pike.git/lib/modules/MIME.pmod/module.pmod:374c1d0d8ffe73d6793995985e741428c310f99a

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 // -*- Pike -*- // // RFC1521 functionality for Pike // // Marcus Comstedt 1996-1999 //! @rfc{1521@}, the @b{Multipurpose Internet Mail Extensions@} memo, defines a //! structure which is the base for all messages read and written by //! modern mail and news programs. It is also partly the base for the //! HTTP protocol. Just like @rfc{822@}, MIME declares that a message should //! consist of two entities, the headers and the body. In addition, the //! following properties are given to these two entities: //! //! @dl //! @item Headers //! @ul //! @item //! A MIME-Version header must be present to signal MIME compatibility //! @item //! A Content-Type header should be present to describe the nature of //! the data in the message body. Seven major types are defined, and an //! extensive number of subtypes are available. The header can also //! contain attributes specific to the type and subtype. //! @item //! A Content-Transfer-Encoding may be present to notify that the data //! of the body is encoded in some particular encoding. //! @endul //! @item Body //! @ul //! @item //! Raw data to be interpreted according to the Content-Type header //! @item //! Can be encoded using one of several Content-Transfer-Encodings to //! allow transport over non 8bit clean channels //! @endul //! @enddl //! //! The MIME module can extract and analyze these two entities from a stream //! of bytes. It can also recreate such a stream from these entities. //! To encapsulate the headers and body entities, the class @[MIME.Message] is //! used. An object of this class holds all the headers as a mapping from //! string to string, and it is possible to obtain the body data in either //! raw or encoded form as a string. Common attributes such as message type //! and text char set are also extracted into separate variables for easy //! access. //! //! The Message class does not make any interpretation of the body //! data, unless the content type is @tt{multipart@}. A multipart //! message contains several individual messages separated by boundary //! strings. The @[Message->create] method of the Message class will //! divide a multipart body on these boundaries, and then create //! individual Message objects for each part. These objects will be //! collected in the array @[Message->body_parts] within the original //! Message object. If any of the new @[Message] objects have a body of //! type multipart, the process is of course repeated recursively. #pike __REAL_VERSION__ inherit ___MIME; //! Class representing a substring of a larger string. //! //! This class is used to reduce the number of string copies //! during parsing of @[MIME.Message]s. protected class StringRange { string data; int start; // Inclusive. int end; // Exclusive. protected void create(string|StringRange s, int start, int end) { if (start == end) { data = ""; this::start = this::end = 0; return; } if (start < 0) start = 0; if (end < 0) end = 0; if (objectp(s)) { start += s->start; if (start > s->end) start = s->end; end += s->start; if (end > s->end) end = s->end; s = s->data; } if ((end - start)*16 < sizeof(s)) { s = s[start..end-1]; end -= start; start = 0; } data = s; this::start = start; this::end = end; } protected int _sizeof() { return end-start; } protected string|StringRange `[..](int low, int ltype, int high, int htype) { int len = end - start; if (ltype == Pike.INDEX_FROM_END) { low = len - (low + 1); } high += 1; if (htype == Pike.INDEX_FROM_END) { high = len - high; } else if (htype == Pike.OPEN_BOUND) { high = len; } if (low < 0) low = 0; if (high < 0) high = 0; if (low > len) low = len; if (high > len) high = len; if (!low && (high == len)) return this; if ((high - low) < 65536) return data[start+low..start+high-1]; return StringRange(this, low, high); } protected int `[](int pos) { int npos = pos; if (npos < 0) { npos += end; if (npos < start) { error("Index out of range [-%d..%d]\n", 1 + end-start, end-start); } } else { npos += start; if (npos >= end) { error("Index out of range [-%d..%d]\n", 1 + end-start, end-start); } } return data[npos]; } protected mixed cast(string type) { if( type == "string" ) return data[start..end-1]; return UNDEFINED; } protected int _search(string frag, int|void pos) { if (pos < 0) error("Start must be greater or equal to zero.\n"); int npos = pos + start; if (npos > end) error("Start must not be greater than the length of the string.\n"); if ((npos + sizeof(frag)) > end) return -1; npos = search(data, frag, npos); if (npos < 0) return npos; if ((npos + sizeof(frag)) > end) return -1; return npos - start; } protected string _sprintf(int c) { if (c == 'O') return sprintf("StringRange(%d bytes[%d..%d] %O)", data && sizeof(data), start, end-1, data && data[..40]); return (string)this; } } #if (__REAL_VERSION__ < 7.8) || ((__REAL_VERSION__) < 7.9 && (__REAL_BUILD__ < 413)) // Compat with some older Pikes... // Support has_prefix on objects. protected int(0..1) has_prefix(string|object s, string prefix) { if (!objectp(s)) return predef::has_prefix(s, prefix); for(int i = 0; i < sizeof(prefix); i++) { if (s[i] != prefix[i]) return 0; } return 1; } #endif //! This function will create a string that can be used as a separator string //! for multipart messages. The generated string is guaranteed not to appear //! in @tt{base64@}, @tt{quoted-printable@}, or @tt{x-uue@} encoded data. //! It is also unlikely to appear in normal text. This function is used by //! the cast method of the @tt{Message@} class if no boundary string is //! specified. //! string generate_boundary( ) { return "'ThIs-RaNdOm-StRiNg-/=_."+random( 1000000000 )+":"; } //! Extract raw data from an encoded string suitable for transport between //! systems. //! //! The encoding can be any of //! @string //! @value "7bit" //! @value "8bit" //! @value "base64" //! @value "binary" //! @value "quoted-printable" //! @value "x-uue" //! @value "x-uuencode" //! @endstring //! //! The encoding string is not case sensitive. //! //! @seealso //! @[MIME.encode()] //! string|StringRange decode( string|StringRange data, string encoding ) { switch (lower_case( encoding || "binary" )) { case "base64": return decode_base64( (string)data ); case "quoted-printable": return decode_qp( (string)data ); case "x-uue": case "x-uuencode": return decode_uue( (string)data ); case "7bit": case "8bit": case "binary": return data; default: error("Unknown transfer encoding %s.\n", encoding); } } //! Encode raw data into something suitable for transport to other systems. //! //! The encoding can be any of //! @string //! @value "7bit" //! @value "8bit" //! @value "base64" //! @value "binary" //! @value "quoted-printable" //! @value "x-uue" //! @value "x-uuencode" //! @endstring //! //! The encoding string is not case sensitive. For the @tt{x-uue@} encoding, //! an optional @[filename] string may be supplied. //! //! If a nonzero value is passed as @[no_linebreaks], the result string //! will not contain any linebreaks (@tt{base64@} and @tt{quoted-printable@} //! only). //! //! @seealso //! @[MIME.decode()] //! string encode( string data, string encoding, void|string filename, void|int no_linebreaks ) { switch (lower_case( encoding || "binary" )) { case "base64": return encode_base64( data, no_linebreaks ); case "quoted-printable": return encode_qp( data, no_linebreaks ); case "x-uue": case "x-uuencode": return encode_uue( data, filename ); case "7bit": case "8bit": case "binary": return data; default: error("Unknown transfer encoding %s.\n", encoding); } } //! Extracts the textual content and character set from an @i{encoded word@} //! as specified by @rfc{1522@}. The result is an array where the first element //! is the raw text, and the second element the name of the character set. //! If the input string is not an encoded word, the result is still an array, //! but the char set element will be set to 0. //! //! @note //! Note that this function can only be applied to individual encoded words. //! //! @seealso //! @[MIME.encode_word()] //! array(string) decode_word( string word ) { string charset, encoding, encoded_text; if (sscanf( word, "=?%[^][ \t()<>@,;:\"\\/?.=]?%[^][ \t()<>@,;:\"\\/?.=]?%s?=", charset, encoding, encoded_text) == 3 ) { switch (lower_case( encoding )) { case "b": encoding = "base64"; break; case "q": encoding = "quoted-printable"; break; default: error( "Invalid rfc1522 encoding %s.\n", encoding ); } return ({ decode( replace( encoded_text, "_", " " ), encoding ), lower_case( charset ) }); } else return ({ word, 0 }); } //! Create an @i{encoded word@} as specified in @rfc{1522@} from an array //! containing a raw text string and a char set name. //! //! The text will be transfer encoded according to the encoding argument, //! which can be either @expr{"base64"@} or @expr{"quoted-printable"@} //! (or either @expr{"b"@} or @expr{"q"@} for short). //! //! If either the second element of the array (the char set name), or //! the encoding argument is 0, the raw text is returned as is. //! //! @seealso //! @[MIME.decode_word()] //! string encode_word( string|array(string) word, string encoding ) { if (stringp(word)) return word; if (!encoding || !word[1]) return word[0]; switch (lower_case(encoding)) { case "b": case "base64": encoding = "base64"; break; case "q": case "quoted-printable": encoding = "quoted-printable"; break; default: error( "Invalid rfc1522 encoding %s.\n", encoding); } string enc = encode( word[0], encoding, 0, 1 ); if (encoding == "quoted-printable") enc = replace( enc, ({ "?", "_", "(", ")", "\\", "\"" }), ({ "=3F", "=5F", "=28", "=29", "=5C", "=22" }) ); return "=?"+word[1]+"?"+encoding[0..0]+"?"+ enc +"?="; } protected string remap(array(string) item) { if (sizeof(item)>1 && item[1]) return Charset.decoder(item[1])->feed(item[0])->drain(); else return item[0]; } protected array(string) reremap(string word, string|function(string:string) selector, string|void replacement,function(string:string)|void repcb) { if(max(@values(word))<128) return ({ word,0 }); string s = stringp(selector)? selector : selector(word); return s? ({ Charset.encoder(s,replacement,repcb)->feed(word)->drain(), s }) : ({ word,0 }); } //! Separates a header value containing @i{text@} into units and calls //! @[MIME.decode_word()] on them. The result is an array where each element //! is a result from @[decode_word()]. //! //! @seealso //! @[MIME.decode_words_tokenized] //! @[MIME.decode_words_text_remapped] //! array(array(string)) decode_words_text( string txt ) { object r = Regexp("^(.*[ \t\n\r]|)(=\\?[^\1- ?]*\\?[^\1- ?]*\\?" "[^\1- ?]*\\?=)(([ \t\n\r]+)(.*)|)$"); array a, res = ({}); while ((a = r->split(txt))) { if(!sizeof(a[2])) a = a[..2]+({"",""}); txt = a[0]||""; if(!sizeof(res) || sizeof(a[4])) a[4]=a[3]+a[4]; array w = decode_word(a[1]); if (sizeof(a[4])) res = ({ w, ({ a[4], 0 }) }) + res; else res = ({ w }) + res; } a = res; res = ({}); if (sizeof(txt)) res = ({ ({ txt, 0 }) }); foreach(a, array(string) word) { if (sizeof(res) && res[-1][1] && (res[-1][1] == word[1])) { // Same character set as previous word -- Join the fragments. // This is a workaround for MUA's that split // the text in the middle of encoded characters. // eg PHPMailer [version 1.73] res[-1][0] += word[0]; } else { res += ({ word }); } } return res; } //! Like @[MIME.decode_words_text()], but the extracted strings are //! also remapped from their specified character encoding into UNICODE, //! and then pasted together. The result is thus a string in the original //! text format, without @rfc{1522@} escapes, and with all characters in UNICODE //! encoding. //! //! @seealso //! @[MIME.decode_words_tokenized_remapped] //! string decode_words_text_remapped( string txt ) { return Array.map(decode_words_text(txt), remap)*""; } //! Tokenizes a header value just like @[MIME.tokenize()], but also //! converts encoded words using @[MIME.decode_word()]. The result is //! an array where each element is either an @expr{int@} representing //! a special character, or an @expr{array@} as returned by //! @[decode_word()] representing an atom or a quoted string. //! //! @seealso //! @[MIME.decode_words_tokenized_labled] //! @[MIME.decode_words_tokenized_remapped] //! @[MIME.decode_words_text] //! array(array(string)|int) decode_words_tokenized( string phrase, int|void flags ) { return Array.map(tokenize(phrase, flags), lambda(string|int item) { return intp(item)? item : decode_word(item); }); } //! Like @[MIME.decode_words_tokenized()], but the extracted atoms are //! also remapped from their specified character encoding into UNICODE. //! The result is thus identical to that of @[MIME.tokenize()], but //! without @rfc{1522@} escapes, and with all characters in UNICODE encoding. //! //! @seealso //! @[MIME.decode_words_tokenized_labled_remapped] //! @[MIME.decode_words_text_remapped] //! array(string|int) decode_words_tokenized_remapped( string phrase, int|void flags ) { return Array.map(decode_words_tokenized(phrase, flags), lambda(array(string)|int item) { return intp(item)? item : remap(item); }); } //! Tokenizes and labels a header value just like @[MIME.tokenize_labled()], //! but also converts encoded words using @[MIME.decode_word()]. The result //! is an array where each element is an array of two or more elements, the //! first being the label. The rest of the array depends on the label: //! //! @string //! @value "special" //! One additional element, containing the character code for the special //! character as an @expr{int@}. //! @value "word" //! Two additional elements, the first being the word, and the second //! being the character set of this word (or 0 if it did not originate //! from an encoded word). //! @value "domain-literal" //! One additional element, containing the domain literal as a string. //! @value "comment" //! One additional element, containing an array as returned by //! @[MIME.decode_words_text()]. //! @endstring //! //! @seealso //! @[MIME.decode_words_tokenized_labled_remapped] //! array(array(string|int|array(array(string)))) decode_words_tokenized_labled( string phrase, int|void flags ) { return Array.map( tokenize_labled( phrase, flags ), lambda(array(string|int) item) { switch(item[0]) { case "encoded-word": return ({ "word", @decode_word(item[1]) }); case "word": return item + ({ 0 }); case "comment": return ({ "comment", decode_words_text(item[1]) }); default: return item; } }); } //! Like @[MIME.decode_words_tokenized_labled()], but the extracted words are //! also remapped from their specified character encoding into UNICODE. //! The result is identical to that of @[MIME.tokenize_labled()], but //! without @rfc{1522@} escapes, and with all characters in UNICODE encoding. //! array(array(string|int)) decode_words_tokenized_labled_remapped(string phrase, int|void flags) { return Array.map(decode_words_tokenized_labled(phrase, flags), lambda(array(string|int|array(array(string|int))) item) { switch(item[0]) { case "word": return ({ "word", remap(item[1..]) }); case "comment": return ({ "comment", Array.map(item[1], remap)*"" }); default: return item; } }); } //! The inverse of @[decode_words_text()], this function accepts //! an array of strings or pairs of strings which will each be encoded //! by @[encode_word()], after which they are all pasted together. //! //! @param encoding //! Either @expr{"base64"@} or @expr{"quoted-printable"@} //! (or either @expr{"b"@} or @expr{"q"@} for short). //! //! @seealso //! @[MIME.encode_words_text_remapped] //! string encode_words_text(array(string|array(string)) phrase, string encoding) { phrase = filter(phrase, lambda(string|array(string) w) { return stringp(w)? sizeof(w) : sizeof(w[0]) || w[1]; }); array(string) ephrase = map(phrase, encode_word, encoding); if(!encoding) return ephrase*""; string res=""; for(int i=0; i<sizeof(ephrase); i++) if(ephrase[i] != (stringp(phrase[i])? phrase[i] : phrase[i][0])) { if(sizeof(res) && !(<' ','\t','\n','\r'>)[res[-1]]) res += " "; res += ephrase[i]; if(i+1<sizeof(ephrase) && !(<' ','\t','\n','\r'>)[ephrase[i+1][0]]) res += " "; } else res += ephrase[i]; return res; } //! This is the reverse of @[MIME.decode_words_text_remapped()]. A //! single UNICODE string is provided, which is separated into //! fragments and transcoded to selected character sets by this //! function as needed. //! //! @param encoding //! Either @expr{"base64"@} or @expr{"quoted-printable"@} //! (or either @expr{"b"@} or @expr{"q"@} for short). //! @param charset //! Either the name of a character set to use, or a function returning //! a character set to use given a text fragment as input. //! @param replacement //! The @[replacement] argument to use when calling @[Charset.encoder] //! @param repcb //! The @[repcb] argument to use when calling @[Charset.encoder] //! //! @seealso //! @[MIME.encode_words_tokenized_remapped] //! string encode_words_text_remapped(string text, string encoding, string|function(string:string) charset, string|void replacement, function(string:string)|void repcb) { array(array(string)) out = ({}); string lastword = ""; while(sizeof(text)) { sscanf(text, "%[ \t\n\r]%[^ \t\n\r]%s", string ws, string word, text); array(string) ww = reremap(word, charset, replacement, repcb); if(sizeof(ws)) if(!ww[1]) ww[0] = ws + ww[0]; else if(!sizeof(out)) out = ({({ws,0})}); else if(!out[-1][1]) out[-1][0] += ws; else { /* Two encoded words joined by whitespace - not possible */ word = lastword+ws+word; ww = reremap(word, charset, replacement, repcb); out = out[..<1]; } lastword = word; out += ({ ww }); } return encode_words_text(out, encoding); } //! The inverse of @[decode_words_tokenized()], this functions accepts //! an array like the argument to @[quote()], but instead of simple strings //! for atoms and quoted-strings, it will also accept pairs of strings to //! be passed to @[encode_word()]. //! //! @param encoding //! Either @expr{"base64"@} or @expr{"quoted-printable"@} //! (or either @expr{"b"@} or @expr{"q"@} for short). //! //! @seealso //! @[MIME.encode_words_quoted_remapped()] //! @[MIME.encode_words_quoted_labled()] //! string encode_words_quoted(array(array(string)|int) phrase, string encoding) { return quote(Array.map(phrase, lambda(array(string)|int item) { return intp(item)? item : encode_word(item, encoding); })); } //! The inverse of @[decode_words_tokenized_remapped()], this functions //! accepts an array equivalent to the argument of @[quote()], but also //! performs on demand word encoding in the same way as //! @[encode_words_text_remapped()]. //! //! @seealso //! @[MIME.encode_words_text_remapped()] //! @[MIME.encode_words_quoted_labled_remapped()] //! string encode_words_quoted_remapped(array(string|int) phrase, string encoding, string|function(string:string) charset, string|void replacement, function(string:string)|void repcb) { return encode_words_quoted(map(phrase, lambda(string|int item) { return intp(item)? item : reremap(item, charset, replacement, repcb); }), encoding); } //! The inverse of @[decode_words_tokenized_labled()], this functions accepts //! an array like the argument to @[quote_labled()], but "word" labled //! elements can optionally contain an additional string element specifying //! a character set, in which case an encoded-word will be used. Also, the //! format for "comment" labled elements is entirely different; instead of //! a single string, an array of strings or pairs like the first argument to //! @[encode_words_text()] is expected. //! //! @param encoding //! Either @expr{"base64"@} or @expr{"quoted-printable"@} //! (or either @expr{"b"@} or @expr{"q"@} for short). //! //! @seealso //! @[MIME.encode_words_quoted()] //! @[MIME.encode_words_quoted_labled_remapped()] //! string encode_words_quoted_labled(array(array(string|int|array(string|array(string)))) phrase, string encoding) { return quote_labled(Array.map(phrase, lambda(array(string|int|array(string)) item) { switch(item[0]) { case "word": if(sizeof(item)>2 && item[2]) return ({ "encoded-word", encode_word(item[1..], encoding) }); else return item; case "comment": return ({ "comment", encode_words_text(item[1], encoding) }); default: return item; } })); } //! The inverse of @[decode_words_tokenized_labled_remapped()], this function //! accepts an array equivalent to the argument of @[quote_labled()], but also //! performs on demand word encoding in the same way as //! @[encode_words_text_remapped()]. //! string encode_words_quoted_labled_remapped(array(array(string|int)) phrase, string encoding, string|function(string:string) charset, string|void replacement, function(string:string)|void repcb) { return quote_labled(map(phrase, lambda(array(string|int) item) { switch(item[0]) { case "word": item = item[..0]+reremap(item[1], charset, replacement, repcb); if(sizeof(item)>2 && item[2]) return ({ "encoded-word", encode_word(item[1..], encoding) }); else return item; case "comment": return ({ "comment", encode_words_text_remapped(item[1], encoding, charset, replacement, repcb) }); default: return item; } })); } //! Provide a reasonable default for the subtype field. //! //! Some pre-@rfc{1521@} mailers provide only a type and no subtype in the //! Content-Type header field. This function can be used to obtain a //! reasonable default subtype given the type of a message. (This is done //! automatically by the @[MIME.Message] class.) //! //! Currently, the function uses the following guesses: //! @string //! @value "text" //! @expr{"plain"@} //! @value "message" //! @expr{"rfc822"@} //! @value "multipart" //! @expr{"mixed"@} //! @endstring //! string guess_subtype( string type ) { switch (type) { case "text": return "plain"; case "message": return "rfc822"; case "multipart": return "mixed"; } return 0; } //! @decl array(mapping(string:string)|string) parse_headers(string message) //! @decl array(mapping(string:array(string))|string) parse_headers( @ //! string message, @ //! int(1..1) use_multiple) //! //! This is a low level function that will separate the headers from the body //! of an encoded message. It will also translate the headers into a mapping. //! It will however not try to analyze the meaning of any particular header. //! This means that the body is returned as is, with any transfer-encoding //! intact. //! //! It is possible to call this function with just the header part //! of a message, in which case an empty body will be returned. //! //! The result is returned in the form of an array containing two elements. //! The first element is a mapping containing the headers found. The second //! element is a string containing the body. //! //! Headers that occurr multiple times will have their contents NUL separated, //! unless @[use_multiple] has been specified, in which case the contents will //! be arrays. //! array(mapping(string:string|array(string))|string|StringRange) parse_headers(string|StringRange message, void|int(1..1) use_multiple) { string head, header, hname, hcontents; string|StringRange body; int mesgsep; if (has_prefix(message, "\r\n") || has_prefix(message, "\n")) { // No headers. return ({ ([]), message[1 + (message[0] == '\r')..] }); } else { int mesgsep1 = search(message, "\r\n\r\n"); int mesgsep2 = search(message, "\n\n"); mesgsep = (mesgsep1<0? mesgsep2 : (mesgsep2<0? mesgsep1 : (mesgsep1<mesgsep2? mesgsep1 : mesgsep2))); if (mesgsep<0) { // No body, or only body. head = (string)message; body = ""; } else if (mesgsep) { head = (string)(mesgsep>0? message[..mesgsep-1]:""); body = message[mesgsep+(message[mesgsep]=='\r'? 4:2)..]; } } mapping(string:string|array) headers = ([ ]); foreach( replace(head, ({"\r", "\n ", "\n\t"}), ({"", " ", " "}))/"\n", header ) { if(4==sscanf(header, "%[!-9;-~]%*[ \t]:%*[ \t]%s", hname, hcontents)) { hname = lower_case(hname); if (use_multiple) headers[hname] += ({hcontents}); else if(headers[hname]) headers[hname] += "\0"+hcontents; else headers[hname] = hcontents; } } if( mesgsep<0 && !sizeof(headers) ) return ({ ([]), (string)message }); return ({ headers, body }); } //! This class is used to hold a decoded MIME message. class Message { import Array; protected string|StringRange encoded_data; protected string|StringRange decoded_data; //! This mapping contains all the headers of the message. //! //! The key is the header name (in lower case) and the value is //! the header value. //! //! Although the mapping contains all headers, some particular headers get //! special treatment by the module and should @b{not@} be accessed through //! this mapping. These fields are currently: //! @string //! @value "content-type" //! @value "content-disposition" //! @value "content-length" //! @value "content-transfer-encoding" //! @endstring //! The contents of these fields can be accessed and/or modified through //! a set of variables and methods available for this purpose. //! //! @seealso //! @[type], @[subtype], @[charset], @[boundary], @[transfer_encoding], //! @[params], @[disposition], @[disp_params], @[setencoding()], //! @[setparam()], @[setdisp_param()], @[setcharset()], @[setboundary()] //! mapping(string:string) headers; //! If the message is of type @tt{multipart@}, this is an array //! containing one Message object for each part of the message. //! If the message is not a multipart, this field is @expr{0@} (zero). //! //! @seealso //! @[type], @[boundary] //! array(object) body_parts; //! For multipart messages, this @tt{Content-Type@} parameter gives a //! delimiter string for separating the individual messages. As multiparts //! are handled internally by the module, you should not need to access this //! field. //! //! @seealso //! @[setboundary()] //! string boundary; //! One of the possible parameters of the @tt{Content-Type@} header is the //! charset attribute. It determines the character encoding used in bodies of //! type @tt{text@}. //! //! If there is no @tt{Content-Type@} header, the value of this field //! is @expr{"us-ascii"@}. //! //! @seealso //! @[type] //! string charset; //! The @tt{Content-Type@} header contains a type, a subtype, and optionally //! some parameters. This field contains the type attribute extracted //! from the header. //! //! If there is no @tt{Content-Type@} header, the value of this field //! is @expr{"text"@}. //! //! @seealso //! @[subtype], @[params] //! string type; //! The @tt{Content-Type@} header contains a type, a subtype, and optionally //! some parameters. This field contains the subtype attribute extracted //! from the header. //! //! If there is no @tt{Content-Type@} header, the value of this field //! is @expr{"plain"@}. //! //! @seealso //! @[type], @[params] //! string subtype; //! The contents of the @tt{Content-Transfer-Encoding@} header. //! //! If no @tt{Content-Transfer-Encoding@} header is given, this field //! is @expr{0@} (zero). //! //! Transfer encoding and decoding is done transparently by the module, //! so this field should be interesting only to applications wishing to //! do auto conversion of certain transfer encodings. //! //! @seealso //! @[setencoding()] //! string transfer_encoding; //! A mapping containing all the additional parameters to the //! @tt{Content-Type@} header. //! //! Some of these parameters have fields of their own, which should //! be accessed instead of this mapping wherever applicable. //! //! @seealso //! @[charset], @[boundary], @[setparam()] //! mapping (string:string) params; //! The first part of the @tt{Content-Disposition@} header, hinting on how //! this part of a multipart message should be presented in an interactive //! application. //! //! If there is no @tt{Content-Disposition@} header, this field //! is @expr{0@}. //! string disposition; //! A mapping containing all the additional parameters to the //! @tt{Content-Disposition@} header. //! //! @seealso //! @[setdisp_param()], @[get_filename()] //! mapping (string:string) disp_params; //! This method tries to find a suitable filename should you want to save the //! body data to disk. //! //! It will examine the @tt{filename@} attribute of the //! @tt{Content-Disposition@} header, and failing that the @tt{name@} //! attribute of the @tt{Content-Type@} header. If neither attribute is set, //! the method returns 0. //! //! @note //! An interactive application should always query the user for the actual //! filename to use. This method may provide a reasonable default though. //! string get_filename( ) { string fn = disp_params["filename"] || params["name"]; return fn && decode_words_text_remapped(fn); } //! If this message is a part of a fragmented message (i.e. has a //! Content-Type of @tt{message/partial@}), an array with three elements //! is returned. //! //! The first element is an identifier string. This string should be used to //! group this message with the other fragments of the message (which will //! have the same id string). //! //! The second element is the sequence number of this fragment. The first //! part will have number 1, the next number 2 etc. //! //! The third element of the array is either the total number of fragments //! that the original message has been split into, or 0 of this information //! is not available. //! //! If this method is called in a message that is not a part of a fragmented //! message, it will return 0. //! //! @seealso //! @[MIME.reconstruct_partial()] //! array(string|int) is_partial( ) { return (type == "message" && subtype == "partial") && ({ params["id"], (int)params["number"], (int)(params["total"]||"0") }); } //! Replaces the body entity of the data with a new piece of raw data. //! //! The new data should comply to the format indicated by the //! @[type] and @[subtype] attributes. //! //! @note //! Do not use this method unless you know what you are doing. //! //! @seealso //! @[getdata()], @[setencoded], @[data] //! void setdata( string data ) { if (data != decoded_data) { decoded_data = data; encoded_data = 0; } } //! @decl string data //! //! This variable contains the raw data of the message body entity. //! //! The @[type] and @[subtype] attributes indicate how this data should //! be interpreted. //! //! @note //! In Pike 7.6 and earlier you had to use @[getdata()] and //! @[setdata()] to access this value. //! //! @seealso //! @[getdata()], @[setdata()] void `->data=(string data) { setdata(data); } //! This method returns the raw data of the message body entity. //! //! The @[type] and @[subtype] attributes indicate how this data should //! be interpreted. //! //! @seealso //! @[setdata()], @[getencoded()], @[data] //! string getdata( ) { if (encoded_data && !decoded_data) decoded_data = decode( encoded_data, transfer_encoding ); return decoded_data = (string)decoded_data; } string `->data() { return getdata(); } //! This method returns the data of the message body entity, encoded //! using the current transfer encoding. //! //! You should never have to call this function. //! //! @seealso //! @[getdata()] //! string getencoded( ) { if (decoded_data && !encoded_data) encoded_data = encode( (string)decoded_data, transfer_encoding, get_filename() ); return (string)encoded_data; } //! Select a new transfer encoding for this message. //! //! The @tt{Content-Transfer-Encoding@} header will be modified accordingly, //! and subsequent calls to @[getencoded] will produce data encoded using //! the new encoding. //! //! See @[MIME.encode()] for a list of valid encodings. //! //! @seealso //! @[getencoded()], @[MIME.encode()] //! void setencoding( string encoding ) { if(encoded_data && !decoded_data) decoded_data = getdata( ); headers["content-transfer-encoding"] = transfer_encoding = lower_case( encoding ); encoded_data = 0; } //! Set or modify the named parameter of the @tt{Content-Type@} header. //! //! Common parameters include @tt{charset@} for text messages, and //! @tt{boundary@} for multipart messages. //! //! @note //! It is not allowed to modify the @tt{Content-Type@} header directly, //! please use this function instead. //! //! @seealso //! @[setcharset()], @[setboundary()], @[setdisp_param()] //! void setparam( string param, string value ) { param = lower_case(param); params[param] = value; switch(param) { case "charset": charset = value; break; case "boundary": boundary = value; break; case "name": if(transfer_encoding != "x-uue" && transfer_encoding != "x-uuencode") break; if(encoded_data && !decoded_data) decoded_data = getdata( ); encoded_data = 0; break; } headers["content-type"] = quote(({ type, '/', subtype })+ `+(@map(indices(params), lambda(string param) { return ({ ';', param, '=', params[param] }); }))); } //! Set or modify the named parameter of the @tt{Content-Disposition@} //! header. //! //! A common parameters is e.g. @tt{filename@}. //! //! @note //! It is not allowed to modify the @tt{Content-Disposition@} header //! directly, please use this function instead. //! //! @seealso //! @[setparam()], @[get_filename()] //! void setdisp_param( string param, string value ) { param = lower_case( param ); disp_params[param] = value; switch (param) { case "filename": if (transfer_encoding != "x-uue" && transfer_encoding != "x-uuencode") break; if (encoded_data && !decoded_data) decoded_data = getdata( ); encoded_data = 0; break; } headers["content-disposition"] = quote(({ disposition || "attachment" })+ `+(@map(indices(disp_params), lambda(string param) { return ({ ';', param, '=', disp_params[param] }); }))); } //! Sets the @tt{charset@} parameter of the @tt{Content-Type@} header. //! //! This is equivalent of calling @expr{setparam("charset", @[charset])@}. //! //! @seealso //! @[setparam()] //! void setcharset( string charset ) { setparam( "charset", charset ); } //! Sets the @tt{boundary@} parameter of the @tt{Content-Type@} header. //! //! This is equivalent of calling @expr{setparam("boundary", @[boundary])@}. //! //! @seealso //! @[setparam()] //! void setboundary( string boundary ) { setparam( "boundary", boundary ); } //! Casting the message object to a string will yield a byte stream suitable //! for transmitting the message over protocols such as ESMTP and NNTP. //! //! The body will be encoded using the current transfer encoding, and //! subparts of a multipart will be collected recursively. If the message //! is a multipart and no boundary string has been set, one will be //! generated using @[generate_boundary()]. //! //! @seealso //! @[create()] protected string cast( string dest_type ) { string data; object body_part; if (dest_type != "string") return UNDEFINED; data = getencoded( ); if (body_parts) { if (!boundary) { if (type != "multipart") { type = "multipart"; subtype = "mixed"; } setboundary( generate_boundary( ) ); } data += "\r\n"; foreach( body_parts, body_part ) data += "--"+boundary+"\r\n"+((string)body_part)+"\r\n"; data += "--"+boundary+"--\r\n"; } headers["content-length"] = ""+sizeof(data); return map( indices(headers), lambda(string hname){ return map(arrayp(headers[hname]) ? headers[hname] : headers[hname]/"\0", lambda(string header,string hname) { return hname+": "+header; }, replace(map(hname/"-", String.capitalize)*"-", "Mime","MIME"))*"\r\n"; } )*"\r\n" + "\r\n\r\n" + data; } protected string token_to_string(string|int token) { return intp(token) ? sprintf("%c", token) : token; } //! Parse a Content-Type or Content-Disposition parameter. //! //! @param params //! Mapping to add parameters to. //! //! @param entry //! Array of tokens containing a parameter declaration. //! //! @param header //! Name of the header from which @[entry] originated. //! This is only used to report errors. //! //! @param guess //! Make a best-effort attempt to parse broken entries. //! //! @param entry2 //! Same as @[entry], but tokenized with @[MIME.TOKENIZE_KEEP_ESCAPES]. //! //! @seealso //! @[create()] protected void parse_param(mapping(string:string) params, array(string|int) entry, string header, int|void guess, array(string|int)|void entry2) { if(sizeof(entry)) { if(sizeof(entry)<3 || entry[1]!='=' || !stringp(entry[0])) if(guess) { if ((sizeof(entry) == 1) && stringp(entry[0])) { if (sizeof(entry = (entry[0]/"-")) > 1) { // Assume there's a typo where the '=' has been replaced // with a '-'. entry = ({ entry[0], '=', entry[1..]*"-" }); } // Just use the entry as a param with "" as the value. } else return; // just ignore the broken data we failed to parse } else error("invalid parameter %O in %s %O (%O)\n", entry[0], header, headers[lower_case(header)], guess); string param = lower_case(entry[0]); string val; if (guess) { val = map(entry[2..], token_to_string) * ""; } else if (sizeof(filter(entry[2..], intp))) { error("invalid quoting of parameter %O in %s %O (%O)\n", entry[0], header, headers[lower_case(header)], guess); } else { val = entry[2..]*""; } params[param] = val; // Check for MSIE: // // MSIE insists on sending the full local path to the file as // the "filename" parameter, but forgets to quote the backslashes. // // Heuristic: // * If there are forward slashes, or properly quoted backslashes, // everything's alright. // * Note that UNC-paths (\\host\dir\file) look like they have // a properly quoted backslash as the first character, so // we disregard the first character. if ((param == "filename") && guess && entry2 && !has_value(val, "/") && !has_value(val[1..], "\\") && (sizeof(entry2) >= 3) && (entry2[1] == '=') && (lower_case(entry2[0]) == param)) { val = map(entry2[2..], token_to_string) * ""; if (has_value(val, "\\")) params[param] = val; } } } //! @decl void create() //! @decl void create(string message) //! @decl void create(string message, @ //! mapping(string:string|array(string)) headers, @ //! array(object)|void parts) //! @decl void create(string message, @ //! mapping(string:string|array(string)) headers, @ //! array(object)|void parts, int(0..1) guess) //! //! There are several ways to call the constructor of the Message class: //! //! @ul //! @item //! With zero arguments, you will get a dummy message with neither //! headers nor body. Not very useful. //! @item //! With one argument, the argument is taken to be a byte stream //! containing a message in encoded form. The constructor will analyze //! the string and extract headers and body. //! @item //! With two or three arguments, the first argument is taken to be the //! raw body data, and the second argument a desired set of headers. //! The keys of this mapping are not case-sensitive. If the given //! headers indicate that the message should be of type multipart, //! an array of Message objects constituting the subparts should be //! given as a third argument. //! @item //! With the @[guess] argument set to 1 (@[headers] and @[parts] may be 0 //! if you don't want to give any), you get a more forgiving MIME Message //! that will do its best to guess what broken input data really meant. It //! won't always guess right, but for applications like mail archives and //! similar where you can't get away with throwing an error at the user, //! this comes in handy. Only use the @[guess] mode only for situations //! where you @i{need@} to process broken MIME messages silently; the //! abuse of overly lax tools is what poisons standards. //! @endul //! //! @seealso //! @[cast()] void create(void | string|StringRange message, void | mapping(string:string|array(string)) hdrs, void | array(object) parts, void | int guess) { encoded_data = 0; decoded_data = 0; headers = ([ ]); params = ([ ]); disp_params = ([ ]); body_parts = 0; type = "text"; subtype = "plain"; charset = "us-ascii"; boundary = 0; disposition = 0; if (message && stringp(message) && (sizeof(message) > 0x100000)) { // Message is larger than 1 MB. // Attempt to reduce memory use by using StringRange. message = StringRange(message, 0, sizeof(message)); } if (hdrs || parts) { string|array(string) hname; decoded_data = message; if (hdrs) foreach( indices(hdrs), hname ) headers[lower_case(hname)] = hdrs[hname]; body_parts = parts; } else if (message) [ headers, encoded_data ] = parse_headers(message); if (headers["content-type"]) { array(array(string|int)) arr = tokenize(headers["content-type"]) / ({';'}); array(string|int) p; if (guess && sizeof(arr[0]) > 3) { // Workspace Webmail 5.6.17 is known to be able to // send attachments with the content-type header // "application/msword application; name=\"Foo.doc\";" // Strip the extraneous tokens. arr[0] = arr[0][..2]; } if(sizeof(arr[0])!=3 || arr[0][1]!='/' || !stringp(arr[0][0]) || !stringp(arr[0][2])) if(sizeof(arr[0])==1 && stringp(arr[0][0]) && (subtype = guess_subtype(lower_case(type = arr[0][0])))) arr = ({ ({ type, '/', subtype }) }) + arr[1..]; else if(!guess) error("invalid Content-Type %O\n", headers["content-type"]); else arr = ({ ({ "application", '/', "octet-stream" }) }) + arr[1..]; type = lower_case(arr[0][0]); subtype = lower_case(arr[0][2]); foreach( arr[1..], p ) parse_param(params, p, "Content-Type", guess); charset = lower_case(params["charset"] || charset); boundary = params["boundary"]; } if (headers["content-disposition"]) { array(array(string|int)) arr; array(array(string|int)) arr2; mixed err = catch { arr = tokenize(headers["content-disposition"]) / ({';'}); }; mixed err2 = catch { arr2 = tokenize(headers["content-disposition"], MIME.TOKENIZE_KEEP_ESCAPES) / ({';'}); }; if (err) { if (!guess || err2) throw(err); // Known broken, probably MSIE. arr = arr2; arr2 = 0; } array(string|int) p; if(sizeof(arr[0])!=1 || !stringp(arr[0][0])) { if(!guess) error("invalid Content-Disposition in message\n"); } else { disposition = lower_case(arr[0][0]); foreach( arr[1..]; int i; p ) parse_param(disp_params, p, "Content-Disposition", guess, arr2 && ((i+1) < sizeof(arr2)) && arr2[i+1]); } } if (headers["content-transfer-encoding"]) { array(string) arr=tokenize(headers["content-transfer-encoding"]); if(sizeof(arr)!=1 || !stringp(arr[0])) { if(!guess) error("invalid Content-Transfer-Encoding %O\n", headers["content-transfer-encoding"]); } else transfer_encoding = lower_case(arr[0]); } if (boundary && type=="multipart" && !body_parts && (encoded_data || decoded_data)) { string|StringRange data = decoded_data || getdata(); string separator = "--" + boundary; array(string) parts = ({}); int start = 0; int found = 0; encoded_data = 0; decoded_data = 0; while ((found = search(data, separator, found)) != -1) { if (found) { if (data[found-1] != '\n') { found += sizeof(separator); continue; } string part; // Strip the terminating LF or CRLF. if ((found > 1) && (data[found - 2] == '\r')) { part = data[start..found-3]; } else { part = data[start..found-2]; } if (start) { parts += ({ part }); } else { decoded_data = part; } } else { decoded_data = ""; } // Skip past the separator and any white space after it. found += sizeof(separator); string terminator = data[found..found+1]; if (terminator == "--") { found += 2; } else { terminator = 0; } while ((found < sizeof(data)) && ((data[found] == ' ') || (data[found] == '\t'))) { found++; } if ((found < sizeof(data)) && (data[found] == '\n')) { found++; } else if ((found < sizeof(data)) && (data[found..found+1] == "\r\n")) { found += 2; } else if (!guess && !terminator) { error("newline missing after multipart boundary\n"); } start = found; if (terminator) break; } string epilogue = data[start..]; if (!decoded_data) { if (guess) { decoded_data = epilogue; epilogue = ""; } else error("boundary missing from multipart-body\n"); } if ((epilogue != "") && !guess) { error("multipart message improperly terminated (%O%s)\n", epilogue[..200], sizeof(epilogue) > 201 ? "[...]" : ""); } body_parts = map(parts, this_program, 0, 0, guess); } if((hdrs || parts) && !decoded_data) { decoded_data = (parts? "This is a multi-part message in MIME format.\r\n": ""); } } protected string _sprintf(int c) { if (c == 'O') return sprintf("Message(%O)", disp_params); return (string)this; } } //! This function will attempt to reassemble a fragmented message from its //! parts. //! //! The array @[collection] should contain @[MIME.Message] objects forming //! a complete set of parts for a single fragmented message. //! The order of the messages in the array is not important, but every part //! must exist at least once. //! //! Should the function succeed in reconstructing the original message, a //! new @[MIME.Message] object will be returned. //! //! If the function fails to reconstruct an original message, an integer //! indicating the reason for the failure will be returned: //! @int //! @value 0 //! Returned if empty @[collection] is passed in, or one that contains //! messages which are not of type @tt{message/partial@}, or parts of //! different fragmented messages. //! @value 1.. //! If more fragments are needed to reconstruct the entire message, the //! number of additional messages needed is returned. //! @value -1 //! If more fragments are needed, but the function can't determine //! exactly how many. //! @endint //! //! @note //! Note that the returned message may in turn be a part of another, //! larger, fragmented message. //! //! @seealso //! @[MIME.Message->is_partial()] //! int|object reconstruct_partial(array(object) collection) { int got = 0, maxgot = 0, top = sizeof(collection), total = 0; mapping(int:object) parts = ([ ]); string id; if(!top) return 0; if(!(id = (collection[0]->is_partial()||({0}))[0])) return 0; foreach(collection, object m) { array(int|string) p = m->is_partial(); if(!(p && p[0] == id)) return 0; if((!total || p[1]==p[2]) && p[2]) total = p[2]; if(p[1]>maxgot) maxgot = p[1]; if(p[1]>0 && !parts[p[1]]) { parts[p[1]] = m; got++; } } if(!total) return -1; if(got == total && maxgot == total) { mapping(string:string) enclosing_headers = parts[1]->headers; object reconstructed = Message(`+(@Array.map(sort(indices(parts)), lambda(int i, mapping(int:object) parts){ return parts[i]->getencoded(); }, parts))); foreach(indices(reconstructed->headers), string h) { if(h != "message-id" && h != "encrypted" && h != "mime-version" && h != "subject" && (sizeof(h)<8 || h[0..7] != "content-")) m_delete(reconstructed->headers, h); } foreach(indices(enclosing_headers), string h) { if(h != "message-id" && h != "encrypted" && h != "mime-version" && h != "subject" && (sizeof(h)<8 || h[0..7] != "content-")) reconstructed->headers[h] = enclosing_headers[h]; } return reconstructed; } else return (maxgot>total? -1 : total-got); } //! Encode strings according to @rfc{4648@} base64url encoding. string encode_base64url(string x) { x = replace(encode_base64(x,1),({ "+", "/" }),({ "-", "_" })); while( sizeof(x) && x[-1]=='=' ) x=x[..<1]; return x; } //! Decode strings according to @rfc{4648@} base64url encoding. string decode_base64url(string x) { return decode_base64(replace(x,({ "-", "_" }),({ "+", "/" }))); }

pike.git/ lib/ modules/ MIME.pmod/ module.pmod > 374c1d0d8ffe73d6793995985e741428c310f99a [Annotate]