help desk",
"reporting",
"sla management",
"customer satisfaction",
"crm",
"communication",
"customer service",
"live chat",
"call centre",
"ticketing systems",
},
"Cybersecurity": {
"ssl tls",
"bash",
"iso 27001",
"networking",
"zero trust",
"pci dss",
"devsecops",
"python",
"nist",
"penetration testing",
"siem",
"soc 2",
"vulnerability management",
"threat intelligence",
"cloud security",
"linux",
"owasp",
"gdpr",
},
"Data & Analytics": {
"scikit-learn",
"power bi",
"data analysis",
"elasticsearch",
"python",
"r",
"pytorch",
"sql",
"tensorflow",
"tableau",
"data science",
"nlp",
"excel analytics",
"machine learning",
"statistics",
"data visualization",
"computer vision",
"qlik",
"microsoft excel",
"looker",
"generative ai",
},
"Data Engineering": {
"data modeling",
"aws",
"azure",
"redis",
"kafka",
"python",
"data pipeline",
"sql",
"data governance",
"dbt",
"postgresql",
"streaming",
"apache hadoop",
"databricks",
"gcp",
"apache spark",
"snowflake",
"apache airflow",
"mongodb",
"elasticsearch",
},
"Design & Creative": {
"canva",
"adobe xd",
"video editing",
"sketch",
"adobe illustrator",
"prototyping",
"figma",
"adobe photoshop",
"photography",
"ui design",
"wireframing",
"adobe after effects",
"miro",
"brand design",
"adobe premiere",
"ux design",
"invision",
"graphic design",
"3d design",
},
"Education & Training": {
"distance learning",
"mentoring",
"communication",
"curriculum development",
"research",
"lms",
"special education",
"e-learning",
"assessment",
"stem",
"teaching",
"classroom management",
"student counseling",
},
"Finance & Accounting": {
"credit analysis",
"derivatives",
"core banking",
"taxation",
"cash flow",
"financial compliance",
"wealth management",
"xero",
"quickbooks",
"accounting",
"risk management",
"financial analysis",
"cfa",
"sage",
"aml",
"payroll",
"acca",
"kyc",
"ifrs",
"sap",
"auditing",
"accounts payable",
"gaap",
"budgeting",
"bloomberg",
"microsoft excel",
"accounts receivable",
"trade finance",
"actuarial",
"reconciliation",
},
"Healthcare": {
"first aid",
"infection control",
"icd coding",
"mental health",
"radiology",
"physiotherapy",
"nursing",
"medical records",
"ehr systems",
"laboratory",
"clinical trials",
"pharmacy",
"telemedicine",
"nutrition",
"clinical skills",
"midwifery",
"patient care",
"surgical",
"hl7",
},
"Hospitality & Property": {
"property management",
"housekeeping",
"real estate",
"customer service",
"communication",
"hospitality management",
"event management",
"food safety",
"revenue management",
},
"Human Resources": {
"employee relations",
"microsoft excel",
"communication",
"workforce planning",
"recruitment",
"succession planning",
"talent management",
"hris",
"job analysis",
"onboarding",
"training and development",
"performance management",
"culture",
"hr compliance",
"compensation",
"dei",
},
"Infrastructure & Cloud": {
"bash",
"datadog",
"splunk",
"ansible",
"backup recovery",
"ci/cd",
"networking",
"sre",
"linux",
"windows server",
"itil",
"opentelemetry",
"high availability",
"hyper-v",
"powershell",
"storage",
"dynatrace",
"kubernetes",
"chef",
"prometheus",
"new relic",
"vagrant",
"vmware",
"cloudwatch",
"aws",
"azure",
"grafana",
"terraform",
"puppet",
"git",
"cisco",
"gcp",
"docker",
"virtualization",
"active directory",
"elk stack",
},
"Legal": {
"legal compliance",
"conveyancing",
"legal research",
"intellectual property",
"legal writing",
"litigation",
"mergers acquisitions",
"arbitration",
"corporate law",
"due diligence",
"contract drafting",
"employment law",
"legal tech",
},
"Marketing & Growth": {
"cro",
"content writing",
"affiliate marketing",
"crm",
"digital marketing",
"marketing automation",
"google ads",
"email marketing",
"google analytics",
"brand management",
"seo",
"social media",
"facebook ads",
"pr",
},
"Operations & Logistics": {
"3pl",
"supply chain",
"erp",
"demand planning",
"reporting",
"health and safety",
"customs",
"warehouse management",
"lean",
"logistics",
"procurement",
"six sigma",
"quality control",
"inventory management",
"project management",
},
"Sales & Business Dev": {
"revenue operations",
"business analysis",
"customer service",
"crm",
"communication",
"lead generation",
"negotiation",
"account management",
"partnership",
"sales",
"customer success",
"retail",
},
"Software Engineering": {
"bash",
"zustand",
"firestore",
"redux",
"flask",
"clickhouse",
"angular",
"css",
"jira",
"entity framework",
"dotnet",
"ngrx",
"sql",
"mqtt",
"swift",
"agile",
"ionic",
"neo4j",
"confluence",
"nlp",
"nunit",
"testng",
"junit",
"context api",
"kubernetes",
"postgresql",
"cypress",
"dynamodb",
"symfony",
"jmeter",
"elasticsearch",
"generative ai",
"jetpack compose",
"f#",
"ios",
"grpc",
"message broker",
"aws",
"scikit-learn",
"cassandra",
"kafka",
"prisma",
"python",
"graphql",
"rust",
"go",
"xunit",
"html",
"terraform",
"typescript",
"ruby",
"selenium",
"hibernate",
"machine learning",
"spring boot",
"gcp",
"oauth",
"mocha",
"computer vision",
"postman",
"microservices",
"rabbitmq",
"sqlalchemy",
"c",
"nestjs",
"ci/cd",
"ansible",
"influxdb",
"scala",
"android",
"flutter",
"redis",
"java",
"rails",
"fastapi",
"rest api",
"powershell",
"django",
"c++",
"jasmine",
"mobx",
"pytest",
"react",
"vuex",
"typeorm",
"laravel",
"php",
"elixir",
"dart",
"next.js",
"groovy",
"oracle db",
"mysql",
"openapi",
"robot framework",
"azure",
"javascript",
"kotlin",
"jwt",
"jest",
"svelte",
"pytorch",
"tdd",
"tensorflow",
"cucumber",
"pinia",
"mariadb",
"node.js",
"c#",
"saml",
"haskell",
"git",
"sequelize",
"tailwind css",
"mongodb",
"kanban",
"soap",
"sqlite",
"vue",
"docker",
},
}
SOFT_SKILL_KEYS: Set[str] = {
"public speaking",
"customer service",
"scheduling",
"communication",
"problem solving",
"leadership",
"negotiation",
"time management",
"emotional intelligence",
"stakeholder management",
"onboarding",
"decision making",
"reporting",
"customer satisfaction",
"mentoring",
"training and development",
"attention to detail",
"teamwork",
"filing",
"adaptability",
"conflict resolution",
}
SENIORITY_PATTERNS: Dict[str, List[str]] = {
"intern": [
"intern",
"internship",
"trainee",
"industrial attachment",
"attachment student",
"graduate trainee",
"pupil",
"cadet",
],
"junior": [
"junior",
"entry level",
"entry-level",
"assistant",
"fresh graduate",
"graduate",
"associate",
"junior officer",
"junior analyst",
"junior developer",
"junior engineer",
],
"mid": [
"mid",
"middle",
"officer",
"specialist",
"developer",
"designer",
"engineer",
"analyst",
"coordinator",
"technician",
"executive",
"consultant",
"representative",
],
"senior": [
"senior",
"lead",
"manager",
"head",
"principal",
"architect",
"director",
"vp",
"vice president",
"chief",
"cto",
"ceo",
"coo",
"cfo",
"superintendent",
"supervisor",
"managing",
"staff engineer",
"distinguished",
"fellow",
],
}
SENIORITY_ORDER: Dict[str, int] = {"intern": 0, "junior": 1, "mid": 2, "senior": 3}
_TECH_LOC_BLACKLIST: Set[str] = {
"splunk",
"nestjs",
"ansible",
"airflow",
"scala",
"android",
"nginx",
"node",
"postgres",
"flask",
"angular",
"flutter",
"golang",
"redis",
"bitbucket",
"mongo",
"jira",
"java",
"rails",
"spring",
"sql",
"swift",
"gitlab",
"ionic",
"django",
"confluence",
"oracle",
"react",
"kibana",
"kubernetes",
"github",
"laravel",
"dart",
"symfony",
"mysql",
"spark",
"express",
"aws",
"azure",
"kotlin",
"kafka",
"python",
"istio",
"figma",
"rust",
"svelte",
"grafana",
"terraform",
"apache",
"ruby",
"windows",
"nextjs",
"helm",
"boot",
"puppet",
"hadoop",
"gcp",
"jenkins",
"vue",
"linux",
"docker",
"slack",
}
TITLE_ROLE_WORDS: List[str] = [
"developer",
"engineer",
"programmer",
"architect",
"devops",
"officer",
"designer",
"assistant",
"accountant",
"manager",
"analyst",
"specialist",
"coordinator",
"director",
"executive",
"lead",
"scientist",
"strategist",
"advisor",
"trainer",
"consultant",
"researcher",
"technician",
"supervisor",
"associate",
"administrator",
"nurse",
"doctor",
"physician",
"pharmacist",
"therapist",
"clinician",
"midwife",
"radiographer",
"physiotherapist",
"auditor",
"bookkeeper",
"controller",
"treasurer",
"actuary",
"recruiter",
"salesperson",
"representative",
"agent",
"broker",
"teacher",
"instructor",
"lecturer",
"professor",
"tutor",
"admin",
"intern",
"student",
"cashier",
"marketing",
"procurement",
"buyer",
"dispatcher",
"operator",
"superintendent",
]
TITLE_PHRASE_RE = re.compile(
r"\b((?:(?:full[\s\-]?stack|front[\s\-]?end|back[\s\-]?end|senior|junior|lead|"
r"mid[\s\-]?level|entry[\s\-]?level|chief|head\s+of|staff|principal)?\s+)?(?:[\w\-]+\s){0,3}"
r"(?:developer|engineer|designer|analyst|manager|specialist|consultant|architect|"
r"programmer|researcher|officer|director|executive|scientist|trainer|accountant|"
r"nurse|doctor|pharmacist|therapist|teacher|instructor|lecturer|recruiter|"
r"coordinator|supervisor|administrator|technician|advisor|auditor|bookkeeper|"
r"physiotherapist|midwife|clinician|representative|salesperson|buyer|dispatcher|"
r"actuary|superintendent|operator))\b",
re.IGNORECASE,
)
# ---------------------------------------------------------------------------
# Normalisation helpers
# ---------------------------------------------------------------------------
def _normalize(text: str) -> str:
text = (text or "").lower()
text = text.replace("/", " ")
text = text.replace("_", " ")
text = re.sub(r"[^a-z0-9+.#\s-]", " ", text)
return re.sub(r"\s+", " ", text).strip()
_ALIAS_REGEX_CACHE = {}
def _has_alias(text_norm: str, alias: str) -> bool:
alias_norm = _normalize(alias)
if not alias_norm:
return False
pattern = _ALIAS_REGEX_CACHE.get(alias_norm)
if pattern is None:
pattern = re.compile(rf"(?<![a-z0-9]){re.escape(alias_norm)}(?![a-z0-9])")
_ALIAS_REGEX_CACHE[alias_norm] = pattern
return pattern.search(text_norm) is not None
# ---------------------------------------------------------------------------
# Skill extraction
# ---------------------------------------------------------------------------
_SKILL_PATTERN = None
_ALIAS_TO_CANONICAL = {}
def _get_skill_pattern():
global _SKILL_PATTERN, _ALIAS_TO_CANONICAL
if _SKILL_PATTERN is not None:
return _SKILL_PATTERN, _ALIAS_TO_CANONICAL
_ALIAS_TO_CANONICAL = {}
alias_list = []
for canon, ali_list in DEFAULT_SKILL_ALIASES.items():
for a in ali_list:
a_norm = _normalize(a)
if a_norm:
if a_norm not in _ALIAS_TO_CANONICAL:
_ALIAS_TO_CANONICAL[a_norm] = canon
alias_list.append(a_norm)
alias_list.sort(key=len, reverse=True)
pattern_str = "|".join(map(re.escape, alias_list))
_SKILL_PATTERN = re.compile(rf"(?<![a-z0-9])({pattern_str})(?![a-z0-9])")
return _SKILL_PATTERN, _ALIAS_TO_CANONICAL
def _extract_skills(
text: str,
aliases: Optional[Dict[str, List[str]]] = None,
) -> Set[str]:
text_norm = _normalize(text)
if aliases is None or aliases is DEFAULT_SKILL_ALIASES:
pattern, alias_map = _get_skill_pattern()
return {alias_map[match.group(1)] for match in pattern.finditer(text_norm)}
return {
canon
for canon, ali_list in aliases.items()
if any(_has_alias(text_norm, a) for a in ali_list)
}
# ---------------------------------------------------------------------------
# Category inference
# ---------------------------------------------------------------------------
_CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
"Admin & Office": [
"admin",
"office",
"stock",
"inventory",
"warehouse",
"cashier",
"receptionist",
"clerk",
],
"Software Engineering": [
"developer",
"engineer",
"programmer",
"frontend",
"backend",
"full stack",
"mobile",
"fullstack",
"software",
"devops",
],
"Infrastructure & Cloud": [
"infrastructure",
"cloud",
"sre",
"network",
"system administrator",
"sysadmin",
"it administrator",
"cloud engineer",
],
"Cybersecurity": [
"security",
"cybersecurity",
"cyber",
"infosec",
"soc analyst",
"penetration tester",
"ethical hacker",
],
"Design & Creative": [
"designer",
"ui",
"ux",
"creative",
"graphic",
"visual",
"illustrator",
"photographer",
],
"Marketing & Growth": [
"marketing",
"seo",
"content",
"social media",
"growth",
"digital",
"brand",
],
"Data & Analytics": [
"data analyst",
"analytics",
"machine learning",
"ai",
"scientist",
"bi analyst",
"business intelligence",
],
"Data Engineering": [
"data engineer",
"etl",
"data pipeline",
"data architect",
"analytics engineer",
],
"Finance & Accounting": [
"accountant",
"finance",
"accounting",
"auditor",
"bookkeeper",
"treasurer",
"payroll",
"tax",
"financial",
],
"Human Resources": [
"hr",
"human resource",
"recruitment",
"recruiter",
"talent",
"people",
"hris",
],
"Sales & Business Dev": [
"sales",
"business development",
"account manager",
"sales executive",
"representative",
],
"Healthcare": [
"nurse",
"doctor",
"clinical",
"medical",
"pharmacy",
"patient",
"health",
"therapist",
"midwife",
],
"Legal": [
"legal",
"lawyer",
"attorney",
"advocate",
"counsel",
"paralegal",
"solicitor",
],
"Education & Training": [
"teacher",
"lecturer",
"tutor",
"instructor",
"educator",
"academic",
"trainer",
"professor",
],
"Operations & Logistics": [
"logistics",
"supply chain",
"procurement",
"operations",
"fleet",
"warehouse manager",
"quality",
],
"Customer Support": [
"customer support",
"help desk",
"call centre",
"contact centre",
"customer care",
],
"Construction & Engineering": [
"civil",
"structural",
"mechanical",
"electrical",
"quantity surveyor",
"site engineer",
"construction",
],
"Hospitality & Property": [
"hotel",
"hospitality",
"property",
"real estate",
"housekeeping",
"f&b",
"restaurant",
],
}
def _infer_category(
text: str,
skills: Set[str],
category_skills: Optional[Dict[str, Set[str]]] = None,
) -> str:
if category_skills is None:
category_skills = DEFAULT_CATEGORY_SKILLS
text_norm = _normalize(text)
best, best_score = "Other", 0.0
for cat, cat_skills in category_skills.items():
skill_overlap = len(skills & cat_skills)
kw_hits = sum(
1 for kw in _CATEGORY_TITLE_KEYWORDS.get(cat, []) if kw in text_norm
)
score = skill_overlap * 2.0 + kw_hits * 1.25
if score > best_score:
best_score, best = score, cat
return best
# ---------------------------------------------------------------------------
# Years-of-experience extraction
# ---------------------------------------------------------------------------
def _extract_years(text: str) -> int:
text_norm = _normalize(text)
patterns = [
r"(\d+)\+?\s*(?:years|year|yrs|yr)\s*(?:of)?\s*(?:experience|exp)",
r"experience\s*(?:of)?\s*(\d+)\+?\s*(?:years|year|yrs|yr)",
r"(\d+)\+?\s*(?:years|year|yrs|yr)\s+(?:in\s+)?(?:the\s+)?(?:industry|field|software|development|practice|profession)",
]
years = [int(m.group(1)) for p in patterns for m in re.finditer(p, text_norm)]
return max(years) if years else 0
# ---------------------------------------------------------------------------
# Years from parsed experience date ranges
# ---------------------------------------------------------------------------
_MONTH_SHORT: Dict[str, int] = {
"jan": 1,
"feb": 2,
"mar": 3,
"apr": 4,
"may": 5,
"jun": 6,
"jul": 7,
"aug": 8,
"sep": 9,
"oct": 10,
"nov": 11,
"dec": 12,
}
def _parse_date_token(token: str) -> Optional[_dt]:
token = token.strip().lower()
if re.match(r"present|current|now|ongoing|till\s*date|to\s*date", token):
return _dt.now()
m = re.match(r"([a-z]+)\s+(\d{4})", token)
if m:
month = _MONTH_SHORT.get(m.group(1)[:3], 1)
try:
return _dt(int(m.group(2)), month, 1)
except ValueError:
return None
m = re.match(r"(\d{4})", token)
if m:
return _dt(int(m.group(1)), 6, 1)
return None
def compute_years_from_experience(entries: List[Dict[str, Any]]) -> int:
"""Sum date-range durations across all experience entries → total years."""
total_months = 0
for entry in entries:
period = (entry.get("period") or "").strip()
if not period:
continue
parts = re.split(r"\s*[-–—]\s*", period, maxsplit=1)
if len(parts) != 2:
continue
start = _parse_date_token(parts[0])
end = _parse_date_token(parts[1])
if start and end and end > start:
months = (end.year - start.year) * 12 + (end.month - start.month)
total_months += max(0, months)
return total_months // 12
# ---------------------------------------------------------------------------
# Seniority detection
# ---------------------------------------------------------------------------
def _detect_seniority(text: str, *, is_cv: bool = False) -> str:
"""Detect seniority: title zone first, then body (guards against
false positives from advice/boilerplate text in job descriptions)."""
title_zone = text[:300]
title_norm = _normalize(title_zone)
text_norm = _normalize(text)
order = (
["senior", "junior", "intern", "mid"]
if is_cv
else ["senior", "intern", "junior", "mid"]
)
for level in order:
if any(_has_alias(title_norm, term) for term in SENIORITY_PATTERNS[level]):
return level
for level in order:
if level == "senior" and not is_cv:
continue # already checked title zone; skip body re-check to avoid boilerplate inflation
if any(_has_alias(text_norm, term) for term in SENIORITY_PATTERNS[level]):
return level
years = _extract_years(text)
if years >= 7:
return "senior"
if years >= 3:
return "mid"
return "junior" if is_cv else "mid"
def refine_seniority_with_years(detected: str, years: int) -> str:
if detected == "mid":
if years >= 7:
return "senior"
if years >= 3:
return "mid"
if 0 < years < 2:
return "junior"
return detected
if detected == "intern" and years >= 2:
if years >= 7:
return "senior"
if years >= 3:
return "mid"
return "junior"
return detected
# ---------------------------------------------------------------------------
# CV title extractor
# ---------------------------------------------------------------------------
def _extract_cv_title(cv_text: str, clean_line_fn=None) -> str:
def _simple_clean(raw: str) -> str:
line = re.sub(r"^#+\s*", "", raw)
line = re.sub(r"\*{1,3}|\_{1,2}|`", "", line)
return re.sub(r"\s+", " ", line).strip()
clean = clean_line_fn or _simple_clean
clean_lines = [clean(x) for x in cv_text.splitlines() if x.strip()]
_role_wb_re = re.compile(
r"\b(" + "|".join(re.escape(w) for w in TITLE_ROLE_WORDS) + r")\b",
re.IGNORECASE,
)
for line in clean_lines[1:30]:
stripped = line.strip("| \t")
if (
len(stripped) <= 80
and bool(_role_wb_re.search(stripped))
and "|" not in stripped
and not re.search(r"[@http]", stripped)
and not re.search(
r"\d{4}\s*[-–]\s*(?:\d{4}|present)", stripped, re.IGNORECASE
)
):
return stripped.title()
_SECTION_HDR_RE = re.compile(
r"^(career\s*summary|professional\s*summary|executive\s*summary|"
r"personal\s*statement|career\s*objective|professional\s*profile|"
r"personal\s*profile|about\s*me|work\s*experience|"
r"professional\s*experience|technical\s*skills?|core\s*skills?|"
r"key\s*skills?|educational?\s*background|academic\s*background|"
r"employment\s*history|career\s*history|skills?\s*&?\s*tools?|"
r"skills?|summary|profile|experience|education|projects?|awards?|"
r"achievements?|contact|links?|certifications?)$",
re.IGNORECASE,
)
non_header = [
ln
for ln in clean_lines[:40]
if not _SECTION_HDR_RE.match(re.sub(r"[^a-zA-Z\s&]", " ", ln).strip())
]
head = ". ".join(non_header)[:1000]
m = TITLE_PHRASE_RE.search(head)
if m:
return m.group(1).strip().title()
return "Unknown"
|