/usr/share/ada/adainclude/gnatcoll/gnatcoll-email-utils.adb is in libgnatcoll16.1.0-dev 17.0.2017-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | ------------------------------------------------------------------------------
-- G N A T C O L L --
-- --
-- Copyright (C) 2006-2017, AdaCore --
-- --
-- This library is free software; you can redistribute it and/or modify it --
-- under terms of the GNU General Public License as published by the Free --
-- Software Foundation; either version 3, or (at your option) any later --
-- version. This library is distributed in the hope that it will be useful, --
-- but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHAN- --
-- TABILITY or FITNESS FOR A PARTICULAR PURPOSE. --
-- --
-- --
-- --
-- --
-- --
-- You should have received a copy of the GNU General Public License and --
-- a copy of the GCC Runtime Library Exception along with this program; --
-- see the files COPYING3 and COPYING.RUNTIME respectively. If not, see --
-- <http://www.gnu.org/licenses/>. --
-- --
------------------------------------------------------------------------------
pragma Ada_2012;
with Ada.Calendar; use Ada.Calendar;
with Ada.Calendar.Time_Zones; use Ada.Calendar.Time_Zones;
with Ada.Calendar.Formatting; use Ada.Calendar.Formatting;
with Ada.Characters.Handling; use Ada.Characters.Handling;
with Ada.Strings.Hash_Case_Insensitive;
with GNATCOLL.Utils; use GNATCOLL.Utils;
with Interfaces; use Interfaces;
with System.WCh_Con; use System.WCh_Con;
with GNAT.Decode_String;
pragma Warnings (Off);
-- Ada.Strings.Unbounded.Aux is an internal GNAT unit
with Ada.Strings.Unbounded.Aux;
pragma Warnings (On);
package body GNATCOLL.Email.Utils is
U_Charset_US_ASCII : constant Unbounded_String :=
To_Unbounded_String (Charset_US_ASCII);
package Decode_Shift_JIS is new GNAT.Decode_String (WCEM_Shift_JIS);
package Decode_EUC is new GNAT.Decode_String (WCEM_EUC);
package Decode_UTF8 is new GNAT.Decode_String (WCEM_UTF8);
type Next_Char_Acc is
access procedure (S : String; Index : in out Natural);
-- Procedure moving Index from one character to the next in S,
-- taking multi-byte encodings into account.
procedure Single_Byte_Next_Char (S : String; Index : in out Natural);
-- Default version for single-byte charsets, simply incrementing Index
---------------------------
-- Single_Byte_Next_Char --
---------------------------
procedure Single_Byte_Next_Char (S : String; Index : in out Natural) is
pragma Unreferenced (S);
begin
Index := Index + 1;
end Single_Byte_Next_Char;
function Next_Char_For_Charset (Charset : String) return Next_Char_Acc is
(if Charset = Charset_Shift_JIS
then Decode_Shift_JIS.Next_Wide_Character'Access
elsif Charset = Charset_EUC
then Decode_EUC.Next_Wide_Character'Access
elsif Charset = Charset_UTF_8
then Decode_UTF8.Next_Wide_Character'Access
else
Single_Byte_Next_Char'Access);
-- Next_Char procedure for the named Charset
procedure Next_Char_Ignore_Invalid
(NC : Next_Char_Acc;
S : String;
Index : in out Natural);
pragma Inline (Next_Char_Ignore_Invalid);
-- Call NC (S, Index), but if an exception is raised (e.g. due to
-- an invalid encoding in S, fall back to incrementing Index by 1.
------------------------------
-- Next_Char_Ignore_Invalid --
------------------------------
procedure Next_Char_Ignore_Invalid
(NC : Next_Char_Acc;
S : String;
Index : in out Natural)
is
Orig_Index : constant Natural := Index;
begin
NC (S, Index);
exception
when others =>
Index := Orig_Index + 1;
end Next_Char_Ignore_Invalid;
function Needs_Quoting
(Char : Character;
Where : Region;
Is_EOL : Boolean) return Boolean;
-- Return True if C needs to be quoted when appearing in Region, False
-- otherwise. Is_EOL indicates whether Char is last of its line.
function Needs_Quoting
(U : Unbounded_String;
Where : Region;
Is_EOL : Boolean) return Boolean;
-- True if any non-whitespace character in U needs to be quoted per
-- the above function. Is_EOL indicates whehter the last character of U is
-- last of its line.
procedure Read_Integer
(S : String; Index : in out Integer; Value : out Integer);
-- return the integer starting at Index, and moves Index after the integer
procedure Skip_Comment (S : String; Index : in out Integer);
-- Skip the comment, if any, that starts at Index.
-- In RFC 2822, comments are between parenthesis, and can be nested
procedure Skip_Quoted_String (S : String; Index : in out Integer);
-- Skip a quoted string, taking properly into account the backslashes
-- Index should point after the opening quote.
procedure Parse_And_Skip_Address
(From_C : in out Charset_String_List.Cursor;
From : in out Integer;
Address : out Email_Address);
-- Parse the first email address at (From_C, From), and leaves them after
-- it, so that if there are more addresses in From_C they can all be parsed
-- easily.
procedure Parse_And_Skip_Address
(Str : String;
From : in out Integer;
Buffer : in out Unbounded_String;
Buffer_Has_At : in out Boolean;
In_Quote : in out Boolean;
Comment : in out Unbounded_String;
Address : in out Email_Address;
Found : out Boolean);
-- Internal version of Parse_And_Skip_Address, which applies to a
-- us-ascii string. It maintains internal data.
-- In_Quote indicates whether we are initially within an open quote ("),
-- and on exit whether we are still processing a quoted string.
procedure Post_Process_Address
(Address : in out Email_Address;
Buffer, Comment : Unbounded_String;
Buffer_Has_At : Boolean);
-- Complete the data in Address, given Buffer and Comment that were
-- generated by Parse_And_Skip_Address. This procedure should be called
-- after Parse_And_Skip_Address, before returning an address to the user.
Special_Chars : constant array (Character) of Boolean :=
('[' | ']' | '\' | '(' | ')' | '<' | '>' | '@' | ',' => True,
':' | ';' | '"' | '.' => True,
others => False);
Quoted_Chars : constant array (Character) of Boolean :=
('[' | ']' | '\' | '(' | ')' | '"' => True,
others => False);
Qp_Convert : constant array (Character) of Short_Integer :=
('0' => 0, '1' => 1, '2' => 2, '3' => 3, '4' => 4,
'5' => 5, '6' => 6, '7' => 7, '8' => 8, '9' => 9,
'A' => 10, 'B' => 11, 'C' => 12, 'D' => 13, 'E' => 14, 'F' => 15,
'a' => 10, 'b' => 11, 'c' => 12, 'd' => 13, 'e' => 14, 'f' => 15,
others => -1);
type Byte is mod 256;
Base64_Convert : constant array (Character) of Byte :=
('+' => 62, '/' => 63, '0' => 52, '1' => 53, '2' => 54, '3' => 55,
'4' => 56, '5' => 57, '6' => 58, '7' => 59, '8' => 60, '9' => 61,
'A' => 0, 'B' => 1, 'C' => 2, 'D' => 3, 'E' => 4, 'F' => 5,
'G' => 6, 'H' => 7, 'I' => 8, 'J' => 9, 'K' => 10, 'L' => 11,
'M' => 12, 'N' => 13, 'O' => 14, 'P' => 15, 'Q' => 16, 'R' => 17,
'S' => 18, 'T' => 19, 'U' => 20, 'V' => 21, 'W' => 22, 'X' => 23,
'Y' => 24, 'Z' => 25, 'a' => 26, 'b' => 27, 'c' => 28, 'd' => 29,
'e' => 30, 'f' => 31, 'g' => 32, 'h' => 33, 'i' => 34, 'j' => 35,
'k' => 36, 'l' => 37, 'm' => 38, 'n' => 39, 'o' => 40, 'p' => 41,
'q' => 42, 'r' => 43, 's' => 44, 't' => 45, 'u' => 46, 'v' => 47,
'w' => 48, 'x' => 49, 'y' => 50, 'z' => 51, others => -1);
type Mod64 is mod 2 ** 6;
To_Base64 : constant array (Mod64) of Character :=
(00 => 'A', 1 => 'B', 2 => 'C', 3 => 'D', 4 => 'E', 5 => 'F',
6 => 'G', 7 => 'H', 8 => 'I', 9 => 'J', 10 => 'K', 11 => 'L',
12 => 'M', 13 => 'N', 14 => 'O', 15 => 'P', 16 => 'Q', 17 => 'R',
18 => 'S', 19 => 'T', 20 => 'U', 21 => 'V', 22 => 'W', 23 => 'X',
24 => 'Y', 25 => 'Z', 26 => 'a', 27 => 'b', 28 => 'c', 29 => 'd',
30 => 'e', 31 => 'f', 32 => 'g', 33 => 'h', 34 => 'i', 35 => 'j',
36 => 'k', 37 => 'l', 38 => 'm', 39 => 'n', 40 => 'o', 41 => 'p',
42 => 'q', 43 => 'r', 44 => 's', 45 => 't', 46 => 'u', 47 => 'v',
48 => 'w', 49 => 'x', 50 => 'y', 51 => 'z', 52 => '0', 53 => '1',
54 => '2', 55 => '3', 56 => '4', 57 => '5', 58 => '6', 59 => '7',
60 => '8', 61 => '9', 62 => '+', 63 => '/');
Hex_Chars : constant array (0 .. 15) of Character := "0123456789ABCDEF";
------------------------
-- Skip_Quoted_String --
------------------------
procedure Skip_Quoted_String (S : String; Index : in out Integer) is
begin
while Index <= S'Last loop
if S (Index) = '"' then
Index := Index + 1;
return;
elsif S (Index) = '\' then
Index := Index + 2;
else
Index := Index + 1;
end if;
end loop;
-- There is no closing '"'
Index := S'Last + 1;
end Skip_Quoted_String;
------------------
-- Skip_Comment --
------------------
procedure Skip_Comment (S : String; Index : in out Integer) is
Par : Natural := 1;
begin
if S (Index) = '(' then
Index := Index + 1;
while Index <= S'Last loop
if S (Index) = ')' then
Par := Par - 1;
if Par = 0 then
Index := Index + 1;
return;
else
Index := Index + 1;
end if;
elsif S (Index) = '(' then
Par := Par + 1;
Index := Index + 1;
elsif S (Index) = '\' then
Index := Index + 2;
else
Index := Index + 1;
end if;
end loop;
-- No closing ')'
Index := S'Last + 1;
end if;
end Skip_Comment;
------------------
-- Read_Integer --
------------------
procedure Read_Integer
(S : String; Index : in out Integer; Value : out Integer)
is
Start : constant Integer := Index;
begin
if S (Index) = '-' or else S (Index) = '+' then
Index := Index + 1;
end if;
while Index <= S'Last
and then S (Index) in '0' .. '9'
loop
Index := Index + 1;
end loop;
Value := Integer'Value (S (Start .. Index - 1));
end Read_Integer;
-------------
-- To_Time --
-------------
function To_Time
(Date : String;
Format : Time_Format := Time_RFC2822) return Ada.Calendar.Time
is
Index : Integer := Date'First;
Index2 : Integer;
Year : Year_Number := Year_Number'First;
Month : Month_Number := Month_Number'First;
Day : Day_Number := Day_Number'First;
Seconds : Day_Duration := 0.0;
TZ : Time_Offset := 0;
Time_Error : exception;
procedure Read_Day;
procedure Read_Month;
procedure Read_Year;
procedure Read_Time;
-- Read the day of month or the year
procedure Read_Time_Zone;
procedure Read_Day is
begin
Read_Integer (Date (Index .. Date'Last), Index, Value => Index2);
Day := Day_Number (Index2);
Skip_Whitespaces (Date (Index .. Date'Last), Index);
end Read_Day;
procedure Read_Month is
pragma Warnings (Off);
type Month_Name is
(Jan, Feb, Mar, Apr, May, Jun, Jul, Aug, Sep, Oct, Nov, Dec);
pragma Warnings (On);
begin
Month :=
Month_Name'Pos (Month_Name'Value (Date (Index .. Index + 2))) + 1;
-- Some mailers print the month in full, not just the first three
-- chars. Although this isn't part of the RFC 2822, we still want to
-- handle these
Index := Index + 3;
while Index <= Date'Last
and then not Is_Whitespace (Date (Index))
loop
Index := Index + 1;
end loop;
Skip_Whitespaces (Date (Index .. Date'Last), Index);
exception
when others =>
-- This really means the date format is incorrect!
null;
end Read_Month;
procedure Read_Year is
begin
Read_Integer (Date (Index .. Date'Last), Index, Value => Index2);
if Index2 < 0 then
raise Time_Error;
elsif Index2 <= 49 then
Year := Year_Number (2000 + Index2);
elsif Index2 <= 99 then
Year := Year_Number (1900 + Index2);
else
Year := Year_Number (Index2);
end if;
Skip_Whitespaces (Date (Index .. Date'Last), Index);
end Read_Year;
procedure Read_Time is
begin
Read_Integer (Date (Index .. Date'Last), Index, Value => Index2);
Seconds := Seconds + Day_Duration (Index2) * 3600.0;
if Date (Index) /= ':' then
raise Time_Error;
end if;
Index := Index + 1;
Read_Integer (Date (Index .. Date'Last), Index, Value => Index2);
Seconds := Seconds + Day_Duration (Index2) * 60.0;
if Date (Index) = ':' then
Index := Index + 1;
Read_Integer (Date (Index .. Date'Last), Index, Value => Index2);
Seconds := Seconds + Day_Duration (Index2);
end if;
Skip_Whitespaces (Date (Index .. Date'Last), Index);
end Read_Time;
procedure Read_Time_Zone is
TZ_Local : Integer;
type Named_TZ is (AST, ADT, EST, EDT, CST, CDT, MST, MDT, PST, PDT);
Named_TZ_Offset : constant array (Named_TZ) of Time_Offset :=
(AST => -240,
ADT => -180,
EST => -300,
EDT => -240,
CST => -360,
CDT => -300,
MST => -420,
MDT => -360,
PST => -480,
PDT => -420);
begin
-- Timezone (we might have none in badly formed dates)
if Index < Date'Last then
if Date (Index) = '-' or else Date (Index) = '+' or else
Date (Index) in '0' .. '9'
then
Read_Integer (Date (Index .. Date'Last), Index,
Value => TZ_Local);
TZ := Time_Offset ((TZ_Local / 100) * 60 + TZ_Local mod 100);
else
-- The timezone table does not include the military time zones
-- defined in RFC822, other than Z. According to RFC1123, the
-- description in RFC822 gets the signs wrong, so we can't rely
-- on any such time zones. RFC1123 recommends that numeric
-- timezone indicators be used instead of timezone names.
if Date (Index .. Index + 1) = "UT"
or else Date (Index .. Index + 2) = "UTC"
or else Date (Index) = 'Z'
then
TZ := 0;
else
TZ := Named_TZ_Offset
(Named_TZ'Value (Date (Index .. Index + 2)));
end if;
end if;
end if;
exception
when Constraint_Error =>
-- Invalid time zone, just ignore
null;
end Read_Time_Zone;
begin
-- RFC 2822 format is
-- [day-of-week] ","] day month-name year FWS time-of-day FWS tz
-- year := 4 * DIGIT | 2 * DIGIT
-- day := 1*2DIGIT
-- time-of-day := hour ":" minute [":" second]
-- tz := (("+" | "-") 4DIGIT) | "UT" | "GMT" | ...
--
-- Envelope format is
-- Tue Jan 24 14:48:49 2006 +0100
Skip_Whitespaces (Date (Index .. Date'Last), Index);
-- Day of week is optional, skip it
case Format is
when Time_RFC2822 =>
Index2 := Next_Occurrence (Date (Index .. Date'Last), ',');
if Index2 <= Date'Last then
Index := Index2 + 1;
Skip_Whitespaces (Date (Index .. Date'Last), Index);
end if;
Read_Day;
Read_Month;
Read_Year;
Read_Time;
when Time_Envelope =>
Index := Index + 3;
Skip_Whitespaces (Date (Index .. Date'Last), Index);
Read_Month;
Read_Day;
Read_Time;
Read_Year;
end case;
Read_Time_Zone;
return Time_Of (Year, Month, Day, Seconds, Time_Zone => TZ);
exception
when Time_Error =>
return No_Time;
when Constraint_Error =>
return No_Time;
end To_Time;
-----------------
-- Format_Time --
-----------------
function Format_Time (Date : Ada.Calendar.Time) return String
is
Result : Unbounded_String;
Y : Year_Number;
M : Month_Number;
D : Day_Number;
H : Hour_Number;
Min : Minute_Number;
S : Second_Number;
SS : Second_Duration;
begin
Split
(Date, Y, M, D, H, Min, S, SS, Time_Zone => 0);
Result := To_Unbounded_String
(Image (Integer (H), Min_Width => 2) & ":");
Append (Result, Image (Integer (Min), Min_Width => 2) & ":");
Append (Result, Image (Integer (S), Min_Width => 2));
return To_String (Result);
end Format_Time;
-----------------
-- Format_Date --
-----------------
Day_Names : constant array (Day_Name) of String (1 .. 3) :=
(Monday => "Mon",
Tuesday => "Tue",
Wednesday => "Wed",
Thursday => "Thu",
Friday => "Fri",
Saturday => "Sat",
Sunday => "Sun");
Month_Names : constant array (1 .. 12) of String (1 .. 3) :=
(1 => "Jan", 2 => "Feb", 3 => "Mar",
4 => "Apr", 5 => "May", 6 => "Jun",
7 => "Jul", 8 => "Aug", 9 => "Sep",
10 => "Oct", 11 => "Nov", 12 => "Dec");
function Format_Date
(Date : Ada.Calendar.Time;
Use_GMT : Boolean := False;
From_Line : Boolean := False;
No_TZ : Boolean := False;
Show_Time : Boolean := True;
Show_Seconds : Boolean := True;
Show_Day : Boolean := True) return String
is
Result : Unbounded_String;
Y : Year_Number;
M : Month_Number;
D : Day_Number;
H : Hour_Number;
Min : Minute_Number;
S : Second_Number;
SS : Second_Duration;
TZ : Time_Offset := 0;
RFC_TZ : Integer;
Unknown_TZ : Boolean := False;
begin
if not (Use_GMT or else No_TZ) then
begin
-- Number of minutes difference for the timezone
TZ := UTC_Time_Offset (Date);
exception
when Unknown_Zone_Error =>
Unknown_TZ := True;
end;
end if;
-- We cannot use GNAT.Calendar.Time_IO for week days, since we always
-- want the english names, not the locale's version.
Split (Date, Y, M, D, H, Min, S, SS, Time_Zone => TZ);
if Show_Day then
-- Note: we can't just call Day_Of_Week (Date), since this gives the
-- day of week for Date *in the local time zone*, and in No_TZ or
-- Use_GMT mode we want the day of week for Date
-- *in the UT time zone*. So, we conjure up another date whose year,
-- month, and day number in month (and therefore day of week) in
-- local time are the same as those of Date in GMT (namely, Y, M,
-- and D).
Result :=
To_Unbounded_String
(Day_Names (Day_Of_Week (Ada.Calendar.Time_Of (Y, M, D))));
if From_Line then
Append (Result, " ");
else
Append (Result, ", ");
end if;
end if;
if not From_Line then
Append (Result, Image (Integer (D), Min_Width => 2) & " ");
end if;
Append (Result, Month_Names (M) & ' ');
if From_Line then
Append (Result, Image (Integer (D), Min_Width => 2) & " ");
else
Append (Result, Image (Integer (Y), Min_Width => 2) & " ");
end if;
if Show_Time then
Append (Result, Image (Integer (H), Min_Width => 2) & ":");
Append (Result, Image (Integer (Min), Min_Width => 2));
if Show_Seconds then
Append (Result, ":" & Image (Integer (S), Min_Width => 2));
end if;
end if;
if From_Line then
Append (Result, " " & Image (Integer (Y), Min_Width => 2));
end if;
if not No_TZ then
if Use_GMT then
Append (Result, " GMT");
elsif Unknown_TZ then
Append (Result, " -0000");
else
RFC_TZ := Integer ((TZ / 60) * 100 + TZ mod 60);
Append (Result, " " & Image (RFC_TZ, Min_Width => 4,
Force_Sign => True));
end if;
end if;
return To_String (Result);
end Format_Date;
-------------------
-- Parse_Address --
-------------------
function Parse_Address (Email : String) return Email_Address is
Index : Integer := Email'First;
Result : Email_Address;
Buffer : Unbounded_String;
Buffer_Has_At : Boolean := False;
Comment : Unbounded_String;
Found : Boolean;
In_Quote : Boolean := False;
begin
Parse_And_Skip_Address
(Str => Email,
From => Index,
Buffer => Buffer,
Buffer_Has_At => Buffer_Has_At,
In_Quote => In_Quote,
Comment => Comment,
Address => Result,
Found => Found);
Post_Process_Address
(Address => Result,
Buffer => Buffer,
Comment => Comment,
Buffer_Has_At => Buffer_Has_At);
return Result;
end Parse_Address;
----------------------------
-- Parse_And_Skip_Address --
----------------------------
procedure Parse_And_Skip_Address
(Str : String;
From : in out Integer;
Buffer : in out Unbounded_String;
Buffer_Has_At : in out Boolean;
In_Quote : in out Boolean;
Comment : in out Unbounded_String;
Address : in out Email_Address;
Found : out Boolean)
is
Index : Integer;
begin
if In_Quote then
Index := From;
Skip_Quoted_String (Str (Index .. Str'Last), Index);
Address.Real_Name := Trim
(To_Unbounded_String
(Str (From + 1 .. Index - 2)), Ada.Strings.Both);
From := Index + 1;
In_Quote := False;
end if;
-- Skip spaces
while From <= Str'Last
and then (Str (From) = ASCII.LF
or else Str (From) = ASCII.CR
or else Str (From) = ASCII.HT
or else Str (From) = ' ')
loop
From := From + 1;
end loop;
-- Only parse the contents of us-ascii strings. The rest cannot
-- contain email addresses nor comments anyway.
while From <= Str'Last loop
if From <= Str'Last then
if Str (From) = '(' then
-- A comment. Ignored in general, but if we do not have a
-- real name, it is likely to be contained in this
-- comment, which is what some old mailers used to do:
-- report@gnat.com (Report)
Index := From;
Skip_Comment (Str (From .. Str'Last), Index);
Append (Comment, Str (From + 1 .. Index - 2));
From := Index;
elsif Str (From) = '<' then
-- The email address
Index := From;
while Index <= Str'Last
and then Str (Index) /= '>'
loop
Index := Index + 1;
end loop;
Address.Address := To_Unbounded_String
(Str (From + 1 .. Index - 1));
From := Index + 1;
-- ',' is the standard separator in mail messages, but ';' is
-- often used by users when manually typing a list of addresses
elsif Str (From) = ','
or else Str (From) = ';'
or else Str (From) = ASCII.LF
or else Str (From) = ASCII.CR
or else Str (From) = ASCII.HT
or else (Buffer_Has_At and then Str (From) = ' ')
then
-- End of current address
From := From + 1;
Found := True;
return;
elsif Str (From) = '"' then
Index := From + 1;
Skip_Quoted_String (Str (Index .. Str'Last), Index);
if Index > Str'Last then
In_Quote := True;
end if;
Address.Real_Name := Trim
(To_Unbounded_String
(Str (From + 1 .. Index - 2)), Ada.Strings.Both);
if Index <= Str'Last and then Str (Index) = ' ' then
From := Index + 1;
else
From := Index;
end if;
else
if Str (From) = '@' then
Buffer_Has_At := True;
end if;
Append (Buffer, Str (From));
From := From + 1;
end if;
end if;
end loop;
Found := False;
end Parse_And_Skip_Address;
----------------------------
-- Parse_And_Skip_Address --
----------------------------
procedure Parse_And_Skip_Address
(From_C : in out Charset_String_List.Cursor;
From : in out Integer;
Address : out Email_Address)
is
use Charset_String_List;
Buffer : Unbounded_String;
Comment : Unbounded_String;
Buffer_Has_At : Boolean := False;
In_Quote : Boolean := False;
-- Quotes are not necessarily encoded, and we could have for instance:
-- " =?iso-2022-jp?b?...?= " <foo@nowhere.jp>
-- which is made of several strings: one for the opening quote, one for
-- the encoded name, and a last one that includes the quote and the
-- email address.
Continue : Boolean;
procedure Analyze (CS : Charset_String);
-- Analyze a given element of the list. Done in nested procedure to
-- avoid a copy of each element of Email
procedure Analyze (CS : Charset_String) is
Tmp : Unbounded_String;
Found : Boolean := False;
begin
-- Only parse the contents of us-ascii strings. The rest cannot
-- contain email addresses nor comments anyway
if CS.Charset = Charset_US_ASCII then
Parse_And_Skip_Address
(Str => To_String (CS.Contents),
From => From,
Buffer => Buffer,
Buffer_Has_At => Buffer_Has_At,
In_Quote => In_Quote,
Comment => Comment,
Address => Address,
Found => Found);
else
-- Reencode, to preserve names in international charsets
Encode (Str => To_String (CS.Contents),
Charset => To_String (CS.Charset),
Where => Addr_Header,
Result => Tmp);
Append (Buffer, Tmp);
end if;
Continue := not Found;
end Analyze;
-- Start of processing for Parse_And_Skip_Address
begin
Address := Null_Address;
while Has_Element (From_C) loop
Query_Element (From_C, Analyze'Unrestricted_Access);
exit when not Continue;
Next (From_C);
From := 1;
end loop;
Post_Process_Address (Address, Buffer, Comment, Buffer_Has_At);
end Parse_And_Skip_Address;
--------------------------
-- Post_Process_Address --
--------------------------
procedure Post_Process_Address
(Address : in out Email_Address;
Buffer, Comment : Unbounded_String;
Buffer_Has_At : Boolean)
is
pragma Unreferenced (Buffer_Has_At);
begin
if Address.Address = Null_Unbounded_String then
-- Ideally, we should test whether Buffer contains a @ string. But
-- there are degenerate cases where we have an email address on its
-- own with no @ sign, and we want to handle them for backward
-- compatibility...
Address.Address := Trim (Buffer, Ada.Strings.Both);
else
if Address.Real_Name = Null_Unbounded_String then
if Buffer = Null_Unbounded_String then
Address.Real_Name := Trim (Comment, Ada.Strings.Both);
else
Address.Real_Name := Trim (Buffer, Ada.Strings.Both);
end if;
end if;
end if;
end Post_Process_Address;
----------------
-- To_Address --
----------------
function To_Address
(Address : String;
Real_Name : String := "") return Email_Address
is
begin
return (Address => To_Unbounded_String (Address),
Real_Name => To_Unbounded_String (Real_Name));
end To_Address;
-------------------
-- Get_Addresses --
-------------------
function Get_Addresses (Str : String) return Address_Set.Set is
use Charset_String_List;
L : Charset_String_List.List;
begin
Append (L, (Contents => To_Unbounded_String (Str),
Charset => To_Unbounded_String (Charset_US_ASCII)));
return Get_Addresses (L);
end Get_Addresses;
function Get_Addresses
(Str : Charset_String_List.List) return Address_Set.Set
is
use Charset_String_List, Address_Set;
C : Charset_String_List.Cursor := First (Str);
From : Integer := 1;
Result : Address_Set.Set;
Addr : Email_Address;
begin
while Has_Element (C) loop
Parse_And_Skip_Address (C, From, Addr);
if Addr /= Null_Address then
Include (Result, Addr);
end if;
end loop;
return Result;
end Get_Addresses;
---------------
-- To_String --
---------------
function To_String
(Addresses : Address_Set.Set;
Separator : String := ", ";
Address_Only : Boolean := False) return String
is
use Address_Set;
Tmp : Unbounded_String;
C : Address_Set.Cursor := First (Addresses);
begin
while Has_Element (C) loop
if Tmp /= Null_Unbounded_String then
Append (Tmp, Separator);
end if;
if Address_Only then
Append (Tmp, Element (C).Address);
else
Append (Tmp, Format_Address (Element (C)));
end if;
Next (C);
end loop;
return To_String (Tmp);
end To_String;
--------------------
-- Format_Address --
--------------------
function Format_Address
(Email : Email_Address;
Charset : String := Charset_US_ASCII) return Charset_String_List.List
is
L : Charset_String_List.List;
begin
-- If Charset is US-ASCII, we can't rely on RFC 2047 encoding to
-- protect any special characters, so fall back to legacy formatting
-- routine, which will do backslash-escaping as needed. If nothing
-- needs quoting, don't bother to go trough RFC 2047 either.
if Charset = Charset_US_ASCII
or else not Needs_Quoting
(Email.Real_Name,
Is_EOL => False, Where => Addr_Header)
then
L.Append ((Contents =>
To_Unbounded_String
(Legacy_Format_Address
(Real => To_String (Email.Real_Name),
Address => To_String (Email.Address))),
Charset => U_Charset_US_ASCII));
-- Case where we have a non-ASCII charset specified
else
-- Here we have a non-default Charset specified: RFC 2047 encoding
-- will also take care of escaping special characters.
L.Append ((Contents => Email.Real_Name,
Charset => To_Unbounded_String (Charset)));
-- Actual address must not be encoded in any way: add a separate
-- US ASCII section.
L.Append (Charset_String'
(Contents => " <" & Email.Address & ">",
Charset => U_Charset_US_ASCII));
end if;
return L;
end Format_Address;
--------------------
-- Format_Address --
--------------------
function Format_Address
(Email : Email_Address;
Charset : String := Charset_US_ASCII) return Unbounded_String
is
Res : Unbounded_String;
begin
To_String (Format_Address (Email, Charset), Res);
return Res;
end Format_Address;
---------------------------
-- Legacy_Format_Address --
---------------------------
function Legacy_Format_Address
(Real : String;
Address : String) return String
is
Has_Special : Boolean := False;
-- True if Real contains any special character that needs to be
-- escaped in an RFC 2822 address header.
begin
if Real = "" then
return Address;
else
for C in Real'Range loop
if Special_Chars (Real (C)) then
Has_Special := True;
exit;
end if;
end loop;
if Has_Special then
return '"' & Quote (Real) & """ <" & Address & '>';
else
return Quote (Real) & " <" & Address & '>';
end if;
end if;
end Legacy_Format_Address;
-----------
-- Quote --
-----------
function Quote (Str : String) return String is
Result : String (Str'First .. Str'Last * 2);
Index : Integer := Result'First;
begin
for C in Str'Range loop
if Quoted_Chars (Str (C)) then
Result (Index) := '\';
Index := Index + 1;
end if;
Result (Index) := Str (C);
Index := Index + 1;
end loop;
return Result (Result'First .. Index - 1);
end Quote;
-------------
-- Unquote --
-------------
function Unquote (Str : String) return String is
Result : String (Str'Range);
Index : Integer := Result'First;
C : Integer := Str'First;
begin
while C <= Str'Last loop
if Str (C) = '\' and then C < Str'Last then
Result (Index) := Str (C + 1);
C := C + 1;
else
Result (Index) := Str (C);
end if;
C := C + 1;
Index := Index + 1;
end loop;
return Result (Result'First .. Index - 1);
end Unquote;
----------
-- Hash --
----------
function Hash (Addr : Email_Address) return Ada.Containers.Hash_Type is
begin
return Ada.Strings.Hash_Case_Insensitive (To_String (Addr.Address));
end Hash;
--------------------
-- Get_Recipients --
--------------------
function Get_Recipients
(Msg : Message'Class;
Include_From : Boolean := False) return Address_Set.Set
is
use Address_Set;
Iter : Header_Iterator := Get_Headers (Msg);
H : Header;
Result : Address_Set.Set;
begin
loop
Next (Iter, H => H);
exit when H = Null_Header;
if Get_Name (H) = "to"
or else Get_Name (H) = "cc"
or else Get_Name (H) = "resent-to"
or else Get_Name (H) = "resent-cc"
or else (Include_From and then Get_Name (H) = "from")
then
-- ??? Should avoid extra copy here
Union (Result, Get_Recipients (H));
end if;
end loop;
return Result;
end Get_Recipients;
--------------------
-- Get_Recipients --
--------------------
function Get_Recipients (H : Header'Class) return Address_Set.Set is
begin
if H.Contents = null then
return Address_Set.Empty_Set;
else
return Get_Addresses (H.Contents.Value);
end if;
end Get_Recipients;
-------------
-- Flatten --
-------------
procedure Flatten
(List : Charset_String_List.List;
Result : out Unbounded_String)
is
use Charset_String_List;
C : Charset_String_List.Cursor := First (List);
begin
Result := Null_Unbounded_String;
while Has_Element (C) loop
Append (Result, Element (C).Contents);
Next (C);
end loop;
end Flatten;
---------------
-- To_String --
---------------
procedure To_String
(List : Charset_String_List.List;
Result : out Unbounded_String;
Where : Any_Header := Other_Header)
is
use Charset_String_List;
C : Charset_String_List.Cursor := First (List);
Tmp : Unbounded_String;
begin
Result := Null_Unbounded_String;
while Has_Element (C) loop
Encode
(Str => To_String (Element (C).Contents),
Charset => To_String (Element (C).Charset),
Where => Where,
Result => Tmp);
Append (Result, Tmp);
Next (C);
end loop;
end To_String;
-------------------------
-- Domain_From_Address --
-------------------------
function Domain_From_Address (Email : String) return String is
begin
for E in Email'First .. Email'Last - 1 loop
if Email (E) = '@' then
return Email (E + 1 .. Email'Last);
end if;
end loop;
return "";
end Domain_From_Address;
function Domain_From_Address (Email : Email_Address) return String is
begin
return Domain_From_Address (To_String (Email.Address));
end Domain_From_Address;
-----------------------
-- Login_From_Address --
------------------------
function Login_From_Address (Email : String) return String is
begin
for E in Email'First .. Email'Last loop
if Email (E) = '@' then
return Email (Email'First .. E - 1);
end if;
end loop;
return Email;
end Login_From_Address;
function Login_From_Address (Email : Email_Address) return String is
begin
return Login_From_Address (To_String (Email.Address));
end Login_From_Address;
-------------------
-- Needs_Quoting --
-------------------
function Needs_Quoting
(Char : Character;
Where : Region;
Is_EOL : Boolean) return Boolean
is
begin
if Char = ' ' or else Char = ASCII.HT then
return Is_EOL or else Where in Any_Header;
elsif Char = '='
or else Char = '?'
or else Character'Pos (Char) not in 32 .. 126
then
return True;
else
return Where = Addr_Header and then Special_Chars (Char);
end if;
end Needs_Quoting;
function Needs_Quoting
(U : Unbounded_String;
Where : Region;
Is_EOL : Boolean) return Boolean
is
use Ada.Strings.Unbounded.Aux;
Str : Big_String_Access;
Last : Integer;
EOL : Boolean;
begin
Get_String (U, Str, Last);
for J in Str'First .. Last loop
EOL := Is_EOL and then J = Last;
-- No need to quote whitespace unless at EOL
if (Str (J) = ' ' or else Str (J) = ASCII.HT) and then not EOL then
null;
elsif Needs_Quoting (Str (J), Where, EOL) then
return True;
end if;
end loop;
return False;
end Needs_Quoting;
-----------------------------
-- Quoted_Printable_Encode --
-----------------------------
procedure Quoted_Printable_Encode
(Str : String;
Charset : String;
Max_Block_Len : Integer := Integer'Last;
Where : Region := Text;
Result : out Unbounded_String)
is
Block_Prefix : constant String :=
(if Where in Any_Header then "=?" & Charset & "?q?" else "");
Block_Suffix : constant String :=
(if Where in Any_Header then "?=" else "");
Block_Separator : constant String :=
(if Where in Any_Header then " " else "=" & ASCII.LF);
-- In Text, use a soft line break
Current_Len : Natural := 0;
Max : constant Natural :=
Integer'Min (Max_Block_Len, (if Where in Any_Header then 75 else 76))
- Block_Prefix'Length
- Block_Suffix'Length
- (Block_Separator'Length - 1);
-- Note: Block_Separator may produce a printable character, so must be
-- counted against the limit.
function Quote (S : String) return String;
-- Encode all characters in S
procedure Append (Substring : String; Splittable : Boolean);
-- Append Substring to Result, taking into account the max line length.
-- If Splittable is false, Substring cannot be cut
-----------
-- Quote --
-----------
function Quote (S : String) return String is
P : Integer;
Result : String (1 .. 3 * S'Length);
Last : Integer := 0;
begin
for J in S'Range loop
if S (J) = ' ' and then Where in Any_Header then
Last := Last + 1;
Result (Last) := '_';
else
Last := Last + 3;
P := Character'Pos (S (J));
Result (Last - 2 .. Last) :=
('=', Hex_Chars (P / 16), Hex_Chars (P mod 16));
end if;
end loop;
return Result (1 .. Last);
end Quote;
------------
-- Append --
------------
procedure Append (Substring : String; Splittable : Boolean) is
S : Integer := Substring'First;
begin
if Substring'Length = 0 then
return;
end if;
if Splittable then
while Substring'Last - S + 1 > Max - Current_Len loop
if Current_Len = 0 then
Append (Result, Block_Prefix);
end if;
Append
(Result,
Substring (S .. S + Max - Current_Len - 1));
Append (Result, Block_Suffix & Block_Separator);
S := S + Max - Current_Len;
Current_Len := 0; -- We just started a new line
end loop;
if Current_Len = 0 then
Append (Result, Block_Prefix);
end if;
Append (Result, Substring (S .. Substring'Last));
Current_Len := Current_Len + Substring'Last - S + 1;
else
if Current_Len + Substring'Length > Max then
if Current_Len /= 0 then
Append (Result, Block_Suffix & Block_Separator);
end if;
Current_Len := 0;
Append (Result, Block_Prefix);
Append (Result, Substring);
Current_Len := Substring'Length;
else
if Current_Len = 0 then
Append (Result, Block_Prefix);
end if;
Append (Result, Substring);
Current_Len := Current_Len + Substring'Length;
end if;
end if;
end Append;
Start, Next, Last : Integer;
-- Start of current encoded sequence,
-- start of next encoded sequence,
-- last element of previous encoded sequence.
procedure Passthrough;
-- Output previous span of unencoded characters, i.e.
-- from Last + 1 to Start - 1.
-----------------
-- Passthrough --
-----------------
procedure Passthrough is
begin
Append (Str (Last + 1 .. Start - 1), Splittable => True);
end Passthrough;
Next_Char : constant Next_Char_Acc :=
(if Where in Any_Header
then Next_Char_For_Charset (Charset)
else Single_Byte_Next_Char'Access);
-- Start of processing for Quoted_Printable_Encode
begin
Result := Null_Unbounded_String;
Next := Str'First;
Last := Next - 1;
loop
Start := Next;
exit when Start > Str'Last;
-- Find end of possibly multibyte sequence starting at Start
Next := Start;
Next_Char_Ignore_Invalid (Next_Char, Str, Next);
-- We encode single characters if needed, and always encode
-- all multibyte characters.
if Last > Start + 1
or else
Needs_Quoting (Str (Start), Where, Is_EOL => Start = Str'Last)
then
Passthrough;
Last := Next - 1;
Append (Quote (Str (Start .. Last)), Splittable => False);
end if;
end loop;
Passthrough;
if Current_Len /= 0 then
Append (Result, Block_Suffix);
end if;
end Quoted_Printable_Encode;
-----------------------------
-- Quoted_Printable_Decode --
-----------------------------
procedure Quoted_Printable_Decode
(Str : String;
Result : out Unbounded_String;
Where : Region := Text)
is
Start : Integer := -1;
S : Integer;
function Is_Hex (Char : Character) return Boolean;
-- Return true if Char is an hexa character
------------
-- Is_Hex --
------------
function Is_Hex (Char : Character) return Boolean is
begin
return Qp_Convert (Char) >= 0;
end Is_Hex;
-- Start of processing for Quoted_Printable_Decode
begin
S := Str'First;
Result := Null_Unbounded_String;
while S <= Str'Last loop
if Str (S) = '_' and then Where in Any_Header then
-- Encoded SPACE
if Start /= -1 then
Append (Result, Str (Start .. S - 1));
Start := -1;
end if;
Append (Result, ' ');
elsif Str (S) /= '=' then
-- Regular character
if Start = -1 then
Start := S;
end if;
elsif Str (S) = '='
and then S + 1 <= Str'Last
and then Str (S + 1) = ASCII.LF
then
-- Soft line break
if Start /= -1 then
Append (Result, Str (Start .. S - 1));
Start := -1;
end if;
S := S + 1;
elsif S + 2 <= Str'Last
and then Is_Hex (Str (S + 1))
and then Is_Hex (Str (S + 2))
then
-- Valid quote sequence
if Start /= -1 then
Append (Result, Str (Start .. S - 1));
Start := -1;
end if;
Append
(Result,
Character'Val
(Qp_Convert (Str (S + 1)) * 16 + Qp_Convert (Str (S + 2))));
S := S + 2;
else
-- Invalid quote sequence. Leave it as is
if Start /= -1 then
Append (Result, Str (Start .. S - 1));
Start := -1;
end if;
end if;
S := S + 1;
end loop;
if Start /= -1 then
Append (Result, Str (Start .. Str'Last));
end if;
end Quoted_Printable_Decode;
-------------------
-- Base64_Encode --
-------------------
procedure Base64_Encode
(Str : String;
Charset : String;
Max_Block_Len : Integer := Integer'Last;
Where : Region := Text;
Result : out Unbounded_String)
is
Block_Prefix : constant String :=
(if Where in Any_Header then "=?" & Charset & "?b?" else "");
Block_Suffix : constant String :=
(if Where in Any_Header then "?=" else "");
Block_Separator : constant String :=
(if Where in Any_Header then " " else (1 => ASCII.LF));
-- In Text, use a soft line break as line separator
Max : constant Natural :=
4 * Integer'Max
(1,
(Integer'Min (Max_Block_Len,
(if Where in Any_Header then 75 else 76))
- Block_Prefix'Length
- Block_Suffix'Length) / 4);
-- Maximum length of encoded data within an encoded block (must be
-- a non-null multiple of 4). Note: block separator does not contain
-- any printable character, so does not count against the limit.
Encoded_Len : constant Integer := (Str'Length + 2) / 3 * 4;
-- Each group of 3 input bytes yields 4 output bytes, including a
-- trailing incomplete group.
Blocks : constant Integer := (Encoded_Len + Max - 1) / Max;
Encoded_Block_Len : constant Integer :=
Block_Prefix'Length + Max + Block_Suffix'Length
+ Block_Separator'Length;
-- Allocation size for each block
Len : constant Integer :=
Blocks * Encoded_Block_Len;
-- Pre-allocation length. This is sufficient to accomodate the entire
-- encoded data, split into blocks, except if some blocks need to be
-- flushed early (while incomplete) in order to avoid incorrect
-- splitting of multi-byte sequences.
Output : Ada.Strings.Unbounded.String_Access := new String (1 .. Len);
Index : Integer := Output'First;
Left : Unsigned_16 := 0;
Leftbits : Natural := 0;
Ch : Mod64;
Current : Integer := 0;
procedure Append (Ch : Character);
-- Append a new character to the output, splitting lines as necessary
------------
-- Append --
------------
procedure Append (Ch : Character) is
New_Output : Ada.Strings.Unbounded.String_Access;
begin
if Current = 0 then
-- Make sure that the string has sufficient space for the
-- full new encoded block
if Output'Last - Index + 1 < Encoded_Block_Len then
New_Output :=
new String (1 .. Output'Length + Encoded_Block_Len);
New_Output (1 .. Index - 1) := Output (1 .. Index - 1);
Free (Output);
Output := New_Output;
end if;
Output (Index .. Index + Block_Prefix'Length - 1) :=
Block_Prefix;
Index := Index + Block_Prefix'Length;
end if;
Output (Index) := Ch;
Index := Index + 1;
Current := Current + 1;
if Current = Max then
-- Append suffix and separator
Output (Index .. Index
+ Block_Suffix'Length
+ Block_Separator'Length - 1) :=
Block_Suffix & Block_Separator;
Index := Index + Block_Suffix'Length + Block_Separator'Length;
Current := 0;
end if;
end Append;
procedure Encode_Append (Str : String);
-- Encode Str and append result to output, splitting if necessary.
-- If Where is Any_Header, then never split Str across two different
-- blocks.
procedure Flush;
-- Flush pending bits, outputting padding characters if necessary
procedure Encode_Append (Str : String) is
Out_Chars : constant Integer := (Leftbits + Str'Length * 8 + 5) / 6;
begin
-- Force flushing now if in header mode and encoded sequence would
-- exceed maximum length.
if Where in Any_Header and then Current + Out_Chars > Max then
Flush;
end if;
for J in Str'Range loop
Left := Shift_Left (Left, 8) or Character'Pos (Str (J));
Leftbits := Leftbits + 8;
while Leftbits >= 6 loop
Ch :=
Mod64 ((Shift_Right (Left, Leftbits - 6)) and 16#3f#);
Leftbits := Leftbits - 6;
Append (To_Base64 (Ch));
end loop;
end loop;
end Encode_Append;
-----------
-- Flush --
-----------
procedure Flush is
begin
case Leftbits is
when 0 =>
null;
when 2 =>
Ch := Mod64 (Shift_Left (Left and 3, 4));
Append (To_Base64 (Ch));
Append ('=');
Append ('=');
when 4 =>
Ch := Mod64 (Shift_Left (Left and 16#F#, 2));
Append (To_Base64 (Ch));
Append ('=');
when others =>
raise Program_Error with "invalid Base64 encoder state";
end case;
Left := 0;
Leftbits := 0;
end Flush;
Start, Next : Integer;
-- Start of current encoded sequence,
-- start of next encoded sequence,
-- last element of previous encoded sequence.
Next_Char : constant Next_Char_Acc :=
(if Where in Any_Header
then Next_Char_For_Charset (Charset)
else Single_Byte_Next_Char'Access);
-- In message bodies, multi-byte encodings can be
-- split across multiple lines; in headers, they can't
-- be split across multiple encoded words.
-- Start of processing for Base64_Encode
begin
Next := Str'First;
loop
Start := Next;
exit when Start > Str'Last;
-- Find end of possibly multibyte sequence starting at Start
Next := Start;
Next_Char_Ignore_Invalid (Next_Char, Str, Next);
Encode_Append (Str (Start .. Next - 1));
end loop;
Flush;
if Current = 0 then
-- Remove last separator
Index := Index - Block_Separator'Length;
elsif Current > 0 then
Output (Index .. Index + Block_Suffix'Length - 1) :=
Block_Suffix;
Index := Index + Block_Suffix'Length;
end if;
if Output'Last /= Index - 1 then
Set_Unbounded_String (Result, Output (1 .. Index - 1));
else
Set_Unbounded_String (Result, Output.all);
end if;
Free (Output);
end Base64_Encode;
-------------------
-- Base64_Decode --
-------------------
procedure Base64_Decode
(Str : String;
Result : out Unbounded_String)
is
type Phase_Type is mod 4;
-- We must use the heap rather than the stack here. In some
-- cases, we'll be able to avoid a copy of the string anyway,
-- and in case where this code is run in a multi-threaded
-- application, the stack size is generally too small anyway
Output : Ada.Strings.Unbounded.String_Access :=
new String (1 .. Str'Length * 6 / 8);
Index : Integer := Output'First;
Phase : Phase_Type := 0;
D, Dlast : Byte := 0;
begin
for S in Str'First .. Str'Last loop
if Str (S) = ASCII.LF
or else Str (S) = ASCII.CR
then
Phase := 0;
Dlast := 0;
else
D := Base64_Convert (Str (S));
if D /= -1 then
case Phase is
when 0 =>
Phase := Phase + 1;
when 1 =>
Output (Index) := Character'Val
(Dlast * 4 or ((D and 16#30#) / 16));
Index := Index + 1;
Phase := Phase + 1;
when 2 =>
Output (Index) := Character'Val
(((Dlast and 16#F#) * 16) or ((D and 16#3C#) / 4));
Index := Index + 1;
Phase := Phase + 1;
when 3 =>
Output (Index) := Character'Val
(((Dlast and 16#3#) * 64) or D);
Index := Index + 1;
Phase := 0;
end case;
Dlast := D;
end if;
end if;
end loop;
if Index - 1 = Output'Last then
Set_Unbounded_String (Result, Output.all);
else
Set_Unbounded_String (Result, Output (Output'First .. Index - 1));
end if;
Free (Output);
end Base64_Decode;
------------
-- Encode --
------------
procedure Encode
(Str : String;
Charset : String := Charset_US_ASCII;
Where : Region := Text;
Result : out Unbounded_String)
is
Encoding : Encoding_Type;
Set : constant String := To_Lower (Charset);
begin
-- Preferred encoding are the same as in Python
if Set = Charset_US_ASCII then
Encoding := Encoding_7bit;
elsif Set = Charset_ISO_8859_1
or else Set = "latin_1" or else Set = "latin-1"
or else Set = Charset_ISO_8859_2
or else Set = "latin_2" or else Set = "latin-2"
or else Set = Charset_ISO_8859_3
or else Set = "latin_3" or else Set = "latin-3"
or else Set = Charset_ISO_8859_4
or else Set = "latin_4" or else Set = "latin-4"
or else Set = Charset_ISO_8859_9
or else Set = "latin_5" or else Set = "latin-5"
or else Set = Charset_ISO_8859_10
or else Set = "latin_6" or else Set = "latin-6"
or else Set = Charset_ISO_8859_13
or else Set = "latin_7" or else Set = "latin-7"
or else Set = Charset_ISO_8859_14
or else Set = "latin_8" or else Set = "latin-8"
or else Set = Charset_ISO_8859_15
or else Set = "latin_9" or else Set = "latin-9"
or else Set = Charset_Windows_1252
or else Set = "viscii"
or else Set = Charset_UTF_8 or else Set = "utf8"
then
Encoding := Encoding_QP;
else
Encoding := Encoding_Base64;
end if;
case Encoding is
when Encoding_Base64 =>
Base64_Encode
(Str, Charset => Set, Where => Where, Result => Result);
when Encoding_QP =>
Quoted_Printable_Encode
(Str, Charset => Set, Where => Where, Result => Result);
when others =>
Result := To_Unbounded_String (Str);
end case;
end Encode;
-------------------
-- Decode_Header --
-------------------
procedure Decode_Header
(Str : String;
Default_Charset : String := Charset_US_ASCII;
Result : out Charset_String_List.List;
Where : Any_Header := Other_Header)
is
use Charset_String_List;
Start : Integer;
Index : Integer;
Index2 : Integer;
Section : Charset_String;
Encoding : Encoding_Type;
S : Integer;
procedure Append (Section : Charset_String);
-- Add Section to the result, merging with previous section if needed.
-- If Section.Charset is empty, use Default_Charset, or Charset_US_ASCII
-- if possible.
------------
-- Append --
------------
procedure Append (Section : Charset_String) is
NSection : Charset_String := Section;
begin
if NSection.Charset = Null_Unbounded_String then
declare
Raw_Str : Ada.Strings.Unbounded.Aux.Big_String_Access;
Raw_Last : Integer;
begin
Ada.Strings.Unbounded.Aux.Get_String
(NSection.Contents, Raw_Str, Raw_Last);
for J in Raw_Str'First .. Raw_Last loop
if Character'Pos (Raw_Str (J)) not in 32 .. 126 then
NSection.Charset := To_Unbounded_String (Default_Charset);
exit;
end if;
end loop;
if NSection.Charset = Null_Unbounded_String then
NSection.Charset := U_Charset_US_ASCII;
end if;
end;
end if;
-- Now append the new section to the sequence
if Is_Empty (Result) then
Append (Result, NSection);
else
-- An empty section between two encoded ones must be ignored
if NSection.Charset /= Default_Charset
and then Element (Last (Result)).Charset = Default_Charset
then
declare
Previous : constant Unbounded_String :=
Element (Last (Result)).Contents;
begin
if Index_Non_Blank (Previous) < 1 then
Delete_Last (Result);
end if;
end;
end if;
-- Try to merge Section with previous one, if possible
if not Is_Empty (Result)
and then NSection.Charset = Element (Last (Result)).Charset
then
Replace_Element
(Result, Last (Result),
(Contents =>
Element (Last (Result)).Contents & NSection.Contents,
Charset => NSection.Charset));
else
Append (Result, NSection);
end if;
end if;
end Append;
-- Start of processing for Decode_Header
begin
Result := Charset_String_List.Empty_List;
S := Str'First;
Start := Str'First;
while S < Str'Last loop
if Str (S) = '='
and then S < Str'Last
and then Str (S + 1) = '?'
then
Index := Next_Occurrence (Str (S + 2 .. Str'Last), '?');
if Index < Str'Last then
Section.Charset :=
To_Unbounded_String (To_Lower (Str (S + 2 .. Index - 1)));
case To_Lower (Str (Index + 1)) is
when 'q' => Encoding := Encoding_QP;
when 'b' => Encoding := Encoding_Base64;
when others => Encoding := Encoding_7bit;
end case;
if Encoding /= Encoding_7bit
and then Index + 2 < Str'Last
then
if Str (Index + 2) = '?' then
-- So far we have the prefix =?<charset>?<encoding>?
Index2 := Index + 3;
Index := Next_Occurrence (Str (Index2 .. Str'Last), '?');
if Index < Str'Last and then Str (Index + 1) = '=' then
case Encoding is
when Encoding_QP =>
Quoted_Printable_Decode
(Str (Index2 .. Index - 1),
Where => Where,
Result => Section.Contents);
when Encoding_Base64 =>
Base64_Decode
(Str (Index2 .. Index - 1),
Result => Section.Contents);
when others => null;
end case;
-- Deal with non-encoded-word part: charset is
-- set to Default_Charset, unless the string has
-- no character which need to be encoded, in which
-- case use US-ASCII instead.
if Start <= S - 1 then
declare
Raw_Section : String
renames Str (Start .. S - 1);
-- Part of Str that is not an encoded-word
begin
Append
((Contents =>
To_Unbounded_String (Raw_Section),
Charset => Null_Unbounded_String));
end;
end if;
Append (Section);
S := Index + 2;
Start := S;
else
S := Index2;
end if;
else
S := Index + 1;
end if;
else
S := Index + 1;
end if;
end if;
end if;
S := S + 1;
end loop;
if Start <= Str'Last then
Append
((Contents => To_Unbounded_String (Str (Start .. Str'Last)),
Charset => Null_Unbounded_String));
end if;
end Decode_Header;
-------------------
-- Get_Main_Type --
-------------------
function Get_Main_Type (MIME_Type : String) return String is
begin
for M in MIME_Type'Range loop
if MIME_Type (M) = '/' then
return MIME_Type (MIME_Type'First .. M - 1);
end if;
end loop;
return MIME_Type;
end Get_Main_Type;
------------------
-- Get_Sub_Type --
------------------
function Get_Sub_Type (MIME_Type : String) return String is
begin
for M in MIME_Type'Range loop
if MIME_Type (M) = '/' then
if M + 1 <= MIME_Type'Last then
return MIME_Type (M + 1 .. MIME_Type'Last);
else
return "";
end if;
end if;
end loop;
return MIME_Type;
end Get_Sub_Type;
end GNATCOLL.Email.Utils;
|