File size: 136,064 Bytes
3a3c77b | 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 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 | # Copyright (c) 2006, Mathieu Fenniak
# Copyright (c) 2007, Ashish Kulkarni <kulkarni.ashish@gmail.com>
#
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
# * The name of the author may not be used to endorse or promote products
# derived from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
import decimal
import enum
import hashlib
import re
import struct
import sys
import uuid
from collections.abc import Iterable, Mapping, Sequence
from io import BytesIO, FileIO, IOBase
from itertools import compress
from pathlib import Path
from re import Pattern
from types import TracebackType
from typing import (
IO,
Any,
Callable,
Literal,
Optional,
Union,
cast,
)
if sys.version_info >= (3, 11):
from typing import Self
else:
from typing_extensions import Self
from ._doc_common import DocumentInformation, PdfDocCommon
from ._encryption import EncryptAlgorithm, Encryption
from ._page import PageObject, Transformation
from ._page_labels import nums_clear_range, nums_insert, nums_next
from ._reader import PdfReader
from ._utils import (
StrByteType,
StreamType,
_get_max_pdf_version_header,
deprecate_with_replacement,
deprecation_no_replacement,
logger_warning,
)
from .constants import AnnotationDictionaryAttributes as AA
from .constants import (
CatalogAttributes,
Core,
GoToActionArguments,
ImageType,
InteractiveFormDictEntries,
OutlineFontFlag,
PageLabelStyle,
PagesAttributes,
TypFitArguments,
UserAccessPermissions,
)
from .constants import FieldDictionaryAttributes as FA
from .constants import PageAttributes as PG
from .constants import TrailerKeys as TK
from .errors import LimitReachedError, PdfReadError, PyPdfError
from .generic import (
PAGE_FIT,
ArrayObject,
BooleanObject,
ByteStringObject,
ContentStream,
Destination,
DictionaryObject,
EmbeddedFile,
Fit,
FloatObject,
IndirectObject,
NameObject,
NullObject,
NumberObject,
PdfObject,
RectangleObject,
ReferenceLink,
StreamObject,
TextStringObject,
TreeObject,
ViewerPreferences,
create_string_object,
extract_links,
hex_to_rgb,
is_null_or_none,
)
from .generic._appearance_stream import TextStreamAppearance
from .pagerange import PageRange, PageRangeSpec
from .types import (
AnnotationSubtype,
BorderArrayType,
LayoutType,
OutlineItemType,
OutlineType,
PagemodeType,
)
from .xmp import XmpInformation
ALL_DOCUMENT_PERMISSIONS = UserAccessPermissions.all()
class ObjectDeletionFlag(enum.IntFlag):
NONE = 0
TEXT = enum.auto()
LINKS = enum.auto()
ATTACHMENTS = enum.auto()
OBJECTS_3D = enum.auto()
ALL_ANNOTATIONS = enum.auto()
XOBJECT_IMAGES = enum.auto()
INLINE_IMAGES = enum.auto()
DRAWING_IMAGES = enum.auto()
IMAGES = XOBJECT_IMAGES | INLINE_IMAGES | DRAWING_IMAGES
def _rolling_checksum(stream: BytesIO, blocksize: int = 65536) -> str:
hash = hashlib.md5(usedforsecurity=False)
for block in iter(lambda: stream.read(blocksize), b""):
hash.update(block)
return hash.hexdigest()
class PdfWriter(PdfDocCommon):
"""
Write a PDF file out, given pages produced by another class or through
cloning a PDF file during initialization.
Typically data is added from a :class:`PdfReader<pypdf.PdfReader>`.
Args:
clone_from: identical to fileobj (for compatibility)
incremental: If true, loads the document and set the PdfWriter in incremental mode.
When writing incrementally, the original document is written first and new/modified
content is appended. To be used for signed document/forms to keep signature valid.
full: If true, loads all the objects (always full if incremental = True).
This parameter may allow loading large PDFs.
strict: If true, pypdf will raise an exception if a PDF does not follow the specification.
If false, pypdf will try to be forgiving and do something reasonable, but it will log
a warning message. It is a best-effort approach.
keep_initial_header: If true, the PDF header of the cloned document is kept
when using ``clone_from`` in non-incremental mode.
"""
def __init__(
self,
fileobj: Union[PdfReader, StrByteType, Path, None] = "",
clone_from: Union[PdfReader, StrByteType, Path, None] = None,
incremental: bool = False,
full: bool = False,
strict: bool = False,
*,
keep_initial_header: bool = False,
incremental_clone_object_count_limit: Optional[int] = 500_000,
incremental_clone_object_id_limit: Optional[int] = 1_000_000,
) -> None:
self.strict = strict
"""
If true, pypdf will raise an exception if a PDF does not follow the specification.
If false, pypdf will try to be forgiving and do something reasonable, but it will log
a warning message. It is a best-effort approach.
"""
self.incremental = incremental or full
"""
Returns if the PdfWriter object has been started in incremental mode.
"""
self._objects: list[Optional[PdfObject]] = []
"""
The indirect objects in the PDF.
For the incremental case, it will be filled with None
in clone_reader_document_root.
"""
self._original_hash: list[int] = []
"""
List of hashes after import; used to identify changes.
"""
self._idnum_hash: dict[bytes, tuple[IndirectObject, list[IndirectObject]]] = {}
"""
Maps hash values of indirect objects to the list of IndirectObjects.
This is used for compression.
"""
self._id_translated: dict[int, dict[Union[int, Literal["PreventGC"]], Any]] = {}
"""List of already translated IDs.
dict[id(pdf)][(idnum, generation)]
"""
self._info_obj: Optional[PdfObject]
"""The PDF files's document information dictionary,
defined by Info in the PDF file's trailer dictionary."""
self._reader: Optional[PdfReader] = None
"""The document being appended to, in incremental mode only."""
self._ID: Union[ArrayObject, None] = None
"""The PDF file identifier,
defined by the ID in the PDF file's trailer dictionary."""
self._unresolved_links: list[tuple[ReferenceLink, ReferenceLink]] = []
"Tracks links in pages added to the writer for resolving later."
self._merged_in_pages: dict[Optional[IndirectObject], Optional[IndirectObject]] = {}
"Tracks pages added to the writer and what page they turned into."
# Security parameters.
self._incremental_clone_object_count_limit = (
incremental_clone_object_count_limit
if isinstance(incremental_clone_object_count_limit, int)
else sys.maxsize
)
self._incremental_clone_object_id_limit = (
incremental_clone_object_id_limit if isinstance(incremental_clone_object_id_limit, int) else sys.maxsize
)
if self.incremental:
if isinstance(fileobj, (str, Path)):
with open(fileobj, "rb") as f:
fileobj = BytesIO(f.read(-1))
if isinstance(fileobj, BytesIO):
fileobj = PdfReader(fileobj)
if not isinstance(fileobj, PdfReader):
raise PyPdfError("Invalid type for incremental mode")
self._reader = fileobj # prev content is in _reader.stream
self._header = fileobj.pdf_header.encode()
self._readonly = True # TODO: to be analysed
else:
self._header = b"%PDF-1.3"
self._info_obj = self._add_object(
DictionaryObject(
{NameObject("/Producer"): create_string_object("pypdf")}
)
)
def _get_clone_from(
fileobj: Union[PdfReader, str, Path, IO[Any], BytesIO, None],
clone_from: Union[PdfReader, str, Path, IO[Any], BytesIO, None],
) -> Union[PdfReader, str, Path, IO[Any], BytesIO, None]:
if isinstance(fileobj, (str, Path, IO, BytesIO)) and (
fileobj == "" or clone_from is not None
):
return clone_from
cloning = True
if isinstance(fileobj, (str, Path)):
fileobj_path = Path(fileobj)
if not fileobj_path.exists() or fileobj_path.stat().st_size == 0:
cloning = False
elif isinstance(fileobj, (IOBase, BytesIO)):
t = fileobj.tell()
if fileobj.seek(0, 2) == 0:
cloning = False
fileobj.seek(t, 0)
if cloning:
clone_from = fileobj
return clone_from
clone_from = _get_clone_from(fileobj, clone_from)
# To prevent overwriting
self.temp_fileobj = fileobj
self.fileobj = ""
self._with_as_usage = False
self._cloned = False
# The root of our page tree node
pages = DictionaryObject(
{
NameObject(PagesAttributes.TYPE): NameObject("/Pages"),
NameObject(PagesAttributes.COUNT): NumberObject(0),
NameObject(PagesAttributes.KIDS): ArrayObject(),
}
)
self.flattened_pages = []
self._encryption: Optional[Encryption] = None
self._encrypt_entry: Optional[DictionaryObject] = None
if clone_from is not None:
if not isinstance(clone_from, PdfReader):
clone_from = PdfReader(clone_from)
self.clone_document_from_reader(clone_from)
self._cloned = True
if keep_initial_header and not self.incremental:
self._header = clone_from.pdf_header.encode()
else:
self._pages = self._add_object(pages)
self._root_object = DictionaryObject(
{
NameObject(PagesAttributes.TYPE): NameObject(Core.CATALOG),
NameObject(Core.PAGES): self._pages,
}
)
self._add_object(self._root_object)
if full and not incremental:
self.incremental = False
if isinstance(self._ID, list):
if isinstance(self._ID[0], TextStringObject):
self._ID[0] = ByteStringObject(self._ID[0].get_original_bytes())
if isinstance(self._ID[1], TextStringObject):
self._ID[1] = ByteStringObject(self._ID[1].get_original_bytes())
# for commonality
@property
def is_encrypted(self) -> bool:
"""
Read-only boolean property showing whether this PDF file is encrypted.
Note that this property, if true, will remain true even after the
:meth:`decrypt()<pypdf.PdfReader.decrypt>` method is called.
"""
return False
@property
def root_object(self) -> DictionaryObject:
"""
Provide direct access to PDF Structure.
Note:
Recommended only for read access.
"""
return self._root_object
@property
def _info(self) -> Optional[DictionaryObject]:
"""
Provide access to "/Info". Standardized with PdfReader.
Returns:
/Info Dictionary; None if the entry does not exist
"""
return (
None
if self._info_obj is None
else cast(DictionaryObject, self._info_obj.get_object())
)
@_info.setter
def _info(self, value: Optional[Union[IndirectObject, DictionaryObject]]) -> None:
if value is None:
try:
self._objects[self._info_obj.indirect_reference.idnum - 1] = None # type: ignore[union-attr]
except (KeyError, AttributeError):
pass
self._info_obj = None
else:
if self._info_obj is None:
self._info_obj = self._add_object(DictionaryObject())
obj = cast(DictionaryObject, self._info_obj.get_object())
obj.clear()
obj.update(cast(DictionaryObject, value.get_object()))
@property
def xmp_metadata(self) -> Optional[XmpInformation]:
"""XMP (Extensible Metadata Platform) data."""
return cast(XmpInformation, self.root_object.xmp_metadata)
@xmp_metadata.setter
def xmp_metadata(self, value: Union[XmpInformation, bytes, None]) -> None:
"""XMP (Extensible Metadata Platform) data."""
if value is None:
if "/Metadata" in self.root_object:
del self.root_object["/Metadata"]
return
metadata = self.root_object.get("/Metadata", None)
if not isinstance(metadata, IndirectObject):
if metadata is not None:
del self.root_object["/Metadata"]
metadata_stream = StreamObject()
stream_reference = self._add_object(metadata_stream)
self.root_object[NameObject("/Metadata")] = stream_reference
else:
metadata_stream = cast(StreamObject, metadata.get_object())
if isinstance(value, XmpInformation):
bytes_data = value.stream.get_data()
else:
bytes_data = value
metadata_stream.set_data(bytes_data)
@property
def with_as_usage(self) -> bool:
deprecation_no_replacement("with_as_usage", "5.0")
@with_as_usage.setter
def with_as_usage(self, value: bool) -> None:
deprecation_no_replacement("with_as_usage", "5.0")
def __enter__(self) -> Self:
"""Store how writer is initialized by 'with'."""
c: bool = self._cloned
t = self.temp_fileobj
self.__init__() # type: ignore[misc]
self._cloned = c
self._with_as_usage = True
self.fileobj = t # type: ignore[assignment]
return self
def __exit__(
self,
exc_type: Optional[type[BaseException]],
exc: Optional[BaseException],
traceback: Optional[TracebackType],
) -> None:
"""Write data to the fileobj."""
if self.fileobj and not self._cloned:
self.write(self.fileobj)
@property
def pdf_header(self) -> str:
"""
Read/Write property of the PDF header that is written.
This should be something like ``'%PDF-1.5'``. It is recommended to set
the lowest version that supports all features which are used within the
PDF file.
Note: `pdf_header` returns a string but accepts bytes or str for writing
"""
return self._header.decode()
@pdf_header.setter
def pdf_header(self, new_header: Union[str, bytes]) -> None:
if isinstance(new_header, str):
new_header = new_header.encode()
self._header = new_header
def _add_object(self, obj: PdfObject) -> IndirectObject:
if (
getattr(obj, "indirect_reference", None) is not None
and obj.indirect_reference.pdf == self # type: ignore[union-attr]
):
return obj.indirect_reference # type: ignore[return-value]
# check for /Contents in Pages (/Contents in annotations are strings)
if isinstance(obj, DictionaryObject) and isinstance(
obj.get(PG.CONTENTS, None), (ArrayObject, DictionaryObject)
):
obj[NameObject(PG.CONTENTS)] = self._add_object(obj[PG.CONTENTS])
self._objects.append(obj)
obj.indirect_reference = IndirectObject(len(self._objects), 0, self)
return obj.indirect_reference
def get_object(
self,
indirect_reference: Union[int, IndirectObject],
) -> PdfObject:
if isinstance(indirect_reference, int):
obj = self._objects[indirect_reference - 1]
elif indirect_reference.pdf != self:
raise ValueError("PDF must be self")
else:
obj = self._objects[indirect_reference.idnum - 1]
if obj is None:
raise PdfReadError(f"Object {indirect_reference!r} not found!")
return obj
def _replace_object(
self,
indirect_reference: Union[int, IndirectObject],
obj: PdfObject,
) -> PdfObject:
if isinstance(indirect_reference, IndirectObject):
if indirect_reference.pdf != self:
raise ValueError("PDF must be self")
indirect_reference = indirect_reference.idnum
gen = self._objects[indirect_reference - 1].indirect_reference.generation # type: ignore[union-attr]
if (
getattr(obj, "indirect_reference", None) is not None
and obj.indirect_reference.pdf != self # type: ignore[union-attr]
):
obj = obj.clone(self)
self._objects[indirect_reference - 1] = obj
obj.indirect_reference = IndirectObject(indirect_reference, gen, self)
assert isinstance(obj, PdfObject), "mypy"
return obj
def _add_page(
self,
page: PageObject,
index: int,
excluded_keys: Iterable[str] = (),
) -> PageObject:
if not isinstance(page, PageObject) or page.get(PagesAttributes.TYPE, None) != Core.PAGE:
raise ValueError("Invalid page object")
assert self.flattened_pages is not None, "mypy"
page_org = page
excluded_keys = list(excluded_keys)
excluded_keys += [PagesAttributes.PARENT, "/StructParents"]
# Acrobat does not accept two indirect references pointing on the same
# page; therefore in order to add multiple copies of the same
# page, we need to create a new dictionary for the page, however the
# objects below (including content) are not duplicated:
try: # delete an already existing page
del self._id_translated[id(page_org.indirect_reference.pdf)][ # type: ignore[union-attr]
page_org.indirect_reference.idnum # type: ignore[union-attr]
]
except Exception:
pass
page = cast(
"PageObject", page_org.clone(self, False, excluded_keys).get_object()
)
if page_org.pdf is not None:
other = page_org.pdf.pdf_header
self.pdf_header = _get_max_pdf_version_header(self.pdf_header, other)
node, idx = self._get_page_in_node(index)
page[NameObject(PagesAttributes.PARENT)] = node.indirect_reference
if idx >= 0:
cast(ArrayObject, node[PagesAttributes.KIDS]).insert(idx, page.indirect_reference)
self.flattened_pages.insert(index, page)
else:
cast(ArrayObject, node[PagesAttributes.KIDS]).append(page.indirect_reference)
self.flattened_pages.append(page)
current: Optional[PdfObject] = node
recurse = 0
while not is_null_or_none(current):
assert current is not None, "mypy" # guarded by is_null_or_none
node_dict = cast(DictionaryObject, current.get_object())
node_dict[NameObject(PagesAttributes.COUNT)] = NumberObject(cast(int, node_dict[PagesAttributes.COUNT]) + 1)
current = node_dict.get(PagesAttributes.PARENT, None)
recurse += 1
if recurse > 1000:
raise PyPdfError("Too many recursive calls!")
if page_org.pdf is not None:
# the page may contain links to other pages, and those other
# pages may or may not already be added. we store the
# information we need, so that we can resolve the references
# later.
self._unresolved_links.extend(extract_links(page, page_org))
self._merged_in_pages[page_org.indirect_reference] = page.indirect_reference
return page
def set_need_appearances_writer(self, state: bool = True) -> None:
"""
Sets the "NeedAppearances" flag in the PDF writer.
The "NeedAppearances" flag indicates whether the appearance dictionary
for form fields should be automatically generated by the PDF viewer or
if the embedded appearance should be used.
Args:
state: The actual value of the NeedAppearances flag.
Returns:
None
"""
# See §12.7.2 and §7.7.2 for more information:
# https://opensource.adobe.com/dc-acrobat-sdk-docs/pdfstandards/PDF32000_2008.pdf
try:
# get the AcroForm tree
if CatalogAttributes.ACRO_FORM not in self._root_object:
self._root_object[
NameObject(CatalogAttributes.ACRO_FORM)
] = self._add_object(DictionaryObject())
need_appearances = NameObject(InteractiveFormDictEntries.NeedAppearances)
cast(DictionaryObject, self._root_object[CatalogAttributes.ACRO_FORM])[
need_appearances
] = BooleanObject(state)
except Exception as exc: # pragma: no cover
logger_warning(
"set_need_appearances_writer(%(state)s) catch : %(exc)s",
source=__name__,
state=state,
exc=exc,
)
def create_viewer_preferences(self) -> ViewerPreferences:
o = ViewerPreferences()
self._root_object[
NameObject(CatalogAttributes.VIEWER_PREFERENCES)
] = self._add_object(o)
return o
def add_page(
self,
page: PageObject,
excluded_keys: Iterable[str] = (),
) -> PageObject:
"""
Add a page to this PDF file.
Recommended for advanced usage including the adequate excluded_keys.
The page is usually acquired from a :class:`PdfReader<pypdf.PdfReader>`
instance.
Args:
page: The page to add to the document. Should be
an instance of :class:`PageObject<pypdf._page.PageObject>`
excluded_keys:
Returns:
The added PageObject.
"""
assert self.flattened_pages is not None, "mypy"
return self._add_page(page, len(self.flattened_pages), excluded_keys)
def insert_page(
self,
page: PageObject,
index: int = 0,
excluded_keys: Iterable[str] = (),
) -> PageObject:
"""
Insert a page in this PDF file. The page is usually acquired from a
:class:`PdfReader<pypdf.PdfReader>` instance.
Args:
page: The page to add to the document.
index: Position at which the page will be inserted.
excluded_keys:
Returns:
The added PageObject.
"""
assert self.flattened_pages is not None, "mypy"
if index < 0:
index += len(self.flattened_pages)
if index < 0:
raise ValueError("Invalid index value")
if index >= len(self.flattened_pages):
return self.add_page(page, excluded_keys)
return self._add_page(page, index, excluded_keys)
def _get_page_number_by_indirect(
self, indirect_reference: Union[int, NullObject, IndirectObject, None]
) -> Optional[int]:
"""
Generate _page_id2num.
Args:
indirect_reference:
Returns:
The page number or None
"""
# To provide same function as in PdfReader
if is_null_or_none(indirect_reference):
return None
assert indirect_reference is not None, "mypy"
if isinstance(indirect_reference, int):
indirect_reference = IndirectObject(indirect_reference, 0, self)
obj = indirect_reference.get_object()
if isinstance(obj, PageObject):
return obj.page_number
return None
def add_blank_page(
self, width: Optional[float] = None, height: Optional[float] = None
) -> PageObject:
"""
Append a blank page to this PDF file and return it.
If no page size is specified, use the size of the last page.
Args:
width: The width of the new page expressed in default user
space units.
height: The height of the new page expressed in default
user space units.
Returns:
The newly appended page.
Raises:
PageSizeNotDefinedError: if width and height are not defined
and previous page does not exist.
"""
page = PageObject.create_blank_page(self, width, height)
return self.add_page(page)
def insert_blank_page(
self,
width: Optional[Union[float, decimal.Decimal]] = None,
height: Optional[Union[float, decimal.Decimal]] = None,
index: int = 0,
) -> PageObject:
"""
Insert a blank page to this PDF file and return it.
If no page size is specified for a dimension, use the size of the last page.
Args:
width: The width of the new page in default user space units.
height: The height of the new page in default user space units.
index: Position to add the page.
Returns:
The newly inserted page.
Raises:
PageSizeNotDefinedError: if width and height are not defined
and previous page does not exist.
IndexError: Index is outside of [-self.get_num_pages(), self.get_num_pages()]
"""
num_pages = self.get_num_pages()
if abs(index) <= num_pages:
# Use the chosen index, but do not exceed the available pages
fixed_index = min(index, num_pages - 1)
mediabox = self.pages[fixed_index].mediabox
if width is None or width <= 0:
width = mediabox.width
if height is None or height <= 0:
height = mediabox.height
else:
raise IndexError(f"Index should be in range [-{num_pages}, {num_pages}]")
page = PageObject.create_blank_page(self, width, height)
self.insert_page(page, index)
return page
@property
def open_destination(
self,
) -> Union[Destination, TextStringObject, ByteStringObject, None]:
return super().open_destination
@open_destination.setter
def open_destination(self, dest: Union[str, Destination, PageObject, None]) -> None:
if dest is None:
try:
del self._root_object["/OpenAction"]
except KeyError:
pass
elif isinstance(dest, str):
self._root_object[NameObject("/OpenAction")] = TextStringObject(dest)
elif isinstance(dest, Destination):
self._root_object[NameObject("/OpenAction")] = dest.dest_array
elif isinstance(dest, PageObject):
self._root_object[NameObject("/OpenAction")] = Destination(
"Opening",
dest.indirect_reference
if dest.indirect_reference is not None
else NullObject(),
PAGE_FIT,
).dest_array
def add_js(self, javascript: str) -> None:
"""
Add JavaScript which will launch upon opening this PDF.
Args:
javascript: Your JavaScript.
Example:
This will launch the print window when the PDF is opened.
>>> from pypdf import PdfWriter
>>> output = PdfWriter()
>>> output.add_js("this.print({bUI:true,bSilent:false,bShrinkToFit:true});")
"""
# Names / JavaScript preferred to be able to add multiple scripts
if "/Names" not in self._root_object:
self._root_object[NameObject(CatalogAttributes.NAMES)] = DictionaryObject()
names = cast(DictionaryObject, self._root_object[CatalogAttributes.NAMES])
if "/JavaScript" not in names:
names[NameObject("/JavaScript")] = DictionaryObject(
{NameObject("/Names"): ArrayObject()}
)
js_list = cast(
ArrayObject, cast(DictionaryObject, names["/JavaScript"])["/Names"]
)
# We need a name for parameterized JavaScript in the PDF file,
# but it can be anything.
js_list.append(create_string_object(str(uuid.uuid4())))
js = DictionaryObject(
{
NameObject(PagesAttributes.TYPE): NameObject("/Action"),
NameObject("/S"): NameObject("/JavaScript"),
NameObject("/JS"): TextStringObject(f"{javascript}"),
}
)
js_list.append(self._add_object(js))
def add_attachment(self, filename: str, data: Union[str, bytes]) -> "EmbeddedFile":
"""
Embed a file inside the PDF.
Reference:
https://opensource.adobe.com/dc-acrobat-sdk-docs/pdfstandards/PDF32000_2008.pdf
Section 7.11.3
Args:
filename: The filename to display.
data: The data in the file.
Returns:
EmbeddedFile instance for the newly created embedded file.
"""
return EmbeddedFile._create_new(self, filename, data)
def append_pages_from_reader(
self,
reader: PdfReader,
after_page_append: Optional[Callable[[PageObject], None]] = None,
) -> None:
"""
Copy pages from reader to writer. Includes an optional callback
parameter which is invoked after pages are appended to the writer.
``append`` should be preferred.
Args:
reader: a PdfReader object from which to copy page
annotations to this writer object. The writer's annots
will then be updated.
after_page_append:
Callback function that is invoked after each page is appended to
the writer. Signature includes a reference to the appended page
(delegates to append_pages_from_reader). The single parameter of
the callback is a reference to the page just appended to the
document.
"""
reader_num_pages = len(reader.pages)
# Copy pages from reader to writer
for reader_page_number in range(reader_num_pages):
reader_page = reader.pages[reader_page_number]
writer_page = self.add_page(reader_page)
# Trigger callback, pass writer page as parameter
if callable(after_page_append):
after_page_append(writer_page)
def _merge_content_stream_to_page(
self,
page: PageObject,
new_content_data: bytes,
) -> None:
"""
Combines existing content stream(s) with new content (as bytes).
Args:
page: The page to which the new content data will be added.
new_content_data: A binary-encoded new content stream, for
instance the commands to draw an XObject.
"""
# First resolve the existing page content. This always is an IndirectObject:
# PDF Explained by John Whitington
# https://www.oreilly.com/library/view/pdf-explained/9781449321581/ch04.html
if NameObject("/Contents") in page:
existing_content_ref = page[NameObject("/Contents")]
existing_content = existing_content_ref.get_object()
if isinstance(existing_content, ArrayObject):
# Create a new StreamObject for the new_content_data
new_stream_obj = StreamObject()
new_stream_obj.set_data(new_content_data)
existing_content.append(self._add_object(new_stream_obj))
page[NameObject("/Contents")] = self._add_object(existing_content)
if isinstance(existing_content, StreamObject):
# Merge new content to existing StreamObject
merged_data = existing_content.get_data() + b"\n" + new_content_data
new_stream = StreamObject()
new_stream.set_data(merged_data)
page[NameObject("/Contents")] = self._add_object(new_stream)
else:
# If no existing content, then we have an empty page.
# Create a new StreamObject in a new /Contents entry.
new_stream = StreamObject()
new_stream.set_data(new_content_data)
page[NameObject("/Contents")] = self._add_object(new_stream)
def _add_apstream_object(
self,
page: PageObject,
appearance_stream_obj: StreamObject,
object_name: str,
x_offset: float,
y_offset: float,
) -> None:
"""
Adds an appearance stream to the page content in the form of
an XObject.
Args:
page: The page to which to add the appearance stream.
appearance_stream_obj: The appearance stream.
object_name: The name of the appearance stream.
x_offset: The horizontal offset for the appearance stream.
y_offset: The vertical offset for the appearance stream.
"""
pg_res = cast(DictionaryObject, page[PG.RESOURCES])
# Always add the resolved stream object to the writer to get a new IndirectObject.
# This ensures we have a valid IndirectObject managed by *this* writer.
xobject_ref = self._add_object(appearance_stream_obj)
xobject_name = NameObject(f"/Fm_{object_name}")._sanitize()
if "/XObject" not in pg_res:
pg_res[NameObject("/XObject")] = DictionaryObject()
pg_xo_res = cast(DictionaryObject, pg_res["/XObject"])
if xobject_name not in pg_xo_res:
pg_xo_res[xobject_name] = xobject_ref
else:
logger_warning(
"XObject %(xobject_name)r already added to page resources. This might be an issue.",
source=__name__,
xobject_name=xobject_name,
)
xobject_cm = Transformation().translate(x_offset, y_offset)
xobject_drawing_commands = f"q\n{xobject_cm._to_cm()}\n{xobject_name} Do\nQ".encode()
self._merge_content_stream_to_page(page, xobject_drawing_commands)
FFBITS_NUL = FA.FfBits(0)
def update_page_form_field_values(
self,
page: Union[PageObject, list[PageObject], None],
fields: Mapping[str, Union[str, list[str], tuple[str, str, float]]],
flags: FA.FfBits = FFBITS_NUL,
auto_regenerate: Optional[bool] = True,
flatten: bool = False,
) -> None:
"""
Update the form field values for a given page from a fields dictionary.
Copy field texts and values from fields to page.
If the field links to a parent object, add the information to the parent.
Args:
page: `PageObject` - references **PDF writer's page** where the
annotations and field data will be updated.
`List[Pageobject]` - provides list of pages to be processed.
`None` - all pages.
fields: a Python dictionary of:
* field names (/T) as keys and text values (/V) as value
* field names (/T) as keys and list of text values (/V) for multiple choice list
* field names (/T) as keys and tuple of:
* text values (/V)
* font id (e.g. /F1, the font id must exist)
* font size (0 for autosize)
flags: A set of flags from :class:`~pypdf.constants.FieldDictionaryAttributes.FfBits`.
auto_regenerate: Set/unset the need_appearances flag;
the flag is unchanged if auto_regenerate is None.
flatten: Whether or not to flatten the annotation. If True, this adds the annotation's
appearance stream to the page contents. Note that this option does not remove the
annotation itself.
"""
if CatalogAttributes.ACRO_FORM not in self._root_object:
raise PyPdfError("No /AcroForm dictionary in PDF of PdfWriter Object")
acro_form = cast(DictionaryObject, self._root_object[CatalogAttributes.ACRO_FORM])
if InteractiveFormDictEntries.Fields not in acro_form:
raise PyPdfError("No /Fields dictionary in PDF of PdfWriter Object")
if isinstance(auto_regenerate, bool):
self.set_need_appearances_writer(auto_regenerate)
# Iterate through pages, update field values
if page is None:
page = list(self.pages)
if isinstance(page, list):
for p in page:
if PG.ANNOTS in p: # just to prevent warnings
self.update_page_form_field_values(p, fields, flags, None, flatten=flatten)
return
if PG.ANNOTS not in page:
logger_warning("No fields to update on this page", source=__name__)
return
appearance_stream_obj: Optional[StreamObject] = None
for annotation in page[PG.ANNOTS]: # type: ignore[attr-defined]
annotation = cast(DictionaryObject, annotation.get_object())
if annotation.get("/Subtype", "") != "/Widget":
continue
if "/FT" in annotation and "/T" in annotation:
parent_annotation = annotation
else:
parent_annotation = annotation.get(
PG.PARENT, DictionaryObject()
).get_object()
for field, value in fields.items():
rectangle = cast(RectangleObject, annotation[AA.Rect])
if not (
self._get_qualified_field_name(parent=parent_annotation) == field
or parent_annotation.get("/T", None) == field
):
continue
if (
parent_annotation.get("/FT", None) == "/Ch"
and "/I" in parent_annotation
):
del parent_annotation["/I"]
if flags:
annotation[NameObject(FA.Ff)] = NumberObject(flags)
# Set the field value
if not (value is None and flatten): # Only change values if given by user and not flattening.
if isinstance(value, list):
lst = ArrayObject(TextStringObject(v) for v in value)
parent_annotation[NameObject(FA.V)] = lst
elif isinstance(value, tuple):
annotation[NameObject(FA.V)] = TextStringObject(
value[0],
)
else:
parent_annotation[NameObject(FA.V)] = TextStringObject(value)
# Get or create the field's appearance stream object
if parent_annotation.get(FA.FT) == "/Btn":
# Checkbox button (no /FT found in Radio widgets);
# We can find the associated appearance stream object
# within the annotation.
v = NameObject(value)
ap = cast(DictionaryObject, annotation[NameObject(AA.AP)])
normal_ap = cast(DictionaryObject, ap["/N"])
if v not in normal_ap:
v = NameObject("/Off")
appearance_stream_obj = normal_ap.get(v)
# Other cases will be updated through the for loop
annotation[NameObject(AA.AS)] = v
annotation[NameObject(FA.V)] = v
elif (
parent_annotation.get(FA.FT) == "/Tx"
or parent_annotation.get(FA.FT) == "/Ch"
):
# Textbox; we need to generate the appearance stream object
if isinstance(value, tuple):
appearance_stream_obj = TextStreamAppearance.from_text_annotation(
self, page, flatten, acro_form, parent_annotation, annotation, value[1], value[2]
)
else:
appearance_stream_obj = TextStreamAppearance.from_text_annotation(
self, page, flatten, acro_form, parent_annotation, annotation
)
# Add the appearance stream object
if AA.AP not in annotation:
annotation[NameObject(AA.AP)] = DictionaryObject(
{NameObject("/N"): self._add_object(appearance_stream_obj)}
)
elif "/N" not in (ap:= cast(DictionaryObject, annotation[AA.AP])):
cast(DictionaryObject, annotation[NameObject(AA.AP)])[
NameObject("/N")
] = self._add_object(appearance_stream_obj)
else: # [/AP][/N] exists
n = annotation[AA.AP]["/N"].indirect_reference.idnum # type: ignore[index]
self._objects[n - 1] = appearance_stream_obj
appearance_stream_obj.indirect_reference = IndirectObject(n, 0, self)
elif (
annotation.get(FA.FT) == "/Sig"
): # deprecated # not implemented yet
logger_warning("Signature forms not implemented yet", source=__name__)
if appearance_stream_obj and flatten:
self._add_apstream_object(page, appearance_stream_obj, field, rectangle[0], rectangle[1])
def reattach_fields(
self, page: Optional[PageObject] = None
) -> list[DictionaryObject]:
"""
Parse annotations within the page looking for orphan fields and
reattach then into the Fields Structure.
Args:
page: page to analyze.
If none is provided, all pages will be analyzed.
Returns:
list of reattached fields.
"""
lst = []
if page is None:
for p in self.pages:
lst += self.reattach_fields(p)
return lst
try:
af = cast(DictionaryObject, self._root_object[CatalogAttributes.ACRO_FORM])
except KeyError:
af = DictionaryObject()
self._root_object[NameObject(CatalogAttributes.ACRO_FORM)] = af
try:
fields = cast(ArrayObject, af[InteractiveFormDictEntries.Fields])
except KeyError:
fields = ArrayObject()
af[NameObject(InteractiveFormDictEntries.Fields)] = fields
if "/Annots" not in page:
return lst
annotations = cast(ArrayObject, page["/Annots"])
for idx, annotation in enumerate(annotations):
is_indirect = isinstance(annotation, IndirectObject)
annotation = cast(DictionaryObject, annotation.get_object())
if annotation.get("/Subtype", "") == "/Widget" and "/FT" in annotation:
if (
"indirect_reference" in annotation.__dict__
and annotation.indirect_reference in fields
):
continue
if not is_indirect:
annotations[idx] = self._add_object(annotation)
fields.append(annotation.indirect_reference)
lst.append(annotation)
return lst
def _collect_incremental_clone_object_ids(self, reader: PdfReader) -> list[int]:
object_ids: set[int] = set()
for xref_entry in reader.xref.values():
object_ids.update(filter(None, xref_entry))
object_ids.update(filter(None, reader.xref_objStm))
object_count = len(object_ids)
if object_count > self._incremental_clone_object_count_limit:
raise LimitReachedError(
f"Incremental clone object count {object_count} exceeds "
f"maximum allowed count {self._incremental_clone_object_count_limit}."
)
max_object_id = max(object_ids, default=0)
if max_object_id > self._incremental_clone_object_id_limit:
raise LimitReachedError(
f"Incremental clone object ID {max_object_id} exceeds "
f"maximum allowed ID {self._incremental_clone_object_id_limit}."
)
return sorted(object_ids)
def clone_reader_document_root(self, reader: PdfReader) -> None:
"""
Copy the reader document root to the writer and all sub-elements,
including pages, threads, outlines,... For partial insertion, ``append``
should be considered.
Args:
reader: PdfReader from which the document root should be copied.
"""
self._info_obj = None
if self.incremental:
object_ids = self._collect_incremental_clone_object_ids(reader)
self._objects = [None] * (object_ids[-1] if object_ids else 0)
for object_id in object_ids:
reader_object = reader.get_object(object_id)
if reader_object is not None:
self._objects[object_id - 1] = reader_object.replicate(self)
else:
self._objects.clear()
self._root_object = reader.root_object.clone(self)
self._pages = self._root_object.raw_get("/Pages")
trailer_size = cast(int, reader.trailer["/Size"])
if len(self._objects) > trailer_size:
if self.strict:
raise PdfReadError(
f"Object count {len(self._objects)} exceeds defined trailer size {trailer_size}"
)
logger_warning(
"Object count %(object_count)d exceeds defined trailer size %(trailer_size)d",
source=__name__,
object_count=len(self._objects),
trailer_size=trailer_size,
)
# must be done here before rewriting
if self.incremental:
self._original_hash = [
(obj.hash_bin() if obj is not None else 0) for obj in self._objects
]
try:
self._flatten()
except IndexError:
raise PdfReadError("Got index error while flattening.")
assert self.flattened_pages is not None
for p in self.flattened_pages:
self._replace_object(cast(IndirectObject, p.indirect_reference).idnum, p)
if not self.incremental:
p[NameObject("/Parent")] = self._pages
if not self.incremental:
cast(DictionaryObject, self._pages.get_object())[
NameObject("/Kids")
] = ArrayObject([p.indirect_reference for p in self.flattened_pages])
def clone_document_from_reader(
self,
reader: PdfReader,
after_page_append: Optional[Callable[[PageObject], None]] = None,
) -> None:
"""
Create a copy (clone) of a document from a PDF file reader cloning
section '/Root' and '/Info' and '/ID' of the pdf.
Args:
reader: PDF file reader instance from which the clone
should be created.
after_page_append:
Callback function that is invoked after each page is appended to
the writer. Signature includes a reference to the appended page
(delegates to append_pages_from_reader). The single parameter of
the callback is a reference to the page just appended to the
document.
"""
self.clone_reader_document_root(reader)
inf = reader._info
if self.incremental:
if inf is not None:
self._info_obj = cast(
IndirectObject, inf.clone(self).indirect_reference
)
assert isinstance(self._info, DictionaryObject), "mypy"
self._original_hash[
self._info_obj.indirect_reference.idnum - 1
] = self._info.hash_bin()
elif inf is not None:
self._info_obj = self._add_object(
DictionaryObject(cast(DictionaryObject, inf.get_object()))
)
# else: _info_obj = None done in clone_reader_document_root()
try:
self._ID = cast(ArrayObject, reader._ID).clone(self)
except AttributeError:
pass
if callable(after_page_append):
for page in cast(
ArrayObject, cast(DictionaryObject, self._pages.get_object())["/Kids"]
):
after_page_append(page.get_object())
def _compute_document_identifier(self) -> ByteStringObject:
stream = BytesIO()
self._write_pdf_structure(stream)
stream.seek(0)
return ByteStringObject(_rolling_checksum(stream).encode("utf8"))
def generate_file_identifiers(self) -> None:
"""
Generate an identifier for the PDF that will be written.
The only point of this is ensuring uniqueness. Reproducibility is not
required.
When a file is first written, both identifiers shall be set to the same value.
If both identifiers match when a file reference is resolved, it is very
likely that the correct and unchanged file has been found. If only the first
identifier matches, a different version of the correct file has been found.
see §14.4 "File Identifiers".
"""
if self._ID:
id1 = self._ID[0]
id2 = self._compute_document_identifier()
else:
id1 = self._compute_document_identifier()
id2 = id1
self._ID = ArrayObject((id1, id2))
def encrypt(
self,
user_password: str,
owner_password: Optional[str] = None,
use_128bit: bool = True,
permissions_flag: UserAccessPermissions = ALL_DOCUMENT_PERMISSIONS,
*,
algorithm: Optional[str] = None,
) -> None:
"""
Encrypt this PDF file with the PDF Standard encryption handler.
Args:
user_password: The password which allows for opening
and reading the PDF file with the restrictions provided.
owner_password: The password which allows for
opening the PDF files without any restrictions. By default,
the owner password is the same as the user password.
use_128bit: flag as to whether to use 128bit
encryption. When false, 40bit encryption will be used.
By default, this flag is on.
permissions_flag: permissions as described in
Table 3.20 of the PDF 1.7 specification. A bit value of 1 means
the permission is granted.
Hence an integer value of -1 will set all flags.
Bit position 3 is for printing, 4 is for modifying content,
5 and 6 control annotations, 9 for form fields,
10 for extraction of text and graphics.
algorithm: encrypt algorithm. Values may be one of "RC4-40", "RC4-128",
"AES-128", "AES-256-R5", "AES-256". If it is valid,
`use_128bit` will be ignored.
"""
if self.incremental:
raise NotImplementedError("Encrypting incremental PDF files is currently not supported.")
if owner_password is None:
owner_password = user_password
if algorithm is not None:
try:
alg = getattr(EncryptAlgorithm, algorithm.replace("-", "_"))
except AttributeError:
raise ValueError(f"Algorithm '{algorithm}' NOT supported")
else:
alg = EncryptAlgorithm.RC4_128
if not use_128bit:
alg = EncryptAlgorithm.RC4_40
self.generate_file_identifiers()
assert self._ID
self._encryption = Encryption.make(alg, permissions_flag, self._ID[0])
# in case call `encrypt` again
entry = self._encryption.write_entry(user_password, owner_password, strict=self.strict)
if self._encrypt_entry:
# replace old encrypt_entry
assert self._encrypt_entry.indirect_reference is not None
entry.indirect_reference = self._encrypt_entry.indirect_reference
self._objects[entry.indirect_reference.idnum - 1] = entry
else:
self._add_object(entry)
self._encrypt_entry = entry
def _resolve_links(self) -> None:
"""Patch up links that were added to the document earlier, to
make sure they still point to the same pages.
"""
for (new_link, old_link) in self._unresolved_links:
old_page = old_link.find_referenced_page()
if not old_page:
continue
new_page = self._merged_in_pages.get(old_page)
if new_page is None:
continue
new_link.patch_reference(self, new_page)
def write_stream(self, stream: StreamType) -> None:
if hasattr(stream, "mode") and "b" not in stream.mode:
logger_warning(
"File <%(stream_name)s> to write to is not in binary mode. "
"It may not be written to correctly.",
source=__name__,
stream_name=stream.name,
)
self._resolve_links()
if self.incremental:
assert self._reader is not None, "mypy"
self._reader.stream.seek(0)
stream.write(self._reader.stream.read(-1))
if len(self.list_objects_in_increment()) > 0:
self._write_increment(stream) # writes objs, xref stream and startxref
else:
object_positions, free_objects = self._write_pdf_structure(stream)
xref_location = self._write_xref_table(
stream, object_positions, free_objects
)
self._write_trailer(stream, xref_location)
def write(self, stream: Union[Path, StrByteType]) -> tuple[bool, IO[Any]]:
"""
Write the collection of pages added to this object out as a PDF file.
Args:
stream: An object to write the file to. The object can support
the write method and the tell method, similar to a file object, or
be a file path, just like the fileobj, just named it stream to keep
existing workflow.
Returns:
A tuple (bool, IO).
"""
my_file = False
if stream == "":
raise ValueError(f"Output({stream=}) is empty.")
if isinstance(stream, (str, Path)):
stream = FileIO(stream, "wb")
my_file = True
self.write_stream(stream)
if my_file:
stream.close()
else:
stream.flush()
return my_file, stream
def list_objects_in_increment(self) -> list[IndirectObject]:
"""
For analysis or debugging.
Provides the list of new or modified objects that will be written
in the increment.
Deleted objects will not be freed but will become orphans.
Returns:
List of new or modified IndirectObjects
"""
original_hash_count = len(self._original_hash)
return [
cast(IndirectObject, obj).indirect_reference
for i, obj in enumerate(self._objects)
if (
obj is not None
and (
i >= original_hash_count
or obj.hash_bin() != self._original_hash[i]
)
)
]
def _write_increment(self, stream: StreamType) -> None:
# Only reached from `write()` inside `if self.incremental`.
assert self._reader is not None, "mypy"
object_positions = {}
object_blocks = []
current_start = -1
current_stop = -2
original_hash_count = len(self._original_hash)
for i, obj in enumerate(self._objects):
if obj is not None and (
i >= original_hash_count
or obj.hash_bin() != self._original_hash[i]
):
idnum = i + 1
assert isinstance(obj, PdfObject), "mypy"
# first write new/modified object
object_positions[idnum] = stream.tell()
stream.write(f"{idnum} 0 obj\n".encode())
""" encryption is not operational
if self._encryption and obj != self._encrypt_entry:
obj = self._encryption.encrypt_object(obj, idnum, 0)
"""
obj.write_to_stream(stream)
stream.write(b"\nendobj\n")
# prepare xref
if idnum != current_stop:
if current_start > 0:
object_blocks.append(
[current_start, current_stop - current_start]
)
current_start = idnum
current_stop = idnum + 1
assert current_start > 0, "for pytest only"
object_blocks.append([current_start, current_stop - current_start])
# write incremented xref
xref_location = stream.tell()
xr_id = len(self._objects) + 1
stream.write(f"{xr_id} 0 obj".encode())
init_data = {
NameObject("/Type"): NameObject("/XRef"),
NameObject("/Size"): NumberObject(xr_id + 1),
NameObject("/Root"): self.root_object.indirect_reference,
NameObject("/Filter"): NameObject("/FlateDecode"),
NameObject("/Index"): ArrayObject(
[NumberObject(_it) for _su in object_blocks for _it in _su]
),
NameObject("/W"): ArrayObject(
[NumberObject(1), NumberObject(4), NumberObject(1)]
),
"__streamdata__": b"",
}
if self._info is not None and (
self._info.indirect_reference.idnum - 1 # type: ignore[union-attr]
>= len(self._original_hash)
or cast(IndirectObject, self._info).hash_bin() # kept for future
!= self._original_hash[
self._info.indirect_reference.idnum - 1 # type: ignore[union-attr]
]
):
init_data[NameObject(TK.INFO)] = self._info.indirect_reference
init_data[NameObject(TK.PREV)] = NumberObject(self._reader._startxref)
if self._ID:
init_data[NameObject(TK.ID)] = self._ID
xr = StreamObject.initialize_from_dictionary(init_data)
xr.set_data(
b"".join(
[struct.pack(b">BIB", 1, _pos, 0) for _pos in object_positions.values()]
)
)
xr.write_to_stream(stream)
stream.write(f"\nendobj\nstartxref\n{xref_location}\n%%EOF\n".encode()) # eof
def _write_pdf_structure(self, stream: StreamType) -> tuple[list[int], list[int]]:
object_positions = []
free_objects = []
stream.write(self.pdf_header.encode() + b"\n")
stream.write(b"%\xE2\xE3\xCF\xD3\n")
for idnum, obj in enumerate(self._objects, start=1):
if obj is not None:
object_positions.append(stream.tell())
stream.write(f"{idnum} 0 obj\n".encode())
if self._encryption and obj != self._encrypt_entry:
obj = self._encryption.encrypt_object(obj, idnum, 0)
obj.write_to_stream(stream)
stream.write(b"\nendobj\n")
else:
object_positions.append(-1)
free_objects.append(idnum)
free_objects.append(0) # add 0 to loop in accordance with specification
return object_positions, free_objects
def _write_xref_table(
self, stream: StreamType, object_positions: list[int], free_objects: list[int]
) -> int:
xref_location = stream.tell()
stream.write(b"xref\n")
stream.write(f"0 {len(self._objects) + 1}\n".encode())
stream.write(f"{free_objects[0]:0>10} {65535:0>5} f \n".encode())
free_idx = 1
for offset in object_positions:
if offset > 0:
stream.write(f"{offset:0>10} {0:0>5} n \n".encode())
else:
stream.write(f"{free_objects[free_idx]:0>10} {1:0>5} f \n".encode())
free_idx += 1
return xref_location
def _write_trailer(self, stream: StreamType, xref_location: int) -> None:
"""
Write the PDF trailer to the stream.
To quote the PDF specification:
[The] trailer [gives] the location of the cross-reference table and
of certain special objects within the body of the file.
"""
stream.write(b"trailer\n")
trailer = DictionaryObject(
{
NameObject(TK.SIZE): NumberObject(len(self._objects) + 1),
NameObject(TK.ROOT): self.root_object.indirect_reference,
}
)
if self._info is not None:
trailer[NameObject(TK.INFO)] = self._info.indirect_reference
if self._ID is not None:
trailer[NameObject(TK.ID)] = self._ID
if self._encrypt_entry:
trailer[NameObject(TK.ENCRYPT)] = self._encrypt_entry.indirect_reference
trailer.write_to_stream(stream)
stream.write(f"\nstartxref\n{xref_location}\n%%EOF\n".encode()) # eof
@property
def metadata(self) -> Optional[DocumentInformation]:
"""
Retrieve/set the PDF file's document information dictionary, if it exists.
Args:
value: dict with the entries to be set. if None : remove the /Info entry from the pdf.
Note that some PDF files use (XMP) metadata streams instead of document
information dictionaries, and these metadata streams will not be
accessed by this function, but by :meth:`~xmp_metadata`.
"""
return super().metadata
@metadata.setter
def metadata(
self,
value: Optional[Union[DocumentInformation, DictionaryObject, dict[Any, Any]]],
) -> None:
if value is None:
self._info = None
else:
if self._info is not None:
self._info.clear()
self.add_metadata(value)
def add_metadata(self, infos: dict[str, Any]) -> None:
"""
Add custom metadata to the output.
Args:
infos: a Python dictionary where each key is a field
and each value is your new metadata.
"""
args = {}
if isinstance(infos, PdfObject):
infos = cast(DictionaryObject, infos.get_object())
for key, value in list(infos.items()):
if isinstance(value, PdfObject):
value = value.get_object()
args[NameObject(key)] = create_string_object(str(value))
if self._info is None:
self._info = DictionaryObject()
self._info.update(args)
_UNSET = object()
def compress_identical_objects(
self,
remove_identicals: Any = _UNSET,
remove_orphans: Any = _UNSET,
*,
remove_duplicates: bool = True,
remove_unreferenced: bool = True,
) -> None:
"""
Parse the PDF file and merge objects that have the same hash.
This will make objects common to multiple pages.
Recommended to be used just before writing output.
Args:
remove_identicals: Deprecated.
remove_orphans: Deprecated.
remove_duplicates: Remove duplicate objects.
remove_unreferenced: Remove unreferenced objects.
"""
if remove_identicals != self._UNSET:
deprecate_with_replacement("remove_identicals", "remove_duplicates", "7.0.0")
assert isinstance(remove_identicals, bool)
remove_duplicates = remove_identicals
if remove_orphans != self._UNSET:
deprecate_with_replacement("remove_orphans", "remove_unreferenced", "7.0.0")
assert isinstance(remove_orphans, bool)
remove_unreferenced = remove_orphans
def replace_in_obj(
obj: PdfObject, crossref: dict[IndirectObject, IndirectObject]
) -> None:
if isinstance(obj, DictionaryObject):
key_val = obj.items()
elif isinstance(obj, ArrayObject):
key_val = enumerate(obj) # type: ignore[assignment]
else:
return
assert isinstance(obj, (DictionaryObject, ArrayObject))
for k, v in key_val:
if isinstance(v, IndirectObject):
unreferenced[v.idnum - 1] = False
if v in crossref:
obj[k] = crossref[v]
else:
"""The filtering on DictionaryObject and ArrayObject only
will be performed within replace_in_obj"""
replace_in_obj(v, crossref)
# _idnum_hash: dict[hash] = (1st_ind_obj, [2nd_ind_obj,...])
self._idnum_hash = {}
unreferenced = [True] * len(self._objects)
# look for similar objects
for idx, obj in enumerate(self._objects):
if is_null_or_none(obj):
continue
assert obj is not None, "mypy" # mypy: TypeGuard of `is_null_or_none` does not help here.
assert isinstance(obj.indirect_reference, IndirectObject)
h = obj.hash_value()
if remove_duplicates and h in self._idnum_hash:
self._idnum_hash[h][1].append(obj.indirect_reference)
self._objects[idx] = None
else:
self._idnum_hash[h] = (obj.indirect_reference, [])
# generate the dict converting others to 1st
cnv = {v[0]: v[1] for v in self._idnum_hash.values() if len(v[1]) > 0}
cnv_rev: dict[IndirectObject, IndirectObject] = {}
for k, v in cnv.items():
cnv_rev.update(zip(v, (k,) * len(v)))
# replace reference to merged objects
for obj in self._objects:
if isinstance(obj, (DictionaryObject, ArrayObject)):
replace_in_obj(obj, cnv_rev)
if remove_unreferenced:
unreferenced[self.root_object.indirect_reference.idnum - 1] = False # type: ignore[union-attr]
if not is_null_or_none(self._info):
unreferenced[self._info.indirect_reference.idnum - 1] = False # type: ignore[union-attr]
try:
unreferenced[self._ID.indirect_reference.idnum - 1] = False # type: ignore[union-attr]
except AttributeError:
pass
for i in compress(range(len(self._objects)), unreferenced):
self._objects[i] = None
def get_reference(self, obj: PdfObject) -> IndirectObject:
idnum = self._objects.index(obj) + 1
ref = IndirectObject(idnum, 0, self)
assert ref.get_object() == obj
return ref
def get_outline_root(self) -> TreeObject:
if Core.OUTLINES in self._root_object:
# Entries in the catalog dictionary
outline = cast(TreeObject, self._root_object[Core.OUTLINES])
if not isinstance(outline, TreeObject):
t = TreeObject(outline)
self._replace_object(outline.indirect_reference.idnum, t)
outline = t
idnum = self._objects.index(outline) + 1
outline_ref = IndirectObject(idnum, 0, self)
assert outline_ref.get_object() == outline
else:
outline = TreeObject()
outline.update({})
outline_ref = self._add_object(outline)
self._root_object[NameObject(Core.OUTLINES)] = outline_ref
return outline
def get_threads_root(self) -> ArrayObject:
"""
The list of threads.
See §12.4.3 of the PDF 1.7 or PDF 2.0 specification.
Returns:
An array (possibly empty) of Dictionaries with an ``/F`` key,
and optionally information about the thread in ``/I`` or ``/Metadata`` keys.
"""
if Core.THREADS in self._root_object:
# Entries in the catalog dictionary
threads = cast(ArrayObject, self._root_object[Core.THREADS])
else:
threads = ArrayObject()
self._root_object[NameObject(Core.THREADS)] = threads
return threads
@property
def threads(self) -> ArrayObject:
"""
Read-only property for the list of threads.
See §12.4.3 of the PDF 1.7 or PDF 2.0 specification.
Each element is a dictionary with an ``/F`` key, and optionally
information about the thread in ``/I`` or ``/Metadata`` keys.
"""
return self.get_threads_root()
def add_outline_item_destination(
self,
page_destination: Union[IndirectObject, PageObject, TreeObject],
parent: Union[TreeObject, IndirectObject, None] = None,
before: Union[TreeObject, IndirectObject, None] = None,
is_open: bool = True,
) -> IndirectObject:
page_destination = cast(PageObject, page_destination.get_object())
if isinstance(page_destination, PageObject):
return self.add_outline_item_destination(
Destination(
f"page #{page_destination.page_number}",
cast(IndirectObject, page_destination.indirect_reference),
Fit.fit(),
)
)
if parent is None:
parent = self.get_outline_root()
page_destination[NameObject("/%is_open%")] = BooleanObject(is_open)
parent = cast(TreeObject, parent.get_object())
page_destination_ref = self._add_object(page_destination)
if before is not None:
before = before.indirect_reference
parent.insert_child(
page_destination_ref,
before,
self,
page_destination.inc_parent_counter_outline
if is_open
else (lambda x, y: 0), # noqa: ARG005
)
if "/Count" not in page_destination:
page_destination[NameObject("/Count")] = NumberObject(0)
return page_destination_ref
def add_outline_item_dict(
self,
outline_item: OutlineItemType,
parent: Union[TreeObject, IndirectObject, None] = None,
before: Union[TreeObject, IndirectObject, None] = None,
is_open: bool = True,
) -> IndirectObject:
outline_item_object = TreeObject()
outline_item_object.update(outline_item)
"""code currently unreachable
if "/A" in outline_item:
action = DictionaryObject()
a_dict = cast(DictionaryObject, outline_item["/A"])
for k, v in list(a_dict.items()):
action[NameObject(str(k))] = v
action_ref = self._add_object(action)
outline_item_object[NameObject("/A")] = action_ref
"""
return self.add_outline_item_destination(
outline_item_object, parent, before, is_open
)
def add_outline_item(
self,
title: str,
page_number: Union[PageObject, IndirectObject, int, None],
parent: Union[TreeObject, IndirectObject, None] = None,
before: Union[TreeObject, IndirectObject, None] = None,
color: Optional[Union[tuple[float, float, float], str]] = None,
bold: bool = False,
italic: bool = False,
fit: Fit = PAGE_FIT,
is_open: bool = True,
) -> IndirectObject:
"""
Add an outline item (commonly referred to as a "Bookmark") to the PDF file.
Args:
title: Title to use for this outline item.
page_number: Page number this outline item will point to.
parent: A reference to a parent outline item to create nested
outline items.
before:
color: Color of the outline item's font as a red, green, blue tuple
from 0.0 to 1.0 or as a Hex String (#RRGGBB)
bold: Outline item font is bold
italic: Outline item font is italic
fit: The fit of the destination page.
Returns:
The added outline item as an indirect object.
"""
page_ref: Union[NullObject, IndirectObject, NumberObject, None]
if isinstance(italic, Fit): # it means that we are on the old params
if fit is not None and page_number is None:
page_number = fit
return self.add_outline_item(
title, page_number, parent, None, before, color, bold, italic, is_open=is_open
)
if page_number is None:
action_ref = None
else:
if isinstance(page_number, IndirectObject):
page_ref = page_number
elif isinstance(page_number, PageObject):
page_ref = page_number.indirect_reference
elif isinstance(page_number, int):
try:
page_ref = self.pages[page_number].indirect_reference
except IndexError:
page_ref = NumberObject(page_number)
if page_ref is None:
logger_warning(
"can not find reference of page %(page_number)s",
source=__name__,
page_number=page_number,
)
page_ref = NullObject()
dest = Destination(
NameObject("/" + title + " outline item"),
page_ref,
fit,
)
action_ref = self._add_object(
DictionaryObject(
{
NameObject(GoToActionArguments.D): dest.dest_array,
NameObject(GoToActionArguments.S): NameObject("/GoTo"),
}
)
)
outline_item = self._add_object(
_create_outline_item(action_ref, title, color, italic, bold)
)
if parent is None:
parent = self.get_outline_root()
return self.add_outline_item_destination(outline_item, parent, before, is_open)
def add_outline(self) -> None:
raise NotImplementedError(
"This method is not yet implemented. Use :meth:`add_outline_item` instead."
)
def add_named_destination_array(
self, title: TextStringObject, destination: Union[IndirectObject, ArrayObject]
) -> None:
named_dest = self.get_named_dest_root()
i = 0
while i < len(named_dest):
if title < named_dest[i]:
named_dest.insert(i, destination)
named_dest.insert(i, TextStringObject(title))
return
i += 2
named_dest.extend([TextStringObject(title), destination])
return
def add_named_destination_object(
self,
page_destination: PdfObject,
) -> IndirectObject:
page_destination_ref = self._add_object(page_destination.dest_array) # type: ignore[attr-defined]
self.add_named_destination_array(
cast("TextStringObject", page_destination["/Title"]), page_destination_ref # type: ignore[index]
)
return page_destination_ref
def add_named_destination(
self,
title: str,
page_number: int,
) -> IndirectObject:
page_ref = self.get_object(self._pages)[PagesAttributes.KIDS][page_number] # type: ignore[index]
dest = DictionaryObject()
dest.update(
{
NameObject(GoToActionArguments.D): ArrayObject(
[page_ref, NameObject(TypFitArguments.FIT_H), NumberObject(826)]
),
NameObject(GoToActionArguments.S): NameObject("/GoTo"),
}
)
dest_ref = self._add_object(dest)
if not isinstance(title, TextStringObject):
title = TextStringObject(str(title))
self.add_named_destination_array(title, dest_ref)
return dest_ref
def remove_links(self) -> None:
"""Remove links and annotations from this output."""
for page in self.pages:
self.remove_objects_from_page(page, ObjectDeletionFlag.ALL_ANNOTATIONS)
def remove_annotations(
self, subtypes: Optional[Union[AnnotationSubtype, Iterable[AnnotationSubtype]]]
) -> None:
"""
Remove annotations by annotation subtype.
Args:
subtypes: subtype or list of subtypes to be removed.
Examples are: "/Link", "/FileAttachment", "/Sound",
"/Movie", "/Screen", ...
If you want to remove all annotations, use subtypes=None.
"""
for page in self.pages:
self._remove_annots_from_page(page, subtypes)
def _remove_annots_from_page(
self,
page: Union[IndirectObject, PageObject, DictionaryObject],
subtypes: Optional[Iterable[str]],
) -> None:
page = cast(DictionaryObject, page.get_object())
if PG.ANNOTS in page:
i = 0
while i < len(cast(ArrayObject, page[PG.ANNOTS])):
an = cast(ArrayObject, page[PG.ANNOTS])[i]
obj = cast(DictionaryObject, an.get_object())
if subtypes is None or cast(str, obj["/Subtype"]) in subtypes:
if isinstance(an, IndirectObject):
self._objects[an.idnum - 1] = NullObject() # to reduce PDF size
del page[PG.ANNOTS][i] # type:ignore
else:
i += 1
def remove_objects_from_page(
self,
page: Union[PageObject, DictionaryObject],
to_delete: Union[ObjectDeletionFlag, Iterable[ObjectDeletionFlag]],
text_filters: Optional[dict[str, Any]] = None
) -> None:
"""
Remove objects specified by ``to_delete`` from the given page.
Args:
page: Page object to clean up.
to_delete: Objects to be deleted; can be a ``ObjectDeletionFlag``
or a list of ObjectDeletionFlag
text_filters: Properties of text to be deleted, if applicable. Optional.
This is a Python dictionary with the following properties:
* font_ids: List of font resource IDs (such as /F1 or /T1_0) to be deleted.
"""
if isinstance(to_delete, (list, tuple)):
for to_d in to_delete:
self.remove_objects_from_page(page, to_d)
return None
assert isinstance(to_delete, ObjectDeletionFlag)
if to_delete & ObjectDeletionFlag.LINKS:
return self._remove_annots_from_page(page, ("/Link",))
if to_delete & ObjectDeletionFlag.ATTACHMENTS:
return self._remove_annots_from_page(
page, ("/FileAttachment", "/Sound", "/Movie", "/Screen")
)
if to_delete & ObjectDeletionFlag.OBJECTS_3D:
return self._remove_annots_from_page(page, ("/3D",))
if to_delete & ObjectDeletionFlag.ALL_ANNOTATIONS:
return self._remove_annots_from_page(page, None)
jump_operators = []
if to_delete & ObjectDeletionFlag.DRAWING_IMAGES:
jump_operators = [
b"w", b"J", b"j", b"M", b"d", b"i",
b"W", b"W*",
b"b", b"b*", b"B", b"B*", b"S", b"s", b"f", b"f*", b"F", b"n",
b"m", b"l", b"c", b"v", b"y", b"h", b"re",
b"sh"
]
if to_delete & ObjectDeletionFlag.TEXT:
jump_operators = [b"Tj", b"TJ", b"'", b'"']
if not isinstance(page, PageObject):
page = PageObject(self, page.indirect_reference) # pragma: no cover
if "/Contents" in page:
content = cast(ContentStream, page.get_contents())
images, forms = self._remove_objects_from_page__clean_forms(
elt=page, stack=[], jump_operators=jump_operators, to_delete=to_delete, text_filters=text_filters,
)
self._remove_objects_from_page__clean(
content=content, images=images, forms=forms,
jump_operators=jump_operators, to_delete=to_delete,
text_filters=text_filters
)
page.replace_contents(content)
return None
def _remove_objects_from_page__clean(
self,
content: ContentStream,
images: list[str],
forms: list[str],
jump_operators: list[bytes],
to_delete: ObjectDeletionFlag,
text_filters: Optional[dict[str, Any]] = None,
) -> None:
font_id = None
font_ids_to_delete = []
if text_filters and to_delete & ObjectDeletionFlag.TEXT:
font_ids_to_delete = text_filters.get("font_ids", [])
i = 0
while i < len(content.operations):
operands, operator = content.operations[i]
if operator == b"Tf":
font_id = operands[0]
if (
(
operator == b"INLINE IMAGE"
and (to_delete & ObjectDeletionFlag.INLINE_IMAGES)
)
or (operator in jump_operators)
or (
operator == b"Do"
and (to_delete & ObjectDeletionFlag.XOBJECT_IMAGES)
and (operands[0] in images)
)
):
if (
not to_delete & ObjectDeletionFlag.TEXT
or (to_delete & ObjectDeletionFlag.TEXT and not text_filters)
or (to_delete & ObjectDeletionFlag.TEXT and font_id in font_ids_to_delete)
):
del content.operations[i]
else:
i += 1
else:
i += 1
content.get_data() # this ensures ._data is rebuilt from the .operations
def _remove_objects_from_page__clean_forms(
self,
elt: DictionaryObject,
stack: list[DictionaryObject],
jump_operators: list[bytes],
to_delete: ObjectDeletionFlag,
text_filters: Optional[dict[str, Any]] = None,
) -> tuple[list[str], list[str]]:
# elt in recursive call is a new ContentStream object, so we have to check the indirect_reference
if (elt in stack) or (
hasattr(elt, "indirect_reference") and any(
elt.indirect_reference == getattr(x, "indirect_reference", -1)
for x in stack
)
):
# to prevent infinite looping
return [], [] # pragma: no cover
try:
d = cast(
dict[Any, Any],
cast(DictionaryObject, elt["/Resources"])["/XObject"],
)
except KeyError:
d = {}
images = []
forms = []
for k, v in d.items():
o = v.get_object()
try:
content: Any = None
if (
to_delete & ObjectDeletionFlag.XOBJECT_IMAGES
and o["/Subtype"] == "/Image"
):
content = NullObject() # to delete the image keeping the entry
images.append(k)
if o["/Subtype"] == "/Form":
forms.append(k)
if isinstance(o, ContentStream):
content = o
else:
content = ContentStream(o, self)
content.update(
{
k1: v1
for k1, v1 in o.items()
if k1 not in ["/Length", "/Filter", "/DecodeParms"]
}
)
try:
content.indirect_reference = o.indirect_reference
except AttributeError: # pragma: no cover
pass
stack.append(elt)
# clean subforms
self._remove_objects_from_page__clean_forms(
elt=content, stack=stack, jump_operators=jump_operators, to_delete=to_delete,
text_filters=text_filters,
)
if content is not None:
if isinstance(v, IndirectObject):
self._objects[v.idnum - 1] = content
else:
# should only occur in a PDF not respecting PDF spec
# where streams must be indirected.
d[k] = self._add_object(content) # pragma: no cover
except (TypeError, KeyError):
pass
for im in images:
del d[im] # for clean-up
if isinstance(elt, StreamObject): # for /Form
if not isinstance(elt, ContentStream): # pragma: no cover
e = ContentStream(elt, self)
e.update(elt.items())
elt = e
# clean the content
self._remove_objects_from_page__clean(
content=elt, images=images, forms=forms, jump_operators=jump_operators,
to_delete=to_delete, text_filters=text_filters
)
return images, forms
def remove_images(
self,
to_delete: ImageType = ImageType.ALL,
) -> None:
"""
Remove images from this output.
Args:
to_delete: The type of images to be deleted
(default = all images types)
"""
if isinstance(to_delete, bool):
to_delete = ImageType.ALL
i = ObjectDeletionFlag.NONE
for image in ("XOBJECT_IMAGES", "INLINE_IMAGES", "DRAWING_IMAGES"):
if to_delete & ImageType[image]:
i |= ObjectDeletionFlag[image]
for page in self.pages:
self.remove_objects_from_page(page, i)
def remove_text(self, font_names: Optional[list[str]] = None) -> None:
"""
Remove text from the PDF.
Args:
font_names: List of font names to remove, such as "Helvetica-Bold".
Optional. If not specified, all text will be removed.
"""
if not font_names:
font_names = []
for page in self.pages:
resource_ids_to_remove = []
# Content streams reference fonts and other resources with names like "/F1" or "/T1_0"
# Font names need to be converted to resource names/IDs for easier removal
if font_names:
# Recursively loop through page objects to gather font info
def get_font_info(
obj: Any,
font_info: Optional[dict[str, Any]] = None,
key: Optional[str] = None
) -> dict[str, Any]:
if font_info is None:
font_info = {}
if isinstance(obj, IndirectObject):
obj = obj.get_object()
if isinstance(obj, dict):
if obj.get("/Type") == "/Font":
font_name = obj.get("/BaseFont", "")
# Normalize font names like "/RRXFFV+Palatino-Bold" to "Palatino-Bold"
normalized_font_name = font_name.lstrip("/").split("+")[-1]
if normalized_font_name not in font_info:
font_info[normalized_font_name] = {
"normalized_font_name": normalized_font_name,
"resource_ids": [],
}
if key not in font_info[normalized_font_name]["resource_ids"]:
font_info[normalized_font_name]["resource_ids"].append(key)
for k in obj:
font_info = get_font_info(obj[k], font_info, k)
elif isinstance(obj, (list, ArrayObject)):
for child_obj in obj:
font_info = get_font_info(child_obj, font_info)
return font_info
# Add relevant resource names for removal
font_info = get_font_info(page.get("/Resources"))
for font_name in font_names:
if font_name in font_info:
resource_ids_to_remove.extend(font_info[font_name]["resource_ids"])
text_filters = {}
if font_names:
text_filters["font_ids"] = resource_ids_to_remove
self.remove_objects_from_page(page, ObjectDeletionFlag.TEXT, text_filters=text_filters)
def add_uri(
self,
page_number: int,
uri: str,
rect: RectangleObject,
border: Optional[Sequence[Any]] = None,
) -> None:
"""
Add an URI from a rectangular area to the specified page.
Args:
page_number: index of the page on which to place the URI action.
uri: URI of resource to link to.
rect: :class:`RectangleObject<pypdf.generic.RectangleObject>` or
array of four integers specifying the clickable rectangular area
``[xLL, yLL, xUR, yUR]``, or string in the form
``"[ xLL yLL xUR yUR ]"``.
border: if provided, an array describing border-drawing
properties. See the PDF spec for details. No border will be
drawn if this argument is omitted.
"""
page_link = self.get_object(self._pages)[PagesAttributes.KIDS][page_number] # type: ignore[index]
page_ref = cast(dict[str, Any], self.get_object(page_link))
border_arr: BorderArrayType
if border is not None:
border_arr = [NumberObject(n) for n in border[:3]]
if len(border) == 4:
dash_pattern = ArrayObject([NumberObject(n) for n in border[3]])
border_arr.append(dash_pattern)
else:
border_arr = [NumberObject(2), NumberObject(2), NumberObject(2)]
if isinstance(rect, str):
rect = NumberObject(rect)
elif isinstance(rect, RectangleObject):
pass
else:
rect = RectangleObject(rect)
lnk2 = DictionaryObject()
lnk2.update(
{
NameObject("/S"): NameObject("/URI"),
NameObject("/URI"): TextStringObject(uri),
}
)
lnk = DictionaryObject()
lnk.update(
{
NameObject(AA.Type): NameObject("/Annot"),
NameObject(AA.Subtype): NameObject("/Link"),
NameObject(AA.P): page_link,
NameObject(AA.Rect): rect,
NameObject("/H"): NameObject("/I"),
NameObject(AA.Border): ArrayObject(border_arr),
NameObject("/A"): lnk2,
}
)
lnk_ref = self._add_object(lnk)
if PG.ANNOTS in page_ref:
page_ref[PG.ANNOTS].append(lnk_ref)
else:
page_ref[NameObject(PG.ANNOTS)] = ArrayObject([lnk_ref])
_valid_layouts = (
"/NoLayout",
"/SinglePage",
"/OneColumn",
"/TwoColumnLeft",
"/TwoColumnRight",
"/TwoPageLeft",
"/TwoPageRight",
)
def _get_page_layout(self) -> Optional[LayoutType]:
try:
return cast(LayoutType, self._root_object["/PageLayout"])
except KeyError:
return None
def _set_page_layout(self, layout: Union[NameObject, LayoutType]) -> None:
"""
Set the page layout.
Args:
layout: The page layout to be used.
.. list-table:: Valid ``layout`` arguments
:widths: 50 200
* - /NoLayout
- Layout explicitly not specified
* - /SinglePage
- Show one page at a time
* - /OneColumn
- Show one column at a time
* - /TwoColumnLeft
- Show pages in two columns, odd-numbered pages on the left
* - /TwoColumnRight
- Show pages in two columns, odd-numbered pages on the right
* - /TwoPageLeft
- Show two pages at a time, odd-numbered pages on the left
* - /TwoPageRight
- Show two pages at a time, odd-numbered pages on the right
"""
if not isinstance(layout, NameObject):
if layout not in self._valid_layouts:
logger_warning(
"Layout should be one of: %(layouts)s",
source=__name__,
layouts={"", "".join(self._valid_layouts)},
)
layout = NameObject(layout)
self._root_object.update({NameObject("/PageLayout"): layout})
def set_page_layout(self, layout: LayoutType) -> None:
"""
Set the page layout.
Args:
layout: The page layout to be used
.. list-table:: Valid ``layout`` arguments
:widths: 50 200
* - /NoLayout
- Layout explicitly not specified
* - /SinglePage
- Show one page at a time
* - /OneColumn
- Show one column at a time
* - /TwoColumnLeft
- Show pages in two columns, odd-numbered pages on the left
* - /TwoColumnRight
- Show pages in two columns, odd-numbered pages on the right
* - /TwoPageLeft
- Show two pages at a time, odd-numbered pages on the left
* - /TwoPageRight
- Show two pages at a time, odd-numbered pages on the right
"""
self._set_page_layout(layout)
@property
def page_layout(self) -> Optional[LayoutType]:
"""
Page layout property.
.. list-table:: Valid ``layout`` values
:widths: 50 200
* - /NoLayout
- Layout explicitly not specified
* - /SinglePage
- Show one page at a time
* - /OneColumn
- Show one column at a time
* - /TwoColumnLeft
- Show pages in two columns, odd-numbered pages on the left
* - /TwoColumnRight
- Show pages in two columns, odd-numbered pages on the right
* - /TwoPageLeft
- Show two pages at a time, odd-numbered pages on the left
* - /TwoPageRight
- Show two pages at a time, odd-numbered pages on the right
"""
return self._get_page_layout()
@page_layout.setter
def page_layout(self, layout: LayoutType) -> None:
self._set_page_layout(layout)
_valid_modes = (
"/UseNone",
"/UseOutlines",
"/UseThumbs",
"/FullScreen",
"/UseOC",
"/UseAttachments",
)
def _get_page_mode(self) -> Optional[PagemodeType]:
try:
return cast(PagemodeType, self._root_object["/PageMode"])
except KeyError:
return None
@property
def page_mode(self) -> Optional[PagemodeType]:
"""
Page mode property.
.. list-table:: Valid ``mode`` values
:widths: 50 200
* - /UseNone
- Do not show outline or thumbnails panels
* - /UseOutlines
- Show outline (aka bookmarks) panel
* - /UseThumbs
- Show page thumbnails panel
* - /FullScreen
- Fullscreen view
* - /UseOC
- Show Optional Content Group (OCG) panel
* - /UseAttachments
- Show attachments panel
"""
return self._get_page_mode()
@page_mode.setter
def page_mode(self, mode: PagemodeType) -> None:
if isinstance(mode, NameObject):
mode_name: NameObject = mode
else:
if mode not in self._valid_modes:
logger_warning(
"Mode should be one of: %(modes)s",
source=__name__,
modes=", ".join(self._valid_modes),
)
mode_name = NameObject(mode)
self._root_object.update({NameObject("/PageMode"): mode_name})
def add_annotation(
self,
page_number: Union[int, PageObject],
annotation: dict[str, Any],
) -> DictionaryObject:
"""
Add a single annotation to the page.
The added annotation must be a new annotation.
It cannot be recycled.
Args:
page_number: PageObject or page index.
annotation: Annotation to be added (created with annotation).
Returns:
The inserted object.
This can be used for popup creation, for example.
"""
page = page_number
if isinstance(page, int):
page = self.pages[page]
elif not isinstance(page, PageObject):
raise TypeError("page: invalid type")
to_add = cast(DictionaryObject, _pdf_objectify(annotation))
to_add[NameObject("/P")] = page.indirect_reference
if page.annotations is None:
page[NameObject("/Annots")] = ArrayObject()
assert page.annotations is not None
# Internal link annotations need the correct object type for the
# destination
if to_add.get("/Subtype") == "/Link" and "/Dest" in to_add:
tmp = cast(dict[Any, Any], to_add[NameObject("/Dest")])
dest = Destination(
NameObject("/LinkName"),
tmp["target_page_index"],
Fit(
fit_type=tmp["fit"], fit_args=dict(tmp)["fit_args"]
), # I have no clue why this dict-hack is necessary
)
to_add[NameObject("/Dest")] = dest.dest_array
page.annotations.append(self._add_object(to_add))
if to_add.get("/Subtype") == "/Popup" and NameObject("/Parent") in to_add:
cast(DictionaryObject, to_add["/Parent"].get_object())[
NameObject("/Popup")
] = to_add.indirect_reference
return to_add
def clean_page(self, page: Union[PageObject, IndirectObject]) -> PageObject:
"""
Perform some clean up in the page.
Currently: convert NameObject named destination to TextStringObject
(required for names/dests list)
Args:
page:
Returns:
The cleaned PageObject
"""
page = cast("PageObject", page.get_object())
for a in page.get("/Annots", []):
a_obj = a.get_object()
d = a_obj.get("/Dest", None)
act = a_obj.get("/A", None)
if isinstance(d, NameObject):
a_obj[NameObject("/Dest")] = TextStringObject(d)
elif act is not None:
act = act.get_object()
d = act.get("/D", None)
if isinstance(d, NameObject):
act[NameObject("/D")] = TextStringObject(d)
return page
def _create_stream(
self, fileobj: Union[Path, StrByteType, PdfReader]
) -> tuple[IOBase, Optional[Encryption]]:
# If the fileobj parameter is a string, assume it is a path
# and create a file object at that location. If it is a file,
# copy the file's contents into a BytesIO stream object; if
# it is a PdfReader, copy that reader's stream into a
# BytesIO stream.
# If fileobj is none of the above types, it is not modified
encryption_obj = None
stream: IOBase
if isinstance(fileobj, (str, Path)):
with FileIO(fileobj, "rb") as f:
stream = BytesIO(f.read())
elif isinstance(fileobj, PdfReader):
if fileobj._encryption:
encryption_obj = fileobj._encryption
orig_tell = fileobj.stream.tell()
fileobj.stream.seek(0)
stream = BytesIO(fileobj.stream.read())
# reset the stream to its original location
fileobj.stream.seek(orig_tell)
elif hasattr(fileobj, "seek") and hasattr(fileobj, "read"):
fileobj.seek(0)
filecontent = fileobj.read()
stream = BytesIO(filecontent)
else:
raise NotImplementedError(
"Merging requires an object that PdfReader can parse. "
"Typically, that is a Path or a string representing a Path, "
"a file object, or an object implementing .seek and .read. "
"Passing a PdfReader directly works as well."
)
return stream, encryption_obj
def append(
self,
fileobj: Union[StrByteType, PdfReader, Path],
outline_item: Union[str, PageRange, tuple[int, int], tuple[int, int, int], list[int], None] = None,
pages: Union[PageRange, tuple[int, int], tuple[int, int, int], list[int], list[PageObject], None] = None,
import_outline: bool = True,
excluded_fields: Optional[Union[list[str], tuple[str, ...]]] = None,
) -> None:
"""
Identical to the :meth:`merge()<merge>` method, but assumes you want to
concatenate all pages onto the end of the file instead of specifying a
position.
Args:
fileobj: A File Object or an object that supports the standard
read and seek methods similar to a File Object. Could also be a
string representing a path to a PDF file.
outline_item: Optionally, you may specify a string to build an
outline (aka 'bookmark') to identify the beginning of the
included file.
pages: Can be a :class:`PageRange<pypdf.pagerange.PageRange>`
or a ``(start, stop[, step])`` tuple
or a list of pages to be processed
to merge only the specified range of pages from the source
document into the output document.
import_outline: You may prevent the source document's
outline (collection of outline items, previously referred to as
'bookmarks') from being imported by specifying this as ``False``.
excluded_fields: Provide the list of fields/keys to be ignored
if ``/Annots`` is part of the list, the annotation will be ignored
if ``/B`` is part of the list, the articles will be ignored
"""
if excluded_fields is None:
excluded_fields = ()
if isinstance(outline_item, (tuple, list, PageRange)):
if isinstance(pages, bool):
if not isinstance(import_outline, bool):
excluded_fields = import_outline
import_outline = pages
pages = outline_item
self.merge(
None,
fileobj,
None,
pages,
import_outline,
excluded_fields,
)
else: # if isinstance(outline_item, str):
self.merge(
None,
fileobj,
outline_item,
pages,
import_outline,
excluded_fields,
)
def merge(
self,
position: Optional[int],
fileobj: Union[Path, StrByteType, PdfReader],
outline_item: Optional[str] = None,
pages: Optional[Union[PageRangeSpec, list[PageObject]]] = None,
import_outline: bool = True,
excluded_fields: Optional[Union[list[str], tuple[str, ...]]] = (),
) -> None:
"""
Merge the pages from the given file into the output file at the
specified page number.
Args:
position: The *page number* to insert this file. File will
be inserted after the given number.
fileobj: A File Object or an object that supports the standard
read and seek methods similar to a File Object. Could also be a
string representing a path to a PDF file.
outline_item: Optionally, you may specify a string to build an outline
(aka 'bookmark') to identify the
beginning of the included file.
pages: can be a :class:`PageRange<pypdf.pagerange.PageRange>`
or a ``(start, stop[, step])`` tuple
or a list of pages to be processed
to merge only the specified range of pages from the source
document into the output document.
import_outline: You may prevent the source document's
outline (collection of outline items, previously referred to as
'bookmarks') from being imported by specifying this as ``False``.
excluded_fields: provide the list of fields/keys to be ignored
if ``/Annots`` is part of the list, the annotation will be ignored
if ``/B`` is part of the list, the articles will be ignored
Raises:
TypeError: The pages attribute is not configured properly
"""
if isinstance(fileobj, PdfDocCommon):
reader = fileobj
else:
stream, _encryption_obj = self._create_stream(fileobj)
# Create a new PdfReader instance using the stream
# (either file or BytesIO or StringIO) created above
reader = PdfReader(stream, strict=False) # type: ignore[arg-type]
if excluded_fields is None:
excluded_fields = ()
# Find the range of pages to merge.
if pages is None:
pages = list(range(len(reader.pages)))
elif isinstance(pages, PageRange):
pages = list(range(*pages.indices(len(reader.pages))))
elif isinstance(pages, list):
pass # keep unchanged
elif isinstance(pages, tuple) and len(pages) <= 3:
pages = list(range(*pages))
elif not isinstance(pages, tuple):
raise TypeError(
'"pages" must be a tuple of (start, stop[, step]) or a list'
)
srcpages = {}
for page in pages:
if isinstance(page, PageObject):
pg = page
else:
pg = reader.pages[page]
assert pg.indirect_reference is not None
if position is None:
# numbers in the exclude list identifies that the exclusion is
# only applicable to 1st level of cloning
srcpages[pg.indirect_reference.idnum] = self.add_page(
pg, [*list(excluded_fields), 1, "/B", 1, "/Annots"] # type: ignore[list-item]
)
else:
srcpages[pg.indirect_reference.idnum] = self.insert_page(
pg, position, [*list(excluded_fields), 1, "/B", 1, "/Annots"] # type: ignore[list-item]
)
position += 1
srcpages[pg.indirect_reference.idnum].original_page = pg
reader._named_destinations = (
reader.named_destinations
) # need for the outline processing below
arr: Any
for dest in reader._named_destinations.values():
self._merge__process_named_dests(dest=dest, reader=reader, srcpages=srcpages)
outline_item_typ: TreeObject
if outline_item is not None:
outline_item_typ = cast(
"TreeObject",
self.add_outline_item(
TextStringObject(outline_item),
next(iter(srcpages.values())).indirect_reference,
fit=PAGE_FIT,
).get_object(),
)
else:
outline_item_typ = self.get_outline_root()
_ro = reader.root_object
if import_outline and Core.OUTLINES in _ro:
outline = self._get_filtered_outline(
node=_ro.get(Core.OUTLINES, None), pages=srcpages, reader=reader
)
self._insert_filtered_outline(
outline, outline_item_typ, None
) # TODO: use before parameter
if "/Annots" not in excluded_fields:
for pag in srcpages.values():
lst = self._insert_filtered_annotations(
pag.original_page.get("/Annots", []), pag, srcpages, reader
)
if len(lst) > 0:
pag[NameObject("/Annots")] = lst
self.clean_page(pag)
if "/AcroForm" in _ro and not is_null_or_none(_ro["/AcroForm"]):
if "/AcroForm" not in self._root_object:
self._root_object[NameObject("/AcroForm")] = self._add_object(
cast(
DictionaryObject,
reader.root_object["/AcroForm"],
).clone(self, False, ("/Fields",))
)
arr = ArrayObject()
else:
arr = cast(
ArrayObject,
cast(DictionaryObject, self._root_object["/AcroForm"])["/Fields"],
)
trslat = self._id_translated[id(reader)]
try:
for f in reader.root_object["/AcroForm"]["/Fields"]: # type: ignore[index]
try:
ind = IndirectObject(trslat[f.idnum], 0, self)
if ind not in arr:
arr.append(ind)
except KeyError:
# for trslat[] which mean the field has not be copied
# through the page
pass
except KeyError: # for /Acroform or /Fields are not existing
arr = self._add_object(ArrayObject())
cast(DictionaryObject, self._root_object["/AcroForm"])[
NameObject("/Fields")
] = arr
if "/B" not in excluded_fields:
self.add_filtered_articles("", srcpages, reader)
def _merge__process_named_dests(self, dest: Any, reader: PdfDocCommon, srcpages: dict[int, PageObject]) -> None:
arr: Any = dest.dest_array
if "/Names" in self._root_object and dest["/Title"] in cast(
list[Any],
cast(
DictionaryObject,
cast(DictionaryObject, self._root_object["/Names"]).get("/Dests", DictionaryObject()),
).get("/Names", DictionaryObject()),
):
# already exists: should not duplicate it
pass
elif dest["/Page"] is None or isinstance(dest["/Page"], NullObject):
pass
elif isinstance(dest["/Page"], int):
# the page reference is a page number normally not a PDF Reference
# page numbers as int are normally accepted only in external goto
try:
p = reader.pages[dest["/Page"]]
except IndexError:
return
assert p.indirect_reference is not None
try:
arr[NumberObject(0)] = NumberObject(
srcpages[p.indirect_reference.idnum].page_number
)
self.add_named_destination_array(dest["/Title"], arr)
except KeyError:
pass
elif dest["/Page"].indirect_reference.idnum in srcpages:
arr[NumberObject(0)] = srcpages[
dest["/Page"].indirect_reference.idnum
].indirect_reference
self.add_named_destination_array(dest["/Title"], arr)
def _add_articles_thread(
self,
thread: DictionaryObject,
pages: dict[int, PageObject],
reader: PdfReader,
) -> IndirectObject:
"""
Clone the thread with only the applicable articles.
Args:
thread: Thread entry from the reader's array of threads
pages: Mapping of object numbers to page objects.
reader: The corresponding reader.
Returns:
The added thread as an indirect reference
"""
new_thread = thread.clone(
self, force_duplicate=True, ignore_fields=("/F",)
) # use of clone to keep link between reader and writer
self.threads.append(new_thread.indirect_reference)
first_article = cast("DictionaryObject", thread["/F"])
current_article: Optional[DictionaryObject] = first_article
new_article: Optional[DictionaryObject] = None
visited: set[int] = set()
while current_article is not None:
article_id = id(current_article)
if article_id in visited:
raise LimitReachedError("Detected cyclic article structure.")
visited.add(article_id)
page = self._get_cloned_page(
cast("PageObject", current_article["/P"]), pages, reader
)
if page is not None:
if new_article is None:
new_article = cast(
"DictionaryObject",
self._add_object(DictionaryObject()).get_object(),
)
new_first = new_article
new_thread[NameObject("/F")] = new_article.indirect_reference
else:
new_article2 = cast(
"DictionaryObject",
self._add_object(
DictionaryObject(
{NameObject("/V"): new_article.indirect_reference}
)
).get_object(),
)
new_article[NameObject("/N")] = new_article2.indirect_reference
new_article = new_article2
new_article[NameObject("/P")] = page
new_article[NameObject("/T")] = new_thread.indirect_reference
new_article[NameObject("/R")] = current_article["/R"]
page_object = cast("PageObject", page.get_object())
if "/B" not in page_object:
page_object[NameObject("/B")] = ArrayObject()
cast("ArrayObject", page_object["/B"]).append(
new_article.indirect_reference
)
current_article = cast("DictionaryObject", current_article["/N"])
if current_article == first_article:
new_article[NameObject("/N")] = new_first.indirect_reference # type: ignore[index]
new_first[NameObject("/V")] = new_article.indirect_reference # type: ignore[union-attr]
current_article = None
assert new_thread.indirect_reference is not None
return new_thread.indirect_reference
def add_filtered_articles(
self,
fltr: Union[
Pattern[Any], str
], # thread entry from the reader's array of threads
pages: dict[int, PageObject],
reader: PdfReader,
) -> None:
"""
Add articles matching the defined criteria.
Args:
fltr:
pages:
reader:
"""
if isinstance(fltr, str):
fltr = re.compile(fltr)
elif not isinstance(fltr, Pattern):
fltr = re.compile("")
for p in pages.values():
pp = p.original_page
for a in pp.get("/B", ()):
a_obj = a.get_object()
if is_null_or_none(a_obj):
continue
thr = a_obj.get("/T")
if thr is None:
continue
thr = thr.get_object()
if thr.indirect_reference.idnum not in self._id_translated[
id(reader)
] and fltr.search((thr.get("/I", {})).get("/Title", "")):
self._add_articles_thread(thr, pages, reader)
def _get_cloned_page(
self,
page: Union[IndirectObject, PageObject, NullObject, int, None],
pages: dict[int, PageObject],
reader: PdfReader,
) -> Optional[IndirectObject]:
if isinstance(page, NullObject):
return None
if isinstance(page, int):
# An explicit destination may reference the target page by its
# (zero-based) index in the source document rather than by an
# indirect reference; this is what `Link(target_page_index=...)`
# produces. Resolve the index through the reader's page list so it
# can be remapped like a regular page reference. A destination that
# points past the end of the source document is dropped.
try:
page = reader.pages[page].indirect_reference
except IndexError:
return None
if isinstance(page, DictionaryObject) and page.get("/Type", "") == "/Page":
_i = page.indirect_reference
elif isinstance(page, IndirectObject):
_i = page
try:
return pages[_i.idnum].indirect_reference # type: ignore[union-attr]
except Exception:
return None
def _insert_filtered_annotations(
self,
annots: Union[IndirectObject, list[PdfObject], None],
page: PageObject,
pages: dict[int, PageObject],
reader: PdfReader,
) -> list[Destination]:
outlist = ArrayObject()
if isinstance(annots, IndirectObject):
annots = cast("list[Any]", annots.get_object())
if annots is None:
return outlist
if not isinstance(annots, list):
logger_warning(
"Expected list of annotations, got %(annots)s of type %(annots_type)s.",
source=__name__,
annots=annots,
annots_type=annots.__class__.__name__,
)
return outlist
for an in annots:
ano = cast("DictionaryObject", an.get_object())
if (
ano["/Subtype"] != "/Link" # type: ignore[comparison-overlap]
or "/A" not in ano
or cast("DictionaryObject", ano["/A"])["/S"] != "/GoTo" # type: ignore[comparison-overlap]
or "/Dest" in ano
):
if "/Dest" not in ano:
outlist.append(self._add_object(ano.clone(self)))
else:
d = ano["/Dest"]
if isinstance(d, str):
# it is a named dest
if str(d) in self.get_named_dest_root():
outlist.append(ano.clone(self).indirect_reference)
else:
if not isinstance(d, ArrayObject) or not d:
continue
p = self._get_cloned_page(d[0], pages, reader)
if p is not None:
anc = ano.clone(self, ignore_fields=("/Dest",))
anc[NameObject("/Dest")] = ArrayObject([p, *d[1:]])
outlist.append(self._add_object(anc))
else:
d = cast("DictionaryObject", ano["/A"]).get("/D", NullObject())
if is_null_or_none(d):
continue
if isinstance(d, str):
# it is a named dest
if str(d) in self.get_named_dest_root():
outlist.append(ano.clone(self).indirect_reference)
else:
if not isinstance(d, ArrayObject) or not d:
continue
p = self._get_cloned_page(d[0], pages, reader)
if p is not None:
anc = ano.clone(self, ignore_fields=("/D",))
cast("DictionaryObject", anc["/A"])[
NameObject("/D")
] = ArrayObject([p, *d[1:]])
outlist.append(self._add_object(anc))
return outlist
def _get_filtered_outline(
self,
*,
node: Any,
pages: dict[int, PageObject],
reader: PdfReader,
visited: Optional[set[int]] = None,
) -> list[Destination]:
"""
Extract outline item entries that are part of the specified page set.
Returns:
A list of destination objects.
"""
if visited is None:
visited = set()
new_outline: list[Destination] = []
if node is None:
return new_outline
node = node.get_object()
if is_null_or_none(node):
node = DictionaryObject()
if node.get("/Type", "") == "/Outlines" or "/Title" not in node:
node_id = id(node)
if node_id in visited:
logger_warning("Detected cycle in outlines.", source=__name__)
return []
visited.add(node_id)
node = node.get("/First", None)
if node is not None:
node = node.get_object()
new_outline += self._get_filtered_outline(node=node, pages=pages, reader=reader, visited=visited)
else:
cloned_page: Union[IndirectObject, NullObject, None]
while True:
node = node.get_object()
node_id = id(node)
if node_id in visited:
logger_warning("Detected cycle in outlines.", source=__name__)
break
visited.add(node_id)
destination = cast("Destination", reader._build_outline_item(node))
cloned_page = self._get_cloned_page(cast("PageObject", destination["/Page"]), pages, reader)
if cloned_page is None:
cloned_page = NullObject()
destination[NameObject("/Page")] = cloned_page
if "/First" in node:
destination._filtered_children = self._get_filtered_outline(
node=node["/First"], pages=pages, reader=reader, visited=visited
)
else:
destination._filtered_children = []
if (
not isinstance(cloned_page, NullObject)
or len(destination._filtered_children) > 0
):
new_outline.append(destination)
if "/Next" not in node:
break
node = node["/Next"]
return new_outline
def _clone_outline(self, dest: Destination) -> TreeObject:
n_ol = TreeObject()
self._add_object(n_ol)
n_ol[NameObject("/Title")] = TextStringObject(dest["/Title"])
if not isinstance(dest["/Page"], NullObject):
if dest.node is not None and "/A" in dest.node:
n_ol[NameObject("/A")] = dest.node["/A"].clone(self)
else:
n_ol[NameObject("/Dest")] = dest.dest_array
# TODO: /SE
if dest.node is not None:
n_ol[NameObject("/F")] = NumberObject(dest.node.get("/F", 0))
color = dest.node.get("/C", NullObject()).get_object()
if not isinstance(color, list):
color = [FloatObject(0.0), FloatObject(0.0), FloatObject(0.0)]
n_ol[NameObject("/C")] = ArrayObject(color)
return n_ol
def _insert_filtered_outline(
self,
outlines: list[Destination],
parent: Union[TreeObject, IndirectObject],
before: Union[TreeObject, IndirectObject, None] = None,
) -> None:
for dest in outlines:
# TODO: can be improved to keep A and SE entries (ignored for the moment)
# with np=self.add_outline_item_destination(dest,parent,before)
if dest.get("/Type", "") == "/Outlines" or "/Title" not in dest:
np = parent
else:
np = self._clone_outline(dest)
cast(TreeObject, parent.get_object()).insert_child(np, before, self)
self._insert_filtered_outline(dest._filtered_children, np, None)
def close(self) -> None:
"""Implemented for API harmonization."""
return
def find_outline_item(
self,
outline_item: dict[str, Any],
root: Optional[OutlineType] = None,
) -> Optional[list[int]]:
if root is None:
o = self.get_outline_root()
else:
o = cast("TreeObject", root)
i = 0
while o is not None:
if (
o.indirect_reference == outline_item
or o.get("/Title", None) == outline_item
):
return [i]
if "/First" in o:
res = self.find_outline_item(
outline_item, cast(OutlineType, o["/First"])
)
if res:
return ([i] if "/Title" in o else []) + res
if "/Next" in o:
i += 1
o = cast(TreeObject, o["/Next"])
else:
return None
raise PyPdfError("This line is theoretically unreachable.") # pragma: no cover
def reset_translation(
self, reader: Union[PdfReader, IndirectObject, None] = None
) -> None:
"""
Reset the translation table between reader and the writer object.
Late cloning will create new independent objects.
Args:
reader: PdfReader or IndirectObject referencing a PdfReader object.
if set to None or omitted, all tables will be reset.
"""
if reader is None:
self._id_translated = {}
elif isinstance(reader, PdfReader):
try:
del self._id_translated[id(reader)]
except Exception:
pass
elif isinstance(reader, IndirectObject):
try:
del self._id_translated[id(reader.pdf)]
except Exception:
pass
else:
raise TypeError(f"Invalid parameter {reader}")
def set_page_label(
self,
page_index_from: int,
page_index_to: int,
style: Optional[PageLabelStyle] = None,
prefix: Optional[str] = None,
start: Optional[int] = 0,
) -> None:
"""
Set a page label to a range of pages.
Page indexes must be given starting from 0.
Labels must have a style, a prefix or both.
If a range is not assigned any page label, a decimal label starting from 1 is applied.
Args:
page_index_from: page index of the beginning of the range starting from 0
page_index_to: page index of the beginning of the range starting from 0
style: The numbering style to be used for the numeric portion of each page label:
* ``/D`` Decimal Arabic numerals
* ``/R`` Uppercase Roman numerals
* ``/r`` Lowercase Roman numerals
* ``/A`` Uppercase letters (A to Z for the first 26 pages,
AA to ZZ for the next 26, and so on)
* ``/a`` Lowercase letters (a to z for the first 26 pages,
aa to zz for the next 26, and so on)
prefix: The label prefix for page labels in this range.
start: The value of the numeric portion for the first page label
in the range.
Subsequent pages are numbered sequentially from this value,
which must be greater than or equal to 1.
Default value: 1.
"""
if style is None and prefix is None:
raise ValueError("At least one of style and prefix must be given")
if page_index_from < 0:
raise ValueError("page_index_from must be greater or equal than 0")
if page_index_to < page_index_from:
raise ValueError(
"page_index_to must be greater or equal than page_index_from"
)
if page_index_to >= len(self.pages):
raise ValueError("page_index_to exceeds number of pages")
if start is not None and start != 0 and start < 1:
raise ValueError("If given, start must be greater or equal than one")
self._set_page_label(page_index_from, page_index_to, style, prefix, start)
def _set_page_label(
self,
page_index_from: int,
page_index_to: int,
style: Optional[PageLabelStyle] = None,
prefix: Optional[str] = None,
start: Optional[int] = 0,
) -> None:
"""
Set a page label to a range of pages.
Page indexes must be given starting from 0.
Labels must have a style, a prefix or both.
If a range is not assigned any page label a decimal label starting from 1 is applied.
Args:
page_index_from: page index of the beginning of the range starting from 0
page_index_to: page index of the beginning of the range starting from 0
style: The numbering style to be used for the numeric portion of each page label:
/D Decimal Arabic numerals
/R Uppercase Roman numerals
/r Lowercase Roman numerals
/A Uppercase letters (A to Z for the first 26 pages,
AA to ZZ for the next 26, and so on)
/a Lowercase letters (a to z for the first 26 pages,
aa to zz for the next 26, and so on)
prefix: The label prefix for page labels in this range.
start: The value of the numeric portion for the first page label
in the range.
Subsequent pages are numbered sequentially from this value,
which must be greater than or equal to 1. Default value: 1.
"""
default_page_label = DictionaryObject()
default_page_label[NameObject("/S")] = NameObject("/D")
new_page_label = DictionaryObject()
if style is not None:
new_page_label[NameObject("/S")] = NameObject(style)
if prefix is not None:
new_page_label[NameObject("/P")] = TextStringObject(prefix)
if start != 0:
new_page_label[NameObject("/St")] = NumberObject(start)
if NameObject(CatalogAttributes.PAGE_LABELS) not in self._root_object:
nums = ArrayObject()
nums_insert(NumberObject(0), default_page_label, nums)
page_labels = TreeObject()
page_labels[NameObject("/Nums")] = nums
self._root_object[NameObject(CatalogAttributes.PAGE_LABELS)] = page_labels
page_labels = cast(
TreeObject, self._root_object[NameObject(CatalogAttributes.PAGE_LABELS)]
)
nums = cast(ArrayObject, page_labels[NameObject("/Nums")])
nums_insert(NumberObject(page_index_from), new_page_label, nums)
nums_clear_range(NumberObject(page_index_from), page_index_to, nums)
next_label_pos, *_ = nums_next(NumberObject(page_index_from), nums)
if next_label_pos != page_index_to + 1 and page_index_to + 1 < len(self.pages):
nums_insert(NumberObject(page_index_to + 1), default_page_label, nums)
page_labels[NameObject("/Nums")] = nums
self._root_object[NameObject(CatalogAttributes.PAGE_LABELS)] = page_labels
def _repr_mimebundle_(
self,
include: Union[Iterable[str], None] = None,
exclude: Union[Iterable[str], None] = None,
) -> dict[str, Any]:
"""
Integration into Jupyter Notebooks.
This method returns a dictionary that maps a mime-type to its
representation.
.. seealso::
https://ipython.readthedocs.io/en/stable/config/integrating.html
"""
pdf_data = BytesIO()
self.write(pdf_data)
data = {
"application/pdf": pdf_data,
}
if include is not None:
# Filter representations based on include list
data = {k: v for k, v in data.items() if k in include}
if exclude is not None:
# Remove representations based on exclude list
data = {k: v for k, v in data.items() if k not in exclude}
return data
def _pdf_objectify(obj: Union[dict[str, Any], str, float, list[Any]]) -> PdfObject:
if isinstance(obj, PdfObject):
return obj
if isinstance(obj, dict):
to_add = DictionaryObject()
for key, value in obj.items():
to_add[NameObject(key)] = _pdf_objectify(value)
return to_add
if isinstance(obj, str):
if obj.startswith("/"):
return NameObject(obj)
return TextStringObject(obj)
if isinstance(obj, (float, int)):
return FloatObject(obj)
if isinstance(obj, list):
return ArrayObject(_pdf_objectify(i) for i in obj)
raise NotImplementedError(
f"{type(obj)=} could not be cast to a PdfObject"
)
def _create_outline_item(
action_ref: Union[IndirectObject, None],
title: str,
color: Union[tuple[float, float, float], str, None],
italic: bool,
bold: bool,
) -> TreeObject:
outline_item = TreeObject()
if action_ref is not None:
outline_item[NameObject("/A")] = action_ref
outline_item.update(
{
NameObject("/Title"): create_string_object(title),
}
)
if color:
if isinstance(color, str):
color = hex_to_rgb(color)
outline_item.update(
{NameObject("/C"): ArrayObject([FloatObject(c) for c in color])}
)
if italic or bold:
format_flag = 0
if italic:
format_flag += OutlineFontFlag.italic
if bold:
format_flag += OutlineFontFlag.bold
outline_item.update({NameObject("/F"): NumberObject(format_flag)})
return outline_item
|